docs/CHANGELOG.md: cut v1.63.0

See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1447

.github/ISSUE_TEMPLATE/bug_report.md

@@ -4,21 +4,37 @@ about: Create a report to help us improve
 title: ''
 labels: ''
 assignees: ''
-
 ---
 
 **Describe the bug**
 A clear and concise description of what the bug is.
+It would be a great [upgrading](https://docs.victoriametrics.com/#how-to-upgrade) 
+to [the latest available release](https://github.com/VictoriaMetrics/VictoriaMetrics/releases)
+and verifying whether the bug is reproducible there.
+It is also recommended reading [troubleshooting docs](https://docs.victoriametrics.com/#troubleshooting).
 
 **To Reproduce**
-Steps to reproduce the behavior
+Steps to reproduce the behavior.
 
 **Expected behavior**
 A clear and concise description of what you expected to happen.
 
+**Logs**
+Check if any warnings or errors were logged by VictoriaMetrics components
+or components in communication with VictoriaMetrics (e.g. Prometheus, Grafana).
+
 **Screenshots**
 If applicable, add screenshots to help explain your problem.
 
+For VictoriaMetrics health-state issues please provide full-length screenshots 
+of Grafana dashboards if possible:
+* [Grafana dashboard for single-node VictoriaMetrics](https://grafana.com/dashboards/10229)
+* [Grafana dashboard for VictoriaMetrics cluster](https://grafana.com/grafana/dashboards/11176)
+
+See how to setup monitoring here:
+* [monitoring for single-node VictoriaMetrics](https://docs.victoriametrics.com/#monitoring)
+* [montioring for VictoriaMetrics cluster](https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html#monitoring)
+
 **Version**
 The line returned when passing `--version` command line flag to binary. For example:
 ```
@@ -27,15 +43,5 @@ victoria-metrics-20190730-121249-heads-single-node-0-g671d9e55
 ```
 
 **Used command-line flags**
-Command-line flags are listed as `flag{name="httpListenAddr", value=":443"} 1` lines at `/metrics` page.
-See the following docs for details:
+Please provide applied command-line flags used for running VictoriaMetrics and its components. 
 
-* [monitoring for single-node VictoriaMetrics](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/README.md#monitoring)
-* [montioring for VictoriaMetrics cluster](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/cluster/README.md#monitoring)
-
-**Additional context**
-Add any other context about the problem here such as error logs from VictoriaMetrics and Prometheus,
-`/metrics` output, screenshots from the official Grafana dashboards for VictoriaMetrics:
-
-* [Grafana dashboard for single-node VictoriaMetrics](https://grafana.com/dashboards/10229)
-* [Grafana dashboard for VictoriaMetrics cluster](https://grafana.com/grafana/dashboards/11176)

.github/dependabot.yml

@@ -0,0 +1,6 @@
+version: 2
+updates:
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "daily"

.github/workflows/check-licenses.yml

@@ -0,0 +1,23 @@
+name: license-check
+on:
+  push:
+    paths:
+      - 'vendor'
+  pull_request:
+    paths:
+      - 'vendor'
+jobs:
+  build:
+    name: Build
+    runs-on: ubuntu-latest
+    steps:
+      - name: Setup Go
+        uses: actions/setup-go@main
+        with:
+          go-version: 1.16
+        id: go
+      - name: Code checkout
+        uses: actions/checkout@master
+      - name: Check License
+        run: |
+          make check-licenses

.github/workflows/github-pages.yml

@@ -1,30 +0,0 @@
-name: github-pages
-on:
-  push:
-    paths:
-      - 'docs/*'
-      - 'README.md'
-    branches:
-      - master
-jobs:
-  build:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@master
-      - name: publish
-        shell: bash
-        env:
-          TOKEN: ${{secrets.CI_TOKEN}}
-        run: |
-          git clone https://vika:${TOKEN}@github.com/VictoriaMetrics/VictoriaMetrics.github.io.git gpages
-          cp docs/* gpages
-          cp README.md gpages
-          cd gpages
-          git config --local user.email "info@victoriametrics.com"
-          git config --local user.name "Vika"
-          git add .
-          git commit -m "update github pages"
-          remote_repo="https://vika:${TOKEN}@github.com/VictoriaMetrics/VictoriaMetrics.github.io.git"
-          git push "${remote_repo}"
-          cd ..
-          rm -rf gpages

.github/workflows/main.yml

@@ -16,15 +16,13 @@ jobs:
       - name: Setup Go
         uses: actions/setup-go@main
         with:
-          go-version: 1.15
+          go-version: 1.16
         id: go
       - name: Dependencies
-        env:
-          GO111MODULE: on
         run: |
           go get -u golang.org/x/lint/golint
           go get -u github.com/kisielk/errcheck
-          curl -sSfL https://raw.githubusercontent.com/golangci/golangci-lint/master/install.sh | sh -s -- -b $(go env GOPATH)/bin v1.27.0
+          curl -sSfL https://raw.githubusercontent.com/golangci/golangci-lint/master/install.sh | sh -s -- -b $(go env GOPATH)/bin v1.29.0
       - name: Code checkout
         uses: actions/checkout@master
       - name: Build
@@ -47,19 +45,22 @@ jobs:
           GOOS=freebsd go build -mod=vendor ./app/vmalert
           GOOS=freebsd go build -mod=vendor ./app/vmbackup
           GOOS=freebsd go build -mod=vendor ./app/vmrestore
+          GOOS=freebsd go build -mod=vendor ./app/vmctl
           GOOS=openbsd go build -mod=vendor ./app/victoria-metrics
           GOOS=openbsd go build -mod=vendor ./app/vmagent
           GOOS=openbsd go build -mod=vendor ./app/vmalert
           GOOS=openbsd go build -mod=vendor ./app/vmbackup
           GOOS=openbsd go build -mod=vendor ./app/vmrestore
+          GOOS=openbsd go build -mod=vendor ./app/vmctl
           GOOS=darwin go build -mod=vendor ./app/victoria-metrics
           GOOS=darwin go build -mod=vendor ./app/vmagent
           GOOS=darwin go build -mod=vendor ./app/vmalert
           GOOS=darwin go build -mod=vendor ./app/vmbackup
           GOOS=darwin go build -mod=vendor ./app/vmrestore
+          GOOS=darwin go build -mod=vendor ./app/vmctl
+          CGO_ENABLED=0 GOOS=windows go build -mod=vendor ./app/vmagent
       - name: Publish coverage
-        uses: codecov/codecov-action@v1.0.6
+        uses: codecov/codecov-action@v1.5.2
         with:
-          token: ${{secrets.CODECOV_TOKEN}}
           file: ./coverage.txt
 

.github/workflows/wiki.yml

@@ -16,7 +16,7 @@ jobs:
           TOKEN: ${{secrets.CI_TOKEN}}
         run: |
           git clone https://vika:${TOKEN}@github.com/VictoriaMetrics/VictoriaMetrics.wiki.git wiki
-          cp docs/* wiki
+          cp -r docs/* wiki
           cd wiki
           git config --local user.email "info@victoriametrics.com"
           git config --local user.name "Vika"

.gitignore

@@ -15,3 +15,4 @@
 /package/temp-rpm-*
 /package/*.deb
 /package/*.rpm
+.DS_store

.wwhrd.yml

@@ -0,0 +1,5 @@
+allowlist:
+  - Apache-2.0
+  - MIT
+  - BSD-3-Clause
+  - BSD-2-Clause

CODE_OF_CONDUCT.md

@@ -7,7 +7,7 @@ contributors and maintainers pledge to making participation in our project and
 our community a harassment-free experience for everyone, regardless of age, body
 size, disability, ethnicity, sex characteristics, gender identity and expression,
 level of experience, education, socio-economic status, nationality, personal
-appearance, race, religion, or sexual identity and orientation.
+appearance, race, religion or sexual identity and orientation.
 
 ## Our Standards
 
@@ -24,9 +24,9 @@ Examples of unacceptable behavior by participants include:
 
 * The use of sexualized language or imagery and unwelcome sexual attention or
  advances
-* Trolling, insulting/derogatory comments, and personal or political attacks
+* Trolling, insulting/derogatory comments and personal or political attacks
 * Public or private harassment
-* Publishing others' private information, such as a physical or electronic
+* Publishing others' private information, such as physical or electronic
  address, without explicit permission
 * Other conduct which could reasonably be considered inappropriate in a
  professional setting
@@ -38,26 +38,26 @@ behavior and are expected to take appropriate and fair corrective action in
 response to any instances of unacceptable behavior.
 
 Project maintainers have the right and responsibility to remove, edit, or
-reject comments, commits, code, wiki edits, issues, and other contributions
-that are not aligned to this Code of Conduct, or to ban temporarily or
+reject comments, commits, code, wiki edits, issues and other contributions
+that are not aligned to this Code of Conduct or to ban temporarily or
 permanently any contributor for other behaviors that they deem inappropriate,
-threatening, offensive, or harmful.
+threatening, offensive or harmful.
 
 ## Scope
 
 This Code of Conduct applies both within project spaces and in public spaces
 when an individual is representing the project or its community. Examples of
 representing a project or community include using an official project e-mail
-address, posting via an official social media account, or acting as an appointed
+address, posting via an official social media account or acting as an appointed
 representative at an online or offline event. Representation of a project may be
 further defined and clarified by project maintainers.
 
 ## Enforcement
 
-Instances of abusive, harassing, or otherwise unacceptable behavior may be
+Instances of abusive, harassing or otherwise unacceptable behavior may be
 reported by contacting the project team at info@victoriametrics.com. All
 complaints will be reviewed and investigated and will result in a response that
-is deemed necessary and appropriate to the circumstances. The project team is
+is deemed necessary and appropriate for the circumstances. The project team is
 obligated to maintain confidentiality with regard to the reporter of an incident.
 Further details of specific enforcement policies may be posted separately.
 

CODE_OF_CONDUCT_RU.md

@@ -0,0 +1,120 @@
+
+# Кодекс Поведения участника
+
+## Наши обязательства
+
+Мы, как участники, авторы и лидеры обязуемся сделать участие в сообществе
+свободным от притеснений для всех, независимо от возраста, телосложения,
+видимых или невидимых ограничений способности, этнической принадлежности,
+половых признаков, гендерной идентичности и выражения, уровня опыта,
+образования, социо-экономического статуса, национальности, внешности,
+расы, религии, или сексуальной идентичности и ориентации.
+
+Мы обещаем действовать и взаимодействовать таким образом, чтобы вносить вклад в открытое,
+дружелюбное, многообразное, инклюзивное и здоровое сообщество.
+
+## Наши стандарты
+
+Примеры поведения, создающие условия для благоприятных взаимоотношений включают в себя:
+
+* Проявление доброты и эмпатии к другим участникам проекта
+* Уважение к чужой точке зрения и опыту
+* Конструктивная критика и принятие конструктивной критики
+* Принятие ответственности, принесение извинений тем, кто пострадал от наших ошибок
+  и извлечение уроков из опыта
+* Ориентирование на то, что лучше подходит для сообщества, а не только для нас лично
+
+Примеры неприемлемого поведения участников включают в себя:
+
+* Использование выражений или изображений сексуального характера и нежелательное сексуальное внимание или домогательство в любой форме
+* Троллинг, оскорбительные или уничижительные комментарии, переход на личности или затрагивание политических убеждений
+* Публичное или приватное домогательство
+* Публикация личной информации других лиц, например, физического или электронного адреса, без явного разрешения
+* Иное поведение, которое обоснованно считать неуместным в профессиональной обстановке
+
+## Обязанности
+
+Лидеры сообщества отвечают за разъяснение и применение наших стандартов приемлемого
+поведения и будут предпринимать соответствующие и честные меры по исправлению положения
+в ответ на любое поведение, которое они сочтут неприемлемым, угрожающим, оскорбительным или вредным.
+
+Лидеры сообщества обладают правом и обязанностью удалять, редактировать или отклонять
+комментарии, коммиты, код, изменения в вики, вопросы и другой вклад, который не совпадает
+с Кодексом Поведения, и предоставят причины принятого решения, когда сочтут нужным.
+
+## Область применения
+
+Данный Кодекс Поведения применим во всех во всех публичных физических и цифровых пространства сообщества,
+а также когда человек официально представляет сообщество в публичных местах.
+Примеры представления проекта или сообщества включают использование официальной электронной почты,
+публикации в официальном аккаунте в социальных сетях,
+или упоминания как представителя в онлайн или оффлайн мероприятии.
+
+## Приведение в исполнение
+
+О случаях домогательства, а так же оскорбительного или иного другого неприемлемого
+поведения можно сообщить ответственным лидерам сообщества с помощью письма на info@victoriametrics.com
+Все жалобы будут рассмотрены и расследованы оперативно и беспристрастно.
+
+Все лидеры сообщества обязаны уважать неприкосновенность частной жизни и личную
+неприкосновенность автора сообщения.
+
+## Руководство по исполнению
+
+Лидеры сообщества будут следовать следующим Принципам Воздействия в Сообществе,
+чтобы определить последствия для тех, кого они считают виновными в нарушении данного Кодекса Поведения:
+
+### 1. Исправление
+
+**Общественное влияние**: Использование недопустимой лексики или другое поведение,
+считающиеся непрофессиональным или нежелательным в сообществе.
+
+**Последствия**: Личное, письменное предупреждение от лидеров сообщества,
+объясняющее суть нарушения и почему такое поведение
+было неуместно. Лидеры сообщества могут попросить принести публичное извинение.
+
+### 2. Предупреждение
+
+**Общественное влияние**: Нарушение в результате одного инцидента или серии действий.
+
+**Последствия**: Предупреждение о последствиях в случае продолжающегося неуместного поведения.
+На определенное время не допускается взаимодействие с людьми, вовлеченными в инцидент,
+включая незапрошенное взаимодействие 
+с теми, кто обеспечивает соблюдение Кодекса. Это включает в себя избегание взаимодействия
+в публичных пространствах, а так же во внешних каналах,
+таких как социальные сети. Нарушение этих правил влечет за собой временный или вечный бан.
+
+### 3. Временный бан
+
+**Общественное влияние**: Серьёзное нарушение стандартов сообщества,
+включая продолжительное неуместное поведение.
+
+**Последствия**: Временный запрет (бан) на любое взаимодействие 
+или публичное общение с сообществом на определенный период времени.
+На этот период не допускается публичное или личное взаимодействие с людьми,
+вовлеченными в инцидент, включая незапрошенное взаимодействие 
+с теми, кто обеспечивает соблюдение Кодекса.
+Нарушение этих правил влечет за собой вечный бан.
+
+### 4. Вечный бан
+
+**Общественное влияние**: Демонстрация систематических нарушений стандартов сообщества,
+включая продолжающееся неуместное поведение, домогательство до отдельных лиц,
+или проявление агрессии либо пренебрежительного отношения к категориям лиц.
+
+**Последствия**: Вечный запрет на любое публичное взаимодействие с сообществом.
+
+## Атрибуция
+
+Данный Кодекс Поведения основан на [Кодекс Поведения участника][homepage],
+версии 2.0, доступной по адресу
+https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.
+
+Принципы Воздействия в Сообществе были вдохновлены [Mozilla's code of conduct
+enforcement ladder](https://github.com/mozilla/diversity).
+
+[homepage]: https://www.contributor-covenant.org
+
+Ответы на общие вопросы о данном кодексе поведения ищите на странице FAQ:
+https://www.contributor-covenant.org/faq. Переводы доступны по адресу
+https://www.contributor-covenant.org/translations.

LICENSE

@@ -175,7 +175,7 @@
 
    END OF TERMS AND CONDITIONS
 
-   Copyright 2019-2020 VictoriaMetrics, Inc.
+   Copyright 2019-2021 VictoriaMetrics, Inc.
 
    Licensed under the Apache License, Version 2.0 (the "License");
    you may not use this file except in compliance with the License.

Makefile

@@ -1,5 +1,6 @@
 PKG_PREFIX := github.com/VictoriaMetrics/VictoriaMetrics
 
+DATEINFO_TAG ?= $(shell date -u +'%Y%m%d-%H%M%S')
 BUILDINFO_TAG ?= $(shell echo $$(git describe --long --all | tr '/' '-')$$( \
 	      git diff-index --quiet HEAD -- || echo '-dirty-'$$(git diff-index -u HEAD | openssl sha1 | cut -c 10-17)))
 
@@ -8,7 +9,9 @@ ifeq ($(PKG_TAG),)
 PKG_TAG := $(BUILDINFO_TAG)
 endif
 
-GO_BUILDINFO = -X '$(PKG_PREFIX)/lib/buildinfo.Version=$(APP_NAME)-$(shell date -u +'%Y%m%d-%H%M%S')-$(BUILDINFO_TAG)'
+GO_BUILDINFO = -X '$(PKG_PREFIX)/lib/buildinfo.Version=$(APP_NAME)-$(DATEINFO_TAG)-$(BUILDINFO_TAG)'
+
+.PHONY: $(MAKECMDGOALS)
 
 all: \
 	victoria-metrics-prod \
@@ -16,7 +19,8 @@ all: \
 	vmalert-prod \
 	vmauth-prod \
 	vmbackup-prod \
-	vmrestore-prod
+	vmrestore-prod \
+	vmctl-prod
 
 include app/*/Makefile
 include deployment/*/Makefile
@@ -30,7 +34,8 @@ publish: \
 	publish-vmalert \
 	publish-vmauth \
 	publish-vmbackup \
-	publish-vmrestore
+	publish-vmrestore \
+	publish-vmctl
 
 package: \
 	package-victoria-metrics \
@@ -38,31 +43,136 @@ package: \
 	package-vmalert \
 	package-vmauth \
 	package-vmbackup \
-	package-vmrestore
+	package-vmrestore \
+	package-vmctl
 
 vmutils: \
 	vmagent \
 	vmalert \
 	vmauth \
 	vmbackup \
-	vmrestore
+	vmrestore \
+	vmctl
+
+vmutils-pure: \
+	vmagent-pure \
+	vmalert-pure \
+	vmauth-pure \
+	vmbackup-pure \
+	vmrestore-pure \
+	vmctl-pure
+
+vmutils-arm64: \
+	vmagent-arm64 \
+	vmalert-arm64 \
+	vmauth-arm64 \
+	vmbackup-arm64 \
+	vmrestore-arm64 \
+	vmctl-arm64
+
+vmutils-arm: \
+	vmagent-arm \
+	vmalert-arm \
+	vmauth-arm \
+	vmbackup-arm \
+	vmrestore-arm \
+	vmctl-arm
+
+vmutils-windows-amd64: \
+	vmagent-windows-amd64 \
+	vmalert-windows-amd64 \
+	vmauth-windows-amd64 \
+	vmctl-windows-amd64
+
+release-snap:
+	snapcraft
+	snapcraft upload "victoriametrics_$(PKG_TAG)_multi.snap" --release beta,edge,candidate
 
 release: \
 	release-victoria-metrics \
 	release-vmutils
 
-release-victoria-metrics: victoria-metrics-prod
-	cd bin && tar czf victoria-metrics-$(PKG_TAG).tar.gz victoria-metrics-prod && \
-		sha256sum victoria-metrics-$(PKG_TAG).tar.gz > victoria-metrics-$(PKG_TAG)_checksums.txt
+release-victoria-metrics: \
+	release-victoria-metrics-amd64 \
+	release-victoria-metrics-arm \
+	release-victoria-metrics-arm64
+
+release-victoria-metrics-amd64:
+	GOARCH=amd64 $(MAKE) release-victoria-metrics-generic
+
+release-victoria-metrics-arm:
+	GOARCH=arm $(MAKE) release-victoria-metrics-generic
+
+release-victoria-metrics-arm64:
+	GOARCH=arm64 $(MAKE) release-victoria-metrics-generic
+
+release-victoria-metrics-generic: victoria-metrics-$(GOARCH)-prod
+	cd bin && \
+		tar --transform="flags=r;s|-$(GOARCH)||" -czf victoria-metrics-$(GOARCH)-$(PKG_TAG).tar.gz \
+			victoria-metrics-$(GOARCH)-prod \
+		&& sha256sum victoria-metrics-$(GOARCH)-$(PKG_TAG).tar.gz \
+			victoria-metrics-$(GOARCH)-prod \
+			| sed s/-$(GOARCH)-prod/-prod/ > victoria-metrics-$(GOARCH)-$(PKG_TAG)_checksums.txt
 
 release-vmutils: \
-	vmagent-prod \
-	vmalert-prod \
-	vmauth-prod \
-	vmbackup-prod \
-	vmrestore-prod
-	cd bin && tar czf vmutils-$(PKG_TAG).tar.gz vmagent-prod vmalert-prod vmauth-prod vmbackup-prod vmrestore-prod && \
-		sha256sum vmutils-$(PKG_TAG).tar.gz > vmutils-$(PKG_TAG)_checksums.txt
+	release-vmutils-amd64 \
+	release-vmutils-arm64 \
+	release-vmutils-arm \
+	release-vmutils-windows-amd64
+
+release-vmutils-amd64:
+	GOARCH=amd64 $(MAKE) release-vmutils-generic
+
+release-vmutils-arm64:
+	GOARCH=arm64 $(MAKE) release-vmutils-generic
+
+release-vmutils-arm:
+	GOARCH=arm $(MAKE) release-vmutils-generic
+
+release-vmutils-windows-amd64:
+	GOARCH=amd64 $(MAKE) release-vmutils-windows-generic
+
+release-vmutils-generic: \
+	vmagent-$(GOARCH)-prod \
+	vmalert-$(GOARCH)-prod \
+	vmauth-$(GOARCH)-prod \
+	vmbackup-$(GOARCH)-prod \
+	vmrestore-$(GOARCH)-prod \
+	vmctl-$(GOARCH)-prod
+	cd bin && \
+		tar --transform="flags=r;s|-$(GOARCH)||" -czf vmutils-$(GOARCH)-$(PKG_TAG).tar.gz \
+			vmagent-$(GOARCH)-prod \
+			vmalert-$(GOARCH)-prod \
+			vmauth-$(GOARCH)-prod \
+			vmbackup-$(GOARCH)-prod \
+			vmrestore-$(GOARCH)-prod \
+			vmctl-$(GOARCH)-prod \
+		&& sha256sum vmutils-$(GOARCH)-$(PKG_TAG).tar.gz \
+			vmagent-$(GOARCH)-prod \
+			vmalert-$(GOARCH)-prod \
+			vmauth-$(GOARCH)-prod \
+			vmbackup-$(GOARCH)-prod \
+			vmrestore-$(GOARCH)-prod \
+			vmctl-$(GOARCH)-prod \
+			| sed s/-$(GOARCH)-prod/-prod/ > vmutils-$(GOARCH)-$(PKG_TAG)_checksums.txt
+
+release-vmutils-windows-generic: \
+	vmagent-windows-$(GOARCH)-prod \
+	vmalert-windows-$(GOARCH)-prod \
+	vmauth-windows-$(GOARCH)-prod \
+	vmctl-windows-$(GOARCH)-prod
+	cd bin && \
+		zip vmutils-windows-$(GOARCH)-$(PKG_TAG).zip \
+			vmagent-windows-$(GOARCH)-prod.exe \
+			vmalert-windows-$(GOARCH)-prod.exe \
+			vmauth-windows-$(GOARCH)-prod.exe \
+			vmctl-windows-$(GOARCH)-prod.exe \
+		&& sha256sum vmutils-windows-$(GOARCH)-$(PKG_TAG).zip \
+			vmagent-windows-$(GOARCH)-prod.exe \
+			vmalert-windows-$(GOARCH)-prod.exe \
+			vmauth-windows-$(GOARCH)-prod.exe \
+			vmctl-windows-$(GOARCH)-prod.exe \
+			> vmutils-windows-$(GOARCH)-$(PKG_TAG)_checksums.txt
 
 pprof-cpu:
 	go tool pprof -trim_path=github.com/VictoriaMetrics/VictoriaMetrics@ $(PPROF_FILE)
@@ -80,7 +190,7 @@ lint: install-golint
 	golint app/...
 
 install-golint:
-	which golint || GO111MODULE=off go get -u golang.org/x/lint/golint
+	which golint || GO111MODULE=off go get golang.org/x/lint/golint
 
 errcheck: install-errcheck
 	errcheck -exclude=errcheck_excludes.txt ./lib/...
@@ -92,9 +202,10 @@ errcheck: install-errcheck
 	errcheck -exclude=errcheck_excludes.txt ./app/vmauth/...
 	errcheck -exclude=errcheck_excludes.txt ./app/vmbackup/...
 	errcheck -exclude=errcheck_excludes.txt ./app/vmrestore/...
+	errcheck -exclude=errcheck_excludes.txt ./app/vmctl/...
 
 install-errcheck:
-	which errcheck || GO111MODULE=off go get -u github.com/kisielk/errcheck
+	which errcheck || GO111MODULE=off go get github.com/kisielk/errcheck
 
 check-all: fmt vet lint errcheck golangci-lint
 
@@ -136,23 +247,43 @@ app-local-pure:
 app-local-with-goarch:
 	GO111MODULE=on go build $(RACE) -mod=vendor -ldflags "$(GO_BUILDINFO)" -o bin/$(APP_NAME)-$(GOARCH)$(RACE) $(PKG_PREFIX)/app/$(APP_NAME)
 
+app-local-windows-with-goarch:
+	CGO_ENABLED=0 GO111MODULE=on go build $(RACE) -mod=vendor -ldflags "$(GO_BUILDINFO)" -o bin/$(APP_NAME)-windows-$(GOARCH)$(RACE).exe $(PKG_PREFIX)/app/$(APP_NAME)
+
 quicktemplate-gen: install-qtc
 	qtc
 
 install-qtc:
-	which qtc || GO111MODULE=off go get -u github.com/valyala/quicktemplate/qtc
+	which qtc || GO111MODULE=off go get github.com/valyala/quicktemplate/qtc
 
 
 golangci-lint: install-golangci-lint
 	golangci-lint run --exclude '(SA4003|SA1019|SA5011):' -D errcheck -D structcheck --timeout 2m
 
 install-golangci-lint:
-	which golangci-lint || GO111MODULE=off go get -u github.com/golangci/golangci-lint/cmd/golangci-lint
+	which golangci-lint || curl -sSfL https://raw.githubusercontent.com/golangci/golangci-lint/master/install.sh | sh -s -- -b $(shell go env GOPATH)/bin v1.40.1
 
+install-wwhrd:
+	which wwhrd || GO111MODULE=off go get github.com/frapposelli/wwhrd
+
+check-licenses: install-wwhrd
+	wwhrd check -f .wwhrd.yml
+
+copy-docs:
+	echo "---\nsort: ${ORDER}\n---\n" > ${DST}
+	cat ${SRC} >> ${DST}
+
+# Copies docs for all components and adds the order tag.
+# Cluster docs are supposed to be ordered as 9th.
+# For The rest of docs is ordered manually.t
 docs-sync:
-	cp app/vmagent/README.md docs/vmagent.md
-	cp app/vmalert/README.md docs/vmalert.md
-	cp app/vmauth/README.md docs/vmauth.md
-	cp app/vmbackup/README.md docs/vmbackup.md
-	cp app/vmrestore/README.md docs/vmrestore.md
-	cp README.md docs/Single-server-VictoriaMetrics.md
+	cp README.md docs/README.md
+	SRC=README.md DST=docs/Single-server-VictoriaMetrics.md ORDER=1 $(MAKE) copy-docs
+	SRC=app/vmagent/README.md DST=docs/vmagent.md ORDER=3 $(MAKE) copy-docs
+	SRC=app/vmalert/README.md DST=docs/vmalert.md ORDER=4 $(MAKE) copy-docs
+	SRC=app/vmauth/README.md DST=docs/vmauth.md ORDER=5 $(MAKE) copy-docs
+	SRC=app/vmbackup/README.md DST=docs/vmbackup.md ORDER=6 $(MAKE) copy-docs
+	SRC=app/vmrestore/README.md DST=docs/vmrestore.md ORDER=7 $(MAKE) copy-docs
+	SRC=app/vmctl/README.md DST=docs/vmctl.md ORDER=8 $(MAKE) copy-docs
+	SRC=app/vmgateway/README.md DST=docs/vmgateway.md ORDER=9 $(MAKE) copy-docs
+	SRC=app/vmbackupmanager/README.md DST=docs/vmbackupmanager.md ORDER=10 $(MAKE) copy-docs

app/victoria-metrics/Makefile

@@ -108,3 +108,10 @@ victoria-metrics-package-deb-rpm-all: \
         victoria-metrics-package-deb-arm64 \
         victoria-metrics-package-rpm \
         victoria-metrics-package-rpm-arm64
+
+### Packaging as snap
+victoria-metrics-package-snap:
+	which snapcraft || snap install snapcraft
+	which multipass || snap install multipass
+	snapcraft
+

app/victoria-metrics/main.go

@@ -9,35 +9,50 @@ import (
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vminsert"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmselect"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmselect/promql"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmstorage"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/buildinfo"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/cgroup"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/envflag"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/fs"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/procutil"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promscrape"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/storage"
 )
 
 var (
 	httpListenAddr    = flag.String("httpListenAddr", ":8428", "TCP address to listen for http connections")
-	minScrapeInterval = flag.Duration("dedup.minScrapeInterval", 0, "Remove superflouos samples from time series if they are located closer to each other than this duration. "+
-		"This may be useful for reducing overhead when multiple identically configured Prometheus instances write data to the same VictoriaMetrics. "+
-		"Deduplication is disabled if the -dedup.minScrapeInterval is 0")
+	minScrapeInterval = flag.Duration("dedup.minScrapeInterval", 0, "Leave only the first sample in every time series per each discrete interval "+
+		"equal to -dedup.minScrapeInterval > 0. See https://docs.victoriametrics.com/#deduplication for details")
+	dryRun = flag.Bool("dryRun", false, "Whether to check only -promscrape.config and then exit. "+
+		"Unknown config entries are allowed in -promscrape.config by default. This can be changed with -promscrape.config.strictParse")
 )
 
 func main() {
 	// Write flags and help message to stdout, since it is easier to grep or pipe.
 	flag.CommandLine.SetOutput(os.Stdout)
+	flag.Usage = usage
 	envflag.Parse()
 	buildinfo.Init()
 	logger.Init()
-	cgroup.UpdateGOMAXPROCSToCPUQuota()
+
+	if promscrape.IsDryRun() {
+		*dryRun = true
+	}
+	if *dryRun {
+		if err := promscrape.CheckConfig(); err != nil {
+			logger.Fatalf("error when checking -promscrape.config: %s", err)
+		}
+		logger.Infof("-promscrape.config is ok; exitting with 0 status code")
+		return
+	}
+
 	logger.Infof("starting VictoriaMetrics at %q...", *httpListenAddr)
 	startTime := time.Now()
 	storage.SetMinScrapeIntervalForDeduplication(*minScrapeInterval)
-	vmstorage.Init()
+	vmstorage.Init(promql.ResetRollupResultCacheIfNeeded)
 	vmselect.Init()
 	vminsert.Init()
 	startSelfScraper()
@@ -67,8 +82,22 @@ func main() {
 }
 
 func requestHandler(w http.ResponseWriter, r *http.Request) bool {
-	if r.RequestURI == "/" {
-		fmt.Fprintf(w, "Single-node VictoriaMetrics. See docs at https://victoriametrics.github.io/")
+	if r.URL.Path == "/" {
+		if r.Method != "GET" {
+			return false
+		}
+		fmt.Fprintf(w, "<h2>Single-node VictoriaMetrics</h2></br>")
+		fmt.Fprintf(w, "See docs at <a href='https://docs.victoriametrics.com/'>https://docs.victoriametrics.com/</a></br>")
+		fmt.Fprintf(w, "Useful endpoints:</br>")
+		httpserver.WriteAPIHelp(w, [][2]string{
+			{"/vmui", "Web UI"},
+			{"/targets", "discovered targets list"},
+			{"/api/v1/targets", "advanced information about discovered targets in JSON format"},
+			{"/metrics", "available service metrics"},
+			{"/api/v1/status/tsdb", "tsdb status page"},
+			{"/api/v1/status/top_queries", "top queries"},
+			{"/api/v1/status/active_queries", "active queries"},
+		})
 		return true
 	}
 	if vminsert.RequestHandler(w, r) {
@@ -82,3 +111,12 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 	}
 	return false
 }
+
+func usage() {
+	const s = `
+victoria-metrics is a time series database and monitoring solution.
+
+See the docs at https://docs.victoriametrics.com/
+`
+	flagutil.Usage(s)
+}

app/victoria-metrics/main_test.go

@@ -20,8 +20,8 @@ import (
 	testutil "github.com/VictoriaMetrics/VictoriaMetrics/app/victoria-metrics/test"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vminsert"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmselect"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmselect/promql"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmstorage"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/envflag"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/fs"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
@@ -57,6 +57,7 @@ var (
 type test struct {
 	Name             string     `json:"name"`
 	Data             []string   `json:"data"`
+	InsertQuery      string     `json:"insert_query"`
 	Query            []string   `json:"query"`
 	ResultMetrics    []Metric   `json:"result_metrics"`
 	ResultSeries     Series     `json:"result_series"`
@@ -129,7 +130,7 @@ func setUp() {
 	storagePath = filepath.Join(os.TempDir(), testStorageSuffix)
 	processFlags()
 	logger.Init()
-	vmstorage.InitWithoutMetrics()
+	vmstorage.InitWithoutMetrics(promql.ResetRollupResultCacheIfNeeded)
 	vmselect.Init()
 	vminsert.Init()
 	go httpserver.Serve(*httpListenAddr, requestHandler)
@@ -147,7 +148,7 @@ func setUp() {
 }
 
 func processFlags() {
-	envflag.Parse()
+	flag.Parse()
 	for _, fv := range []struct {
 		flag  string
 		value string
@@ -192,7 +193,7 @@ func TestWriteRead(t *testing.T) {
 	time.Sleep(1 * time.Second)
 	vmstorage.Stop()
 	// open storage after stop in write
-	vmstorage.InitWithoutMetrics()
+	vmstorage.InitWithoutMetrics(promql.ResetRollupResultCacheIfNeeded)
 	t.Run("read", testRead)
 }
 
@@ -208,7 +209,7 @@ func testWrite(t *testing.T) {
 				t.Errorf("error compressing %v %s", r, err)
 				t.Fail()
 			}
-			httpWrite(t, testPromWriteHTTPPath, bytes.NewBuffer(data))
+			httpWrite(t, testPromWriteHTTPPath, test.InsertQuery, bytes.NewBuffer(data))
 		}
 	})
 
@@ -217,7 +218,7 @@ func testWrite(t *testing.T) {
 			test := x
 			t.Run(test.Name, func(t *testing.T) {
 				t.Parallel()
-				httpWrite(t, testWriteHTTPPath, bytes.NewBufferString(strings.Join(test.Data, "\n")))
+				httpWrite(t, testWriteHTTPPath, test.InsertQuery, bytes.NewBufferString(strings.Join(test.Data, "\n")))
 			})
 		}
 	})
@@ -245,7 +246,7 @@ func testWrite(t *testing.T) {
 			t.Run(test.Name, func(t *testing.T) {
 				t.Parallel()
 				logger.Infof("writing %s", test.Data)
-				httpWrite(t, testOpenTSDBWriteHTTPPath, bytes.NewBufferString(strings.Join(test.Data, "\n")))
+				httpWrite(t, testOpenTSDBWriteHTTPPath, test.InsertQuery, bytes.NewBufferString(strings.Join(test.Data, "\n")))
 			})
 		}
 	})
@@ -323,10 +324,10 @@ func readIn(readFor string, t *testing.T, insertTime time.Time) []test {
 	return tt
 }
 
-func httpWrite(t *testing.T, address string, r io.Reader) {
+func httpWrite(t *testing.T, address, query string, r io.Reader) {
 	t.Helper()
 	s := newSuite(t)
-	resp, err := http.Post(address, "", r)
+	resp, err := http.Post(address+query, "", r)
 	s.noError(err)
 	s.noError(resp.Body.Close())
 	s.equalInt(resp.StatusCode, 204)

app/victoria-metrics/multiarch/Dockerfile

@@ -0,0 +1,12 @@
+# See https://medium.com/on-docker/use-multi-stage-builds-to-inject-ca-certs-ad1e8f01de1b
+ARG certs_image
+ARG root_image
+FROM $certs_image as certs
+RUN apk --update --no-cache add ca-certificates
+
+FROM $root_image
+COPY --from=certs /etc/ssl/certs/ca-certificates.crt /etc/ssl/certs/ca-certificates.crt
+EXPOSE 8428
+ENTRYPOINT ["/victoria-metrics-prod"]
+ARG TARGETARCH
+COPY victoria-metrics-${TARGETARCH}-prod ./victoria-metrics-prod

app/victoria-metrics/testdata/graphite/comparison-not-inf-not-nan.json

@@ -11,6 +11,6 @@
     "status":"success",
     "data":{"resultType":"matrix",
       "result":[
-	      {"metric":{"item":"y"},"values":[["{TIME_S-1m}","0.5"],["{TIME_S}","0.5"]]}
+	      {"metric":{"item":"y"},"values":[["{TIME_S-1m}","0.5"]]}
       ]}}
 }

app/victoria-metrics/testdata/graphite/graphite-selector.json

@@ -0,0 +1,17 @@
+{
+  "name": "graphite-selector",
+  "issue": "",
+  "data": [
+    "graphite-selector.bar.baz 1 {TIME_S-1m}",
+    "graphite-selector.xxx.yy  2 {TIME_S-1m}",
+    "graphite-selector.bb.cc 3 {TIME_S-1m}",
+    "graphite-selector.a.baz 4 {TIME_S-1m}"],
+  "query": ["/api/v1/query?query=sort({__graphite__='graphite-selector.*.baz'})&time={TIME_S-1m}"],
+  "result_query": {
+    "status":"success",
+    "data":{"resultType":"vector","result":[
+	    {"metric":{"__name__":"graphite-selector.bar.baz"},"value":["{TIME_S-1m}","1"]},
+	    {"metric":{"__name__":"graphite-selector.a.baz"},"value":["{TIME_S-1m}","4"]}
+    ]}
+  }
+}

app/victoria-metrics/testdata/graphite/name-plus-negative-filter.json

@@ -0,0 +1,16 @@
+{
+  "name": "name-plus-negative-filter",
+  "issue": "",
+  "data": [
+    "name-plus-negative-filter;foo=123 1 {TIME_S-1m}",
+    "name-plus-negative-filter;bar=123 2 {TIME_S-1m}",
+    "name-plus-negative-filter;foo=qwe 3 {TIME_S-1m}"
+  ],
+  "query": ["/api/v1/query?query={__name__='name-plus-negative-filter',foo!='123'}&time={TIME_S-1m}"],
+  "result_query": {
+    "status":"success",
+    "data":{"resultType":"vector","result":[
+	    {"metric":{"__name__":"name-plus-negative-filter","foo":"qwe"},"value":["{TIME_S-1m}","3"]}
+    ]}
+  }
+}

app/victoria-metrics/testdata/graphite/not-nan-as-missing-data.json

@@ -13,6 +13,6 @@
     "data":{"resultType":"matrix",
       "result":[
 	      {"metric":{"__name__":"not_nan_as_missing_data","item":"x"},"values":[["{TIME_S-2m}","2"]]},
-	      {"metric":{"__name__":"not_nan_as_missing_data","item":"y"},"values":[["{TIME_S-2m}","4"],["{TIME_S-1m}","3"],["{TIME_S}","3"]]}
+	      {"metric":{"__name__":"not_nan_as_missing_data","item":"y"},"values":[["{TIME_S-2m}","4"],["{TIME_S-1m}","3"]]}
       ]}}
 }

app/victoria-metrics/testdata/influxdb/with_extra_labels.json

@@ -0,0 +1,10 @@
+{
+  "name": "insert_with_extra_labels",
+  "data": ["measurement,tag1=value1,tag2=value2 field6=1.23,field5=123 {TIME_NS}"],
+  "insert_query": "?extra_label=job=test&extra_label=tag2=value10",
+  "query": ["/api/v1/export?match={__name__!=''}"],
+  "result_metrics": [
+    {"metric":{"__name__":"measurement_field5","tag1":"value1","job": "test","tag2":"value10"},"values":[123], "timestamps": ["{TIME_MS}"]},
+    {"metric":{"__name__":"measurement_field6","tag1":"value1","job": "test","tag2":"value10"},"values":[1.23], "timestamps": ["{TIME_MS}"]}
+  ]
+}

app/victoria-metrics/testdata/opentsdbhttp/with_extra_labels.json

@@ -0,0 +1,9 @@
+{
+  "name": "insert_with_extra_labels",
+  "data": ["{\"metric\": \"opentsdbhttp.foobar\", \"value\": 1001, \"timestamp\": {TIME_S}, \"tags\": {\"bar\":\"baz\", \"x\": \"y\"}}"],
+  "insert_query": "?extra_label=job=open-test&extra_label=x=z",
+  "query": ["/api/v1/export?match={__name__!=''}"],
+  "result_metrics": [
+    {"metric":{"__name__":"opentsdbhttp.foobar","bar":"baz","x":"z","job": "open-test"},"values":[1001], "timestamps": ["{TIME_MSZ}"]}
+  ]
+}

app/victoria-metrics/testdata/prometheus/with_extra_labels.json

@@ -0,0 +1,9 @@
+{
+  "name": "basic_insertion_with_extra_labels",
+  "insert_query": "?extra_label=job=prom-test&extra_label=baz=bar",
+  "data": ["[{\"labels\":[{\"name\":\"__name__\",\"value\":\"prometheus.foobar\"},{\"name\":\"baz\",\"value\":\"qux\"}],\"samples\":[{\"value\":100000,\"timestamp\":\"{TIME_MS}\"}]}]"],
+  "query": ["/api/v1/export?match={__name__!=''}"],
+  "result_metrics": [
+    {"metric":{"__name__":"prometheus.foobar","baz":"bar","job": "prom-test"},"values":[100000], "timestamps": ["{TIME_MS}"]}
+  ]
+}

app/victoria-metrics/testdata/prometheus/with_request_extra_filter.json

@@ -0,0 +1,8 @@
+{
+  "name": "basic_select_with_extra_labels",
+  "data": ["[{\"labels\":[{\"name\":\"__name__\",\"value\":\"prometheus.tenant.limits\"},{\"name\":\"baz\",\"value\":\"qux\"},{\"name\":\"tenant\",\"value\":\"dev\"}],\"samples\":[{\"value\":100000,\"timestamp\":\"{TIME_MS}\"}]},{\"labels\":[{\"name\":\"__name__\",\"value\":\"prometheus.up\"},{\"name\":\"baz\",\"value\":\"qux\"}],\"samples\":[{\"value\":100000,\"timestamp\":\"{TIME_MS}\"}]}]"],
+  "query": ["/api/v1/export?match={__name__!=''}&extra_label=tenant=dev"],
+  "result_metrics": [
+    {"metric":{"__name__":"prometheus.tenant.limits","baz":"qux","tenant": "dev"},"values":[100000], "timestamps": ["{TIME_MS}"]}
+  ]
+}

app/vmagent/Makefile

@@ -78,3 +78,9 @@ vmagent-local-with-goarch:
 
 vmagent-pure:
 	APP_NAME=vmagent $(MAKE) app-local-pure
+
+vmagent-windows-amd64:
+	GOARCH=amd64 APP_NAME=vmagent $(MAKE) app-local-windows-with-goarch
+
+vmagent-windows-amd64-prod:
+	APP_NAME=vmagent $(MAKE) app-via-docker-windows-amd64

app/vmagent/README.md

@@ -1,48 +1,51 @@
-## vmagent
+# vmagent
 
-`vmagent` is a tiny but brave agent, which helps you collect metrics from various sources
-and stores them in [VictoriaMetrics](https://github.com/VictoriaMetrics/VictoriaMetrics)
-or any other Prometheus-compatible storage system that supports the `remote_write` protocol.
+`vmagent` is a tiny but mighty agent which helps you collect metrics from various sources
+and store them in [VictoriaMetrics](https://github.com/VictoriaMetrics/VictoriaMetrics)
+or any other Prometheus-compatible storage systems that support the `remote_write` protocol.
 
 <img alt="vmagent" src="vmagent.png">
 
 
-### Motivation
+## Motivation
 
 While VictoriaMetrics provides an efficient solution to store and observe metrics, our users needed something fast
-and RAM friendly to scrape metrics from Prometheus-compatible exporters to VictoriaMetrics.
-Also, we found that users’ infrastructure are snowflakes - no two are alike, and we decided to add more flexibility
-to `vmagent` (like the ability to push metrics instead of pulling them). We did our best and plan to do even more.
+and RAM friendly to scrape metrics from Prometheus-compatible exporters into VictoriaMetrics.
+Also, we found that our user's infrastructure are like snowflakes in that no two are alike. Therefore we decided to add more flexibility
+to `vmagent` such as the ability to push metrics instead of pulling them. We did our best and will continue to improve vmagent.
 
 
-### Features
+## Features
 
-* Can be used as drop-in replacement for Prometheus for scraping targets such as [node_exporter](https://github.com/prometheus/node_exporter).
+* Can be used as a drop-in replacement for Prometheus for scraping targets such as [node_exporter](https://github.com/prometheus/node_exporter).
   See [Quick Start](#quick-start) for details.
 * Can add, remove and modify labels (aka tags) via Prometheus relabeling. Can filter data before sending it to remote storage. See [these docs](#relabeling) for details.
-* Accepts data via all the ingestion protocols supported by VictoriaMetrics:
-  * Influx line protocol via `http://<vmagent>:8429/write`. See [these docs](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/README.md#how-to-send-data-from-influxdb-compatible-agents-such-as-telegraf).
-  * Graphite plaintext protocol if `-graphiteListenAddr` command-line flag is set. See [these docs](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/README.md#how-to-send-data-from-graphite-compatible-agents-such-as-statsd).
-  * OpenTSDB telnet and http protocols if `-opentsdbListenAddr` command-line flag is set. See [these docs](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/README.md#how-to-send-data-from-opentsdb-compatible-agents).
+* Accepts data via all ingestion protocols supported by VictoriaMetrics:
+  * Influx line protocol via `http://<vmagent>:8429/write`. See [these docs](https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html#how-to-send-data-from-influxdb-compatible-agents-such-as-telegraf).
+  * Graphite plaintext protocol if `-graphiteListenAddr` command-line flag is set. See [these docs](https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html#how-to-send-data-from-graphite-compatible-agents-such-as-statsd).
+  * OpenTSDB telnet and http protocols if `-opentsdbListenAddr` command-line flag is set. See [these docs](https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html#how-to-send-data-from-opentsdb-compatible-agents).
   * Prometheus remote write protocol via `http://<vmagent>:8429/api/v1/write`.
-  * JSON lines import protocol via `http://<vmagent>:8429/api/v1/import`. See [these docs](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/README.md#how-to-import-data-in-json-line-format).
-  * Native data import protocol via `http://<vmagent>:8429/api/v1/import/native`. See [these docs](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/README.md#how-to-import-data-in-native-format).
-  * Data in Prometheus exposition format. See [these docs](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/README.md#how-to-import-data-in-prometheus-exposition-format) for details.
-  * Arbitrary CSV data via `http://<vmagent>:8429/api/v1/import/csv`. See [these docs](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/README.md#how-to-import-csv-data).
+  * JSON lines import protocol via `http://<vmagent>:8429/api/v1/import`. See [these docs](https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html#how-to-import-data-in-json-line-format).
+  * Native data import protocol via `http://<vmagent>:8429/api/v1/import/native`. See [these docs](https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html#how-to-import-data-in-native-format).
+  * Data in Prometheus exposition format. See [these docs](https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html#how-to-import-data-in-prometheus-exposition-format) for details.
+  * Arbitrary CSV data via `http://<vmagent>:8429/api/v1/import/csv`. See [these docs](https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html#how-to-import-csv-data).
 * Can replicate collected metrics simultaneously to multiple remote storage systems.
-* Works in environments with unstable connections to remote storage. If the remote storage is unavailable, the collected metrics
-  are buffered at `-remoteWrite.tmpDataPath`. The buffered metrics are sent to remote storage as soon as connection
-  to remote storage is recovered. The maximum disk usage for the buffer can be limited with `-remoteWrite.maxDiskUsagePerURL`.
-* Uses lower amounts of RAM, CPU, disk IO and network bandwidth compared to Prometheus.
+* Works smoothly in environments with unstable connections to remote storage. If the remote storage is unavailable, the collected metrics
+  are buffered at `-remoteWrite.tmpDataPath`. The buffered metrics are sent to remote storage as soon as the connection
+  to the remote storage is repaired. The maximum disk usage for the buffer can be limited with `-remoteWrite.maxDiskUsagePerURL`.
+* Uses lower amounts of RAM, CPU, disk IO and network bandwidth compared with Prometheus.
+* Scrape targets can be spread among multiple `vmagent` instances when big number of targets must be scraped. See [these docs](#scraping-big-number-of-targets).
+* Can efficiently scrape targets that expose millions of time series such as [/federate endpoint in Prometheus](https://prometheus.io/docs/prometheus/latest/federation/). See [these docs](#stream-parsing-mode).
+* Can deal with high cardinality and high churn rate issues by limiting the number of unique time series sent to remote storage systems. See [these docs](#cardinality-limiter).
 
 
-### Quick Start
+## Quick Start
 
-Just download `vmutils-*` archive from [releases page](https://github.com/VictoriaMetrics/VictoriaMetrics/releases), unpack it
-and pass the following flags to `vmagent` binary in order to start scraping Prometheus targets:
+Please download `vmutils-*` archive from [releases page](https://github.com/VictoriaMetrics/VictoriaMetrics/releases), unpack it
+and configure the following flags to the `vmagent` binary in order to start scraping Prometheus targets:
 
-* `-promscrape.config` with the path to Prometheus config file (it is usually located at `/etc/prometheus/prometheus.yml`)
-* `-remoteWrite.url` with the remote storage endpoint such as VictoriaMetrics. The `-remoteWrite.url` argument can be specified multiple times in order to replicate data concurrently to an arbitrary number of remote storage systems.
+* `-promscrape.config` with the path to Prometheus config file (usually located at `/etc/prometheus/prometheus.yml`)
+* `-remoteWrite.url` with the remote storage endpoint such as VictoriaMetrics, the `-remoteWrite.url` argument can be specified multiple times to replicate data concurrently to an arbitrary number of remote storage systems.
 
 Example command line:
 
@@ -50,20 +53,20 @@ Example command line:
 /path/to/vmagent -promscrape.config=/path/to/prometheus.yml -remoteWrite.url=https://victoria-metrics-host:8428/api/v1/write
 ```
 
-If you only need to collect Influx data, then the following is sufficient:
+If you only need to collect Influx data, then the following command is sufficient:
 
