docs/CHANGELOG.md: cut v1.74.0

* update package.json

* update package-lock.json

* app/vmselect: `make vmui-update`

Co-authored-by: Aliaksandr Valialkin <valyala@victoriametrics.com>

.dockerignore

@@ -4,3 +4,4 @@ gocache-for-docker
 victoria-metrics-data
 vmstorage-data
 vmselect-cache
+.vscode

.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 +1,26 @@
+version: 2
+updates:
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "daily"
+  - package-ecosystem: "gomod"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+  - package-ecosystem: "bundler"
+    directory: "/docs"
+    schedule:
+      interval: "daily"
+  - package-ecosystem: "gomod"
+    directory: "/app/vmui/packages/vmui/web"
+    schedule:
+      interval: "weekly"
+  - package-ecosystem: "docker"
+    directory: "/"
+    schedule:
+      interval: "daily"
+  - package-ecosystem: "npm"
+    directory: "/app/vmui/packages/vmui"
+    schedule:
+      interval: "weekly"

.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: 1.17
+        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

@@ -14,19 +14,17 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Setup Go
-        uses: actions/setup-go@master
+        uses: actions/setup-go@main
         with:
-          go-version: 1.14
+          go-version: 1.17
         id: go
-      - name: Dependencies
-        env:
-          GO111MODULE: on
-        run: |
-          go get -u golang.org/x/lint/golint
-          go get -u github.com/kisielk/errcheck
-          go get -u github.com/golangci/golangci-lint/cmd/golangci-lint
       - name: Code checkout
         uses: actions/checkout@master
+      - name: Dependencies
+        run: |
+          make install-golint
+          make install-errcheck
+          make install-golangci-lint
       - name: Build
         env:
           GO111MODULE: on
@@ -43,10 +41,26 @@ jobs:
           make victoria-metrics-arm64
           make vmutils
           GOOS=freebsd go build -mod=vendor ./app/victoria-metrics
+          GOOS=freebsd go build -mod=vendor ./app/vmagent
+          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@v2.1.0
         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

@@ -4,6 +4,7 @@
 *.pprof
 /bin
 .idea
+.vscode
 *.test
 *.swp
 /gocache-for-docker
@@ -15,3 +16,7 @@
 /package/temp-rpm-*
 /package/*.deb
 /package/*.rpm
+.DS_store
+Gemfile.lock
+/_site
+_site

.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 2019-2022 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 \
@@ -16,10 +19,13 @@ all: \
 	vmalert-prod \
 	vmauth-prod \
 	vmbackup-prod \
-	vmrestore-prod
+	vmrestore-prod \
+	vmctl-prod
 
 include app/*/Makefile
 include deployment/*/Makefile
+include snap/local/Makefile
+
 
 clean:
 	rm -rf bin/*
@@ -30,7 +36,8 @@ publish: \
 	publish-vmalert \
 	publish-vmauth \
 	publish-vmbackup \
-	publish-vmrestore
+	publish-vmrestore \
+	publish-vmctl
 
 package: \
 	package-victoria-metrics \
@@ -38,31 +45,156 @@ 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
+
+
+publish-release:
+	git checkout $(TAG) && $(MAKE) release publish && \
+		git checkout $(TAG)-cluster && $(MAKE) release publish && \
+		git checkout $(TAG)-enterprise && $(MAKE) release publish && \
+		git checkout $(TAG)-enterprise-cluster && $(MAKE) release publish
 
 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-darwin-amd64 \
+	release-victoria-metrics-darwin-arm64
+
+release-victoria-metrics-amd64:
+	OSARCH=amd64 $(MAKE) release-victoria-metrics-generic
+
+release-victoria-metrics-arm:
+	OSARCH=arm $(MAKE) release-victoria-metrics-generic
+
+release-victoria-metrics-arm64:
+	OSARCH=arm64 $(MAKE) release-victoria-metrics-generic
+
+release-victoria-metrics-darwin-amd64:
+	OSARCH=darwin-amd64 $(MAKE) release-victoria-metrics-generic
+
+release-victoria-metrics-darwin-arm64:
+	OSARCH=darwin-arm64 $(MAKE) release-victoria-metrics-generic
+
+release-victoria-metrics-generic: victoria-metrics-$(OSARCH)-prod
+	cd bin && \
+		tar --transform="flags=r;s|-$(OSARCH)||" -czf victoria-metrics-$(OSARCH)-$(PKG_TAG).tar.gz \
+			victoria-metrics-$(OSARCH)-prod \
+		&& sha256sum victoria-metrics-$(OSARCH)-$(PKG_TAG).tar.gz \
+			victoria-metrics-$(OSARCH)-prod \
+			| sed s/-$(OSARCH)-prod/-prod/ > victoria-metrics-$(OSARCH)-$(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-darwin-amd64  \
+	release-vmutils-darwin-arm64 \
+	release-vmutils-windows-amd64
+
+release-vmutils-amd64:
+	OSARCH=amd64 $(MAKE) release-vmutils-generic
+
+release-vmutils-arm64:
+	OSARCH=arm64 $(MAKE) release-vmutils-generic
+
+release-vmutils-arm:
+	OSARCH=arm $(MAKE) release-vmutils-generic
+
+release-vmutils-darwin-amd64:
+	OSARCH=darwin-amd64 $(MAKE) release-vmutils-generic
+
+release-vmutils-darwin-arm64:
+	OSARCH=darwin-arm64 $(MAKE) release-vmutils-generic
+
+release-vmutils-windows-amd64:
+	GOARCH=amd64 $(MAKE) release-vmutils-windows-generic
+
+release-vmutils-generic: \
+	vmagent-$(OSARCH)-prod \
+	vmalert-$(OSARCH)-prod \
+	vmauth-$(OSARCH)-prod \
+	vmbackup-$(OSARCH)-prod \
+	vmrestore-$(OSARCH)-prod \
+	vmctl-$(OSARCH)-prod
+	cd bin && \
+		tar --transform="flags=r;s|-$(OSARCH)||" -czf vmutils-$(OSARCH)-$(PKG_TAG).tar.gz \
+			vmagent-$(OSARCH)-prod \
+			vmalert-$(OSARCH)-prod \
+			vmauth-$(OSARCH)-prod \
+			vmbackup-$(OSARCH)-prod \
+			vmrestore-$(OSARCH)-prod \
+			vmctl-$(OSARCH)-prod \
+		&& sha256sum vmutils-$(OSARCH)-$(PKG_TAG).tar.gz \
+			vmagent-$(OSARCH)-prod \
+			vmalert-$(OSARCH)-prod \
+			vmauth-$(OSARCH)-prod \
+			vmbackup-$(OSARCH)-prod \
+			vmrestore-$(OSARCH)-prod \
+			vmctl-$(OSARCH)-prod \
+			| sed s/-$(OSARCH)-prod/-prod/ > vmutils-$(OSARCH)-$(PKG_TAG)_checksums.txt
+
+release-vmutils-windows-generic: \
+	vmagent-windows-$(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 +212,7 @@ 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 +224,10 @@ 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
 
@@ -122,8 +255,8 @@ benchmark-pure:
 	GO111MODULE=on CGO_ENABLED=0 go test -mod=vendor -bench=. ./app/...
 
 vendor-update:
-	GO111MODULE=on go get -u ./lib/...
-	GO111MODULE=on go get -u ./app/...
+	GO111MODULE=on go get -u -d ./lib/...
+	GO111MODULE=on go get -u -d ./app/...
 	GO111MODULE=on go mod tidy
 	GO111MODULE=on go mod vendor
 
@@ -133,15 +266,46 @@ app-local:
 app-local-pure:
 	CGO_ENABLED=0 GO111MODULE=on go build $(RACE) -mod=vendor -ldflags "$(GO_BUILDINFO)" -o bin/$(APP_NAME)-pure$(RACE) $(PKG_PREFIX)/app/$(APP_NAME)
 
+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 v1.44.1
+
+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 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

@@ -27,6 +27,12 @@ victoria-metrics-ppc64le-prod:
 victoria-metrics-386-prod:
 	APP_NAME=victoria-metrics $(MAKE) app-via-docker-386
 
+victoria-metrics-darwin-amd64-prod:
+	APP_NAME=victoria-metrics $(MAKE) app-via-docker-darwin-amd64
+
+victoria-metrics-darwin-arm64-prod:
+	APP_NAME=victoria-metrics $(MAKE) app-via-docker-darwin-arm64
+
 package-victoria-metrics:
 	APP_NAME=victoria-metrics $(MAKE) package-via-docker
 
@@ -108,3 +114,10 @@ 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

@@ -2,36 +2,57 @@ package main
 
 import (
 	"flag"
+	"fmt"
 	"net/http"
+	"os"
 	"time"
 
 	"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/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 and https://docs.victoriametrics.com/#downsampling")
+	dryRun = flag.Bool("dryRun", false, "Whether to check only -promscrape.config and then exit. "+
+		"Unknown config entries aren't allowed in -promscrape.config by default. This can be changed with -promscrape.config.strictParse=false command-line flag")
 )
 
 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()
+
+	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()
+	storage.SetDedupInterval(*minScrapeInterval)
+	vmstorage.Init(promql.ResetRollupResultCacheIfNeeded)
 	vmselect.Init()
 	vminsert.Init()
 	startSelfScraper()
@@ -61,6 +82,26 @@ func main() {
 }
 
 func requestHandler(w http.ResponseWriter, r *http.Request) bool {
+	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"},
+			{"config", "-promscrape.config contents"},
+			{"metrics", "available service metrics"},
+			{"flags", "command-line flags"},
+			{"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) {
 		return true
 	}
@@ -72,3 +113,12 @@ 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)
@@ -373,7 +374,7 @@ func checkMetricsResult(got, want []Metric) error {
 		want = removeIfFoundMetrics(r, want)
 	}
 	if len(want) > 0 {
-		return fmt.Errorf("exptected metrics %+v not found in %+v", want, got)
+		return fmt.Errorf("expected metrics %+v not found in %+v", want, got)
 	}
 	return nil
 }

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/self_scraper.go

@@ -85,7 +85,6 @@ func selfScraper(scrapeInterval time.Duration) {
 			mr.Timestamp = currentTimestamp
 			mr.Value = r.Value
 		}
-		logger.Infof("writing %d rows at timestamp %d", len(mrs), currentTimestamp)
 		vmstorage.AddRows(mrs)
 	}
 }

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"], ["{TIME_S}","0.5"]]}
       ]}}
 }

app/victoria-metrics/testdata/graphite/empty-label-match.json

@@ -5,12 +5,12 @@
     "empty_label_match 1 {TIME_S-1m}",
     "empty_label_match;foo=bar 2 {TIME_S-1m}",
     "empty_label_match;foo=baz 3 {TIME_S-1m}"],
-  "query": ["/api/v1/query_range?query=empty_label_match{foo=~'bar|'}&start={TIME_S}&end={TIME_S}&step=60"],
+  "query": ["/api/v1/query_range?query=empty_label_match{foo=~'bar|'}&start={TIME_S-1m}&end={TIME_S}&step=60"],
   "result_query_range": {
     "status":"success",
     "data":{"resultType":"matrix",
       "result":[
-	      {"metric":{"__name__":"empty_label_match"},"values":[["{TIME_S}","1"]]},
-	      {"metric":{"__name__":"empty_label_match","foo":"bar"},"values":[["{TIME_S}","2"]]}
+	      {"metric":{"__name__":"empty_label_match"},"values":[["{TIME_S-1m}","1"],["{TIME_S}","1"]]},
+	      {"metric":{"__name__":"empty_label_match","foo":"bar"},"values":[["{TIME_S-1m}","2"],["{TIME_S}","2"]]}
       ]}}
 }

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/max_lookback_set.json

@@ -16,6 +16,8 @@
 	      ["{TIME_S-120s}","3"],
 	      ["{TIME_S-60s}","2"],
 	      ["{TIME_S-30s}","1"],
-	      ["{TIME_S-20s}","1"]
+	      ["{TIME_S-20s}","1"],
+	      ["{TIME_S-10s}","1"],
+	      ["{TIME_S-0s}","1"]
       ]}]}}
 }

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

@@ -19,6 +19,7 @@
 	      ["{TIME_S-110s}","3"],
 	      ["{TIME_S-100s}","3"],
 	      ["{TIME_S-90s}","3"],
+	      ["{TIME_S-80s}","3"],
 	      ["{TIME_S-60s}","2"],
 	      ["{TIME_S-50s}","2"],
 	      ["{TIME_S-40s}","2"],