 ```
 /path/to/vmagent -remoteWrite.url=https://victoria-metrics-host:8428/api/v1/write
 ```
 
-Then send Influx data to `http://vmagent-host:8429`. See [these docs](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/README.md#how-to-send-data-from-influxdb-compatible-agents-such-as-telegraf) for more details.
+Then send Influx data to `http://vmagent-host:8429`. See [these docs](https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html#how-to-send-data-from-influxdb-compatible-agents-such-as-telegraf) for more details.
 
 `vmagent` is also available in [docker images](https://hub.docker.com/r/victoriametrics/vmagent/tags).
 
-Pass `-help` to `vmagent` in order to see the full list of supported command-line flags with their descriptions.
+Pass `-help` to `vmagent` in order to see [the full list of supported command-line flags with their descriptions](#advanced-usage).
 
 
-### Configuration update
+## Configuration update
 
 `vmagent` should be restarted in order to update config options set via command-line args.
 
@@ -79,139 +82,155 @@ Pass `-help` to `vmagent` in order to see the full list of supported command-lin
 There is also `-promscrape.configCheckInterval` command-line option, which can be used for automatic reloading configs from updated `-promscrape.config` file.
 
 
-### Use cases
+## Use cases
 
 
-#### IoT and Edge monitoring
+### IoT and Edge monitoring
 
-`vmagent` can run and collect metrics in IoT and industrial networks with unreliable or scheduled connections to the remote storage.
+`vmagent` can run and collect metrics in IoT and industrial networks with unreliable or scheduled connections to their remote storage.
 It buffers the collected data in local files until the connection to remote storage becomes available and then sends the buffered
-data to the remote storage. It re-tries sending the data to remote storage on any errors.
+data to the remote storage. It re-tries sending the data to remote storage until any errors are resolved.
 The maximum buffer size can be limited with `-remoteWrite.maxDiskUsagePerURL`.
 
-`vmagent` works on various architectures from IoT world - 32-bit arm, 64-bit arm, ppc64, 386, amd64.
+`vmagent` works on various architectures from the IoT world - 32-bit arm, 64-bit arm, ppc64, 386, amd64.
 See [the corresponding Makefile rules](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/app/vmagent/Makefile) for details.
 
 
-#### Drop-in replacement for Prometheus
+### Drop-in replacement for Prometheus
 
-If you use Prometheus only for scraping metrics from various targets and forwarding these metrics to remote storage,
-then `vmagent` can replace such Prometheus setup. Usually `vmagent` requires lower amounts of RAM, CPU and network bandwidth comparing to Prometheus for such a setup.
+If you use Prometheus only for scraping metrics from various targets and forwarding those metrics to remote storage
+then `vmagent` can replace Prometheus. Typically, `vmagent` requires lower amounts of RAM, CPU and network bandwidth compared with Prometheus.
 See [these docs](#how-to-collect-metrics-in-prometheus-format) for details.
 
 
-#### Replication and high availability
+### Replication and high availability
 
 `vmagent` replicates the collected metrics among multiple remote storage instances configured via `-remoteWrite.url` args.
-If a single remote storage instance temporarily is out of service, then the collected data remains available in another remote storage instances.
-`vmagent` buffers the collected data in files at `-remoteWrite.tmpDataPath` until the remote storage becomes available again.
-Then it sends the buffered data to the remote storage in order to prevent data gaps in the remote storage.
+If a single remote storage instance temporarily is out of service, then the collected data remains available in another remote storage instance.
+`vmagent` buffers the collected data in files at `-remoteWrite.tmpDataPath` until the remote storage becomes available again and then it sends the buffered data to the remote storage in order to prevent data gaps.
 
 
-#### Relabeling and filtering
+### Relabeling and filtering
 
-`vmagent` can add, remove or update labels on the collected data before sending it to remote storage. Additionally,
+`vmagent` can add, remove or update labels on the collected data before sending it to the remote storage. Additionally,
 it can remove unwanted samples via Prometheus-like relabeling before sending the collected data to remote storage.
-See [these docs](#relabeling) for details.
+Please see [these docs](#relabeling) for details.
 
 
-#### Splitting data streams among multiple systems
+### Splitting data streams among multiple systems
 
 `vmagent` supports splitting the collected data between muliple destinations with the help of `-remoteWrite.urlRelabelConfig`,
-which is applied independently for each configured `-remoteWrite.url` destination. For instance, it is possible to replicate or split
-data among long-term remote storage, short-term remote storage and real-time analytical system [built on top of Kafka](https://github.com/Telefonica/prometheus-kafka-adapter).
-Note that each destination can receive its own subset of the collected data thanks to per-destination relabeling via `-remoteWrite.urlRelabelConfig`.
+which is applied independently for each configured `-remoteWrite.url` destination. For example, it is possible to replicate or split
+data among long-term remote storage, short-term remote storage and a real-time analytical system [built on top of Kafka](https://github.com/Telefonica/prometheus-kafka-adapter).
+Note that each destination can receive it's own subset of the collected data due to per-destination relabeling via `-remoteWrite.urlRelabelConfig`.
 
 
-#### Prometheus remote_write proxy
+### Prometheus remote_write proxy
 
-`vmagent` may be used as a proxy for Prometheus data sent via Prometheus `remote_write` protocol. It can accept data via `remote_write` API
-at `/api/v1/write` endpoint, apply relabeling and filtering and then proxy it to another `remote_write` systems.
+`vmagent` can be used as a proxy for Prometheus data sent via Prometheus `remote_write` protocol. It can accept data via the `remote_write` API
+at the`/api/v1/write` endpoint. Then apply relabeling and filtering and proxy it to another `remote_write` system .
 The `vmagent` can be configured to encrypt the incoming `remote_write` requests with `-tls*` command-line flags.
-Additionally, Basic Auth can be enabled for the incoming `remote_write` requests with `-httpAuth.*` command-line flags.
+Also, Basic Auth can be enabled for the incoming `remote_write` requests with `-httpAuth.*` command-line flags.
 
 
+### remote_write for clustered version
 
-### How to collect metrics in Prometheus format
+While `vmagent` can accept data in several supported protocols (OpenTSDB, Influx, Prometheus, Graphite) and scrape data from various targets, writes are always peformed in Promethes remote_write protocol. Therefore for the [clustered version](https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html), `-remoteWrite.url` the command-line flag should be configured as `<schema>://<vminsert-host>:8480/insert/<customer-id>/prometheus/api/v1/write`
 
-Pass the path to `prometheus.yml` to `-promscrape.config` command-line flag. `vmagent` takes into account the following
+
+## How to collect metrics in Prometheus format
+
+Specify the path to `prometheus.yml` file via `-promscrape.config` command-line flag. `vmagent` takes into account the following
 sections from [Prometheus config file](https://prometheus.io/docs/prometheus/latest/configuration/configuration/):
 
 * `global`
 * `scrape_configs`
 
-All the other sections are ignored, including [remote_write](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#remote_write) section.
-Use `-remoteWrite.*` command-line flags instead for configuring remote write settings.
+All other sections are ignored, including the [remote_write](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#remote_write) section.
+Use `-remoteWrite.*` command-line flag instead for configuring remote write settings.
 
 The following scrape types in [scrape_config](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#scrape_config) section are supported:
 
-* `static_configs` - for scraping statically defined targets. See [these docs](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#static_config) for details.
-* `file_sd_configs` - for scraping targets defined in external files aka file-based service discover.
-  See [these docs](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#file_sd_config) for details.
+* `static_configs` - is for scraping statically defined targets. See [these docs](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#static_config) for details.
+* `file_sd_configs` - is for scraping targets defined in external files (aka file-based service discover).
+  See [these docs](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#file_sd_config) for details
 * `kubernetes_sd_configs` - for scraping targets in Kubernetes (k8s).
   See [kubernetes_sd_config](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#kubernetes_sd_config) for details.
-* `ec2_sd_configs` - for scraping targets in Amazon EC2.
+* `ec2_sd_configs` - is for scraping targets in Amazon EC2.
   See [ec2_sd_config](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#ec2_sd_config) for details.
-  `vmagent` doesn't support `profile` config param and aws credentials file yet.
-* `gce_sd_configs` - for scraping targets in Google Compute Engine (GCE).
+  `vmagent` doesn't support the `profile` config param yet.
+* `gce_sd_configs` - is for scraping targets in Google Compute Engine (GCE).
   See [gce_sd_config](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#gce_sd_config) for details.
   `vmagent` provides the following additional functionality for `gce_sd_config`:
-  * if `project` arg is missing, then `vmagent` uses the project for the instance where it runs;
-  * if `zone` arg is missing, then `vmagent` uses the zone for the instance where it runs;
-  * if `zone` arg equals to `"*"`, then `vmagent` discovers all the zones for the given project;
-  * `zone` may contain arbitrary number of zones, i.e. `zone: [us-east1-a, us-east1-b]`.
-* `consul_sd_configs` - for scraping targets registered in Consul.
+  * if `project` arg is missing then `vmagent` uses the project for the instance where it runs;
+  * if `zone` arg is missing then `vmagent` uses the zone for the instance where it runs;
+  * if `zone` arg is equal to `"*"`, then `vmagent` discovers all the zones for the given project;
+  * `zone` may contain an arbitrary number of zones, i.e. `zone: [us-east1-a, us-east1-b]`.
+* `consul_sd_configs` - is for scraping the targets registered in Consul.
   See [consul_sd_config](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#consul_sd_config) for details.
-* `dns_sd_configs` - for scraping targets discovered from DNS records (SRV, A and AAAA).
+* `dns_sd_configs` - is for scraping targets discovered from DNS records (SRV, A and AAAA).
   See [dns_sd_config](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#dns_sd_config) for details.
-* `openstack_sd_configs` - for scraping OpenStack targets.
+* `openstack_sd_configs` - is for scraping OpenStack targets.
   See [openstack_sd_config](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#openstack_sd_config) for details.
   [OpenStack identity API v3](https://docs.openstack.org/api-ref/identity/v3/) is supported only.
-* `dockerswarm_sd_configs` - for scraping Docker Swarm targets.
+* `docker_sd_configs` - is for scraping Docker targets.
+  See [docker_sd_config](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#docker_sd_config) for details.
+* `dockerswarm_sd_configs` - is for scraping Docker Swarm targets.
   See [dockerswarm_sd_config](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#dockerswarm_sd_config) for details.
+* `eureka_sd_configs` - is for scraping targets registered in [Netflix Eureka](https://github.com/Netflix/eureka).
+  See [eureka_sd_config](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#eureka_sd_config) for details.
+* `digitalocean_sd_configs` is for scraping targerts registered in [DigitalOcean](https://www.digitalocean.com/)
+  See [digitalocean_sd_config](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#digitalocean_sd_config) for details.
+* `http_sd_configs` is for scraping targerts registered in http service discovery.
+  See [http_sd_config](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#http_sd_config) for details.
 
-File feature requests at [our issue tracker](https://github.com/VictoriaMetrics/VictoriaMetrics/issues) if you need other service discovery mechanisms to be supported by `vmagent`.
+Please file feature requests to [our issue tracker](https://github.com/VictoriaMetrics/VictoriaMetrics/issues) if you need other service discovery mechanisms to be supported by `vmagent`.
 
-`vmagent` also support the following additional options in `scrape_config` section:
+`vmagent` also support the following additional options in `scrape_configs` section:
 
-* `disable_compression: true` - for disabling response compression on a per-job basis. By default `vmagent` requests compressed responses from scrape targets
-  in order to save network bandwidth.
-* `disable_keepalive: true` - for disabling [HTTP keep-alive connections](https://en.wikipedia.org/wiki/HTTP_persistent_connection) on a per-job basis.
-  By default `vmagent` uses keep-alive connections to scrape targets in order to reduce overhead on connection re-establishing.
+* `disable_compression: true` - to disable response compression on a per-job basis. By default `vmagent` requests compressed responses from scrape targets
+  to save network bandwidth.
+* `disable_keepalive: true` - to disable [HTTP keep-alive connections](https://en.wikipedia.org/wiki/HTTP_persistent_connection) on a per-job basis.
+  By default, `vmagent` uses keep-alive connections to scrape targets to reduce overhead on connection re-establishing.
+* `stream_parse: true` - for scraping targets in a streaming manner. This may be useful for targets exporting big number of metrics. See [these docs](#stream-parsing-mode).
 
-Note that `vmagent` doesn't support `refresh_interval` option these scrape configs. Use the corresponding `-promscrape.*CheckInterval`
+Note that `vmagent` doesn't support `refresh_interval` option for these scrape configs. Use the corresponding `-promscrape.*CheckInterval`
 command-line flag instead. For example, `-promscrape.consulSDCheckInterval=60s` sets `refresh_interval` for all the `consul_sd_configs`
-entries to 60s. Run `vmagent -help` in order to see default values for `-promscrape.*CheckInterval` flags.
+entries to 60s. Run `vmagent -help` in order to see default values for the `-promscrape.*CheckInterval` flags.
 
-The file pointed by `-promscrape.config` may contain `%{ENV_VAR}` placeholders, which are substituted by the corresponding `ENV_VAR` environment variable values.
+The file pointed by `-promscrape.config` may contain `%{ENV_VAR}` placeholders which are substituted by the corresponding `ENV_VAR` environment variable values.
 
 
-### Adding labels to metrics
+## Adding labels to metrics
 
-Labels can be added to metrics via the following mechanisms:
+Labels can be added to metrics by the following mechanisms:
 
-* Via `global -> external_labels` section in `-promscrape.config` file. These labels are added only to metrics scraped from targets configured in `-promscrape.config` file.
-* Via `-remoteWrite.label` command-line flag. These labels are added to all the collected metrics before sending them to `-remoteWrite.url`.
+* The `global -> external_labels` section in `-promscrape.config` file. These labels are added only to metrics scraped from targets configured in the `-promscrape.config` file. They aren't added to metrics collected via other [data ingestion protocols](https://docs.victoriametrics.com/#how-to-import-time-series-data).
+* The `-remoteWrite.label` command-line flag. These labels are added to all the collected metrics before sending them to `-remoteWrite.url`. For example, the following command will start `vmagent`, which will add `{datacenter="foobar"}` label to all the metrics pushed to all the configured remote storage systems (all the `-remoteWrite.url` flag values):
+
+```
+/path/to/vmagent -remoteWrite.label=datacenter=foobar ...
+```
 
 
-### Relabeling
+## Relabeling
 
 `vmagent` supports [Prometheus relabeling](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config).
-Additionally it provides the following extra actions:
+and also provides the following actions:
 
-* `replace_all`: replaces all the occurences of `regex` in the values of `source_labels` with the `replacement` and stores the result in the `target_label`.
-* `labelmap_all`: replaces all the occurences of `regex` in all the label names with the `replacement`.
-* `keep_if_equal`: keeps the entry if all label values from `source_labels` are equal.
+* `replace_all`: replaces all of the occurences of `regex` in the values of `source_labels` with the `replacement` and stores the results in the `target_label`.
+* `labelmap_all`: replaces all of the occurences of `regex` in all the label names with the `replacement`.
+* `keep_if_equal`: keeps the entry if all the label values from `source_labels` are equal.
 * `drop_if_equal`: drops the entry if all the label values from `source_labels` are equal.
 
 The relabeling can be defined in the following places:
 
-* At `scrape_config -> relabel_configs` section in `-promscrape.config` file. This relabeling is applied to target labels.
-* At `scrape_config -> metric_relabel_configs` section in `-promscrape.config` file. This relabeling is applied to all the scraped metrics in the given `scrape_config`.
-* At `-remoteWrite.relabelConfig` file. This relabeling is aplied to all the collected metrics before sending them to remote storage.
-* At `-remoteWrite.urlRelabelConfig` files. This relabeling is applied to metrics before sending them to the corresponding `-remoteWrite.url`.
+* At the `scrape_config -> relabel_configs` section in `-promscrape.config` file. This relabeling is applied to target labels. This relabeling can be debugged by passing `relabel_debug: true` option to the corresponding `scrape_config` section. In this case `vmagent` logs target labels before and after the relabeling and then drops the logged target.
+* At the `scrape_config -> metric_relabel_configs` section in `-promscrape.config` file. This relabeling is applied to all the scraped metrics in the given `scrape_config`. This relabeling can be debugged by passing `metric_relabel_debug: true` option to the corresponding `scrape_config` section. In this case `vmagent` logs metrics before and after the relabeling and then drops the logged metrics.
+* At the `-remoteWrite.relabelConfig` file. This relabeling is aplied to all the collected metrics before sending them to remote storage. This relabeling can be debugged by passing `-remoteWrite.relabelDebug` command-line option to `vmagent`. In this case `vmagent` logs metrics before and after the relabeling and then drops all the logged metrics instead of sending them to remote storage.
+* At the `-remoteWrite.urlRelabelConfig` files. This relabeling is applied to metrics before sending them to the corresponding `-remoteWrite.url`. This relabeling can be debugged by passing `-remoteWrite.urlRelabelDebug` command-line options to `vmagent`. In this case `vmagent` logs metrics before and after the relabeling and then drops all the logged metrics instead of sending them to the corresponding `-remoteWrite.url`.
 
-Read more about relabeling in the following articles:
+You can read more about relabeling in the following articles:
 
 * [How to use Relabeling in Prometheus and VictoriaMetrics](https://valyala.medium.com/how-to-use-relabeling-in-prometheus-and-victoriametrics-8b90fc22c4b2)
 * [Life of a label](https://www.robustperception.io/life-of-a-label)
@@ -221,45 +240,9 @@ Read more about relabeling in the following articles:
 * [relabel_configs vs metric_relabel_configs](https://www.robustperception.io/relabel_configs-vs-metric_relabel_configs)
 
 
-### Monitoring
+## Stream parsing mode
 
-`vmagent` exports various metrics in Prometheus exposition format at `http://vmagent-host:8429/metrics` page. It is recommended setting up regular scraping of this page
-either via `vmagent` itself or via Prometheus, so the exported metrics could be analyzed later.
-Use official [Grafana dashboard](https://grafana.com/grafana/dashboards/12683) for `vmagent` state overview.
-If you have suggestions, improvements or found a bug - feel free to open an issue on github or add review to the dashboard.
-
-`vmagent` also exports target statuses at the following handlers:
-
-* `http://vmagent-host:8429/targets`. This handler returns human-readable plaintext status for every active target.
-This page is convenient to query from command line with `wget`, `curl` or similar tools.
-It accepts optional `show_original_labels=1` query arg, which shows the original labels per each target before applying relabeling.
-This information may be useful for debugging target relabeling.
-* `http://vmagent-host:8429/api/v1/targets`. This handler returns data compatible with [the corresponding page from Prometheus API](https://prometheus.io/docs/prometheus/latest/querying/api/#targets).
-
-* `http://vmagent-host:8429/ready`. This handler returns http 200 status code when `vmagent` finishes initialization for all service_discovery configs.
-It may be useful for performing `vmagent` rolling update without scrape loss.
-
-
-### Troubleshooting
-
-* It is recommended [setting up the official Grafana dashboard](#monitoring) in order to monitor `vmagent` state.
-
-* It is recommended increasing the maximum number of open files in the system (`ulimit -n`) when scraping big number of targets,
-  since `vmagent` establishes at least a single TCP connection per each target.
-
-* When `vmagent` scrapes many unreliable targets, it can flood error log with scrape errors. These errors can be suppressed
-  by passing `-promscrape.suppressScrapeErrors` command-line flag to `vmagent`. The most recent scrape error per each target can be observed at `http://vmagent-host:8429/targets`
-  and `http://vmagent-host:8429/api/v1/targets`.
-
-* The `/api/v1/targets` page could be useful for debugging relabeling process for scrape targets.
-  This page contains original labels for targets dropped during relabeling (see "droppedTargets" section in the page output). By default up to `-promscrape.maxDroppedTargets` targets are shown here. If your setup drops more targets during relabeling, then increase `-promscrape.maxDroppedTargets` command-line flag value in order to see all the dropped targets. Note that tracking each dropped target requires up to 10Kb of RAM, so big values for `-promscrape.maxDroppedTargets` may result in increased memory usage if big number of scrape targets are dropped during relabeling.
-
-* If `vmagent` scrapes big number of targets, then `-promscrape.dropOriginalLabels` command-line option may be passed to `vmagent` in order to reduce memory usage.
-  This option drops `"discoveredLabels"` and `"droppedTargets"` lists at `/api/v1/targets` page, which may result in reduced debuggability for improperly configured per-target relabeling.
-
-* If `vmagent` scrapes targets with millions of metrics per each target (for instance, when scraping [federation endpoints](https://prometheus.io/docs/prometheus/latest/federation/)),
-  then it is recommended enabling `stream parsing mode` in order to reduce memory usage during scraping. This mode may be enabled either globally for all the scrape targets
-  by passing `-promscrape.streamParse` command-line flag or on a per-scrape target basis with `stream_parse: true` option. For example:
+By default `vmagent` reads the full response from scrape target into memory, then parses it, applies [relabeling](#relabeling) and then pushes the resulting metrics to the configured `-remoteWrite.url`. This mode works good for the majority of cases when the scrape target exposes small number of metrics (e.g. less than 10 thousand). But this mode may take big amounts of memory when the scrape target exposes big number of metrics. In this case it is recommended enabling stream parsing mode. When this mode is enabled, then `vmagent` reads response from scrape target in chunks, then immediately processes every chunk and pushes the processed metrics to remote storage. This allows saving memory when scraping targets that expose millions of metrics. Stream parsing mode may be enabled either globally for all of the scrape targets by passing `-promscrape.streamParse` command-line flag or on a per-scrape target basis with `stream_parse: true` option. For example:
 
   ```yml
   scrape_configs:
@@ -275,30 +258,176 @@ It may be useful for performing `vmagent` rolling update without scrape loss.
       'match[]': ['{__name__!=""}']
   ```
 
-* It is recommended to increase `-remoteWrite.queues` if `vmagent_remotewrite_pending_data_bytes` metric exported at `http://vmagent-host:8429/metrics` page constantly grows.
+Note that `sample_limit` option doesn't prevent from data push to remote storage if stream parsing is enabled because the parsed data is pushed to remote storage as soon as it is parsed.
 
-* If you see gaps on the data pushed by `vmagent` to remote storage when `-remoteWrite.maxDiskUsagePerURL` is set, then try increasing `-remoteWrite.queues`.
-  Such gaps may appear because `vmagent` cannot keep up with sending the collected data to remote storage, so it starts dropping the buffered data
+
+## Scraping big number of targets
+
+A single `vmagent` instance can scrape tens of thousands of scrape targets. Sometimes this isn't enough due to limitations on CPU, network, RAM, etc.
+In this case scrape targets can be split among multiple `vmagent` instances (aka `vmagent` horizontal scaling, sharding and clustering).
+Each `vmagent` instance in the cluster must use identical `-promscrape.config` files with distinct `-promscrape.cluster.memberNum` values.
+The flag value must be in the range `0 ... N-1`, where `N` is the number of `vmagent` instances in the cluster.
+The number of `vmagent` instances in the cluster must be passed to `-promscrape.cluster.membersCount` command-line flag. For example, the following commands
+spread scrape targets among a cluster of two `vmagent` instances:
+
+```
+/path/to/vmagent -promscrape.cluster.membersCount=2 -promscrape.cluster.memberNum=0 -promscrape.config=/path/to/config.yml ...
+/path/to/vmagent -promscrape.cluster.membersCount=2 -promscrape.cluster.memberNum=1 -promscrape.config=/path/to/config.yml ...
+```
+
+By default each scrape target is scraped only by a single `vmagent` instance in the cluster. If there is a need for replicating scrape targets among multiple `vmagent` instances,
+then `-promscrape.cluster.replicationFactor` command-line flag must be set to the desired number of replicas. For example, the following commands
+start a cluster of three `vmagent` instances, where each target is scraped by two `vmagent` instances:
+
+```
+/path/to/vmagent -promscrape.cluster.membersCount=3 -promscrape.cluster.replicationFactor=2 -promscrape.cluster.memberNum=0 -promscrape.config=/path/to/config.yml ...
+/path/to/vmagent -promscrape.cluster.membersCount=3 -promscrape.cluster.replicationFactor=2 -promscrape.cluster.memberNum=1 -promscrape.config=/path/to/config.yml ...
+/path/to/vmagent -promscrape.cluster.membersCount=3 -promscrape.cluster.replicationFactor=2 -promscrape.cluster.memberNum=2 -promscrape.config=/path/to/config.yml ...
+```
+
+If each target is scraped by multiple `vmagent` instances, then data deduplication must be enabled at remote storage pointed by `-remoteWrite.url`.
+See [these docs](https://docs.victoriametrics.com/#deduplication) for details.
+
+
+## Scraping targets via a proxy
+
+`vmagent` supports scraping targets via http, https and socks5 proxies. Proxy address must be specified in `proxy_url` option. For example, the following scrape config instructs
+target scraping via https proxy at `https://proxy-addr:1234`:
+
+```yml
+scrape_configs:
+- job_name: foo
+  proxy_url: https://proxy-addr:1234
+```
+
+Proxy can be configured with the following optional settings:
+
+* `proxy_authorization` for generic token authorization. See [Prometheus docs for details on authorization section](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#scrape_config)
+* `proxy_bearer_token` and `proxy_bearer_token_file` for Bearer token authorization
+* `proxy_basic_auth` for Basic authorization. See [these docs](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#scrape_config).
+* `proxy_tls_config` for TLS config. See [these docs](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#tls_config).
+
+For example:
+
+```yml
+scrape_configs:
+- job_name: foo
+  proxy_url: https://proxy-addr:1234
+  proxy_basic_auth:
+    username: foobar
+    password: secret
+  proxy_tls_config:
+    insecure_skip_verify: true
+    cert_file: /path/to/cert
+    key_file: /path/to/key
+    ca_file: /path/to/ca
+    server_name: real-server-name
+```
+
+## Cardinality limiter
+
+By default `vmagent` doesn't limit the number of time series written to remote storage systems specified at `-remoteWrite.url`. The limit can be enforced by setting the following command-line flags:
+
+* `-remoteWrite.maxHourlySeries` - limits the number of unique time series `vmagent` can write to remote storage systems during the last hour. Useful for limiting the number of active time series.
+* `-remoteWrite.maxDailySeries` - limits the number of unique time series `vmagent` can write to remote storage systems during the last day. Useful for limiting daily churn rate.
+
+Both limits can be set simultaneously. If any of these limits is reached, then samples for new time series are dropped instead of sending them to remote storage systems. A sample of dropped series is put in the log with `WARNING` level.
+
+The exceeded limits can be [monitored](#monitoring) with the following metrics:
+
+* `vmagent_hourly_series_limit_rows_dropped_total` - the number of metrics dropped due to exceeded hourly limit on the number of unique time series.
+* `vmagent_daily_series_limit_rows_dropped_total` - the number of metrics dropped due to exceeded daily limit on the number of unique time series.
+
+These limits are approximate, so `vmagent` can underflow/overflow the limit by a small percentage (usually less than 1%).
+
+
+## Monitoring
+
+`vmagent` exports various metrics in Prometheus exposition format at `http://vmagent-host:8429/metrics` page. We recommend setting up regular scraping of this page
+either through `vmagent` itself or by Prometheus so that the exported metrics may be analyzed later.
+Use official [Grafana dashboard](https://grafana.com/grafana/dashboards/12683) for `vmagent` state overview.
+If you have suggestions for improvements or have found a bug - please open an issue on github or add a review to the dashboard.
+
+`vmagent` also exports the status for various targets at the following handlers:
+
+* `http://vmagent-host:8429/targets`. This handler returns human-readable status for every active target.
+This page is easy to query from the command line with `wget`, `curl` or similar tools.
+It accepts optional `show_original_labels=1` query arg which shows the original labels per each target before applying the relabeling.
+This information may be useful for debugging target relabeling.
+* `http://vmagent-host:8429/api/v1/targets`. This handler returns data compatible with [the corresponding page from Prometheus API](https://prometheus.io/docs/prometheus/latest/querying/api/#targets).
+
+* `http://vmagent-host:8429/ready`. This handler returns http 200 status code when `vmagent` finishes it's initialization for all service_discovery configs.
+It may be useful to perform `vmagent` rolling update without any scrape loss.
+
+
+## Troubleshooting
+
+* We recommend you [set up the official Grafana dashboard](#monitoring) in order to monitor the state of `vmagent'.
+
+* We recommend you increase the maximum number of open files in the system (`ulimit -n`) when scraping a big number of targets,
+  as `vmagent` establishes at least a single TCP connection per target.
+
+* If `vmagent` uses too big amounts of memory, then the following options can help:
+  * Enabling stream parsing. See [these docs](#stream-parsing-mode).
+  * Reducing the number of output queues with `-remoteWrite.queues` command-line option.
+  * Reducing the amounts of RAM vmagent can use for in-memory buffering with `-memory.allowedPercent` or `-memory.allowedBytes` command-line option. Another option is to reduce memory limits in Docker and/or Kuberntes if `vmagent` runs under these systems.
+  * Reducing the number of CPU cores vmagent can use by passing `GOMAXPROCS=N` environment variable to `vmagent`, where `N` is the desired limit on CPU cores. Another option is to reduce CPU limits in Docker or Kubernetes if `vmagent` runs under these systems.
+
+* When `vmagent` scrapes many unreliable targets, it can flood the error log with scrape errors. These errors can be suppressed
+  by passing `-promscrape.suppressScrapeErrors` command-line flag to `vmagent`. The most recent scrape error per each target can be observed at `http://vmagent-host:8429/targets`
+  and `http://vmagent-host:8429/api/v1/targets`.
+
+* The `/api/v1/targets` page could be useful for debugging relabeling process for scrape targets.
+  This page contains original labels for targets dropped during relabeling (see "droppedTargets" section in the page output). By default the `-promscrape.maxDroppedTargets` targets are shown here. If your setup drops more targets during relabeling, then increase `-promscrape.maxDroppedTargets` command-line flag value to see all the dropped targets. Note that tracking each dropped target requires up to 10Kb of RAM. Therefore big values for `-promscrape.maxDroppedTargets` may result in increased memory usage if a big number of scrape targets are dropped during relabeling.
+
+* If `vmagent` scrapes a big number of targets then the `-promscrape.dropOriginalLabels` command-line option may be passed to `vmagent` in order to reduce memory usage.
+  This option drops `"discoveredLabels"` and `"droppedTargets"` lists at `/api/v1/targets` page, which may result in reduced debuggability for improperly configured per-target relabeling.
+
+* If `vmagent` scrapes targets with millions of metrics per target (for example, when scraping [federation endpoints](https://prometheus.io/docs/prometheus/latest/federation/)),
+  we recommend enabling [stream parsing mode](#stream-parsing-mode) in order to reduce memory usage during scraping.
+
+* We recommend you increase `-remoteWrite.queues` if `vmagent_remotewrite_pending_data_bytes` metric exported at `http://vmagent-host:8429/metrics` page grows constantly.
+
+* If you see gaps in the data pushed by `vmagent` to remote storage when `-remoteWrite.maxDiskUsagePerURL` is set, try increasing `-remoteWrite.queues`.
+  Such gaps may appear because `vmagent` cannot keep up with sending the collected data to remote storage. Therefore it starts dropping the buffered data
   if the on-disk buffer size exceeds `-remoteWrite.maxDiskUsagePerURL`.
 
-* `vmagent` buffers scraped data at `-remoteWrite.tmpDataPath` directory until it is sent to `-remoteWrite.url`.
+* `vmagent` drops data blocks if remote storage replies with `400 Bad Request` and `409 Conflict` HTTP responses. The number of dropped blocks can be monitored via `vmagent_remotewrite_packets_dropped_total` metric exported at [/metrics page](#monitoring).
+
+* Use `-remoteWrite.queues=1` when `-remoteWrite.url` points to remote storage, which doesn't accept out-of-order samples (aka data backfilling). Such storage systems include Prometheus, Cortex and Thanos.
+
+* `vmagent` buffers scraped data at the `-remoteWrite.tmpDataPath` directory until it is sent to `-remoteWrite.url`.
   The directory can grow large when remote storage is unavailable for extended periods of time and if `-remoteWrite.maxDiskUsagePerURL` isn't set.
-  If you don't want to send all the data from the directory to remote storage, simply stop `vmagent` and delete the directory.
+  If you don't want to send all the data from the directory to remote storage then simply stop `vmagent` and delete the directory.
 
 * By default `vmagent` masks `-remoteWrite.url` with `secret-url` values in logs and at `/metrics` page because
   the url may contain sensitive information such as auth tokens or passwords.
   Pass `-remoteWrite.showURL` command-line flag when starting `vmagent` in order to see all the valid urls.
 
-* If you see `skipping duplicate scrape target with identical labels` errors when scraping Kubernetes pods, then it is likely these pods listen multiple ports
-  or they use init container. These errors can be either fixed or suppressed with `-promscrape.suppressDuplicateScrapeTargetErrors` command-line flag.
-  See available options below if you prefer fixing the root cause of the error:
+* By default `vmagent` evenly spreads scrape load in time. If a particular scrape target must be scraped at the beginning of some interval,
+  then `scrape_align_interval` option  must be used. For example, the following config aligns hourly scrapes to the beginning of hour:
 
-  The following `relabel_configs` section may help determining `__meta_*` labels resulting in duplicate targets:
   ```yml
-  - action: labelmap
-    regex: __meta_(.*)
+  scrape_configs:
+  - job_name: foo
+    scrape_interval: 1h
+    scrape_align_interval: 1h
   ```
 
+* By default `vmagent` evenly spreads scrape load in time. If a particular scrape target must be scraped at specific offset, then `scrape_offset` option must be used.
+  For example, the following config instructs `vmagent` to scrape the target at 10 seconds of every minute:
+
+  ```yml
+  scrape_configs:
+  - job_name: foo
+    scrape_interval: 1m
+    scrape_offset: 10s
+  ```
+
+* If you see `skipping duplicate scrape target with identical labels` errors when scraping Kubernetes pods, then it is likely these pods listen to multiple ports
+  or they use an init container. These errors can either be fixed or suppressed with the `-promscrape.suppressDuplicateScrapeTargetErrors` command-line flag.
+  See the available options below if you prefer fixing the root cause of the error:
+
   The following relabeling rule may be added to `relabel_configs` section in order to filter out pods with unneeded ports:
   ```yml
   - action: keep_if_equal
@@ -313,27 +442,27 @@ It may be useful for performing `vmagent` rolling update without scrape loss.
   ```
 
 
-### How to build from sources
+## How to build from sources
 
-It is recommended using [binary releases](https://github.com/VictoriaMetrics/VictoriaMetrics/releases) - `vmagent` is located in `vmutils-*` archives there.
+We recommend using [binary releases](https://github.com/VictoriaMetrics/VictoriaMetrics/releases) - `vmagent` is located in the `vmutils-*` archives .
 
 
-#### Development build
+### Development build
 
-1. [Install Go](https://golang.org/doc/install). The minimum supported version is Go 1.13.
-2. Run `make vmagent` from the root folder of the repository.
-   It builds `vmagent` binary and puts it into the `bin` folder.
+1. [Install Go](https://golang.org/doc/install). The minimum supported version is Go 1.16.
+2. Run `make vmagent` from the root folder of [the repository](https://github.com/VictoriaMetrics/VictoriaMetrics).
+   It builds the `vmagent` binary and puts it into the `bin` folder.
 
-#### Production build
+### Production build
 
 1. [Install docker](https://docs.docker.com/install/).
-2. Run `make vmagent-prod` from the root folder of the repository.
+2. Run `make vmagent-prod` from the root folder of [the repository](https://github.com/VictoriaMetrics/VictoriaMetrics).
    It builds `vmagent-prod` binary and puts it into the `bin` folder.
 
-#### Building docker images
+### Building docker images
 
 Run `make package-vmagent`. It builds `victoriametrics/vmagent:<PKG_TAG>` docker image locally.
-`<PKG_TAG>` is auto-generated image tag, which depends on source code in the repository.
+`<PKG_TAG>` is an auto-generated image tag, which depends on source code in [the repository](https://github.com/VictoriaMetrics/VictoriaMetrics).
 The `<PKG_TAG>` may be manually set via `PKG_TAG=foobar make package-vmagent`.
 
 The base docker image is [alpine](https://hub.docker.com/_/alpine) but it is possible to use any other base image
@@ -343,34 +472,34 @@ by setting it via `<ROOT_IMAGE>` environment variable. For example, the followin
 ROOT_IMAGE=scratch make package-vmagent
 ```
 
-#### ARM build
+### ARM build
 
 ARM build may run on Raspberry Pi or on [energy-efficient ARM servers](https://blog.cloudflare.com/arm-takes-wing/).
 
-#### Development ARM build
+### Development ARM build
 
-1. [Install Go](https://golang.org/doc/install). The minimum supported version is Go 1.13.
-2. Run `make vmagent-arm` or `make vmagent-arm64` from the root folder of the repository.
+1. [Install Go](https://golang.org/doc/install). The minimum supported version is Go 1.16.
+2. Run `make vmagent-arm` or `make vmagent-arm64` from the root folder of [the repository](https://github.com/VictoriaMetrics/VictoriaMetrics)
    It builds `vmagent-arm` or `vmagent-arm64` binary respectively and puts it into the `bin` folder.
 
-#### Production ARM build
+### Production ARM build
 
 1. [Install docker](https://docs.docker.com/install/).
-2. Run `make vmagent-arm-prod` or `make vmagent-arm64-prod` from the root folder of the repository.
+2. Run `make vmagent-arm-prod` or `make vmagent-arm64-prod` from the root folder of [the repository](https://github.com/VictoriaMetrics/VictoriaMetrics).
    It builds `vmagent-arm-prod` or `vmagent-arm64-prod` binary respectively and puts it into the `bin` folder.
 
 
-### Profiling
+## Profiling
 
 `vmagent` provides handlers for collecting the following [Go profiles](https://blog.golang.org/profiling-go-programs):
 
-* Memory profile. It can be collected with the following command:
+* Memory profile can be collected with the following command:
 
 ```bash
 curl -s http://<vmagent-host>:8429/debug/pprof/heap > mem.pprof
 ```
 