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"],["{TIME_S}", "3"]]}
       ]}}
 }

app/victoria-metrics/testdata/graphite/subquery-aggregation.json

@@ -9,6 +9,6 @@
   "query": ["/api/v1/query?query=min%20by%20(item)%20(min_over_time(forms_daily_count[10m:1m]))&time={TIME_S-1m}"],
   "result_query": {
     "status":"success",
-    "data":{"resultType":"vector","result":[{"metric":{"item":"x"},"value":["{TIME_S-1m}","1"]},{"metric":{"item":"y"},"value":["{TIME_S-1m}","3"]}]}
+    "data":{"resultType":"vector","result":[{"metric":{"item":"x"},"value":["{TIME_S-1m}","2"]},{"metric":{"item":"y"},"value":["{TIME_S-1m}","4"]}]}
   }
 }

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

@@ -27,6 +27,15 @@ vmagent-ppc64le-prod:
 vmagent-386-prod:
 	APP_NAME=vmagent $(MAKE) app-via-docker-386
 
+vmagent-darwin-amd64-prod:
+	APP_NAME=vmagent $(MAKE) app-via-docker-darwin-amd64
+
+vmagent-darwin-arm64-prod:
+	APP_NAME=vmagent $(MAKE) app-via-docker-darwin-arm64
+
+vmagent-windows-amd64-prod:
+	APP_NAME=vmagent $(MAKE) app-via-docker-windows-amd64
+
 package-vmagent:
 	APP_NAME=vmagent $(MAKE) package-via-docker
 
@@ -52,25 +61,32 @@ publish-vmagent:
 	APP_NAME=vmagent $(MAKE) publish-via-docker
 
 run-vmagent:
-	mkdir -p vmagent-data
-	DOCKER_OPTS='-v $(shell pwd)/vmagent-data:/vmagent-data' \
+	mkdir -p vmagent-remotewrite-data
+	DOCKER_OPTS='-v $(shell pwd)/vmagent-remotewrite-data:/vmagent-remotewrite-data' \
+	ARGS='-remoteWrite.url=http://localhost:8428/api/v1/write' \
 	APP_NAME=vmagent \
 	$(MAKE) run-via-docker
 
 vmagent-amd64:
-	CGO_ENABLED=1 GOOS=linux GOARCH=amd64 GO111MODULE=on go build -mod=vendor -ldflags "$(GO_BUILDINFO)" -o bin/vmagent-amd64 ./app/vmagent
+	CGO_ENABLED=1 GOARCH=amd64 $(MAKE) vmagent-local-with-goarch
 
 vmagent-arm:
-	CGO_ENABLED=0 GOOS=linux GOARCH=arm GO111MODULE=on go build -mod=vendor -ldflags "$(GO_BUILDINFO)" -o bin/vmagent-arm ./app/vmagent
+	CGO_ENABLED=0 GOARCH=arm $(MAKE) vmagent-local-with-goarch
 
 vmagent-arm64:
-	CGO_ENABLED=0 GOOS=linux GOARCH=arm64 GO111MODULE=on go build -mod=vendor -ldflags "$(GO_BUILDINFO)" -o bin/vmagent-arm64 ./app/vmagent
+	CGO_ENABLED=0 GOARCH=arm64 $(MAKE) vmagent-local-with-goarch
 
 vmagent-ppc64le:
-	CGO_ENABLED=0 GOOS=linux GOARCH=ppc64le GO111MODULE=on go build -mod=vendor -ldflags "$(GO_BUILDINFO)" -o bin/vmagent-ppc64le ./app/vmagent
+	CGO_ENABLED=0 GOARCH=ppc64le $(MAKE) vmagent-local-with-goarch
 
 vmagent-386:
-	CGO_ENABLED=0 GOOS=linux GOARCH=386 GO111MODULE=on go build -mod=vendor -ldflags "$(GO_BUILDINFO)" -o bin/vmagent-386 ./app/vmagent
+	CGO_ENABLED=0 GOARCH=386 $(MAKE) vmagent-local-with-goarch
+
+vmagent-local-with-goarch:
+	APP_NAME=vmagent $(MAKE) app-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

app/vmagent/common/push_ctx.go

@@ -1,10 +1,11 @@
 package common
 
 import (
-	"runtime"
 	"sync"
 
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/cgroup"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
 )
 
 // PushCtx is a context used for populating WriteRequest.
@@ -28,12 +29,7 @@ func (ctx *PushCtx) Reset() {
 	}
 	ctx.WriteRequest.Timeseries = ctx.WriteRequest.Timeseries[:0]
 
-	labels := ctx.Labels
-	for i := range labels {
-		label := &labels[i]
-		label.Name = ""
-		label.Value = ""
-	}
+	promrelabel.CleanLabels(ctx.Labels)
 	ctx.Labels = ctx.Labels[:0]
 
 	ctx.Samples = ctx.Samples[:0]
@@ -67,4 +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/csvimport/request_handler.go

@@ -5,25 +5,35 @@ import (
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/common"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
+	parserCommon "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
 	parser "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/csvimport"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
 	"github.com/VictoriaMetrics/metrics"
 )
 
 var (
-	rowsInserted  = metrics.NewCounter(`vmagent_rows_inserted_total{type="csvimport"}`)
-	rowsPerInsert = metrics.NewHistogram(`vmagent_rows_per_insert{type="csvimport"}`)
+	rowsInserted       = metrics.NewCounter(`vmagent_rows_inserted_total{type="csvimport"}`)
+	rowsTenantInserted = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_rows_total{type="csvimport"}`)
+	rowsPerInsert      = metrics.NewHistogram(`vmagent_rows_per_insert{type="csvimport"}`)
 )
 
 // InsertHandler processes csv data from req.
-func InsertHandler(req *http.Request) error {
+func InsertHandler(at *auth.Token, 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(at, rows, extraLabels)
+		})
 	})
 }
 
-func insertRows(rows []parser.Row) error {
+func insertRows(at *auth.Token, rows []parser.Row, extraLabels []prompbmarshal.Label) error {
 	ctx := common.GetPushCtx()
 	defer common.PutPushCtx(ctx)
 
@@ -44,6 +54,7 @@ func insertRows(rows []parser.Row) error {
 				Value: tag.Value,
 			})
 		}
+		labels = append(labels, extraLabels...)
 		samples = append(samples, prompbmarshal.Sample{
 			Value:     r.Value,
 			Timestamp: r.Timestamp,
@@ -56,8 +67,11 @@ func insertRows(rows []parser.Row) error {
 	ctx.WriteRequest.Timeseries = tssDst
 	ctx.Labels = labels
 	ctx.Samples = samples
-	remotewrite.Push(&ctx.WriteRequest)
+	remotewrite.PushWithAuthToken(at, &ctx.WriteRequest)
 	rowsInserted.Add(len(rows))
+	if at != nil {
+		rowsTenantInserted.Get(at).Add(len(rows))
+	}
 	rowsPerInsert.Update(float64(len(rows)))
 	return nil
 }

app/vmagent/datadog/request_handler.go

@@ -0,0 +1,99 @@
+package datadog
+
+import (
+	"fmt"
+	"net/http"
+	"strings"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/common"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
+	parserCommon "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
+	parser "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadog"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
+	"github.com/VictoriaMetrics/metrics"
+)
+
+var (
+	rowsInserted       = metrics.NewCounter(`vmagent_rows_inserted_total{type="datadog"}`)
+	rowsTenantInserted = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_rows_total{type="datadog"}`)
+	rowsPerInsert      = metrics.NewHistogram(`vmagent_rows_per_insert{type="datadog"}`)
+)
+
+// InsertHandlerForHTTP processes remote write for DataDog POST /api/v1/series request.
+//
+// See https://docs.datadoghq.com/api/latest/metrics/#submit-metrics
+func InsertHandlerForHTTP(at *auth.Token, req *http.Request) error {
+	extraLabels, err := parserCommon.GetExtraLabels(req)
+	if err != nil {
+		return err
+	}
+	return writeconcurrencylimiter.Do(func() error {
+		ce := req.Header.Get("Content-Encoding")
+		return parser.ParseStream(req.Body, ce, func(series []parser.Series) error {
+			return insertRows(at, series, extraLabels)
+		})
+	})
+}
+
+func insertRows(at *auth.Token, series []parser.Series, extraLabels []prompbmarshal.Label) error {
+	ctx := common.GetPushCtx()
+	defer common.PutPushCtx(ctx)
+
+	rowsTotal := 0
+	tssDst := ctx.WriteRequest.Timeseries[:0]
+	labels := ctx.Labels[:0]
+	samples := ctx.Samples[:0]
+	for i := range series {
+		ss := &series[i]
+		rowsTotal += len(ss.Points)
+		labelsLen := len(labels)
+		labels = append(labels, prompbmarshal.Label{
+			Name:  "__name__",
+			Value: ss.Metric,
+		})
+		labels = append(labels, prompbmarshal.Label{
+			Name:  "host",
+			Value: ss.Host,
+		})
+		for _, tag := range ss.Tags {
+			n := strings.IndexByte(tag, ':')
+			if n < 0 {
+				return fmt.Errorf("cannot find ':' in tag %q", tag)
+			}
+			name := tag[:n]
+			value := tag[n+1:]
+			if name == "host" {
+				name = "exported_host"
+			}
+			labels = append(labels, prompbmarshal.Label{
+				Name:  name,
+				Value: value,
+			})
+		}
+		labels = append(labels, extraLabels...)
+		samplesLen := len(samples)
+		for _, pt := range ss.Points {
+			samples = append(samples, prompbmarshal.Sample{
+				Timestamp: pt.Timestamp(),
+				Value:     pt.Value(),
+			})
+		}
+		tssDst = append(tssDst, prompbmarshal.TimeSeries{
+			Labels:  labels[labelsLen:],
+			Samples: samples[samplesLen:],
+		})
+	}
+	ctx.WriteRequest.Timeseries = tssDst
+	ctx.Labels = labels
+	ctx.Samples = samples
+	remotewrite.PushWithAuthToken(at, &ctx.WriteRequest)
+	rowsInserted.Add(rowsTotal)
+	if at != nil {
+		rowsTenantInserted.Get(at).Add(rowsTotal)
+	}
+	rowsPerInsert.Update(float64(rowsTotal))
+	return nil
+}

app/vmagent/influx/request_handler.go

@@ -4,52 +4,67 @@ 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/auth"
 	"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/tenantmetrics"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
 	"github.com/VictoriaMetrics/metrics"
 )
 
 var (
-	measurementFieldSeparator = flag.String("influxMeasurementFieldSeparator", "_", "Separator for '{measurement}{separator}{field_name}' metric name when inserted via Influx line protocol")
-	skipSingleField           = flag.Bool("influxSkipSingleField", false, "Uses '{measurement}' instead of '{measurement}{separator}{field_name}' for metic name if Influx line contains only a single field")
+	measurementFieldSeparator = flag.String("influxMeasurementFieldSeparator", "_", "Separator for '{measurement}{separator}{field_name}' metric name when inserted via InfluxDB line protocol")
+	skipSingleField           = flag.Bool("influxSkipSingleField", false, "Uses '{measurement}' instead of '{measurement}{separator}{field_name}' for metic name if InfluxDB line contains only a single field")
+	skipMeasurement           = flag.Bool("influxSkipMeasurement", false, "Uses '{field_name}' as a metric name while ignoring '{measurement}' and '-influxMeasurementFieldSeparator'")
+	dbLabel                   = flag.String("influxDBLabel", "db", "Default label for the DB name sent over '?db={db_name}' query parameter")
 )
 
 var (
-	rowsInserted  = metrics.NewCounter(`vmagent_rows_inserted_total{type="influx"}`)
-	rowsPerInsert = metrics.NewHistogram(`vmagent_rows_per_insert{type="influx"}`)
+	rowsInserted       = metrics.NewCounter(`vmagent_rows_inserted_total{type="influx"}`)
+	rowsTenantInserted = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_rows_total{type="influx"}`)
+	rowsPerInsert      = metrics.NewHistogram(`vmagent_rows_per_insert{type="influx"}`)
 )
 
 // InsertHandlerForReader processes remote write for influx line protocol.
 //
 // See https://github.com/influxdata/telegraf/tree/master/plugins/inputs/socket_listener/
-func InsertHandlerForReader(r io.Reader) error {
+func InsertHandlerForReader(r io.Reader, isGzipped bool) error {
 	return writeconcurrencylimiter.Do(func() error {
-		return parser.ParseStream(r, false, "", "", insertRows)
+		return parser.ParseStream(r, isGzipped, "", "", func(db string, rows []parser.Row) error {
+			return insertRows(nil, db, rows, nil)
+		})
 	})
 }
 
 // InsertHandlerForHTTP processes remote write for influx line protocol.
 //
 // See https://github.com/influxdata/influxdb/blob/4cbdc197b8117fee648d62e2e5be75c6575352f0/tsdb/README.md
-func InsertHandlerForHTTP(req *http.Request) error {
+func InsertHandlerForHTTP(at *auth.Token, 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(at, db, rows, extraLabels)
+		})
 	})
 }
 
-func insertRows(db string, rows []parser.Row) error {
+func insertRows(at *auth.Token, db string, rows []parser.Row, extraLabels []prompbmarshal.Label) error {
 	ctx := getPushCtx()
 	defer putPushCtx(ctx)
 
@@ -61,26 +76,32 @@ func insertRows(db string, rows []parser.Row) error {
 	buf := ctx.buf[:0]
 	for i := range rows {
 		r := &rows[i]
+		rowsTotal += len(r.Fields)
 		commonLabels = commonLabels[:0]
-		hasDBLabel := false
+		hasDBKey := false
 		for j := range r.Tags {
 			tag := &r.Tags[j]
-			if tag.Key == "db" {
-				hasDBLabel = true
+			if tag.Key == *dbLabel {
+				hasDBKey = true
 			}
 			commonLabels = append(commonLabels, prompbmarshal.Label{
 				Name:  tag.Key,
 				Value: tag.Value,
 			})
 		}
-		if len(db) > 0 && !hasDBLabel {
+		if len(db) > 0 && !hasDBKey {
 			commonLabels = append(commonLabels, prompbmarshal.Label{
-				Name:  "db",
+				Name:  *dbLabel,
 				Value: db,
 			})
 		}
-		ctx.metricGroupBuf = append(ctx.metricGroupBuf[:0], r.Measurement...)
-		skipFieldKey := len(r.Fields) == 1 && *skipSingleField
+		commonLabels = append(commonLabels, extraLabels...)
+		ctx.metricGroupBuf = ctx.metricGroupBuf[:0]
+		if !*skipMeasurement {
+			ctx.metricGroupBuf = append(ctx.metricGroupBuf, r.Measurement...)
+		}
+		// 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...)
 		}
@@ -107,15 +128,17 @@ func insertRows(db string, rows []parser.Row) error {
 				Samples: samples[len(samples)-1:],
 			})
 		}
-		rowsTotal += len(r.Fields)
 	}
 	ctx.buf = buf
 	ctx.ctx.WriteRequest.Timeseries = tssDst
 	ctx.ctx.Labels = labels
 	ctx.ctx.Samples = samples
 	ctx.commonLabels = commonLabels
-	remotewrite.Push(&ctx.ctx.WriteRequest)
+	remotewrite.PushWithAuthToken(at, &ctx.ctx.WriteRequest)
 	rowsInserted.Add(rowsTotal)
+	if at != nil {
+		rowsTenantInserted.Get(at).Add(rowsTotal)
+	}
 	rowsPerInsert.Update(float64(rowsTotal))
 
 	return nil
@@ -131,12 +154,8 @@ type pushCtx struct {
 func (ctx *pushCtx) reset() {
 	ctx.ctx.Reset()
 
-	commonLabels := ctx.commonLabels
-	for i := range commonLabels {
-		label := &commonLabels[i]
-		label.Name = ""
-		label.Value = ""
-	}
+	promrelabel.CleanLabels(ctx.commonLabels)
+	ctx.commonLabels = ctx.commonLabels[:0]
 
 	ctx.metricGroupBuf = ctx.metricGroupBuf[:0]
 	ctx.buf = ctx.buf[:0]
@@ -164,4 +183,4 @@ 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

@@ -3,21 +3,30 @@ package main
 import (
 	"flag"
 	"fmt"
+	"io"
 	"net/http"
+	"os"
 	"strings"
+	"sync/atomic"
 	"time"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/csvimport"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/datadog"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/graphite"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/influx"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/native"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/opentsdb"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/opentsdbhttp"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/prometheusimport"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/promremotewrite"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/vmimport"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/buildinfo"
 	"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"
@@ -25,6 +34,7 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/procutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promscrape"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
 	"github.com/VictoriaMetrics/metrics"
 )
@@ -33,12 +43,17 @@ var (
 	httpListenAddr = flag.String("httpListenAddr", ":8429", "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=''")
-	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")
+	influxListenAddr = flag.String("influxListenAddr", "", "TCP and UDP address to listen for InfluxDB 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")
 	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")
+	configAuthKey          = flag.String("configAuthKey", "", "Authorization key for accessing /config page. It must be passed via authKey query arg")
+	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 . "+
+		"Unknown config entries aren't allowed in -promscrape.config by default. This can be changed by passing -promscrape.config.strictParse=false command-line flag")
 )
 
 var (
@@ -49,15 +64,41 @@ var (
 )
 
 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()
+	remotewrite.InitSecretFlags()
 	buildinfo.Init()
 	logger.Init()
+
+	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 -promscrape.config: %s", err)
+		}
+		logger.Infof("all the configs are ok; exitting with 0 status code")
+		return
+	}
+
 	logger.Infof("starting vmagent at %q...", *httpListenAddr)
 	startTime := time.Now()
 	remotewrite.Init()
+	common.StartUnmarshalWorkers()
 	writeconcurrencylimiter.Init()
 	if len(*influxListenAddr) > 0 {
-		influxServer = influxserver.MustStart(*influxListenAddr, influx.InsertHandlerForReader)
+		influxServer = influxserver.MustStart(*influxListenAddr, func(r io.Reader) error {
+			return influx.InsertHandlerForReader(r, false)
+		})
 	}
 	if len(*graphiteListenAddr) > 0 {
 		graphiteServer = graphiteserver.MustStart(*graphiteListenAddr, graphite.InsertHandler)
@@ -102,70 +143,283 @@ func main() {
 	if len(*opentsdbHTTPListenAddr) > 0 {
 		opentsdbhttpServer.MustStop()
 	}
+	common.StopUnmarshalWorkers()
 	remotewrite.Stop()
 
 	logger.Infof("successfully stopped vmagent in %.3f seconds", time.Since(startTime).Seconds())
 }
 
 func requestHandler(w http.ResponseWriter, r *http.Request) bool {
+	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"},
+			{"config", "-promscrape.config contents"},
+			{"metrics", "available service metrics"},
+			{"flags", "command-line flags"},
+			{"-/reload", "reload configuration"},
+		})
+		return true
+	}
+
 	path := strings.Replace(r.URL.Path, "//", "/", -1)
 	switch path {
 	case "/api/v1/write":
 		prometheusWriteRequests.Inc()
-		if err := promremotewrite.InsertHandler(r); err != nil {
+		if err := promremotewrite.InsertHandler(nil, r); err != nil {
 			prometheusWriteErrors.Inc()
-			httpserver.Errorf(w, "error in %q: %s", r.URL.Path, err)
+			httpserver.Errorf(w, r, "%s", err)
 			return true
 		}
 		w.WriteHeader(http.StatusNoContent)
 		return true
 	case "/api/v1/import":
 		vmimportRequests.Inc()
-		if err := vmimport.InsertHandler(r); err != nil {
+		if err := vmimport.InsertHandler(nil, r); err != nil {
 			vmimportErrors.Inc()
-			httpserver.Errorf(w, "error in %q: %s", r.URL.Path, err)
+			httpserver.Errorf(w, r, "%s", err)
 			return true
 		}
 		w.WriteHeader(http.StatusNoContent)
 		return true
 	case "/api/v1/import/csv":
 		csvimportRequests.Inc()
-		if err := csvimport.InsertHandler(r); err != nil {
+		if err := csvimport.InsertHandler(nil, r); err != nil {
 			csvimportErrors.Inc()
-			httpserver.Errorf(w, "error in %q: %s", r.URL.Path, err)
+			httpserver.Errorf(w, r, "%s", err)
+			return true
+		}
+		w.WriteHeader(http.StatusNoContent)
+		return true
+	case "/api/v1/import/prometheus":
+		prometheusimportRequests.Inc()
+		if err := prometheusimport.InsertHandler(nil, r); err != nil {
+			prometheusimportErrors.Inc()
+			httpserver.Errorf(w, r, "%s", err)
+			return true
+		}
+		w.WriteHeader(http.StatusNoContent)
+		return true
+	case "/api/v1/import/native":
+		nativeimportRequests.Inc()
+		if err := native.InsertHandler(nil, r); err != nil {
+			nativeimportErrors.Inc()
+			httpserver.Errorf(w, r, "%s", err)
 			return true
 		}
 		w.WriteHeader(http.StatusNoContent)
 		return true
 	case "/write", "/api/v2/write":
 		influxWriteRequests.Inc()
-		if err := influx.InsertHandlerForHTTP(r); err != nil {
+		if err := influx.InsertHandlerForHTTP(nil, r); err != nil {
 			influxWriteErrors.Inc()
-			httpserver.Errorf(w, "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 "/datadog/api/v1/series":
+		datadogWriteRequests.Inc()
+		if err := datadog.InsertHandlerForHTTP(nil, r); err != nil {
+			datadogWriteErrors.Inc()
+			httpserver.Errorf(w, r, "%s", err)
+			return true
+		}
+		// See https://docs.datadoghq.com/api/latest/metrics/#submit-metrics
+		w.Header().Set("Content-Type", "application/json")
+		w.WriteHeader(202)
+		fmt.Fprintf(w, `{"status":"ok"}`)
+		return true
+	case "/datadog/api/v1/validate":
+		datadogValidateRequests.Inc()
+		// See https://docs.datadoghq.com/api/latest/authentication/#validate-api-key
+		w.Header().Set("Content-Type", "application/json")
+		fmt.Fprintf(w, `{"valid":true}`)
+		return true
+	case "/datadog/api/v1/check_run":
+		datadogCheckRunRequests.Inc()
+		// See https://docs.datadoghq.com/api/latest/service-checks/#submit-a-service-check
+		w.Header().Set("Content-Type", "application/json")
+		w.WriteHeader(202)
+		fmt.Fprintf(w, `{"status":"ok"}`)
+		return true
+	case "/datadog/intake/":
+		datadogIntakeRequests.Inc()
+		w.Header().Set("Content-Type", "application/json")
+		fmt.Fprintf(w, `{}`)
 		return true
 	case "/targets":
 		promscrapeTargetsRequests.Inc()
-		w.Header().Set("Content-Type", "text/plain")
-		promscrape.WriteHumanReadableTargetsStatus(w)
+		promscrape.WriteHumanReadableTargetsStatus(w, r)
+		return true
+	case "/target_response":
+		promscrapeTargetResponseRequests.Inc()
+		if err := promscrape.WriteTargetResponse(w, r); err != nil {
+			promscrapeTargetResponseErrors.Inc()
+			httpserver.Errorf(w, r, "%s", err)
+			return true
+		}
+		return true
+	case "/config":
+		if *configAuthKey != "" && r.FormValue("authKey") != *configAuthKey {
+			err := &httpserver.ErrorWithStatusCode{
+				Err:        fmt.Errorf("The provided authKey doesn't match -configAuthKey"),
+				StatusCode: http.StatusUnauthorized,
+			}
+			httpserver.Errorf(w, r, "%s", err)
+			return true
+		}
+		promscrapeConfigRequests.Inc()
+		w.Header().Set("Content-Type", "text/plain; charset=utf-8")
+		promscrape.WriteConfigData(w)
+		return true
+	case "/api/v1/targets":
+		promscrapeAPIV1TargetsRequests.Inc()
+		w.Header().Set("Content-Type", "application/json")
+		state := r.FormValue("state")
+		promscrape.WriteAPIV1Targets(w, state)
 		return true
 	case "/-/reload":
 		promscrapeConfigReloadRequests.Inc()
 		procutil.SelfSIGHUP()
 		w.WriteHeader(http.StatusOK)
 		return true
+	case "/ready":
+		if rdy := atomic.LoadInt32(&promscrape.PendingScrapeConfigs); rdy > 0 {
+			errMsg := fmt.Sprintf("waiting for scrapes to init, left: %d", rdy)
+			http.Error(w, errMsg, http.StatusTooEarly)
+		} else {
+			w.Header().Set("Content-Type", "text/plain; charset=utf-8")
+			w.WriteHeader(http.StatusOK)
+			w.Write([]byte("OK"))
+		}
+		return true
+	}
+	if remotewrite.MultitenancyEnabled() {
+		return processMultitenantRequest(w, r, path)
 	}
 	return false
 }
 