-* CPU profile. It can be collected with the following command:
+* CPU profile can be collected with the following command:
 
 ```bash
 curl -s http://<vmagent-host>:8429/debug/pprof/profile > cpu.pprof
@@ -379,3 +508,276 @@ curl -s http://<vmagent-host>:8429/debug/pprof/profile > cpu.pprof
 The command for collecting CPU profile waits for 30 seconds before returning.
 
 The collected profiles may be analyzed with [go tool pprof](https://github.com/google/pprof).
+
+
+## Advanced usage
+
+`vmagent` can be fine-tuned with various command-line flags. Run `./vmagent -help` in order to see the full list of these flags with their desciptions and default values:
+
+```
+./vmagent -help
+
+vmagent collects metrics data via popular data ingestion protocols and routes them to VictoriaMetrics.
+
+See the docs at https://docs.victoriametrics.com/vmagent.html .
+
+  -csvTrimTimestamp duration
+    	Trim timestamps when importing csv data to this duration. Minimum practical duration is 1ms. Higher duration (i.e. 1s) may be used for reducing disk space usage for timestamp data (default 1ms)
+  -dryRun
+    	Whether to check only config files without running vmagent. The following files are checked: -promscrape.config, -remoteWrite.relabelConfig, -remoteWrite.urlRelabelConfig . Unknown config entries are allowed in -promscrape.config by default. This can be changed with -promscrape.config.strictParse
+  -enableTCP6
+    	Whether to enable IPv6 for listening and dialing. By default only IPv4 TCP and UDP is used
+  -envflag.enable
+    	Whether to enable reading flags from environment variables additionally to command line. Command line flag values have priority over values from environment vars. Flags are read only from command line if this flag isn't set
+  -envflag.prefix string
+    	Prefix for environment variables if -envflag.enable is set
+  -fs.disableMmap
+    	Whether to use pread() instead of mmap() for reading data files. By default mmap() is used for 64-bit arches and pread() is used for 32-bit arches, since they cannot read data files bigger than 2^32 bytes in memory. mmap() is usually faster for reading small data chunks than pread()
+  -graphiteListenAddr string
+    	TCP and UDP address to listen for Graphite plaintext data. Usually :2003 must be set. Doesn't work if empty
+  -graphiteTrimTimestamp duration
+    	Trim timestamps for Graphite data to this duration. Minimum practical duration is 1s. Higher duration (i.e. 1m) may be used for reducing disk space usage for timestamp data (default 1s)
+  -http.connTimeout duration
+    	Incoming http connections are closed after the configured timeout. This may help to spread the incoming load among a cluster of services behind a load balancer. Please note that the real timeout may be bigger by up to 10% as a protection against the thundering herd problem (default 2m0s)
+  -http.disableResponseCompression
+    	Disable compression of HTTP responses to save CPU resources. By default compression is enabled to save network bandwidth
+  -http.idleConnTimeout duration
+    	Timeout for incoming idle http connections (default 1m0s)
+  -http.maxGracefulShutdownDuration duration
+    	The maximum duration for a graceful shutdown of the HTTP server. A highly loaded server may require increased value for a graceful shutdown (default 7s)
+  -http.pathPrefix string
+    	An optional prefix to add to all the paths handled by http server. For example, if '-http.pathPrefix=/foo/bar' is set, then all the http requests will be handled on '/foo/bar/*' paths. This may be useful for proxied requests. See https://www.robustperception.io/using-external-urls-and-proxies-with-prometheus
+  -http.shutdownDelay duration
+    	Optional delay before http server shutdown. During this delay, the server returns non-OK responses from /health page, so load balancers can route new requests to other servers
+  -httpAuth.password string
+    	Password for HTTP Basic Auth. The authentication is disabled if -httpAuth.username is empty
+  -httpAuth.username string
+    	Username for HTTP Basic Auth. The authentication is disabled if empty. See also -httpAuth.password
+  -httpListenAddr string
+    	TCP address to listen for http connections. Set this flag to empty value in order to disable listening on any port. This mode may be useful for running multiple vmagent instances on the same server. Note that /targets and /metrics pages aren't available if -httpListenAddr='' (default ":8429")
+  -import.maxLineLen size
+    	The maximum length in bytes of a single line accepted by /api/v1/import; the line length can be limited with 'max_rows_per_line' query arg passed to /api/v1/export
+    	Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 104857600)
+  -influx.databaseNames array
+    	Comma-separated list of database names to return from /query and /influx/query API. This can be needed for accepting data from Telegraf plugins such as https://github.com/fangli/fluent-plugin-influxdb
+    	Supports an array of values separated by comma or specified via multiple flags.
+  -influx.maxLineSize size
+    	The maximum size in bytes for a single Influx line during parsing
+    	Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 262144)
+  -influxListenAddr string
+    	TCP and UDP address to listen for Influx line protocol data. Usually :8189 must be set. Doesn't work if empty. This flag isn't needed when ingesting data over HTTP - just send it to http://<vmagent>:8429/write
+  -influxMeasurementFieldSeparator string
+    	Separator for '{measurement}{separator}{field_name}' metric name when inserted via Influx line protocol (default "_")
+  -influxSkipMeasurement
+    	Uses '{field_name}' as a metric name while ignoring '{measurement}' and '-influxMeasurementFieldSeparator'
+  -influxSkipSingleField
+    	Uses '{measurement}' instead of '{measurement}{separator}{field_name}' for metic name if Influx line contains only a single field
+  -influxTrimTimestamp duration
+    	Trim timestamps for Influx line protocol data to this duration. Minimum practical duration is 1ms. Higher duration (i.e. 1s) may be used for reducing disk space usage for timestamp data (default 1ms)
+  -insert.maxQueueDuration duration
+    	The maximum duration for waiting in the queue for insert requests due to -maxConcurrentInserts (default 1m0s)
+  -loggerDisableTimestamps
+    	Whether to disable writing timestamps in logs
+  -loggerErrorsPerSecondLimit int
+    	Per-second limit on the number of ERROR messages. If more than the given number of errors are emitted per second, the remaining errors are suppressed. Zero values disable the rate limit
+  -loggerFormat string
+    	Format for logs. Possible values: default, json (default "default")
+  -loggerLevel string
+    	Minimum level of errors to log. Possible values: INFO, WARN, ERROR, FATAL, PANIC (default "INFO")
+  -loggerOutput string
+    	Output for the logs. Supported values: stderr, stdout (default "stderr")
+  -loggerTimezone string
+    	Timezone to use for timestamps in logs. Timezone must be a valid IANA Time Zone. For example: America/New_York, Europe/Berlin, Etc/GMT+3 or Local (default "UTC")
+  -loggerWarnsPerSecondLimit int
+    	Per-second limit on the number of WARN messages. If more than the given number of warns are emitted per second, then the remaining warns are suppressed. Zero values disable the rate limit
+  -maxConcurrentInserts int
+    	The maximum number of concurrent inserts. Default value should work for most cases, since it minimizes the overhead for concurrent inserts. This option is tigthly coupled with -insert.maxQueueDuration (default 16)
+  -maxInsertRequestSize size
+    	The maximum size in bytes of a single Prometheus remote_write API request
+    	Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 33554432)
+  -memory.allowedBytes size
+    	Allowed size of system memory VictoriaMetrics caches may occupy. This option overrides -memory.allowedPercent if set to a non-zero value. Too low a value may increase the cache miss rate usually resulting in higher CPU and disk IO usage. Too high a value may evict too much data from OS page cache resulting in higher disk IO usage
+    	Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 0)
+  -memory.allowedPercent float
+    	Allowed percent of system memory VictoriaMetrics caches may occupy. See also -memory.allowedBytes. Too low a value may increase cache miss rate usually resulting in higher CPU and disk IO usage. Too high a value may evict too much data from OS page cache which will result in higher disk IO usage (default 60)
+  -metricsAuthKey string
+    	Auth key for /metrics. It overrides httpAuth settings
+  -opentsdbHTTPListenAddr string
+    	TCP address to listen for OpentTSDB HTTP put requests. Usually :4242 must be set. Doesn't work if empty
+  -opentsdbListenAddr string
+    	TCP and UDP address to listen for OpentTSDB metrics. Telnet put messages and HTTP /api/put messages are simultaneously served on TCP port. Usually :4242 must be set. Doesn't work if empty
+  -opentsdbTrimTimestamp duration
+    	Trim timestamps for OpenTSDB 'telnet put' data to this duration. Minimum practical duration is 1s. Higher duration (i.e. 1m) may be used for reducing disk space usage for timestamp data (default 1s)
+  -opentsdbhttp.maxInsertRequestSize size
+    	The maximum size of OpenTSDB HTTP put request
+    	Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 33554432)
+  -opentsdbhttpTrimTimestamp duration
+    	Trim timestamps for OpenTSDB HTTP data to this duration. Minimum practical duration is 1ms. Higher duration (i.e. 1s) may be used for reducing disk space usage for timestamp data (default 1ms)
+  -pprofAuthKey string
+    	Auth key for /debug/pprof. It overrides httpAuth settings
+  -promscrape.cluster.memberNum int
+    	The number of number in the cluster of scrapers. It must be an unique value in the range 0 ... promscrape.cluster.membersCount-1 across scrapers in the cluster
+  -promscrape.cluster.membersCount int
+    	The number of members in a cluster of scrapers. Each member must have an unique -promscrape.cluster.memberNum in the range 0 ... promscrape.cluster.membersCount-1 . Each member then scrapes roughly 1/N of all the targets. By default cluster scraping is disabled, i.e. a single scraper scrapes all the targets
+  -promscrape.cluster.replicationFactor int
+    	The number of members in the cluster, which scrape the same targets. If the replication factor is greater than 2, then the deduplication must be enabled at remote storage side. See https://docs.victoriametrics.com/#deduplication (default 1)
+  -promscrape.config string
+    	Optional path to Prometheus config file with 'scrape_configs' section containing targets to scrape. See https://docs.victoriametrics.com/#how-to-scrape-prometheus-exporters-such-as-node-exporter for details
+  -promscrape.config.dryRun
+    	Checks -promscrape.config file for errors and unsupported fields and then exits. Returns non-zero exit code on parsing errors and emits these errors to stderr. See also -promscrape.config.strictParse command-line flag. Pass -loggerLevel=ERROR if you don't need to see info messages in the output.
+  -promscrape.config.strictParse
+    	Whether to allow only supported fields in -promscrape.config . By default unsupported fields are silently skipped
+  -promscrape.configCheckInterval duration
+    	Interval for checking for changes in '-promscrape.config' file. By default the checking is disabled. Send SIGHUP signal in order to force config check for changes
+  -promscrape.consul.waitTime duration
+    	Wait time used by Consul service discovery. Default value is used if not set
+  -promscrape.consulSDCheckInterval duration
+    	Interval for checking for changes in Consul. This works only if consul_sd_configs is configured in '-promscrape.config' file. See https://prometheus.io/docs/prometheus/latest/configuration/configuration/#consul_sd_config for details (default 30s)
+  -promscrape.digitaloceanSDCheckInterval duration
+        Interval for checking for changes in digital ocean. This works only if digitalocean_sd_configs is configured in '-promscrape.config' file. See https://prometheus.io/docs/prometheus/latest/configuration/configuration/#digitalocean_sd_config for details (default 1m0s)    	
+  -promscrape.disableCompression
+    	Whether to disable sending 'Accept-Encoding: gzip' request headers to all the scrape targets. This may reduce CPU usage on scrape targets at the cost of higher network bandwidth utilization. It is possible to set 'disable_compression: true' individually per each 'scrape_config' section in '-promscrape.config' for fine grained control
+  -promscrape.disableKeepAlive
+    	Whether to disable HTTP keep-alive connections when scraping all the targets. This may be useful when targets has no support for HTTP keep-alive connection. It is possible to set 'disable_keepalive: true' individually per each 'scrape_config' section in '-promscrape.config' for fine grained control. Note that disabling HTTP keep-alive may increase load on both vmagent and scrape targets
+  -promscrape.discovery.concurrency int
+    	The maximum number of concurrent requests to Prometheus autodiscovery API (Consul, Kubernetes, etc.) (default 100)
+  -promscrape.discovery.concurrentWaitTime duration
+    	The maximum duration for waiting to perform API requests if more than -promscrape.discovery.concurrency requests are simultaneously performed (default 1m0s)
+  -promscrape.dnsSDCheckInterval duration
+    	Interval for checking for changes in dns. This works only if dns_sd_configs is configured in '-promscrape.config' file. See https://prometheus.io/docs/prometheus/latest/configuration/configuration/#dns_sd_config for details (default 30s)
+  -promscrape.dockerswarmSDCheckInterval duration
+    	Interval for checking for changes in dockerswarm. This works only if dockerswarm_sd_configs is configured in '-promscrape.config' file. See https://prometheus.io/docs/prometheus/latest/configuration/configuration/#dockerswarm_sd_config for details (default 30s)
+  -promscrape.dropOriginalLabels
+    	Whether to drop original labels for scrape targets at /targets and /api/v1/targets pages. This may be needed for reducing memory usage when original labels for big number of scrape targets occupy big amounts of memory. Note that this reduces debuggability for improper per-target relabeling configs
+  -promscrape.ec2SDCheckInterval duration
+    	Interval for checking for changes in ec2. This works only if ec2_sd_configs is configured in '-promscrape.config' file. See https://prometheus.io/docs/prometheus/latest/configuration/configuration/#ec2_sd_config for details (default 1m0s)
+  -promscrape.eurekaSDCheckInterval duration
+    	Interval for checking for changes in eureka. This works only if eureka_sd_configs is configured in '-promscrape.config' file. See https://prometheus.io/docs/prometheus/latest/configuration/configuration/#eureka_sd_config for details (default 30s)
+  -promscrape.fileSDCheckInterval duration
+    	Interval for checking for changes in 'file_sd_config'. See https://prometheus.io/docs/prometheus/latest/configuration/configuration/#file_sd_config for details (default 30s)
+  -promscrape.gceSDCheckInterval duration
+    	Interval for checking for changes in gce. This works only if gce_sd_configs is configured in '-promscrape.config' file. See https://prometheus.io/docs/prometheus/latest/configuration/configuration/#gce_sd_config for details (default 1m0s)
+  -promscrape.httpSDCheckInterval duration
+        Interval for checking for changes in http service discovery. This works only if http_sd_configs is configured in '-promscrape.config' file. See https://prometheus.io/docs/prometheus/latest/configuration/configuration/#http_sd_config for details (default 1m0s)    	   	
+  -promscrape.kubernetes.apiServerTimeout duration
+    	How frequently to reload the full state from Kuberntes API server (default 30m0s)
+  -promscrape.kubernetesSDCheckInterval duration
+    	Interval for checking for changes in Kubernetes API server. This works only if kubernetes_sd_configs is configured in '-promscrape.config' file. See https://prometheus.io/docs/prometheus/latest/configuration/configuration/#kubernetes_sd_config for details (default 30s)
+  -promscrape.maxDroppedTargets int
+    	The maximum number of droppedTargets to show at /api/v1/targets page. Increase this value if your setup drops more scrape targets during relabeling and you need investigating labels for all the dropped targets. Note that the increased number of tracked dropped targets may result in increased memory usage (default 1000)
+  -promscrape.maxScrapeSize size
+    	The maximum size of scrape response in bytes to process from Prometheus targets. Bigger responses are rejected
+    	Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 16777216)
+  -promscrape.openstackSDCheckInterval duration
+    	Interval for checking for changes in openstack API server. This works only if openstack_sd_configs is configured in '-promscrape.config' file. See https://prometheus.io/docs/prometheus/latest/configuration/configuration/#openstack_sd_config for details (default 30s)
+  -promscrape.streamParse
+    	Whether to enable stream parsing for metrics obtained from scrape targets. This may be useful for reducing memory usage when millions of metrics are exposed per each scrape target. It is posible to set 'stream_parse: true' individually per each 'scrape_config' section in '-promscrape.config' for fine grained control
+  -promscrape.suppressDuplicateScrapeTargetErrors
+    	Whether to suppress 'duplicate scrape target' errors; see https://docs.victoriametrics.com/vmagent.html#troubleshooting for details
+  -promscrape.suppressScrapeErrors
+    	Whether to suppress scrape errors logging. The last error for each target is always available at '/targets' page even if scrape errors logging is suppressed
+  -remoteWrite.basicAuth.password array
+    	Optional basic auth password to use for -remoteWrite.url. If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url
+    	Supports an array of values separated by comma or specified via multiple flags.
+  -remoteWrite.basicAuth.passwordFile array
+    	Optional path to basic auth password to use for -remoteWrite.url. The file is re-read every second. If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url
+    	Supports an array of values separated by comma or specified via multiple flags.
+  -remoteWrite.basicAuth.username array
+    	Optional basic auth username to use for -remoteWrite.url. If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url
+    	Supports an array of values separated by comma or specified via multiple flags.
+  -remoteWrite.bearerToken array
+    	Optional bearer auth token to use for -remoteWrite.url. If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url
+    	Supports an array of values separated by comma or specified via multiple flags.
+  -remoteWrite.bearerTokenFile array
+    	Optional path to bearer token file to use for -remoteWrite.url. The token is re-read from the file every second. If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url
+    	Supports an array of values separated by comma or specified via multiple flags.
+  -remoteWrite.flushInterval duration
+    	Interval for flushing the data to remote storage. This option takes effect only when less than 10K data points per second are pushed to -remoteWrite.url (default 1s)
+  -remoteWrite.label array
+    	Optional label in the form 'name=value' to add to all the metrics before sending them to -remoteWrite.url. Pass multiple -remoteWrite.label flags in order to add multiple labels to metrics before sending them to remote storage
+    	Supports an array of values separated by comma or specified via multiple flags.
+  -remoteWrite.maxBlockSize size
+    	The maximum size in bytes of unpacked request to send to remote storage. It shouldn't exceed -maxInsertRequestSize from VictoriaMetrics
+    	Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 8388608)
+  -remoteWrite.maxDailySeries int
+    	The maximum number of unique series vmagent can send to remote storage systems during the last 24 hours. Excess series are logged and dropped. This can be useful for limiting series churn rate. See also -remoteWrite.maxHourlySeries
+  -remoteWrite.maxDiskUsagePerURL size
+    	The maximum file-based buffer size in bytes at -remoteWrite.tmpDataPath for each -remoteWrite.url. When buffer size reaches the configured maximum, then old data is dropped when adding new data to the buffer. Buffered data is stored in ~500MB chunks, so the minimum practical value for this flag is 500000000. Disk usage is unlimited if the value is set to 0
+    	Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 0)
+  -remoteWrite.maxHourlySeries int
+    	The maximum number of unique series vmagent can send to remote storage systems during the last hour. Excess series are logged and dropped. This can be useful for limiting series cardinality. See also -remoteWrite.maxDailySeries
+  -remoteWrite.oauth2.clientID array
+    	Optional OAuth2 clientID to use for -remoteWrite.url. If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url
+    	Supports an array of values separated by comma or specified via multiple flags.
+  -remoteWrite.oauth2.clientSecret array
+    	Optional OAuth2 clientSecret to use for -remoteWrite.url. If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url
+    	Supports an array of values separated by comma or specified via multiple flags.
+  -remoteWrite.oauth2.clientSecretFile array
+    	Optional OAuth2 clientSecretFile to use for -remoteWrite.url. If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url
+    	Supports an array of values separated by comma or specified via multiple flags.
+  -remoteWrite.oauth2.scopes array
+    	Optional OAuth2 scopes to use for -remoteWrite.url. Scopes must be delimited by ';'. If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url
+    	Supports an array of values separated by comma or specified via multiple flags.
+  -remoteWrite.oauth2.tokenUrl array
+    	Optional OAuth2 tokenURL to use for -remoteWrite.url. If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url
+    	Supports an array of values separated by comma or specified via multiple flags.
+  -remoteWrite.proxyURL array
+    	Optional proxy URL for writing data to -remoteWrite.url. Supported proxies: http, https, socks5. Example: -remoteWrite.proxyURL=socks5://proxy:1234
+    	Supports an array of values separated by comma or specified via multiple flags.
+  -remoteWrite.queues int
+    	The number of concurrent queues to each -remoteWrite.url. Set more queues if default number of queues isn't enough for sending high volume of collected data to remote storage (default 2 * numberOfAvailableCPUs)
+  -remoteWrite.rateLimit array
+    	Optional rate limit in bytes per second for data sent to -remoteWrite.url. By default the rate limit is disabled. It can be useful for limiting load on remote storage when big amounts of buffered data is sent after temporary unavailability of the remote storage
+    	Supports array of values separated by comma or specified via multiple flags.
+  -remoteWrite.relabelConfig string
+    	Optional path to file with relabel_config entries. These entries are applied to all the metrics before sending them to -remoteWrite.url. See https://docs.victoriametrics.com/vmagent.html#relabeling for details
+  -remoteWrite.relabelDebug
+    	Whether to log metrics before and after relabeling with -remoteWrite.relabelConfig. If the -remoteWrite.relabelDebug is enabled, then the metrics aren't sent to remote storage. This is useful for debugging the relabeling configs
+  -remoteWrite.roundDigits array
+    	Round metric values to this number of decimal digits after the point before writing them to remote storage. Examples: -remoteWrite.roundDigits=2 would round 1.236 to 1.24, while -remoteWrite.roundDigits=-1 would round 126.78 to 130. By default digits rounding is disabled. Set it to 100 for disabling it for a particular remote storage. This option may be used for improving data compression for the stored metrics
+    	Supports array of values separated by comma or specified via multiple flags.
+  -remoteWrite.sendTimeout array
+    	Timeout for sending a single block of data to -remoteWrite.url
+    	Supports array of values separated by comma or specified via multiple flags.
+  -remoteWrite.showURL
+    	Whether to show -remoteWrite.url in the exported metrics. It is hidden by default, since it can contain sensitive info such as auth key
+  -remoteWrite.significantFigures array
+    	The number of significant figures to leave in metric values before writing them to remote storage. See https://en.wikipedia.org/wiki/Significant_figures . Zero value saves all the significant figures. This option may be used for improving data compression for the stored metrics. See also -remoteWrite.roundDigits
+    	Supports array of values separated by comma or specified via multiple flags.
+  -remoteWrite.tlsCAFile array
+    	Optional path to TLS CA file to use for verifying connections to -remoteWrite.url. By default system CA is used. If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url
+    	Supports an array of values separated by comma or specified via multiple flags.
+  -remoteWrite.tlsCertFile array
+    	Optional path to client-side TLS certificate file to use when connecting to -remoteWrite.url. If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url
+    	Supports an array of values separated by comma or specified via multiple flags.
+  -remoteWrite.tlsInsecureSkipVerify array
+    	Whether to skip tls verification when connecting to -remoteWrite.url
+    	Supports array of values separated by comma or specified via multiple flags.
+  -remoteWrite.tlsKeyFile array
+    	Optional path to client-side TLS certificate key to use when connecting to -remoteWrite.url. If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url
+    	Supports an array of values separated by comma or specified via multiple flags.
+  -remoteWrite.tlsServerName array
+    	Optional TLS server name to use for connections to -remoteWrite.url. By default the server name from -remoteWrite.url is used. If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url
+    	Supports an array of values separated by comma or specified via multiple flags.
+  -remoteWrite.tmpDataPath string
+    	Path to directory where temporary data for remote write component is stored. See also -remoteWrite.maxDiskUsagePerURL (default "vmagent-remotewrite-data")
+  -remoteWrite.url array
+    	Remote storage URL to write data to. It must support Prometheus remote_write API. It is recommended using VictoriaMetrics as remote storage. Example url: http://<victoriametrics-host>:8428/api/v1/write . Pass multiple -remoteWrite.url flags in order to write data concurrently to multiple remote storage systems
+    	Supports an array of values separated by comma or specified via multiple flags.
+  -remoteWrite.urlRelabelConfig array
+    	Optional path to relabel config for the corresponding -remoteWrite.url
+    	Supports an array of values separated by comma or specified via multiple flags.
+  -remoteWrite.urlRelabelDebug array
+    	Whether to log metrics before and after relabeling with -remoteWrite.urlRelabelConfig. If the -remoteWrite.urlRelabelDebug is enabled, then the metrics aren't sent to the corresponding -remoteWrite.url. This is useful for debugging the relabeling configs
+    	Supports array of values separated by comma or specified via multiple flags.
+  -sortLabels
+    	Whether to sort labels for incoming samples before writing them to all the configured remote storage systems. This may be needed for reducing memory usage at remote storage when the order of labels in incoming samples is random. For example, if m{k1="v1",k2="v2"} may be sent as m{k2="v2",k1="v1"}Enabled sorting for labels can slow down ingestion performance a bit
+  -tls
+    	Whether to enable TLS (aka HTTPS) for incoming requests. -tlsCertFile and -tlsKeyFile must be set if -tls is set
+  -tlsCertFile string
+    	Path to file with TLS certificate. Used only if -tls is set. Prefer ECDSA certs instead of RSA certs as RSA certs are slower
+  -tlsKeyFile string
+    	Path to file with TLS key. Used only if -tls is set
+  -version
+    	Show VictoriaMetrics version
+```

app/vmagent/common/push_ctx.go

@@ -1,9 +1,9 @@
 package common
 
 import (
-	"runtime"
 	"sync"
 
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/cgroup"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
 )
@@ -63,4 +63,4 @@ func PutPushCtx(ctx *PushCtx) {
 }
 
 var pushCtxPool sync.Pool
-var pushCtxPoolCh = make(chan *PushCtx, runtime.GOMAXPROCS(-1))
+var pushCtxPoolCh = make(chan *PushCtx, cgroup.AvailableCPUs())

app/vmagent/influx/request_handler.go

@@ -4,14 +4,15 @@ import (
 	"flag"
 	"io"
 	"net/http"
-	"runtime"
 	"sync"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/common"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/cgroup"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
+	parserCommon "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
 	parser "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/influx"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
 	"github.com/VictoriaMetrics/metrics"
@@ -33,7 +34,9 @@ var (
 // See https://github.com/influxdata/telegraf/tree/master/plugins/inputs/socket_listener/
 func InsertHandlerForReader(r io.Reader) error {
 	return writeconcurrencylimiter.Do(func() error {
-		return parser.ParseStream(r, false, "", "", insertRows)
+		return parser.ParseStream(r, false, "", "", func(db string, rows []parser.Row) error {
+			return insertRows(db, rows, nil)
+		})
 	})
 }
 
@@ -41,17 +44,23 @@ func InsertHandlerForReader(r io.Reader) error {
 //
 // See https://github.com/influxdata/influxdb/blob/4cbdc197b8117fee648d62e2e5be75c6575352f0/tsdb/README.md
 func InsertHandlerForHTTP(req *http.Request) error {
+	extraLabels, err := parserCommon.GetExtraLabels(req)
+	if err != nil {
+		return err
+	}
 	return writeconcurrencylimiter.Do(func() error {
 		isGzipped := req.Header.Get("Content-Encoding") == "gzip"
 		q := req.URL.Query()
 		precision := q.Get("precision")
 		// Read db tag from https://docs.influxdata.com/influxdb/v1.7/tools/api/#write-http-endpoint
 		db := q.Get("db")
-		return parser.ParseStream(req.Body, isGzipped, precision, db, insertRows)
+		return parser.ParseStream(req.Body, isGzipped, precision, db, func(db string, rows []parser.Row) error {
+			return insertRows(db, rows, extraLabels)
+		})
 	})
 }
 
-func insertRows(db string, rows []parser.Row) error {
+func insertRows(db string, rows []parser.Row, extraLabels []prompbmarshal.Label) error {
 	ctx := getPushCtx()
 	defer putPushCtx(ctx)
 
@@ -82,11 +91,13 @@ func insertRows(db string, rows []parser.Row) error {
 				Value: db,
 			})
 		}
+		commonLabels = append(commonLabels, extraLabels...)
 		ctx.metricGroupBuf = ctx.metricGroupBuf[:0]
 		if !*skipMeasurement {
 			ctx.metricGroupBuf = append(ctx.metricGroupBuf, r.Measurement...)
 		}
-		skipFieldKey := len(r.Fields) == 1 && *skipSingleField
+		// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1139
+		skipFieldKey := len(r.Measurement) > 0 && len(r.Fields) == 1 && *skipSingleField
 		if len(ctx.metricGroupBuf) > 0 && !skipFieldKey {
 			ctx.metricGroupBuf = append(ctx.metricGroupBuf, *measurementFieldSeparator...)
 		}
@@ -165,4 +176,4 @@ func putPushCtx(ctx *pushCtx) {
 }
 
 var pushCtxPool sync.Pool
-var pushCtxPoolCh = make(chan *pushCtx, runtime.GOMAXPROCS(-1))
+var pushCtxPoolCh = make(chan *pushCtx, cgroup.AvailableCPUs())

app/vmagent/main.go

@@ -5,7 +5,6 @@ import (
 	"fmt"
 	"net/http"
 	"os"
-	"strconv"
 	"strings"
 	"sync/atomic"
 	"time"
@@ -21,9 +20,10 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/vmimport"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/buildinfo"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/cgroup"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/envflag"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/influxutils"
 	graphiteserver "github.com/VictoriaMetrics/VictoriaMetrics/lib/ingestserver/graphite"
 	influxserver "github.com/VictoriaMetrics/VictoriaMetrics/lib/ingestserver/influx"
 	opentsdbserver "github.com/VictoriaMetrics/VictoriaMetrics/lib/ingestserver/opentsdb"
@@ -41,14 +41,15 @@ var (
 		"Set this flag to empty value in order to disable listening on any port. This mode may be useful for running multiple vmagent instances on the same server. "+
 		"Note that /targets and /metrics pages aren't available if -httpListenAddr=''")
 	influxListenAddr = flag.String("influxListenAddr", "", "TCP and UDP address to listen for Influx line protocol data. Usually :8189 must be set. Doesn't work if empty. "+
-		"This flag isn't needed when ingesting data over HTTP - just send it to `http://<vmagent>:8429/write`")
+		"This flag isn't needed when ingesting data over HTTP - just send it to http://<vmagent>:8429/write")
 	graphiteListenAddr = flag.String("graphiteListenAddr", "", "TCP and UDP address to listen for Graphite plaintext data. Usually :2003 must be set. Doesn't work if empty")
 	opentsdbListenAddr = flag.String("opentsdbListenAddr", "", "TCP and UDP address to listen for OpentTSDB metrics. "+
 		"Telnet put messages and HTTP /api/put messages are simultaneously served on TCP port. "+
 		"Usually :4242 must be set. Doesn't work if empty")
 	opentsdbHTTPListenAddr = flag.String("opentsdbHTTPListenAddr", "", "TCP address to listen for OpentTSDB HTTP put requests. Usually :4242 must be set. Doesn't work if empty")
 	dryRun                 = flag.Bool("dryRun", false, "Whether to check only config files without running vmagent. The following files are checked: "+
-		"-promscrape.config, -remoteWrite.relabelConfig, -remoteWrite.urlRelabelConfig . See also -promscrape.config.dryRun")
+		"-promscrape.config, -remoteWrite.relabelConfig, -remoteWrite.urlRelabelConfig . "+
+		"Unknown config entries are allowed in -promscrape.config by default. This can be changed with -promscrape.config.strictParse")
 )
 
 var (
@@ -66,17 +67,20 @@ func main() {
 	remotewrite.InitSecretFlags()
 	buildinfo.Init()
 	logger.Init()
-	cgroup.UpdateGOMAXPROCSToCPUQuota()
 
-	if *dryRun {
-		if err := flag.Set("promscrape.config.strictParse", "true"); err != nil {
-			logger.Panicf("BUG: cannot set promscrape.config.strictParse=true: %s", err)
+	if promscrape.IsDryRun() {
+		if err := promscrape.CheckConfig(); err != nil {
+			logger.Fatalf("error when checking -promscrape.config: %s", err)
 		}
+		logger.Infof("-promscrape.config is ok; exitting with 0 status code")
+		return
+	}
+	if *dryRun {
 		if err := remotewrite.CheckRelabelConfigs(); err != nil {
 			logger.Fatalf("error when checking relabel configs: %s", err)
 		}
 		if err := promscrape.CheckConfig(); err != nil {
-			logger.Fatalf("error when checking Prometheus config: %s", err)
+			logger.Fatalf("error when checking -promscrape.config: %s", err)
 		}
 		logger.Infof("all the configs are ok; exitting with 0 status code")
 		return
@@ -140,8 +144,19 @@ func main() {
 }
 
 func requestHandler(w http.ResponseWriter, r *http.Request) bool {
-	if r.RequestURI == "/" {
-		fmt.Fprintf(w, "vmagent - see docs at https://victoriametrics.github.io/vmagent.html")
+	if r.URL.Path == "/" {
+		if r.Method != "GET" {
+			return false
+		}
+		fmt.Fprintf(w, "<h2>vmagent</h2>")
+		fmt.Fprintf(w, "See docs at <a href='https://docs.victoriametrics.com/vmagent.html'>https://docs.victoriametrics.com/vmagent.html</a></br>")
+		fmt.Fprintf(w, "Useful endpoints:</br>")
+		httpserver.WriteAPIHelp(w, [][2]string{
+			{"/targets", "discovered targets list"},
+			{"/api/v1/targets", "advanced information about discovered targets in JSON format"},
+			{"/metrics", "available service metrics"},
+			{"/-/reload", "reload configuration"},
+		})
 		return true
 	}
 	path := strings.Replace(r.URL.Path, "//", "/", -1)
@@ -150,7 +165,7 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 		prometheusWriteRequests.Inc()
 		if err := promremotewrite.InsertHandler(r); err != nil {
 			prometheusWriteErrors.Inc()
-			httpserver.Errorf(w, r, "error in %q: %s", r.URL.Path, err)
+			httpserver.Errorf(w, r, "%s", err)
 			return true
 		}
 		w.WriteHeader(http.StatusNoContent)
@@ -159,7 +174,7 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 		vmimportRequests.Inc()
 		if err := vmimport.InsertHandler(r); err != nil {
 			vmimportErrors.Inc()
-			httpserver.Errorf(w, r, "error in %q: %s", r.URL.Path, err)
+			httpserver.Errorf(w, r, "%s", err)
 			return true
 		}
 		w.WriteHeader(http.StatusNoContent)
@@ -168,7 +183,7 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 		csvimportRequests.Inc()
 		if err := csvimport.InsertHandler(r); err != nil {
 			csvimportErrors.Inc()
-			httpserver.Errorf(w, r, "error in %q: %s", r.URL.Path, err)
+			httpserver.Errorf(w, r, "%s", err)
 			return true
 		}
 		w.WriteHeader(http.StatusNoContent)
@@ -177,7 +192,7 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 		prometheusimportRequests.Inc()
 		if err := prometheusimport.InsertHandler(r); err != nil {
 			prometheusimportErrors.Inc()
-			httpserver.Errorf(w, r, "error in %q: %s", r.URL.Path, err)
+			httpserver.Errorf(w, r, "%s", err)
 			return true
 		}
 		w.WriteHeader(http.StatusNoContent)
@@ -186,7 +201,7 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 		nativeimportRequests.Inc()
 		if err := native.InsertHandler(r); err != nil {
 			nativeimportErrors.Inc()
-			httpserver.Errorf(w, r, "error in %q: %s", r.URL.Path, err)
+			httpserver.Errorf(w, r, "%s", err)
 			return true
 		}
 		w.WriteHeader(http.StatusNoContent)
@@ -195,22 +210,18 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 		influxWriteRequests.Inc()
 		if err := influx.InsertHandlerForHTTP(r); err != nil {
 			influxWriteErrors.Inc()
-			httpserver.Errorf(w, r, "error in %q: %s", r.URL.Path, err)
+			httpserver.Errorf(w, r, "%s", err)
 			return true
 		}
 		w.WriteHeader(http.StatusNoContent)
 		return true
 	case "/query":
-		// Emulate fake response for influx query.
-		// This is required for TSBS benchmark.
 		influxQueryRequests.Inc()
-		fmt.Fprintf(w, `{"results":[{"series":[{"values":[]}]}]}`)
+		influxutils.WriteDatabaseNames(w)
 		return true
 	case "/targets":
 		promscrapeTargetsRequests.Inc()
-		w.Header().Set("Content-Type", "text/plain; charset=utf-8")
-		showOriginalLabels, _ := strconv.ParseBool(r.FormValue("show_original_labels"))
-		promscrape.WriteHumanReadableTargetsStatus(w, showOriginalLabels)
+		promscrape.WriteHumanReadableTargetsStatus(w, r)
 		return true
 	case "/api/v1/targets":
 		promscrapeAPIV1TargetsRequests.Inc()
@@ -268,10 +279,7 @@ func usage() {
 	const s = `
 vmagent collects metrics data via popular data ingestion protocols and routes it to VictoriaMetrics.
 
-See the docs at https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/app/vmagent/README.md .
+See the docs at https://docs.victoriametrics.com/vmagent.html .
 `
-
-	f := flag.CommandLine.Output()
-	fmt.Fprintf(f, "%s\n", s)
-	flag.PrintDefaults()
+	flagutil.Usage(s)
 }

app/vmagent/multiarch/Dockerfile

@@ -0,0 +1,12 @@
+# See https://medium.com/on-docker/use-multi-stage-builds-to-inject-ca-certs-ad1e8f01de1b
+ARG certs_image
+ARG root_image
+FROM $certs_image as certs
+RUN apk --update --no-cache add ca-certificates
+
+FROM $root_image
+COPY --from=certs /etc/ssl/certs/ca-certificates.crt /etc/ssl/certs/ca-certificates.crt
+EXPOSE 8429
+ENTRYPOINT ["/vmagent-prod"]
+ARG TARGETARCH
+COPY vmagent-${TARGETARCH}-prod ./vmagent-prod

app/vmagent/opentsdbhttp/request_handler.go

@@ -6,6 +6,7 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/common"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
+	parserCommon "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
 	parser "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/opentsdbhttp"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
 	"github.com/VictoriaMetrics/metrics"
@@ -19,12 +20,18 @@ var (
 // InsertHandler processes HTTP OpenTSDB put requests.
 // See http://opentsdb.net/docs/build/html/api_http/put.html
 func InsertHandler(req *http.Request) error {
+	extraLabels, err := parserCommon.GetExtraLabels(req)
+	if err != nil {
+		return err
+	}
 	return writeconcurrencylimiter.Do(func() error {
-		return parser.ParseStream(req, insertRows)
+		return parser.ParseStream(req, func(rows []parser.Row) error {
+			return insertRows(rows, extraLabels)
+		})
 	})
 }
 
-func insertRows(rows []parser.Row) error {
+func insertRows(rows []parser.Row, extraLabels []prompbmarshal.Label) error {
 	ctx := common.GetPushCtx()
 	defer common.PutPushCtx(ctx)
 
@@ -45,6 +52,7 @@ func insertRows(rows []parser.Row) error {
 				Value: tag.Value,
 			})
 		}
+		labels = append(labels, extraLabels...)
 		samples = append(samples, prompbmarshal.Sample{
 			Value:     r.Value,
 			Timestamp: r.Timestamp,

app/vmagent/prometheusimport/request_handler.go

@@ -31,7 +31,7 @@ func InsertHandler(req *http.Request) error {
 		isGzipped := req.Header.Get("Content-Encoding") == "gzip"
 		return parser.ParseStream(req.Body, defaultTimestamp, isGzipped, func(rows []parser.Row) error {
 			return insertRows(rows, extraLabels)
-		})
+		}, nil)
 	})
 }
 

app/vmagent/promremotewrite/request_handler.go

@@ -8,6 +8,7 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
+	parserCommon "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
 	parser "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/promremotewrite"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
 	"github.com/VictoriaMetrics/metrics"
@@ -20,12 +21,18 @@ var (
 
 // InsertHandler processes remote write for prometheus.
 func InsertHandler(req *http.Request) error {
+	extraLabels, err := parserCommon.GetExtraLabels(req)
+	if err != nil {
+		return err
+	}
 	return writeconcurrencylimiter.Do(func() error {
-		return parser.ParseStream(req, insertRows)
+		return parser.ParseStream(req, func(tss []prompb.TimeSeries) error {
+			return insertRows(tss, extraLabels)
+		})
 	})
 }
 
-func insertRows(timeseries []prompb.TimeSeries) error {
+func insertRows(timeseries []prompb.TimeSeries, extraLabels []prompbmarshal.Label) error {
 	ctx := common.GetPushCtx()
 	defer common.PutPushCtx(ctx)
 
@@ -44,6 +51,7 @@ func insertRows(timeseries []prompb.TimeSeries) error {
 				Value: bytesutil.ToUnsafeString(label.Value),
 			})
 		}
+		labels = append(labels, extraLabels...)
 		samplesLen := len(samples)
 		for i := range ts.Samples {
 			sample := &ts.Samples[i]

app/vmagent/remotewrite/client.go

@@ -2,9 +2,6 @@ package remotewrite
 
 import (
 	"bytes"
-	"crypto/tls"
-	"encoding/base64"
-	"flag"
 	"fmt"
 	"io/ioutil"
 	"net/http"
@@ -17,15 +14,19 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/persistentqueue"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promauth"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/timerpool"
 	"github.com/VictoriaMetrics/metrics"
 )
 
 var (
-	sendTimeout = flag.Duration("remoteWrite.sendTimeout", time.Minute, "Timeout for sending a single block of data to -remoteWrite.url")
+	rateLimit = flagutil.NewArrayInt("remoteWrite.rateLimit", "Optional rate limit in bytes per second for data sent to -remoteWrite.url. "+
+		"By default the rate limit is disabled. It can be useful for limiting load on remote storage when big amounts of buffered data "+
+		"is sent after temporary unavailability of the remote storage")
+	sendTimeout = flagutil.NewArrayDuration("remoteWrite.sendTimeout", "Timeout for sending a single block of data to -remoteWrite.url")
 	proxyURL    = flagutil.NewArray("remoteWrite.proxyURL", "Optional proxy URL for writing data to -remoteWrite.url. Supported proxies: http, https, socks5. "+
 		"Example: -remoteWrite.proxyURL=socks5://proxy:1234")
 
-	tlsInsecureSkipVerify = flag.Bool("remoteWrite.tlsInsecureSkipVerify", false, "Whether to skip tls verification when connecting to -remoteWrite.url")
+	tlsInsecureSkipVerify = flagutil.NewArrayBool("remoteWrite.tlsInsecureSkipVerify", "Whether to skip tls verification when connecting to -remoteWrite.url")
 	tlsCertFile           = flagutil.NewArray("remoteWrite.tlsCertFile", "Optional path to client-side TLS certificate file to use when connecting to -remoteWrite.url. "+
 		"If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url")
 	tlsKeyFile = flagutil.NewArray("remoteWrite.tlsKeyFile", "Optional path to client-side TLS certificate key to use when connecting to -remoteWrite.url. "+
@@ -39,17 +40,39 @@ var (
 		"If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url")
 	basicAuthPassword = flagutil.NewArray("remoteWrite.basicAuth.password", "Optional basic auth password to use for -remoteWrite.url. "+
 		"If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url")
+	basicAuthPasswordFile = flagutil.NewArray("remoteWrite.basicAuth.passwordFile", "Optional path to basic auth password to use for -remoteWrite.url. "+
+		"The file is re-read every second. "+
+		"If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url")
 	bearerToken = flagutil.NewArray("remoteWrite.bearerToken", "Optional bearer auth token to use for -remoteWrite.url. "+
 		"If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url")
+	bearerTokenFile = flagutil.NewArray("remoteWrite.bearerTokenFile", "Optional path to bearer token file to use for -remoteWrite.url. "+
+		"The token is re-read from the file every second. "+
+		"If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url")
+
+	oauth2ClientID = flagutil.NewArray("remoteWrite.oauth2.clientID", "Optional OAuth2 clientID to use for -remoteWrite.url. "+
+		"If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url")
+	oauth2ClientSecret = flagutil.NewArray("remoteWrite.oauth2.clientSecret", "Optional OAuth2 clientSecret to use for -remoteWrite.url. "+
+		"If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url")
+	oauth2ClientSecretFile = flagutil.NewArray("remoteWrite.oauth2.clientSecretFile", "Optional OAuth2 clientSecretFile to use for -remoteWrite.url. "+
+		"If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url")
+	oauth2TokenURL = flagutil.NewArray("remoteWrite.oauth2.tokenUrl", "Optional OAuth2 tokenURL to use for -remoteWrite.url. "+
+		"If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url")
+	oauth2Scopes = flagutil.NewArray("remoteWrite.oauth2.scopes", "Optional OAuth2 scopes to use for -remoteWrite.url. Scopes must be delimited by ';'. "+
+		"If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url")
 )
 
 type client struct {
 	sanitizedURL   string
 	remoteWriteURL string
-	authHeader     string
 	fq             *persistentqueue.FastQueue
 	hc             *http.Client
 
+	authCfg *promauth.Config
+
+	rl rateLimiter
+
+	bytesSent       *metrics.Counter
+	blocksSent      *metrics.Counter
 	requestDuration *metrics.Histogram
 	requestsOKCount *metrics.Counter
 	errorsCount     *metrics.Counter
@@ -61,10 +84,11 @@ type client struct {
 }
 
 func newClient(argIdx int, remoteWriteURL, sanitizedURL string, fq *persistentqueue.FastQueue, concurrency int) *client {
-	tlsCfg, err := getTLSConfig(argIdx)
+	authCfg, err := getAuthConfig(argIdx)
 	if err != nil {
-		logger.Panicf("FATAL: cannot initialize TLS config: %s", err)
+		logger.Panicf("FATAL: cannot initialize auth config: %s", err)
 	}
+	tlsCfg := authCfg.NewTLSConfig()
 	tr := &http.Transport{
 		Dial:                statDial,
 		TLSClientConfig:     tlsCfg,
@@ -85,33 +109,25 @@ func newClient(argIdx int, remoteWriteURL, sanitizedURL string, fq *persistentqu
 		}
 		tr.Proxy = http.ProxyURL(urlProxy)
 	}
-	authHeader := ""
-	username := basicAuthUsername.GetOptionalArg(argIdx)
-	password := basicAuthPassword.GetOptionalArg(argIdx)
-	if len(username) > 0 || len(password) > 0 {
-		// See https://en.wikipedia.org/wiki/Basic_access_authentication
-		token := username + ":" + password
-		token64 := base64.StdEncoding.EncodeToString([]byte(token))
-		authHeader = "Basic " + token64
-	}
-	token := bearerToken.GetOptionalArg(argIdx)
-	if len(token) > 0 {
-		if authHeader != "" {
-			logger.Fatalf("`-remoteWrite.bearerToken`=%q cannot be set when `-remoteWrite.basicAuth.*` flags are set", token)
-		}
-		authHeader = "Bearer " + token
-	}
 	c := &client{
 		sanitizedURL:   sanitizedURL,
 		remoteWriteURL: remoteWriteURL,
-		authHeader:     authHeader,
+		authCfg:        authCfg,
 		fq:             fq,
 		hc: &http.Client{
 			Transport: tr,
-			Timeout:   *sendTimeout,
+			Timeout:   sendTimeout.GetOptionalArgOrDefault(argIdx, time.Minute),
 		},
 		stopCh: make(chan struct{}),
 	}
+	if bytesPerSec := rateLimit.GetOptionalArgOrDefault(argIdx, 0); bytesPerSec > 0 {
+		logger.Infof("applying %d bytes per second rate limit for -remoteWrite.url=%q", bytesPerSec, sanitizedURL)
+		c.rl.perSecondLimit = int64(bytesPerSec)
+	}
+	c.rl.limitReached = metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remote_write_rate_limit_reached_total{url=%q}`, c.sanitizedURL))
+
+	c.bytesSent = metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_bytes_sent_total{url=%q}`, c.sanitizedURL))
+	c.blocksSent = metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_blocks_sent_total{url=%q}`, c.sanitizedURL))
 	c.requestDuration = metrics.GetOrCreateHistogram(fmt.Sprintf(`vmagent_remotewrite_duration_seconds{url=%q}`, c.sanitizedURL))
 	c.requestsOKCount = metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_requests_total{url=%q, status_code="2XX"}`, c.sanitizedURL))
 	c.errorsCount = metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_errors_total{url=%q}`, c.sanitizedURL))
@@ -134,60 +150,97 @@ func (c *client) MustStop() {
 	logger.Infof("stopped client for -remoteWrite.url=%q", c.sanitizedURL)
 }
 
-func getTLSConfig(argIdx int) (*tls.Config, error) {
-	c := &promauth.TLSConfig{
+func getAuthConfig(argIdx int) (*promauth.Config, error) {
+	username := basicAuthUsername.GetOptionalArg(argIdx)
+	password := basicAuthPassword.GetOptionalArg(argIdx)
+	passwordFile := basicAuthPasswordFile.GetOptionalArg(argIdx)
+	var basicAuthCfg *promauth.BasicAuthConfig
+	if username != "" || password != "" || passwordFile != "" {
+		basicAuthCfg = &promauth.BasicAuthConfig{
+			Username:     username,
+			Password:     password,
+			PasswordFile: passwordFile,
+		}
+	}
+
+	token := bearerToken.GetOptionalArg(argIdx)
+	tokenFile := bearerTokenFile.GetOptionalArg(argIdx)
+
+	var oauth2Cfg *promauth.OAuth2Config
+	clientSecret := oauth2ClientSecret.GetOptionalArg(argIdx)
+	clientSecretFile := oauth2ClientSecretFile.GetOptionalArg(argIdx)
+	if clientSecretFile != "" || clientSecret != "" {
+		oauth2Cfg = &promauth.OAuth2Config{
+			ClientID:         oauth2ClientID.GetOptionalArg(argIdx),
+			ClientSecret:     clientSecret,
+			ClientSecretFile: clientSecretFile,
+			TokenURL:         oauth2TokenURL.GetOptionalArg(argIdx),
+			Scopes:           strings.Split(oauth2Scopes.GetOptionalArg(argIdx), ";"),
+		}
+	}
+
+	tlsCfg := &promauth.TLSConfig{
 		CAFile:             tlsCAFile.GetOptionalArg(argIdx),
 		CertFile:           tlsCertFile.GetOptionalArg(argIdx),
 		KeyFile:            tlsKeyFile.GetOptionalArg(argIdx),
 		ServerName:         tlsServerName.GetOptionalArg(argIdx),
-		InsecureSkipVerify: *tlsInsecureSkipVerify,
+		InsecureSkipVerify: tlsInsecureSkipVerify.GetOptionalArg(argIdx),
 	}
-	if c.CAFile == "" && c.CertFile == "" && c.KeyFile == "" && c.ServerName == "" && !c.InsecureSkipVerify {
-		return nil, nil
-	}
-	cfg, err := promauth.NewConfig(".", nil, "", "", c)
+
+	authCfg, err := promauth.NewConfig(".", nil, basicAuthCfg, token, tokenFile, oauth2Cfg, tlsCfg)
 	if err != nil {
-		return nil, fmt.Errorf("cannot populate TLS config: %w", err)
+		return nil, fmt.Errorf("cannot populate OAuth2 config for remoteWrite idx: %d, err: %w", argIdx, err)
 	}
-	tlsCfg := cfg.NewTLSConfig()
-	return tlsCfg, nil
+	return authCfg, nil
 }
 
 func (c *client) runWorker() {
 	var ok bool
 	var block []byte
-	ch := make(chan struct{})
+	ch := make(chan bool, 1)
 	for {
 		block, ok = c.fq.MustReadBlock(block[:0])
 		if !ok {
 			return
 		}
 		go func() {
-			c.sendBlock(block)
-			ch <- struct{}{}
+			ch <- c.sendBlock(block)
 		}()
 		select {
-		case <-ch:
-			// The block has been sent successfully
-			continue
+		case ok := <-ch:
+			if ok {
+				// The block has been sent successfully
+				continue
+			}
+			// Return unsent block to the queue.
+			c.fq.MustWriteBlock(block)
+			return
 		case <-c.stopCh:
 			// c must be stopped. Wait for a while in the hope the block will be sent.
 			graceDuration := 5 * time.Second
 			select {
-			case <-ch:
-				// The block has been sent successfully.
+			case ok := <-ch:
+				if !ok {
+					// Return unsent block to the queue.
+					c.fq.MustWriteBlock(block)
+				}
 			case <-time.After(graceDuration):
-				logger.Errorf("couldn't sent block with size %d bytes to %q in %.3f seconds during shutdown; dropping it",
-					len(block), c.sanitizedURL, graceDuration.Seconds())
+				// Return unsent block to the queue.
+				c.fq.MustWriteBlock(block)
 			}
 			return
 		}
 	}
 }
 
-func (c *client) sendBlock(block []byte) {
+// sendBlock returns false only if c.stopCh is closed.
+// Otherwise it tries sending the block to remote storage indefinitely.
+func (c *client) sendBlock(block []byte) bool {
+	c.rl.register(len(block), c.stopCh)
 	retryDuration := time.Second
 	retriesCount := 0
+	c.bytesSent.Add(len(block))
+	c.blocksSent.Inc()
 
 again:
 	req, err := http.NewRequest("POST", c.remoteWriteURL, bytes.NewBuffer(block))
@@ -199,8 +252,8 @@ again:
 	h.Set("Content-Type", "application/x-protobuf")
 	h.Set("Content-Encoding", "snappy")
 	h.Set("X-Prometheus-Remote-Write-Version", "0.1.0")
-	if c.authHeader != "" {
-		req.Header.Set("Authorization", c.authHeader)
+	if ah := c.authCfg.GetAuthHeader(); ah != "" {
+		req.Header.Set("Authorization", ah)
 	}
 
 	startTime := time.Now()
@@ -212,14 +265,15 @@ again:
 		if retryDuration > time.Minute {
 			retryDuration = time.Minute
 		}
-		logger.Errorf("couldn't send a block with size %d bytes to %q: %s; re-sending the block in %.3f seconds",
+		logger.Warnf("couldn't send a block with size %d bytes to %q: %s; re-sending the block in %.3f seconds",
 			len(block), c.sanitizedURL, err, retryDuration.Seconds())
-		t := time.NewTimer(retryDuration)
+		t := timerpool.Get(retryDuration)
 		select {
 		case <-c.stopCh:
-			t.Stop()
-			return
+			timerpool.Put(t)
+			return false
 		case <-t.C:
+			timerpool.Put(t)
 		}
 		c.retriesCount.Inc()
 		goto again
@@ -228,18 +282,16 @@ again:
 	if statusCode/100 == 2 {
 		_ = resp.Body.Close()
 		c.requestsOKCount.Inc()
-		return
+		return true
 	}
 	metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_requests_total{url=%q, status_code="%d"}`, c.sanitizedURL, statusCode)).Inc()
-	if statusCode == 409 {
-		// Just drop block on 409 status code like Prometheus does.
+	if statusCode == 409 || statusCode == 400 {
+		// Just drop block on 409 and 400 status codes like Prometheus does.
 		// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/873
-		body, _ := ioutil.ReadAll(resp.Body)
+		// and https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1149
 		_ = resp.Body.Close()
-		logger.Errorf("unexpected status code received when sending a block with size %d bytes to %q: #%d; dropping the block like Prometheus does; "+
-			"response body=%q", len(block), c.sanitizedURL, statusCode, body)
 		c.packetsDropped.Inc()
-		return
+		return true
 	}
 
 	// Unexpected status code returned
@@ -256,13 +308,56 @@ again:
 		logger.Errorf("unexpected status code received after sending a block with size %d bytes to %q during retry #%d: %d; response body=%q; "+
 			"re-sending the block in %.3f seconds", len(block), c.sanitizedURL, retriesCount, statusCode, body, retryDuration.Seconds())
 	}
-	t := time.NewTimer(retryDuration)
+	t := timerpool.Get(retryDuration)
 	select {
 	case <-c.stopCh:
-		t.Stop()
-		return
+		timerpool.Put(t)
+		return false
 	case <-t.C:
+		timerpool.Put(t)
 	}
 	c.retriesCount.Inc()
 	goto again
 }
+
+type rateLimiter struct {
+	perSecondLimit int64
+
+	// mu protects budget and deadline from concurrent access.
+	mu sync.Mutex
+
+	// The current budget. It is increased by perSecondLimit every second.
+	budget int64
+
+	// The next deadline for increasing the budget by perSecondLimit
+	deadline time.Time
+
+	limitReached *metrics.Counter
+}
+
+func (rl *rateLimiter) register(dataLen int, stopCh <-chan struct{}) {
+	limit := rl.perSecondLimit
+	if limit <= 0 {
+		return
+	}
+
+	rl.mu.Lock()
+	defer rl.mu.Unlock()
+
+	for rl.budget <= 0 {
+		if d := time.Until(rl.deadline); d > 0 {
+			rl.limitReached.Inc()
+			t := timerpool.Get(d)
+			select {
+			case <-stopCh:
+				timerpool.Put(t)
+				return
+			case <-t.C:
+				timerpool.Put(t)
+			}
+		}
+		rl.budget += limit
+		rl.deadline = time.Now().Add(time.Second)
+	}
+	rl.budget -= int64(dataLen)
+}

app/vmagent/remotewrite/pendingseries.go

@@ -7,6 +7,7 @@ import (
 	"time"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/decimal"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/fasttime"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/persistentqueue"
@@ -18,8 +19,7 @@ import (
 
 var (
 	flushInterval = flag.Duration("remoteWrite.flushInterval", time.Second, "Interval for flushing the data to remote storage. "+
-		"Higher value reduces network bandwidth usage at the cost of delayed push of scraped data to remote storage. "+
-		"Minimum supported interval is 1 second")
+		"This option takes effect only when less than 10K data points per second are pushed to -remoteWrite.url")
 	maxUnpackedBlockSize = flagutil.NewBytes("remoteWrite.maxBlockSize", 8*1024*1024, "The maximum size in bytes of unpacked request to send to remote storage. "+
 		"It shouldn't exceed -maxInsertRequestSize from VictoriaMetrics")
 )
@@ -27,6 +27,9 @@ var (
 // the maximum number of rows to send per each block.
 const maxRowsPerBlock = 10000
 
+// the maximum number of labels to send per each block.
+const maxLabelsPerBlock = 10 * maxRowsPerBlock
+
 type pendingSeries struct {
 	mu sync.Mutex
 	wr writeRequest
@@ -35,9 +38,11 @@ type pendingSeries struct {
 	periodicFlusherWG sync.WaitGroup
 }
 
-func newPendingSeries(pushBlock func(block []byte)) *pendingSeries {
+func newPendingSeries(pushBlock func(block []byte), significantFigures, roundDigits int) *pendingSeries {
 	var ps pendingSeries
 	ps.wr.pushBlock = pushBlock
+	ps.wr.significantFigures = significantFigures
+	ps.wr.roundDigits = roundDigits
 	ps.stopCh = make(chan struct{})
 	ps.periodicFlusherWG.Add(1)
 	go func() {
@@ -85,9 +90,17 @@ type writeRequest struct {
 	// Move lastFlushTime to the top of the struct in order to guarantee atomic access on 32-bit architectures.
 	lastFlushTime uint64
 
-	wr        prompbmarshal.WriteRequest
+	// pushBlock is called when whe write request is ready to be sent.
 	pushBlock func(block []byte)
 
+	// How many significant figures must be left before sending the writeRequest to pushBlock.
+	significantFigures int
+
+	// How many decimal digits after point must be left before sending the writeRequest to pushBlock.
+	roundDigits int
+
+	wr prompbmarshal.WriteRequest
+
 	tss []prompbmarshal.TimeSeries
 
 	labels  []prompbmarshal.Label
@@ -96,6 +109,8 @@ type writeRequest struct {
 }
 
 func (wr *writeRequest) reset() {
+	// Do not reset pushBlock, significantFigures and roundDigits, since they are re-used.
+
 	wr.wr.Timeseries = nil
 
 	for i := range wr.tss {
@@ -114,17 +129,34 @@ func (wr *writeRequest) reset() {
 
 func (wr *writeRequest) flush() {
 	wr.wr.Timeseries = wr.tss
+	wr.adjustSampleValues()
 	atomic.StoreUint64(&wr.lastFlushTime, fasttime.UnixTimestamp())
 	pushWriteRequest(&wr.wr, wr.pushBlock)
 	wr.reset()
 }
 
+func (wr *writeRequest) adjustSampleValues() {
+	samples := wr.samples
+	if n := wr.significantFigures; n > 0 {
+		for i := range samples {
+			s := &samples[i]
+			s.Value = decimal.RoundToSignificantFigures(s.Value, n)
+		}
+	}
+	if n := wr.roundDigits; n < 100 {
+		for i := range samples {
+			s := &samples[i]
+			s.Value = decimal.RoundToDecimalDigits(s.Value, n)
+		}
+	}
+}
+
 func (wr *writeRequest) push(src []prompbmarshal.TimeSeries) {
 	tssDst := wr.tss
 	for i := range src {
 		tssDst = append(tssDst, prompbmarshal.TimeSeries{})
 		wr.copyTimeSeries(&tssDst[len(tssDst)-1], &src[i])
-		if len(wr.samples) >= maxRowsPerBlock {
+		if len(wr.samples) >= maxRowsPerBlock || len(wr.labels) >= maxLabelsPerBlock {
 			wr.tss = tssDst
 			wr.flush()
 			tssDst = wr.tss

app/vmagent/remotewrite/relabel.go

@@ -14,10 +14,15 @@ import (
 
 var (
 	unparsedLabelsGlobal = flagutil.NewArray("remoteWrite.label", "Optional label in the form 'name=value' to add to all the metrics before sending them to -remoteWrite.url. "+
-		"Pass multiple -remoteWrite.label flags in order to add multiple flags to metrics before sending them to remote storage")
+		"Pass multiple -remoteWrite.label flags in order to add multiple labels to metrics before sending them to remote storage")
 	relabelConfigPathGlobal = flag.String("remoteWrite.relabelConfig", "", "Optional path to file with relabel_config entries. These entries are applied to all the metrics "+
-		"before sending them to -remoteWrite.url. See https://victoriametrics.github.io/vmagent.html#relabeling for details")
+		"before sending them to -remoteWrite.url. See https://docs.victoriametrics.com/vmagent.html#relabeling for details")
+	relabelDebugGlobal = flag.Bool("remoteWrite.relabelDebug", false, "Whether to log metrics before and after relabeling with -remoteWrite.relabelConfig. "+
+		"If the -remoteWrite.relabelDebug is enabled, then the metrics aren't sent to remote storage. This is useful for debugging the relabeling configs")
 	relabelConfigPaths = flagutil.NewArray("remoteWrite.urlRelabelConfig", "Optional path to relabel config for the corresponding -remoteWrite.url")
+	relabelDebug       = flagutil.NewArrayBool("remoteWrite.urlRelabelDebug", "Whether to log metrics before and after relabeling with -remoteWrite.urlRelabelConfig. "+
+		"If the -remoteWrite.urlRelabelDebug is enabled, then the metrics aren't sent to the corresponding -remoteWrite.url. "+
+		"This is useful for debugging the relabeling configs")
 )
 
 var labelsGlobal []prompbmarshal.Label
@@ -31,7 +36,7 @@ func CheckRelabelConfigs() error {
 func loadRelabelConfigs() (*relabelConfigs, error) {
 	var rcs relabelConfigs
 	if *relabelConfigPathGlobal != "" {
-		global, err := promrelabel.LoadRelabelConfigs(*relabelConfigPathGlobal)
+		global, err := promrelabel.LoadRelabelConfigs(*relabelConfigPathGlobal, *relabelDebugGlobal)
 		if err != nil {
 			return nil, fmt.Errorf("cannot load -remoteWrite.relabelConfig=%q: %w", *relabelConfigPathGlobal, err)
 		}
@@ -41,13 +46,13 @@ func loadRelabelConfigs() (*relabelConfigs, error) {
 		return nil, fmt.Errorf("too many -remoteWrite.urlRelabelConfig args: %d; it mustn't exceed the number of -remoteWrite.url args: %d",
 			len(*relabelConfigPaths), len(*remoteWriteURLs))
 	}
-	rcs.perURL = make([][]promrelabel.ParsedRelabelConfig, len(*remoteWriteURLs))
+	rcs.perURL = make([]*promrelabel.ParsedConfigs, len(*remoteWriteURLs))
 	for i, path := range *relabelConfigPaths {
 		if len(path) == 0 {
 			// Skip empty relabel config.
 			continue
 		}
-		prc, err := promrelabel.LoadRelabelConfigs(path)
+		prc, err := promrelabel.LoadRelabelConfigs(path, relabelDebug.GetOptionalArg(i))
 		if err != nil {
 			return nil, fmt.Errorf("cannot load relabel configs from -remoteWrite.urlRelabelConfig=%q: %w", path, err)
 		}
@@ -57,14 +62,17 @@ func loadRelabelConfigs() (*relabelConfigs, error) {
 }
 
 type relabelConfigs struct {
-	global []promrelabel.ParsedRelabelConfig
-	perURL [][]promrelabel.ParsedRelabelConfig
+	global *promrelabel.ParsedConfigs
+	perURL []*promrelabel.ParsedConfigs
 }
 
 // initLabelsGlobal must be called after parsing command-line flags.
 func initLabelsGlobal() {
 	labelsGlobal = nil
 	for _, s := range *unparsedLabelsGlobal {
+		if len(s) == 0 {
+			continue
+		}
 		n := strings.IndexByte(s, '=')
 		if n < 0 {
 			logger.Fatalf("missing '=' in `-remoteWrite.label`. It must contain label in the form `name=value`; got %q", s)
@@ -76,8 +84,8 @@ func initLabelsGlobal() {
 	}
 }
 
-func (rctx *relabelCtx) applyRelabeling(tss []prompbmarshal.TimeSeries, extraLabels []prompbmarshal.Label, prcs []promrelabel.ParsedRelabelConfig) []prompbmarshal.TimeSeries {
-	if len(extraLabels) == 0 && len(prcs) == 0 {
+func (rctx *relabelCtx) applyRelabeling(tss []prompbmarshal.TimeSeries, extraLabels []prompbmarshal.Label, pcs *promrelabel.ParsedConfigs) []prompbmarshal.TimeSeries {
+	if len(extraLabels) == 0 && pcs.Len() == 0 {
 		// Nothing to change.
 		return tss
 	}
@@ -97,7 +105,7 @@ func (rctx *relabelCtx) applyRelabeling(tss []prompbmarshal.TimeSeries, extraLab
 				labels = append(labels, *extraLabel)
 			}
 		}
-		labels = promrelabel.ApplyRelabelConfigs(labels, labelsLen, prcs, true)
+		labels = pcs.Apply(labels, labelsLen, true)
 		if len(labels) == labelsLen {
 			// Drop the current time series, since relabeling removed all the labels.
 			continue

app/vmagent/remotewrite/remotewrite.go

@@ -3,17 +3,21 @@ package remotewrite
 import (
 	"flag"
 	"fmt"
-	"runtime"
+	"strconv"
 	"sync"
 	"sync/atomic"
+	"time"
 
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/decimal"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bloomfilter"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/cgroup"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/memory"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/persistentqueue"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/procutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
 	"github.com/VictoriaMetrics/metrics"
 	xxhash "github.com/cespare/xxhash/v2"
 )
@@ -22,18 +26,31 @@ var (
 	remoteWriteURLs = flagutil.NewArray("remoteWrite.url", "Remote storage URL to write data to. It must support Prometheus remote_write API. "+
 		"It is recommended using VictoriaMetrics as remote storage. Example url: http://<victoriametrics-host>:8428/api/v1/write . "+
 		"Pass multiple -remoteWrite.url flags in order to write data concurrently to multiple remote storage systems")
-	tmpDataPath = flag.String("remoteWrite.tmpDataPath", "vmagent-remotewrite-data", "Path to directory where temporary data for remote write component is stored")
-	queues      = flag.Int("remoteWrite.queues", 4, "The number of concurrent queues to each -remoteWrite.url. Set more queues if default number of queues "+
-		"isn't enough for sending high volume of collected data to remote storage")
+	tmpDataPath = flag.String("remoteWrite.tmpDataPath", "vmagent-remotewrite-data", "Path to directory where temporary data for remote write component is stored. "+
+		"See also -remoteWrite.maxDiskUsagePerURL")
+	queues = flag.Int("remoteWrite.queues", cgroup.AvailableCPUs()*2, "The number of concurrent queues to each -remoteWrite.url. Set more queues if default number of queues "+
+		"isn't enough for sending high volume of collected data to remote storage. Default value if 2 * numberOfAvailableCPUs")
 	showRemoteWriteURL = flag.Bool("remoteWrite.showURL", false, "Whether to show -remoteWrite.url in the exported metrics. "+
 		"It is hidden by default, since it can contain sensitive info such as auth key")
 	maxPendingBytesPerURL = flagutil.NewBytes("remoteWrite.maxDiskUsagePerURL", 0, "The maximum file-based buffer size in bytes at -remoteWrite.tmpDataPath "+
 		"for each -remoteWrite.url. When buffer size reaches the configured maximum, then old data is dropped when adding new data to the buffer. "+
 		"Buffered data is stored in ~500MB chunks, so the minimum practical value for this flag is 500000000. "+
 		"Disk usage is unlimited if the value is set to 0")
-	significantFigures = flag.Int("remoteWrite.significantFigures", 0, "The number of significant figures to leave in metric values before writing them to remote storage. "+
-		"See https://en.wikipedia.org/wiki/Significant_figures . Zero value saves all the significant figures. "+
-		"This option may be used for increasing on-disk compression level for the stored metrics")
+	significantFigures = flagutil.NewArrayInt("remoteWrite.significantFigures", "The number of significant figures to leave in metric values before writing them "+
+		"to remote storage. See https://en.wikipedia.org/wiki/Significant_figures . Zero value saves all the significant figures. "+
+		"This option may be used for improving data compression for the stored metrics. See also -remoteWrite.roundDigits")
+	roundDigits = flagutil.NewArrayInt("remoteWrite.roundDigits", "Round metric values to this number of decimal digits after the point before writing them to remote storage. "+
+		"Examples: -remoteWrite.roundDigits=2 would round 1.236 to 1.24, while -remoteWrite.roundDigits=-1 would round 126.78 to 130. "+
+		"By default digits rounding is disabled. Set it to 100 for disabling it for a particular remote storage. "+
+		"This option may be used for improving data compression for the stored metrics")
+	sortLabels = flag.Bool("sortLabels", false, `Whether to sort labels for incoming samples before writing them to all the configured remote storage systems. `+
+		`This may be needed for reducing memory usage at remote storage when the order of labels in incoming samples is random. `+
+		`For example, if m{k1="v1",k2="v2"} may be sent as m{k2="v2",k1="v1"}`+
+		`Enabled sorting for labels can slow down ingestion performance a bit`)
+	maxHourlySeries = flag.Int("remoteWrite.maxHourlySeries", 0, "The maximum number of unique series vmagent can send to remote storage systems during the last hour. "+
+		"Excess series are logged and dropped. This can be useful for limiting series cardinality. See also -remoteWrite.maxDailySeries")
+	maxDailySeries = flag.Int("remoteWrite.maxDailySeries", 0, "The maximum number of unique series vmagent can send to remote storage systems during the last 24 hours. "+
+		"Excess series are logged and dropped. This can be useful for limiting series churn rate. See also -remoteWrite.maxHourlySeries")
 )
 
 var rwctxs []*remoteWriteCtx
@@ -43,7 +60,7 @@ var allRelabelConfigs atomic.Value
 
 // maxQueues limits the maximum value for `-remoteWrite.queues`. There is no sense in setting too high value,
 // since it may lead to high memory usage due to big number of buffers.
-var maxQueues = runtime.GOMAXPROCS(-1) * 4
+var maxQueues = cgroup.AvailableCPUs() * 16
 
 // InitSecretFlags must be called after flag.Parse and before any logging.
 func InitSecretFlags() {
@@ -62,6 +79,24 @@ func Init() {
 	if len(*remoteWriteURLs) == 0 {
 		logger.Fatalf("at least one `-remoteWrite.url` command-line flag must be set")
 	}
+	if *maxHourlySeries > 0 {
+		hourlySeriesLimiter = bloomfilter.NewLimiter(*maxHourlySeries, time.Hour)
+		_ = metrics.NewGauge(`vmagent_hourly_series_limit_max_series`, func() float64 {
+			return float64(hourlySeriesLimiter.MaxItems())
+		})
+		_ = metrics.NewGauge(`vmagent_hourly_series_limit_current_series`, func() float64 {
+			return float64(hourlySeriesLimiter.CurrentItems())
+		})
+	}
+	if *maxDailySeries > 0 {
+		dailySeriesLimiter = bloomfilter.NewLimiter(*maxDailySeries, 24*time.Hour)
+		_ = metrics.NewGauge(`vmagent_daily_series_limit_max_series`, func() float64 {
+			return float64(dailySeriesLimiter.MaxItems())
+		})
+		_ = metrics.NewGauge(`vmagent_daily_series_limit_current_series`, func() float64 {
+			return float64(dailySeriesLimiter.CurrentItems())
+		})
+	}
 	if *queues > maxQueues {
 		*queues = maxQueues
 	}
@@ -69,6 +104,12 @@ func Init() {
 		*queues = 1
 	}
 	initLabelsGlobal()
+
+	// Register SIGHUP handler for config reload before loadRelabelConfigs.
+	// This guarantees that the config will be re-read if the signal arrives just after loadRelabelConfig.
+	// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1240
+	sighupCh := procutil.NewSighupChan()
+
 	rcs, err := loadRelabelConfigs()
 	if err != nil {
 		logger.Fatalf("cannot load relabel configs: %s", err)
@@ -76,11 +117,11 @@ func Init() {
 	allRelabelConfigs.Store(rcs)
 
 	maxInmemoryBlocks := memory.Allowed() / len(*remoteWriteURLs) / maxRowsPerBlock / 100
-	if maxInmemoryBlocks > 200 {
+	if maxInmemoryBlocks > 400 {
 		// There is no much sense in keeping higher number of blocks in memory,
 		// since this means that the producer outperforms consumer and the queue
 		// will continue growing. It is better storing the queue to file.
-		maxInmemoryBlocks = 200
+		maxInmemoryBlocks = 400
 	}
 	if maxInmemoryBlocks < 2 {
 		maxInmemoryBlocks = 2
@@ -95,7 +136,6 @@ func Init() {
 	}
 
 	// Start config reloader.
-	sighupCh := procutil.NewSighupChan()
 	configReloaderWG.Add(1)
 	go func() {
 		defer configReloaderWG.Done()
@@ -137,32 +177,23 @@ func Stop() {
 //
 // Note that wr may be modified by Push due to relabeling and rounding.
 func Push(wr *prompbmarshal.WriteRequest) {
-	if *significantFigures > 0 {
-		// Round values according to significantFigures
-		for i := range wr.Timeseries {
-			samples := wr.Timeseries[i].Samples
-			for j := range samples {
-				s := &samples[j]
-				s.Value = decimal.Round(s.Value, *significantFigures)
-			}
-		}
-	}
-
 	var rctx *relabelCtx
 	rcs := allRelabelConfigs.Load().(*relabelConfigs)
-	prcsGlobal := rcs.global
-	if len(prcsGlobal) > 0 || len(labelsGlobal) > 0 {
+	pcsGlobal := rcs.global
+	if pcsGlobal.Len() > 0 || len(labelsGlobal) > 0 {
 		rctx = getRelabelCtx()
 	}
 	tss := wr.Timeseries
 	for len(tss) > 0 {
 		// Process big tss in smaller blocks in order to reduce the maximum memory usage
 		samplesCount := 0
+		labelsCount := 0
 		i := 0
 		for i < len(tss) {
 			samplesCount += len(tss[i].Samples)
+			labelsCount += len(tss[i].Labels)
 			i++
-			if samplesCount > maxRowsPerBlock {
+			if samplesCount >= maxRowsPerBlock || labelsCount >= maxLabelsPerBlock {
 				break
 			}
 		}
@@ -175,11 +206,15 @@ func Push(wr *prompbmarshal.WriteRequest) {
 		}
 		if rctx != nil {
 			tssBlockLen := len(tssBlock)
-			tssBlock = rctx.applyRelabeling(tssBlock, labelsGlobal, prcsGlobal)
+			tssBlock = rctx.applyRelabeling(tssBlock, labelsGlobal, pcsGlobal)
 			globalRelabelMetricsDropped.Add(tssBlockLen - len(tssBlock))
 		}
-		for _, rwctx := range rwctxs {
-			rwctx.Push(tssBlock)
+		sortLabelsIfNeeded(tssBlock)
+		tssBlock = limitSeriesCardinality(tssBlock)
+		if len(tssBlock) > 0 {
+			for _, rwctx := range rwctxs {
+				rwctx.Push(tssBlock)
+			}
 		}
 		if rctx != nil {
 			rctx.reset()
@@ -190,6 +225,87 @@ func Push(wr *prompbmarshal.WriteRequest) {
 	}
 }
 
+// sortLabelsIfNeeded sorts labels if -sortLabels command-line flag is set.
+func sortLabelsIfNeeded(tss []prompbmarshal.TimeSeries) {
+	if !*sortLabels {
+		return
+	}
+	for i := range tss {
+		promrelabel.SortLabels(tss[i].Labels)
+	}
+}
+
+func limitSeriesCardinality(tss []prompbmarshal.TimeSeries) []prompbmarshal.TimeSeries {
+	if hourlySeriesLimiter == nil && dailySeriesLimiter == nil {
+		return tss
+	}
+	dst := make([]prompbmarshal.TimeSeries, 0, len(tss))
+	for i := range tss {
+		labels := tss[i].Labels
+		h := getLabelsHash(labels)
+		if hourlySeriesLimiter != nil && !hourlySeriesLimiter.Add(h) {
+			hourlySeriesLimitRowsDropped.Add(len(tss[i].Samples))
+			logSkippedSeries(labels, "-remoteWrite.maxHourlySeries", hourlySeriesLimiter.MaxItems())
+			continue
+		}
+		if dailySeriesLimiter != nil && !dailySeriesLimiter.Add(h) {
+			dailySeriesLimitRowsDropped.Add(len(tss[i].Samples))
+			logSkippedSeries(labels, "-remoteWrite.maxDailySeries", dailySeriesLimiter.MaxItems())
+			continue
+		}
+		dst = append(dst, tss[i])
+	}
+	return dst
+}
+
+var (
+	hourlySeriesLimiter *bloomfilter.Limiter
+	dailySeriesLimiter  *bloomfilter.Limiter
+
+	hourlySeriesLimitRowsDropped = metrics.NewCounter(`vmagent_hourly_series_limit_rows_dropped_total`)
+	dailySeriesLimitRowsDropped  = metrics.NewCounter(`vmagent_daily_series_limit_rows_dropped_total`)
+)
+
+func getLabelsHash(labels []prompbmarshal.Label) uint64 {
+	bb := labelsHashBufPool.Get()
+	b := bb.B[:0]
+	for _, label := range labels {
+		b = append(b, label.Name...)
+		b = append(b, label.Value...)
+	}
+	h := xxhash.Sum64(b)
+	bb.B = b
+	labelsHashBufPool.Put(bb)
+	return h
+}
+
+var labelsHashBufPool bytesutil.ByteBufferPool
+
+func logSkippedSeries(labels []prompbmarshal.Label, flagName string, flagValue int) {
+	select {
+	case <-logSkippedSeriesTicker.C:
+		logger.Warnf("skip series %s because %s=%d reached", labelsToString(labels), flagName, flagValue)
+	default:
+	}
+}
+
+var logSkippedSeriesTicker = time.NewTicker(5 * time.Second)
+
+func labelsToString(labels []prompbmarshal.Label) string {
+	var b []byte
+	b = append(b, '{')
+	for i, label := range labels {
+		b = append(b, label.Name...)
+		b = append(b, '=')
+		b = strconv.AppendQuote(b, label.Value)
+		if i+1 < len(labels) {
+			b = append(b, ',')
+		}
+	}
+	b = append(b, '}')
+	return string(b)
+}
+
 var globalRelabelMetricsDropped = metrics.NewCounter("vmagent_remotewrite_global_relabel_metrics_dropped_total")
 
 type remoteWriteCtx struct {
@@ -213,9 +329,17 @@ func newRemoteWriteCtx(argIdx int, remoteWriteURL string, maxInmemoryBlocks int,
 		return float64(fq.GetInmemoryQueueLen())
 	})
 	c := newClient(argIdx, remoteWriteURL, sanitizedURL, fq, *queues)
-	pss := make([]*pendingSeries, *queues)
+	sf := significantFigures.GetOptionalArgOrDefault(argIdx, 0)
+	rd := roundDigits.GetOptionalArgOrDefault(argIdx, 100)
+	pssLen := *queues
+	if n := cgroup.AvailableCPUs(); pssLen > n {
+		// There is no sense in running more than availableCPUs concurrent pendingSeries,
+		// since every pendingSeries can saturate up to a single CPU.
+		pssLen = n
+	}
+	pss := make([]*pendingSeries, pssLen)
 	for i := range pss {
-		pss[i] = newPendingSeries(fq.MustWriteBlock)
+		pss[i] = newPendingSeries(fq.MustWriteBlock, sf, rd)
 	}
 	return &remoteWriteCtx{
 		idx: argIdx,
@@ -233,10 +357,11 @@ func (rwctx *remoteWriteCtx) MustStop() {
 	}
 	rwctx.idx = 0
 	rwctx.pss = nil
-	rwctx.fq.MustClose()
-	rwctx.fq = nil
+	rwctx.fq.UnblockAllReaders()
 	rwctx.c.MustStop()
 	rwctx.c = nil
+	rwctx.fq.MustClose()
+	rwctx.fq = nil
 
 	rwctx.relabelMetricsDropped = nil
 }
@@ -245,8 +370,8 @@ func (rwctx *remoteWriteCtx) Push(tss []prompbmarshal.TimeSeries) {
 	var rctx *relabelCtx
 	var v *[]prompbmarshal.TimeSeries
 	rcs := allRelabelConfigs.Load().(*relabelConfigs)
-	prcs := rcs.perURL[rwctx.idx]
-	if len(prcs) > 0 {
+	pcs := rcs.perURL[rwctx.idx]
+	if pcs.Len() > 0 {
 		rctx = getRelabelCtx()
 		// Make a copy of tss before applying relabeling in order to prevent
 		// from affecting time series for other remoteWrite.url configs.
@@ -255,7 +380,7 @@ func (rwctx *remoteWriteCtx) Push(tss []prompbmarshal.TimeSeries) {
 		v = tssRelabelPool.Get().(*[]prompbmarshal.TimeSeries)
 		tss = append(*v, tss...)
 		tssLen := len(tss)
-		tss = rctx.applyRelabeling(tss, nil, prcs)
+		tss = rctx.applyRelabeling(tss, nil, pcs)
 		rwctx.relabelMetricsDropped.Add(tssLen - len(tss))
 	}
 	pss := rwctx.pss

app/vmagent/remotewrite/statconn.go

@@ -1,25 +1,17 @@
 package remotewrite
 
 import (
-	"fmt"
 	"net"
-	"strings"
 	"sync/atomic"
+	"time"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/netutil"
-	"github.com/VictoriaMetrics/fasthttp"
 	"github.com/VictoriaMetrics/metrics"
 )
 
-func statDial(network, addr string) (conn net.Conn, err error) {
-	if !strings.HasPrefix(network, "tcp") {
-		return nil, fmt.Errorf("unexpected network passed to statDial: %q; it must start from `tcp`", network)
-	}
-	if netutil.TCP6Enabled() {
-		conn, err = fasthttp.DialDualStack(addr)
-	} else {
-		conn, err = fasthttp.Dial(addr)
-	}
+func statDial(networkUnused, addr string) (conn net.Conn, err error) {
+	network := netutil.GetTCPNetwork()
+	conn, err = net.DialTimeout(network, addr, 5*time.Second)
 	dialsTotal.Inc()
 	if err != nil {
 		dialErrors.Inc()

app/vmalert/Makefile

@@ -66,7 +66,17 @@ run-vmalert: vmalert
 		-remoteRead.url=http://localhost:8428 \
 		-external.label=cluster=east-1 \
 		-external.label=replica=a \
-		-evaluationInterval=3s
+		-evaluationInterval=3s \
+		-rule.configCheckInterval=10s
+
+replay-vmalert: vmalert
+	./bin/vmalert -rule=app/vmalert/config/testdata/rules-replay-good.rules \
+		-datasource.url=http://localhost:8428 \
+		-remoteWrite.url=http://localhost:8428 \
+		-external.label=cluster=east-1 \
+		-external.label=replica=a \
+		-replay.timeFrom=2021-05-11T07:21:43Z \
+		-replay.timeTo=2021-05-29T18:40:43Z
 
 vmalert-amd64:
 	CGO_ENABLED=1 GOARCH=amd64 $(MAKE) vmalert-local-with-goarch
@@ -88,3 +98,9 @@ vmalert-local-with-goarch:
 
 vmalert-pure:
 	APP_NAME=vmalert $(MAKE) app-local-pure
+
+vmalert-windows-amd64:
+	GOARCH=amd64 APP_NAME=vmalert $(MAKE) app-local-windows-with-goarch
+
+vmalert-windows-amd64-prod:
+	APP_NAME=vmalert $(MAKE) app-via-docker-windows-amd64

app/vmalert/README.md

@@ -1,30 +1,32 @@
-## vmalert
+# vmalert
 
-`vmalert` executes a list of given [alerting](https://prometheus.io/docs/prometheus/latest/configuration/alerting_rules/)
+`vmalert` executes a list of the given [alerting](https://prometheus.io/docs/prometheus/latest/configuration/alerting_rules/)
 or [recording](https://prometheus.io/docs/prometheus/latest/configuration/recording_rules/)
-rules against configured address.
+rules against configured address. It is heavily inspired by [Prometheus](https://prometheus.io/docs/alerting/latest/overview/)
+implementation and aims to be compatible with its syntax.
 
-### Features:
+## Features
 * Integration with [VictoriaMetrics](https://github.com/VictoriaMetrics/VictoriaMetrics) TSDB;
-* VictoriaMetrics [MetricsQL](https://github.com/VictoriaMetrics/VictoriaMetrics/wiki/MetricsQL)
+* VictoriaMetrics [MetricsQL](https://docs.victoriametrics.com/MetricsQL.html)
  support and expressions validation;
 * Prometheus [alerting rules definition format](https://prometheus.io/docs/prometheus/latest/configuration/alerting_rules/#defining-alerting-rules)
  support;
 * Integration with [Alertmanager](https://github.com/prometheus/alertmanager);
-* Keeps the alerts [state on restarts](https://github.com/VictoriaMetrics/VictoriaMetrics/tree/master/app/vmalert#alerts-state-on-restarts);
+* Keeps the alerts [state on restarts](#alerts-state-on-restarts);
+* Graphite datasource can be used for alerting and recording rules. See [these docs](#graphite);
+* Recording and Alerting rules backfilling (aka `replay`). See [these docs](#rules-backfilling);
 * Lightweight without extra dependencies.
 
-### Limitations:
-* `vmalert` execute queries against remote datasource which has reliability risks because of network. 
+## Limitations
+* `vmalert` execute queries against remote datasource which has reliability risks because of network.
 It is recommended to configure alerts thresholds and rules expressions with understanding that network request
 may fail;
 * by default, rules execution is sequential within one group, but persisting of execution results to remote
 storage is asynchronous. Hence, user shouldn't rely on recording rules chaining when result of previous
 recording rule is reused in next one;
-* there is no `query` function support in templates yet;
 * `vmalert` has no UI, just an API for getting groups and rules statuses.
 
-### QuickStart
+## QuickStart
 
 To build `vmalert` from sources:
 ```
@@ -37,80 +39,104 @@ The build binary will be placed to `VictoriaMetrics/bin` folder.
 To start using `vmalert` you will need the following things:
 * list of rules - PromQL/MetricsQL expressions to execute;
 * datasource address - reachable VictoriaMetrics instance for rules execution;
-* notifier address - reachable [Alert Manager](https://github.com/prometheus/alertmanager) instance for processing, 
+* notifier address - reachable [Alert Manager](https://github.com/prometheus/alertmanager) instance for processing,
 aggregating alerts and sending notifications.
-* remote write address - [remote write](https://prometheus.io/docs/prometheus/latest/storage/#remote-storage-integrations)
-compatible storage address for storing recording rules results and alerts state in for of timeseries. This is optional.
+* remote write address [optional] - [remote write](https://prometheus.io/docs/prometheus/latest/storage/#remote-storage-integrations)
+compatible storage address for storing recording rules results and alerts state in for of timeseries.
 
 Then configure `vmalert` accordingly:
 ```
-./bin/vmalert -rule=alert.rules \
+./bin/vmalert -rule=alert.rules \            # Path to the file with rules configuration. Supports wildcard
     -datasource.url=http://localhost:8428 \  # PromQL compatible datasource
     -notifier.url=http://localhost:9093 \    # AlertManager URL
     -notifier.url=http://127.0.0.1:9093 \    # AlertManager replica URL
-    -remoteWrite.url=http://localhost:8428 \ # remote write compatible storage to persist rules
-    -remoteRead.url=http://localhost:8428 \  # PromQL compatible datasource to restore alerts state from
+    -remoteWrite.url=http://localhost:8428 \ # Remote write compatible storage to persist rules
+    -remoteRead.url=http://localhost:8428 \  # MetricsQL compatible datasource to restore alerts state from
     -external.label=cluster=east-1 \         # External label to be applied for each rule
-    -external.label=replica=a \              # Multiple external labels may be set
-    -evaluationInterval=3s                   # Default evaluation interval if not specified in rules group
+    -external.label=replica=a                # Multiple external labels may be set
 ```
 
-If you run multiple `vmalert` services for the same datastore or AlertManager - do not forget
-to specify different `external.label` flags in order to define which `vmalert` generated rules or alerts. 
+See the fill list of configuration flags in [configuration](#configuration) section.
 
-Configuration for [recording](https://prometheus.io/docs/prometheus/latest/configuration/recording_rules/) 
-and [alerting](https://prometheus.io/docs/prometheus/latest/configuration/alerting_rules/) rules is very 
-similar to Prometheus rules and configured using YAML. Configuration examples may be found 
+If you run multiple `vmalert` services for the same datastore or AlertManager - do not forget
+to specify different `external.label` flags in order to define which `vmalert` generated rules or alerts.
+
+Configuration for [recording](https://prometheus.io/docs/prometheus/latest/configuration/recording_rules/)
+and [alerting](https://prometheus.io/docs/prometheus/latest/configuration/alerting_rules/) rules is very
+similar to Prometheus rules and configured using YAML. Configuration examples may be found
 in [testdata](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/app/vmalert/config/testdata) folder.
-Every `rule` belongs to `group` and every configuration file may contain arbitrary number of groups:
+Every `rule` belongs to a `group` and every configuration file may contain arbitrary number of groups:
 ```yaml
 groups:
   [ - <rule_group> ]
 ```
 
-#### Groups
+### Groups
 
-Each group has following attributes:
+Each group has the following attributes:
 ```yaml
 # The name of the group. Must be unique within a file.
 name: <string>
 
 # How often rules in the group are evaluated.
-[ interval: <duration> | default = global.evaluation_interval ]
+[ interval: <duration> | default = -evaluationInterval flag ]
 
-# How many rules execute at once. Increasing concurrency may speed
-# up round execution speed. 
+# How many rules execute at once within a group. Increasing concurrency may speed
+# up round execution speed.
 [ concurrency: <integer> | default = 1 ]
 
+# Optional type for expressions inside the rules. Supported values: "graphite" and "prometheus".
+# By default "prometheus" rule type is used.
+[ type: <string> ]
+
+# Optional list of label filters applied to every rule's
+# request withing a group. Is compatible only with VM datasource.
+# See more details at https://docs.victoriametrics.com#prometheus-querying-api-enhancements
+extra_filter_labels:
+  [ <labelname>: <labelvalue> ... ]
+
 rules:
   [ - <rule> ... ]
 ```
 
-#### Rules
+### Rules
+
+Every rule contains `expr` field for [PromQL](https://prometheus.io/docs/prometheus/latest/querying/basics/)
+or [MetricsQL](https://docs.victoriametrics.com/MetricsQL.html) expression. Vmalert will execute the configured
+expression and then act according to the Rule type.
 
 There are two types of Rules:
-* [alerting](https://prometheus.io/docs/prometheus/latest/configuration/alerting_rules/) - 
-Alerting rules allows to define alert conditions via [MetricsQL](https://github.com/VictoriaMetrics/VictoriaMetrics/wiki/MetricsQL)
-and to send notifications about firing alerts to [Alertmanager](https://github.com/prometheus/alertmanager).
-* [recording](https://prometheus.io/docs/prometheus/latest/configuration/recording_rules/) - 
-Recording rules allow you to precompute frequently needed or computationally expensive expressions 
-and save their result as a new set of time series.
+* [alerting](https://prometheus.io/docs/prometheus/latest/configuration/alerting_rules/) -
+Alerting rules allows to define alert conditions via `expr` field and to send notifications 
+[Alertmanager](https://github.com/prometheus/alertmanager) if execution result is not empty.
+* [recording](https://prometheus.io/docs/prometheus/latest/configuration/recording_rules/) -
+Recording rules allows to define `expr` which result will be than backfilled to configured
+`-remoteWrite.url`. Recording rules are used to precompute frequently needed or computationally 
+expensive expressions and save their result as a new set of time series.
 
 `vmalert` forbids to define duplicates - rules with the same combination of name, expression and labels
-within one group. 
+within one group.
 
-##### Alerting rules
+#### Alerting rules
 
-The syntax for alerting rule is following:
+The syntax for alerting rule is the following:
 ```yaml
 # The name of the alert. Must be a valid metric name.
 alert: <string>
 
-# The MetricsQL expression to evaluate.
+# Optional type for the rule. Supported values: "graphite", "prometheus".
+# By default "prometheus" rule type is used.
+[ type: <string> ]
+
+# The expression to evaluate. The expression language depends on the type value.
+# By default PromQL/MetricsQL expression is used. If type="graphite", then the expression
+# must contain valid Graphite expression.
 expr: <string>
 
 # Alerts are considered firing once they have been returned for this long.
 # Alerts which have not yet fired for long enough are considered pending.
+# If param is omitted or set to 0 then alerts will be immediately considered
+# as firing once they return.
 [ for: <duration> | default = 0s ]
 
 # Labels to add or overwrite for each alert.
@@ -120,16 +146,27 @@ labels:
 # Annotations to add to each alert.
 annotations:
   [ <labelname>: <tmpl_string> ]
-``` 
+```
 
-##### Recording rules
+It is allowed to use [Go templating](https://golang.org/pkg/text/template/) in annotations
+to format data, iterate over it or execute expressions.
+Additionally, `vmalert` provides some extra templating functions
+listed [here](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/app/vmalert/notifier/template_func.go).
+
+#### Recording rules
 
 The syntax for recording rules is following:
 ```yaml
 # The name of the time series to output to. Must be a valid metric name.
 record: <string>
 
-# The MetricsQL expression to evaluate.
+# Optional type for the rule. Supported values: "graphite", "prometheus".
+# By default "prometheus" rule type is used.
+[ type: <string> ]
+
+# The expression to evaluate. The expression language depends on the type value.
+# By default MetricsQL expression is used. If type="graphite", then the expression
+# must contain valid Graphite expression.
 expr: <string>
 