+func processMultitenantRequest(w http.ResponseWriter, r *http.Request, path string) bool {
+	p, err := httpserver.ParsePath(path)
+	if err != nil {
+		// Cannot parse multitenant path. Skip it - probably it will be parsed later.
+		return false
+	}
+	if p.Prefix != "insert" {
+		httpserver.Errorf(w, r, `unsupported multitenant prefix: %q; expected "insert"`, p.Prefix)
+		return true
+	}
+	at, err := auth.NewToken(p.AuthToken)
+	if err != nil {
+		httpserver.Errorf(w, r, "cannot obtain auth token: %s", err)
+		return true
+	}
+	switch p.Suffix {
+	case "prometheus/", "prometheus", "prometheus/api/v1/write":
+		prometheusWriteRequests.Inc()
+		if err := promremotewrite.InsertHandler(at, r); err != nil {
+			prometheusWriteErrors.Inc()
+			httpserver.Errorf(w, r, "%s", err)
+			return true
+		}
+		w.WriteHeader(http.StatusNoContent)
+		return true
+	case "prometheus/api/v1/import":
+		vmimportRequests.Inc()
+		if err := vmimport.InsertHandler(at, r); err != nil {
+			vmimportErrors.Inc()
+			httpserver.Errorf(w, r, "%s", err)
+			return true
+		}
+		w.WriteHeader(http.StatusNoContent)
+		return true
+	case "prometheus/api/v1/import/csv":
+		csvimportRequests.Inc()
+		if err := csvimport.InsertHandler(at, r); err != nil {
+			csvimportErrors.Inc()
+			httpserver.Errorf(w, r, "%s", err)
+			return true
+		}
+		w.WriteHeader(http.StatusNoContent)
+		return true
+	case "prometheus/api/v1/import/prometheus":
+		prometheusimportRequests.Inc()
+		if err := prometheusimport.InsertHandler(at, r); err != nil {
+			prometheusimportErrors.Inc()
+			httpserver.Errorf(w, r, "%s", err)
+			return true
+		}
+		w.WriteHeader(http.StatusNoContent)
+		return true
+	case "prometheus/api/v1/import/native":
+		nativeimportRequests.Inc()
+		if err := native.InsertHandler(at, r); err != nil {
+			nativeimportErrors.Inc()
+			httpserver.Errorf(w, r, "%s", err)
+			return true
+		}
+		w.WriteHeader(http.StatusNoContent)
+		return true
+	case "influx/write", "influx/api/v2/write":
+		influxWriteRequests.Inc()
+		if err := influx.InsertHandlerForHTTP(at, r); err != nil {
+			influxWriteErrors.Inc()
+			httpserver.Errorf(w, r, "%s", err)
+			return true
+		}
+		w.WriteHeader(http.StatusNoContent)
+		return true
+	case "influx/query":
+		influxQueryRequests.Inc()
+		influxutils.WriteDatabaseNames(w)
+		return true
+	case "datadog/api/v1/series":
+		datadogWriteRequests.Inc()
+		if err := datadog.InsertHandlerForHTTP(at, r); err != nil {
+			datadogWriteErrors.Inc()
+			httpserver.Errorf(w, r, "%s", err)
+			return true
+		}
+		// See https://docs.datadoghq.com/api/latest/metrics/#submit-metrics
+		w.WriteHeader(202)
+		fmt.Fprintf(w, `{"status":"ok"}`)
+		return true
+	case "datadog/api/v1/validate":
+		datadogValidateRequests.Inc()
+		// See https://docs.datadoghq.com/api/latest/authentication/#validate-api-key
+		w.Header().Set("Content-Type", "application/json")
+		fmt.Fprintf(w, `{"valid":true}`)
+		return true
+	case "datadog/api/v1/check_run":
+		datadogCheckRunRequests.Inc()
+		// See https://docs.datadoghq.com/api/latest/service-checks/#submit-a-service-check
+		w.Header().Set("Content-Type", "application/json")
+		w.WriteHeader(202)
+		fmt.Fprintf(w, `{"status":"ok"}`)
+		return true
+	case "datadog/intake/":
+		datadogIntakeRequests.Inc()
+		w.Header().Set("Content-Type", "application/json")
+		fmt.Fprintf(w, `{}`)
+		return true
+	default:
+		httpserver.Errorf(w, r, "unsupported multitenant path suffix: %q", p.Suffix)
+		return true
+	}
+}
+
 var (
 	prometheusWriteRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/api/v1/write", protocol="promremotewrite"}`)
 	prometheusWriteErrors   = metrics.NewCounter(`vmagent_http_request_errors_total{path="/api/v1/write", protocol="promremotewrite"}`)
@@ -176,12 +430,40 @@ var (
 	csvimportRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/api/v1/import/csv", protocol="csvimport"}`)
 	csvimportErrors   = metrics.NewCounter(`vmagent_http_request_errors_total{path="/api/v1/import/csv", protocol="csvimport"}`)
 
-	influxWriteRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/write", protocol="influx"}`)
-	influxWriteErrors   = metrics.NewCounter(`vmagent_http_request_errors_total{path="/write", protocol="influx"}`)
+	prometheusimportRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/api/v1/import/prometheus", protocol="prometheusimport"}`)
+	prometheusimportErrors   = metrics.NewCounter(`vmagent_http_request_errors_total{path="/api/v1/import/prometheus", protocol="prometheusimport"}`)
 
-	influxQueryRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/query", protocol="influx"}`)
+	nativeimportRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/api/v1/import/native", protocol="nativeimport"}`)
+	nativeimportErrors   = metrics.NewCounter(`vmagent_http_request_errors_total{path="/api/v1/import/native", protocol="nativeimport"}`)
 
-	promscrapeTargetsRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/targets"}`)
+	influxWriteRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/influx/write", protocol="influx"}`)
+	influxWriteErrors   = metrics.NewCounter(`vmagent_http_request_errors_total{path="/influx/write", protocol="influx"}`)
+
+	influxQueryRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/influx/query", protocol="influx"}`)
+
+	datadogWriteRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/datadog/api/v1/series", protocol="datadog"}`)
+	datadogWriteErrors   = metrics.NewCounter(`vmagent_http_request_errors_total{path="/datadog/api/v1/series", protocol="datadog"}`)
+
+	datadogValidateRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/datadog/api/v1/validate", protocol="datadog"}`)
+	datadogCheckRunRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/datadog/api/v1/check_run", protocol="datadog"}`)
+	datadogIntakeRequests   = metrics.NewCounter(`vmagent_http_requests_total{path="/datadog/intake/", protocol="datadog"}`)
+
+	promscrapeTargetsRequests      = metrics.NewCounter(`vmagent_http_requests_total{path="/targets"}`)
+	promscrapeAPIV1TargetsRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/api/v1/targets"}`)
+
+	promscrapeTargetResponseRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/target_response"}`)
+	promscrapeTargetResponseErrors   = metrics.NewCounter(`vmagent_http_request_errors_total{path="/target_response"}`)
+
+	promscrapeConfigRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/config"}`)
 
 	promscrapeConfigReloadRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/-/reload"}`)
 )
+
+func usage() {
+	const s = `
+vmagent collects metrics data via popular data ingestion protocols and routes it to VictoriaMetrics.
+
+See the docs at https://docs.victoriametrics.com/vmagent.html .
+`
+	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/native/request_handler.go

@@ -0,0 +1,91 @@
+package native
+
+import (
+	"net/http"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/common"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
+	parserCommon "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
+	parser "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/native"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
+	"github.com/VictoriaMetrics/metrics"
+)
+
+var (
+	rowsInserted       = metrics.NewCounter(`vmagent_rows_inserted_total{type="native"}`)
+	rowsTenantInserted = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_rows_total{type="native"}`)
+	rowsPerInsert      = metrics.NewHistogram(`vmagent_rows_per_insert{type="native"}`)
+)
+
+// InsertHandler processes `/api/v1/import` request.
+//
+// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/6
+func InsertHandler(at *auth.Token, req *http.Request) error {
+	extraLabels, err := parserCommon.GetExtraLabels(req)
+	if err != nil {
+		return err
+	}
+	return writeconcurrencylimiter.Do(func() error {
+		return parser.ParseStream(req, func(block *parser.Block) error {
+			return insertRows(at, block, extraLabels)
+		})
+	})
+}
+
+func insertRows(at *auth.Token, block *parser.Block, extraLabels []prompbmarshal.Label) error {
+	ctx := common.GetPushCtx()
+	defer common.PutPushCtx(ctx)
+
+	// Update rowsInserted and rowsPerInsert before actual inserting,
+	// since relabeling can prevent from inserting the rows.
+	rowsLen := len(block.Values)
+	rowsInserted.Add(rowsLen)
+	if at != nil {
+		rowsTenantInserted.Get(at).Add(rowsLen)
+	}
+	rowsPerInsert.Update(float64(rowsLen))
+
+	tssDst := ctx.WriteRequest.Timeseries[:0]
+	labels := ctx.Labels[:0]
+	samples := ctx.Samples[:0]
+	mn := &block.MetricName
+	labelsLen := len(labels)
+	labels = append(labels, prompbmarshal.Label{
+		Name:  "__name__",
+		Value: bytesutil.ToUnsafeString(mn.MetricGroup),
+	})
+	for j := range mn.Tags {
+		tag := &mn.Tags[j]
+		labels = append(labels, prompbmarshal.Label{
+			Name:  bytesutil.ToUnsafeString(tag.Key),
+			Value: bytesutil.ToUnsafeString(tag.Value),
+		})
+	}
+	labels = append(labels, extraLabels...)
+	values := block.Values
+	timestamps := block.Timestamps
+	if len(timestamps) != len(values) {
+		logger.Panicf("BUG: len(timestamps)=%d must match len(values)=%d", len(timestamps), len(values))
+	}
+	samplesLen := len(samples)
+	for j, value := range values {
+		samples = append(samples, prompbmarshal.Sample{
+			Value:     value,
+			Timestamp: timestamps[j],
+		})
+	}
+	tssDst = append(tssDst, prompbmarshal.TimeSeries{
+		Labels:  labels[labelsLen:],
+		Samples: samples[samplesLen:],
+	})
+	ctx.WriteRequest.Timeseries = tssDst
+	ctx.Labels = labels
+	ctx.Samples = samples
+	remotewrite.PushWithAuthToken(at, &ctx.WriteRequest)
+	return nil
+}

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

@@ -0,0 +1,92 @@
+package prometheusimport
+
+import (
+	"io"
+	"net/http"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/common"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
+	parserCommon "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
+	parser "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/prometheus"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
+	"github.com/VictoriaMetrics/metrics"
+)
+
+var (
+	rowsInserted       = metrics.NewCounter(`vmagent_rows_inserted_total{type="prometheus"}`)
+	rowsTenantInserted = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_rows_total{type="prometheus"}`)
+	rowsPerInsert      = metrics.NewHistogram(`vmagent_rows_per_insert{type="prometheus"}`)
+)
+
+// InsertHandler processes `/api/v1/import/prometheus` request.
+func InsertHandler(at *auth.Token, req *http.Request) error {
+	extraLabels, err := parserCommon.GetExtraLabels(req)
+	if err != nil {
+		return err
+	}
+	defaultTimestamp, err := parserCommon.GetTimestamp(req)
+	if err != nil {
+		return err
+	}
+	return writeconcurrencylimiter.Do(func() error {
+		isGzipped := req.Header.Get("Content-Encoding") == "gzip"
+		return parser.ParseStream(req.Body, defaultTimestamp, isGzipped, func(rows []parser.Row) error {
+			return insertRows(at, rows, extraLabels)
+		}, nil)
+	})
+}
+
+// InsertHandlerForReader processes metrics from given reader with optional gzip format
+func InsertHandlerForReader(r io.Reader, isGzipped bool) error {
+	return writeconcurrencylimiter.Do(func() error {
+		return parser.ParseStream(r, 0, isGzipped, func(rows []parser.Row) error {
+			return insertRows(nil, rows, nil)
+		}, nil)
+	})
+}
+
+func insertRows(at *auth.Token, rows []parser.Row, extraLabels []prompbmarshal.Label) error {
+	ctx := common.GetPushCtx()
+	defer common.PutPushCtx(ctx)
+
+	tssDst := ctx.WriteRequest.Timeseries[:0]
+	labels := ctx.Labels[:0]
+	samples := ctx.Samples[:0]
+	for i := range rows {
+		r := &rows[i]
+		labelsLen := len(labels)
+		labels = append(labels, prompbmarshal.Label{
+			Name:  "__name__",
+			Value: r.Metric,
+		})
+		for j := range r.Tags {
+			tag := &r.Tags[j]
+			labels = append(labels, prompbmarshal.Label{
+				Name:  tag.Key,
+				Value: tag.Value,
+			})
+		}
+		labels = append(labels, extraLabels...)
+		samples = append(samples, prompbmarshal.Sample{
+			Value:     r.Value,
+			Timestamp: r.Timestamp,
+		})
+		tssDst = append(tssDst, prompbmarshal.TimeSeries{
+			Labels:  labels[labelsLen:],
+			Samples: samples[len(samples)-1:],
+		})
+	}
+	ctx.WriteRequest.Timeseries = tssDst
+	ctx.Labels = labels
+	ctx.Samples = samples
+	remotewrite.PushWithAuthToken(at, &ctx.WriteRequest)
+	rowsInserted.Add(len(rows))
+	if at != nil {
+		rowsTenantInserted.Get(at).Add(len(rows))
+	}
+	rowsPerInsert.Update(float64(len(rows)))
+	return nil
+}

app/vmagent/promremotewrite/request_handler.go

@@ -1,31 +1,51 @@
 package promremotewrite
 
 import (
+	"io"
 	"net/http"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/common"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
 	"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/tenantmetrics"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
 	"github.com/VictoriaMetrics/metrics"
 )
 
 var (
-	rowsInserted  = metrics.NewCounter(`vmagent_rows_inserted_total{type="promremotewrite"}`)
-	rowsPerInsert = metrics.NewHistogram(`vmagent_rows_per_insert{type="promremotewrite"}`)
+	rowsInserted       = metrics.NewCounter(`vmagent_rows_inserted_total{type="promremotewrite"}`)
+	rowsTenantInserted = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_rows_total{type="promremotewrite"}`)
+	rowsPerInsert      = metrics.NewHistogram(`vmagent_rows_per_insert{type="promremotewrite"}`)
 )
 
 // InsertHandler processes remote write for prometheus.
-func InsertHandler(req *http.Request) error {
+func InsertHandler(at *auth.Token, 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.Body, func(tss []prompb.TimeSeries) error {
+			return insertRows(at, tss, extraLabels)
+		})
 	})
 }
 
-func insertRows(timeseries []prompb.TimeSeries) error {
+// InsertHandlerForReader processes metrics from given reader
+func InsertHandlerForReader(at *auth.Token, r io.Reader) error {
+	return writeconcurrencylimiter.Do(func() error {
+		return parser.ParseStream(r, func(tss []prompb.TimeSeries) error {
+			return insertRows(at, tss, nil)
+		})
+	})
+}
+
+func insertRows(at *auth.Token, timeseries []prompb.TimeSeries, extraLabels []prompbmarshal.Label) error {
 	ctx := common.GetPushCtx()
 	defer common.PutPushCtx(ctx)
 
@@ -35,6 +55,7 @@ func insertRows(timeseries []prompb.TimeSeries) error {
 	samples := ctx.Samples[:0]
 	for i := range timeseries {
 		ts := &timeseries[i]
+		rowsTotal += len(ts.Samples)
 		labelsLen := len(labels)
 		for i := range ts.Labels {
 			label := &ts.Labels[i]
@@ -43,6 +64,7 @@ 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]
@@ -55,13 +77,15 @@ func insertRows(timeseries []prompb.TimeSeries) error {
 			Labels:  labels[labelsLen:],
 			Samples: samples[samplesLen:],
 		})
-		rowsTotal += len(ts.Samples)
 	}
 	ctx.WriteRequest.Timeseries = tssDst
 	ctx.Labels = labels
 	ctx.Samples = samples
-	remotewrite.Push(&ctx.WriteRequest)
+	remotewrite.PushWithAuthToken(at, &ctx.WriteRequest)
 	rowsInserted.Add(rowsTotal)
+	if at != nil {
+		rowsTenantInserted.Get(at).Add(rowsTotal)
+	}
 	rowsPerInsert.Update(float64(rowsTotal))
 	return nil
 }

app/vmagent/remotewrite/client.go

@@ -1,10 +1,11 @@
 package remotewrite
 
 import (
-	"crypto/tls"
-	"encoding/base64"
-	"flag"
+	"bytes"
 	"fmt"
+	"io/ioutil"
+	"net/http"
+	"net/url"
 	"strings"
 	"sync"
 	"time"
@@ -13,14 +14,19 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/persistentqueue"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promauth"
-	"github.com/VictoriaMetrics/fasthttp"
+	"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. "+
@@ -34,107 +40,107 @@ 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 {
-	urlLabelValue  string
+	sanitizedURL   string
 	remoteWriteURL string
-	host           string
-	requestURI     string
-	authHeader     string
 	fq             *persistentqueue.FastQueue
-	hc             *fasthttp.HostClient
+	hc             *http.Client
 
+	sendBlock func(block []byte) bool
+	authCfg   *promauth.Config
+
+	rl rateLimiter
+
+	bytesSent       *metrics.Counter
+	blocksSent      *metrics.Counter
 	requestDuration *metrics.Histogram
 	requestsOKCount *metrics.Counter
 	errorsCount     *metrics.Counter
+	packetsDropped  *metrics.Counter
 	retriesCount    *metrics.Counter
+	sendDuration    *metrics.FloatCounter
 
 	wg     sync.WaitGroup
 	stopCh chan struct{}
 }
 
-func newClient(argIdx int, remoteWriteURL, urlLabelValue string, fq *persistentqueue.FastQueue, concurrency int) *client {
-	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
+func newHTTPClient(argIdx int, remoteWriteURL, sanitizedURL string, fq *persistentqueue.FastQueue, concurrency int) *client {
+	authCfg, err := getAuthConfig(argIdx)
+	if err != nil {
+		logger.Panicf("FATAL: cannot initialize auth config: %s", err)
 	}
-	token := bearerToken.GetOptionalArg(argIdx)
-	if len(token) > 0 {
-		if authHeader != "" {
-			logger.Panicf("FATAL: `-remoteWrite.bearerToken`=%q cannot be set when `-remoteWrite.basicAuth.*` flags are set", token)
-		}
-		authHeader = "Bearer " + token
-	}
-
-	readTimeout := *sendTimeout
-	if readTimeout <= 0 {
-		readTimeout = time.Minute
-	}
-	writeTimeout := readTimeout
-	var u fasthttp.URI
-	u.Update(remoteWriteURL)
-	scheme := string(u.Scheme())
-	switch scheme {
-	case "http", "https":
-	default:
-		logger.Panicf("FATAL: unsupported scheme in -remoteWrite.url=%q: %q. It must be http or https", remoteWriteURL, scheme)
-	}
-	host := string(u.Host())
-	if len(host) == 0 {
-		logger.Panicf("FATAL: invalid -remoteWrite.url=%q: host cannot be empty. Make sure the url looks like `http://host:port/path`", remoteWriteURL)
-	}
-	requestURI := string(u.RequestURI())
-	isTLS := scheme == "https"
-	var tlsCfg *tls.Config
-	if isTLS {
-		var err error
-		tlsCfg, err = getTLSConfig(argIdx)
-		if err != nil {
-			logger.Panicf("FATAL: cannot initialize TLS config: %s", err)
-		}
-	}
-	if !strings.Contains(host, ":") {
-		if isTLS {
-			host += ":443"
-		} else {
-			host += ":80"
-		}
-	}
-	maxConns := 2 * concurrency
-	hc := &fasthttp.HostClient{
-		Addr:                host,
-		Name:                "vmagent",
+	tlsCfg := authCfg.NewTLSConfig()
+	tr := &http.Transport{
 		Dial:                statDial,
-		IsTLS:               isTLS,
-		TLSConfig:           tlsCfg,
-		MaxConns:            maxConns,
-		MaxIdleConnDuration: 10 * readTimeout,
-		ReadTimeout:         readTimeout,
-		WriteTimeout:        writeTimeout,
-		MaxResponseBodySize: 1024 * 1024,
+		TLSClientConfig:     tlsCfg,
+		TLSHandshakeTimeout: 5 * time.Second,
+		MaxConnsPerHost:     2 * concurrency,
+		MaxIdleConnsPerHost: 2 * concurrency,
+		IdleConnTimeout:     time.Minute,
+		WriteBufferSize:     64 * 1024,
+	}
+	pURL := proxyURL.GetOptionalArg(argIdx)
+	if len(pURL) > 0 {
+		if !strings.Contains(pURL, "://") {
+			logger.Fatalf("cannot parse -remoteWrite.proxyURL=%q: it must start with `http://`, `https://` or `socks5://`", pURL)
+		}
+		pu, err := url.Parse(pURL)
+		if err != nil {
+			logger.Fatalf("cannot parse -remoteWrite.proxyURL=%q: %s", pURL, err)
+		}
+		tr.Proxy = http.ProxyURL(pu)
 	}
 	c := &client{
-		urlLabelValue:  urlLabelValue,
+		sanitizedURL:   sanitizedURL,
 		remoteWriteURL: remoteWriteURL,
-		host:           host,
-		requestURI:     requestURI,
-		authHeader:     authHeader,
+		authCfg:        authCfg,
 		fq:             fq,
-		hc:             hc,
-		stopCh:         make(chan struct{}),
+		hc: &http.Client{
+			Transport: tr,
+			Timeout:   sendTimeout.GetOptionalArgOrDefault(argIdx, time.Minute),
+		},
+		stopCh: make(chan struct{}),
 	}
-	c.requestDuration = metrics.GetOrCreateHistogram(fmt.Sprintf(`vmagent_remotewrite_duration_seconds{url=%q}`, c.urlLabelValue))
-	c.requestsOKCount = metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_requests_total{url=%q, status_code="2XX"}`, c.urlLabelValue))
-	c.errorsCount = metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_errors_total{url=%q}`, c.urlLabelValue))
-	c.retriesCount = metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_retries_count_total{url=%q}`, c.urlLabelValue))
+	c.sendBlock = c.sendBlockHTTP
+	return c
+}
+
+func (c *client) init(argIdx, concurrency int, sanitizedURL string) {
+	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))
+	c.packetsDropped = metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_packets_dropped_total{url=%q}`, c.sanitizedURL))
+	c.retriesCount = metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_retries_count_total{url=%q}`, c.sanitizedURL))
+	c.sendDuration = metrics.GetOrCreateFloatCounter(fmt.Sprintf(`vmagent_remotewrite_send_duration_seconds_total{url=%q}`, c.sanitizedURL))
 	for i := 0; i < concurrency; i++ {
 		c.wg.Add(1)
 		go func() {
@@ -142,91 +148,125 @@ func newClient(argIdx int, remoteWriteURL, urlLabelValue string, fq *persistentq
 			c.runWorker()
 		}()
 	}
-	logger.Infof("initialized client for -remoteWrite.url=%q", c.remoteWriteURL)
-	return c
+	logger.Infof("initialized client for -remoteWrite.url=%q", c.sanitizedURL)
 }
 
 func (c *client) MustStop() {
 	close(c.stopCh)
 	c.wg.Wait()
-	logger.Infof("stopped client for -remoteWrite.url=%q", c.remoteWriteURL)
+	logger.Infof("stopped client for -remoteWrite.url=%q", c.sanitizedURL)
 }
 
-func getTLSConfig(argIdx int) (*tls.Config, error) {
-	tlsConfig := &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:     promauth.NewSecret(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:     promauth.NewSecret(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),
 	}
-	cfg, err := promauth.NewConfig(".", nil, "", "", tlsConfig)
+
+	authCfg, err := promauth.NewConfig(".", nil, basicAuthCfg, token, tokenFile, oauth2Cfg, tlsCfg)
 	if err != nil {
-		return nil, fmt.Errorf("cannot populate TLS config: %s", 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{}{}
+			startTime := time.Now()
+			ch <- c.sendBlock(block)
+			c.sendDuration.Add(time.Since(startTime).Seconds())
 		}()
 		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.remoteWriteURL, graceDuration.Seconds())
+				// Return unsent block to the queue.
+				c.fq.MustWriteBlock(block)
 			}
 			return
 		}
 	}
 }
 