 # Labels to add or overwrite before storing the result.
@@ -137,243 +174,413 @@ labels:
   [ <labelname>: <labelvalue> ]
 ```
 
-For recording rules to work `-remoteWrite.url` must specified.
+For recording rules to work `-remoteWrite.url` must be specified.
 
 
-#### Alerts state on restarts
+### Alerts state on restarts
 
-`vmalert` has no local storage, so alerts state is stored in the process memory. Hence, after reloading of `vmalert` 
+`vmalert` has no local storage, so alerts state is stored in the process memory. Hence, after restart of `vmalert`
 the process alerts state will be lost. To avoid this situation, `vmalert` should be configured via the following flags:
-* `-remoteWrite.url` - URL to VictoriaMetrics (Single) or VMInsert (Cluster). `vmalert` will persist alerts state 
-into the configured address in the form of time series named `ALERTS` and `ALERTS_FOR_STATE` via remote-write protocol. 
-These are regular time series and may be queried from VM just as any other time series. 
+* `-remoteWrite.url` - URL to VictoriaMetrics (Single) or vminsert (Cluster). `vmalert` will persist alerts state
+into the configured address in the form of time series named `ALERTS` and `ALERTS_FOR_STATE` via remote-write protocol.
+These are regular time series and may be queried from VM just as any other time series.
 The state stored to the configured address on every rule evaluation.
-* `-remoteRead.url` - URL to VictoriaMetrics (Single) or VMSelect (Cluster). `vmalert` will try to restore alerts state 
+* `-remoteRead.url` - URL to VictoriaMetrics (Single) or vmselect (Cluster). `vmalert` will try to restore alerts state
 from configured address by querying time series with name `ALERTS_FOR_STATE`.
 
 Both flags are required for the proper state restoring. Restore process may fail if time series are missing
-in configured `-remoteRead.url`, weren't updated in the last `1h` or received state doesn't match current `vmalert` 
-rules configuration.
+in configured `-remoteRead.url`, weren't updated in the last `1h` (controlled by `-remoteRead.lookback`) 
+or received state doesn't match current `vmalert` rules configuration.
 
 
-#### WEB
+### Multitenancy
+
+There are the following approaches for alerting and recording rules across 
+[multiple tenants](https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html#multitenancy):
+
+* To run a separate `vmalert` instance per each tenant. 
+  The corresponding tenant must be specified in `-datasource.url` command-line flag 
+  according to [these docs](https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html#url-format). 
+  For example, `/path/to/vmalert -datasource.url=http://vmselect:8481/select/123/prometheus`
+  would run alerts against `AccountID=123`. For recording rules the `-remoteWrite.url` command-line 
+  flag must contain the url for the specific tenant as well. 
+  For example, `-remoteWrite.url=http://vminsert:8480/insert/123/prometheus` would write recording 
+  rules to `AccountID=123`.
+
+* To specify `tenant` parameter per each alerting and recording group if 
+  [enterprise version of vmalert](https://victoriametrics.com/enterprise.html) is used 
+  with `-clusterMode` command-line flag. For example:
+
+```yaml
+groups:
+- name: rules_for_tenant_123
+  tenant: "123"
+  rules:
+    # Rules for accountID=123
+
+- name: rules_for_tenant_456:789
+  tenant: "456:789"
+  rules:
+    # Rules for accountID=456, projectID=789
+```
+
+If `-clusterMode` is enabled, then `-datasource.url`, `-remoteRead.url` and `-remoteWrite.url` must 
+contain only the hostname without tenant id. For example: `-datasource.url=http://vmselect:8481`. 
+`vmselect` automatically adds the specified tenant to urls per each recording rule in this case.
+
+The enterprise version of vmalert is available in `vmutils-*-enterprise.tar.gz` files 
+at [release page](https://github.com/VictoriaMetrics/VictoriaMetrics/releases) and in `*-enterprise` 
+tags at [Docker Hub](https://hub.docker.com/r/victoriametrics/vmalert/tags).
+
+
+### WEB
 
 `vmalert` runs a web-server (`-httpListenAddr`) for serving metrics and alerts endpoints:
 * `http://<vmalert-addr>/api/v1/groups` - list of all loaded groups and rules;
 * `http://<vmalert-addr>/api/v1/alerts` - list of all active alerts;
-* `http://<vmalert-addr>/api/v1/<groupName>/<alertID>/status" ` - get alert status by ID.
+* `http://<vmalert-addr>/api/v1/<groupID>/<alertID>/status" ` - get alert status by ID.
 Used as alert source in AlertManager.
 * `http://<vmalert-addr>/metrics` - application metrics.
 * `http://<vmalert-addr>/-/reload` - hot configuration reload.
 
 
-### Configuration
+## Graphite
+
+vmalert sends requests to `<-datasource.url>/render?format=json` during evaluation of alerting and recording rules
+if the corresponding group or rule contains `type: "graphite"` config option. It is expected that the `<-datasource.url>/render`
+implements [Graphite Render API](https://graphite.readthedocs.io/en/stable/render_api.html) for `format=json`.
+When using vmalert with both `graphite` and `prometheus` rules configured against cluster version of VM do not forget
+to set `-datasource.appendTypePrefix` flag to `true`, so vmalert can adjust URL prefix automatically based on query type.
+
+## Rules backfilling
+
+vmalert supports alerting and recording rules backfilling (aka `replay`). In replay mode vmalert
+can read the same rules configuration as normally, evaluate them on the given time range and backfill
+results via remote write to the configured storage. vmalert supports any PromQL/MetricsQL compatible
+data source for backfilling.
+
+### How it works
+
+In `replay` mode vmalert works as a cli-tool and exits immediately after work is done.
+To run vmalert in `replay` mode:
+```
+./bin/vmalert -rule=path/to/your.rules \        # path to files with rules you usually use with vmalert
+    -datasource.url=http://localhost:8428 \     # PromQL/MetricsQL compatible datasource
+    -remoteWrite.url=http://localhost:8428 \    # remote write compatible storage to persist results
+    -replay.timeFrom=2021-05-11T07:21:43Z \     # time from begin replay
+    -replay.timeTo=2021-05-29T18:40:43Z         # time to finish replay
+```
+
+The output of the command will look like the following:
+```
+Replay mode:
+from:   2021-05-11 07:21:43 +0000 UTC   # set by -replay.timeFrom
+to:     2021-05-29 18:40:43 +0000 UTC   # set by -replay.timeTo
+max data points per request: 1000       # set by -replay.maxDatapointsPerQuery
+
+Group "ReplayGroup"
+interval:       1m0s
+requests to make:       27
+max range per request:  16h40m0s
+> Rule "type:vm_cache_entries:rate5m" (ID: 1792509946081842725)
+27 / 27 [----------------------------------------------------------------------------------------------------] 100.00% 78 p/s
+> Rule "go_cgo_calls_count:rate5m" (ID: 17958425467471411582)
+27 / 27 [-----------------------------------------------------------------------------------------------------] 100.00% ? p/s
+
+Group "vmsingleReplay"
+interval:       30s
+requests to make:       54
+max range per request:  8h20m0s
+> Rule "RequestErrorsToAPI" (ID: 17645863024999990222)
+54 / 54 [-----------------------------------------------------------------------------------------------------] 100.00% ? p/s
+> Rule "TooManyLogs" (ID: 9042195394653477652)
+54 / 54 [-----------------------------------------------------------------------------------------------------] 100.00% ? p/s
+2021-06-07T09:59:12.098Z        info    app/vmalert/replay.go:68        replay finished! Imported 511734 samples
+```
+
+In `replay` mode all groups are executed sequentially one-by-one. Rules within the group are
+executed sequentially as well (`concurrency` setting is ignored). Vmalert sends rule's expression
+to [/query_range](https://prometheus.io/docs/prometheus/latest/querying/api/#range-queries) endpoint
+of the configured `-datasource.url`. Returned data then processed according to the rule type and
+backfilled to `-remoteWrite.url` via [Remote Write protocol](https://prometheus.io/docs/prometheus/latest/storage/#remote-storage-integrations).
+Vmalert respects `evaluationInterval` value set by flag or per-group during the replay.
+
+#### Recording rules
+
+Result of recording rules `replay` should match with results of normal rules evaluation.
+
+#### Alerting rules
+
+Result of alerting rules `replay` is time series reflecting [alert's state](#alerts-state-on-restarts).
+To see if `replayed` alert has fired in the past use the following PromQL/MetricsQL expression:
+```
+ALERTS{alertname="your_alertname", alertstate="firing"}
+```
+Execute the query against storage which was used for `-remoteWrite.url` during the `replay`.
+
+### Additional configuration
+
+There are following non-required `replay` flags:
+
+* `-replay.maxDatapointsPerQuery` - the max number of data points expected to receive in one request.
+In two words, it affects the max time range for every `/query_range` request. The higher the value,
+the less requests will be issued during `replay`.
+* `-replay.ruleRetryAttempts` - when datasource fails to respond vmalert will make this number of retries
+per rule before giving up.
+* `-replay.rulesDelay` - delay between sequential rules execution. Important in cases if there are chaining
+(rules which depend on each other) rules. It is expected, that remote storage will be able to persist
+previously accepted data during the delay, so data will be available for the subsequent queries.
+Keep it equal or bigger than `-remoteWrite.flushInterval`.
+
+See full description for these flags in `./vmalert --help`.
+
+### Limitations
+
+* Graphite engine isn't supported yet;
+* `query` template function is disabled for performance reasons (might be changed in future);
+
+
+## Configuration
+
+Pass `-help` to `vmalert` in order to see the full list of supported
+command-line flags with their descriptions.
 
 The shortlist of configuration flags is the following:
 ```
+  -datasource.appendTypePrefix
+        Whether to add type prefix to -datasource.url based on the query type. Set to true if sending different query types to the vmselect URL.
   -datasource.basicAuth.password string
-    	Optional basic auth password for -datasource.url
+        Optional basic auth password for -datasource.url
   -datasource.basicAuth.username string
-    	Optional basic auth username for -datasource.url
+        Optional basic auth username for -datasource.url
   -datasource.lookback duration
-        Lookback defines how far to look into past when evaluating queries. For example, if datasource.lookback=5m then param "time" with value now()-5m will be added to every query.
+        Lookback defines how far into the past to look when evaluating queries. For example, if the datasource.lookback=5m then param "time" with value now()-5m will be added to every query.
   -datasource.maxIdleConnections int
-        Defines the number of idle (keep-alive connections) to configured datasource.Consider to set this value equal to the value: groups_total * group.concurrency. Too low value may result into high number of sockets in TIME_WAIT state. (default 100)
+        Defines the number of idle (keep-alive connections) to each configured datasource. Consider setting this value equal to the value: groups_total * group.concurrency. Too low a value may result in a high number of sockets in TIME_WAIT state. (default 100)
+  -datasource.queryStep duration
+        queryStep defines how far a value can fallback to when evaluating queries. For example, if datasource.queryStep=15s then param "step" with value "15s" will be added to every query.If queryStep isn't specified, rule's evaluationInterval will be used instead.
+  -datasource.roundDigits int
+        Adds "round_digits" GET param to datasource requests. In VM "round_digits" limits the number of digits after the decimal point in response values.
   -datasource.tlsCAFile string
-    	Optional path to TLS CA file to use for verifying connections to -datasource.url. By default system CA is used
+        Optional path to TLS CA file to use for verifying connections to -datasource.url. By default, system CA is used
   -datasource.tlsCertFile string
-    	Optional path to client-side TLS certificate file to use when connecting to -datasource.url
+        Optional path to client-side TLS certificate file to use when connecting to -datasource.url
   -datasource.tlsInsecureSkipVerify
-    	Whether to skip tls verification when connecting to -datasource.url
+        Whether to skip tls verification when connecting to -datasource.url
   -datasource.tlsKeyFile string
-    	Optional path to client-side TLS certificate key to use when connecting to -datasource.url
+        Optional path to client-side TLS certificate key to use when connecting to -datasource.url
   -datasource.tlsServerName string
-    	Optional TLS server name to use for connections to -datasource.url. By default the server name from -datasource.url is used
+        Optional TLS server name to use for connections to -datasource.url. By default, the server name from -datasource.url is used
   -datasource.url string
-    	Victoria Metrics or VMSelect url. Required parameter. E.g. http://127.0.0.1:8428
+        VictoriaMetrics or vmselect url. Required parameter. E.g. http://127.0.0.1:8428
+  -dryRun -rule
+        Whether to check only config files without running vmalert. The rules file are validated. The -rule flag must be specified.
   -enableTCP6
-    	Whether to enable IPv6 for listening and dialing. By default only IPv4 TCP is used
+        Whether to enable IPv6 for listening and dialing. By default only IPv4 TCP and UDP is used
   -envflag.enable
-    	Whether to enable reading flags from environment variables additionally to command line. Command line flag values have priority over values from environment vars. Flags are read only from command line if this flag isn't set
+        Whether to enable reading flags from environment variables additionally to command line. Command line flag values have priority over values from environment vars. Flags are read only from command line if this flag isn't set
   -envflag.prefix string
-    	Prefix for environment variables if -envflag.enable is set
+        Prefix for environment variables if -envflag.enable is set
   -evaluationInterval duration
-    	How often to evaluate the rules (default 1m0s)
+        How often to evaluate the rules (default 1m0s)
   -external.alert.source string
-    	External Alert Source allows to override the Source link for alerts sent to AlertManager for cases where you want to build a custom link to Grafana, Prometheus or any other service.
-    	eg. 'explore?orgId=1&left=[\"now-1h\",\"now\",\"VictoriaMetrics\",{\"expr\": \"{{$expr|quotesEscape|pathEscape}}\"},{\"mode\":\"Metrics\"},{\"ui\":[true,true,true,\"none\"]}]'.If empty '/api/v1/:groupID/alertID/status' is used
+        External Alert Source allows to override the Source link for alerts sent to AlertManager for cases where you want to build a custom link to Grafana, Prometheus or any other service.
+        eg. 'explore?orgId=1&left=[\"now-1h\",\"now\",\"VictoriaMetrics\",{\"expr\": \"{{$expr|quotesEscape|crlfEscape|queryEscape}}\"},{\"mode\":\"Metrics\"},{\"ui\":[true,true,true,\"none\"]}]'.If empty '/api/v1/:groupID/alertID/status' is used
   -external.label array
-    	Optional label in the form 'name=value' to add to all generated recording rules and alerts. Pass multiple -label flags in order to add multiple label sets.
-    	Supports array of values separated by comma or specified via multiple flags.
+        Optional label in the form 'name=value' to add to all generated recording rules and alerts. Pass multiple -label flags in order to add multiple label sets.
+        Supports an array of values separated by comma or specified via multiple flags.
   -external.url string
-    	External URL is used as alert's source for sent alerts to the notifier
+        External URL is used as alert's source for sent alerts to the notifier
+  -fs.disableMmap
+        Whether to use pread() instead of mmap() for reading data files. By default mmap() is used for 64-bit arches and pread() is used for 32-bit arches, since they cannot read data files bigger than 2^32 bytes in memory. mmap() is usually faster for reading small data chunks than pread()
   -http.connTimeout duration
-    	Incoming http connections are closed after the configured timeout. This may help spreading incoming load among a cluster of services behind load balancer. Note that the real timeout may be bigger by up to 10% as a protection from Thundering herd problem (default 2m0s)
+        Incoming http connections are closed after the configured timeout. This may help to spread the incoming load among a cluster of services behind a load balancer. Please note that the real timeout may be bigger by up to 10% as a protection against the thundering herd problem (default 2m0s)
   -http.disableResponseCompression
-    	Disable compression of HTTP responses for saving CPU resources. By default compression is enabled to save network bandwidth
+        Disable compression of HTTP responses to save CPU resources. By default compression is enabled to save network bandwidth
   -http.idleConnTimeout duration
-    	Timeout for incoming idle http connections (default 1m0s)
+        Timeout for incoming idle http connections (default 1m0s)
   -http.maxGracefulShutdownDuration duration
-    	The maximum duration for graceful shutdown of HTTP server. Highly loaded server may require increased value for graceful shutdown (default 7s)
+        The maximum duration for a graceful shutdown of the HTTP server. A highly loaded server may require increased value for a graceful shutdown (default 7s)
   -http.pathPrefix string
-    	An optional prefix to add to all the paths handled by http server. For example, if '-http.pathPrefix=/foo/bar' is set, then all the http requests will be handled on '/foo/bar/*' paths. This may be useful for proxied requests. See https://www.robustperception.io/using-external-urls-and-proxies-with-prometheus
+        An optional prefix to add to all the paths handled by http server. For example, if '-http.pathPrefix=/foo/bar' is set, then all the http requests will be handled on '/foo/bar/*' paths. This may be useful for proxied requests. See https://www.robustperception.io/using-external-urls-and-proxies-with-prometheus
   -http.shutdownDelay duration
-    	Optional delay before http server shutdown. During this dealy the servier returns non-OK responses from /health page, so load balancers can route new requests to other servers
+        Optional delay before http server shutdown. During this delay, the server returns non-OK responses from /health page, so load balancers can route new requests to other servers
   -httpAuth.password string
-    	Password for HTTP Basic Auth. The authentication is disabled if -httpAuth.username is empty
+        Password for HTTP Basic Auth. The authentication is disabled if -httpAuth.username is empty
   -httpAuth.username string
-    	Username for HTTP Basic Auth. The authentication is disabled if empty. See also -httpAuth.password
+        Username for HTTP Basic Auth. The authentication is disabled if empty. See also -httpAuth.password
   -httpListenAddr string
-    	Address to listen for http connections (default ":8880")
+        Address to listen for http connections (default ":8880")
+  -loggerDisableTimestamps
+        Whether to disable writing timestamps in logs
   -loggerErrorsPerSecondLimit int
-    	Per-second limit on the number of ERROR messages. If more than the given number of errors are emitted per second, then the remaining errors are suppressed. Zero value disables the rate limit (default 10)
+        Per-second limit on the number of ERROR messages. If more than the given number of errors are emitted per second, the remaining errors are suppressed. Zero values disable the rate limit
   -loggerFormat string
-    	Format for logs. Possible values: default, json (default "default")
+        Format for logs. Possible values: default, json (default "default")
   -loggerLevel string
-    	Minimum level of errors to log. Possible values: INFO, WARN, ERROR, FATAL, PANIC (default "INFO")
+        Minimum level of errors to log. Possible values: INFO, WARN, ERROR, FATAL, PANIC (default "INFO")
   -loggerOutput string
-    	Output for the logs. Supported values: stderr, stdout (default "stderr")
-  -memory.allowedBytes value
-    	Allowed size of system memory VictoriaMetrics caches may occupy. This option overrides -memory.allowedPercent if set to non-zero value. Too low value may increase cache miss rate, which usually results in higher CPU and disk IO usage. Too high value may evict too much data from OS page cache, which will result in higher disk IO usage
-    	Supports the following optional suffixes for values: KB, MB, GB, KiB, MiB, GiB (default 0)
+        Output for the logs. Supported values: stderr, stdout (default "stderr")
+  -loggerTimezone string
+        Timezone to use for timestamps in logs. Timezone must be a valid IANA Time Zone. For example: America/New_York, Europe/Berlin, Etc/GMT+3 or Local (default "UTC")
+  -loggerWarnsPerSecondLimit int
+        Per-second limit on the number of WARN messages. If more than the given number of warns are emitted per second, then the remaining warns are suppressed. Zero values disable the rate limit
+  -memory.allowedBytes size
+        Allowed size of system memory VictoriaMetrics caches may occupy. This option overrides -memory.allowedPercent if set to a non-zero value. Too low a value may increase the cache miss rate usually resulting in higher CPU and disk IO usage. Too high a value may evict too much data from OS page cache resulting in higher disk IO usage
+        Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 0)
   -memory.allowedPercent float
-    	Allowed percent of system memory VictoriaMetrics caches may occupy. See also -memory.allowedBytes. Too low value may increase cache miss rate, which usually results in higher CPU and disk IO usage. Too high value may evict too much data from OS page cache, which will result in higher disk IO usage (default 60)
+        Allowed percent of system memory VictoriaMetrics caches may occupy. See also -memory.allowedBytes. Too low a value may increase cache miss rate usually resulting in higher CPU and disk IO usage. Too high a value may evict too much data from OS page cache which will result in higher disk IO usage (default 60)
   -metricsAuthKey string
-    	Auth key for /metrics. It overrides httpAuth settings
+        Auth key for /metrics. It overrides httpAuth settings
   -notifier.basicAuth.password array
-    	Optional basic auth password for -datasource.url
-    	Supports array of values separated by comma or specified via multiple flags.
+        Optional basic auth password for -notifier.url
+        Supports an array of values separated by comma or specified via multiple flags.
   -notifier.basicAuth.username array
-    	Optional basic auth username for -datasource.url
-    	Supports array of values separated by comma or specified via multiple flags.
+        Optional basic auth username for -notifier.url
+        Supports an array of values separated by comma or specified via multiple flags.
   -notifier.tlsCAFile array
-    	Optional path to TLS CA file to use for verifying connections to -notifier.url. By default system CA is used
-    	Supports array of values separated by comma or specified via multiple flags.
+        Optional path to TLS CA file to use for verifying connections to -notifier.url. By default system CA is used
+        Supports an array of values separated by comma or specified via multiple flags.
   -notifier.tlsCertFile array
-    	Optional path to client-side TLS certificate file to use when connecting to -notifier.url
-    	Supports array of values separated by comma or specified via multiple flags.
-  -notifier.tlsInsecureSkipVerify
-    	Whether to skip tls verification when connecting to -notifier.url
+        Optional path to client-side TLS certificate file to use when connecting to -notifier.url
+        Supports an array of values separated by comma or specified via multiple flags.
+  -notifier.tlsInsecureSkipVerify array
+        Whether to skip tls verification when connecting to -notifier.url
+        Supports array of values separated by comma or specified via multiple flags.
   -notifier.tlsKeyFile array
-    	Optional path to client-side TLS certificate key to use when connecting to -notifier.url
-    	Supports array of values separated by comma or specified via multiple flags.
+        Optional path to client-side TLS certificate key to use when connecting to -notifier.url
+        Supports an array of values separated by comma or specified via multiple flags.
   -notifier.tlsServerName array
-    	Optional TLS server name to use for connections to -notifier.url. By default the server name from -notifier.url is used
-    	Supports array of values separated by comma or specified via multiple flags.
+        Optional TLS server name to use for connections to -notifier.url. By default the server name from -notifier.url is used
+        Supports an array of values separated by comma or specified via multiple flags.
   -notifier.url array
-    	Prometheus alertmanager URL. Required parameter. e.g. http://127.0.0.1:9093
-    	Supports array of values separated by comma or specified via multiple flags.
+        Prometheus alertmanager URL. Required parameter. e.g. http://127.0.0.1:9093
+        Supports an array of values separated by comma or specified via multiple flags.
   -pprofAuthKey string
-    	Auth key for /debug/pprof. It overrides httpAuth settings
+        Auth key for /debug/pprof. It overrides httpAuth settings
   -remoteRead.basicAuth.password string
-    	Optional basic auth password for -remoteRead.url
+        Optional basic auth password for -remoteRead.url
   -remoteRead.basicAuth.username string
-    	Optional basic auth username for -remoteRead.url
+        Optional basic auth username for -remoteRead.url
+  -remoteRead.ignoreRestoreErrors
+        Whether to ignore errors from remote storage when restoring alerts state on startup. (default true)
   -remoteRead.lookback duration
-    	Lookback defines how far to look into past for alerts timeseries. For example, if lookback=1h then range from now() to now()-1h will be scanned. (default 1h0m0s)
+        Lookback defines how far to look into past for alerts timeseries. For example, if lookback=1h then range from now() to now()-1h will be scanned. (default 1h0m0s)
   -remoteRead.tlsCAFile string
-    	Optional path to TLS CA file to use for verifying connections to -remoteRead.url. By default system CA is used
+        Optional path to TLS CA file to use for verifying connections to -remoteRead.url. By default system CA is used
   -remoteRead.tlsCertFile string
-    	Optional path to client-side TLS certificate file to use when connecting to -remoteRead.url
+        Optional path to client-side TLS certificate file to use when connecting to -remoteRead.url
   -remoteRead.tlsInsecureSkipVerify
-    	Whether to skip tls verification when connecting to -remoteRead.url
+        Whether to skip tls verification when connecting to -remoteRead.url
   -remoteRead.tlsKeyFile string
-    	Optional path to client-side TLS certificate key to use when connecting to -remoteRead.url
+        Optional path to client-side TLS certificate key to use when connecting to -remoteRead.url
   -remoteRead.tlsServerName string
-    	Optional TLS server name to use for connections to -remoteRead.url. By default the server name from -remoteRead.url is used
+        Optional TLS server name to use for connections to -remoteRead.url. By default the server name from -remoteRead.url is used
   -remoteRead.url vmalert
-    	Optional URL to Victoria Metrics or VMSelect that will be used to restore alerts state. This configuration makes sense only if vmalert was configured with `remoteWrite.url` before and has been successfully persisted its state. E.g. http://127.0.0.1:8428
+        Optional URL to VictoriaMetrics or vmselect that will be used to restore alerts state. This configuration makes sense only if vmalert was configured with `remoteWrite.url` before and has been successfully persisted its state. E.g. http://127.0.0.1:8428
   -remoteWrite.basicAuth.password string
-    	Optional basic auth password for -remoteWrite.url
+        Optional basic auth password for -remoteWrite.url
   -remoteWrite.basicAuth.username string
-    	Optional basic auth username for -remoteWrite.url
+        Optional basic auth username for -remoteWrite.url
   -remoteWrite.concurrency int
-    	Defines number of writers for concurrent writing into remote querier (default 1)
+        Defines number of writers for concurrent writing into remote querier (default 1)
   -remoteWrite.flushInterval duration
-    	Defines interval of flushes to remote write endpoint (default 5s)
+        Defines interval of flushes to remote write endpoint (default 5s)
   -remoteWrite.maxBatchSize int
-    	Defines defines max number of timeseries to be flushed at once (default 1000)
+        Defines defines max number of timeseries to be flushed at once (default 1000)
   -remoteWrite.maxQueueSize int
-    	Defines the max number of pending datapoints to remote write endpoint (default 100000)
+        Defines the max number of pending datapoints to remote write endpoint (default 100000)
   -remoteWrite.tlsCAFile string
-    	Optional path to TLS CA file to use for verifying connections to -remoteWrite.url. By default system CA is used
+        Optional path to TLS CA file to use for verifying connections to -remoteWrite.url. By default system CA is used
   -remoteWrite.tlsCertFile string
-    	Optional path to client-side TLS certificate file to use when connecting to -remoteWrite.url
+        Optional path to client-side TLS certificate file to use when connecting to -remoteWrite.url
   -remoteWrite.tlsInsecureSkipVerify
-    	Whether to skip tls verification when connecting to -remoteWrite.url
+        Whether to skip tls verification when connecting to -remoteWrite.url
   -remoteWrite.tlsKeyFile string
-    	Optional path to client-side TLS certificate key to use when connecting to -remoteWrite.url
+        Optional path to client-side TLS certificate key to use when connecting to -remoteWrite.url
   -remoteWrite.tlsServerName string
-    	Optional TLS server name to use for connections to -remoteWrite.url. By default the server name from -remoteWrite.url is used
+        Optional TLS server name to use for connections to -remoteWrite.url. By default the server name from -remoteWrite.url is used
   -remoteWrite.url string
-    	Optional URL to Victoria Metrics or VMInsert where to persist alerts state and recording rules results in form of timeseries. E.g. http://127.0.0.1:8428
+        Optional URL to VictoriaMetrics or vminsert where to persist alerts state and recording rules results in form of timeseries. E.g. http://127.0.0.1:8428
+  -replay.maxDatapointsPerQuery int
+        Max number of data points expected in one request. The higher the value, the less requests will be made during replay. (default 1000)
+  -replay.ruleRetryAttempts int
+        Defines how many retries to make before giving up on rule if request for it returns an error. (default 5)
+  -replay.rulesDelay duration
+        Delay between rules evaluation within the group. Could be important if there are chained rules inside of the groupand processing need to wait for previous rule results to be persisted by remote storage before evaluating the next rule. Keep it equal or bigger than -remoteWrite.flushInterval. (default 1s)
+  -replay.timeFrom string
+        The time filter in RFC3339 format to select time series with timestamp equal or higher than provided value. E.g. '2020-01-01T20:07:00Z'
+  -replay.timeTo string
+        The time filter in RFC3339 format to select timeseries with timestamp equal or lower than provided value. E.g. '2020-01-01T20:07:00Z'
   -rule array
-    	Path to the file with alert rules. 
-    	Supports patterns. Flag can be specified multiple times. 
-    	Examples:
-    	 -rule="/path/to/file". Path to a single file with alerting rules
-    	 -rule="dir/*.yaml" -rule="/*.yaml". Relative path to all .yaml files in "dir" folder, 
-    	absolute path to all .yaml files in root.
-    	Rule files may contain %{ENV_VAR} placeholders, which are substituted by the corresponding env vars.
-    	Supports array of values separated by comma or specified via multiple flags.
+        Path to the file with alert rules.
+        Supports patterns. Flag can be specified multiple times.
+        Examples:
+         -rule="/path/to/file". Path to a single file with alerting rules
+         -rule="dir/*.yaml" -rule="/*.yaml". Relative path to all .yaml files in "dir" folder,
+        absolute path to all .yaml files in root.
+        Rule files may contain %{ENV_VAR} placeholders, which are substituted by the corresponding env vars.
+        Supports an array of values separated by comma or specified via multiple flags.
+  -rule.configCheckInterval duration
+        Interval for checking for changes in '-rule' files. By default the checking is disabled. Send SIGHUP signal in order to force config check for changes
   -rule.validateExpressions
-    	Whether to validate rules expressions via MetricsQL engine (default true)
+        Whether to validate rules expressions via MetricsQL engine (default true)
   -rule.validateTemplates
-    	Whether to validate annotation and label templates (default true)
+        Whether to validate annotation and label templates (default true)
   -tls
-    	Whether to enable TLS (aka HTTPS) for incoming requests. -tlsCertFile and -tlsKeyFile must be set if -tls is set
+        Whether to enable TLS (aka HTTPS) for incoming requests. -tlsCertFile and -tlsKeyFile must be set if -tls is set
   -tlsCertFile string
-    	Path to file with TLS certificate. Used only if -tls is set. Prefer ECDSA certs instead of RSA certs, since RSA certs are slow
+        Path to file with TLS certificate. Used only if -tls is set. Prefer ECDSA certs instead of RSA certs as RSA certs are slower
   -tlsKeyFile string
-    	Path to file with TLS key. Used only if -tls is set
+        Path to file with TLS key. Used only if -tls is set
   -version
-    	Show VictoriaMetrics version
+        Show VictoriaMetrics version
 ```
 
-Pass `-help` to `vmalert` in order to see the full list of supported 
-command-line flags with their descriptions.
+`vmalert` supports "hot" config reload via the following methods:
+* send SIGHUP signal to `vmalert` process;
+* send GET request to `/-/reload` endpoint;
+* configure `-rule.configCheckInterval` flag for periodic reload
+on config change.
 
-To reload configuration without `vmalert` restart send SIGHUP signal
-or send GET request to `/-/reload` endpoint.
-
-### Contributing
+## Contributing
 
 `vmalert` is mostly designed and built by VictoriaMetrics community.
-Feel free to share your experience and ideas for improving this 
+Feel free to share your experience and ideas for improving this
 software. Please keep simplicity as the main priority.
 
-### How to build from sources
+## How to build from sources
 
-It is recommended using 
-[binary releases](https://github.com/VictoriaMetrics/VictoriaMetrics/releases) 
+It is recommended using
+[binary releases](https://github.com/VictoriaMetrics/VictoriaMetrics/releases)
 - `vmalert` is located in `vmutils-*` archives there.
 
 
-#### Development build
+### Development build
 
-1. [Install Go](https://golang.org/doc/install). The minimum supported version is Go 1.13.
-2. Run `make vmalert` from the root folder of the repository.
+1. [Install Go](https://golang.org/doc/install). The minimum supported version is Go 1.16.
+2. Run `make vmalert` from the root folder of [the repository](https://github.com/VictoriaMetrics/VictoriaMetrics).
    It builds `vmalert` binary and puts it into the `bin` folder.
 
-#### Production build
+### Production build
 
 1. [Install docker](https://docs.docker.com/install/).
-2. Run `make vmalert-prod` from the root folder of the repository.
+2. Run `make vmalert-prod` from the root folder of [the repository](https://github.com/VictoriaMetrics/VictoriaMetrics).
    It builds `vmalert-prod` binary and puts it into the `bin` folder.
 
 
-#### ARM build
+### ARM build
 
 ARM build may run on Raspberry Pi or on [energy-efficient ARM servers](https://blog.cloudflare.com/arm-takes-wing/).
 
-#### Development ARM build
+### Development ARM build
 
-1. [Install Go](https://golang.org/doc/install). The minimum supported version is Go 1.13.
-2. Run `make vmalert-arm` or `make vmalert-arm64` from the root folder of the repository.
+1. [Install Go](https://golang.org/doc/install). The minimum supported version is Go 1.16.
+2. Run `make vmalert-arm` or `make vmalert-arm64` from the root folder of [the repository](https://github.com/VictoriaMetrics/VictoriaMetrics).
    It builds `vmalert-arm` or `vmalert-arm64` binary respectively and puts it into the `bin` folder.
 
-#### Production ARM build
+### Production ARM build
 
 1. [Install docker](https://docs.docker.com/install/).
-2. Run `make vmalert-arm-prod` or `make vmalert-arm64-prod` from the root folder of the repository.
+2. Run `make vmalert-arm-prod` or `make vmalert-arm64-prod` from the root folder of [the repository](https://github.com/VictoriaMetrics/VictoriaMetrics).
    It builds `vmalert-arm-prod` or `vmalert-arm64-prod` binary respectively and puts it into the `bin` folder.

app/vmalert/alerting.go

@@ -19,14 +19,18 @@ import (
 
 // AlertingRule is basic alert entity
 type AlertingRule struct {
-	RuleID      uint64
-	Name        string
-	Expr        string
-	For         time.Duration
-	Labels      map[string]string
-	Annotations map[string]string
-	GroupID     uint64
-	GroupName   string
+	Type         datasource.Type
+	RuleID       uint64
+	Name         string
+	Expr         string
+	For          time.Duration
+	Labels       map[string]string
+	Annotations  map[string]string
+	GroupID      uint64
+	GroupName    string
+	EvalInterval time.Duration
+
+	q datasource.Querier
 
 	// guard status fields
 	mu sync.RWMutex
@@ -48,18 +52,25 @@ type alertingRuleMetrics struct {
 	active  *gauge
 }
 
-func newAlertingRule(group *Group, cfg config.Rule) *AlertingRule {
+func newAlertingRule(qb datasource.QuerierBuilder, group *Group, cfg config.Rule) *AlertingRule {
 	ar := &AlertingRule{
-		RuleID:      cfg.ID,
-		Name:        cfg.Alert,
-		Expr:        cfg.Expr,
-		For:         cfg.For.Duration(),
-		Labels:      cfg.Labels,
-		Annotations: cfg.Annotations,
-		GroupID:     group.ID(),
-		GroupName:   group.Name,
-		alerts:      make(map[uint64]*notifier.Alert),
-		metrics:     &alertingRuleMetrics{},
+		Type:         cfg.Type,
+		RuleID:       cfg.ID,
+		Name:         cfg.Alert,
+		Expr:         cfg.Expr,
+		For:          cfg.For.Duration(),
+		Labels:       cfg.Labels,
+		Annotations:  cfg.Annotations,
+		GroupID:      group.ID(),
+		GroupName:    group.Name,
+		EvalInterval: group.Interval,
+		q: qb.BuildWithParams(datasource.QuerierParams{
+			DataSourceType:     &cfg.Type,
+			EvaluationInterval: group.Interval,
+			ExtraLabels:        group.ExtraFilterLabels,
+		}),
+		alerts:  make(map[uint64]*notifier.Alert),
+		metrics: &alertingRuleMetrics{},
 	}
 
 	labels := fmt.Sprintf(`alertname=%q, group=%q, id="%d"`, ar.Name, group.Name, ar.ID())
@@ -117,10 +128,67 @@ func (ar *AlertingRule) ID() uint64 {
 	return ar.RuleID
 }
 
+// ExecRange executes alerting rule on the given time range similarly to Exec.
+// It doesn't update internal states of the Rule and meant to be used just
+// to get time series for backfilling.
+// It returns ALERT and ALERT_FOR_STATE time series as result.
+func (ar *AlertingRule) ExecRange(ctx context.Context, start, end time.Time) ([]prompbmarshal.TimeSeries, error) {
+	series, err := ar.q.QueryRange(ctx, ar.Expr, start, end)
+	if err != nil {
+		return nil, err
+	}
+	var result []prompbmarshal.TimeSeries
+	qFn := func(query string) ([]datasource.Metric, error) {
+		return nil, fmt.Errorf("`query` template isn't supported in replay mode")
+	}
+	for _, s := range series {
+		// extra labels could contain templates, so we expand them first
+		labels, err := expandLabels(s, qFn, ar)
+		if err != nil {
+			return nil, fmt.Errorf("failed to expand labels: %s", err)
+		}
+		for k, v := range labels {
+			// apply extra labels to datasource
+			// so the hash key will be consistent on restore
+			s.SetLabel(k, v)
+		}
+
+		a, err := ar.newAlert(s, time.Time{}, qFn) // initial alert
+		if err != nil {
+			return nil, fmt.Errorf("failed to create alert: %s", err)
+		}
+		if ar.For == 0 { // if alert is instant
+			a.State = notifier.StateFiring
+			for i := range s.Values {
+				result = append(result, ar.alertToTimeSeries(a, s.Timestamps[i])...)
+			}
+			continue
+		}
+
+		// if alert with For > 0
+		prevT := time.Time{}
+		//activeAt := time.Time{}
+		for i := range s.Values {
+			at := time.Unix(s.Timestamps[i], 0)
+			if at.Sub(prevT) > ar.EvalInterval {
+				// reset to Pending if there are gaps > EvalInterval between DPs
+				a.State = notifier.StatePending
+				//activeAt = at
+				a.Start = at
+			} else if at.Sub(a.Start) >= ar.For {
+				a.State = notifier.StateFiring
+			}
+			prevT = at
+			result = append(result, ar.alertToTimeSeries(a, s.Timestamps[i])...)
+		}
+	}
+	return result, nil
+}
+
 // Exec executes AlertingRule expression via the given Querier.
 // Based on the Querier results AlertingRule maintains notifier.Alerts
-func (ar *AlertingRule) Exec(ctx context.Context, q datasource.Querier, series bool) ([]prompbmarshal.TimeSeries, error) {
-	qMetrics, err := q.Query(ctx, ar.Expr)
+func (ar *AlertingRule) Exec(ctx context.Context) ([]prompbmarshal.TimeSeries, error) {
+	qMetrics, err := ar.q.Query(ctx, ar.Expr)
 	ar.mu.Lock()
 	defer ar.mu.Unlock()
 
@@ -137,14 +205,20 @@ func (ar *AlertingRule) Exec(ctx context.Context, q datasource.Querier, series b
 		}
 	}
 
+	qFn := func(query string) ([]datasource.Metric, error) { return ar.q.Query(ctx, query) }
 	updated := make(map[uint64]struct{})
 	// update list of active alerts
 	for _, m := range qMetrics {
-		for k, v := range ar.Labels {
-			// apply extra labels
+		// extra labels could contain templates, so we expand them first
+		labels, err := expandLabels(m, qFn, ar)
+		if err != nil {
+			return nil, fmt.Errorf("failed to expand labels: %s", err)
+		}
+		for k, v := range labels {
+			// apply extra labels to datasource
+			// so the hash key will be consistent on restore
 			m.SetLabel(k, v)
 		}
-
 		h := hash(m)
 		if _, ok := updated[h]; ok {
 			// duplicate may be caused by extra labels
@@ -153,19 +227,19 @@ func (ar *AlertingRule) Exec(ctx context.Context, q datasource.Querier, series b
 		}
 		updated[h] = struct{}{}
 		if a, ok := ar.alerts[h]; ok {
-			if a.Value != m.Value {
+			if a.Value != m.Values[0] {
 				// update Value field with latest value
-				a.Value = m.Value
+				a.Value = m.Values[0]
 				// and re-exec template since Value can be used
-				// in templates
-				err = ar.template(a)
+				// in annotations
+				a.Annotations, err = a.ExecTemplate(qFn, ar.Annotations)
 				if err != nil {
 					return nil, err
 				}
 			}
 			continue
 		}
-		a, err := ar.newAlert(m, ar.lastExecTime)
+		a, err := ar.newAlert(m, ar.lastExecTime, qFn)
 		if err != nil {
 			ar.lastExecError = err
 			return nil, fmt.Errorf("failed to create alert: %w", err)
@@ -193,13 +267,23 @@ func (ar *AlertingRule) Exec(ctx context.Context, q datasource.Querier, series b
 			alertsFired.Inc()
 		}
 	}
-	if series {
-		return ar.toTimeSeries(ar.lastExecTime), nil
-	}
-	return nil, nil
+	return ar.toTimeSeries(ar.lastExecTime.Unix()), nil
 }
 
-func (ar *AlertingRule) toTimeSeries(timestamp time.Time) []prompbmarshal.TimeSeries {
+func expandLabels(m datasource.Metric, q notifier.QueryFn, ar *AlertingRule) (map[string]string, error) {
+	metricLabels := make(map[string]string)
+	for _, l := range m.Labels {
+		metricLabels[l.Name] = l.Value
+	}
+	tpl := notifier.AlertTplData{
+		Labels: metricLabels,
+		Value:  m.Values[0],
+		Expr:   ar.Expr,
+	}
+	return notifier.ExecTemplate(q, ar.Labels, tpl)
+}
+
+func (ar *AlertingRule) toTimeSeries(timestamp int64) []prompbmarshal.TimeSeries {
 	var tss []prompbmarshal.TimeSeries
 	for _, a := range ar.alerts {
 		if a.State == notifier.StateInactive {
@@ -223,6 +307,8 @@ func (ar *AlertingRule) UpdateWith(r Rule) error {
 	ar.For = nr.For
 	ar.Labels = nr.Labels
 	ar.Annotations = nr.Annotations
+	ar.EvalInterval = nr.EvalInterval
+	ar.q = nr.q
 	return nil
 }
 
@@ -245,18 +331,20 @@ func hash(m datasource.Metric) uint64 {
 	return hash.Sum64()
 }
 
-func (ar *AlertingRule) newAlert(m datasource.Metric, start time.Time) (*notifier.Alert, error) {
+func (ar *AlertingRule) newAlert(m datasource.Metric, start time.Time, qFn notifier.QueryFn) (*notifier.Alert, error) {
 	a := &notifier.Alert{
 		GroupID: ar.GroupID,
 		Name:    ar.Name,
 		Labels:  map[string]string{},
-		Value:   m.Value,
+		Value:   m.Values[0],
 		Start:   start,
 		Expr:    ar.Expr,
 	}
 	// label defined here to make override possible by
 	// time series labels.
-	a.Labels[alertGroupNameLabel] = ar.GroupName
+	if ar.GroupName != "" {
+		a.Labels[alertGroupNameLabel] = ar.GroupName
+	}
 	for _, l := range m.Labels {
 		// drop __name__ to be consistent with Prometheus alerting
 		if l.Name == "__name__" {
@@ -264,17 +352,9 @@ func (ar *AlertingRule) newAlert(m datasource.Metric, start time.Time) (*notifie
 		}
 		a.Labels[l.Name] = l.Value
 	}
-	return a, ar.template(a)
-}
-
-func (ar *AlertingRule) template(a *notifier.Alert) error {
 	var err error
-	a.Labels, err = a.ExecTemplate(a.Labels)
-	if err != nil {
-		return err
-	}
-	a.Annotations, err = a.ExecTemplate(ar.Annotations)
-	return err
+	a.Annotations, err = a.ExecTemplate(qFn, ar.Annotations)
+	return a, err
 }
 
 // AlertAPI generates APIAlert object from alert by its id(hash)
@@ -299,6 +379,7 @@ func (ar *AlertingRule) RuleAPI() APIAlertingRule {
 		// encode as strings to avoid rounding
 		ID:          fmt.Sprintf("%d", ar.ID()),
 		GroupID:     fmt.Sprintf("%d", ar.GroupID),
+		Type:        ar.Type.String(),
 		Name:        ar.Name,
 		Expression:  ar.Expr,
 		For:         ar.For.String(),
@@ -352,7 +433,7 @@ const (
 )
 
 // alertToTimeSeries converts the given alert with the given timestamp to timeseries
-func (ar *AlertingRule) alertToTimeSeries(a *notifier.Alert, timestamp time.Time) []prompbmarshal.TimeSeries {
+func (ar *AlertingRule) alertToTimeSeries(a *notifier.Alert, timestamp int64) []prompbmarshal.TimeSeries {
 	var tss []prompbmarshal.TimeSeries
 	tss = append(tss, alertToTimeSeries(ar.Name, a, timestamp))
 	if ar.For > 0 {
@@ -361,7 +442,7 @@ func (ar *AlertingRule) alertToTimeSeries(a *notifier.Alert, timestamp time.Time
 	return tss
 }
 
-func alertToTimeSeries(name string, a *notifier.Alert, timestamp time.Time) prompbmarshal.TimeSeries {
+func alertToTimeSeries(name string, a *notifier.Alert, timestamp int64) prompbmarshal.TimeSeries {
 	labels := make(map[string]string)
 	for k, v := range a.Labels {
 		labels[k] = v
@@ -369,19 +450,19 @@ func alertToTimeSeries(name string, a *notifier.Alert, timestamp time.Time) prom
 	labels["__name__"] = alertMetricName
 	labels[alertNameLabel] = name
 	labels[alertStateLabel] = a.State.String()
-	return newTimeSeries(1, labels, timestamp)
+	return newTimeSeries([]float64{1}, []int64{timestamp}, labels)
 }
 
 // alertForToTimeSeries returns a timeseries that represents
 // state of active alerts, where value is time when alert become active
-func alertForToTimeSeries(name string, a *notifier.Alert, timestamp time.Time) prompbmarshal.TimeSeries {
+func alertForToTimeSeries(name string, a *notifier.Alert, timestamp int64) prompbmarshal.TimeSeries {
 	labels := make(map[string]string)
 	for k, v := range a.Labels {
 		labels[k] = v
 	}
 	labels["__name__"] = alertForStateMetricName
 	labels[alertNameLabel] = name
-	return newTimeSeries(float64(a.Start.Unix()), labels, timestamp)
+	return newTimeSeries([]float64{float64(a.Start.Unix())}, []int64{timestamp}, labels)
 }
 
 // Restore restores the state of active alerts basing on previously written timeseries.
@@ -393,6 +474,8 @@ func (ar *AlertingRule) Restore(ctx context.Context, q datasource.Querier, lookb
 		return fmt.Errorf("querier is nil")
 	}
 
+	qFn := func(query string) ([]datasource.Metric, error) { return ar.q.Query(ctx, query) }
+
 	// account for external labels in filter
 	var labelsFilter string
 	for k, v := range labels {
@@ -421,7 +504,7 @@ func (ar *AlertingRule) Restore(ctx context.Context, q datasource.Querier, lookb
 			m.Labels = append(m.Labels, l)
 		}
 
-		a, err := ar.newAlert(m, time.Unix(int64(m.Value), 0))
+		a, err := ar.newAlert(m, time.Unix(int64(m.Values[0]), 0), qFn)
 		if err != nil {
 			return fmt.Errorf("failed to create alert: %w", err)
 		}

app/vmalert/alerting_test.go

@@ -3,6 +3,7 @@ package main
 import (
 	"context"
 	"errors"
+	"reflect"
 	"strings"
 	"testing"
 	"time"
@@ -23,11 +24,11 @@ func TestAlertingRule_ToTimeSeries(t *testing.T) {
 			newTestAlertingRule("instant", 0),
 			&notifier.Alert{State: notifier.StateFiring},
 			[]prompbmarshal.TimeSeries{
-				newTimeSeries(1, map[string]string{
+				newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()}, map[string]string{
 					"__name__":      alertMetricName,
 					alertStateLabel: notifier.StateFiring.String(),
 					alertNameLabel:  "instant",
-				}, timestamp),
+				}),
 			},
 		},
 		{
@@ -37,13 +38,13 @@ func TestAlertingRule_ToTimeSeries(t *testing.T) {
 				"instance": "bar",
 			}},
 			[]prompbmarshal.TimeSeries{
-				newTimeSeries(1, map[string]string{
+				newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()}, map[string]string{
 					"__name__":      alertMetricName,
 					alertStateLabel: notifier.StateFiring.String(),
 					alertNameLabel:  "instant extra labels",
 					"job":           "foo",
 					"instance":      "bar",
-				}, timestamp),
+				}),
 			},
 		},
 		{
@@ -53,48 +54,52 @@ func TestAlertingRule_ToTimeSeries(t *testing.T) {
 				"__name__":      "bar",
 			}},
 			[]prompbmarshal.TimeSeries{
-				newTimeSeries(1, map[string]string{
+				newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()}, map[string]string{
 					"__name__":      alertMetricName,
 					alertStateLabel: notifier.StateFiring.String(),
 					alertNameLabel:  "instant labels override",
-				}, timestamp),
+				}),
 			},
 		},
 		{
 			newTestAlertingRule("for", time.Second),
 			&notifier.Alert{State: notifier.StateFiring, Start: timestamp.Add(time.Second)},
 			[]prompbmarshal.TimeSeries{
-				newTimeSeries(1, map[string]string{
+				newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()}, map[string]string{
 					"__name__":      alertMetricName,
 					alertStateLabel: notifier.StateFiring.String(),
 					alertNameLabel:  "for",
-				}, timestamp),
-				newTimeSeries(float64(timestamp.Add(time.Second).Unix()), map[string]string{
-					"__name__":     alertForStateMetricName,
-					alertNameLabel: "for",
-				}, timestamp),
+				}),
+				newTimeSeries([]float64{float64(timestamp.Add(time.Second).Unix())},
+					[]int64{timestamp.UnixNano()},
+					map[string]string{
+						"__name__":     alertForStateMetricName,
+						alertNameLabel: "for",
+					}),
 			},
 		},
 		{
 			newTestAlertingRule("for pending", 10*time.Second),
 			&notifier.Alert{State: notifier.StatePending, Start: timestamp.Add(time.Second)},
 			[]prompbmarshal.TimeSeries{
-				newTimeSeries(1, map[string]string{
+				newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()}, map[string]string{
 					"__name__":      alertMetricName,
 					alertStateLabel: notifier.StatePending.String(),
 					alertNameLabel:  "for pending",
-				}, timestamp),
-				newTimeSeries(float64(timestamp.Add(time.Second).Unix()), map[string]string{
-					"__name__":     alertForStateMetricName,
-					alertNameLabel: "for pending",
-				}, timestamp),
+				}),
+				newTimeSeries([]float64{float64(timestamp.Add(time.Second).Unix())},
+					[]int64{timestamp.UnixNano()},
+					map[string]string{
+						"__name__":     alertForStateMetricName,
+						alertNameLabel: "for pending",
+					}),
 			},
 		},
 	}
 	for _, tc := range testCases {
 		t.Run(tc.rule.Name, func(t *testing.T) {
 			tc.rule.alerts[tc.alert.ID] = tc.alert
-			tss := tc.rule.toTimeSeries(timestamp)
+			tss := tc.rule.toTimeSeries(timestamp.Unix())
 			if err := compareTimeSeries(t, tc.expTS, tss); err != nil {
 				t.Fatalf("timeseries missmatch: %s", err)
 			}
@@ -117,7 +122,7 @@ func TestAlertingRule_Exec(t *testing.T) {
 		{
 			newTestAlertingRule("empty labels", 0),
 			[][]datasource.Metric{
-				{datasource.Metric{}},
+				{datasource.Metric{Values: []float64{1}, Timestamps: []int64{1}}},
 			},
 			map[uint64]*notifier.Alert{
 				hash(datasource.Metric{}): {State: notifier.StateFiring},
@@ -293,11 +298,12 @@ func TestAlertingRule_Exec(t *testing.T) {
 	for _, tc := range testCases {
 		t.Run(tc.rule.Name, func(t *testing.T) {
 			fq := &fakeQuerier{}
+			tc.rule.q = fq
 			tc.rule.GroupID = fakeGroup.ID()
 			for _, step := range tc.steps {
 				fq.reset()
 				fq.add(step...)
-				if _, err := tc.rule.Exec(context.TODO(), fq, false); err != nil {
+				if _, err := tc.rule.Exec(context.TODO()); err != nil {
 					t.Fatalf("unexpected err: %s", err)
 				}
 				// artificial delay between applying steps
@@ -319,6 +325,166 @@ func TestAlertingRule_Exec(t *testing.T) {
 	}
 }
 
+func TestAlertingRule_ExecRange(t *testing.T) {
+	testCases := []struct {
+		rule      *AlertingRule
+		data      []datasource.Metric
+		expAlerts []*notifier.Alert
+	}{
+		{
+			newTestAlertingRule("empty", 0),
+			[]datasource.Metric{},
+			nil,
+		},
+		{
+			newTestAlertingRule("empty labels", 0),
+			[]datasource.Metric{
+				{Values: []float64{1}, Timestamps: []int64{1}},
+			},
+			[]*notifier.Alert{
+				{State: notifier.StateFiring},
+			},
+		},
+		{
+			newTestAlertingRule("single-firing", 0),
+			[]datasource.Metric{
+				metricWithLabels(t, "name", "foo"),
+			},
+			[]*notifier.Alert{
+				{
+					Labels: map[string]string{"name": "foo"},
+					State:  notifier.StateFiring,
+				},
+			},
+		},
+		{
+			newTestAlertingRule("single-firing-on-range", 0),
+			[]datasource.Metric{
+				{Values: []float64{1, 1, 1}, Timestamps: []int64{1e3, 2e3, 3e3}},
+			},
+			[]*notifier.Alert{
+				{State: notifier.StateFiring},
+				{State: notifier.StateFiring},
+				{State: notifier.StateFiring},
+			},
+		},
+		{
+			newTestAlertingRule("for-pending", time.Second),
+			[]datasource.Metric{
+				{Values: []float64{1, 1, 1}, Timestamps: []int64{1, 3, 5}},
+			},
+			[]*notifier.Alert{
+				{State: notifier.StatePending, Start: time.Unix(1, 0)},
+				{State: notifier.StatePending, Start: time.Unix(3, 0)},
+				{State: notifier.StatePending, Start: time.Unix(5, 0)},
+			},
+		},
+		{
+			newTestAlertingRule("for-firing", 3*time.Second),
+			[]datasource.Metric{
+				{Values: []float64{1, 1, 1}, Timestamps: []int64{1, 3, 5}},
+			},
+			[]*notifier.Alert{
+				{State: notifier.StatePending, Start: time.Unix(1, 0)},
+				{State: notifier.StatePending, Start: time.Unix(1, 0)},
+				{State: notifier.StateFiring, Start: time.Unix(1, 0)},
+			},
+		},
+		{
+			newTestAlertingRule("for=>pending=>firing=>pending=>firing=>pending", time.Second),
+			[]datasource.Metric{
+				{Values: []float64{1, 1, 1, 1, 1}, Timestamps: []int64{1, 2, 5, 6, 20}},
+			},
+			[]*notifier.Alert{
+				{State: notifier.StatePending, Start: time.Unix(1, 0)},
+				{State: notifier.StateFiring, Start: time.Unix(1, 0)},
+				{State: notifier.StatePending, Start: time.Unix(5, 0)},
+				{State: notifier.StateFiring, Start: time.Unix(5, 0)},
+				{State: notifier.StatePending, Start: time.Unix(20, 0)},
+			},
+		},
+		{
+			newTestAlertingRule("multi-series-for=>pending=>pending=>firing", 3*time.Second),
+			[]datasource.Metric{
+				{Values: []float64{1, 1, 1}, Timestamps: []int64{1, 3, 5}},
+				{Values: []float64{1, 1}, Timestamps: []int64{1, 5},
+					Labels: []datasource.Label{{Name: "foo", Value: "bar"}},
+				},
+			},
+			[]*notifier.Alert{
+				{State: notifier.StatePending, Start: time.Unix(1, 0)},
+				{State: notifier.StatePending, Start: time.Unix(1, 0)},
+				{State: notifier.StateFiring, Start: time.Unix(1, 0)},
+				//
+				{State: notifier.StatePending, Start: time.Unix(1, 0),
+					Labels: map[string]string{
+						"foo": "bar",
+					}},
+				{State: notifier.StatePending, Start: time.Unix(5, 0),
+					Labels: map[string]string{
+						"foo": "bar",
+					}},
+			},
+		},
+		{
+			newTestRuleWithLabels("multi-series-firing", "source", "vm"),
+			[]datasource.Metric{
+				{Values: []float64{1, 1}, Timestamps: []int64{1, 100}},
+				{Values: []float64{1, 1}, Timestamps: []int64{1, 5},
+					Labels: []datasource.Label{{Name: "foo", Value: "bar"}},
+				},
+			},
+			[]*notifier.Alert{
+				{State: notifier.StateFiring, Labels: map[string]string{
+					"source": "vm",
+				}},
+				{State: notifier.StateFiring, Labels: map[string]string{
+					"source": "vm",
+				}},
+				//
+				{State: notifier.StateFiring, Labels: map[string]string{
+					"foo":    "bar",
+					"source": "vm",
+				}},
+				{State: notifier.StateFiring, Labels: map[string]string{
+					"foo":    "bar",
+					"source": "vm",
+				}},
+			},
+		},
+	}
+	fakeGroup := Group{Name: "TestRule_ExecRange"}
+	for _, tc := range testCases {
+		t.Run(tc.rule.Name, func(t *testing.T) {
+			fq := &fakeQuerier{}
+			tc.rule.q = fq
+			tc.rule.GroupID = fakeGroup.ID()
+			fq.add(tc.data...)
+			gotTS, err := tc.rule.ExecRange(context.TODO(), time.Now(), time.Now())
+			if err != nil {
+				t.Fatalf("unexpected err: %s", err)
+			}
+			var expTS []prompbmarshal.TimeSeries
+			var j int
+			for _, series := range tc.data {
+				for _, timestamp := range series.Timestamps {
+					expTS = append(expTS, tc.rule.alertToTimeSeries(tc.expAlerts[j], timestamp)...)
+					j++
+				}
+			}
+			if len(gotTS) != len(expTS) {
+				t.Fatalf("expected %d time series; got %d", len(expTS), len(gotTS))
+			}
+			for i := range expTS {
+				got, exp := gotTS[i], expTS[i]
+				if !reflect.DeepEqual(got, exp) {
+					t.Fatalf("%d: expected \n%v but got \n%v", i, exp, got)
+				}
+			}
+		})
+	}
+}
+
 func TestAlertingRule_Restore(t *testing.T) {
 	testCases := []struct {
 		rule      *AlertingRule
@@ -409,6 +575,7 @@ func TestAlertingRule_Restore(t *testing.T) {
 		t.Run(tc.rule.Name, func(t *testing.T) {
 			fq := &fakeQuerier{}
 			tc.rule.GroupID = fakeGroup.ID()
+			tc.rule.q = fq
 			fq.add(tc.metrics...)
 			if err := tc.rule.Restore(context.TODO(), fq, time.Hour, nil); err != nil {
 				t.Fatalf("unexpected err: %s", err)
@@ -436,17 +603,18 @@ func TestAlertingRule_Exec_Negative(t *testing.T) {
 	fq := &fakeQuerier{}
 	ar := newTestAlertingRule("test", 0)
 	ar.Labels = map[string]string{"job": "test"}
+	ar.q = fq
 
 	// successful attempt
 	fq.add(metricWithValueAndLabels(t, 1, "__name__", "foo", "job", "bar"))
-	_, err := ar.Exec(context.TODO(), fq, false)
+	_, err := ar.Exec(context.TODO())
 	if err != nil {
 		t.Fatal(err)
 	}
 
 	// label `job` will collide with rule extra label and will make both time series equal
 	fq.add(metricWithValueAndLabels(t, 1, "__name__", "foo", "job", "baz"))
-	_, err = ar.Exec(context.TODO(), fq, false)
+	_, err = ar.Exec(context.TODO())
 	if !errors.Is(err, errDuplicate) {
 		t.Fatalf("expected to have %s error; got %s", errDuplicate, err)
 	}
@@ -455,7 +623,7 @@ func TestAlertingRule_Exec_Negative(t *testing.T) {
 
 	expErr := "connection reset by peer"
 	fq.setErr(errors.New(expErr))
-	_, err = ar.Exec(context.TODO(), fq, false)
+	_, err = ar.Exec(context.TODO())
 	if err == nil {
 		t.Fatalf("expected to get err; got nil")
 	}
@@ -464,6 +632,103 @@ func TestAlertingRule_Exec_Negative(t *testing.T) {
 	}
 }
 
+func TestAlertingRule_Template(t *testing.T) {
+	testCases := []struct {
+		rule      *AlertingRule
+		metrics   []datasource.Metric
+		expAlerts map[uint64]*notifier.Alert
+	}{
+		{
+			newTestRuleWithLabels("common", "region", "east"),
+			[]datasource.Metric{
+				metricWithValueAndLabels(t, 1, "instance", "foo"),
+				metricWithValueAndLabels(t, 1, "instance", "bar"),
+			},
+			map[uint64]*notifier.Alert{
+				hash(metricWithLabels(t, "region", "east", "instance", "foo")): {
+					Annotations: map[string]string{},
+					Labels: map[string]string{
+						"region":   "east",
+						"instance": "foo",
+					},
+				},
+				hash(metricWithLabels(t, "region", "east", "instance", "bar")): {
+					Annotations: map[string]string{},
+					Labels: map[string]string{
+						"region":   "east",
+						"instance": "bar",
+					},
+				},
+			},
+		},
+		{
+			&AlertingRule{
+				Name: "override label",
+				Labels: map[string]string{
+					"instance": "{{ $labels.instance }}",
+					"region":   "east",
+				},
+				Annotations: map[string]string{
+					"summary":     `Too high connection number for "{{ $labels.instance }}" for region {{ $labels.region }}`,
+					"description": `It is {{ $value }} connections for "{{ $labels.instance }}"`,
+				},
+				alerts: make(map[uint64]*notifier.Alert),
+			},
+			[]datasource.Metric{
+				metricWithValueAndLabels(t, 2, "instance", "foo"),
+				metricWithValueAndLabels(t, 10, "instance", "bar"),
+			},
+			map[uint64]*notifier.Alert{
+				hash(metricWithLabels(t, "region", "east", "instance", "foo")): {
+					Labels: map[string]string{
+						"instance": "foo",
+						"region":   "east",
+					},
+					Annotations: map[string]string{
+						"summary":     `Too high connection number for "foo" for region east`,
+						"description": `It is 2 connections for "foo"`,
+					},
+				},
+				hash(metricWithLabels(t, "region", "east", "instance", "bar")): {
+					Labels: map[string]string{
+						"instance": "bar",
+						"region":   "east",
+					},
+					Annotations: map[string]string{
+						"summary":     `Too high connection number for "bar" for region east`,
+						"description": `It is 10 connections for "bar"`,
+					},
+				},
+			},
+		},
+	}
+	fakeGroup := Group{Name: "TestRule_Exec"}
+	for _, tc := range testCases {
+		t.Run(tc.rule.Name, func(t *testing.T) {
+			fq := &fakeQuerier{}
+			tc.rule.GroupID = fakeGroup.ID()
+			tc.rule.q = fq
+			fq.add(tc.metrics...)
+			if _, err := tc.rule.Exec(context.TODO()); err != nil {
+				t.Fatalf("unexpected err: %s", err)
+			}
+			for hash, expAlert := range tc.expAlerts {
+				gotAlert := tc.rule.alerts[hash]
+				if gotAlert == nil {
+					t.Fatalf("alert %d is missing; labels: %v; annotations: %v",
+						hash, expAlert.Labels, expAlert.Annotations)
+				}
+				if !reflect.DeepEqual(expAlert.Annotations, gotAlert.Annotations) {
+					t.Fatalf("expected to have annotations %#v; got %#v", expAlert.Annotations, gotAlert.Annotations)
+				}
+				if !reflect.DeepEqual(expAlert.Labels, gotAlert.Labels) {
+					t.Fatalf("expected to have labels %#v; got %#v", expAlert.Labels, gotAlert.Labels)
+				}
+			}
+		})
+	}
+}
+
 func newTestRuleWithLabels(name string, labels ...string) *AlertingRule {
 	r := newTestAlertingRule(name, 0)
 	r.Labels = make(map[string]string)
@@ -474,5 +739,5 @@ func newTestRuleWithLabels(name string, labels ...string) *AlertingRule {
 }
 
 func newTestAlertingRule(name string, waitFor time.Duration) *AlertingRule {
-	return &AlertingRule{Name: name, alerts: make(map[uint64]*notifier.Alert), For: waitFor}
+	return &AlertingRule{Name: name, alerts: make(map[uint64]*notifier.Alert), For: waitFor, EvalInterval: waitFor}
 }

app/vmalert/config/config.go

@@ -8,24 +8,29 @@ import (
 	"path/filepath"
 	"sort"
 	"strings"
-	"time"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/utils"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/envtemplate"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
-	"github.com/VictoriaMetrics/metricsql"
 	"gopkg.in/yaml.v2"
 )
 
 // Group contains list of Rules grouped into
 // entity with one name and evaluation interval
 type Group struct {
+	Type        datasource.Type `yaml:"type,omitempty"`
 	File        string
-	Name        string        `yaml:"name"`
-	Interval    time.Duration `yaml:"interval,omitempty"`
-	Rules       []Rule        `yaml:"rules"`
-	Concurrency int           `yaml:"concurrency"`
+	Name        string             `yaml:"name"`
+	Interval    utils.PromDuration `yaml:"interval,omitempty"`
+	Rules       []Rule             `yaml:"rules"`
+	Concurrency int                `yaml:"concurrency"`
+	// ExtraFilterLabels is a list label filters applied to every rule
+	// request withing a group. Is compatible only with VM datasources.
+	// See https://docs.victoriametrics.com#prometheus-querying-api-enhancements
+	ExtraFilterLabels map[string]string `yaml:"extra_filter_labels"`
 	// Checksum stores the hash of yaml definition for this group.
 	// May be used to detect any changes like rules re-ordering etc.
 	Checksum string
@@ -44,6 +49,19 @@ func (g *Group) UnmarshalYAML(unmarshal func(interface{}) error) error {
 	if err != nil {
 		return fmt.Errorf("failed to marshal group configuration for checksum: %w", err)
 	}
+	// change default value to prometheus datasource.
+	if g.Type.Get() == "" {
+		g.Type.Set(datasource.NewPrometheusType())
+	}
+	// update rules with empty type.
+	for i, r := range g.Rules {
+		if r.Type.Get() == "" {
+			r.Type.Set(g.Type)
+			r.ID = HashRule(r)
+			g.Rules[i] = r
+		}
+	}
+
 	h := md5.New()
 	h.Write(b)
 	g.Checksum = fmt.Sprintf("%x", h.Sum(nil))
@@ -58,6 +76,7 @@ func (g *Group) Validate(validateAnnotations, validateExpressions bool) error {
 	if len(g.Rules) == 0 {
 		return fmt.Errorf("group %q can't contain no rules", g.Name)
 	}
+
 	uniqueRules := map[uint64]struct{}{}
 	for _, r := range g.Rules {
 		ruleName := r.Record
@@ -72,7 +91,13 @@ func (g *Group) Validate(validateAnnotations, validateExpressions bool) error {
 			return fmt.Errorf("invalid rule %q.%q: %w", g.Name, ruleName, err)
 		}
 		if validateExpressions {
-			if _, err := metricsql.Parse(r.Expr); err != nil {
+			// its needed only for tests.
+			// because correct types must be inherited after unmarshalling.
+			exprValidator := g.Type.ValidateExpr
+			if r.Type.Get() != "" {
+				exprValidator = r.Type.ValidateExpr
+			}
+			if err := exprValidator(r.Expr); err != nil {
 				return fmt.Errorf("invalid expression for rule %q.%q: %w", g.Name, ruleName, err)
 			}
 		}
@@ -92,48 +117,18 @@ func (g *Group) Validate(validateAnnotations, validateExpressions bool) error {
 // recording rule or alerting rule.
 type Rule struct {
 	ID          uint64
-	Record      string            `yaml:"record,omitempty"`
-	Alert       string            `yaml:"alert,omitempty"`
-	Expr        string            `yaml:"expr"`
-	For         PromDuration      `yaml:"for,omitempty"`
-	Labels      map[string]string `yaml:"labels,omitempty"`
-	Annotations map[string]string `yaml:"annotations,omitempty"`
+	Type        datasource.Type    `yaml:"type,omitempty"`
+	Record      string             `yaml:"record,omitempty"`
+	Alert       string             `yaml:"alert,omitempty"`
+	Expr        string             `yaml:"expr"`
+	For         utils.PromDuration `yaml:"for"`
+	Labels      map[string]string  `yaml:"labels,omitempty"`
+	Annotations map[string]string  `yaml:"annotations,omitempty"`
 
 	// Catches all undefined fields and must be empty after parsing.
 	XXX map[string]interface{} `yaml:",inline"`
 }
 
-// PromDuration is Prometheus duration.
-type PromDuration struct {
-	milliseconds int64
-}
-
-// NewPromDuration returns PromDuration for given d.
-func NewPromDuration(d time.Duration) PromDuration {
-	return PromDuration{
-		milliseconds: d.Milliseconds(),
-	}
-}
-
-// UnmarshalYAML implements yaml.Unmarshaler interface.
-func (pd *PromDuration) UnmarshalYAML(unmarshal func(interface{}) error) error {
-	var s string
-	if err := unmarshal(&s); err != nil {
-		return err
-	}
-	ms, err := metricsql.DurationValue(s, 0)
-	if err != nil {
-		return err
-	}
-	pd.milliseconds = ms
-	return nil
-}
-
-// Duration returns duration for pd.
-func (pd *PromDuration) Duration() time.Duration {
-	return time.Duration(pd.milliseconds) * time.Millisecond
-}
-
 // UnmarshalYAML implements the yaml.Unmarshaler interface.
 func (r *Rule) UnmarshalYAML(unmarshal func(interface{}) error) error {
 	type rule Rule
@@ -164,6 +159,7 @@ func HashRule(r Rule) uint64 {
 		h.Write([]byte("alerting"))
 		h.Write([]byte(r.Alert))
 	}
+	h.Write([]byte(r.Type.Get()))
 	kv := sortMap(r.Labels)
 	for _, i := range kv {
 		h.Write([]byte(i.key))

app/vmalert/config/config_test.go

@@ -7,7 +7,9 @@ import (
 	"testing"
 	"time"
 
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/utils"
 	"gopkg.in/yaml.v2"
 )
 
@@ -42,7 +44,7 @@ func TestParseBad(t *testing.T) {
 		},
 		{
 			[]string{"testdata/dir/rules2-bad.rules"},
-			"function \"value\" not defined",
+			"function \"unknown\" not defined",
 		},
 		{
 			[]string{"testdata/dir/rules3-bad.rules"},
@@ -52,6 +54,10 @@ func TestParseBad(t *testing.T) {
 			[]string{"testdata/dir/rules4-bad.rules"},
 			"either `record` or `alert` must be set",
 		},
+		{
+			[]string{"testdata/rules1-bad.rules"},
+			"bad graphite expr",
+		},
 	}
 	for _, tc := range testCases {
 		_, err := Parse(tc.path, true, true)
@@ -137,12 +143,14 @@ func TestGroup_Validate(t *testing.T) {
 						Alert: "alert",
 						Expr:  "up == 1",
 						Labels: map[string]string{
-							"summary": "{{ value|query }}",
+							"summary": `
+{{ with printf "node_memory_MemTotal{job='node',instance='%s'}" "localhost" | query }}
+  {{ . | first | value | humanize1024 }}B
+{{ end }}`,
 						},
 					},
 				},
 			},
-			expErr:              "error parsing annotation",
 			validateAnnotations: true,
 		},
 		{
@@ -212,6 +220,75 @@ func TestGroup_Validate(t *testing.T) {
 			},
 			expErr: "",
 		},
+		{
+			group: &Group{Name: "test thanos",
+				Type: datasource.NewRawType("thanos"),
+				Rules: []Rule{
+					{Alert: "alert", Expr: "up == 1", Labels: map[string]string{
+						"description": "{{ value|query }}",
+					}},
+				},
+			},
+			validateExpressions: true,
+			expErr:              "unknown datasource type",
+		},
+		{
+			group: &Group{Name: "test graphite",
+				Type: datasource.NewGraphiteType(),
+				Rules: []Rule{
+					{Alert: "alert", Expr: "up == 1", Labels: map[string]string{
+						"description": "some-description",
+					}},
+				},
+			},
+			validateExpressions: true,
+			expErr:              "",
+		},
+		{
+			group: &Group{Name: "test prometheus",
+				Type: datasource.NewPrometheusType(),
+				Rules: []Rule{
+					{Alert: "alert", Expr: "up == 1", Labels: map[string]string{
+						"description": "{{ value|query }}",
+					}},
+				},
+			},
+			validateExpressions: true,
+			expErr:              "",
+		},
+		{
+			group: &Group{
+				Name: "test graphite inherit",
+				Type: datasource.NewGraphiteType(),
+				Rules: []Rule{
+					{
+						Expr: "sumSeries(time('foo.bar',10))",
+						For:  utils.NewPromDuration(10 * time.Millisecond),
+					},
+					{
+						Expr: "sum(up == 0 ) by (host)",
+						Type: datasource.NewPrometheusType(),
+					},
+				},
+			},
+		},
+		{
+			group: &Group{
+				Name: "test graphite prometheus bad expr",
+				Type: datasource.NewGraphiteType(),
+				Rules: []Rule{
+					{
+						Expr: "sum(up == 0 ) by (host)",
+						For:  utils.NewPromDuration(10 * time.Millisecond),
+					},
+					{
+						Expr: "sumSeries(time('foo.bar',10))",
+						Type: datasource.NewPrometheusType(),
+					},
+				},
+			},
+			expErr: "invalid rule",
+		},
 	}
 	for _, tc := range testCases {
 		err := tc.group.Validate(tc.validateAnnotations, tc.validateExpressions)
@@ -270,7 +347,7 @@ func TestHashRule(t *testing.T) {
 			true,
 		},
 		{
-			Rule{Alert: "alert", Expr: "up == 1", For: NewPromDuration(time.Minute)},
+			Rule{Alert: "alert", Expr: "up == 1", For: utils.NewPromDuration(time.Minute)},
 			Rule{Alert: "alert", Expr: "up == 1"},
 			true,
 		},
@@ -323,34 +400,55 @@ func TestHashRule(t *testing.T) {
 }
 
 func TestGroupChecksum(t *testing.T) {
-	data := `
+	f := func(t *testing.T, data, newData string) {
+		t.Helper()
+		var g Group
+		if err := yaml.Unmarshal([]byte(data), &g); err != nil {
+			t.Fatalf("failed to unmarshal: %s", err)
+		}
+		if g.Checksum == "" {
+			t.Fatalf("expected to get non-empty checksum")
+		}
+
+		var ng Group
+		if err := yaml.Unmarshal([]byte(newData), &ng); err != nil {
+			t.Fatalf("failed to unmarshal: %s", err)
+		}
+		if g.Checksum == ng.Checksum {
+			t.Fatalf("expected to get different checksums")
+		}
+	}
+	t.Run("Ok", func(t *testing.T) {
+		f(t, `
 name: TestGroup
 rules:
   - alert: ExampleAlertAlwaysFiring
     expr: sum by(job) (up == 1)
   - record: handler:requests:rate5m
     expr: sum(rate(prometheus_http_requests_total[5m])) by (handler)
-`
-	var g Group
-	if err := yaml.Unmarshal([]byte(data), &g); err != nil {
-		t.Fatalf("failed to unmarshal: %s", err)
-	}
-	if g.Checksum == "" {
-		t.Fatalf("expected to get non-empty checksum")
-	}
-	newData := `
+`, `
 name: TestGroup
 rules:
   - record: handler:requests:rate5m
     expr: sum(rate(prometheus_http_requests_total[5m])) by (handler)
   - alert: ExampleAlertAlwaysFiring
     expr: sum by(job) (up == 1)
-`
-	var ng Group
-	if err := yaml.Unmarshal([]byte(newData), &g); err != nil {
-		t.Fatalf("failed to unmarshal: %s", err)
-	}
-	if g.Checksum == ng.Checksum {
-		t.Fatalf("expected to get different checksums")
-	}
+`)
+	})
+
+	t.Run("Ok, `for` must change cs", func(t *testing.T) {
+		f(t, `
+name: TestGroup
+rules:
+  - alert: ExampleAlertWithFor
+    expr: sum by(job) (up == 1)
+    for: 5m
+`, `
+name: TestGroup
+rules:
+  - alert: ExampleAlertWithFor
+    expr: sum by(job) (up == 1)
+`)
+	})
+
 }

app/vmalert/config/testdata/dir/rules-update0-good.rules

@@ -0,0 +1,13 @@
+groups:
+  - name: TestUpdateGroup
+    interval: 2s
+    concurrency: 2
+    type: prometheus
+    rules:
+      - alert: up
+        expr: up == 0
+        for: 30s
+      - alert: up graphite
+        expr: filterSeries(time('host.1',20),'>','0')
+        for: 30s
+        type: graphite

app/vmalert/config/testdata/dir/rules-update1-good.rules

@@ -0,0 +1,12 @@
+groups:
+  - name: TestUpdateGroup
+    interval: 30s
+    type: graphite
+    rules:
+      - alert: up
+        expr: filterSeries(time('host.2',20),'>','0')
+        for: 30s
+      - alert: up graphite
+        expr: filterSeries(time('host.1',20),'>','0')
+        for: 30s
+        type: graphite

app/vmalert/config/testdata/dir/rules2-bad.rules

@@ -6,6 +6,6 @@ groups:
         expr: vm_rows > 0
         labels:
           label: bar
-          summary: "{{ value|query }}"
+          summary: "{{ unknown|query }}"
         annotations:
           description: "{{$labels}}"

app/vmalert/config/testdata/rules-query-good.rules

@@ -0,0 +1,15 @@
+groups:
+  - name: alertmanager.rules
+    rules:
+      - alert: AlertmanagerConfigInconsistent
+        annotations:
+          message: |
+            The configuration of the instances of the Alertmanager cluster `{{ $labels.namespace }}/{{ $labels.service }}` are out of sync.
+            {{ range printf "alertmanager_config_hash{namespace=\"%s\",service=\"%s\"}" $labels.namespace $labels.service | query }}
+            Configuration hash for pod {{ .Labels.pod }} is "{{ printf "%.f" .Value }}"
+            {{ end }}
+        expr: |
+          count by(namespace,service) (count_values by(namespace,service) ("config_hash", alertmanager_config_hash{job="alertmanager-main",namespace="openshift-monitoring"})) != 1
+        for: 5m
+        labels:
+          severity: critical

app/vmalert/config/testdata/rules-replay-good.rules

@@ -0,0 +1,39 @@
+groups:
+  - name: ReplayGroup
+    interval: 1m
+    concurrency: 1
+    rules:
+      - record: type:vm_cache_entries:rate5m
+        expr: sum(rate(vm_cache_entries[5m])) by (type)
+        labels:
+          recording: true
+      - record: go_cgo_calls_count:rate5m
+        expr: rate(go_cgo_calls_count{job="vmdb"}[5m])
+        labels:
+          recording: true
+
+  - name: vmsingleReplay
+    interval: 30s
+    concurrency: 2
+    rules:
+      - alert: RequestErrorsToAPI
+        expr: increase(vm_http_request_errors_total[5m]) > 0
+        for: 15m
+        labels:
+          severity: warning
+        annotations:
+          dashboard: "http://localhost:3000/d/wNf0q_kZk?viewPanel=35&var-instance={{ $labels.instance }}"
+          summary: "Too many errors served for path {{ $labels.path }} (instance {{ $labels.instance }})"
+          description: "Requests to path {{ $labels.path }} are receiving errors.
+            Please verify if clients are sending correct requests."
+
+      - alert: TooManyLogs
+        expr: sum(increase(vm_log_messages_total{level!="info"}[5m])) by (job, instance) > 0
+        for: 15m
+        labels:
+          severity: warning
+        annotations:
+          dashboard: "http://localhost:3000/d/wNf0q_kZk?viewPanel=67&var-instance={{ $labels.instance }}"
+          summary: "Too many logs printed for job \"{{ $labels.job }}\" ({{ $labels.instance }})"
+          description: "Logging rate for job \"{{ $labels.job }}\" ({{ $labels.instance }}) is {{ $value }} for last 15m.\n
+           Worth to check logs for specific error messages."

app/vmalert/config/testdata/rules1-bad.rules

@@ -0,0 +1,12 @@
+groups:
+  - name: TestGraphiteBadGroup
+    interval: 2s
+    concurrency: 2
+    type: graphite
+    rules:
+      - alert: Conns
+        expr: filterSeries(sumSeries(host.receiver.interface.cons),'last','>', 500) by instance
+        for: 3m
+        annotations:
+          summary: Too high connection number for {{$labels.instance}}
+          description: "It is {{ $value }} connections for {{$labels.instance}}"

app/vmalert/config/testdata/rules2-good.rules

@@ -2,16 +2,29 @@ groups:
   - name: TestGroup
     interval: 2s
     concurrency: 2
+    extra_filter_labels:
+        job: victoriametrics
     rules:
       - alert: Conns
         expr: sum(vm_tcplistener_conns) by(instance) > 1
         for: 3m
         annotations:
-          summary: "Too high connection number for {{$labels.instance}}"
+          summary: Too high connection number for {{$labels.instance}}
+            {{ with printf "sum(vm_tcplistener_conns{instance=%q})" .Labels.instance | query }}
+              {{ . | first | value }}
+            {{ end }}
           description: "It is {{ $value }} connections for {{$labels.instance}}"
       - alert: ExampleAlertAlwaysFiring
         expr: sum by(job)
           (up == 1)
+        labels:
+          job: '{{ $labels.job }}'
+          dynamic: '{{ $x := query "up" | first | value }}{{ if eq 1.0 $x }}one{{ else }}unknown{{ end }}'
+        annotations:
+          description: Job {{ $labels.job }} is up!
+          summary: All instances up {{ range query "up" }}
+            {{ . | label "instance" }}
+            {{ end }}
       - record: handler:requests:rate5m
         expr: sum(rate(prometheus_http_requests_total[5m])) by (handler)
         labels:

app/vmalert/config/testdata/rules3-good.rules

@@ -0,0 +1,30 @@
+groups:
+  - name: TestGroup
+    interval: 2s
+    concurrency: 2
+    type: graphite
+    rules:
+      - alert: Conns
+        expr: filterSeries(sumSeries(host.receiver.interface.cons),'last','>', 500)
+        for: 3m
+        annotations:
+          summary: Too high connection number for {{$labels.instance}}
+          description: "It is {{ $value }} connections for {{$labels.instance}}"
+  - name: TestGroupPromMixed
+    interval: 2s
+    concurrency: 2
+    type: prometheus
+    rules:
+      - alert: Conns
+        expr: sum(vm_tcplistener_conns) by (instance) > 1
+        for: 3m
+        annotations:
+          summary: Too high connection number for {{$labels.instance}}
+          description: "It is {{ $value }} connections for {{$labels.instance}}"
+      - alert: HostDown
+        type: graphite
+        expr: filterSeries(sumSeries(host.receiver.interface.up),'last','=', 0)
+        for: 3m
+        annotations:
+          summary: Too high connection number for {{$labels.instance}}
+          description: "It is {{ $value }} connections for {{$labels.instance}}"

app/vmalert/datasource/datasource.go

@@ -1,20 +1,34 @@
 package datasource
 
-import "context"
+import (
+	"context"
+	"time"
+)
 
-// Querier interface wraps Query method which
-// executes given query and returns list of Metrics
-// as result
+// Querier interface wraps Query and QueryRange methods
 type Querier interface {
 	Query(ctx context.Context, query string) ([]Metric, error)
+	QueryRange(ctx context.Context, query string, from, to time.Time) ([]Metric, error)
+}
+
+// QuerierBuilder builds Querier with given params.
+type QuerierBuilder interface {
+	BuildWithParams(params QuerierParams) Querier
+}
+
+// QuerierParams params for Querier.
+type QuerierParams struct {
+	DataSourceType     *Type
+	EvaluationInterval time.Duration
+	// see https://docs.victoriametrics.com/#prometheus-querying-api-enhancements
+	ExtraLabels map[string]string
 }
 
 // Metric is the basic entity which should be return by datasource
-// It represents single data point with full list of labels
 type Metric struct {
-	Labels    []Label
-	Timestamp int64
-	Value     float64
+	Labels     []Label
+	Timestamps []int64
+	Values     []float64
 }
 
 // SetLabel adds or updates existing one label
@@ -34,6 +48,17 @@ func (m *Metric) AddLabel(key, value string) {
 	m.Labels = append(m.Labels, Label{Name: key, Value: value})
 }
 
+// Label returns the given label value.
+// If label is missing empty string will be returned
+func (m *Metric) Label(key string) string {
+	for _, l := range m.Labels {
+		if l.Name == key {
+			return l.Value
+		}
+	}
+	return ""
+}
+
 // Label represents metric's label
 type Label struct {
 	Name  string

app/vmalert/datasource/datasource_test.go

@@ -0,0 +1,18 @@
+package datasource
+
+import "testing"
+
+func TestMetric_Label(t *testing.T) {
+	m := &Metric{}
+
+	m.AddLabel("foo", "bar")
+	checkEqualString(t, "bar", m.Label("foo"))
+
+	m.SetLabel("foo", "baz")
+	checkEqualString(t, "baz", m.Label("foo"))
+
+	m.SetLabel("qux", "quux")
+	checkEqualString(t, "quux", m.Label("qux"))
+
+	checkEqualString(t, "", m.Label("non-existing"))
+}

app/vmalert/datasource/init.go

@@ -4,40 +4,59 @@ import (
 	"flag"
 	"fmt"
 	"net/http"
+	"strings"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/utils"
 )
 
 var (
-	addr = flag.String("datasource.url", "", "Victoria Metrics or VMSelect url. Required parameter."+
-		" E.g. http://127.0.0.1:8428")
+	addr = flag.String("datasource.url", "", "VictoriaMetrics or vmselect url. Required parameter. "+
+		"E.g. http://127.0.0.1:8428")
+	appendTypePrefix  = flag.Bool("datasource.appendTypePrefix", false, "Whether to add type prefix to -datasource.url based on the query type. Set to true if sending different query types to the vmselect URL.")
 	basicAuthUsername = flag.String("datasource.basicAuth.username", "", "Optional basic auth username for -datasource.url")
 	basicAuthPassword = flag.String("datasource.basicAuth.password", "", "Optional basic auth password for -datasource.url")
 
 	tlsInsecureSkipVerify = flag.Bool("datasource.tlsInsecureSkipVerify", false, "Whether to skip tls verification when connecting to -datasource.url")
 	tlsCertFile           = flag.String("datasource.tlsCertFile", "", "Optional path to client-side TLS certificate file to use when connecting to -datasource.url")
 	tlsKeyFile            = flag.String("datasource.tlsKeyFile", "", "Optional path to client-side TLS certificate key to use when connecting to -datasource.url")
-	tlsCAFile             = flag.String("datasource.tlsCAFile", "", "Optional path to TLS CA file to use for verifying connections to -datasource.url. "+
-		"By default system CA is used")
-	tlsServerName = flag.String("datasource.tlsServerName", "", "Optional TLS server name to use for connections to -datasource.url. "+
-		"By default the server name from -datasource.url is used")
+	tlsCAFile             = flag.String("datasource.tlsCAFile", "", `Optional path to TLS CA file to use for verifying connections to -datasource.url. By default, system CA is used`)
+	tlsServerName         = flag.String("datasource.tlsServerName", "", `Optional TLS server name to use for connections to -datasource.url. By default, the server name from -datasource.url is used`)
 
-	lookBack = flag.Duration("datasource.lookback", 0, "Lookback defines how far to look into past when evaluating queries. "+
-		"For example, if datasource.lookback=5m then param \"time\" with value now()-5m will be added to every query.")
-	maxIdleConnections = flag.Int("datasource.maxIdleConnections", 100, "Defines the number of idle (keep-alive connections) to configured datasource."+
-		"Consider to set this value equal to the value: groups_total * group.concurrency. Too low value may result into high number of sockets in TIME_WAIT state.")
+	lookBack  = flag.Duration("datasource.lookback", 0, `Lookback defines how far into the past to look when evaluating queries. For example, if the datasource.lookback=5m then param "time" with value now()-5m will be added to every query.`)
+	queryStep = flag.Duration("datasource.queryStep", 0, "queryStep defines how far a value can fallback to when evaluating queries. "+
+		"For example, if datasource.queryStep=15s then param \"step\" with value \"15s\" will be added to every query."+
+		"If queryStep isn't specified, rule's evaluationInterval will be used instead.")
+	maxIdleConnections = flag.Int("datasource.maxIdleConnections", 100, `Defines the number of idle (keep-alive connections) to each configured datasource. Consider setting this value equal to the value: groups_total * group.concurrency. Too low a value may result in a high number of sockets in TIME_WAIT state.`)
+	roundDigits        = flag.Int("datasource.roundDigits", 0, `Adds "round_digits" GET param to datasource requests. `+
+		`In VM "round_digits" limits the number of digits after the decimal point in response values.`)
 )
 
 // Init creates a Querier from provided flag values.
-func Init() (Querier, error) {
+func Init() (QuerierBuilder, error) {
 	if *addr == "" {
 		return nil, fmt.Errorf("datasource.url is empty")
 	}
+
 	tr, err := utils.Transport(*addr, *tlsCertFile, *tlsKeyFile, *tlsCAFile, *tlsServerName, *tlsInsecureSkipVerify)
 	if err != nil {
 		return nil, fmt.Errorf("failed to create transport: %w", err)
 	}
-	tr.MaxIdleConns = *maxIdleConnections
-	c := &http.Client{Transport: tr}
-	return NewVMStorage(*addr, *basicAuthUsername, *basicAuthPassword, *lookBack, c), nil
+	tr.MaxIdleConnsPerHost = *maxIdleConnections
+
+	var rd string
+	if *roundDigits > 0 {
+		rd = fmt.Sprintf("%d", *roundDigits)
+	}
+
+	return &VMStorage{
+		c:                &http.Client{Transport: tr},
+		basicAuthUser:    *basicAuthUsername,
+		basicAuthPass:    *basicAuthPassword,
+		datasourceURL:    strings.TrimSuffix(*addr, "/"),
+		appendTypePrefix: *appendTypePrefix,
+		lookBack:         *lookBack,
+		queryStep:        *queryStep,
+		roundDigits:      rd,
+		dataSourceType:   NewPrometheusType(),
+	}, nil
 }

app/vmalert/datasource/type.go

@@ -0,0 +1,89 @@
+package datasource
+
+import (
+	"fmt"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmselect/graphiteql"
+	"github.com/VictoriaMetrics/metricsql"
+)
+
+const graphiteType = "graphite"
+const prometheusType = "prometheus"
+
+// Type represents data source type
+type Type struct {
+	name string
+}
+
+// NewPrometheusType returns prometheus datasource type
+func NewPrometheusType() Type {
+	return Type{name: prometheusType}
+}
+
+// NewGraphiteType returns graphite datasource type
+func NewGraphiteType() Type {
+	return Type{name: graphiteType}
+}
+
+// NewRawType returns datasource type from raw string
+// without validation.
+func NewRawType(d string) Type {
+	return Type{name: d}
+}
+
+// Get returns datasource type
+func (t *Type) Get() string {
+	return t.name
+}
+
+// Set changes datasource type
+func (t *Type) Set(d Type) {
+	t.name = d.name
+}
+
+// String implements String interface with default value.
+func (t Type) String() string {
+	if t.name == "" {
+		return prometheusType
+	}
+	return t.name
+}
+
+// ValidateExpr validates query expression with datasource ql.
+func (t *Type) ValidateExpr(expr string) error {
+	switch t.name {
+	case graphiteType:
+		if _, err := graphiteql.Parse(expr); err != nil {
+			return fmt.Errorf("bad graphite expr: %q, err: %w", expr, err)
+		}
+	case "", prometheusType:
+		if _, err := metricsql.Parse(expr); err != nil {
+			return fmt.Errorf("bad prometheus expr: %q, err: %w", expr, err)
+		}
+	default:
+		return fmt.Errorf("unknown datasource type=%q", t.name)
+	}
+	return nil
+}
+
+// UnmarshalYAML implements the yaml.Unmarshaler interface.
+func (t *Type) UnmarshalYAML(unmarshal func(interface{}) error) error {
+	var s string
+	if err := unmarshal(&s); err != nil {
+		return err
+	}
+	switch s {
+	case "":
+		s = prometheusType
+	case graphiteType, prometheusType:
+	default:
+		return fmt.Errorf("unknown datasource type=%q, want %q or %q", s, prometheusType, graphiteType)
+	}
+	t.name = s
+	return nil
+}
+
+// MarshalYAML implements the yaml.Unmarshaler interface.
+func (t Type) MarshalYAML() (interface{}, error) {
+	return t.name, nil
+}

app/vmalert/datasource/vm.go

@@ -2,83 +2,149 @@ package datasource
 
 import (
 	"context"
-	"encoding/json"
 	"fmt"
 	"io/ioutil"
 	"net/http"
-	"net/url"
-	"strconv"
 	"strings"
 	"time"
 )
 
-type response struct {
-	Status string `json:"status"`
-	Data   struct {
-		ResultType string `json:"resultType"`
-		Result     []struct {
-			Labels map[string]string `json:"metric"`
-			TV     [2]interface{}    `json:"value"`
-		} `json:"result"`
-	} `json:"data"`
-	ErrorType string `json:"errorType"`
-	Error     string `json:"error"`
-}
-
-func (r response) metrics() ([]Metric, error) {
-	var ms []Metric
-	var m Metric
-	var f float64
-	var err error
-	for i, res := range r.Data.Result {
-		f, err = strconv.ParseFloat(res.TV[1].(string), 64)
-		if err != nil {
-			return nil, fmt.Errorf("metric %v, unable to parse float64 from %s: %w", res, res.TV[1], err)
-		}
-		m.Labels = nil
-		for k, v := range r.Data.Result[i].Labels {
-			m.AddLabel(k, v)
-		}
-		m.Timestamp = int64(res.TV[0].(float64))
-		m.Value = f
-		ms = append(ms, m)
-	}
-	return ms, nil
-}
-
 // VMStorage represents vmstorage entity with ability to read and write metrics
 type VMStorage struct {
-	c             *http.Client
-	queryURL      string
-	basicAuthUser string
-	basicAuthPass string
-	lookBack      time.Duration
+	c                *http.Client
+	datasourceURL    string
+	basicAuthUser    string
+	basicAuthPass    string
+	appendTypePrefix bool
+	lookBack         time.Duration
+	queryStep        time.Duration
+	roundDigits      string
+
+	dataSourceType     Type
+	evaluationInterval time.Duration
+	extraLabels        []string
 }
 
-const queryPath = "/api/v1/query?query="
+// Clone makes clone of VMStorage, shares http client.
+func (s *VMStorage) Clone() *VMStorage {
+	return &VMStorage{
+		c:                s.c,
+		datasourceURL:    s.datasourceURL,
+		basicAuthUser:    s.basicAuthUser,
+		basicAuthPass:    s.basicAuthPass,
+		lookBack:         s.lookBack,
+		queryStep:        s.queryStep,
+		appendTypePrefix: s.appendTypePrefix,
+		dataSourceType:   s.dataSourceType,
+	}
+}
+
+// ApplyParams - changes given querier params.
+func (s *VMStorage) ApplyParams(params QuerierParams) *VMStorage {
+	if params.DataSourceType != nil {
+		s.dataSourceType = *params.DataSourceType
+	}
+	s.evaluationInterval = params.EvaluationInterval
+	for k, v := range params.ExtraLabels {
+		s.extraLabels = append(s.extraLabels, fmt.Sprintf("%s=%s", k, v))
+	}
+	return s
+}
+
+// BuildWithParams - implements interface.
+func (s *VMStorage) BuildWithParams(params QuerierParams) Querier {
+	return s.Clone().ApplyParams(params)
+}
 
 // NewVMStorage is a constructor for VMStorage
-func NewVMStorage(baseURL, basicAuthUser, basicAuthPass string, lookBack time.Duration, c *http.Client) *VMStorage {
+func NewVMStorage(baseURL, basicAuthUser, basicAuthPass string, lookBack time.Duration, queryStep time.Duration, appendTypePrefix bool, c *http.Client) *VMStorage {
 	return &VMStorage{
-		c:             c,
-		basicAuthUser: basicAuthUser,
-		basicAuthPass: basicAuthPass,
-		queryURL:      strings.TrimSuffix(baseURL, "/") + queryPath,
-		lookBack:      lookBack,
+		c:                c,
+		basicAuthUser:    basicAuthUser,
+		basicAuthPass:    basicAuthPass,
+		datasourceURL:    strings.TrimSuffix(baseURL, "/"),
+		appendTypePrefix: appendTypePrefix,
+		lookBack:         lookBack,
+		queryStep:        queryStep,
+		dataSourceType:   NewPrometheusType(),
 	}
 }
 
-// Query reads metrics from datasource by given query
+// Query executes the given query and returns parsed response
 func (s *VMStorage) Query(ctx context.Context, query string) ([]Metric, error) {
-	const (
-		statusSuccess, statusError, rtVector = "success", "error", "vector"
-	)
-	q := s.queryURL + url.QueryEscape(query)
-	if s.lookBack > 0 {
-		lookBack := time.Now().Add(-s.lookBack)
-		q += fmt.Sprintf("&time=%d", lookBack.Unix())
+	req, err := s.newRequestPOST()
+	if err != nil {
+		return nil, err
 	}
-	req, err := http.NewRequest("POST", q, nil)
+
+	ts := time.Now()
+	switch s.dataSourceType.name {
+	case "", prometheusType:
+		s.setPrometheusInstantReqParams(req, query, ts)
+	case graphiteType:
+		s.setGraphiteReqParams(req, query, ts)
+	default:
+		return nil, fmt.Errorf("engine not found: %q", s.dataSourceType.name)
+	}
+
+	resp, err := s.do(ctx, req)
+	if err != nil {
+		return nil, err
+	}
+	defer func() {
+		_ = resp.Body.Close()
+	}()
+
+	parseFn := parsePrometheusResponse
+	if s.dataSourceType.name != prometheusType {
+		parseFn = parseGraphiteResponse
+	}
+	return parseFn(req, resp)
+}
+
+// QueryRange executes the given query on the given time range.
+// For Prometheus type see https://prometheus.io/docs/prometheus/latest/querying/api/#range-queries
+// Graphite type isn't supported.
+func (s *VMStorage) QueryRange(ctx context.Context, query string, start, end time.Time) ([]Metric, error) {
+	if s.dataSourceType.name != prometheusType {
+		return nil, fmt.Errorf("%q is not supported for QueryRange", s.dataSourceType.name)
+	}
+	req, err := s.newRequestPOST()
+	if err != nil {
+		return nil, err
+	}
+	if start.IsZero() {
+		return nil, fmt.Errorf("start param is missing")
+	}
+	if end.IsZero() {
+		return nil, fmt.Errorf("end param is missing")
+	}
+	s.setPrometheusRangeReqParams(req, query, start, end)
+	resp, err := s.do(ctx, req)
+	if err != nil {
+		return nil, err
+	}
+	defer func() {
+		_ = resp.Body.Close()
+	}()
+	return parsePrometheusResponse(req, resp)
+}
+
+func (s *VMStorage) do(ctx context.Context, req *http.Request) (*http.Response, error) {
+	resp, err := s.c.Do(req.WithContext(ctx))
+	if err != nil {
+		return nil, fmt.Errorf("error getting response from %s: %w", req.URL, err)
+	}
+	if resp.StatusCode != http.StatusOK {
+		body, _ := ioutil.ReadAll(resp.Body)
+		_ = resp.Body.Close()
+		return nil, fmt.Errorf("unexpected response code %d for %s. Response body %s", resp.StatusCode, req.URL, body)
+	}
+	return resp, nil
+}
+
+func (s *VMStorage) newRequestPOST() (*http.Request, error) {
+	req, err := http.NewRequest("POST", s.datasourceURL, nil)
 	if err != nil {
 		return nil, err
 	}
@@ -86,27 +152,5 @@ func (s *VMStorage) Query(ctx context.Context, query string) ([]Metric, error) {
 	if s.basicAuthPass != "" {
 		req.SetBasicAuth(s.basicAuthUser, s.basicAuthPass)
 	}
-	resp, err := s.c.Do(req.WithContext(ctx))
-	if err != nil {
-		return nil, fmt.Errorf("error getting response from %s: %w", req.URL, err)
-	}
-	defer func() { _ = resp.Body.Close() }()
-	if resp.StatusCode != http.StatusOK {
-		body, _ := ioutil.ReadAll(resp.Body)
-		return nil, fmt.Errorf("datasource returns unexpected response code %d for %s. Response body %s", resp.StatusCode, req.URL, body)
-	}
-	r := &response{}
-	if err := json.NewDecoder(resp.Body).Decode(r); err != nil {
-		return nil, fmt.Errorf("error parsing metrics for %s: %w", req.URL, err)
-	}
-	if r.Status == statusError {
-		return nil, fmt.Errorf("response error, query: %s, errorType: %s, error: %s", req.URL, r.ErrorType, r.Error)
-	}
-	if r.Status != statusSuccess {
-		return nil, fmt.Errorf("unknown status: %s, Expected success or error ", r.Status)
-	}
-	if r.Data.ResultType != rtVector {
-		return nil, fmt.Errorf("unknown result type:%s. Expected vector", r.Data.ResultType)
-	}
-	return r.metrics()
+	return req, nil
 }

app/vmalert/datasource/vm_graphite_api.go

@@ -0,0 +1,67 @@
+package datasource
+
+import (
+	"encoding/json"
+	"fmt"
+	"net/http"
+	"strconv"
+	"time"
+)
+
+type graphiteResponse []graphiteResponseTarget
+
+type graphiteResponseTarget struct {
+	Target     string            `json:"target"`
+	Tags       map[string]string `json:"tags"`
+	DataPoints [][2]float64      `json:"datapoints"`
+}
+
+func (r graphiteResponse) metrics() []Metric {
+	var ms []Metric
+	for _, res := range r {
+		if len(res.DataPoints) < 1 {
+			continue
+		}
+		var m Metric
+		// add only last value to the result.
+		last := res.DataPoints[len(res.DataPoints)-1]
+		m.Values = append(m.Values, last[0])
+		m.Timestamps = append(m.Timestamps, int64(last[1]))
+		for k, v := range res.Tags {
+			m.AddLabel(k, v)
+		}
+		ms = append(ms, m)
+	}
+	return ms
+}
+
+func parseGraphiteResponse(req *http.Request, resp *http.Response) ([]Metric, error) {
+	r := &graphiteResponse{}
+	if err := json.NewDecoder(resp.Body).Decode(r); err != nil {
+		return nil, fmt.Errorf("error parsing graphite metrics for %s: %w", req.URL, err)
+	}
+	return r.metrics(), nil
+}
+
+const (
+	graphitePath   = "/render"
+	graphitePrefix = "/graphite"
+)
+
+func (s *VMStorage) setGraphiteReqParams(r *http.Request, query string, timestamp time.Time) {
+	if s.appendTypePrefix {
+		r.URL.Path += graphitePrefix
+	}
+	r.URL.Path += graphitePath
+	q := r.URL.Query()
+	q.Set("format", "json")
+	q.Set("target", query)
+	from := "-5min"
+	if s.lookBack > 0 {
+		lookBack := timestamp.Add(-s.lookBack)
+		from = strconv.FormatInt(lookBack.Unix(), 10)
+	}
+	q.Set("from", from)
+	q.Set("until", "now")
+	r.URL.RawQuery = q.Encode()
+}

app/vmalert/datasource/vm_prom_api.go

@@ -0,0 +1,165 @@
+package datasource
+
+import (
+	"encoding/json"
+	"fmt"
+	"net/http"
+	"strconv"
+	"time"
+)
+
+type promResponse struct {
+	Status    string `json:"status"`
+	ErrorType string `json:"errorType"`
+	Error     string `json:"error"`
+	Data      struct {
+		ResultType string          `json:"resultType"`
+		Result     json.RawMessage `json:"result"`
+	} `json:"data"`
+}
+
+type promInstant struct {
+	Result []struct {
+		Labels map[string]string `json:"metric"`
+		TV     [2]interface{}    `json:"value"`
+	} `json:"result"`
+}
+
+type promRange struct {
+	Result []struct {
+		Labels map[string]string `json:"metric"`
+		TVs    [][2]interface{}  `json:"values"`
+	} `json:"result"`
+}
+
+func (r promInstant) metrics() ([]Metric, error) {
+	var result []Metric
+	for i, res := range r.Result {
+		f, err := strconv.ParseFloat(res.TV[1].(string), 64)
+		if err != nil {
+			return nil, fmt.Errorf("metric %v, unable to parse float64 from %s: %w", res, res.TV[1], err)
+		}
+		var m Metric
+		for k, v := range r.Result[i].Labels {
+			m.AddLabel(k, v)
+		}
+		m.Timestamps = append(m.Timestamps, int64(res.TV[0].(float64)))
+		m.Values = append(m.Values, f)
+		result = append(result, m)
+	}
+	return result, nil
+}
+
+func (r promRange) metrics() ([]Metric, error) {
+	var result []Metric
+	for i, res := range r.Result {
+		var m Metric
+		for _, tv := range res.TVs {
+			f, err := strconv.ParseFloat(tv[1].(string), 64)
+			if err != nil {
+				return nil, fmt.Errorf("metric %v, unable to parse float64 from %s: %w", res, tv[1], err)
+			}
+			m.Values = append(m.Values, f)
+			m.Timestamps = append(m.Timestamps, int64(tv[0].(float64)))
+		}
+		if len(m.Values) < 1 || len(m.Timestamps) < 1 {
+			return nil, fmt.Errorf("metric %v contains no values", res)
+		}
+		m.Labels = nil
+		for k, v := range r.Result[i].Labels {
+			m.AddLabel(k, v)
+		}
+		result = append(result, m)
+	}
+	return result, nil
+}
+
+const (
+	statusSuccess, statusError = "success", "error"
+	rtVector, rtMatrix         = "vector", "matrix"
+)
+
+func parsePrometheusResponse(req *http.Request, resp *http.Response) ([]Metric, error) {
+	r := &promResponse{}
+	if err := json.NewDecoder(resp.Body).Decode(r); err != nil {
+		return nil, fmt.Errorf("error parsing prometheus metrics for %s: %w", req.URL, err)
+	}
+	if r.Status == statusError {
+		return nil, fmt.Errorf("response error, query: %s, errorType: %s, error: %s", req.URL, r.ErrorType, r.Error)
+	}
+	if r.Status != statusSuccess {