-func (c *client) sendBlock(block []byte) {
-	req := fasthttp.AcquireRequest()
-	req.SetRequestURI(c.requestURI)
-	req.SetHost(c.host)
-	req.Header.SetMethod("POST")
-	req.Header.Add("Content-Type", "application/x-protobuf")
-	req.Header.Add("Content-Encoding", "snappy")
-	req.Header.Add("X-Prometheus-Remote-Write-Version", "0.1.0")
-	if c.authHeader != "" {
-		req.Header.Set("Authorization", c.authHeader)
-	}
-	req.SetBody(block)
-
+// sendBlockHTTP returns false only if c.stopCh is closed.
+// Otherwise it tries sending the block to remote storage indefinitely.
+func (c *client) sendBlockHTTP(block []byte) bool {
+	c.rl.register(len(block), c.stopCh)
 	retryDuration := time.Second
-	resp := fasthttp.AcquireResponse()
+	retriesCount := 0
+	c.bytesSent.Add(len(block))
+	c.blocksSent.Inc()
 
 again:
-	select {
-	case <-c.stopCh:
-		fasthttp.ReleaseRequest(req)
-		fasthttp.ReleaseResponse(resp)
-		return
-	default:
+	req, err := http.NewRequest("POST", c.remoteWriteURL, bytes.NewBuffer(block))
+	if err != nil {
+		logger.Panicf("BUG: unexpected error from http.NewRequest(%q): %s", c.sanitizedURL, err)
+	}
+	h := req.Header
+	h.Set("User-Agent", "vmagent")
+	h.Set("Content-Type", "application/x-protobuf")
+	h.Set("Content-Encoding", "snappy")
+	h.Set("X-Prometheus-Remote-Write-Version", "0.1.0")
+	if ah := c.authCfg.GetAuthHeader(); ah != "" {
+		req.Header.Set("Authorization", ah)
 	}
 
 	startTime := time.Now()
-	err := doRequestWithPossibleRetry(c.hc, req, resp)
+	resp, err := c.hc.Do(req)
 	c.requestDuration.UpdateDuration(startTime)
 	if err != nil {
 		c.errorsCount.Inc()
@@ -234,41 +274,110 @@ 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",
-			len(block), c.remoteWriteURL, err, retryDuration.Seconds())
-		time.Sleep(retryDuration)
-		c.retriesCount.Inc()
-		goto again
-	}
-	statusCode := resp.StatusCode()
-	if statusCode/100 != 2 {
-		metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_requests_total{url=%q, status_code="%d"}`, c.urlLabelValue, statusCode)).Inc()
-		retryDuration *= 2
-		if retryDuration > time.Minute {
-			retryDuration = time.Minute
+		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 := timerpool.Get(retryDuration)
+		select {
+		case <-c.stopCh:
+			timerpool.Put(t)
+			return false
+		case <-t.C:
+			timerpool.Put(t)
 		}
-		logger.Errorf("unexpected status code received after sending a block with size %d bytes to %q: %d; response body=%q; re-sending the block in %.3f seconds",
-			len(block), c.remoteWriteURL, statusCode, resp.Body(), retryDuration.Seconds())
-		time.Sleep(retryDuration)
 		c.retriesCount.Inc()
 		goto again
 	}
-	c.requestsOKCount.Inc()
+	statusCode := resp.StatusCode
+	if statusCode/100 == 2 {
+		_ = resp.Body.Close()
+		c.requestsOKCount.Inc()
+		return true
+	}
+	metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_requests_total{url=%q, status_code="%d"}`, c.sanitizedURL, statusCode)).Inc()
+	if statusCode == 409 || statusCode == 400 {
+		body, err := ioutil.ReadAll(resp.Body)
+		_ = resp.Body.Close()
+		l := logger.WithThrottler("remoteWriteRejected", 5*time.Second)
+		if err != nil {
+			l.Errorf("sending a block with size %d bytes to %q was rejected (skipping the block): status code %d; "+
+				"failed to read response body: %s",
+				len(block), c.sanitizedURL, statusCode, err)
+		} else {
+			l.Errorf("sending a block with size %d bytes to %q was rejected (skipping the block): status code %d; response body: %s",
+				len(block), c.sanitizedURL, statusCode, string(body))
+		}
+		// Just drop block on 409 and 400 status codes like Prometheus does.
+		// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/873
+		// and https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1149
+		_ = resp.Body.Close()
+		c.packetsDropped.Inc()
+		return true
+	}
 
-	// The block has been successfully sent to the remote storage.
-	fasthttp.ReleaseResponse(resp)
-	fasthttp.ReleaseRequest(req)
+	// Unexpected status code returned
+	retriesCount++
+	retryDuration *= 2
+	if retryDuration > time.Minute {
+		retryDuration = time.Minute
+	}
+	body, err := ioutil.ReadAll(resp.Body)
+	_ = resp.Body.Close()
+	if err != nil {
+		logger.Errorf("cannot read response body from %q during retry #%d: %s", c.sanitizedURL, retriesCount, err)
+	} else {
+		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 := timerpool.Get(retryDuration)
+	select {
+	case <-c.stopCh:
+		timerpool.Put(t)
+		return false
+	case <-t.C:
+		timerpool.Put(t)
+	}
+	c.retriesCount.Inc()
+	goto again
 }
 
-func doRequestWithPossibleRetry(hc *fasthttp.HostClient, req *fasthttp.Request, resp *fasthttp.Response) error {
-	// There is no need in calling DoTimeout, since the timeout must be already set in hc.ReadTimeout.
-	err := hc.Do(req, resp)
-	if err == nil {
-		return nil
-	}
-	if err != fasthttp.ErrConnectionClosed {
-		return err
-	}
-	// Retry request if the server closed the keep-alive connection during the first attempt.
-	return hc.Do(req, resp)
+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

@@ -3,26 +3,27 @@ package remotewrite
 import (
 	"flag"
 	"sync"
+	"sync/atomic"
 	"time"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/decimal"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/fasttime"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/persistentqueue"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
 	"github.com/VictoriaMetrics/metrics"
 	"github.com/golang/snappy"
 )
 
 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")
-	maxUnpackedBlockSize = flag.Int("remoteWrite.maxBlockSize", 32*1024*1024, "The maximum size in bytes of unpacked request to send to remote storage. "+
-		"It shouldn't exceed -maxInsertRequestSize from VictoriaMetrics")
+		"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 block size to send to remote storage. Bigger blocks may improve performance at the cost of the increased memory usage. See also -remoteWrite.maxRowsPerBlock")
+	maxRowsPerBlock      = flag.Int("remoteWrite.maxRowsPerBlock", 10000, "The maximum number of samples to send in each block to remote storage. Higher number may improve performance at the cost of the increased memory usage. See also -remoteWrite.maxBlockSize")
 )
 
-// the maximum number of rows to send per each block.
-const maxRowsPerBlock = 10000
-
 type pendingSeries struct {
 	mu sync.Mutex
 	wr writeRequest
@@ -31,9 +32,11 @@ 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() {
@@ -55,6 +58,10 @@ func (ps *pendingSeries) Push(tss []prompbmarshal.TimeSeries) {
 }
 
 func (ps *pendingSeries) periodicFlusher() {
+	flushSeconds := int64(flushInterval.Seconds())
+	if flushSeconds <= 0 {
+		flushSeconds = 1
+	}
 	ticker := time.NewTicker(*flushInterval)
 	defer ticker.Stop()
 	mustStop := false
@@ -63,7 +70,7 @@ func (ps *pendingSeries) periodicFlusher() {
 		case <-ps.stopCh:
 			mustStop = true
 		case <-ticker.C:
-			if time.Since(ps.wr.lastFlushTime) < *flushInterval/2 {
+			if fasttime.UnixTimestamp()-atomic.LoadUint64(&ps.wr.lastFlushTime) < uint64(flushSeconds) {
 				continue
 			}
 		}
@@ -74,9 +81,19 @@ func (ps *pendingSeries) periodicFlusher() {
 }
 
 type writeRequest struct {
-	wr            prompbmarshal.WriteRequest
-	pushBlock     func(block []byte)
-	lastFlushTime time.Time
+	// Move lastFlushTime to the top of the struct in order to guarantee atomic access on 32-bit architectures.
+	lastFlushTime uint64
+
+	// 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
 
@@ -86,6 +103,8 @@ 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 {
@@ -95,11 +114,7 @@ func (wr *writeRequest) reset() {
 	}
 	wr.tss = wr.tss[:0]
 
-	for i := range wr.labels {
-		label := &wr.labels[i]
-		label.Name = ""
-		label.Value = ""
-	}
+	promrelabel.CleanLabels(wr.labels)
 	wr.labels = wr.labels[:0]
 
 	wr.samples = wr.samples[:0]
@@ -108,18 +123,38 @@ func (wr *writeRequest) reset() {
 
 func (wr *writeRequest) flush() {
 	wr.wr.Timeseries = wr.tss
-	wr.lastFlushTime = time.Now()
+	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
+	maxSamplesPerBlock := *maxRowsPerBlock
+	// Allow up to 10x of labels per each block on average.
+	maxLabelsPerBlock := 10 * maxSamplesPerBlock
 	for i := range src {
 		tssDst = append(tssDst, prompbmarshal.TimeSeries{})
-		dst := &tssDst[len(tssDst)-1]
-		wr.copyTimeSeries(dst, &src[i])
-		if len(wr.tss) >= maxRowsPerBlock {
+		wr.copyTimeSeries(&tssDst[len(tssDst)-1], &src[i])
+		if len(wr.samples) >= maxSamplesPerBlock || len(wr.labels) >= maxLabelsPerBlock {
+			wr.tss = tssDst
 			wr.flush()
 			tssDst = wr.tss
 		}
@@ -144,13 +179,8 @@ func (wr *writeRequest) copyTimeSeries(dst, src *prompbmarshal.TimeSeries) {
 	}
 	dst.Labels = labelsDst[labelsLen:]
 
-	samplesDst = append(samplesDst, prompbmarshal.Sample{})
-	dstSample := &samplesDst[len(samplesDst)-1]
-	if len(src.Samples) != 1 {
-		logger.Panicf("BUG: unexpected number of samples in time series; got %d; want 1", len(src.Samples))
-	}
-	*dstSample = src.Samples[0]
-	dst.Samples = samplesDst[len(samplesDst)-1:]
+	samplesDst = append(samplesDst, src.Samples...)
+	dst.Samples = samplesDst[len(samplesDst)-len(src.Samples):]
 
 	wr.samples = samplesDst
 	wr.labels = labelsDst
@@ -164,7 +194,7 @@ func pushWriteRequest(wr *prompbmarshal.WriteRequest, pushBlock func(block []byt
 	}
 	bb := writeRequestBufPool.Get()
 	bb.B = prompbmarshal.MarshalWriteRequest(bb.B[:0], wr)
-	if len(bb.B) <= *maxUnpackedBlockSize {
+	if len(bb.B) <= maxUnpackedBlockSize.N {
 		zb := snappyBufPool.Get()
 		zb.B = snappy.Encode(zb.B[:cap(zb.B)], bb.B)
 		writeRequestBufPool.Put(bb)

app/vmagent/remotewrite/relabel.go

@@ -2,6 +2,7 @@ package remotewrite
 
 import (
 	"flag"
+	"fmt"
 	"strings"
 	"sync"
 
@@ -13,42 +14,80 @@ 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")
-	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://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config for details")
+		"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. "+
+		"The path can point either to local file or to http url. These entries are applied to all the metrics "+
+		"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. "+
+		"The path can point either to local file or to http 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
-var prcsGlobal []promrelabel.ParsedRelabelConfig
 
-// initRelabelGlobal must be called after parsing command-line flags.
-func initRelabelGlobal() {
-	// Init labelsGlobal
+// CheckRelabelConfigs checks -remoteWrite.relabelConfig and -remoteWrite.urlRelabelConfig.
+func CheckRelabelConfigs() error {
+	_, err := loadRelabelConfigs()
+	return err
+}
+
+func loadRelabelConfigs() (*relabelConfigs, error) {
+	var rcs relabelConfigs
+	if *relabelConfigPathGlobal != "" {
+		global, err := promrelabel.LoadRelabelConfigs(*relabelConfigPathGlobal, *relabelDebugGlobal)
+		if err != nil {
+			return nil, fmt.Errorf("cannot load -remoteWrite.relabelConfig=%q: %w", *relabelConfigPathGlobal, err)
+		}
+		rcs.global = global
+	}
+	if len(*relabelConfigPaths) > (len(*remoteWriteURLs) + len(*remoteWriteMultitenantURLs)) {
+		return nil, fmt.Errorf("too many -remoteWrite.urlRelabelConfig args: %d; it mustn't exceed the number of -remoteWrite.url or -remoteWrite.multitenantURL args: %d",
+			len(*relabelConfigPaths), (len(*remoteWriteURLs) + len(*remoteWriteMultitenantURLs)))
+	}
+	rcs.perURL = make([]*promrelabel.ParsedConfigs, (len(*remoteWriteURLs) + len(*remoteWriteMultitenantURLs)))
+	for i, path := range *relabelConfigPaths {
+		if len(path) == 0 {
+			// Skip empty relabel config.
+			continue
+		}
+		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)
+		}
+		rcs.perURL[i] = prc
+	}
+	return &rcs, nil
+}
+
+type relabelConfigs struct {
+	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.Panicf("FATAL: missing '=' in `-remoteWrite.label`. It must contain label in the form `name=value`; got %q", s)
+			logger.Fatalf("missing '=' in `-remoteWrite.label`. It must contain label in the form `name=value`; got %q", s)
 		}
 		labelsGlobal = append(labelsGlobal, prompbmarshal.Label{
 			Name:  s[:n],
 			Value: s[n+1:],
 		})
 	}
-
-	// Init prcsGlobal
-	prcsGlobal = nil
-	if len(*relabelConfigPathGlobal) > 0 {
-		var err error
-		prcsGlobal, err = promrelabel.LoadRelabelConfigs(*relabelConfigPathGlobal)
-		if err != nil {
-			logger.Panicf("FATAL: cannot load relabel configs from -remoteWrite.relabelConfig=%q: %s", *relabelConfigPathGlobal, err)
-		}
-	}
 }
 
-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
 	}
@@ -68,7 +107,7 @@ 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
@@ -88,12 +127,7 @@ type relabelCtx struct {
 }
 
 func (rctx *relabelCtx) reset() {
-	labels := rctx.labels
-	for i := range labels {
-		label := &labels[i]
-		label.Name = ""
-		label.Value = ""
-	}
+	promrelabel.CleanLabels(rctx.labels)
 	rctx.labels = rctx.labels[:0]
 }
 

app/vmagent/remotewrite/remotewrite.go

@@ -3,15 +3,24 @@ package remotewrite
 import (
 	"flag"
 	"fmt"
+	"net/url"
+	"strconv"
+	"sync"
 	"sync/atomic"
+	"time"
 
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
+	"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/httpserver"
 	"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/VictoriaMetrics/lib/tenantmetrics"
 	"github.com/VictoriaMetrics/metrics"
 	xxhash "github.com/cespare/xxhash/v2"
 )
@@ -19,20 +28,68 @@ import (
 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")
-	relabelConfigPaths = flagutil.NewArray("remoteWrite.urlRelabelConfig", "Optional path to relabel config for the corresponding -remoteWrite.url")
-	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", 1, "The number of concurrent queues to each -remoteWrite.url. Set more queues if a single queue "+
-		"isn't enough for sending high volume of collected data to remote storage")
+		"Pass multiple -remoteWrite.url flags in order to replicate data to multiple remote storage systems. See also -remoteWrite.multitenantURL")
+	remoteWriteMultitenantURLs = flagutil.NewArray("remoteWrite.multitenantURL", "Base path for multitenant remote storage URL to write data to. "+
+		"See https://docs.victoriametrics.com/vmagent.html#multitenancy for details. Example url: http://<vminsert>:8480 . "+
+		"Pass multiple -remoteWrite.multitenantURL flags in order to replicate data to multiple remote storage systems. See also -remoteWrite.url")
+	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 is 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 sensistive auth info")
-	maxPendingBytesPerURL = flag.Int("remoteWrite.maxDiskUsagePerURL", 0, "The maximum file-based buffer size in bytes at -remoteWrite.tmpDataPath "+
+		"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 = 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 https://docs.victoriametrics.com/vmagent.html#cardinality-limiter")
+	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 https://docs.victoriametrics.com/vmagent.html#cardinality-limiter")
 )
 
-var rwctxs []*remoteWriteCtx
+var (
+	// rwctxsDefault contains statically populated entries when -remoteWrite.url is specified.
+	rwctxsDefault []*remoteWriteCtx
+
+	// rwctxsMap contains dynamically populated entries when -remoteWrite.multitenantURL is specified.
+	rwctxsMap     = make(map[tenantmetrics.TenantID][]*remoteWriteCtx)
+	rwctxsMapLock sync.Mutex
+
+	// Data without tenant id is written to defaultAuthToken if -remoteWrite.multitenantURL is specified.
+	defaultAuthToken = &auth.Token{}
+)
+
+// MultitenancyEnabled returns true if -remoteWrite.multitenantURL is specified.
+func MultitenancyEnabled() bool {
+	return len(*remoteWriteMultitenantURLs) > 0
+}
+
+// Contains the current relabelConfigs.
+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 = cgroup.AvailableCPUs() * 16
+
+// InitSecretFlags must be called after flag.Parse and before any logging.
+func InitSecretFlags() {
+	if !*showRemoteWriteURL {
+		// remoteWrite.url can contain authentication codes, so hide it at `/metrics` output.
+		flagutil.RegisterSecretFlag("remoteWrite.url")
+	}
+}
 
 // Init initializes remotewrite.
 //
@@ -40,78 +97,214 @@ var rwctxs []*remoteWriteCtx
 //
 // Stop must be called for graceful shutdown.
 func Init() {
-	if len(*remoteWriteURLs) == 0 {
-		logger.Panicf("FATAL: at least one `-remoteWrite.url` must be set")
+	if len(*remoteWriteURLs) == 0 && len(*remoteWriteMultitenantURLs) == 0 {
+		logger.Fatalf("at least one `-remoteWrite.url` or `-remoteWrite.multitenantURL` command-line flag must be set")
+	}
+	if len(*remoteWriteURLs) > 0 && len(*remoteWriteMultitenantURLs) > 0 {
+		logger.Fatalf("cannot set both `-remoteWrite.url` and `-remoteWrite.multitenantURL` command-line flags")
+	}
+	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
+	}
+	if *queues <= 0 {
+		*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)
+	}
+	allRelabelConfigs.Store(rcs)
+
+	if len(*remoteWriteURLs) > 0 {
+		rwctxsDefault = newRemoteWriteCtxs(nil, *remoteWriteURLs)
 	}
 
-	if !*showRemoteWriteURL {
-		// remoteWrite.url can contain authentication codes, so hide it at `/metrics` output.
-		httpserver.RegisterSecretFlag("remoteWrite.url")
-	}
-	initRelabelGlobal()
+	// Start config reloader.
+	configReloaderWG.Add(1)
+	go func() {
+		defer configReloaderWG.Done()
+		for {
+			select {
+			case <-sighupCh:
+			case <-stopCh:
+				return
+			}
+			logger.Infof("SIGHUP received; reloading relabel configs pointed by -remoteWrite.relabelConfig and -remoteWrite.urlRelabelConfig")
+			rcs, err := loadRelabelConfigs()
+			if err != nil {
+				logger.Errorf("cannot reload relabel configs; preserving the previous configs; error: %s", err)
+				continue
+			}
+			allRelabelConfigs.Store(rcs)
+			logger.Infof("Successfully reloaded relabel configs")
+		}
+	}()
+}
 
-	maxInmemoryBlocks := memory.Allowed() / len(*remoteWriteURLs) / maxRowsPerBlock / 100
-	if maxInmemoryBlocks > 200 {
+func newRemoteWriteCtxs(at *auth.Token, urls []string) []*remoteWriteCtx {
+	if len(urls) == 0 {
+		logger.Panicf("BUG: urls must be non-empty")
+	}
+
+	maxInmemoryBlocks := memory.Allowed() / len(urls) / *maxRowsPerBlock / 100
+	if maxInmemoryBlocks / *queues > 100 {
 		// 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 = 100 * *queues
 	}
 	if maxInmemoryBlocks < 2 {
 		maxInmemoryBlocks = 2
 	}
-	for i, remoteWriteURL := range *remoteWriteURLs {
-		relabelConfigPath := ""
-		if i < len(*relabelConfigPaths) {
-			relabelConfigPath = (*relabelConfigPaths)[i]
+	rwctxs := make([]*remoteWriteCtx, len(urls))
+	for i, remoteWriteURLRaw := range urls {
+		remoteWriteURL, err := url.Parse(remoteWriteURLRaw)
+		if err != nil {
+			logger.Fatalf("invalid -remoteWrite.url=%q: %s", remoteWriteURL, err)
+		}
+		sanitizedURL := fmt.Sprintf("%d:secret-url", i+1)
+		if at != nil {
+			// Construct full remote_write url for the given tenant according to https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html#url-format
+			remoteWriteURL.Path = fmt.Sprintf("%s/insert/%d:%d/prometheus/api/v1/write", remoteWriteURL.Path, at.AccountID, at.ProjectID)
+			sanitizedURL = fmt.Sprintf("%s:%d:%d", sanitizedURL, at.AccountID, at.ProjectID)
 		}
-		urlLabelValue := fmt.Sprintf("secret-url-%d", i+1)
 		if *showRemoteWriteURL {
-			urlLabelValue = remoteWriteURL
+			sanitizedURL = fmt.Sprintf("%d:%s", i+1, remoteWriteURL)
 		}
-		rwctx := newRemoteWriteCtx(i, remoteWriteURL, relabelConfigPath, maxInmemoryBlocks, urlLabelValue)
-		rwctxs = append(rwctxs, rwctx)
+		rwctxs[i] = newRemoteWriteCtx(i, at, remoteWriteURL, maxInmemoryBlocks, sanitizedURL)
 	}
+	return rwctxs
 }
 
+var stopCh = make(chan struct{})
+var configReloaderWG sync.WaitGroup
+
 // Stop stops remotewrite.
 //
 // It is expected that nobody calls Push during and after the call to this func.
 func Stop() {
-	for _, rwctx := range rwctxs {
+	close(stopCh)
+	configReloaderWG.Wait()
+
+	for _, rwctx := range rwctxsDefault {
 		rwctx.MustStop()
 	}
-	rwctxs = nil
+	rwctxsDefault = nil
+
+	// There is no need in locking rwctxsMapLock here, since nobody should call Push during the Stop call.
+	for _, rwctxs := range rwctxsMap {
+		for _, rwctx := range rwctxs {
+			rwctx.MustStop()
+		}
+	}
+	rwctxsMap = nil
+
+	if sl := hourlySeriesLimiter; sl != nil {
+		sl.MustStop()
+	}
+	if sl := dailySeriesLimiter; sl != nil {
+		sl.MustStop()
+	}
 }
 
 // Push sends wr to remote storage systems set via `-remoteWrite.url`.
 //
-// Each timeseries in wr.Timeseries must contain one sample.
-//
-// Note that wr may be modified by Push due to relabeling.
+// Note that wr may be modified by Push due to relabeling and rounding.
 func Push(wr *prompbmarshal.WriteRequest) {
+	PushWithAuthToken(nil, wr)
+}
+
+// PushWithAuthToken sends wr to remote storage systems set via `-remoteWrite.multitenantURL`.
+//
+// Note that wr may be modified by Push due to relabeling and rounding.
+func PushWithAuthToken(at *auth.Token, wr *prompbmarshal.WriteRequest) {
+	if at == nil && len(*remoteWriteMultitenantURLs) > 0 {
+		// Write data to default tenant if at isn't set while -remoteWrite.multitenantURL is set.
+		at = defaultAuthToken
+	}
+	var rwctxs []*remoteWriteCtx
+	if at == nil {
+		rwctxs = rwctxsDefault
+	} else {
+		if len(*remoteWriteMultitenantURLs) == 0 {
+			logger.Panicf("BUG: remoteWriteMultitenantURLs must be non-empty for non-nil at")
+		}
+		rwctxsMapLock.Lock()
+		tenantID := tenantmetrics.TenantID{
+			AccountID: at.AccountID,
+			ProjectID: at.ProjectID,
+		}
+		rwctxs = rwctxsMap[tenantID]
+		if rwctxs == nil {
+			rwctxs = newRemoteWriteCtxs(at, *remoteWriteMultitenantURLs)
+			rwctxsMap[tenantID] = rwctxs
+		}
+		rwctxsMapLock.Unlock()
+	}
+
 	var rctx *relabelCtx
-	if len(prcsGlobal) > 0 || len(labelsGlobal) > 0 {
+	rcs := allRelabelConfigs.Load().(*relabelConfigs)
+	pcsGlobal := rcs.global
+	if pcsGlobal.Len() > 0 || len(labelsGlobal) > 0 {
 		rctx = getRelabelCtx()
 	}
 	tss := wr.Timeseries
+	maxSamplesPerBlock := *maxRowsPerBlock
+	// Allow up to 10x of labels per each block on average.
+	maxLabelsPerBlock := 10 * maxSamplesPerBlock
 	for len(tss) > 0 {
-		// Process big tss in smaller blocks in order to reduce maxmimum memory usage
+		// 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 >= maxSamplesPerBlock || labelsCount >= maxLabelsPerBlock {
+				break
+			}
+		}
 		tssBlock := tss
-		if len(tssBlock) > maxRowsPerBlock {
-			tssBlock = tss[:maxRowsPerBlock]
-			tss = tss[maxRowsPerBlock:]
+		if i < len(tss) {
+			tssBlock = tss[:i]
+			tss = tss[i:]
 		} else {
 			tss = nil
 		}
 		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)
+		pushBlockToRemoteStorages(rwctxs, tssBlock)
 		if rctx != nil {
 			rctx.reset()
 		}
@@ -121,50 +314,160 @@ func Push(wr *prompbmarshal.WriteRequest) {
 	}
 }
 
+func pushBlockToRemoteStorages(rwctxs []*remoteWriteCtx, tssBlock []prompbmarshal.TimeSeries) {
+	if len(tssBlock) == 0 {
+		// Nothing to push
+		return
+	}
+	// Push block to remote storages in parallel in order to reduce the time needed for sending the data to multiple remote storage systems.
+	var wg sync.WaitGroup
+	for _, rwctx := range rwctxs {
+		wg.Add(1)
+		go func(rwctx *remoteWriteCtx) {
+			defer wg.Done()
+			rwctx.Push(tssBlock)
+		}(rwctx)
+	}
+	wg.Wait()
+}
+
+// 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:
+		// Do not use logger.WithThrottler() here, since this will increase CPU usage
+		// because every call to logSkippedSeries will result to a call to labelsToString.
+		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 {
+	idx        int
 	fq         *persistentqueue.FastQueue
 	c          *client
-	prcs       []promrelabel.ParsedRelabelConfig
 	pss        []*pendingSeries
 	pssNextIdx uint64
 