+		return nil, fmt.Errorf("unknown status: %s, Expected success or error ", r.Status)
+	}
+	switch r.Data.ResultType {
+	case rtVector:
+		var pi promInstant
+		if err := json.Unmarshal(r.Data.Result, &pi.Result); err != nil {
+			return nil, fmt.Errorf("umarshal err %s; \n %#v", err, string(r.Data.Result))
+		}
+		return pi.metrics()
+	case rtMatrix:
+		var pr promRange
+		if err := json.Unmarshal(r.Data.Result, &pr.Result); err != nil {
+			return nil, err
+		}
+		return pr.metrics()
+	default:
+		return nil, fmt.Errorf("unknown result type %q", r.Data.ResultType)
+	}
+}
+
+const (
+	prometheusInstantPath = "/api/v1/query"
+	prometheusRangePath   = "/api/v1/query_range"
+	prometheusPrefix      = "/prometheus"
+)
+
+func (s *VMStorage) setPrometheusInstantReqParams(r *http.Request, query string, timestamp time.Time) {
+	if s.appendTypePrefix {
+		r.URL.Path += prometheusPrefix
+	}
+	r.URL.Path += prometheusInstantPath
+	q := r.URL.Query()
+	if s.lookBack > 0 {
+		timestamp = timestamp.Add(-s.lookBack)
+	}
+	if s.evaluationInterval > 0 {
+		// see https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1232
+		timestamp = timestamp.Truncate(s.evaluationInterval)
+	}
+	q.Set("time", fmt.Sprintf("%d", timestamp.Unix()))
+	r.URL.RawQuery = q.Encode()
+	s.setPrometheusReqParams(r, query)
+}
+
+func (s *VMStorage) setPrometheusRangeReqParams(r *http.Request, query string, start, end time.Time) {
+	if s.appendTypePrefix {
+		r.URL.Path += prometheusPrefix
+	}
+	r.URL.Path += prometheusRangePath
+	q := r.URL.Query()
+	q.Add("start", fmt.Sprintf("%d", start.Unix()))
+	q.Add("end", fmt.Sprintf("%d", end.Unix()))
+	r.URL.RawQuery = q.Encode()
+	s.setPrometheusReqParams(r, query)
+}
+
+func (s *VMStorage) setPrometheusReqParams(r *http.Request, query string) {
+	q := r.URL.Query()
+	q.Set("query", query)
+	if s.evaluationInterval > 0 {
+		// set step as evaluationInterval by default
+		q.Set("step", s.evaluationInterval.String())
+	}
+	if s.queryStep > 0 {
+		// override step with user-specified value
+		q.Set("step", s.queryStep.String())
+	}
+	if s.roundDigits != "" {
+		q.Set("round_digits", s.roundDigits)
+	}
+	for _, l := range s.extraLabels {
+		q.Add("extra_label", l)
+	}
+	r.URL.RawQuery = q.Encode()
+}

app/vmalert/datasource/vm_test.go

@@ -2,9 +2,12 @@ package datasource
 
 import (
 	"context"
+	"fmt"
 	"net/http"
 	"net/http/httptest"
+	"reflect"
 	"strconv"
+	"strings"
 	"testing"
 	"time"
 )
@@ -14,14 +17,22 @@ var (
 	basicAuthName = "foo"
 	basicAuthPass = "bar"
 	query         = "vm_rows"
+	queryRender   = "constantLine(10)"
 )
 
-func TestVMSelectQuery(t *testing.T) {
+func TestVMInstantQuery(t *testing.T) {
 	mux := http.NewServeMux()
 	mux.HandleFunc("/", func(_ http.ResponseWriter, _ *http.Request) {
 		t.Errorf("should not be called")
 	})
 	c := -1
+	mux.HandleFunc("/render", func(w http.ResponseWriter, request *http.Request) {
+		c++
+		switch c {
+		case 7:
+			w.Write([]byte(`[{"target":"constantLine(10)","tags":{"name":"constantLine(10)"},"datapoints":[[10,1611758343],[10,1611758373],[10,1611758403]]}]`))
+		}
+	})
 	mux.HandleFunc("/api/v1/query", func(w http.ResponseWriter, r *http.Request) {
 		c++
 		if r.Method != http.MethodPost {
@@ -55,32 +66,133 @@ func TestVMSelectQuery(t *testing.T) {
 		case 5:
 			w.Write([]byte(`{"status":"success","data":{"resultType":"matrix"}}`))
 		case 6:
-			w.Write([]byte(`{"status":"success","data":{"resultType":"vector","result":[{"metric":{"__name__":"vm_rows"},"value":[1583786142,"13763"]}]}}`))
+			w.Write([]byte(`{"status":"success","data":{"resultType":"vector","result":[{"metric":{"__name__":"vm_rows"},"value":[1583786142,"13763"]},{"metric":{"__name__":"vm_requests"},"value":[1583786140,"2000"]}]}}`))
 		}
 	})
 
 	srv := httptest.NewServer(mux)
 	defer srv.Close()
-	am := NewVMStorage(srv.URL, basicAuthName, basicAuthPass, time.Minute, srv.Client())
-	if _, err := am.Query(ctx, query); err == nil {
+
+	s := NewVMStorage(srv.URL, basicAuthName, basicAuthPass, time.Minute, 0, false, srv.Client())
+
+	p := NewPrometheusType()
+	pq := s.BuildWithParams(QuerierParams{DataSourceType: &p, EvaluationInterval: 15 * time.Second})
+
+	if _, err := pq.Query(ctx, query); err == nil {
 		t.Fatalf("expected connection error got nil")
 	}
-	if _, err := am.Query(ctx, query); err == nil {
+	if _, err := pq.Query(ctx, query); err == nil {
 		t.Fatalf("expected invalid response status error got nil")
 	}
-	if _, err := am.Query(ctx, query); err == nil {
+	if _, err := pq.Query(ctx, query); err == nil {
 		t.Fatalf("expected response body error got nil")
 	}
-	if _, err := am.Query(ctx, query); err == nil {
+	if _, err := pq.Query(ctx, query); err == nil {
 		t.Fatalf("expected error status got nil")
 	}
-	if _, err := am.Query(ctx, query); err == nil {
+	if _, err := pq.Query(ctx, query); err == nil {
 		t.Fatalf("expected unknown status got nil")
 	}
-	if _, err := am.Query(ctx, query); err == nil {
+	if _, err := pq.Query(ctx, query); err == nil {
 		t.Fatalf("expected non-vector resultType error  got nil")
 	}
-	m, err := am.Query(ctx, query)
+	m, err := pq.Query(ctx, query)
+	if err != nil {
+		t.Fatalf("unexpected %s", err)
+	}
+	if len(m) != 2 {
+		t.Fatalf("expected 2 metrics got %d in %+v", len(m), m)
+	}
+	expected := []Metric{
+		{
+			Labels:     []Label{{Value: "vm_rows", Name: "__name__"}},
+			Timestamps: []int64{1583786142},
+			Values:     []float64{13763},
+		},
+		{
+			Labels:     []Label{{Value: "vm_requests", Name: "__name__"}},
+			Timestamps: []int64{1583786140},
+			Values:     []float64{2000},
+		},
+	}
+	if !reflect.DeepEqual(m, expected) {
+		t.Fatalf("unexpected metric %+v want %+v", m, expected)
+	}
+
+	g := NewGraphiteType()
+	gq := s.BuildWithParams(QuerierParams{DataSourceType: &g})
+
+	m, err = gq.Query(ctx, queryRender)
+	if err != nil {
+		t.Fatalf("unexpected %s", err)
+	}
+	if len(m) != 1 {
+		t.Fatalf("expected 1 metric  got %d in %+v", len(m), m)
+	}
+	exp := Metric{
+		Labels:     []Label{{Value: "constantLine(10)", Name: "name"}},
+		Timestamps: []int64{1611758403},
+		Values:     []float64{10},
+	}
+	if !reflect.DeepEqual(m[0], exp) {
+		t.Fatalf("unexpected metric %+v want %+v", m[0], expected)
+	}
+}
+
+func TestVMRangeQuery(t *testing.T) {
+	mux := http.NewServeMux()
+	mux.HandleFunc("/", func(_ http.ResponseWriter, _ *http.Request) {
+		t.Errorf("should not be called")
+	})
+	c := -1
+	mux.HandleFunc("/api/v1/query_range", func(w http.ResponseWriter, r *http.Request) {
+		c++
+		if r.Method != http.MethodPost {
+			t.Errorf("expected POST method got %s", r.Method)
+		}
+		if name, pass, _ := r.BasicAuth(); name != basicAuthName || pass != basicAuthPass {
+			t.Errorf("expected %s:%s as basic auth got %s:%s", basicAuthName, basicAuthPass, name, pass)
+		}
+		if r.URL.Query().Get("query") != query {
+			t.Errorf("expected %s in query param, got %s", query, r.URL.Query().Get("query"))
+		}
+		startTS := r.URL.Query().Get("start")
+		if startTS == "" {
+			t.Errorf("expected 'start' in query param, got nil instead")
+		}
+		if _, err := strconv.ParseInt(startTS, 10, 64); err != nil {
+			t.Errorf("failed to parse 'start' query param: %s", err)
+		}
+		endTS := r.URL.Query().Get("end")
+		if endTS == "" {
+			t.Errorf("expected 'end' in query param, got nil instead")
+		}
+		if _, err := strconv.ParseInt(endTS, 10, 64); err != nil {
+			t.Errorf("failed to parse 'end' query param: %s", err)
+		}
+		switch c {
+		case 0:
+			w.Write([]byte(`{"status":"success","data":{"resultType":"matrix","result":[{"metric":{"__name__":"vm_rows"},"values":[[1583786142,"13763"]]}]}}`))
+		}
+	})
+
+	srv := httptest.NewServer(mux)
+	defer srv.Close()
+
+	s := NewVMStorage(srv.URL, basicAuthName, basicAuthPass, time.Minute, 0, false, srv.Client())
+
+	p := NewPrometheusType()
+	pq := s.BuildWithParams(QuerierParams{DataSourceType: &p, EvaluationInterval: 15 * time.Second})
+
+	_, err := pq.QueryRange(ctx, query, time.Now(), time.Time{})
+	expectError(t, err, "is missing")
+
+	_, err = pq.QueryRange(ctx, query, time.Time{}, time.Now())
+	expectError(t, err, "is missing")
+
+	start, end := time.Now().Add(-time.Minute), time.Now()
+
+	m, err := pq.QueryRange(ctx, query, start, end)
 	if err != nil {
 		t.Fatalf("unexpected %s", err)
 	}
@@ -88,14 +200,263 @@ func TestVMSelectQuery(t *testing.T) {
 		t.Fatalf("expected 1 metric  got %d in %+v", len(m), m)
 	}
 	expected := Metric{
-		Labels:    []Label{{Value: "vm_rows", Name: "__name__"}},
-		Timestamp: 1583786142,
-		Value:     13763,
+		Labels:     []Label{{Value: "vm_rows", Name: "__name__"}},
+		Timestamps: []int64{1583786142},
+		Values:     []float64{13763},
 	}
-	if m[0].Timestamp != expected.Timestamp &&
-		m[0].Value != expected.Value &&
-		m[0].Labels[0].Value != expected.Labels[0].Value &&
-		m[0].Labels[0].Name != expected.Labels[0].Name {
+	if !reflect.DeepEqual(m[0], expected) {
 		t.Fatalf("unexpected metric %+v want %+v", m[0], expected)
 	}
+
+	g := NewGraphiteType()
+	gq := s.BuildWithParams(QuerierParams{DataSourceType: &g})
+
+	_, err = gq.QueryRange(ctx, queryRender, start, end)
+	expectError(t, err, "is not supported")
+}
+
+func TestRequestParams(t *testing.T) {
+	query := "up"
+	timestamp := time.Date(2001, 2, 3, 4, 5, 6, 0, time.UTC)
+	testCases := []struct {
+		name       string
+		queryRange bool
+		vm         *VMStorage
+		checkFn    func(t *testing.T, r *http.Request)
+	}{
+		{
+			"prometheus path",
+			false,
+			&VMStorage{
+				dataSourceType: NewPrometheusType(),
+			},
+			func(t *testing.T, r *http.Request) {
+				checkEqualString(t, prometheusInstantPath, r.URL.Path)
+			},
+		},
+		{
+			"prometheus prefix",
+			false,
+			&VMStorage{
+				dataSourceType:   NewPrometheusType(),
+				appendTypePrefix: true,
+			},
+			func(t *testing.T, r *http.Request) {
+				checkEqualString(t, prometheusPrefix+prometheusInstantPath, r.URL.Path)
+			},
+		},
+		{
+			"prometheus range path",
+			true,
+			&VMStorage{
+				dataSourceType: NewPrometheusType(),
+			},
+			func(t *testing.T, r *http.Request) {
+				checkEqualString(t, prometheusRangePath, r.URL.Path)
+			},
+		},
+		{
+			"prometheus range prefix",
+			true,
+			&VMStorage{
+				dataSourceType:   NewPrometheusType(),
+				appendTypePrefix: true,
+			},
+			func(t *testing.T, r *http.Request) {
+				checkEqualString(t, prometheusPrefix+prometheusRangePath, r.URL.Path)
+			},
+		},
+		{
+			"graphite path",
+			false,
+			&VMStorage{
+				dataSourceType: NewGraphiteType(),
+			},
+			func(t *testing.T, r *http.Request) {
+				checkEqualString(t, graphitePath, r.URL.Path)
+			},
+		},
+		{
+			"graphite prefix",
+			false,
+			&VMStorage{
+				dataSourceType:   NewGraphiteType(),
+				appendTypePrefix: true,
+			},
+			func(t *testing.T, r *http.Request) {
+				checkEqualString(t, graphitePrefix+graphitePath, r.URL.Path)
+			},
+		},
+		{
+			"default params",
+			false,
+			&VMStorage{},
+			func(t *testing.T, r *http.Request) {
+				exp := fmt.Sprintf("query=%s&time=%d", query, timestamp.Unix())
+				checkEqualString(t, exp, r.URL.RawQuery)
+			},
+		},
+		{
+			"default range params",
+			true,
+			&VMStorage{},
+			func(t *testing.T, r *http.Request) {
+				exp := fmt.Sprintf("end=%d&query=%s&start=%d", timestamp.Unix(), query, timestamp.Unix())
+				checkEqualString(t, exp, r.URL.RawQuery)
+			},
+		},
+		{
+			"basic auth",
+			false,
+			&VMStorage{
+				basicAuthUser: "foo",
+				basicAuthPass: "bar",
+			},
+			func(t *testing.T, r *http.Request) {
+				u, p, _ := r.BasicAuth()
+				checkEqualString(t, "foo", u)
+				checkEqualString(t, "bar", p)
+			},
+		},
+		{
+			"basic auth range",
+			true,
+			&VMStorage{
+				basicAuthUser: "foo",
+				basicAuthPass: "bar",
+			},
+			func(t *testing.T, r *http.Request) {
+				u, p, _ := r.BasicAuth()
+				checkEqualString(t, "foo", u)
+				checkEqualString(t, "bar", p)
+			},
+		},
+		{
+			"lookback",
+			false,
+			&VMStorage{
+				lookBack: time.Minute,
+			},
+			func(t *testing.T, r *http.Request) {
+				exp := fmt.Sprintf("query=%s&time=%d", query, timestamp.Add(-time.Minute).Unix())
+				checkEqualString(t, exp, r.URL.RawQuery)
+			},
+		},
+		{
+			"evaluation interval",
+			false,
+			&VMStorage{
+				evaluationInterval: 15 * time.Second,
+			},
+			func(t *testing.T, r *http.Request) {
+				evalInterval := 15 * time.Second
+				tt := timestamp.Truncate(evalInterval)
+				exp := fmt.Sprintf("query=%s&step=%v&time=%d", query, evalInterval, tt.Unix())
+				checkEqualString(t, exp, r.URL.RawQuery)
+			},
+		},
+		{
+			"lookback + evaluation interval",
+			false,
+			&VMStorage{
+				lookBack:           time.Minute,
+				evaluationInterval: 15 * time.Second,
+			},
+			func(t *testing.T, r *http.Request) {
+				evalInterval := 15 * time.Second
+				tt := timestamp.Add(-time.Minute)
+				tt = tt.Truncate(evalInterval)
+				exp := fmt.Sprintf("query=%s&step=%v&time=%d", query, evalInterval, tt.Unix())
+				checkEqualString(t, exp, r.URL.RawQuery)
+			},
+		},
+		{
+			"step override",
+			false,
+			&VMStorage{
+				queryStep: time.Minute,
+			},
+			func(t *testing.T, r *http.Request) {
+				exp := fmt.Sprintf("query=%s&step=%v&time=%d", query, time.Minute, timestamp.Unix())
+				checkEqualString(t, exp, r.URL.RawQuery)
+			},
+		},
+		{
+			"round digits",
+			false,
+			&VMStorage{
+				roundDigits: "10",
+			},
+			func(t *testing.T, r *http.Request) {
+				exp := fmt.Sprintf("query=%s&round_digits=10&time=%d", query, timestamp.Unix())
+				checkEqualString(t, exp, r.URL.RawQuery)
+			},
+		},
+		{
+			"extra labels",
+			false,
+			&VMStorage{
+				extraLabels: []string{
+					"env=prod",
+					"query=es=cape",
+				},
+			},
+			func(t *testing.T, r *http.Request) {
+				exp := fmt.Sprintf("extra_label=env%%3Dprod&extra_label=query%%3Des%%3Dcape&query=%s&time=%d", query, timestamp.Unix())
+				checkEqualString(t, exp, r.URL.RawQuery)
+			},
+		},
+		{
+			"extra labels range",
+			true,
+			&VMStorage{
+				extraLabels: []string{
+					"env=prod",
+					"query=es=cape",
+				},
+			},
+			func(t *testing.T, r *http.Request) {
+				exp := fmt.Sprintf("end=%d&extra_label=env%%3Dprod&extra_label=query%%3Des%%3Dcape&query=%s&start=%d",
+					timestamp.Unix(), query, timestamp.Unix())
+				checkEqualString(t, exp, r.URL.RawQuery)
+			},
+		},
+	}
+
+	for _, tc := range testCases {
+		t.Run(tc.name, func(t *testing.T) {
+			req, err := tc.vm.newRequestPOST()
+			if err != nil {
+				t.Fatalf("unexpected error: %s", err)
+			}
+			switch tc.vm.dataSourceType.name {
+			case "", prometheusType:
+				if tc.queryRange {
+					tc.vm.setPrometheusRangeReqParams(req, query, timestamp, timestamp)
+				} else {
+					tc.vm.setPrometheusInstantReqParams(req, query, timestamp)
+				}
+			case graphiteType:
+				tc.vm.setGraphiteReqParams(req, query, timestamp)
+			}
+			tc.checkFn(t, req)
+		})
+	}
+}
+
+func checkEqualString(t *testing.T, exp, got string) {
+	t.Helper()
+	if got != exp {
+		t.Errorf("expected to get %q; got %q", exp, got)
+	}
+}
+
+func expectError(t *testing.T, err error, exp string) {
+	t.Helper()
+	if err == nil {
+		t.Errorf("expected non-nil error")
+	}
+	if !strings.Contains(err.Error(), exp) {
+		t.Errorf("expected error %q to contain %q", err, exp)
+	}
 }

app/vmalert/group.go

@@ -18,13 +18,15 @@ import (
 
 // Group is an entity for grouping rules
 type Group struct {
-	mu          sync.RWMutex
-	Name        string
-	File        string
-	Rules       []Rule
-	Interval    time.Duration
-	Concurrency int
-	Checksum    string
+	mu                sync.RWMutex
+	Name              string
+	File              string
+	Rules             []Rule
+	Type              datasource.Type
+	Interval          time.Duration
+	Concurrency       int
+	Checksum          string
+	ExtraFilterLabels map[string]string
 
 	doneCh     chan struct{}
 	finishedCh chan struct{}
@@ -48,16 +50,19 @@ func newGroupMetrics(name, file string) *groupMetrics {
 	return m
 }
 
-func newGroup(cfg config.Group, defaultInterval time.Duration, labels map[string]string) *Group {
+func newGroup(cfg config.Group, qb datasource.QuerierBuilder, defaultInterval time.Duration, labels map[string]string) *Group {
 	g := &Group{
-		Name:        cfg.Name,
-		File:        cfg.File,
-		Interval:    cfg.Interval,
-		Concurrency: cfg.Concurrency,
-		Checksum:    cfg.Checksum,
-		doneCh:      make(chan struct{}),
-		finishedCh:  make(chan struct{}),
-		updateCh:    make(chan *Group),
+		Type:              cfg.Type,
+		Name:              cfg.Name,
+		File:              cfg.File,
+		Interval:          cfg.Interval.Duration(),
+		Concurrency:       cfg.Concurrency,
+		Checksum:          cfg.Checksum,
+		ExtraFilterLabels: cfg.ExtraFilterLabels,
+
+		doneCh:     make(chan struct{}),
+		finishedCh: make(chan struct{}),
+		updateCh:   make(chan *Group),
 	}
 	g.metrics = newGroupMetrics(g.Name, g.File)
 	if g.Interval == 0 {
@@ -79,17 +84,17 @@ func newGroup(cfg config.Group, defaultInterval time.Duration, labels map[string
 			}
 			r.Labels[k] = v
 		}
-		rules[i] = g.newRule(r)
+		rules[i] = g.newRule(qb, r)
 	}
 	g.Rules = rules
 	return g
 }
 
-func (g *Group) newRule(rule config.Rule) Rule {
+func (g *Group) newRule(qb datasource.QuerierBuilder, rule config.Rule) Rule {
 	if rule.Alert != "" {
-		return newAlertingRule(g, rule)
+		return newAlertingRule(qb, g, rule)
 	}
-	return newRecordingRule(g, rule)
+	return newRecordingRule(qb, g, rule)
 }
 
 // ID return unique group ID that consists of
@@ -99,11 +104,12 @@ func (g *Group) ID() uint64 {
 	hash.Write([]byte(g.File))
 	hash.Write([]byte("\xff"))
 	hash.Write([]byte(g.Name))
+	hash.Write([]byte(g.Type.Get()))
 	return hash.Sum64()
 }
 
 // Restore restores alerts state for group rules
-func (g *Group) Restore(ctx context.Context, q datasource.Querier, lookback time.Duration, labels map[string]string) error {
+func (g *Group) Restore(ctx context.Context, qb datasource.QuerierBuilder, lookback time.Duration, labels map[string]string) error {
 	for _, rule := range g.Rules {
 		rr, ok := rule.(*AlertingRule)
 		if !ok {
@@ -112,6 +118,9 @@ func (g *Group) Restore(ctx context.Context, q datasource.Querier, lookback time
 		if rr.For < 1 {
 			continue
 		}
+		// ignore g.ExtraFilterLabels on purpose, so it
+		// won't affect the restore procedure.
+		q := qb.BuildWithParams(datasource.QuerierParams{})
 		if err := rr.Restore(ctx, q, lookback, labels); err != nil {
 			return fmt.Errorf("error while restoring rule %q: %w", rule, err)
 		}
@@ -157,7 +166,9 @@ func (g *Group) updateWith(newGroup *Group) error {
 	for _, nr := range rulesRegistry {
 		newRules = append(newRules, nr)
 	}
+	g.Type = newGroup.Type
 	g.Concurrency = newGroup.Concurrency
+	g.ExtraFilterLabels = newGroup.ExtraFilterLabels
 	g.Checksum = newGroup.Checksum
 	g.Rules = newRules
 	return nil
@@ -185,7 +196,7 @@ func (g *Group) close() {
 
 var skipRandSleepOnGroupStart bool
 
-func (g *Group) start(ctx context.Context, querier datasource.Querier, nts []notifier.Notifier, rw *remotewrite.Client) {
+func (g *Group) start(ctx context.Context, nts []notifier.Notifier, rw *remotewrite.Client) {
 	defer func() { close(g.finishedCh) }()
 
 	// Spread group rules evaluation over time in order to reduce load on VictoriaMetrics.
@@ -209,7 +220,7 @@ func (g *Group) start(ctx context.Context, querier datasource.Querier, nts []not
 	}
 
 	logger.Infof("group %q started; interval=%v; concurrency=%d", g.Name, g.Interval, g.Concurrency)
-	e := &executor{querier, nts, rw}
+	e := &executor{nts, rw}
 	t := time.NewTicker(g.Interval)
 	defer t.Stop()
 	for {
@@ -252,22 +263,16 @@ func (g *Group) start(ctx context.Context, querier datasource.Querier, nts []not
 }
 
 type executor struct {
-	querier   datasource.Querier
 	notifiers []notifier.Notifier
 	rw        *remotewrite.Client
 }
 
 func (e *executor) execConcurrently(ctx context.Context, rules []Rule, concurrency int, interval time.Duration) chan error {
 	res := make(chan error, len(rules))
-	var returnSeries bool
-	if e.rw != nil {
-		returnSeries = true
-	}
-
 	if concurrency == 1 {
 		// fast path
 		for _, rule := range rules {
-			res <- e.exec(ctx, rule, returnSeries, interval)
+			res <- e.exec(ctx, rule, interval)
 		}
 		close(res)
 		return res
@@ -280,7 +285,7 @@ func (e *executor) execConcurrently(ctx context.Context, rules []Rule, concurren
 			sem <- struct{}{}
 			wg.Add(1)
 			go func(r Rule) {
-				res <- e.exec(ctx, r, returnSeries, interval)
+				res <- e.exec(ctx, r, interval)
 				<-sem
 				wg.Done()
 			}(rule)
@@ -299,14 +304,14 @@ var (
 	remoteWriteErrors = metrics.NewCounter(`vmalert_remotewrite_errors_total`)
 )
 
-func (e *executor) exec(ctx context.Context, rule Rule, returnSeries bool, interval time.Duration) error {
+func (e *executor) exec(ctx context.Context, rule Rule, interval time.Duration) error {
 	execTotal.Inc()
 	execStart := time.Now()
 	defer func() {
 		execDuration.UpdateDuration(execStart)
 	}()
 
-	tss, err := rule.Exec(ctx, e.querier, returnSeries)
+	tss, err := rule.Exec(ctx)
 	if err != nil {
 		execErrors.Inc()
 		return fmt.Errorf("rule %q: failed to execute: %w", rule, err)

app/vmalert/group_test.go

@@ -7,7 +7,9 @@ import (
 	"time"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/config"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/utils"
 )
 
 func init() {
@@ -32,7 +34,7 @@ func TestUpdateWith(t *testing.T) {
 			[]config.Rule{{
 				Alert: "foo",
 				Expr:  "up > 0",
-				For:   config.NewPromDuration(time.Second),
+				For:   utils.NewPromDuration(time.Second),
 				Labels: map[string]string{
 					"bar": "baz",
 				},
@@ -44,7 +46,7 @@ func TestUpdateWith(t *testing.T) {
 			[]config.Rule{{
 				Alert: "foo",
 				Expr:  "up > 10",
-				For:   config.NewPromDuration(time.Second),
+				For:   utils.NewPromDuration(time.Second),
 				Labels: map[string]string{
 					"baz": "bar",
 				},
@@ -105,20 +107,32 @@ func TestUpdateWith(t *testing.T) {
 				{Record: "foo5"},
 			},
 		},
+		{
+			"update datasource type",
+			[]config.Rule{
+				{Alert: "foo1", Type: datasource.NewPrometheusType()},
+				{Alert: "foo3", Type: datasource.NewGraphiteType()},
+			},
+			[]config.Rule{
+				{Alert: "foo1", Type: datasource.NewGraphiteType()},
+				{Alert: "foo10", Type: datasource.NewPrometheusType()},
+			},
+		},
 	}
 
 	for _, tc := range testCases {
 		t.Run(tc.name, func(t *testing.T) {
 			g := &Group{Name: "test"}
+			qb := &fakeQuerier{}
 			for _, r := range tc.currentRules {
 				r.ID = config.HashRule(r)
-				g.Rules = append(g.Rules, g.newRule(r))
+				g.Rules = append(g.Rules, g.newRule(qb, r))
 			}
 
 			ng := &Group{Name: "test"}
 			for _, r := range tc.newRules {
 				r.ID = config.HashRule(r)
-				ng.Rules = append(ng.Rules, ng.newRule(r))
+				ng.Rules = append(ng.Rules, ng.newRule(qb, r))
 			}
 
 			err := g.updateWith(ng)
@@ -156,18 +170,18 @@ func TestGroupStart(t *testing.T) {
 		t.Fatalf("failed to parse rules: %s", err)
 	}
 	const evalInterval = time.Millisecond
-	g := newGroup(groups[0], evalInterval, map[string]string{"cluster": "east-1"})
-	g.Concurrency = 2
-
-	fn := &fakeNotifier{}
 	fs := &fakeQuerier{}
+	fn := &fakeNotifier{}
+
+	g := newGroup(groups[0], fs, evalInterval, map[string]string{"cluster": "east-1"})
+	g.Concurrency = 2
 
 	const inst1, inst2, job = "foo", "bar", "baz"
 	m1 := metricWithLabels(t, "instance", inst1, "job", job)
 	m2 := metricWithLabels(t, "instance", inst2, "job", job)
 
 	r := g.Rules[0].(*AlertingRule)
-	alert1, err := r.newAlert(m1, time.Now())
+	alert1, err := r.newAlert(m1, time.Now(), nil)
 	if err != nil {
 		t.Fatalf("faield to create alert: %s", err)
 	}
@@ -179,7 +193,7 @@ func TestGroupStart(t *testing.T) {
 	alert1.Labels["host"] = inst1
 	alert1.ID = hash(m1)
 
-	alert2, err := r.newAlert(m2, time.Now())
+	alert2, err := r.newAlert(m2, time.Now(), nil)
 	if err != nil {
 		t.Fatalf("faield to create alert: %s", err)
 	}
@@ -195,7 +209,7 @@ func TestGroupStart(t *testing.T) {
 	fs.add(m1)
 	fs.add(m2)
 	go func() {
-		g.start(context.Background(), fs, []notifier.Notifier{fn}, nil)
+		g.start(context.Background(), []notifier.Notifier{fn}, nil)
 		close(finished)
 	}()
 

app/vmalert/helpers_test.go

@@ -7,6 +7,7 @@ import (
 	"sort"
 	"sync"
 	"testing"
+	"time"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
@@ -38,6 +39,14 @@ func (fq *fakeQuerier) add(metrics ...datasource.Metric) {
 	fq.Unlock()
 }
 
+func (fq *fakeQuerier) BuildWithParams(_ datasource.QuerierParams) datasource.Querier {
+	return fq
+}
+
+func (fq *fakeQuerier) QueryRange(ctx context.Context, q string, _, _ time.Time) ([]datasource.Metric, error) {
+	return fq.Query(ctx, q)
+}
+
 func (fq *fakeQuerier) Query(_ context.Context, _ string) ([]datasource.Metric, error) {
 	fq.Lock()
 	defer fq.Unlock()
@@ -68,9 +77,16 @@ func (fn *fakeNotifier) getAlerts() []notifier.Alert {
 }
 
 func metricWithValueAndLabels(t *testing.T, value float64, labels ...string) datasource.Metric {
+	return metricWithValuesAndLabels(t, []float64{value}, labels...)
+}
+
+func metricWithValuesAndLabels(t *testing.T, values []float64, labels ...string) datasource.Metric {
 	t.Helper()
 	m := metricWithLabels(t, labels...)
-	m.Value = value
+	m.Values = values
+	for i := range values {
+		m.Timestamps = append(m.Timestamps, int64(i))
+	}
 	return m
 }
 
@@ -79,7 +95,7 @@ func metricWithLabels(t *testing.T, labels ...string) datasource.Metric {
 	if len(labels) == 0 || len(labels)%2 != 0 {
 		t.Fatalf("expected to get even number of labels")
 	}
-	m := datasource.Metric{}
+	m := datasource.Metric{Values: []float64{1}, Timestamps: []int64{1}}
 	for i := 0; i < len(labels); i += 2 {
 		m.Labels = append(m.Labels, datasource.Label{
 			Name:  labels[i],
@@ -160,6 +176,9 @@ func compareAlertingRules(t *testing.T, a, b *AlertingRule) error {
 	if !reflect.DeepEqual(a.Labels, b.Labels) {
 		return fmt.Errorf("expected to have labels %#v; got %#v", a.Labels, b.Labels)
 	}
+	if a.Type.String() != b.Type.String() {
+		return fmt.Errorf("expected to have Type %#v; got %#v", a.Type.String(), b.Type.String())
+	}
 	return nil
 }
 

app/vmalert/main.go

@@ -16,7 +16,6 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/remoteread"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/remotewrite"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/buildinfo"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/cgroup"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/envflag"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/fasttime"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
@@ -27,14 +26,17 @@ import (
 )
 
 var (
-	rulePath = flagutil.NewArray("rule", `Path to the file with alert rules. 
-Supports patterns. Flag can be specified multiple times. 
+	rulePath = flagutil.NewArray("rule", `Path to the file with alert rules.
+Supports patterns. Flag can be specified multiple times.
 Examples:
  -rule="/path/to/file". Path to a single file with alerting rules
- -rule="dir/*.yaml" -rule="/*.yaml". Relative path to all .yaml files in "dir" folder, 
+ -rule="dir/*.yaml" -rule="/*.yaml". Relative path to all .yaml files in "dir" folder,
 absolute path to all .yaml files in root.
 Rule files may contain %{ENV_VAR} placeholders, which are substituted by the corresponding env vars.`)
 
+	rulesCheckInterval = flag.Duration("rule.configCheckInterval", 0, "Interval for checking for changes in '-rule' files. "+
+		"By default the checking is disabled. Send SIGHUP signal in order to force config check for changes")
+
 	httpListenAddr     = flag.String("httpListenAddr", ":8880", "Address to listen for http connections")
 	evaluationInterval = flag.Duration("evaluationInterval", time.Minute, "How often to evaluate the rules")
 
@@ -42,12 +44,13 @@ Rule files may contain %{ENV_VAR} placeholders, which are substituted by the cor
 	validateExpressions = flag.Bool("rule.validateExpressions", true, "Whether to validate rules expressions via MetricsQL engine")
 	externalURL         = flag.String("external.url", "", "External URL is used as alert's source for sent alerts to the notifier")
 	externalAlertSource = flag.String("external.alert.source", "", `External Alert Source allows to override the Source link for alerts sent to AlertManager for cases where you want to build a custom link to Grafana, Prometheus or any other service.
-eg. 'explore?orgId=1&left=[\"now-1h\",\"now\",\"VictoriaMetrics\",{\"expr\": \"{{$expr|quotesEscape|pathEscape}}\"},{\"mode\":\"Metrics\"},{\"ui\":[true,true,true,\"none\"]}]'.If empty '/api/v1/:groupID/alertID/status' is used`)
+eg. 'explore?orgId=1&left=[\"now-1h\",\"now\",\"VictoriaMetrics\",{\"expr\": \"{{$expr|quotesEscape|crlfEscape|queryEscape}}\"},{\"mode\":\"Metrics\"},{\"ui\":[true,true,true,\"none\"]}]'.If empty '/api/v1/:groupID/alertID/status' is used`)
 	externalLabels = flagutil.NewArray("external.label", "Optional label in the form 'name=value' to add to all generated recording rules and alerts. "+
 		"Pass multiple -label flags in order to add multiple label sets.")
 
 	remoteReadLookBack = flag.Duration("remoteRead.lookback", time.Hour, "Lookback defines how far to look into past for alerts timeseries."+
 		" For example, if lookback=1h then range from now() to now()-1h will be scanned.")
+	remoteReadIgnoreRestoreErrors = flag.Bool("remoteRead.ignoreRestoreErrors", true, "Whether to ignore errors from remote storage when restoring alerts state on startup.")
 
 	dryRun = flag.Bool("dryRun", false, "Whether to check only config files without running vmalert. The rules file are validated. The `-rule` flag must be specified.")
 )
@@ -59,49 +62,60 @@ func main() {
 	envflag.Parse()
 	buildinfo.Init()
 	logger.Init()
-	cgroup.UpdateGOMAXPROCSToCPUQuota()
 
 	if *dryRun {
 		u, _ := url.Parse("https://victoriametrics.com/")
 		notifier.InitTemplateFunc(u)
 		groups, err := config.Parse(*rulePath, true, true)
 		if err != nil {
-			logger.Fatalf(err.Error())
+			logger.Fatalf("failed to parse %q: %s", *rulePath, err)
 		}
 		if len(groups) == 0 {
 			logger.Fatalf("No rules for validation. Please specify path to file(s) with alerting and/or recording rules using `-rule` flag")
 		}
 		return
 	}
+	if *replayFrom != "" || *replayTo != "" {
+		rw, err := remotewrite.Init(context.Background())
+		if err != nil {
+			logger.Fatalf("failed to init remoteWrite: %s", err)
+		}
+		eu, err := getExternalURL(*externalURL, *httpListenAddr, httpserver.IsTLS())
+		if err != nil {
+			logger.Fatalf("failed to init `external.url`: %s", err)
+		}
+		notifier.InitTemplateFunc(eu)
+		groupsCfg, err := config.Parse(*rulePath, *validateTemplates, *validateExpressions)
+		if err != nil {
+			logger.Fatalf("cannot parse configuration file: %s", err)
+		}
+		q, err := datasource.Init()
+		if err != nil {
+			logger.Fatalf("failed to init datasource: %s", err)
+		}
+		if err := replay(groupsCfg, q, rw); err != nil {
+			logger.Fatalf("replay failed: %s", err)
+		}
+		return
+	}
+
 	ctx, cancel := context.WithCancel(context.Background())
 	manager, err := newManager(ctx)
 	if err != nil {
 		logger.Fatalf("failed to init: %s", err)
 	}
-	if err := manager.start(ctx, *rulePath, *validateTemplates, *validateExpressions); err != nil {
+
+	logger.Infof("reading rules configuration file from %q", strings.Join(*rulePath, ";"))
+	groupsCfg, err := config.Parse(*rulePath, *validateTemplates, *validateExpressions)
+	if err != nil {
+		logger.Fatalf("cannot parse configuration file: %s", err)
+	}
+
+	if err := manager.start(ctx, groupsCfg); err != nil {
 		logger.Fatalf("failed to start: %s", err)
 	}
 
-	go func() {
-		// init reload metrics with positive values to improve alerting conditions
-		configSuccess.Set(1)
-		configTimestamp.Set(fasttime.UnixTimestamp())
-		sigHup := procutil.NewSighupChan()
-		for {
-			<-sigHup
-			configReloads.Inc()
-			logger.Infof("SIGHUP received. Going to reload rules %q ...", *rulePath)
-			if err := manager.update(ctx, *rulePath, *validateTemplates, *validateExpressions, false); err != nil {
-				configReloadErrors.Inc()
-				configSuccess.Set(0)
-				logger.Errorf("error while reloading rules: %s", err)
-				continue
-			}
-			configSuccess.Set(1)
-			configTimestamp.Set(fasttime.UnixTimestamp())
-			logger.Infof("Rules reloaded successfully from %q", *rulePath)
-		}
-	}()
+	go configReload(ctx, manager, groupsCfg)
 
 	rh := &requestHandler{m: manager}
 	go httpserver.Serve(*httpListenAddr, rh.handler)
@@ -142,10 +156,10 @@ func newManager(ctx context.Context) (*manager, error) {
 	}
 
 	manager := &manager{
-		groups:    make(map[uint64]*Group),
-		querier:   q,
-		notifiers: nts,
-		labels:    map[string]string{},
+		groups:         make(map[uint64]*Group),
+		querierBuilder: q,
+		notifiers:      nts,
+		labels:         map[string]string{},
 	}
 	rw, err := remotewrite.Init(ctx)
 	if err != nil {
@@ -160,6 +174,9 @@ func newManager(ctx context.Context) (*manager, error) {
 	manager.rr = rr
 
 	for _, s := range *externalLabels {
+		if len(s) == 0 {
+			continue
+		}
 		n := strings.IndexByte(s, '=')
 		if n < 0 {
 			return nil, fmt.Errorf("missing '=' in `-label`. It must contain label in the form `name=value`; got %q", s)
@@ -205,7 +222,7 @@ func getAlertURLGenerator(externalURL *url.URL, externalAlertSource string, vali
 		"tpl": externalAlertSource,
 	}
 	return func(alert notifier.Alert) string {
-		templated, err := alert.ExecTemplate(m)
+		templated, err := alert.ExecTemplate(nil, m)
 		if err != nil {
 			logger.Errorf("can not exec source template %s", err)
 		}
@@ -217,10 +234,66 @@ func usage() {
 	const s = `
 vmalert processes alerts and recording rules.
 
-See the docs at https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/app/vmalert/README.md .
+See the docs at https://docs.victoriametrics.com/vmalert.html .
 `
-
-	f := flag.CommandLine.Output()
-	fmt.Fprintf(f, "%s\n", s)
-	flag.PrintDefaults()
+	flagutil.Usage(s)
+}
+
+func configReload(ctx context.Context, m *manager, groupsCfg []config.Group) {
+	// Register SIGHUP handler for config re-read just before manager.start call.
+	// This guarantees that the config will be re-read if the signal arrives during manager.start call.
+	// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1240
+	sighupCh := procutil.NewSighupChan()
+
+	var configCheckCh <-chan time.Time
+	if *rulesCheckInterval > 0 {
+		ticker := time.NewTicker(*rulesCheckInterval)
+		configCheckCh = ticker.C
+		defer ticker.Stop()
+	}
+
+	// init reload metrics with positive values to improve alerting conditions
+	configSuccess.Set(1)
+	configTimestamp.Set(fasttime.UnixTimestamp())
+	for {
+		select {
+		case <-ctx.Done():
+			return
+		case <-sighupCh:
+			logger.Infof("SIGHUP received. Going to reload rules %q ...", *rulePath)
+			configReloads.Inc()
+		case <-configCheckCh:
+		}
+		newGroupsCfg, err := config.Parse(*rulePath, *validateTemplates, *validateExpressions)
+		if err != nil {
+			logger.Errorf("cannot parse configuration file: %s", err)
+			continue
+		}
+		if configsEqual(newGroupsCfg, groupsCfg) {
+			// config didn't change - skip it
+			continue
+		}
+		groupsCfg = newGroupsCfg
+		if err := m.update(ctx, groupsCfg, false); err != nil {
+			configReloadErrors.Inc()
+			configSuccess.Set(0)
+			logger.Errorf("error while reloading rules: %s", err)
+			continue
+		}
+		configSuccess.Set(1)
+		configTimestamp.Set(fasttime.UnixTimestamp())
+		logger.Infof("Rules reloaded successfully from %q", *rulePath)
+	}
+}
+
+func configsEqual(a, b []config.Group) bool {
+	if len(a) != len(b) {
+		return false
+	}
+	for i := range a {
+		if a[i].Checksum != b[i].Checksum {
+			return false
+		}
+	}
+	return true
 }

app/vmalert/main_test.go

@@ -1,12 +1,16 @@
 package main
 
 import (
+	"context"
 	"fmt"
+	"io/ioutil"
 	"net/url"
 	"os"
 	"testing"
+	"time"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/procutil"
 )
 
 func TestGetExternalURL(t *testing.T) {
@@ -51,3 +55,95 @@ func TestGetAlertURLGenerator(t *testing.T) {
 		t.Errorf("unexpected url want %s, got %s", exp, fn(testAlert))
 	}
 }
+
+func TestConfigReload(t *testing.T) {
+	originalRulePath := *rulePath
+	defer func() {
+		*rulePath = originalRulePath
+	}()
+
+	const (
+		rules1 = `
+groups:
+  - name: group-1
+    rules:
+      - alert: ExampleAlertAlwaysFiring
+        expr: sum by(job) (up == 1)
+      - record: handler:requests:rate5m 
+        expr: sum(rate(prometheus_http_requests_total[5m])) by (handler)
+`
+		rules2 = `
+groups:
+  - name: group-1
+    rules:
+      - alert: ExampleAlertAlwaysFiring
+        expr: sum by(job) (up == 1)
+  - name: group-2
+    rules:
+      - record: handler:requests:rate5m 
+        expr: sum(rate(prometheus_http_requests_total[5m])) by (handler)
+`
+	)
+
+	f, err := ioutil.TempFile("", "")
+	if err != nil {
+		t.Fatal(err)
+	}
+	writeToFile(t, f.Name(), rules1)
+
+	*rulesCheckInterval = 200 * time.Millisecond
+	*rulePath = []string{f.Name()}
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+
+	m := &manager{
+		querierBuilder: &fakeQuerier{},
+		groups:         make(map[uint64]*Group),
+		labels:         map[string]string{},
+	}
+	go configReload(ctx, m, nil)
+
+	lenLocked := func(m *manager) int {
+		m.groupsMu.RLock()
+		defer m.groupsMu.RUnlock()
+		return len(m.groups)
+	}
+
+	time.Sleep(*rulesCheckInterval * 2)
+	groupsLen := lenLocked(m)
+	if groupsLen != 1 {
+		t.Fatalf("expected to have exactly 1 group loaded; got %d", groupsLen)
+	}
+
+	writeToFile(t, f.Name(), rules2)
+	time.Sleep(*rulesCheckInterval * 2)
+	groupsLen = lenLocked(m)
+	if groupsLen != 2 {
+		fmt.Println(m.groups)
+		t.Fatalf("expected to have exactly 2 groups loaded; got %d", groupsLen)
+	}
+
+	writeToFile(t, f.Name(), rules1)
+	procutil.SelfSIGHUP()
+	time.Sleep(*rulesCheckInterval / 2)
+	groupsLen = lenLocked(m)
+	if groupsLen != 1 {
+		t.Fatalf("expected to have exactly 1 group loaded; got %d", groupsLen)
+	}
+
+	writeToFile(t, f.Name(), `corrupted`)
+	procutil.SelfSIGHUP()
+	time.Sleep(*rulesCheckInterval / 2)
+	groupsLen = lenLocked(m)
+	if groupsLen != 1 { // should remain unchanged
+		t.Fatalf("expected to have exactly 1 group loaded; got %d", groupsLen)
+	}
+}
+
+func writeToFile(t *testing.T, file, b string) {
+	t.Helper()
+	err := ioutil.WriteFile(file, []byte(b), 0644)
+	if err != nil {
+		t.Fatal(err)
+	}
+}

app/vmalert/manager.go

@@ -3,7 +3,6 @@ package main
 import (
 	"context"
 	"fmt"
-	"strings"
 	"sync"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/config"
@@ -15,11 +14,12 @@ import (
 
 // manager controls group states
 type manager struct {
-	querier   datasource.Querier
-	notifiers []notifier.Notifier
+	querierBuilder datasource.QuerierBuilder
+	notifiers      []notifier.Notifier
 
 	rw *remotewrite.Client
-	rr datasource.Querier
+	// remote read builder.
+	rr datasource.QuerierBuilder
 
 	wg     sync.WaitGroup
 	labels map[string]string
@@ -49,8 +49,8 @@ func (m *manager) AlertAPI(gID, aID uint64) (*APIAlert, error) {
 	return nil, fmt.Errorf("can't find alert with id %q in group %q", aID, g.Name)
 }
 
-func (m *manager) start(ctx context.Context, path []string, validateTpl, validateExpr bool) error {
-	return m.update(ctx, path, validateTpl, validateExpr, true)
+func (m *manager) start(ctx context.Context, groupsCfg []config.Group) error {
+	return m.update(ctx, groupsCfg, true)
 }
 
 func (m *manager) close() {
@@ -63,10 +63,13 @@ func (m *manager) close() {
 	m.wg.Wait()
 }
 
-func (m *manager) startGroup(ctx context.Context, group *Group, restore bool) {
+func (m *manager) startGroup(ctx context.Context, group *Group, restore bool) error {
 	if restore && m.rr != nil {
 		err := group.Restore(ctx, m.rr, *remoteReadLookBack, m.labels)
 		if err != nil {
+			if !*remoteReadIgnoreRestoreErrors {
+				return fmt.Errorf("failed to restore state for group %q: %w", group.Name, err)
+			}
 			logger.Errorf("error while restoring state for group %q: %s", group.Name, err)
 		}
 	}
@@ -74,22 +77,17 @@ func (m *manager) startGroup(ctx context.Context, group *Group, restore bool) {
 	m.wg.Add(1)
 	id := group.ID()
 	go func() {
-		group.start(ctx, m.querier, m.notifiers, m.rw)
+		group.start(ctx, m.notifiers, m.rw)
 		m.wg.Done()
 	}()
 	m.groups[id] = group
+	return nil
 }
 
-func (m *manager) update(ctx context.Context, path []string, validateTpl, validateExpr, restore bool) error {
-	logger.Infof("reading rules configuration file from %q", strings.Join(path, ";"))
-	groupsCfg, err := config.Parse(path, validateTpl, validateExpr)
-	if err != nil {
-		return fmt.Errorf("cannot parse configuration file: %w", err)
-	}
-
+func (m *manager) update(ctx context.Context, groupsCfg []config.Group, restore bool) error {
 	groupsRegistry := make(map[uint64]*Group)
 	for _, cfg := range groupsCfg {
-		ng := newGroup(cfg, *evaluationInterval, m.labels)
+		ng := newGroup(cfg, m.querierBuilder, *evaluationInterval, m.labels)
 		groupsRegistry[ng.ID()] = ng
 	}
 
@@ -116,7 +114,9 @@ func (m *manager) update(ctx context.Context, path []string, validateTpl, valida
 		}
 	}
 	for _, ng := range groupsRegistry {
-		m.startGroup(ctx, ng, restore)
+		if err := m.startGroup(ctx, ng, restore); err != nil {
+			return err
+		}
 	}
 	m.groupsMu.Unlock()
 
@@ -140,11 +140,14 @@ func (g *Group) toAPI() APIGroup {
 
 	ag := APIGroup{
 		// encode as string to avoid rounding
-		ID:          fmt.Sprintf("%d", g.ID()),
-		Name:        g.Name,
-		File:        g.File,
-		Interval:    g.Interval.String(),
-		Concurrency: g.Concurrency,
+		ID: fmt.Sprintf("%d", g.ID()),
+
+		Name:              g.Name,
+		Type:              g.Type.String(),
+		File:              g.File,
+		Interval:          g.Interval.String(),
+		Concurrency:       g.Concurrency,
+		ExtraFilterLabels: g.ExtraFilterLabels,
 	}
 	for _, r := range g.Rules {
 		switch v := r.(type) {

app/vmalert/manager_test.go

@@ -9,6 +9,8 @@ import (
 	"testing"
 	"time"
 
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/config"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
 )
 
@@ -23,9 +25,8 @@ func TestMain(m *testing.M) {
 // starting with empty rules folder
 func TestManagerEmptyRulesDir(t *testing.T) {
 	m := &manager{groups: make(map[uint64]*Group)}
-	path := []string{"foo/bar"}
-	err := m.update(context.Background(), path, true, true, false)
-	if err != nil {
+	cfg := loadCfg(t, []string{"foo/bar"}, true, true)
+	if err := m.update(context.Background(), cfg, false); err != nil {
 		t.Fatalf("expected to load succesfully with empty rules dir; got err instead: %v", err)
 	}
 }
@@ -35,9 +36,9 @@ func TestManagerEmptyRulesDir(t *testing.T) {
 // Should be executed with -race flag
 func TestManagerUpdateConcurrent(t *testing.T) {
 	m := &manager{
-		groups:    make(map[uint64]*Group),
-		querier:   &fakeQuerier{},
-		notifiers: []notifier.Notifier{&fakeNotifier{}},
+		groups:         make(map[uint64]*Group),
+		querierBuilder: &fakeQuerier{},
+		notifiers:      []notifier.Notifier{&fakeNotifier{}},
 	}
 	paths := []string{
 		"config/testdata/dir/rules0-good.rules",
@@ -48,8 +49,11 @@ func TestManagerUpdateConcurrent(t *testing.T) {
 		"config/testdata/rules1-good.rules",
 		"config/testdata/rules2-good.rules",
 	}
+	evalInterval := *evaluationInterval
+	defer func() { *evaluationInterval = evalInterval }()
 	*evaluationInterval = time.Millisecond
-	if err := m.start(context.Background(), []string{paths[0]}, true, true); err != nil {
+	cfg := loadCfg(t, []string{paths[0]}, true, true)
+	if err := m.start(context.Background(), cfg); err != nil {
 		t.Fatalf("failed to start: %s", err)
 	}
 
@@ -62,8 +66,11 @@ func TestManagerUpdateConcurrent(t *testing.T) {
 			defer wg.Done()
 			for i := 0; i < iterations; i++ {
 				rnd := rand.Intn(len(paths))
-				path := []string{paths[rnd]}
-				_ = m.update(context.Background(), path, true, true, false)
+				cfg, err := config.Parse([]string{paths[rnd]}, true, true)
+				if err != nil { // update can fail and this is expected
+					continue
+				}
+				_ = m.update(context.Background(), cfg, false)
 			}
 		}()
 	}
@@ -106,6 +113,18 @@ func TestManagerUpdate(t *testing.T) {
 			Name: "ExampleAlertAlwaysFiring",
 			Expr: "sum by(job) (up == 1)",
 		}
+		ExampleAlertGraphite = &AlertingRule{
+			Name: "up graphite",
+			Expr: "filterSeries(time('host.1',20),'>','0')",
+			Type: datasource.NewGraphiteType(),
+			For:  defaultEvalInterval,
+		}
+		ExampleAlertGraphite2 = &AlertingRule{
+			Name: "up",
+			Expr: "filterSeries(time('host.2',20),'>','0')",
+			Type: datasource.NewGraphiteType(),
+			For:  defaultEvalInterval,
+		}
 	)
 
 	testCases := []struct {
@@ -122,6 +141,7 @@ func TestManagerUpdate(t *testing.T) {
 				{
 					File:     "config/testdata/dir/rules1-good.rules",
 					Name:     "duplicatedGroupDiffFiles",
+					Type:     datasource.NewPrometheusType(),
 					Interval: defaultEvalInterval,
 					Rules: []Rule{
 						&AlertingRule{
@@ -146,12 +166,14 @@ func TestManagerUpdate(t *testing.T) {
 				{
 					File:     "config/testdata/rules0-good.rules",
 					Name:     "groupGorSingleAlert",
+					Type:     datasource.NewPrometheusType(),
 					Rules:    []Rule{VMRows},
 					Interval: defaultEvalInterval,
 				},
 				{
 					File:     "config/testdata/rules0-good.rules",
 					Interval: defaultEvalInterval,
+					Type:     datasource.NewPrometheusType(),
 					Name:     "TestGroup", Rules: []Rule{
 						Conns,
 						ExampleAlertAlwaysFiring,
@@ -166,13 +188,16 @@ func TestManagerUpdate(t *testing.T) {
 				{
 					File:     "config/testdata/rules0-good.rules",
 					Name:     "groupGorSingleAlert",
+					Type:     datasource.NewPrometheusType(),
 					Interval: defaultEvalInterval,
 					Rules:    []Rule{VMRows},
 				},
 				{
 					File:     "config/testdata/rules0-good.rules",
 					Interval: defaultEvalInterval,
-					Name:     "TestGroup", Rules: []Rule{
+					Name:     "TestGroup",
+					Type:     datasource.NewPrometheusType(),
+					Rules: []Rule{
 						Conns,
 						ExampleAlertAlwaysFiring,
 					}},
@@ -186,12 +211,14 @@ func TestManagerUpdate(t *testing.T) {
 				{
 					File:     "config/testdata/rules0-good.rules",
 					Name:     "groupGorSingleAlert",
+					Type:     datasource.NewPrometheusType(),
 					Interval: defaultEvalInterval,
 					Rules:    []Rule{VMRows},
 				},
 				{
 					File:     "config/testdata/rules0-good.rules",
 					Interval: defaultEvalInterval,
+					Type:     datasource.NewPrometheusType(),
 					Name:     "TestGroup", Rules: []Rule{
 						Conns,
 						ExampleAlertAlwaysFiring,
@@ -199,18 +226,38 @@ func TestManagerUpdate(t *testing.T) {
 				},
 			},
 		},
+		{
+			name:       "update prometheus to graphite type",
+			initPath:   "config/testdata/dir/rules-update0-good.rules",
+			updatePath: "config/testdata/dir/rules-update1-good.rules",
+			want: []*Group{
+				{
+					File:     "config/testdata/dir/rules-update1-good.rules",
+					Interval: defaultEvalInterval,
+					Type:     datasource.NewGraphiteType(),
+					Name:     "TestUpdateGroup",
+					Rules: []Rule{
+						ExampleAlertGraphite2,
+						ExampleAlertGraphite,
+					},
+				},
+			},
+		},
 	}
 	for _, tc := range testCases {
 		t.Run(tc.name, func(t *testing.T) {
 			ctx, cancel := context.WithCancel(context.TODO())
-			m := &manager{groups: make(map[uint64]*Group), querier: &fakeQuerier{}}
-			path := []string{tc.initPath}
-			if err := m.update(ctx, path, true, true, false); err != nil {
+			m := &manager{groups: make(map[uint64]*Group), querierBuilder: &fakeQuerier{}}
+
+			cfgInit := loadCfg(t, []string{tc.initPath}, true, true)
+			if err := m.update(ctx, cfgInit, false); err != nil {
 				t.Fatalf("failed to complete initial rules update: %s", err)
 			}
 
-			path = []string{tc.updatePath}
-			_ = m.update(ctx, path, true, true, false)
+			cfgUpdate, err := config.Parse([]string{tc.updatePath}, true, true)
+			if err == nil { // update can fail and that's expected
+				_ = m.update(ctx, cfgUpdate, false)
+			}
 			if len(tc.want) != len(m.groups) {
 				t.Fatalf("\nwant number of groups: %d;\ngot: %d ", len(tc.want), len(m.groups))
 			}
@@ -228,3 +275,12 @@ func TestManagerUpdate(t *testing.T) {
 		})
 	}
 }
+
+func loadCfg(t *testing.T, path []string, validateAnnotations, validateExpressions bool) []config.Group {
+	t.Helper()
+	cfg, err := config.Parse(path, validateAnnotations, validateExpressions)
+	if err != nil {
+		t.Fatal(err)
+	}
+	return cfg
+}

app/vmalert/multiarch/Dockerfile

@@ -0,0 +1,12 @@
+# See https://medium.com/on-docker/use-multi-stage-builds-to-inject-ca-certs-ad1e8f01de1b
+ARG certs_image
+ARG root_image
+FROM $certs_image as certs
+RUN apk --update --no-cache add ca-certificates
+
+FROM $root_image
+COPY --from=certs /etc/ssl/certs/ca-certificates.crt /etc/ssl/certs/ca-certificates.crt
+EXPOSE 8880
+ENTRYPOINT ["/vmalert-prod"]
+ARG TARGETARCH
+COPY vmalert-${TARGETARCH}-prod ./vmalert-prod

app/vmalert/notifier/alert.go

@@ -52,7 +52,8 @@ func (as AlertState) String() string {
 	return "inactive"
 }
 
-type alertTplData struct {
+// AlertTplData is used to execute templating
+type AlertTplData struct {
 	Labels map[string]string
 	Value  float64
 	Expr   string
@@ -60,23 +61,30 @@ type alertTplData struct {
 
 const tplHeader = `{{ $value := .Value }}{{ $labels := .Labels }}{{ $expr := .Expr }}`
 
-// ExecTemplate executes the Alert template for give
+// ExecTemplate executes the Alert template for given
 // map of annotations.
-func (a *Alert) ExecTemplate(annotations map[string]string) (map[string]string, error) {
-	tplData := alertTplData{Value: a.Value, Labels: a.Labels, Expr: a.Expr}
-	return templateAnnotations(annotations, tplHeader, tplData)
+// Every alert could have a different datasource, so function
+// requires a queryFunction as an argument.
+func (a *Alert) ExecTemplate(q QueryFn, annotations map[string]string) (map[string]string, error) {
+	tplData := AlertTplData{Value: a.Value, Labels: a.Labels, Expr: a.Expr}
+	return templateAnnotations(annotations, tplData, funcsWithQuery(q))
+}
+
+// ExecTemplate executes the given template for given annotations map.
+func ExecTemplate(q QueryFn, annotations map[string]string, tpl AlertTplData) (map[string]string, error) {
+	return templateAnnotations(annotations, tpl, funcsWithQuery(q))
 }
 
 // ValidateTemplates validate annotations for possible template error, uses empty data for template population
 func ValidateTemplates(annotations map[string]string) error {
-	_, err := templateAnnotations(annotations, tplHeader, alertTplData{
+	_, err := templateAnnotations(annotations, AlertTplData{
 		Labels: map[string]string{},
 		Value:  0,
-	})
+	}, tmplFunc)
 	return err
 }
 
-func templateAnnotations(annotations map[string]string, header string, data alertTplData) (map[string]string, error) {
+func templateAnnotations(annotations map[string]string, data AlertTplData, funcs template.FuncMap) (map[string]string, error) {
 	var builder strings.Builder
 	var buf bytes.Buffer
 	eg := new(utils.ErrGroup)
@@ -85,10 +93,10 @@ func templateAnnotations(annotations map[string]string, header string, data aler
 		r[key] = text
 		buf.Reset()
 		builder.Reset()
-		builder.Grow(len(header) + len(text))
-		builder.WriteString(header)
+		builder.Grow(len(tplHeader) + len(text))
+		builder.WriteString(tplHeader)
 		builder.WriteString(text)
-		if err := templateAnnotation(&buf, builder.String(), data); err != nil {
+		if err := templateAnnotation(&buf, builder.String(), data, funcs); err != nil {
 			eg.Add(fmt.Errorf("key %q, template %q: %w", key, text, err))
 			continue
 		}
@@ -97,8 +105,9 @@ func templateAnnotations(annotations map[string]string, header string, data aler
 	return r, eg.Err()
 }
 
-func templateAnnotation(dst io.Writer, text string, data alertTplData) error {
-	tpl, err := template.New("").Funcs(tmplFunc).Option("missingkey=zero").Parse(text)
+func templateAnnotation(dst io.Writer, text string, data AlertTplData, funcs template.FuncMap) error {
+	t := template.New("").Funcs(funcs).Option("missingkey=zero")
+	tpl, err := t.Parse(text)
 	if err != nil {
 		return fmt.Errorf("error parsing annotation: %w", err)
 	}

app/vmalert/notifier/alert_test.go

@@ -2,6 +2,8 @@ package notifier
 
 import (
 	"testing"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
 )
 
 func TestAlert_ExecTemplate(t *testing.T) {
@@ -60,11 +62,43 @@ func TestAlert_ExecTemplate(t *testing.T) {
 				"exprEscapedPath":  "vm_rows%7B%5C%22label%5C%22=%5C%22bar%5C%22%7D%3E0",
 			},
 		},
+		{
+			name:  "query",
+			alert: &Alert{Expr: `vm_rows{"label"="bar"}>0`},
+			annotations: map[string]string{
+				"summary": `{{ query "foo" | first | value }}`,
+				"desc":    `{{ range query "bar" }}{{ . | label "foo" }} {{ . | value }};{{ end }}`,
+			},
+			expTpl: map[string]string{
+				"summary": "1",
+				"desc":    "bar 1;garply 2;",
+			},
+		},
 	}
 
+	qFn := func(q string) ([]datasource.Metric, error) {
+		return []datasource.Metric{
+			{
+				Labels: []datasource.Label{
+					{Name: "foo", Value: "bar"},
+					{Name: "baz", Value: "qux"},
+				},
+				Values:     []float64{1},
+				Timestamps: []int64{1},
+			},
+			{
+				Labels: []datasource.Label{
+					{Name: "foo", Value: "garply"},
+					{Name: "baz", Value: "fred"},
+				},
+				Values:     []float64{2},
+				Timestamps: []int64{1},
+			},
+		}, nil
+	}
 	for _, tc := range testCases {
 		t.Run(tc.name, func(t *testing.T) {
-			tpl, err := tc.alert.ExecTemplate(tc.annotations)
+			tpl, err := tc.alert.ExecTemplate(qFn, tc.annotations)
 			if err != nil {
 				t.Fatal(err)
 			}

app/vmalert/notifier/init.go

@@ -1,7 +1,6 @@
 package notifier
 
 import (
-	"flag"
 	"fmt"
 	"net/http"
 
@@ -11,10 +10,10 @@ import (
 
 var (
 	addrs             = flagutil.NewArray("notifier.url", "Prometheus alertmanager URL. Required parameter. e.g. http://127.0.0.1:9093")
-	basicAuthUsername = flagutil.NewArray("notifier.basicAuth.username", "Optional basic auth username for -datasource.url")
-	basicAuthPassword = flagutil.NewArray("notifier.basicAuth.password", "Optional basic auth password for -datasource.url")
+	basicAuthUsername = flagutil.NewArray("notifier.basicAuth.username", "Optional basic auth username for -notifier.url")
+	basicAuthPassword = flagutil.NewArray("notifier.basicAuth.password", "Optional basic auth password for -notifier.url")
 
-	tlsInsecureSkipVerify = flag.Bool("notifier.tlsInsecureSkipVerify", false, "Whether to skip tls verification when connecting to -notifier.url")
+	tlsInsecureSkipVerify = flagutil.NewArrayBool("notifier.tlsInsecureSkipVerify", "Whether to skip tls verification when connecting to -notifier.url")
 	tlsCertFile           = flagutil.NewArray("notifier.tlsCertFile", "Optional path to client-side TLS certificate file to use when connecting to -notifier.url")
 	tlsKeyFile            = flagutil.NewArray("notifier.tlsKeyFile", "Optional path to client-side TLS certificate key to use when connecting to -notifier.url")
 	tlsCAFile             = flagutil.NewArray("notifier.tlsCAFile", "Optional path to TLS CA file to use for verifying connections to -notifier.url. "+
@@ -33,7 +32,7 @@ func Init(gen AlertURLGenerator) ([]Notifier, error) {
 	for i, addr := range *addrs {
 		cert, key := tlsCertFile.GetOptionalArg(i), tlsKeyFile.GetOptionalArg(i)
 		ca, serverName := tlsCAFile.GetOptionalArg(i), tlsServerName.GetOptionalArg(i)
-		tr, err := utils.Transport(addr, cert, key, ca, serverName, *tlsInsecureSkipVerify)
+		tr, err := utils.Transport(addr, cert, key, ca, serverName, tlsInsecureSkipVerify.GetOptionalArg(i))
 		if err != nil {
 			return nil, fmt.Errorf("failed to create transport: %w", err)
 		}

app/vmalert/notifier/template_func.go

@@ -14,39 +14,87 @@
 package notifier
 
 import (
+	"errors"
 	"fmt"
-	html_template "html/template"
 	"math"
 	"net/url"
 	"regexp"
 	"strings"
-	text_template "text/template"
 	"time"
+
+	htmlTpl "html/template"
+	textTpl "text/template"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
 )
 
-var tmplFunc text_template.FuncMap
+// metric is private copy of datasource.Metric,
+// it is used for templating annotations,
+// Labels as map simplifies templates evaluation.
+type metric struct {
+	Labels    map[string]string
+	Timestamp int64
+	Value     float64
+}
 
-// InitTemplateFunc returns template helper functions
+// datasourceMetricsToTemplateMetrics converts Metrics from datasource package to private copy for templating.
+func datasourceMetricsToTemplateMetrics(ms []datasource.Metric) []metric {
+	mss := make([]metric, 0, len(ms))
+	for _, m := range ms {
+		labelsMap := make(map[string]string, len(m.Labels))
+		for _, labelValue := range m.Labels {
+			labelsMap[labelValue.Name] = labelValue.Value
+		}
+		mss = append(mss, metric{
+			Labels:    labelsMap,
+			Timestamp: m.Timestamps[0],
+			Value:     m.Values[0]})
+	}
+	return mss
+}
+
+// QueryFn is used to wrap a call to datasource into simple-to-use function
+// for templating functions.
+type QueryFn func(query string) ([]datasource.Metric, error)
+
+var tmplFunc textTpl.FuncMap
+
+// InitTemplateFunc initiates template helper functions
 func InitTemplateFunc(externalURL *url.URL) {
-	tmplFunc = text_template.FuncMap{
-		"args": func(args ...interface{}) map[string]interface{} {
-			result := make(map[string]interface{})
-			for i, a := range args {
-				result[fmt.Sprintf("arg%d", i)] = a
-			}
-			return result
-		},
+	tmplFunc = textTpl.FuncMap{
+		/* Strings */
+
+		// reReplaceAll ReplaceAllString returns a copy of src, replacing matches of the Regexp with
+		// the replacement string repl. Inside repl, $ signs are interpreted as in Expand,
+		// so for instance $1 represents the text of the first submatch.
+		// alias for https://golang.org/pkg/regexp/#Regexp.ReplaceAllString
 		"reReplaceAll": func(pattern, repl, text string) string {
 			re := regexp.MustCompile(pattern)
 			return re.ReplaceAllString(text, repl)
 		},
-		"safeHtml": func(text string) html_template.HTML {
-			return html_template.HTML(text)
-		},
-		"match":   regexp.MatchString,
-		"title":   strings.Title,
+
+		// match reports whether the string s
+		// contains any match of the regular expression pattern.
+		// alias for https://golang.org/pkg/regexp/#MatchString
+		"match": regexp.MatchString,
+
+		// title returns a copy of the string s with all Unicode letters
+		// that begin words mapped to their Unicode title case.
+		// alias for https://golang.org/pkg/strings/#Title
+		"title": strings.Title,
+
+		// toUpper returns s with all Unicode letters mapped to their upper case.
+		// alias for https://golang.org/pkg/strings/#ToUpper
 		"toUpper": strings.ToUpper,
+
+		// toLower returns s with all Unicode letters mapped to their lower case.
+		// alias for https://golang.org/pkg/strings/#ToLower
 		"toLower": strings.ToLower,
+
+		/* Numbers */
+
+		// humanize converts given number to a human readable format
+		// by adding metric prefixes https://en.wikipedia.org/wiki/Metric_prefix
 		"humanize": func(v float64) string {
 			if v == 0 || math.IsNaN(v) || math.IsInf(v, 0) {
 				return fmt.Sprintf("%.4g", v)
@@ -72,6 +120,8 @@ func InitTemplateFunc(externalURL *url.URL) {
 			}
 			return fmt.Sprintf("%.4g%s", v, prefix)
 		},
+
+		// humanize1024 converts given number to a human readable format with 1024 as base
 		"humanize1024": func(v float64) string {
 			if math.Abs(v) <= 1 || math.IsNaN(v) || math.IsInf(v, 0) {
 				return fmt.Sprintf("%.4g", v)
@@ -86,6 +136,8 @@ func InitTemplateFunc(externalURL *url.URL) {
 			}
 			return fmt.Sprintf("%.4g%s", v, prefix)
 		},
+
+		// humanizeDuration converts given seconds to a human readable duration
 		"humanizeDuration": func(v float64) string {
 			if math.IsNaN(v) || math.IsInf(v, 0) {
 				return fmt.Sprintf("%.4g", v)
@@ -126,9 +178,13 @@ func InitTemplateFunc(externalURL *url.URL) {
 			}
 			return fmt.Sprintf("%.4g%ss", v, prefix)
 		},
+
+		// humanizePercentage converts given ratio value to a fraction of 100
 		"humanizePercentage": func(v float64) string {
 			return fmt.Sprintf("%.4g%%", v*100)
 		},
+
+		// humanizeTimestamp converts given timestamp to a human readable time equivalent
 		"humanizeTimestamp": func(v float64) string {
 			if math.IsNaN(v) || math.IsInf(v, 0) {
 				return fmt.Sprintf("%.4g", v)
@@ -136,24 +192,115 @@ func InitTemplateFunc(externalURL *url.URL) {
 			t := TimeFromUnixNano(int64(v * 1e9)).Time().UTC()
 			return fmt.Sprint(t)
 		},
-		"pathPrefix": func() string {
-			return externalURL.Path
-		},
+
+		/* URLs */
+
+		// externalURL returns value of `external.url` flag
 		"externalURL": func() string {
 			return externalURL.String()
 		},
+
+		// pathPrefix returns a Path segment from the URL value in `external.url` flag
+		"pathPrefix": func() string {
+			return externalURL.Path
+		},
+
+		// pathEscape escapes the string so it can be safely placed inside a URL path segment,
+		// replacing special characters (including /) with %XX sequences as needed.
+		// alias for https://golang.org/pkg/net/url/#PathEscape
 		"pathEscape": func(u string) string {
 			return url.PathEscape(u)
 		},
+
+		// queryEscape escapes the string so it can be safely placed
+		// inside a URL query.
+		// alias for https://golang.org/pkg/net/url/#QueryEscape
 		"queryEscape": func(q string) string {
 			return url.QueryEscape(q)
 		},
+
+		// crlfEscape replaces new line chars to skip URL encoding.
+		// see https://github.com/VictoriaMetrics/VictoriaMetrics/issues/890
+		"crlfEscape": func(q string) string {
+			q = strings.Replace(q, "\n", `\n`, -1)
+			return strings.Replace(q, "\r", `\r`, -1)
+		},
+
+		// quotesEscape escapes quote char
 		"quotesEscape": func(q string) string {
 			return strings.Replace(q, `"`, `\"`, -1)
 		},
+
+		// query executes the MetricsQL/PromQL query against
+		// configured `datasource.url` address.
+		// For example, {{ query "foo" | first | value }} will
+		// execute "/api/v1/query?query=foo" request and will return
+		// the first value in response.
+		"query": func(q string) ([]metric, error) {
+			// query function supposed to be substituted at funcsWithQuery().
+			// it is present here only for validation purposes, when there is no
+			// provided datasource.
+			//
+			// return non-empty slice to pass validation with chained functions in template
+			// see issue #989 for details
+			return []metric{{}}, nil
+		},
+
+		// first returns the first by order element from the given metrics list.
+		// usually used alongside with `query` template function.
+		"first": func(metrics []metric) (metric, error) {
+			if len(metrics) > 0 {
+				return metrics[0], nil
+			}
+			return metric{}, errors.New("first() called on vector with no elements")
+		},
+
+		// label returns the value of the given label name for the given metric.
+		// usually used alongside with `query` template function.
+		"label": func(label string, m metric) string {
+			return m.Labels[label]
+		},
+
+		// value returns the value of the given metric.
+		// usually used alongside with `query` template function.
+		"value": func(m metric) float64 {
+			return m.Value
+		},
+
+		/* Helpers */
+
+		// Converts a list of objects to a map with keys arg0, arg1 etc.
+		// This is intended to allow multiple arguments to be passed to templates.
+		"args": func(args ...interface{}) map[string]interface{} {
+			result := make(map[string]interface{})
+			for i, a := range args {
+				result[fmt.Sprintf("arg%d", i)] = a
+			}
+			return result
+		},
+
+		// safeHtml marks string as HTML not requiring auto-escaping.
+		"safeHtml": func(text string) htmlTpl.HTML {
+			return htmlTpl.HTML(text)
+		},
 	}
 }
 
+func funcsWithQuery(query QueryFn) textTpl.FuncMap {
+	fm := make(textTpl.FuncMap)
+	for k, fn := range tmplFunc {
+		fm[k] = fn
+	}
+	fm["query"] = func(q string) ([]metric, error) {
+		result, err := query(q)
+		if err != nil {
+			return nil, err
+		}
+		return datasourceMetricsToTemplateMetrics(result), nil
+	}
+	return fm
+}
+
 // Time is the number of milliseconds since the epoch
 // (1970-01-01 00:00 UTC) excluding leap seconds.
 type Time int64

app/vmalert/recording.go

@@ -3,8 +3,8 @@ package main
 import (
 	"context"
 	"fmt"
-	"hash/fnv"
 	"sort"
+	"strings"
 	"sync"
 	"time"
 
@@ -18,12 +18,15 @@ import (
 // to evaluate configured Expression and
 // return TimeSeries as result.
 type RecordingRule struct {
+	Type    datasource.Type
 	RuleID  uint64
 	Name    string
 	Expr    string
 	Labels  map[string]string
 	GroupID uint64
 
+	q datasource.Querier
+
 	// guard status fields
 	mu sync.RWMutex
 	// stores last moment of time Exec was called
@@ -51,15 +54,22 @@ func (rr *RecordingRule) ID() uint64 {
 	return rr.RuleID
 }
 
-func newRecordingRule(group *Group, cfg config.Rule) *RecordingRule {
+func newRecordingRule(qb datasource.QuerierBuilder, group *Group, cfg config.Rule) *RecordingRule {
 	rr := &RecordingRule{
+		Type:    cfg.Type,
 		RuleID:  cfg.ID,
 		Name:    cfg.Record,
 		Expr:    cfg.Expr,
 		Labels:  cfg.Labels,
 		GroupID: group.ID(),
 		metrics: &recordingRuleMetrics{},
+		q: qb.BuildWithParams(datasource.QuerierParams{
+			DataSourceType:     &cfg.Type,
+			EvaluationInterval: group.Interval,
+			ExtraLabels:        group.ExtraFilterLabels,
+		}),
 	}
+
 	labels := fmt.Sprintf(`recording=%q, group=%q, id="%d"`, rr.Name, group.Name, rr.ID())
 	rr.metrics.errors = getOrCreateGauge(fmt.Sprintf(`vmalert_recording_rules_error{%s}`, labels),
 		func() float64 {
@@ -78,14 +88,31 @@ func (rr *RecordingRule) Close() {
 	metrics.UnregisterMetric(rr.metrics.errors.name)
 }
 
-// Exec executes RecordingRule expression via the given Querier.
-func (rr *RecordingRule) Exec(ctx context.Context, q datasource.Querier, series bool) ([]prompbmarshal.TimeSeries, error) {
-	if !series {
-		return nil, nil
+// ExecRange executes recording rule on the given time range similarly to Exec.
+// It doesn't update internal states of the Rule and meant to be used just
+// to get time series for backfilling.
+func (rr *RecordingRule) ExecRange(ctx context.Context, start, end time.Time) ([]prompbmarshal.TimeSeries, error) {
+	series, err := rr.q.QueryRange(ctx, rr.Expr, start, end)
+	if err != nil {
+		return nil, err
 	}
+	duplicates := make(map[string]struct{}, len(series))
+	var tss []prompbmarshal.TimeSeries
+	for _, s := range series {
+		ts := rr.toTimeSeries(s)
+		key := stringifyLabels(ts)
+		if _, ok := duplicates[key]; ok {
+			return nil, fmt.Errorf("original metric %v; resulting labels %q: %w", s.Labels, key, errDuplicate)
+		}
+		duplicates[key] = struct{}{}
+		tss = append(tss, ts)
+	}
+	return tss, nil
+}
 
-	qMetrics, err := q.Query(ctx, rr.Expr)
-
+// Exec executes RecordingRule expression via the given Querier.
+func (rr *RecordingRule) Exec(ctx context.Context) ([]prompbmarshal.TimeSeries, error) {
+	qMetrics, err := rr.q.Query(ctx, rr.Expr)
 	rr.mu.Lock()
 	defer rr.mu.Unlock()
 
@@ -95,36 +122,41 @@ func (rr *RecordingRule) Exec(ctx context.Context, q datasource.Querier, series
 		return nil, fmt.Errorf("failed to execute query %q: %w", rr.Expr, err)
 	}
 
-	duplicates := make(map[uint64]prompbmarshal.TimeSeries, len(qMetrics))
+	duplicates := make(map[string]struct{}, len(qMetrics))
 	var tss []prompbmarshal.TimeSeries
 	for _, r := range qMetrics {
-		ts := rr.toTimeSeries(r, rr.lastExecTime)
-		h := hashTimeSeries(ts)
-		if _, ok := duplicates[h]; ok {
+		ts := rr.toTimeSeries(r)
+		key := stringifyLabels(ts)
+		if _, ok := duplicates[key]; ok {
 			rr.lastExecError = errDuplicate
-			return nil, errDuplicate
+			return nil, fmt.Errorf("original metric %v; resulting labels %q: %w", r, key, errDuplicate)
 		}
-		duplicates[h] = ts
+		duplicates[key] = struct{}{}
 		tss = append(tss, ts)
 	}
 	return tss, nil
 }
 
-func hashTimeSeries(ts prompbmarshal.TimeSeries) uint64 {
-	hash := fnv.New64a()
+func stringifyLabels(ts prompbmarshal.TimeSeries) string {
 	labels := ts.Labels
-	sort.Slice(labels, func(i, j int) bool {
-		return labels[i].Name < labels[j].Name
-	})
-	for _, l := range labels {
-		hash.Write([]byte(l.Name))
-		hash.Write([]byte(l.Value))
-		hash.Write([]byte("\xff"))
+	if len(labels) > 1 {
+		sort.Slice(labels, func(i, j int) bool {
+			return labels[i].Name < labels[j].Name
+		})
 	}
-	return hash.Sum64()
+	b := strings.Builder{}
+	for i, l := range labels {
+		b.WriteString(l.Name)
+		b.WriteString("=")
+		b.WriteString(l.Value)
+		if i != len(labels)-1 {
+			b.WriteString(",")
+		}
+	}
+	return b.String()
 }
 
-func (rr *RecordingRule) toTimeSeries(m datasource.Metric, timestamp time.Time) prompbmarshal.TimeSeries {
+func (rr *RecordingRule) toTimeSeries(m datasource.Metric) prompbmarshal.TimeSeries {
 	labels := make(map[string]string)
 	for _, l := range m.Labels {
 		labels[l.Name] = l.Value
@@ -134,12 +166,10 @@ func (rr *RecordingRule) toTimeSeries(m datasource.Metric, timestamp time.Time)
 	for k, v := range rr.Labels {
 		labels[k] = v
 	}
-	return newTimeSeries(m.Value, labels, timestamp)
+	return newTimeSeries(m.Values, m.Timestamps, labels)
 }
 
 // UpdateWith copies all significant fields.
-// alerts state isn't copied since
-// it should be updated in next 2 Execs
 func (rr *RecordingRule) UpdateWith(r Rule) error {
 	nr, ok := r.(*RecordingRule)
 	if !ok {
@@ -147,6 +177,7 @@ func (rr *RecordingRule) UpdateWith(r Rule) error {
 	}
 	rr.Expr = nr.Expr
 	rr.Labels = nr.Labels
+	rr.q = nr.q
 	return nil
 }
 
@@ -162,6 +193,7 @@ func (rr *RecordingRule) RuleAPI() APIRecordingRule {
 		ID:         fmt.Sprintf("%d", rr.ID()),
 		GroupID:    fmt.Sprintf("%d", rr.GroupID),
 		Name:       rr.Name,
+		Type:       rr.Type.String(),
 		Expression: rr.Expr,
 		LastError:  lastErr,
 		LastExec:   rr.lastExecTime,

app/vmalert/recording_test.go

@@ -11,7 +11,7 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
 )
 
-func TestRecoridngRule_ToTimeSeries(t *testing.T) {
+func TestRecoridngRule_Exec(t *testing.T) {
 	timestamp := time.Now()
 	testCases := []struct {
 		rule    *RecordingRule
@@ -24,9 +24,9 @@ func TestRecoridngRule_ToTimeSeries(t *testing.T) {
 				"__name__", "bar",
 			)},
 			[]prompbmarshal.TimeSeries{
-				newTimeSeries(10, map[string]string{
+				newTimeSeries([]float64{10}, []int64{timestamp.UnixNano()}, map[string]string{
 					"__name__": "foo",
-				}, timestamp),
+				}),
 			},
 		},
 		{
@@ -37,18 +37,18 @@ func TestRecoridngRule_ToTimeSeries(t *testing.T) {
 				metricWithValueAndLabels(t, 3, "__name__", "baz", "job", "baz"),
 			},
 			[]prompbmarshal.TimeSeries{
-				newTimeSeries(1, map[string]string{
+				newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()}, map[string]string{
 					"__name__": "foobarbaz",
 					"job":      "foo",
-				}, timestamp),
-				newTimeSeries(2, map[string]string{
+				}),
+				newTimeSeries([]float64{2}, []int64{timestamp.UnixNano()}, map[string]string{
 					"__name__": "foobarbaz",
 					"job":      "bar",
-				}, timestamp),
-				newTimeSeries(3, map[string]string{
+				}),
+				newTimeSeries([]float64{3}, []int64{timestamp.UnixNano()}, map[string]string{
 					"__name__": "foobarbaz",
 					"job":      "baz",
-				}, timestamp),
+				}),
 			},
 		},
 		{
@@ -59,16 +59,16 @@ func TestRecoridngRule_ToTimeSeries(t *testing.T) {
 				metricWithValueAndLabels(t, 2, "__name__", "foo", "job", "foo"),
 				metricWithValueAndLabels(t, 1, "__name__", "bar", "job", "bar")},
 			[]prompbmarshal.TimeSeries{
-				newTimeSeries(2, map[string]string{
+				newTimeSeries([]float64{2}, []int64{timestamp.UnixNano()}, map[string]string{
 					"__name__": "job:foo",
 					"job":      "foo",
 					"source":   "test",
-				}, timestamp),
-				newTimeSeries(1, map[string]string{
+				}),
+				newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()}, map[string]string{
 					"__name__": "job:foo",
 					"job":      "bar",
 					"source":   "test",
-				}, timestamp),
+				}),
 			},
 		},
 	}
@@ -76,7 +76,8 @@ func TestRecoridngRule_ToTimeSeries(t *testing.T) {
 		t.Run(tc.rule.Name, func(t *testing.T) {
 			fq := &fakeQuerier{}
 			fq.add(tc.metrics...)
-			tss, err := tc.rule.Exec(context.TODO(), fq, true)
+			tc.rule.q = fq
+			tss, err := tc.rule.Exec(context.TODO())
 			if err != nil {
 				t.Fatalf("unexpected Exec err: %s", err)
 			}
@@ -87,7 +88,88 @@ func TestRecoridngRule_ToTimeSeries(t *testing.T) {
 	}
 }
 
-func TestRecoridngRule_ToTimeSeriesNegative(t *testing.T) {
+func TestRecoridngRule_ExecRange(t *testing.T) {
+	timestamp := time.Now()
+	testCases := []struct {
+		rule    *RecordingRule
+		metrics []datasource.Metric
+		expTS   []prompbmarshal.TimeSeries
+	}{
+		{
+			&RecordingRule{Name: "foo"},
+			[]datasource.Metric{metricWithValuesAndLabels(t, []float64{10, 20, 30},
+				"__name__", "bar",
+			)},
+			[]prompbmarshal.TimeSeries{
+				newTimeSeries([]float64{10, 20, 30},
+					[]int64{timestamp.UnixNano(), timestamp.UnixNano(), timestamp.UnixNano()},
+					map[string]string{
+						"__name__": "foo",
+					}),
+			},
+		},
+		{
+			&RecordingRule{Name: "foobarbaz"},
+			[]datasource.Metric{
+				metricWithValuesAndLabels(t, []float64{1}, "__name__", "foo", "job", "foo"),
+				metricWithValuesAndLabels(t, []float64{2, 3}, "__name__", "bar", "job", "bar"),
+				metricWithValuesAndLabels(t, []float64{4, 5, 6}, "__name__", "baz", "job", "baz"),
+			},
+			[]prompbmarshal.TimeSeries{
+				newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()}, map[string]string{
+					"__name__": "foobarbaz",
+					"job":      "foo",
+				}),
+				newTimeSeries([]float64{2, 3}, []int64{timestamp.UnixNano(), timestamp.UnixNano()}, map[string]string{
+					"__name__": "foobarbaz",
+					"job":      "bar",
+				}),
+				newTimeSeries([]float64{4, 5, 6},
+					[]int64{timestamp.UnixNano(), timestamp.UnixNano(), timestamp.UnixNano()},
+					map[string]string{
+						"__name__": "foobarbaz",
+						"job":      "baz",
+					}),
+			},
+		},
+		{
+			&RecordingRule{Name: "job:foo", Labels: map[string]string{
+				"source": "test",
+			}},
+			[]datasource.Metric{
+				metricWithValueAndLabels(t, 2, "__name__", "foo", "job", "foo"),
+				metricWithValueAndLabels(t, 1, "__name__", "bar", "job", "bar")},
+			[]prompbmarshal.TimeSeries{
+				newTimeSeries([]float64{2}, []int64{timestamp.UnixNano()}, map[string]string{
+					"__name__": "job:foo",
+					"job":      "foo",
+					"source":   "test",
+				}),
+				newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()}, map[string]string{
+					"__name__": "job:foo",
+					"job":      "bar",
+					"source":   "test",
+				}),
+			},
+		},
+	}
+	for _, tc := range testCases {
+		t.Run(tc.rule.Name, func(t *testing.T) {
+			fq := &fakeQuerier{}
+			fq.add(tc.metrics...)
+			tc.rule.q = fq
+			tss, err := tc.rule.ExecRange(context.TODO(), time.Now(), time.Now())
+			if err != nil {
+				t.Fatalf("unexpected Exec err: %s", err)
+			}
+			if err := compareTimeSeries(t, tc.expTS, tss); err != nil {
+				t.Fatalf("timeseries missmatch: %s", err)
+			}
+		})
+	}
+}
+
+func TestRecoridngRule_ExecNegative(t *testing.T) {
 	rr := &RecordingRule{Name: "job:foo", Labels: map[string]string{
 		"job": "test",
 	}}
@@ -95,8 +177,8 @@ func TestRecoridngRule_ToTimeSeriesNegative(t *testing.T) {
 	fq := &fakeQuerier{}
 	expErr := "connection reset by peer"
 	fq.setErr(errors.New(expErr))
-
-	_, err := rr.Exec(context.TODO(), fq, true)
+	rr.q = fq
+	_, err := rr.Exec(context.TODO())
 	if err == nil {
 		t.Fatalf("expected to get err; got nil")
 	}
@@ -111,7 +193,7 @@ func TestRecoridngRule_ToTimeSeriesNegative(t *testing.T) {
 	fq.add(metricWithValueAndLabels(t, 1, "__name__", "foo", "job", "foo"))
 	fq.add(metricWithValueAndLabels(t, 2, "__name__", "foo", "job", "bar"))
 
-	_, err = rr.Exec(context.TODO(), fq, true)
+	_, err = rr.Exec(context.TODO())
 	if err == nil {
 		t.Fatalf("expected to get err; got nil")
 	}

app/vmalert/remoteread/init.go

@@ -10,9 +10,9 @@ import (
 )
 
 var (
-	addr = flag.String("remoteRead.url", "", "Optional URL to Victoria Metrics or VMSelect that will be used to restore alerts"+
-		" state. This configuration makes sense only if `vmalert` was configured with `remoteWrite.url` before and has been successfully persisted its state."+
-		" E.g. http://127.0.0.1:8428")
+	addr = flag.String("remoteRead.url", "", "Optional URL to VictoriaMetrics or vmselect that will be used to restore alerts "+
+		"state. This configuration makes sense only if `vmalert` was configured with `remoteWrite.url` before and has been successfully persisted its state. "+
+		"E.g. http://127.0.0.1:8428")
 	basicAuthUsername     = flag.String("remoteRead.basicAuth.username", "", "Optional basic auth username for -remoteRead.url")
 	basicAuthPassword     = flag.String("remoteRead.basicAuth.password", "", "Optional basic auth password for -remoteRead.url")
 	tlsInsecureSkipVerify = flag.Bool("remoteRead.tlsInsecureSkipVerify", false, "Whether to skip tls verification when connecting to -remoteRead.url")
@@ -26,7 +26,7 @@ var (
 
 // Init creates a Querier from provided flag values.
 // Returns nil if addr flag wasn't set.
-func Init() (datasource.Querier, error) {
+func Init() (datasource.QuerierBuilder, error) {
 	if *addr == "" {
 		return nil, nil
 	}
@@ -35,5 +35,5 @@ func Init() (datasource.Querier, error) {
 		return nil, fmt.Errorf("failed to create transport: %w", err)
 	}
 	c := &http.Client{Transport: tr}
-	return datasource.NewVMStorage(*addr, *basicAuthUsername, *basicAuthPassword, 0, c), nil
+	return datasource.NewVMStorage(*addr, *basicAuthUsername, *basicAuthPassword, 0, 0, false, c), nil
 }

app/vmalert/remotewrite/init.go

@@ -10,8 +10,8 @@ import (
 )
 
 var (
-	addr = flag.String("remoteWrite.url", "", "Optional URL to Victoria Metrics or VMInsert where to persist alerts state"+
-		" and recording rules results in form of timeseries. E.g. http://127.0.0.1:8428")
+	addr = flag.String("remoteWrite.url", "", "Optional URL to VictoriaMetrics or vminsert where to persist alerts state "+
+		"and recording rules results in form of timeseries. E.g. http://127.0.0.1:8428")
 	basicAuthUsername = flag.String("remoteWrite.basicAuth.username", "", "Optional basic auth username for -remoteWrite.url")
 	basicAuthPassword = flag.String("remoteWrite.basicAuth.password", "", "Optional basic auth password for -remoteWrite.url")
 

app/vmalert/remotewrite/remotewrite.go

@@ -94,7 +94,7 @@ func NewClient(ctx context.Context, cfg Config) (*Client, error) {
 			Timeout:   cfg.WriteTimeout,
 			Transport: cfg.Transport,
 		},
-		addr:          strings.TrimSuffix(cfg.Addr, "/") + writePath,
+		addr:          strings.TrimSuffix(cfg.Addr, "/"),
 		baUser:        cfg.BasicAuthUser,
 		baPass:        cfg.BasicAuthPass,
 		flushInterval: cfg.FlushInterval,
@@ -231,6 +231,7 @@ func (c *Client) send(ctx context.Context, data []byte) error {
 	if c.baPass != "" {
 		req.SetBasicAuth(c.baUser, c.baPass)
 	}
+	req.URL.Path += writePath
 	resp, err := c.c.Do(req.WithContext(ctx))
 	if err != nil {
 		return fmt.Errorf("error while sending request to %s: %w; Data len %d(%d)",

app/vmalert/replay.go

@@ -0,0 +1,160 @@
+package main
+
+import (
+	"context"
+	"flag"
+	"fmt"
+	"strings"
+	"time"
+
+	"github.com/cheggaaa/pb/v3"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/config"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/remotewrite"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
+)
+
+var (
+	replayFrom = flag.String("replay.timeFrom", "",
+		"The time filter in RFC3339 format to select time series with timestamp equal or higher than provided value. E.g. '2020-01-01T20:07:00Z'")
+	replayTo = flag.String("replay.timeTo", "",
+		"The time filter in RFC3339 format to select timeseries with timestamp equal or lower than provided value. E.g. '2020-01-01T20:07:00Z'")
+	replayRulesDelay = flag.Duration("replay.rulesDelay", time.Second,
+		"Delay between rules evaluation within the group. Could be important if there are chained rules inside of the group"+
+			"and processing need to wait for previous rule results to be persisted by remote storage before evaluating the next rule."+
+			"Keep it equal or bigger than -remoteWrite.flushInterval.")
+	replayMaxDatapoints = flag.Int("replay.maxDatapointsPerQuery", 1e3,
+		"Max number of data points expected in one request. The higher the value, the less requests will be made during replay.")
+	replayRuleRetryAttempts = flag.Int("replay.ruleRetryAttempts", 5,
+		"Defines how many retries to make before giving up on rule if request for it returns an error.")
+)
+
+func replay(groupsCfg []config.Group, qb datasource.QuerierBuilder, rw *remotewrite.Client) error {
+	if *replayMaxDatapoints < 1 {
+		return fmt.Errorf("replay.maxDatapointsPerQuery can't be lower than 1")
+	}
+	tFrom, err := time.Parse(time.RFC3339, *replayFrom)
+	if err != nil {
+		return fmt.Errorf("failed to parse %q: %s", *replayFrom, err)
+	}
+	tTo, err := time.Parse(time.RFC3339, *replayTo)
+	if err != nil {
+		return fmt.Errorf("failed to parse %q: %s", *replayTo, err)
+	}
+	if !tTo.After(tFrom) {
+		return fmt.Errorf("replay.timeTo must be bigger than replay.timeFrom")
+	}
+	labels := make(map[string]string)
+	for _, s := range *externalLabels {
+		if len(s) == 0 {
+			continue
+		}
+		n := strings.IndexByte(s, '=')
+		if n < 0 {
+			return fmt.Errorf("missing '=' in `-label`. It must contain label in the form `name=value`; got %q", s)
+		}
+		labels[s[:n]] = s[n+1:]
+	}
+
+	fmt.Printf("Replay mode:"+
+		"\nfrom: \t%v "+
+		"\nto: \t%v "+
+		"\nmax data points per request: %d\n",
+		tFrom, tTo, *replayMaxDatapoints)
+
+	var total int
+	for _, cfg := range groupsCfg {
+		ng := newGroup(cfg, qb, *evaluationInterval, labels)
+		total += ng.replay(tFrom, tTo, rw)
+	}
+	logger.Infof("replay finished! Imported %d samples", total)
+	if rw != nil {
+		return rw.Close()
+	}
+	return nil
+}
+
+func (g *Group) replay(start, end time.Time, rw *remotewrite.Client) int {
+	var total int
+	step := g.Interval * time.Duration(*replayMaxDatapoints)
+	ri := rangeIterator{start: start, end: end, step: step}
+	iterations := int(end.Sub(start)/step) + 1
+	fmt.Printf("\nGroup %q"+
+		"\ninterval: \t%v"+
+		"\nrequests to make: \t%d"+
+		"\nmax range per request: \t%v\n",
+		g.Name, g.Interval, iterations, step)
+	for _, rule := range g.Rules {
+		fmt.Printf("> Rule %q (ID: %d)\n", rule, rule.ID())
+		bar := pb.StartNew(iterations)
+		ri.reset()
+		for ri.next() {
+			n, err := replayRule(rule, ri.s, ri.e, rw)
+			if err != nil {
+				logger.Fatalf("rule %q: %s", rule, err)
+			}
+			total += n
+			bar.Increment()
+		}
+		bar.Finish()
+		// sleep to let remote storage to flush data on-disk
+		// so chained rules could be calculated correctly
+		time.Sleep(*replayRulesDelay)
+	}
+	return total
+}
+
+func replayRule(rule Rule, start, end time.Time, rw *remotewrite.Client) (int, error) {
+	var err error
+	var tss []prompbmarshal.TimeSeries
+	for i := 0; i < *replayRuleRetryAttempts; i++ {
+		tss, err = rule.ExecRange(context.Background(), start, end)
+		if err == nil {
+			break
+		}
+		logger.Errorf("attempt %d to execute rule %q failed: %s", i+1, rule, err)
+		time.Sleep(time.Second)
+	}
+	if err != nil { // means all attempts failed
+		return 0, err
+	}
+	if len(tss) < 1 {
+		return 0, nil
+	}
+	var n int
+	for _, ts := range tss {
+		if err := rw.Push(ts); err != nil {
+			return n, fmt.Errorf("remote write failure: %s", err)
+		}
+		n += len(ts.Samples)
+	}
+	return n, nil
+}
+
+type rangeIterator struct {
+	step       time.Duration
+	start, end time.Time
+
+	iter int
+	s, e time.Time
+}
+
+func (ri *rangeIterator) reset() {
+	ri.iter = 0
+	ri.s, ri.e = time.Time{}, time.Time{}
+}
+
+func (ri *rangeIterator) next() bool {
+	ri.s = ri.start.Add(ri.step * time.Duration(ri.iter))
+	if !ri.end.After(ri.s) {
+		return false
+	}
+	ri.e = ri.s.Add(ri.step)
+	if ri.e.After(ri.end) {
+		ri.e = ri.end
+	}
+	ri.iter++
+	return true
+}

app/vmalert/replay_test.go

@@ -0,0 +1,250 @@
+package main
+
+import (
+	"context"
+	"fmt"
+	"testing"
+	"time"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/config"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/utils"
+)
+
+type fakeReplayQuerier struct {
+	fakeQuerier
+	registry map[string]map[string]struct{}
+}
+
+func (fr *fakeReplayQuerier) BuildWithParams(_ datasource.QuerierParams) datasource.Querier {
+	return fr
+}
+
+func (fr *fakeReplayQuerier) QueryRange(_ context.Context, q string, from, to time.Time) ([]datasource.Metric, error) {
+	key := fmt.Sprintf("%s+%s", from.Format("15:04:05"), to.Format("15:04:05"))
+	dps, ok := fr.registry[q]
+	if !ok {
+		return nil, fmt.Errorf("unexpected query received: %q", q)
+	}
+	_, ok = dps[key]
+	if !ok {
+		return nil, fmt.Errorf("unexpected time range received: %q", key)
+	}
+	delete(dps, key)
+	if len(fr.registry[q]) < 1 {
+		delete(fr.registry, q)
+	}
+	return nil, nil
+}
+
+func TestReplay(t *testing.T) {
+	testCases := []struct {
+		name     string
+		from, to string
+		maxDP    int
+		cfg      []config.Group
+		qb       *fakeReplayQuerier
+	}{
+		{
+			name:  "one rule + one response",
+			from:  "2021-01-01T12:00:00.000Z",
+			to:    "2021-01-01T12:02:00.000Z",
+			maxDP: 10,
+			cfg: []config.Group{
+				{Rules: []config.Rule{{Record: "foo", Expr: "sum(up)"}}},
+			},
+			qb: &fakeReplayQuerier{
+				registry: map[string]map[string]struct{}{
+					"sum(up)": {"12:00:00+12:02:00": {}},
+				},
+			},
+		},
+		{
+			name:  "one rule + multiple responses",
+			from:  "2021-01-01T12:00:00.000Z",
+			to:    "2021-01-01T12:02:30.000Z",
+			maxDP: 1,
+			cfg: []config.Group{
+				{Rules: []config.Rule{{Record: "foo", Expr: "sum(up)"}}},
+			},
+			qb: &fakeReplayQuerier{
+				registry: map[string]map[string]struct{}{
+					"sum(up)": {
+						"12:00:00+12:01:00": {},
+						"12:01:00+12:02:00": {},
+						"12:02:00+12:02:30": {},
+					},
+				},
+			},
+		},
+		{
+			name:  "datapoints per step",
+			from:  "2021-01-01T12:00:00.000Z",
+			to:    "2021-01-01T15:02:30.000Z",
+			maxDP: 60,
+			cfg: []config.Group{
+				{Interval: utils.NewPromDuration(time.Minute), Rules: []config.Rule{{Record: "foo", Expr: "sum(up)"}}},
+			},
+			qb: &fakeReplayQuerier{
+				registry: map[string]map[string]struct{}{
+					"sum(up)": {
+						"12:00:00+13:00:00": {},
+						"13:00:00+14:00:00": {},
+						"14:00:00+15:00:00": {},
+						"15:00:00+15:02:30": {},
+					},
+				},
+			},
+		},
+		{
+			name:  "multiple recording rules + multiple responses",
+			from:  "2021-01-01T12:00:00.000Z",
+			to:    "2021-01-01T12:02:30.000Z",
+			maxDP: 1,
+			cfg: []config.Group{
+				{Rules: []config.Rule{{Record: "foo", Expr: "sum(up)"}}},
+				{Rules: []config.Rule{{Record: "bar", Expr: "max(up)"}}},
+			},
+			qb: &fakeReplayQuerier{
+				registry: map[string]map[string]struct{}{
+					"sum(up)": {
+						"12:00:00+12:01:00": {},
+						"12:01:00+12:02:00": {},
+						"12:02:00+12:02:30": {},
+					},
+					"max(up)": {
+						"12:00:00+12:01:00": {},
+						"12:01:00+12:02:00": {},
+						"12:02:00+12:02:30": {},
+					},
+				},
+			},
+		},
+		{
+			name:  "multiple alerting rules + multiple responses",
+			from:  "2021-01-01T12:00:00.000Z",
+			to:    "2021-01-01T12:02:30.000Z",
+			maxDP: 1,
+			cfg: []config.Group{
+				{Rules: []config.Rule{{Alert: "foo", Expr: "sum(up) > 1"}}},
+				{Rules: []config.Rule{{Alert: "bar", Expr: "max(up) < 1"}}},
+			},
+			qb: &fakeReplayQuerier{
+				registry: map[string]map[string]struct{}{
+					"sum(up) > 1": {
+						"12:00:00+12:01:00": {},
+						"12:01:00+12:02:00": {},
+						"12:02:00+12:02:30": {},
+					},
+					"max(up) < 1": {
+						"12:00:00+12:01:00": {},
+						"12:01:00+12:02:00": {},
+						"12:02:00+12:02:30": {},
+					},
+				},
+			},
+		},
+	}
+
+	from, to, maxDP := *replayFrom, *replayTo, *replayMaxDatapoints
+	retries, delay := *replayRuleRetryAttempts, *replayRulesDelay
+	defer func() {
+		*replayFrom, *replayTo = from, to
+		*replayMaxDatapoints, *replayRuleRetryAttempts = maxDP, retries
+		*replayRulesDelay = delay
+	}()
+
+	*replayRuleRetryAttempts = 1
+	*replayRulesDelay = time.Millisecond
+	for _, tc := range testCases {
+		t.Run(tc.name, func(t *testing.T) {
+			*replayFrom = tc.from
+			*replayTo = tc.to
+			*replayMaxDatapoints = tc.maxDP
+			if err := replay(tc.cfg, tc.qb, nil); err != nil {
+				t.Fatalf("replay failed: %s", err)
+			}
+			if len(tc.qb.registry) > 0 {
+				t.Fatalf("not all requests were sent: %#v", tc.qb.registry)
+			}
+		})
+	}
+}
+
+func TestRangeIterator(t *testing.T) {
+	testCases := []struct {
+		ri     rangeIterator
+		result [][2]time.Time
+	}{
+		{
+			ri: rangeIterator{
+				start: parseTime(t, "2021-01-01T12:00:00.000Z"),
+				end:   parseTime(t, "2021-01-01T12:30:00.000Z"),
+				step:  5 * time.Minute,
+			},
+			result: [][2]time.Time{
+				{parseTime(t, "2021-01-01T12:00:00.000Z"), parseTime(t, "2021-01-01T12:05:00.000Z")},
+				{parseTime(t, "2021-01-01T12:05:00.000Z"), parseTime(t, "2021-01-01T12:10:00.000Z")},
+				{parseTime(t, "2021-01-01T12:10:00.000Z"), parseTime(t, "2021-01-01T12:15:00.000Z")},
+				{parseTime(t, "2021-01-01T12:15:00.000Z"), parseTime(t, "2021-01-01T12:20:00.000Z")},
+				{parseTime(t, "2021-01-01T12:20:00.000Z"), parseTime(t, "2021-01-01T12:25:00.000Z")},
+				{parseTime(t, "2021-01-01T12:25:00.000Z"), parseTime(t, "2021-01-01T12:30:00.000Z")},
+			},
+		},
+		{
+			ri: rangeIterator{
+				start: parseTime(t, "2021-01-01T12:00:00.000Z"),
+				end:   parseTime(t, "2021-01-01T12:30:00.000Z"),
+				step:  45 * time.Minute,
+			},
+			result: [][2]time.Time{
+				{parseTime(t, "2021-01-01T12:00:00.000Z"), parseTime(t, "2021-01-01T12:30:00.000Z")},
+				{parseTime(t, "2021-01-01T12:30:00.000Z"), parseTime(t, "2021-01-01T12:30:00.000Z")},
+			},
+		},
+		{
+			ri: rangeIterator{
+				start: parseTime(t, "2021-01-01T12:00:12.000Z"),
+				end:   parseTime(t, "2021-01-01T12:00:17.000Z"),
+				step:  time.Second,
+			},
+			result: [][2]time.Time{
+				{parseTime(t, "2021-01-01T12:00:12.000Z"), parseTime(t, "2021-01-01T12:00:13.000Z")},
+				{parseTime(t, "2021-01-01T12:00:13.000Z"), parseTime(t, "2021-01-01T12:00:14.000Z")},
+				{parseTime(t, "2021-01-01T12:00:14.000Z"), parseTime(t, "2021-01-01T12:00:15.000Z")},
+				{parseTime(t, "2021-01-01T12:00:15.000Z"), parseTime(t, "2021-01-01T12:00:16.000Z")},
+				{parseTime(t, "2021-01-01T12:00:16.000Z"), parseTime(t, "2021-01-01T12:00:17.000Z")},
+			},
+		},
+	}
+
+	for i, tc := range testCases {
+		t.Run(fmt.Sprintf("case %d", i), func(t *testing.T) {
+			var j int
+			for tc.ri.next() {
+				if len(tc.result) < j+1 {
+					t.Fatalf("unexpected result for iterator on step %d: %v - %v",
+						j, tc.ri.s, tc.ri.e)
+				}
+				s, e := tc.ri.s, tc.ri.e
+				expS, expE := tc.result[j][0], tc.result[j][1]
+				if s != expS {
+					t.Fatalf("expected to get start=%v; got %v", expS, s)
+				}
+				if e != expE {
+					t.Fatalf("expected to get end=%v; got %v", expE, e)
+				}
+				j++
+			}
+		})
+	}
+}
+
+func parseTime(t *testing.T, s string) time.Time {
+	t.Helper()
+	tt, err := time.Parse("2006-01-02T15:04:05.000Z", s)
+	if err != nil {
+		t.Fatal(err)
+	}
+	return tt
+}

app/vmalert/rule.go

@@ -3,22 +3,21 @@ package main
 import (
 	"context"
 	"errors"
-
-	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
+	"time"
 )
 
 // Rule represents alerting or recording rule
 // that has unique ID, can be Executed and
 // updated with other Rule.
 type Rule interface {
-	// Returns unique ID that may be used for
+	// ID returns unique ID that may be used for
 	// identifying this Rule among others.
 	ID() uint64
 	// Exec executes the rule with given context
-	// and Querier. If returnSeries is true, Exec
-	// may return TimeSeries as result of execution
-	Exec(ctx context.Context, q datasource.Querier, returnSeries bool) ([]prompbmarshal.TimeSeries, error)
+	Exec(ctx context.Context) ([]prompbmarshal.TimeSeries, error)
+	// ExecRange executes the rule on the given time range
+	ExecRange(ctx context.Context, start, end time.Time) ([]prompbmarshal.TimeSeries, error)
 	// UpdateWith performs modification of current Rule
 	// with fields of the given Rule.
 	UpdateWith(Rule) error

app/vmalert/utils.go

@@ -7,17 +7,21 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
 )
 
-func newTimeSeries(value float64, labels map[string]string, timestamp time.Time) prompbmarshal.TimeSeries {
-	ts := prompbmarshal.TimeSeries{}
-	ts.Samples = append(ts.Samples, prompbmarshal.Sample{
-		Value:     value,
-		Timestamp: timestamp.UnixNano() / 1e6,
-	})
+func newTimeSeries(values []float64, timestamps []int64, labels map[string]string) prompbmarshal.TimeSeries {
+	ts := prompbmarshal.TimeSeries{
+		Samples: make([]prompbmarshal.Sample, len(values)),
+	}
+	for i := range values {
+		ts.Samples[i] = prompbmarshal.Sample{
+			Value:     values[i],
+			Timestamp: time.Unix(timestamps[i], 0).UnixNano() / 1e6,
+		}
+	}
 	keys := make([]string, 0, len(labels))
 	for k := range labels {
 		keys = append(keys, k)
 	}
-	sort.Strings(keys)
+	sort.Strings(keys) // make order deterministic
 	for _, key := range keys {
 		ts.Labels = append(ts.Labels, prompbmarshal.Label{
 			Name:  key,

app/vmalert/utils/prom_duration.go

@@ -0,0 +1,43 @@
+package utils
+
+import (
+	"time"
+
+	"github.com/VictoriaMetrics/metricsql"
+)
+
+// PromDuration is Prometheus duration.
+type PromDuration struct {
+	milliseconds int64
+}
+
+// NewPromDuration returns PromDuration for given d.
+func NewPromDuration(d time.Duration) PromDuration {
+	return PromDuration{
+		milliseconds: d.Milliseconds(),
+	}
+}
+
+// MarshalYAML implements yaml.Marshaler interface.
+func (pd PromDuration) MarshalYAML() (interface{}, error) {
+	return pd.Duration().String(), nil
+}
+
+// UnmarshalYAML implements yaml.Unmarshaler interface.
+func (pd *PromDuration) UnmarshalYAML(unmarshal func(interface{}) error) error {
+	var s string
+	if err := unmarshal(&s); err != nil {
+		return err
+	}
+	ms, err := metricsql.DurationValue(s, 0)
+	if err != nil {
+		return err
+	}
+	pd.milliseconds = ms
+	return nil
+}
+
+// Duration returns duration for pd.
+func (pd *PromDuration) Duration() time.Duration {
+	return time.Duration(pd.milliseconds) * time.Millisecond
+}

app/vmalert/utils/tls_test.go

@@ -13,6 +13,7 @@ func TestTLSConfig(t *testing.T) {
 	}
 	if tlsCfg == nil {
 		t.Errorf("expected tlsConfig to be set, got nil")
+		return
 	}
 	if tlsCfg.ServerName != serverName {
 		t.Errorf("unexpected ServerName, want %s, got %s", serverName, tlsCfg.ServerName)

app/vmalert/web.go

@@ -17,27 +17,24 @@ type requestHandler struct {
 	m *manager
 }
 
-var pathList = [][]string{
-	{"/api/v1/groups", "list all loaded groups and rules"},
-	{"/api/v1/alerts", "list all active alerts"},
-	{"/api/v1/groupID/alertID/status", "get alert status by ID"},
-	// /metrics is served by httpserver by default
-	{"/metrics", "list of application metrics"},
-	{"/-/reload", "reload configuration"},
-}
-
 func (rh *requestHandler) handler(w http.ResponseWriter, r *http.Request) bool {
 	switch r.URL.Path {
 	case "/":
-		for _, path := range pathList {
-			p, doc := path[0], path[1]
-			fmt.Fprintf(w, "<a href='%s'>%q</a> - %s<br/>", p, p, doc)
+		if r.Method != "GET" {
+			return false
 		}
+		httpserver.WriteAPIHelp(w, [][2]string{
+			{"/api/v1/groups", "list all loaded groups and rules"},
+			{"/api/v1/alerts", "list all active alerts"},
+			{"/api/v1/groupID/alertID/status", "get alert status by ID"},
+			{"/metrics", "list of application metrics"},
+			{"/-/reload", "reload configuration"},
+		})
 		return true
 	case "/api/v1/groups":
 		data, err := rh.listGroups()
 		if err != nil {
-			httpserver.Errorf(w, r, "error in %q: %s", r.URL.Path, err)
+			httpserver.Errorf(w, r, "%s", err)
 			return true
 		}
 		w.Header().Set("Content-Type", "application/json; charset=utf-8")
@@ -46,7 +43,7 @@ func (rh *requestHandler) handler(w http.ResponseWriter, r *http.Request) bool {
 	case "/api/v1/alerts":
 		data, err := rh.listAlerts()
 		if err != nil {
-			httpserver.Errorf(w, r, "error in %q: %s", r.URL.Path, err)
+			httpserver.Errorf(w, r, "%s", err)
 			return true
 		}
 		w.Header().Set("Content-Type", "application/json; charset=utf-8")
@@ -64,7 +61,7 @@ func (rh *requestHandler) handler(w http.ResponseWriter, r *http.Request) bool {
 		// /api/v1/<groupName>/<alertID>/status
 		data, err := rh.alert(r.URL.Path)
 		if err != nil {
-			httpserver.Errorf(w, r, "error in %q: %s", r.URL.Path, err)
+			httpserver.Errorf(w, r, "%s", err)
 			return true
 		}
 		w.Header().Set("Content-Type", "application/json; charset=utf-8")

app/vmalert/web_types.go

@@ -20,19 +20,22 @@ type APIAlert struct {
 
 // APIGroup represents Group for WEB view
 type APIGroup struct {
-	Name           string             `json:"name"`
-	ID             string             `json:"id"`
-	File           string             `json:"file"`
-	Interval       string             `json:"interval"`
-	Concurrency    int                `json:"concurrency"`
-	AlertingRules  []APIAlertingRule  `json:"alerting_rules"`
-	RecordingRules []APIRecordingRule `json:"recording_rules"`
+	Name              string             `json:"name"`
+	Type              string             `json:"type"`
+	ID                string             `json:"id"`
+	File              string             `json:"file"`
+	Interval          string             `json:"interval"`
+	Concurrency       int                `json:"concurrency"`
+	ExtraFilterLabels map[string]string  `json:"extra_filter_labels"`
+	AlertingRules     []APIAlertingRule  `json:"alerting_rules"`
+	RecordingRules    []APIRecordingRule `json:"recording_rules"`
 }
 
 // APIAlertingRule represents AlertingRule for WEB view
 type APIAlertingRule struct {
 	ID          string            `json:"id"`
 	Name        string            `json:"name"`
+	Type        string            `json:"type"`
 	GroupID     string            `json:"group_id"`
 	Expression  string            `json:"expression"`
 	For         string            `json:"for"`
@@ -46,6 +49,7 @@ type APIAlertingRule struct {
 type APIRecordingRule struct {
 	ID         string            `json:"id"`
 	Name       string            `json:"name"`
+	Type       string            `json:"type"`
 	GroupID    string            `json:"group_id"`
 	Expression string            `json:"expression"`
 	LastError  string            `json:"last_error"`

app/vmauth/Makefile

@@ -77,3 +77,9 @@ vmauth-local-with-goarch:
 
 vmauth-pure:
 	APP_NAME=vmauth $(MAKE) app-local-pure
+
+vmauth-windows-amd64:
+	GOARCH=amd64 APP_NAME=vmauth $(MAKE) app-local-windows-with-goarch
+
+vmauth-windows-amd64-prod:
+	APP_NAME=vmauth $(MAKE) app-via-docker-windows-amd64

app/vmauth/README.md

@@ -1,11 +1,11 @@
-## vmauth
+# vmauth
 
-`vmauth` is a simple auth proxy and router for [VictoriaMetrics](https://github.com/VictoriaMetrics/VictoriaMetrics).
-It reads username and password from [Basic Auth headers](https://en.wikipedia.org/wiki/Basic_access_authentication),
-matches them against configs pointed by `-auth.config` command-line flag and proxies incoming HTTP requests to the configured per-user `url_prefix` on successful match.
+`vmauth` is a simple auth proxy, router and [load balancer](#load-balancing) for [VictoriaMetrics](https://github.com/VictoriaMetrics/VictoriaMetrics).
+It reads auth credentials from `Authorization` http header ([Basic Auth](https://en.wikipedia.org/wiki/Basic_access_authentication) and `Bearer token` is supported),
+matches them against configs pointed by [-auth.config](#auth-config) command-line flag and proxies incoming HTTP requests to the configured per-user `url_prefix` on successful match.
 
 
-### Quick start
+## Quick start
 
 Just download `vmutils-*` archive from [releases page](https://github.com/VictoriaMetrics/VictoriaMetrics/releases), unpack it
 and pass the following flag to `vmauth` binary in order to start authorizing and routing requests:
@@ -17,18 +17,24 @@ and pass the following flag to `vmauth` binary in order to start authorizing and
 After that `vmauth` starts accepting HTTP requests on port `8427` and routing them according to the provided [-auth.config](#auth-config).
 The port can be modified via `-httpListenAddr` command-line flag.
 
-The auth config can be reloaded by passing `SIGHUP` signal to `vmauth`.
+The auth config can be reloaded either by passing `SIGHUP` signal to `vmauth` or by querying `/-/reload` http endpoint.
 
 Docker images for `vmauth` are available [here](https://hub.docker.com/r/victoriametrics/vmauth/tags).
 
 Pass `-help` to `vmauth` in order to see all the supported command-line flags with their descriptions.
 
-Feel free [contacting us](mailto:info@victoriametrics.com) if you need customized auth proxy for VictoriaMetrics with the support of LDAP, SSO, RBAC, SAML, accounting, limits, etc.
+Feel free [contacting us](mailto:info@victoriametrics.com) if you need customized auth proxy for VictoriaMetrics with the support of LDAP, SSO, RBAC, SAML,
+accounting and rate limiting such as [vmgateway](https://docs.victoriametrics.com/vmgateway.html).
 
 
-### Auth config
+## Load balancing
 
-Auth config is represented in the following simple `yml` format:
+Each `url_prefix` in the [-auth.config](#auth-config) may contain either a single url or a list of urls. In the latter case `vmauth` balances load among the configured urls in a round-robin manner. This feature is useful for balancing the load among multiple `vmselect` and/or `vminsert` nodes in [VictoriaMetrics cluster](https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html).
+
+
+## Auth config
+
+`-auth.config` is represented in the following simple `yml` format:
 
 ```yml
 
@@ -36,39 +42,80 @@ Auth config is represented in the following simple `yml` format:
 # Usernames must be unique.
 
 users:
+  # Requests with the 'Authorization: Bearer XXXX' header are proxied to http://localhost:8428 .
+  # For example, http://vmauth:8427/api/v1/query is proxied to http://localhost:8428/api/v1/query
+- bearer_token: "XXXX"
+  url_prefix: "http://localhost:8428"
 
   # The user for querying local single-node VictoriaMetrics.
   # All the requests to http://vmauth:8427 with the given Basic Auth (username:password)
-  # will be routed to http://localhost:8428 .
-  # For example, http://vmauth:8427/api/v1/query is routed to http://localhost:8428/api/v1/query
+  # will be proxied to http://localhost:8428 .
+  # For example, http://vmauth:8427/api/v1/query is proxied to http://localhost:8428/api/v1/query
 - username: "local-single-node"
   password: "***"
   url_prefix: "http://localhost:8428"
 
-  # The user for querying account 123 in VictoriaMetrics cluster
-  # See https://github.com/VictoriaMetrics/VictoriaMetrics/blob/cluster/README.md#url-format
+  # The user for querying local single-node VictoriaMetrics with extra_label team=dev.
   # All the requests to http://vmauth:8427 with the given Basic Auth (username:password)
-  # will be routed to http://vmselect:8481/select/123/prometheus .
-  # For example, http://vmauth:8427/api/v1/query is routed to http://vmselect:8481/select/123/prometheus/api/v1/select
+  # will be routed to http://localhost:8428 with extra_label=team=dev query arg.
+  # For example, http://vmauth:8427/api/v1/query is routed to http://localhost:8428/api/v1/query?extra_label=team=dev
+- username: "local-single-node"
+  password: "***"
+  url_prefix: "http://localhost:8428?extra_label=team=dev"
+
+  # The user for querying account 123 in VictoriaMetrics cluster
+  # See https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html#url-format
+  # All the requests to http://vmauth:8427 with the given Basic Auth (username:password)
+  # will be load-balanced among http://vmselect1:8481/select/123/prometheus and http://vmselect2:8481/select/123/prometheus
+  # For example, http://vmauth:8427/api/v1/query is proxied to the following urls in a round-robin manner:
+  #   - http://vmselect1:8481/select/123/prometheus/api/v1/select
+  #   - http://vmselect2:8481/select/123/prometheus/api/v1/select
 - username: "cluster-select-account-123"
   password: "***"
-  url_prefix: "http://vmselect:8481/select/123/prometheus"
+  url_prefix:
+  - "http://vmselect1:8481/select/123/prometheus"
+  - "http://vmselect2:8481/select/123/prometheus"
 
   # The user for inserting Prometheus data into VictoriaMetrics cluster under account 42
-  # See https://github.com/VictoriaMetrics/VictoriaMetrics/blob/cluster/README.md#url-format
-  # All the reuqests to http://vmauth:8427 with the given Basic Auth (username:password)
-  # will be routed to http://vminsert:8480/insert/42/prometheus .
-  # For example, http://vmauth:8427/api/v1/write is routed to http://vminsert:8480/insert/42/prometheus/api/v1/write
+  # See https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html#url-format
+  # All the requests to http://vmauth:8427 with the given Basic Auth (username:password)
+  # will be load-balanced between http://vminsert1:8480/insert/42/prometheus and http://vminsert2:8480/insert/42/prometheus
+  # For example, http://vmauth:8427/api/v1/write is proxied to the following urls in a round-robin manner:
+  #   - http://vminsert1:8480/insert/42/prometheus/api/v1/write
+  #   - http://vminsert2:8480/insert/42/prometheus/api/v1/write
 - username: "cluster-insert-account-42"
   password: "***"
-  url_prefix: "http://vminsert:8480/insert/42/prometheus"
+  url_prefix:
+  - "http://vminsert1:8480/insert/42/prometheus"
+  - "http://vminsert2:8480/insert/42/prometheus"
+
+
+  # A single user for querying and inserting data:
+  # - Requests to http://vmauth:8427/api/v1/query, http://vmauth:8427/api/v1/query_range
+  #   and http://vmauth:8427/api/v1/label/<label_name>/values are proxied to the following urls in a round-robin manner:
+  #     - http://vmselect1:8481/select/42/prometheus
+  #     - http://vmselect2:8481/select/42/prometheus
+  #   For example, http://vmauth:8427/api/v1/query is proxied to http://vmselect1:8480/select/42/prometheus/api/v1/query
+  #   or to http://vmselect2:8480/select/42/prometheus/api/v1/query .
+  # - Requests to http://vmauth:8427/api/v1/write are proxied to http://vminsert:8480/insert/42/prometheus/api/v1/write
+- username: "foobar"
+  url_map:
+  - src_paths:
+    - "/api/v1/query"
+    - "/api/v1/query_range"
+    - "/api/v1/label/[^/]+/values"
+    url_prefix:
+    - "http://vmselect1:8481/select/42/prometheus"
+    - "http://vmselect2:8481/select/42/prometheus"
+  - src_paths: ["/api/v1/write"]
+    url_prefix: "http://vminsert:8480/insert/42/prometheus"
 ```
 
 The config may contain `%{ENV_VAR}` placeholders, which are substituted by the corresponding `ENV_VAR` environment variable values.
 This may be useful for passing secrets to the config.
 
 
-### Security
+## Security
 
 Do not transfer Basic Auth headers in plaintext over untrusted networks. Enable https. This can be done by passing the following `-tls*` command-line flags to `vmauth`:
 
@@ -83,31 +130,33 @@ Do not transfer Basic Auth headers in plaintext over untrusted networks. Enable
 
 Alternatively, [https termination proxy](https://en.wikipedia.org/wiki/TLS_termination_proxy) may be put in front of `vmauth`.
 
+It is recommended protecting `/-/reload` endpoint with `-reloadAuthKey` command-line flag, so external users couldn't trigger config reload.
 
-### Monitoring
+
+## Monitoring
 
 `vmauth` exports various metrics in Prometheus exposition format at `http://vmauth-host:8427/metrics` page. It is recommended setting up regular scraping of this page
-either via [vmagent](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/app/vmagent/README.md) or via Prometheus, so the exported metrics could be analyzed later.
+either via [vmagent](https://docs.victoriametrics.com/vmagent.html) or via Prometheus, so the exported metrics could be analyzed later.
 
 
-### How to build from sources
+## How to build from sources
 
 It is recommended using [binary releases](https://github.com/VictoriaMetrics/VictoriaMetrics/releases) - `vmauth` is located in `vmutils-*` archives there.
 
 
-#### Development build
+### Development build
 
-1. [Install Go](https://golang.org/doc/install). The minimum supported version is Go 1.13.
-2. Run `make vmauth` from the root folder of the repository.
+1. [Install Go](https://golang.org/doc/install). The minimum supported version is Go 1.16.
+2. Run `make vmauth` from the root folder of [the repository](https://github.com/VictoriaMetrics/VictoriaMetrics).
    It builds `vmauth` binary and puts it into the `bin` folder.
 
-#### Production build
+### Production build
 
 1. [Install docker](https://docs.docker.com/install/).
-2. Run `make vmauth-prod` from the root folder of the repository.
+2. Run `make vmauth-prod` from the root folder of [the repository](https://github.com/VictoriaMetrics/VictoriaMetrics).
    It builds `vmauth-prod` binary and puts it into the `bin` folder.
 
-#### Building docker images
+### Building docker images
 
 Run `make package-vmauth`. It builds `victoriametrics/vmauth:<PKG_TAG>` docker image locally.
 `<PKG_TAG>` is auto-generated image tag, which depends on source code in the repository.
@@ -121,7 +170,7 @@ ROOT_IMAGE=scratch make package-vmauth
 ```
 
 
-### Profiling
+## Profiling
 
 `vmauth` provides handlers for collecting the following [Go profiles](https://blog.golang.org/profiling-go-programs):
 
@@ -142,7 +191,7 @@ The command for collecting CPU profile waits for 30 seconds before returning.
 The collected profiles may be analyzed with [go tool pprof](https://github.com/google/pprof).
 
 
-### Advanced usage
+## Advanced usage
 
 Pass `-help` command-line arg to `vmauth` in order to see all the configuration options:
 
@@ -151,55 +200,67 @@ Pass `-help` command-line arg to `vmauth` in order to see all the configuration
 
 vmauth authenticates and authorizes incoming requests and proxies them to VictoriaMetrics.
 
-See the docs at https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/app/vmauth/README.md .
+See the docs at https://docs.victoriametrics.com/vmauth.html .
 
   -auth.config string
-    	Path to auth config. See https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/app/vmauth/README.md for details on the format of this auth config
+    	Path to auth config. See https://docs.victoriametrics.com/vmauth.html for details on the format of this auth config
   -enableTCP6
-    	Whether to enable IPv6 for listening and dialing. By default only IPv4 TCP is used
+    	Whether to enable IPv6 for listening and dialing. By default only IPv4 TCP and UDP is used
   -envflag.enable
     	Whether to enable reading flags from environment variables additionally to command line. Command line flag values have priority over values from environment vars. Flags are read only from command line if this flag isn't set
   -envflag.prefix string
     	Prefix for environment variables if -envflag.enable is set
+  -fs.disableMmap
+    	Whether to use pread() instead of mmap() for reading data files. By default mmap() is used for 64-bit arches and pread() is used for 32-bit arches, since they cannot read data files bigger than 2^32 bytes in memory. mmap() is usually faster for reading small data chunks than pread()
   -http.connTimeout duration
-    	Incoming http connections are closed after the configured timeout. This may help spreading incoming load among a cluster of services behind load balancer. Note that the real timeout may be bigger by up to 10% as a protection from Thundering herd problem (default 2m0s)
+    	Incoming http connections are closed after the configured timeout. This may help to spread the incoming load among a cluster of services behind a load balancer. Please note that the real timeout may be bigger by up to 10% as a protection against the thundering herd problem (default 2m0s)
   -http.disableResponseCompression
-    	Disable compression of HTTP responses for saving CPU resources. By default compression is enabled to save network bandwidth
+    	Disable compression of HTTP responses to save CPU resources. By default compression is enabled to save network bandwidth
   -http.idleConnTimeout duration
     	Timeout for incoming idle http connections (default 1m0s)
   -http.maxGracefulShutdownDuration duration
-    	The maximum duration for graceful shutdown of HTTP server. Highly loaded server may require increased value for graceful shutdown (default 7s)
+    	The maximum duration for a graceful shutdown of the HTTP server. A highly loaded server may require increased value for a graceful shutdown (default 7s)
   -http.pathPrefix string
     	An optional prefix to add to all the paths handled by http server. For example, if '-http.pathPrefix=/foo/bar' is set, then all the http requests will be handled on '/foo/bar/*' paths. This may be useful for proxied requests. See https://www.robustperception.io/using-external-urls-and-proxies-with-prometheus
   -http.shutdownDelay duration
-    	Optional delay before http server shutdown. During this dealy the servier returns non-OK responses from /health page, so load balancers can route new requests to other servers
+    	Optional delay before http server shutdown. During this delay, the server returns non-OK responses from /health page, so load balancers can route new requests to other servers
   -httpAuth.password string
     	Password for HTTP Basic Auth. The authentication is disabled if -httpAuth.username is empty
   -httpAuth.username string
     	Username for HTTP Basic Auth. The authentication is disabled if empty. See also -httpAuth.password
   -httpListenAddr string
     	TCP address to listen for http connections (default ":8427")
+  -loggerDisableTimestamps
+    	Whether to disable writing timestamps in logs
   -loggerErrorsPerSecondLimit int
-    	Per-second limit on the number of ERROR messages. If more than the given number of errors are emitted per second, then the remaining errors are suppressed. Zero value disables the rate limit (default 10)
+    	Per-second limit on the number of ERROR messages. If more than the given number of errors are emitted per second, the remaining errors are suppressed. Zero values disable the rate limit
   -loggerFormat string
     	Format for logs. Possible values: default, json (default "default")
   -loggerLevel string
     	Minimum level of errors to log. Possible values: INFO, WARN, ERROR, FATAL, PANIC (default "INFO")
   -loggerOutput string
     	Output for the logs. Supported values: stderr, stdout (default "stderr")
-  -memory.allowedBytes value
-    	Allowed size of system memory VictoriaMetrics caches may occupy. This option overrides -memory.allowedPercent if set to non-zero value. Too low value may increase cache miss rate, which usually results in higher CPU and disk IO usage. Too high value may evict too much data from OS page cache, which will result in higher disk IO usage
-    	Supports the following optional suffixes for values: KB, MB, GB, KiB, MiB, GiB (default 0)
+  -loggerTimezone string
+    	Timezone to use for timestamps in logs. Timezone must be a valid IANA Time Zone. For example: America/New_York, Europe/Berlin, Etc/GMT+3 or Local (default "UTC")
+  -loggerWarnsPerSecondLimit int
+    	Per-second limit on the number of WARN messages. If more than the given number of warns are emitted per second, then the remaining warns are suppressed. Zero values disable the rate limit
+  -maxIdleConnsPerBackend int
+    	The maximum number of idle connections vmauth can open per each backend host (default 100)
+  -memory.allowedBytes size
+    	Allowed size of system memory VictoriaMetrics caches may occupy. This option overrides -memory.allowedPercent if set to a non-zero value. Too low a value may increase the cache miss rate usually resulting in higher CPU and disk IO usage. Too high a value may evict too much data from OS page cache resulting in higher disk IO usage
+    	Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 0)
   -memory.allowedPercent float
-    	Allowed percent of system memory VictoriaMetrics caches may occupy. See also -memory.allowedBytes. Too low value may increase cache miss rate, which usually results in higher CPU and disk IO usage. Too high value may evict too much data from OS page cache, which will result in higher disk IO usage (default 60)
+    	Allowed percent of system memory VictoriaMetrics caches may occupy. See also -memory.allowedBytes. Too low a value may increase cache miss rate usually resulting in higher CPU and disk IO usage. Too high a value may evict too much data from OS page cache which will result in higher disk IO usage (default 60)
   -metricsAuthKey string
     	Auth key for /metrics. It overrides httpAuth settings
   -pprofAuthKey string
     	Auth key for /debug/pprof. It overrides httpAuth settings
+  -reloadAuthKey string
+    	Auth key for /-/reload http endpoint. It must be passed as authKey=...
   -tls
     	Whether to enable TLS (aka HTTPS) for incoming requests. -tlsCertFile and -tlsKeyFile must be set if -tls is set
   -tlsCertFile string
-    	Path to file with TLS certificate. Used only if -tls is set. Prefer ECDSA certs instead of RSA certs, since RSA certs are slow
+    	Path to file with TLS certificate. Used only if -tls is set. Prefer ECDSA certs instead of RSA certs as RSA certs are slower
   -tlsKeyFile string
     	Path to file with TLS key. Used only if -tls is set
   -version

app/vmauth/auth_config.go

@@ -1,10 +1,14 @@
 package main
 
 import (
+	"encoding/base64"
 	"flag"
 	"fmt"
 	"io/ioutil"
 	"net/url"
+	"os"
+	"regexp"
+	"strconv"
 	"strings"
 	"sync"
 	"sync/atomic"
@@ -17,7 +21,7 @@ import (
 )
 
 var (
-	authConfigPath = flag.String("auth.config", "", "Path to auth config. See https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/app/vmauth/README.md "+
+	authConfigPath = flag.String("auth.config", "", "Path to auth config. See https://docs.victoriametrics.com/vmauth.html "+
 		"for details on the format of this auth config")
 )
 
@@ -28,17 +32,140 @@ type AuthConfig struct {
 
 // UserInfo is user information read from authConfigPath
 type UserInfo struct {
-	Username  string `yaml:"username"`
-	Password  string `yaml:"password"`
-	URLPrefix string `yaml:"url_prefix"`
+	BearerToken string     `yaml:"bearer_token"`
+	Username    string     `yaml:"username"`
+	Password    string     `yaml:"password"`
+	URLPrefix   *URLPrefix `yaml:"url_prefix"`
+	URLMap      []URLMap   `yaml:"url_map"`
 
 	requests *metrics.Counter
 }
 
+// URLMap is a mapping from source paths to target urls.
+type URLMap struct {
+	SrcPaths  []*SrcPath `yaml:"src_paths"`
+	URLPrefix *URLPrefix `yaml:"url_prefix"`
+}
+
+// SrcPath represents an src path
+type SrcPath struct {
+	sOriginal string
+	re        *regexp.Regexp
+}
+
+// URLPrefix represents pased `url_prefix`
+type URLPrefix struct {
+	n    uint32
+	urls []*url.URL
+}
+
+func (up *URLPrefix) getNextURL() *url.URL {
+	n := atomic.AddUint32(&up.n, 1)
+	idx := n % uint32(len(up.urls))
+	return up.urls[idx]
+}
+
+// UnmarshalYAML unmarshals up from yaml.
+func (up *URLPrefix) UnmarshalYAML(f func(interface{}) error) error {
+	var v interface{}
+	if err := f(&v); err != nil {
+		return err
+	}
+	var urls []string
+	switch x := v.(type) {
+	case string:
+		urls = []string{x}
+	case []interface{}:
+		if len(x) == 0 {
+			return fmt.Errorf("`url_prefix` must contain at least a single url")
+		}
+		us := make([]string, len(x))
+		for i, xx := range x {
+			s, ok := xx.(string)
+			if !ok {
+				return fmt.Errorf("`url_prefix` must contain array of strings; got %T", xx)
+			}
+			us[i] = s
+		}
+		urls = us
+	default:
+		return fmt.Errorf("unexpected type for `url_prefix`: %T; want string or []string", v)
+	}
+	pus := make([]*url.URL, len(urls))
+	for i, u := range urls {
+		pu, err := url.Parse(u)
+		if err != nil {
+			return fmt.Errorf("cannot unmarshal %q into url: %w", u, err)
+		}
+		pus[i] = pu
+	}
+	up.urls = pus
+	return nil
+}
+
+// MarshalYAML marshals up to yaml.
+func (up *URLPrefix) MarshalYAML() (interface{}, error) {
+	var b []byte
+	if len(up.urls) == 1 {
+		u := up.urls[0].String()
+		b = strconv.AppendQuote(b, u)
+		return string(b), nil
+	}
+	b = append(b, '[')
+	for i, pu := range up.urls {
+		u := pu.String()
+		b = strconv.AppendQuote(b, u)
+		if i+1 < len(up.urls) {
+			b = append(b, ',')
+		}
+	}
+	b = append(b, ']')
+	return string(b), nil
+}
+
+func (sp *SrcPath) match(s string) bool {
+	prefix, ok := sp.re.LiteralPrefix()
+	if ok {
+		// Fast path - literal match
+		return s == prefix
+	}
+	if !strings.HasPrefix(s, prefix) {
+		return false
+	}
+	return sp.re.MatchString(s)
+}
+
+// UnmarshalYAML implements yaml.Unmarshaler
+func (sp *SrcPath) UnmarshalYAML(f func(interface{}) error) error {
+	var s string
+	if err := f(&s); err != nil {
+		return err
+	}
+	sAnchored := "^(?:" + s + ")$"
+	re, err := regexp.Compile(sAnchored)
+	if err != nil {
+		return fmt.Errorf("cannot build regexp from %q: %w", s, err)
+	}
+	sp.sOriginal = s
+	sp.re = re
+	return nil
+}
+
+// MarshalYAML implements yaml.Marshaler.
+func (sp *SrcPath) MarshalYAML() (interface{}, error) {
+	return sp.sOriginal, nil
+}
+
 func initAuthConfig() {
 	if len(*authConfigPath) == 0 {
 		logger.Fatalf("missing required `-auth.config` command-line flag")
 	}
+
+	// Register SIGHUP handler for config re-read just before readAuthConfig call.
+	// This guarantees that the config will be re-read if the signal arrives during readAuthConfig call.
+	// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1240
+	sighupCh := procutil.NewSighupChan()
+
 	m, err := readAuthConfig(*authConfigPath)
 	if err != nil {
 		logger.Fatalf("cannot load auth config from `-auth.config=%s`: %s", *authConfigPath, err)
@@ -48,7 +175,7 @@ func initAuthConfig() {
 	authConfigWG.Add(1)
 	go func() {
 		defer authConfigWG.Done()
-		authConfigReloader()
+		authConfigReloader(sighupCh)
 	}()
 }
 
@@ -57,8 +184,7 @@ func stopAuthConfig() {
 	authConfigWG.Wait()
 }
 
-func authConfigReloader() {
-	sighupCh := procutil.NewSighupChan()
+func authConfigReloader(sighupCh <-chan os.Signal) {
 	for {
 		select {
 		case <-stopCh:
@@ -103,29 +229,93 @@ func parseAuthConfig(data []byte) (map[string]*UserInfo, error) {
 	if len(uis) == 0 {
 		return nil, fmt.Errorf("`users` section cannot be empty in AuthConfig")
 	}
-	m := make(map[string]*UserInfo, len(uis))
+	byAuthToken := make(map[string]*UserInfo, len(uis))
+	byUsername := make(map[string]bool, len(uis))
+	byBearerToken := make(map[string]bool, len(uis))
 	for i := range uis {
 		ui := &uis[i]
-		if m[ui.Username] != nil {
+		if ui.BearerToken == "" && ui.Username == "" {
+			return nil, fmt.Errorf("either bearer_token or username must be set")
+		}
+		if ui.BearerToken != "" && ui.Username != "" {
+			return nil, fmt.Errorf("bearer_token=%q and username=%q cannot be set simultaneously", ui.BearerToken, ui.Username)
+		}
+		if byBearerToken[ui.BearerToken] {
+			return nil, fmt.Errorf("duplicate bearer_token found; bearer_token: %q", ui.BearerToken)
+		}
+		if byUsername[ui.Username] {
 			return nil, fmt.Errorf("duplicate username found; username: %q", ui.Username)
 		}
-		urlPrefix := ui.URLPrefix
-		// Remove trailing '/' from urlPrefix
-		for strings.HasSuffix(urlPrefix, "/") {
-			urlPrefix = urlPrefix[:len(urlPrefix)-1]
+		authToken := getAuthToken(ui.BearerToken, ui.Username, ui.Password)
+		if byAuthToken[authToken] != nil {
+			return nil, fmt.Errorf("duplicate auth token found for bearer_token=%q, username=%q: %q", authToken, ui.BearerToken, ui.Username)
 		}
-		// Validate urlPrefix
-		target, err := url.Parse(urlPrefix)
-		if err != nil {
-			return nil, fmt.Errorf("invalid `url_prefix: %q`: %w", urlPrefix, err)
+		if ui.URLPrefix != nil {
+			if err := ui.URLPrefix.sanitize(); err != nil {
+				return nil, err
+			}
 		}
-		if target.Scheme != "http" && target.Scheme != "https" {
-			return nil, fmt.Errorf("unsupported scheme for `url_prefix: %q`: %q; must be `http` or `https`", urlPrefix, target.Scheme)
+		for _, e := range ui.URLMap {
+			if len(e.SrcPaths) == 0 {
+				return nil, fmt.Errorf("missing `src_paths` in `url_map`")
+			}
+			if e.URLPrefix == nil {
+				return nil, fmt.Errorf("missing `url_prefix` in `url_map`")
+			}
+			if err := e.URLPrefix.sanitize(); err != nil {
+				return nil, err
+			}
 		}
-
-		ui.URLPrefix = urlPrefix
-		ui.requests = metrics.GetOrCreateCounter(fmt.Sprintf(`vmauth_user_requests_total{username=%q}`, ui.Username))
-		m[ui.Username] = ui
+		if len(ui.URLMap) == 0 && ui.URLPrefix == nil {
+			return nil, fmt.Errorf("missing `url_prefix`")
+		}
+		if ui.BearerToken != "" {
+			if ui.Password != "" {
+				return nil, fmt.Errorf("password shouldn't be set for bearer_token %q", ui.BearerToken)
+			}
+			ui.requests = metrics.GetOrCreateCounter(`vmauth_user_requests_total{username="bearer_token"}`)
+			byBearerToken[ui.BearerToken] = true
+		}
+		if ui.Username != "" {
+			ui.requests = metrics.GetOrCreateCounter(fmt.Sprintf(`vmauth_user_requests_total{username=%q}`, ui.Username))
+			byUsername[ui.Username] = true
+		}
+		byAuthToken[authToken] = ui
 	}
-	return m, nil
+	return byAuthToken, nil
+}
+
+func getAuthToken(bearerToken, username, password string) string {
+	if bearerToken != "" {
+		return "Bearer " + bearerToken
+	}
+	token := username + ":" + password
+	token64 := base64.StdEncoding.EncodeToString([]byte(token))
+	return "Basic " + token64
+}
+
+func (up *URLPrefix) sanitize() error {
+	for i, pu := range up.urls {
+		puNew, err := sanitizeURLPrefix(pu)
+		if err != nil {
+			return err
+		}
+		up.urls[i] = puNew
+	}
+	return nil
+}
+
+func sanitizeURLPrefix(urlPrefix *url.URL) (*url.URL, error) {
+	// Remove trailing '/' from urlPrefix
+	for strings.HasSuffix(urlPrefix.Path, "/") {
+		urlPrefix.Path = urlPrefix.Path[:len(urlPrefix.Path)-1]
+	}
+	// Validate urlPrefix
+	if urlPrefix.Scheme != "http" && urlPrefix.Scheme != "https" {
+		return nil, fmt.Errorf("unsupported scheme for `url_prefix: %q`: %q; must be `http` or `https`", urlPrefix, urlPrefix.Scheme)
+	}
+	if urlPrefix.Host == "" {
+		return nil, fmt.Errorf("missing hostname in `url_prefix %q`", urlPrefix.Host)
+	}
+	return urlPrefix, nil
 }

app/vmauth/auth_config_test.go

@@ -1,8 +1,13 @@
 package main
 
 import (
-	"reflect"
+	"bytes"
+	"fmt"
+	"net/url"
+	"regexp"
 	"testing"
+
+	"gopkg.in/yaml.v2"
 )
 
 func TestParseAuthConfigFailure(t *testing.T) {
@@ -46,6 +51,46 @@ users:
 - username: foo
   url_prefix: //bar
 `)
+	f(`
+users:
+- username: foo
+  url_prefix: http:///bar
+`)
+	f(`
+users:
+- username: foo
+  url_prefix:
+    bar: baz
+`)
+	f(`
+users:
+- username: foo
+  url_prefix:
+  - [foo]
+`)
+
+	// empty url_prefix
+	f(`
+users:
+- username: foo
+  url_prefix: []
+`)
+
+	// Username and bearer_token in a single config
+	f(`
+users:
+- username: foo
+  bearer_token: bbb
+  url_prefix: http://foo.bar
+`)
+
+	// Bearer_token and password in a single config
+	f(`
+users:
+- password: foo
+  bearer_token: bbb
+  url_prefix: http://foo.bar
+`)
 
 	// Duplicate users
 	f(`
@@ -57,6 +102,60 @@ users:
 - username: foo
   url_prefix: https://sss.sss
 `)
+
+	// Duplicate bearer_tokens
+	f(`
+users:
+- bearer_token: foo
+  url_prefix: http://foo.bar
+- username: bar
+  url_prefix: http://xxx.yyy
+- bearer_token: foo
+  url_prefix: https://sss.sss
+`)
+
+	// Missing url_prefix in url_map
+	f(`
+users:
+- username: a
+  url_map:
+  - src_paths: ["/foo/bar"]
+`)
+
+	// Invalid url_prefix in url_map
+	f(`
+users:
+- username: a
+  url_map:
+  - src_paths: ["/foo/bar"]
+    url_prefix: foo.bar
+`)
+
+	// empty url_prefix in url_map
+	f(`
+users:
+- username: a
+  url_map:
+  - src_paths: ['/foo/bar']
+    url_prefix: []
+`)
+
+	// Missing src_paths in url_map
+	f(`
+users:
+- username: a
+  url_map:
+  - url_prefix: http://foobar
+`)
+
+	// Invalid regexp in src_path.
+	f(`
+users:
+- username: a
+  url_map:
+  - src_paths: ['fo[obar']
+    url_prefix: http://foobar
+`)
 }
 
 func TestParseAuthConfigSuccess(t *testing.T) {
@@ -67,8 +166,8 @@ func TestParseAuthConfigSuccess(t *testing.T) {
 			t.Fatalf("unexpected error: %s", err)
 		}
 		removeMetrics(m)
-		if !reflect.DeepEqual(m, expectedAuthConfig) {
-			t.Fatalf("unexpected auth config\ngot\n%v\nwant\n%v", m, expectedAuthConfig)
+		if err := areEqualConfigs(m, expectedAuthConfig); err != nil {
+			t.Fatal(err)
 		}
 	}
 
@@ -79,10 +178,29 @@ users:
   password: bar
   url_prefix: http://aaa:343/bbb
 `, map[string]*UserInfo{
-		"foo": {
+		getAuthToken("", "foo", "bar"): {
 			Username:  "foo",
 			Password:  "bar",
-			URLPrefix: "http://aaa:343/bbb",
+			URLPrefix: mustParseURL("http://aaa:343/bbb"),
+		},
+	})
+
+	// Multiple url_prefix entries
+	f(`
+users:
+- username: foo
+  password: bar
+  url_prefix:
+  - http://node1:343/bbb
+  - http://node2:343/bbb
+`, map[string]*UserInfo{
+		getAuthToken("", "foo", "bar"): {
+			Username: "foo",
+			Password: "bar",
+			URLPrefix: mustParseURLs([]string{
+				"http://node1:343/bbb",
+				"http://node2:343/bbb",
+			}),
 		},
 	})
 
@@ -94,15 +212,54 @@ users:
 - username: bar
   url_prefix: https://bar/x///
 `, map[string]*UserInfo{
-		"foo": {
+		getAuthToken("", "foo", ""): {
 			Username:  "foo",
-			URLPrefix: "http://foo",
+			URLPrefix: mustParseURL("http://foo"),
 		},
-		"bar": {
+		getAuthToken("", "bar", ""): {
 			Username:  "bar",
-			URLPrefix: "https://bar/x",
+			URLPrefix: mustParseURL("https://bar/x"),
 		},
 	})
+
+	// non-empty URLMap
+	f(`
+users:
+- bearer_token: foo
+  url_map:
+  - src_paths: ["/api/v1/query","/api/v1/query_range","/api/v1/label/[^./]+/.+"]
+    url_prefix: http://vmselect/select/0/prometheus
+  - src_paths: ["/api/v1/write"]
+    url_prefix: ["http://vminsert1/insert/0/prometheus","http://vminsert2/insert/0/prometheus"]
+`, map[string]*UserInfo{
+		getAuthToken("foo", "", ""): {
+			BearerToken: "foo",
+			URLMap: []URLMap{
+				{
+					SrcPaths:  getSrcPaths([]string{"/api/v1/query", "/api/v1/query_range", "/api/v1/label/[^./]+/.+"}),
+					URLPrefix: mustParseURL("http://vmselect/select/0/prometheus"),
+				},
+				{
+					SrcPaths: getSrcPaths([]string{"/api/v1/write"}),
+					URLPrefix: mustParseURLs([]string{
+						"http://vminsert1/insert/0/prometheus",
+						"http://vminsert2/insert/0/prometheus",
+					}),
+				},
+			},
+		},
+	})
+}
+
+func getSrcPaths(paths []string) []*SrcPath {
+	var sps []*SrcPath
+	for _, path := range paths {
+		sps = append(sps, &SrcPath{
+			sOriginal: path,
+			re:        regexp.MustCompile("^(?:" + path + ")$"),
+		})
+	}
+	return sps
 }
 
 func removeMetrics(m map[string]*UserInfo) {
@@ -110,3 +267,36 @@ func removeMetrics(m map[string]*UserInfo) {
 		info.requests = nil
 	}
 }
+
+func areEqualConfigs(a, b map[string]*UserInfo) error {
+	aData, err := yaml.Marshal(a)
+	if err != nil {
+		return fmt.Errorf("cannot marshal a: %w", err)
+	}
+	bData, err := yaml.Marshal(b)
+	if err != nil {
+		return fmt.Errorf("cannot marshal b: %w", err)
+	}
+	if !bytes.Equal(aData, bData) {
+		return fmt.Errorf("unexpected configs;\ngot\n%s\nwant\n%s", aData, bData)
+	}
+	return nil
+}
+
+func mustParseURL(u string) *URLPrefix {
+	return mustParseURLs([]string{u})
+}
+
+func mustParseURLs(us []string) *URLPrefix {
+	pus := make([]*url.URL, len(us))
+	for i, u := range us {
+		pu, err := url.Parse(u)
+		if err != nil {
+			panic(fmt.Errorf("BUG: cannot parse %q: %w", u, err))
+		}
+		pus[i] = pu
+	}
+	return &URLPrefix{
+		urls: pus,
+	}
+}

app/vmauth/example_config.yml

@@ -2,30 +2,70 @@
 # Usernames must be unique.
 
 users:
+  # Requests with the 'Authorization: Bearer XXXX' header are proxied to http://localhost:8428 .
+  # For example, http://vmauth:8427/api/v1/query is proxied to http://localhost:8428/api/v1/query
+- bearer_token: "XXXX"
+  url_prefix: "http://localhost:8428"
 
   # The user for querying local single-node VictoriaMetrics.
   # All the requests to http://vmauth:8427 with the given Basic Auth (username:password)
-  # will be routed to http://localhost:8428 .
-  # For example, http://vmauth:8427/api/v1/query is routed to http://localhost:8428/api/v1/query
+  # will be proxied to http://localhost:8428 .
+  # For example, http://vmauth:8427/api/v1/query is proxied to http://localhost:8428/api/v1/query
 - username: "local-single-node"
   password: "***"
   url_prefix: "http://localhost:8428"
 
-  # The user for querying account 123 in VictoriaMetrics cluster
-  # See https://github.com/VictoriaMetrics/VictoriaMetrics/blob/cluster/README.md#url-format
+  # The user for querying local single-node VictoriaMetrics with extra_label team=dev.
   # All the requests to http://vmauth:8427 with the given Basic Auth (username:password)
-  # will be routed to http://vmselect:8481/select/123/prometheus .
-  # For example, http://vmauth:8427/api/v1/query is routed to http://vmselect:8481/select/123/prometheus/api/v1/select
+  # will be routed to http://localhost:8428 with extra_label=team=dev query arg.
+  # For example, http://vmauth:8427/api/v1/query is routed to http://localhost:8428/api/v1/query?extra_label=team=dev
+- username: "local-single-node"
+  password: "***"
+  url_prefix: "http://localhost:8428?extra_label=team=dev"
+
+  # The user for querying account 123 in VictoriaMetrics cluster
+  # See https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html#url-format
+  # All the requests to http://vmauth:8427 with the given Basic Auth (username:password)
+  # will be load-balanced among http://vmselect1:8481/select/123/prometheus and http://vmselect2:8481/select/123/prometheus
+  # For example, http://vmauth:8427/api/v1/query is proxied to the following urls in a round-robin manner:
+  #   - http://vmselect1:8481/select/123/prometheus/api/v1/select
+  #   - http://vmselect2:8481/select/123/prometheus/api/v1/select
 - username: "cluster-select-account-123"
   password: "***"
-  url_prefix: "http://vmselect:8481/select/123/prometheus"
+  url_prefix:
+  - "http://vmselect1:8481/select/123/prometheus"
+  - "http://vmselect2:8481/select/123/prometheus"
 
   # The user for inserting Prometheus data into VictoriaMetrics cluster under account 42
-  # See https://github.com/VictoriaMetrics/VictoriaMetrics/blob/cluster/README.md#url-format
-  # All the reuqests to http://vmauth:8427 with the given Basic Auth (username:password)
-  # will be routed to http://vminsert:8480/insert/42/prometheus .
-  # For example, http://vmauth:8427/api/v1/write is routed to http://vminsert:8480/insert/42/prometheus/api/v1/write
+  # See https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html#url-format
+  # All the requests to http://vmauth:8427 with the given Basic Auth (username:password)
+  # will be load-balanced between http://vminsert1:8480/insert/42/prometheus and http://vminsert2:8480/insert/42/prometheus
+  # For example, http://vmauth:8427/api/v1/write is proxied to the following urls in a round-robin manner:
+  #   - http://vminsert1:8480/insert/42/prometheus/api/v1/write
+  #   - http://vminsert2:8480/insert/42/prometheus/api/v1/write
 - username: "cluster-insert-account-42"
   password: "***"
-  url_prefix: "http://vminsert:8480/insert/42/prometheus"
+  url_prefix:
+  - "http://vminsert1:8480/insert/42/prometheus"
+  - "http://vminsert2:8480/insert/42/prometheus"
 
+
+  # A single user for querying and inserting data:
+  # - Requests to http://vmauth:8427/api/v1/query, http://vmauth:8427/api/v1/query_range
+  #   and http://vmauth:8427/api/v1/label/<label_name>/values are proxied to the following urls in a round-robin manner:
+  #     - http://vmselect1:8481/select/42/prometheus
+  #     - http://vmselect2:8481/select/42/prometheus
+  #   For example, http://vmauth:8427/api/v1/query is proxied to http://vmselect1:8480/select/42/prometheus/api/v1/query
+  #   or to http://vmselect2:8480/select/42/prometheus/api/v1/query .
+  # - Requests to http://vmauth:8427/api/v1/write are proxied to http://vminsert:8480/insert/42/prometheus/api/v1/write
+- username: "foobar"
+  url_map:
+  - src_paths:
+    - "/api/v1/query"
+    - "/api/v1/query_range"
+    - "/api/v1/label/[^/]+/values"
+    url_prefix:
+    - "http://vmselect1:8481/select/42/prometheus"
+    - "http://vmselect2:8481/select/42/prometheus"
+  - src_paths: ["/api/v1/write"]
+    url_prefix: "http://vminsert:8480/insert/42/prometheus"

app/vmauth/main.go

@@ -2,7 +2,6 @@ package main
 
 import (
 	"flag"
-	"fmt"
 	"net/http"
 	"net/http/httputil"
 	"net/url"
@@ -10,15 +9,18 @@ import (
 	"time"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/buildinfo"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/cgroup"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/envflag"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/procutil"
+	"github.com/VictoriaMetrics/metrics"
 )
 
 var (
-	httpListenAddr = flag.String("httpListenAddr", ":8427", "TCP address to listen for http connections")
+	httpListenAddr         = flag.String("httpListenAddr", ":8427", "TCP address to listen for http connections")
+	maxIdleConnsPerBackend = flag.Int("maxIdleConnsPerBackend", 100, "The maximum number of idle connections vmauth can open per each backend host")
+	reloadAuthKey          = flag.String("reloadAuthKey", "", "Auth key for /-/reload http endpoint. It must be passed as authKey=...")
 )
 
 func main() {
@@ -28,7 +30,6 @@ func main() {
 	envflag.Parse()
 	buildinfo.Init()
 	logger.Init()
-	cgroup.UpdateGOMAXPROCSToCPUQuota()
 	logger.Infof("starting vmauth at %q...", *httpListenAddr)
 	startTime := time.Now()
 	initAuthConfig()
@@ -49,30 +50,57 @@ func main() {
 }
 
 func requestHandler(w http.ResponseWriter, r *http.Request) bool {
-	username, password, ok := r.BasicAuth()
-	if !ok {
+	switch r.URL.Path {
+	case "/-/reload":
+		authKey := r.FormValue("authKey")
+		if authKey != *reloadAuthKey {
+			httpserver.Errorf(w, r, "invalid authKey %q. It must match the value from -reloadAuthKey command line flag", authKey)
+			return true
+		}
+		configReloadRequests.Inc()
+		procutil.SelfSIGHUP()
+		w.WriteHeader(http.StatusOK)
+		return true
+	}
+	authToken := r.Header.Get("Authorization")
+	if authToken == "" {
 		w.Header().Set("WWW-Authenticate", `Basic realm="Restricted"`)
-		http.Error(w, "missing `Authorization: Basic *` header", http.StatusUnauthorized)
+		http.Error(w, "missing `Authorization` request header", http.StatusUnauthorized)
 		return true
 	}
 	ac := authConfig.Load().(map[string]*UserInfo)
-	info := ac[username]
-	if info == nil || info.Password != password {
-		httpserver.Errorf(w, r, "cannot find the provided username %q or password in config", username)
+	ui := ac[authToken]
+	if ui == nil {
+		httpserver.Errorf(w, r, "cannot find the provided auth token %q in config", authToken)
 		return true
 	}
-	info.requests.Inc()
-
-	targetURL := createTargetURL(info.URLPrefix, r.URL)
-	if _, err := url.Parse(targetURL); err != nil {
-		httpserver.Errorf(w, r, "invalid targetURL=%q: %s", targetURL, err)
+	ui.requests.Inc()
+	targetURL, err := createTargetURL(ui, r.URL)
+	if err != nil {
+		httpserver.Errorf(w, r, "cannot determine targetURL: %s", err)
 		return true
 	}
-	r.Header.Set("vm-target-url", targetURL)
-	reverseProxy.ServeHTTP(w, r)
+	r.Header.Set("vm-target-url", targetURL.String())
+	proxyRequest(w, r)
 	return true
 }
 
+func proxyRequest(w http.ResponseWriter, r *http.Request) {
+	defer func() {
+		err := recover()
+		if err == nil || err == http.ErrAbortHandler {
+			// Suppress http.ErrAbortHandler panic.
+			// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1353
+			return
+		}
+		// Forward other panics to the caller.
+		panic(err)
+	}()
+	reverseProxy.ServeHTTP(w, r)
+}
+
+var configReloadRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/-/reload"}`)
+
 var reverseProxy = &httputil.ReverseProxy{
 	Director: func(r *http.Request) {
 		targetURL := r.Header.Get("vm-target-url")
@@ -88,6 +116,7 @@ var reverseProxy = &httputil.ReverseProxy{
 		tr.DisableCompression = true
 		// Disable HTTP/2.0, since VictoriaMetrics components don't support HTTP/2.0 (because there is no sense in this).
 		tr.ForceAttemptHTTP2 = false
+		tr.MaxIdleConnsPerHost = *maxIdleConnsPerBackend
 		return tr
 	}(),
 	FlushInterval: time.Second,
@@ -98,10 +127,7 @@ func usage() {
 	const s = `
 vmauth authenticates and authorizes incoming requests and proxies them to VictoriaMetrics.
 
-See the docs at https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/app/vmauth/README.md .
+See the docs at https://docs.victoriametrics.com/vmauth.html .
 `
-
-	f := flag.CommandLine.Output()
-	fmt.Fprintf(f, "%s\n", s)
-	flag.PrintDefaults()
+	flagutil.Usage(s)
 }

app/vmauth/multiarch/Dockerfile

@@ -0,0 +1,12 @@
+# See https://medium.com/on-docker/use-multi-stage-builds-to-inject-ca-certs-ad1e8f01de1b
+ARG certs_image
+ARG root_image
+FROM $certs_image as certs
+RUN apk --update --no-cache add ca-certificates
+
+FROM $root_image
+COPY --from=certs /etc/ssl/certs/ca-certificates.crt /etc/ssl/certs/ca-certificates.crt
+EXPOSE 8427
+ENTRYPOINT ["/vmauth-prod"]
+ARG TARGETARCH
+COPY vmauth-${TARGETARCH}-prod ./vmauth-prod

app/vmauth/target_url.go

@@ -1,16 +1,56 @@
 package main
 
 import (
+	"fmt"
 	"net/url"
 	"path"
 	"strings"
 )
 
-func createTargetURL(prefix string, u *url.URL) string {
+func (up *URLPrefix) mergeURLs(requestURI *url.URL) *url.URL {
+	pu := up.getNextURL()
+	return mergeURLs(pu, requestURI)
+}
+
+func mergeURLs(uiURL, requestURI *url.URL) *url.URL {
+	targetURL := *uiURL
+	targetURL.Path += requestURI.Path
+	requestParams := requestURI.Query()
+	// fast path
+	if len(requestParams) == 0 {
+		return &targetURL
+	}
+	// merge query parameters from requests.
+	uiParams := targetURL.Query()
+	for k, v := range requestParams {
+		// skip clashed query params from original request
+		if exist := uiParams.Get(k); len(exist) > 0 {
+			continue
+		}
+		for i := range v {
+			uiParams.Add(k, v[i])
+		}
+	}
+	targetURL.RawQuery = uiParams.Encode()
+	return &targetURL
+}
+
+func createTargetURL(ui *UserInfo, uOrig *url.URL) (*url.URL, error) {
+	u := *uOrig
 	// Prevent from attacks with using `..` in r.URL.Path
 	u.Path = path.Clean(u.Path)
 	if !strings.HasPrefix(u.Path, "/") {
 		u.Path = "/" + u.Path
 	}
-	return prefix + u.RequestURI()
+	for _, e := range ui.URLMap {
+		for _, sp := range e.SrcPaths {
+			if sp.match(u.Path) {
+				return e.URLPrefix.mergeURLs(&u), nil
+			}
+		}
+	}
+	if ui.URLPrefix != nil {
+		return ui.URLPrefix.mergeURLs(&u), nil
+	}
+	return nil, fmt.Errorf("missing route for %q", u.String())
 }

app/vmauth/target_url_test.go

@@ -5,22 +5,109 @@ import (
 	"testing"
 )
 
-func TestCreateTargetURL(t *testing.T) {
-	f := func(prefix, requestURI, expectedTarget string) {
+func TestCreateTargetURLSuccess(t *testing.T) {
+	f := func(ui *UserInfo, requestURI, expectedTarget string) {
 		t.Helper()
 		u, err := url.Parse(requestURI)
 		if err != nil {
 			t.Fatalf("cannot parse %q: %s", requestURI, err)
 		}
-		target := createTargetURL(prefix, u)
-		if target != expectedTarget {
+		target, err := createTargetURL(ui, u)
+		if err != nil {
+			t.Fatalf("unexpected error: %s", err)
+		}
+		if target.String() != expectedTarget {
 			t.Fatalf("unexpected target; got %q; want %q", target, expectedTarget)
 		}
 	}
-	f("http://foo.bar", "", "http://foo.bar/.")
-	f("http://foo.bar", "/", "http://foo.bar/")
-	f("http://foo.bar", "a/b?c=d", "http://foo.bar/a/b?c=d")
-	f("https://sss:3894/x/y", "/z", "https://sss:3894/x/y/z")
-	f("https://sss:3894/x/y", "/../../aaa", "https://sss:3894/x/y/aaa")
-	f("https://sss:3894/x/y", "/./asd/../../aaa?a=d&s=s/../d", "https://sss:3894/x/y/aaa?a=d&s=s/../d")
+	// Simple routing with `url_prefix`
+	f(&UserInfo{
+		URLPrefix: mustParseURL("http://foo.bar"),
+	}, "", "http://foo.bar/.")
+	f(&UserInfo{
+		URLPrefix: mustParseURL("http://foo.bar"),
+	}, "/", "http://foo.bar/")
+	f(&UserInfo{
+		URLPrefix: mustParseURL("http://foo.bar"),
+	}, "a/b?c=d", "http://foo.bar/a/b?c=d")
+	f(&UserInfo{
+		URLPrefix: mustParseURL("https://sss:3894/x/y"),
+	}, "/z", "https://sss:3894/x/y/z")
+	f(&UserInfo{
+		URLPrefix: mustParseURL("https://sss:3894/x/y"),
+	}, "/../../aaa", "https://sss:3894/x/y/aaa")
+	f(&UserInfo{
+		URLPrefix: mustParseURL("https://sss:3894/x/y"),
+	}, "/./asd/../../aaa?a=d&s=s/../d", "https://sss:3894/x/y/aaa?a=d&s=s%2F..%2Fd")
+
+	// Complex routing with `url_map`
+	ui := &UserInfo{
+		URLMap: []URLMap{
+			{
+				SrcPaths:  getSrcPaths([]string{"/api/v1/query"}),
+				URLPrefix: mustParseURL("http://vmselect/0/prometheus"),
+			},
+			{
+				SrcPaths:  getSrcPaths([]string{"/api/v1/write"}),
+				URLPrefix: mustParseURL("http://vminsert/0/prometheus"),
+			},
+		},
+		URLPrefix: mustParseURL("http://default-server"),
+	}
+	f(ui, "/api/v1/query?query=up", "http://vmselect/0/prometheus/api/v1/query?query=up")
+	f(ui, "/api/v1/write", "http://vminsert/0/prometheus/api/v1/write")
+	f(ui, "/api/v1/query_range", "http://default-server/api/v1/query_range")
+
+	// Complex routing regexp paths in `url_map`
+	ui = &UserInfo{
+		URLMap: []URLMap{
+			{
+				SrcPaths:  getSrcPaths([]string{"/api/v1/query(_range)?", "/api/v1/label/[^/]+/values"}),
+				URLPrefix: mustParseURL("http://vmselect/0/prometheus"),
+			},
+			{
+				SrcPaths:  getSrcPaths([]string{"/api/v1/write"}),
+				URLPrefix: mustParseURL("http://vminsert/0/prometheus"),
+			},
+		},
+		URLPrefix: mustParseURL("http://default-server"),
+	}
+	f(ui, "/api/v1/query?query=up", "http://vmselect/0/prometheus/api/v1/query?query=up")
+	f(ui, "/api/v1/query_range?query=up", "http://vmselect/0/prometheus/api/v1/query_range?query=up")
+	f(ui, "/api/v1/label/foo/values", "http://vmselect/0/prometheus/api/v1/label/foo/values")
+	f(ui, "/api/v1/write", "http://vminsert/0/prometheus/api/v1/write")
+	f(ui, "/api/v1/foo/bar", "http://default-server/api/v1/foo/bar")
+	f(&UserInfo{
+		URLPrefix: mustParseURL("http://foo.bar?extra_label=team=dev"),
+	}, "/api/v1/query", "http://foo.bar/api/v1/query?extra_label=team=dev")
+	f(&UserInfo{
+		URLPrefix: mustParseURL("http://foo.bar?extra_label=team=mobile"),
+	}, "/api/v1/query?extra_label=team=dev", "http://foo.bar/api/v1/query?extra_label=team%3Dmobile")
+
+}
+
+func TestCreateTargetURLFailure(t *testing.T) {
+	f := func(ui *UserInfo, requestURI string) {
+		t.Helper()
+		u, err := url.Parse(requestURI)
+		if err != nil {
+			t.Fatalf("cannot parse %q: %s", requestURI, err)
+		}
+		target, err := createTargetURL(ui, u)
+		if err == nil {
+			t.Fatalf("expecting non-nil error")
+		}
+		if target != nil {
+			t.Fatalf("unexpected target=%q; want empty string", target)
+		}
+	}
+	f(&UserInfo{}, "/foo/bar")
+	f(&UserInfo{
+		URLMap: []URLMap{
+			{
+				SrcPaths:  getSrcPaths([]string{"/api/v1/query"}),
+				URLPrefix: mustParseURL("http://foobar/baz"),
+			},
+		},
+	}, "/api/v1/write")
 }

app/vmbackup/README.md

@@ -1,6 +1,6 @@
-## vmbackup
+# vmbackup
 
-`vmbackup` creates VictoriaMetrics data backups from [instant snapshots](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/README.md#how-to-work-with-snapshots).
+`vmbackup` creates VictoriaMetrics data backups from [instant snapshots](https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html#how-to-work-with-snapshots).
 
 Supported storage systems for backups:
 
@@ -15,17 +15,17 @@ data between the existing backup and new backup. It saves time and costs on data
 
 Backup process can be interrupted at any time. It is automatically resumed from the interruption point when restarting `vmbackup` with the same args.
 
-Backed up data can be restored with [vmrestore](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/app/vmrestore/README.md).
+Backed up data can be restored with [vmrestore](https://docs.victoriametrics.com/vmrestore.html).
 
 See [this article](https://medium.com/@valyala/speeding-up-backups-for-big-time-series-databases-533c1a927883) for more details.
 
-See also [vmbackuper](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/466) tool built on top of `vmbackup`. This tool simplifies
+See also [vmbackupmanager](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/466) tool built on top of `vmbackup`. This tool simplifies
 creation of hourly, daily, weekly and monthly backups.
 
 
-### Use cases
+## Use cases
 
-#### Regular backups
+### Regular backups
 
 Regular backup can be performed with the following command:
 
@@ -34,13 +34,13 @@ vmbackup -storageDataPath=</path/to/victoria-metrics-data> -snapshotName=<local-
 ```
 
 * `</path/to/victoria-metrics-data>` - path to VictoriaMetrics data pointed by `-storageDataPath` command-line flag in single-node VictoriaMetrics or in cluster `vmstorage`.
-  There is no need to stop VictoriaMetrics for creating backups, since they are performed from immutable [instant snapshots](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/README.md#how-to-work-with-snapshots).
-* `<local-snapshot>` is the snapshot to back up. See [how to create instant snapshots](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/README.md#how-to-work-with-snapshots).
+  There is no need to stop VictoriaMetrics for creating backups, since they are performed from immutable [instant snapshots](https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html#how-to-work-with-snapshots).
+* `<local-snapshot>` is the snapshot to back up. See [how to create instant snapshots](https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html#how-to-work-with-snapshots). `vmbackup` can create the snapshot on itself if `-snapshot.createURL` command-line flag is set to an url for creating snapshots. In this case `-snapshotName` flag isn't needed.
 * `<bucket>` is an already existing name for [GCS bucket](https://cloud.google.com/storage/docs/creating-buckets).
 * `<path/to/new/backup>` is the destination path where new backup will be placed.
 
 
-#### Regular backups with server-side copy from existing backup
+### Regular backups with server-side copy from existing backup
 
 If the destination GCS bucket already contains the previous backup at `-origin` path, then new backup can be sped up
 with the following command:
@@ -52,7 +52,7 @@ vmbackup -storageDataPath=</path/to/victoria-metrics-data> -snapshotName=<local-
 It saves time and network bandwidth costs by performing server-side copy for the shared data from the `-origin` to `-dst`.
 
 
-#### Incremental backups
+### Incremental backups
 
 Incremental backups performed if `-dst` points to an already existing backup. In this case only new data uploaded to remote storage.
 It saves time and network bandwidth costs when working with big backups:
@@ -62,7 +62,7 @@ vmbackup -storageDataPath=</path/to/victoria-metrics-data> -snapshotName=<local-
 ```
 
 
-#### Smart backups
+### Smart backups
 
 Smart backups mean storing full daily backups into `YYYYMMDD` folders and creating incremental hourly backup into `latest` folder:
 
@@ -72,7 +72,7 @@ Smart backups mean storing full daily backups into `YYYYMMDD` folders and creati
 vmbackup -snapshotName=<latest-snapshot> -dst=gcs://<bucket>/latest
 ```
 
-Where `<latest-snapshot>` is the latest [snapshot](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/README.md#how-to-work-with-snapshots).
+Where `<latest-snapshot>` is the latest [snapshot](https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html#how-to-work-with-snapshots).
 The command will upload only changed data to `gcs://<bucket>/latest`.
 
 * Run the following command once a day:
@@ -89,10 +89,10 @@ or from any day (`YYYYMMDD` backups). Note that hourly backup shouldn't run when
 
 Do not forget removing old snapshots and backups when they are no longer needed for saving storage costs.
 
-See also [vmbackuper tool](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/466) for automating smart backups.
+See also [vmbackupmanager tool](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/466) for automating smart backups.
 
 
-### How does it work?
+## How does it work?
 
 The backup algorithm is the following:
 
@@ -118,16 +118,16 @@ See [this article](https://medium.com/@valyala/speeding-up-backups-for-big-time-
 `vmbackup` can work improperly or slowly when these properties are violated.
 
 
-### Troubleshooting
+## Troubleshooting
 
 * If the backup is slow, then try setting higher value for `-concurrency` flag. This will increase the number of concurrent workers that upload data to backup storage.
 * If `vmbackup` eats all the network bandwidth, then set `-maxBytesPerSecond` to the desired value.
 * If `vmbackup` has been interrupted due to temporary error, then just restart it with the same args. It will resume the backup process.
-* Backups created from [single-node VictoriaMetrics](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/README.md) cannot be restored
-  at [cluster VictoriaMetrics](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/cluster/README.md) and vice versa.
+* Backups created from [single-node VictoriaMetrics](https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html) cannot be restored
+  at [cluster VictoriaMetrics](https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html) and vice versa.
 
 
-### Advanced usage
+## Advanced usage
 
 
 * Obtaining credentials from a file.
@@ -191,30 +191,36 @@ See [this article](https://medium.com/@valyala/speeding-up-backups-for-big-time-
     	Prefix for environment variables if -envflag.enable is set
   -fs.disableMmap
     	Whether to use pread() instead of mmap() for reading data files. By default mmap() is used for 64-bit arches and pread() is used for 32-bit arches, since they cannot read data files bigger than 2^32 bytes in memory. mmap() is usually faster for reading small data chunks than pread()
+  -loggerDisableTimestamps
+    	Whether to disable writing timestamps in logs
   -loggerErrorsPerSecondLimit int
-    	Per-second limit on the number of ERROR messages. If more than the given number of errors are emitted per second, then the remaining errors are suppressed. Zero value disables the rate limit (default 10)
+    	Per-second limit on the number of ERROR messages. If more than the given number of errors are emitted per second, the remaining errors are suppressed. Zero values disable the rate limit
   -loggerFormat string
     	Format for logs. Possible values: default, json (default "default")
   -loggerLevel string
     	Minimum level of errors to log. Possible values: INFO, WARN, ERROR, FATAL, PANIC (default "INFO")
   -loggerOutput string
     	Output for the logs. Supported values: stderr, stdout (default "stderr")
-  -maxBytesPerSecond value
+  -loggerTimezone string
+    	Timezone to use for timestamps in logs. Timezone must be a valid IANA Time Zone. For example: America/New_York, Europe/Berlin, Etc/GMT+3 or Local (default "UTC")
+  -loggerWarnsPerSecondLimit int
+    	Per-second limit on the number of WARN messages. If more than the given number of warns are emitted per second, then the remaining warns are suppressed. Zero values disable the rate limit
+  -maxBytesPerSecond size
     	The maximum upload speed. There is no limit if it is set to 0
-    	Supports the following optional suffixes for values: KB, MB, GB, KiB, MiB, GiB (default 0)
-  -memory.allowedBytes value
-    	Allowed size of system memory VictoriaMetrics caches may occupy. This option overrides -memory.allowedPercent if set to non-zero value. Too low value may increase cache miss rate, which usually results in higher CPU and disk IO usage. Too high value may evict too much data from OS page cache, which will result in higher disk IO usage
-    	Supports the following optional suffixes for values: KB, MB, GB, KiB, MiB, GiB (default 0)
+    	Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 0)
+  -memory.allowedBytes size
+    	Allowed size of system memory VictoriaMetrics caches may occupy. This option overrides -memory.allowedPercent if set to a non-zero value. Too low a value may increase the cache miss rate usually resulting in higher CPU and disk IO usage. Too high a value may evict too much data from OS page cache resulting in higher disk IO usage
+    	Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 0)
   -memory.allowedPercent float
-    	Allowed percent of system memory VictoriaMetrics caches may occupy. See also -memory.allowedBytes. Too low value may increase cache miss rate, which usually results in higher CPU and disk IO usage. Too high value may evict too much data from OS page cache, which will result in higher disk IO usage (default 60)
+    	Allowed percent of system memory VictoriaMetrics caches may occupy. See also -memory.allowedBytes. Too low a value may increase cache miss rate usually resulting in higher CPU and disk IO usage. Too high a value may evict too much data from OS page cache which will result in higher disk IO usage (default 60)
   -origin string
     	Optional origin directory on the remote storage with old backup for server-side copying when performing full backup. This speeds up full backups
   -snapshot.createURL string
-    	VictoriaMetrics create snapshot url. When this is given a snapshot will automatically be created during backup. Example: http://victoriametrics:8428/snaphsot/create
+    	VictoriaMetrics create snapshot url. When this is given a snapshot will automatically be created during backup. Example: http://victoriametrics:8428/snapshot/create . There is no need in setting -snapshotName if -snapshot.createURL is set
   -snapshot.deleteURL string
-    	VictoriaMetrics delete snapshot url. Optional. Will be generated from -snapshot.createURL if not provided. All created snaphosts will be automatically deleted. Example: http://victoriametrics:8428/snaphsot/delete
+    	VictoriaMetrics delete snapshot url. Optional. Will be generated from -snapshot.createURL if not provided. All created snapshots will be automatically deleted. Example: http://victoriametrics:8428/snapshot/delete
   -snapshotName string
-    	Name for the snapshot to backup. See https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/README.md#how-to-work-with-snapshots
+    	Name for the snapshot to backup. See https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html#how-to-work-with-snapshots. There is no need in setting -snapshotName if -snapshot.createURL is set
   -storageDataPath string
     	Path to VictoriaMetrics data. Must match -storageDataPath from VictoriaMetrics or vmstorage (default "victoria-metrics-data")
   -version
@@ -222,24 +228,24 @@ See [this article](https://medium.com/@valyala/speeding-up-backups-for-big-time-
 ```
 
 
-### How to build from sources
+## How to build from sources
 
 It is recommended using [binary releases](https://github.com/VictoriaMetrics/VictoriaMetrics/releases) - see `vmutils-*` archives there.
 
 
-#### Development build
+### Development build
 
-1. [Install Go](https://golang.org/doc/install). The minimum supported version is Go 1.13.
-2. Run `make vmbackup` from the root folder of the repository.
+1. [Install Go](https://golang.org/doc/install). The minimum supported version is Go 1.16.
+2. Run `make vmbackup` from the root folder of [the repository](https://github.com/VictoriaMetrics/VictoriaMetrics).
    It builds `vmbackup` binary and puts it into the `bin` folder.
 
-#### Production build
+### Production build
 
 1. [Install docker](https://docs.docker.com/install/).
-2. Run `make vmbackup-prod` from the root folder of the repository.
+2. Run `make vmbackup-prod` from the root folder of [the repository](https://github.com/VictoriaMetrics/VictoriaMetrics).
    It builds `vmbackup-prod` binary and puts it into the `bin` folder.
 
-#### Building docker images
+### Building docker images
 
 Run `make package-vmbackup`. It builds `victoriametrics/vmbackup:<PKG_TAG>` docker image locally.
 `<PKG_TAG>` is auto-generated image tag, which depends on source code in the repository.

app/vmbackup/main.go

@@ -12,7 +12,6 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/backup/fslocal"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/backup/fsnil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/buildinfo"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/cgroup"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/envflag"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
@@ -20,11 +19,11 @@ import (
 
 var (
 	storageDataPath   = flag.String("storageDataPath", "victoria-metrics-data", "Path to VictoriaMetrics data. Must match -storageDataPath from VictoriaMetrics or vmstorage")
-	snapshotName      = flag.String("snapshotName", "", "Name for the snapshot to backup. See https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/README.md#how-to-work-with-snapshots")
+	snapshotName      = flag.String("snapshotName", "", "Name for the snapshot to backup. See https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html#how-to-work-with-snapshots. There is no need in setting -snapshotName if -snapshot.createURL is set")
 	snapshotCreateURL = flag.String("snapshot.createURL", "", "VictoriaMetrics create snapshot url. When this is given a snapshot will automatically be created during backup. "+
-		"Example: http://victoriametrics:8428/snaphsot/create")
+		"Example: http://victoriametrics:8428/snapshot/create . There is no need in setting -snapshotName if -snapshot.createURL is set")
 	snapshotDeleteURL = flag.String("snapshot.deleteURL", "", "VictoriaMetrics delete snapshot url. Optional. Will be generated from -snapshot.createURL if not provided. "+
-		"All created snaphosts will be automatically deleted. Example: http://victoriametrics:8428/snaphsot/delete")
+		"All created snapshots will be automatically deleted. Example: http://victoriametrics:8428/snapshot/delete")
 	dst = flag.String("dst", "", "Where to put the backup on the remote storage. "+
 		"Example: gcs://bucket/path/to/backup/dir, s3://bucket/path/to/backup/dir or fs:///path/to/local/backup/dir\n"+
 		"-dst can point to the previous backup. In this case incremental backup is performed, i.e. only changed data is uploaded")
@@ -40,10 +39,11 @@ func main() {
 	envflag.Parse()
 	buildinfo.Init()
 	logger.Init()
-	cgroup.UpdateGOMAXPROCSToCPUQuota()
 
 	if len(*snapshotCreateURL) > 0 {
-		logger.Infof("%s", "Snapshots enabled")
+		if len(*snapshotName) > 0 {
+			logger.Fatalf("-snapshotName shouldn't be set if -snapshot.createURL is set, since snapshots are created automatically in this case")
+		}
 		logger.Infof("Snapshot create url %s", *snapshotCreateURL)
 		if len(*snapshotDeleteURL) <= 0 {
 			err := flag.Set("snapshot.deleteURL", strings.Replace(*snapshotCreateURL, "/create", "/delete", 1))
@@ -55,17 +55,17 @@ func main() {
 
 		name, err := snapshot.Create(*snapshotCreateURL)
 		if err != nil {
-			logger.Fatalf("%s", err)
+			logger.Fatalf("cannot create snapshot: %s", err)
 		}
 		err = flag.Set("snapshotName", name)
 		if err != nil {
-			logger.Fatalf("Failed to set snapshotName flag: %v", err)
+			logger.Fatalf("cannot set snapshotName flag: %v", err)
 		}
 
 		defer func() {
 			err := snapshot.Delete(*snapshotDeleteURL, name)
 			if err != nil {
-				logger.Fatalf("%s", err)
+				logger.Fatalf("cannot delete snapshot: %s", err)
 			}
 		}()
 	}
@@ -101,12 +101,9 @@ func usage() {
 vmbackup performs backups for VictoriaMetrics data from instant snapshots to gcs, s3
 or local filesystem. Backed up data can be restored with vmrestore.
 
-See the docs at https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/app/vmbackup/README.md .
+See the docs at https://docs.victoriametrics.com/vmbackup.html .
 `
-
-	f := flag.CommandLine.Output()
-	fmt.Fprintf(f, "%s\n", s)
-	flag.PrintDefaults()
+	flagutil.Usage(s)
 }
 
 func newSrcFS() (*fslocal.FS, error) {

app/vmbackup/multiarch/Dockerfile

@@ -0,0 +1,11 @@
+# See https://medium.com/on-docker/use-multi-stage-builds-to-inject-ca-certs-ad1e8f01de1b
+ARG certs_image
+ARG root_image
+FROM $certs_image as certs
+RUN apk --update --no-cache add ca-certificates
+
+FROM $root_image
+COPY --from=certs /etc/ssl/certs/ca-certificates.crt /etc/ssl/certs/ca-certificates.crt
+ENTRYPOINT ["/vmbackup-prod"]
+ARG TARGETARCH
+COPY vmbackup-${TARGETARCH}-prod ./vmbackup-prod

app/vmbackup/snapshot/snapshot.go

@@ -20,26 +20,27 @@ type snapshot struct {
 // Create creates a snapshot and the provided api endpoint and returns
 // the snapshot name
 func Create(createSnapshotURL string) (string, error) {
-	logger.Infof("%s", "Creating snapshot")
+	logger.Infof("Creating snapshot")
 	u, err := url.Parse(createSnapshotURL)
 	if err != nil {
 		return "", err
 	}
-
 	resp, err := http.Get(u.String())
 	if err != nil {
 		return "", err
 	}
-
 	body, err := ioutil.ReadAll(resp.Body)
 	if err != nil {
 		return "", err
 	}
+	if resp.StatusCode != http.StatusOK {
+		return "", fmt.Errorf("unexpected status code returned from %q; expecting %d; got %d; response body: %q", createSnapshotURL, resp.StatusCode, http.StatusOK, body)
+	}
 
 	snap := snapshot{}
 	err = json.Unmarshal(body, &snap)
 	if err != nil {
-		return "", err
+		return "", fmt.Errorf("cannot parse JSON response from %q: %w; response body: %q", createSnapshotURL, err, body)
 	}
 
 	if snap.Status == "ok" {
@@ -58,26 +59,26 @@ func Delete(deleteSnapshotURL string, snapshotName string) error {
 	formData := url.Values{
 		"snapshot": {snapshotName},
 	}
-
 	u, err := url.Parse(deleteSnapshotURL)
 	if err != nil {
 		return err
 	}
-
 	resp, err := http.PostForm(u.String(), formData)
 	if err != nil {
 		return err
 	}
-
 	body, err := ioutil.ReadAll(resp.Body)
 	if err != nil {
 		return err
 	}
+	if resp.StatusCode != http.StatusOK {
+		return fmt.Errorf("unexpected status code returned from %q; expecting %d; got %d; response body: %q", deleteSnapshotURL, resp.StatusCode, http.StatusOK, body)
+	}
 
 	snap := snapshot{}
 	err = json.Unmarshal(body, &snap)
 	if err != nil {
-		return err
+		return fmt.Errorf("cannot parse JSON response from %q: %w; response body: %q", deleteSnapshotURL, err, body)
 	}
 
 	if snap.Status == "ok" {