-	tss []prompbmarshal.TimeSeries
-
 	relabelMetricsDropped *metrics.Counter
 }
 
-func newRemoteWriteCtx(argIdx int, remoteWriteURL, relabelConfigPath string, maxInmemoryBlocks int, urlLabelValue string) *remoteWriteCtx {
-	h := xxhash.Sum64([]byte(remoteWriteURL))
-	path := fmt.Sprintf("%s/persistent-queue/%016X", *tmpDataPath, h)
-	fq := persistentqueue.MustOpenFastQueue(path, remoteWriteURL, maxInmemoryBlocks, *maxPendingBytesPerURL)
-	_ = metrics.GetOrCreateGauge(fmt.Sprintf(`vmagent_remotewrite_pending_data_bytes{path=%q, url=%q}`, path, urlLabelValue), func() float64 {
+func newRemoteWriteCtx(argIdx int, at *auth.Token, remoteWriteURL *url.URL, maxInmemoryBlocks int, sanitizedURL string) *remoteWriteCtx {
+	// strip query params, otherwise changing params resets pq
+	pqURL := *remoteWriteURL
+	pqURL.RawQuery = ""
+	pqURL.Fragment = ""
+	h := xxhash.Sum64([]byte(pqURL.String()))
+	queuePath := fmt.Sprintf("%s/persistent-queue/%d_%016X", *tmpDataPath, argIdx+1, h)
+	fq := persistentqueue.MustOpenFastQueue(queuePath, sanitizedURL, maxInmemoryBlocks, maxPendingBytesPerURL.N)
+	_ = metrics.GetOrCreateGauge(fmt.Sprintf(`vmagent_remotewrite_pending_data_bytes{path=%q, url=%q}`, queuePath, sanitizedURL), func() float64 {
 		return float64(fq.GetPendingBytes())
 	})
-	_ = metrics.GetOrCreateGauge(fmt.Sprintf(`vmagent_remotewrite_pending_inmemory_blocks{path=%q, url=%q}`, path, urlLabelValue), func() float64 {
+	_ = metrics.GetOrCreateGauge(fmt.Sprintf(`vmagent_remotewrite_pending_inmemory_blocks{path=%q, url=%q}`, queuePath, sanitizedURL), func() float64 {
 		return float64(fq.GetInmemoryQueueLen())
 	})
-	c := newClient(argIdx, remoteWriteURL, urlLabelValue, fq, *queues)
-	var prcs []promrelabel.ParsedRelabelConfig
-	if len(relabelConfigPath) > 0 {
-		var err error
-		prcs, err = promrelabel.LoadRelabelConfigs(relabelConfigPath)
-		if err != nil {
-			logger.Panicf("FATAL: cannot load relabel configs from -remoteWrite.urlRelabelConfig=%q: %s", relabelConfigPath, err)
-		}
+	var c *client
+	switch remoteWriteURL.Scheme {
+	case "http", "https":
+		c = newHTTPClient(argIdx, remoteWriteURL.String(), sanitizedURL, fq, *queues)
+	default:
+		logger.Fatalf("unsupported scheme: %s for remoteWriteURL: %s, want `http`, `https`", remoteWriteURL.Scheme, sanitizedURL)
 	}
-	pss := make([]*pendingSeries, *queues)
+	c.init(argIdx, *queues, sanitizedURL)
+
+	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{
-		fq:   fq,
-		c:    c,
-		prcs: prcs,
-		pss:  pss,
+		idx: argIdx,
+		fq:  fq,
+		c:   c,
+		pss: pss,
 
-		relabelMetricsDropped: metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_relabel_metrics_dropped_total{path=%q, url=%q}`, path, urlLabelValue)),
+		relabelMetricsDropped: metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_relabel_metrics_dropped_total{path=%q, url=%q}`, queuePath, sanitizedURL)),
 	}
 }
 
@@ -172,35 +475,47 @@ func (rwctx *remoteWriteCtx) MustStop() {
 	for _, ps := range rwctx.pss {
 		ps.MustStop()
 	}
+	rwctx.idx = 0
 	rwctx.pss = nil
-	rwctx.fq.MustClose()
-	rwctx.fq = nil
-	rwctx.prcs = nil
+	rwctx.fq.UnblockAllReaders()
 	rwctx.c.MustStop()
 	rwctx.c = nil
+	rwctx.fq.MustClose()
+	rwctx.fq = nil
 
 	rwctx.relabelMetricsDropped = nil
 }
 
 func (rwctx *remoteWriteCtx) Push(tss []prompbmarshal.TimeSeries) {
 	var rctx *relabelCtx
-	if len(rwctx.prcs) > 0 {
+	var v *[]prompbmarshal.TimeSeries
+	rcs := allRelabelConfigs.Load().(*relabelConfigs)
+	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.
-		// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/467 for details.
-		rwctx.tss = append(rwctx.tss[:0], tss...)
-		tss = rwctx.tss
-		rctx = getRelabelCtx()
+		// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/467
+		// and https://github.com/VictoriaMetrics/VictoriaMetrics/issues/599
+		v = tssRelabelPool.Get().(*[]prompbmarshal.TimeSeries)
+		tss = append(*v, tss...)
 		tssLen := len(tss)
-		tss = rctx.applyRelabeling(tss, nil, rwctx.prcs)
+		tss = rctx.applyRelabeling(tss, nil, pcs)
 		rwctx.relabelMetricsDropped.Add(tssLen - len(tss))
 	}
 	pss := rwctx.pss
 	idx := atomic.AddUint64(&rwctx.pssNextIdx, 1) % uint64(len(pss))
 	pss[idx].Push(tss)
 	if rctx != nil {
+		*v = prompbmarshal.ResetTimeSeries(tss)
+		tssRelabelPool.Put(v)
 		putRelabelCtx(rctx)
-		// Zero rwctx.tss in order to free up GC references.
-		rwctx.tss = prompbmarshal.ResetTimeSeries(rwctx.tss)
 	}
 }
+
+var tssRelabelPool = &sync.Pool{
+	New: func() interface{} {
+		a := []prompbmarshal.TimeSeries{}
+		return &a
+	},
+}

app/vmagent/remotewrite/statconn.go

@@ -3,18 +3,15 @@ package remotewrite
 import (
 	"net"
 	"sync/atomic"
+	"time"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/netutil"
-	"github.com/VictoriaMetrics/fasthttp"
 	"github.com/VictoriaMetrics/metrics"
 )
 
-func statDial(addr string) (conn net.Conn, err error) {
-	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/vmagent/vmimport/request_handler.go

@@ -1,32 +1,54 @@
 package vmimport
 
 import (
+	"io"
 	"net/http"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/common"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
+	parserCommon "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
 	parser "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/vmimport"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
 	"github.com/VictoriaMetrics/metrics"
 )
 
 var (
-	rowsInserted  = metrics.NewCounter(`vmagent_rows_inserted_total{type="vmimport"}`)
-	rowsPerInsert = metrics.NewHistogram(`vmagent_rows_per_insert{type="vmimport"}`)
+	rowsInserted       = metrics.NewCounter(`vmagent_rows_inserted_total{type="vmimport"}`)
+	rowsTenantInserted = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_rows_total{type="vmimport"}`)
+	rowsPerInsert      = metrics.NewHistogram(`vmagent_rows_per_insert{type="vmimport"}`)
 )
 
 // InsertHandler processes `/api/v1/import` request.
 //
 // See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/6
-func InsertHandler(req *http.Request) error {
+func InsertHandler(at *auth.Token, req *http.Request) error {
+	extraLabels, err := parserCommon.GetExtraLabels(req)
+	if err != nil {
+		return err
+	}
 	return writeconcurrencylimiter.Do(func() error {
-		return parser.ParseStream(req, insertRows)
+		isGzipped := req.Header.Get("Content-Encoding") == "gzip"
+		return parser.ParseStream(req.Body, isGzipped, func(rows []parser.Row) error {
+			return insertRows(at, rows, extraLabels)
+		})
 	})
 }
 
-func insertRows(rows []parser.Row) error {
+// InsertHandlerForReader processes metrics from given reader
+func InsertHandlerForReader(r io.Reader, isGzipped bool) error {
+	return writeconcurrencylimiter.Do(func() error {
+		return parser.ParseStream(r, isGzipped, func(rows []parser.Row) error {
+			return insertRows(nil, rows, nil)
+		})
+	})
+}
+
+func insertRows(at *auth.Token, rows []parser.Row, extraLabels []prompbmarshal.Label) error {
 	ctx := common.GetPushCtx()
 	defer common.PutPushCtx(ctx)
 
@@ -36,6 +58,7 @@ func insertRows(rows []parser.Row) error {
 	samples := ctx.Samples[:0]
 	for i := range rows {
 		r := &rows[i]
+		rowsTotal += len(r.Values)
 		labelsLen := len(labels)
 		for j := range r.Tags {
 			tag := &r.Tags[j]
@@ -44,9 +67,12 @@ func insertRows(rows []parser.Row) error {
 				Value: bytesutil.ToUnsafeString(tag.Value),
 			})
 		}
+		labels = append(labels, extraLabels...)
 		values := r.Values
 		timestamps := r.Timestamps
-		_ = timestamps[len(values)-1]
+		if len(timestamps) != len(values) {
+			logger.Panicf("BUG: len(timestamps)=%d must match len(values)=%d", len(timestamps), len(values))
+		}
 		samplesLen := len(samples)
 		for j, value := range values {
 			samples = append(samples, prompbmarshal.Sample{
@@ -58,13 +84,15 @@ func insertRows(rows []parser.Row) error {
 			Labels:  labels[labelsLen:],
 			Samples: samples[samplesLen:],
 		})
-		rowsTotal += len(values)
 	}
 	ctx.WriteRequest.Timeseries = tssDst
 	ctx.Labels = labels
 	ctx.Samples = samples
-	remotewrite.Push(&ctx.WriteRequest)
+	remotewrite.PushWithAuthToken(at, &ctx.WriteRequest)
 	rowsInserted.Add(rowsTotal)
+	if at != nil {
+		rowsTenantInserted.Get(at).Add(rowsTotal)
+	}
 	rowsPerInsert.Update(float64(rowsTotal))
 	return nil
 }

app/vmalert/Makefile

@@ -27,6 +27,15 @@ vmalert-ppc64le-prod:
 vmalert-386-prod:
 	APP_NAME=vmalert $(MAKE) app-via-docker-386
 
+vmalert-darwin-amd64-prod:
+	APP_NAME=vmalert $(MAKE) app-via-docker-darwin-amd64
+
+vmalert-darwin-arm64-prod:
+	APP_NAME=vmalert $(MAKE) app-via-docker-darwin-arm64
+
+vmalert-windows-amd64-prod:
+	APP_NAME=vmalert $(MAKE) app-via-docker-windows-amd64
+
 package-vmalert:
 	APP_NAME=vmalert $(MAKE) package-via-docker
 
@@ -52,30 +61,60 @@ publish-vmalert:
 	APP_NAME=vmalert $(MAKE) publish-via-docker
 
 test-vmalert:
-	go test -race -cover ./app/vmalert
+	go test -v -race -cover ./app/vmalert -loggerLevel=ERROR
+	go test -v -race -cover ./app/vmalert/datasource
+	go test -v -race -cover ./app/vmalert/notifier
+	go test -v -race -cover ./app/vmalert/config
+	go test -v -race -cover ./app/vmalert/remotewrite
 
 run-vmalert: vmalert
-	./bin/vmalert -rule=app/vmalert/testdata/rules0-good.rules \
+	./bin/vmalert -rule=app/vmalert/config/testdata/rules2-good.rules \
 		-datasource.url=http://localhost:8428 \
 		-notifier.url=http://localhost:9093 \
-		-remotewrite.url=http://localhost:8428 \
-		-remoteread.url=http://localhost:8428 \
-		-evaluationInterval=3s
+		-notifier.url=http://127.0.0.1:9093 \
+		-remoteWrite.url=http://localhost:8428 \
+		-remoteRead.url=http://localhost:8428 \
+		-external.label=cluster=east-1 \
+		-external.label=replica=a \
+		-evaluationInterval=3s \
+		-rule.configCheckInterval=10s
+
+run-vmalert-sd: vmalert
+	./bin/vmalert -rule=app/vmalert/config/testdata/rules2-good.rules \
+		-datasource.url=http://localhost:8428 \
+		-remoteWrite.url=http://localhost:8428 \
+		-notifier.config=app/vmalert/notifier/testdata/consul.good.yaml \
+		-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 GOOS=linux GOARCH=amd64 GO111MODULE=on go build -mod=vendor -ldflags "$(GO_BUILDINFO)" -o bin/vmalert-amd64 ./app/vmalert
+	CGO_ENABLED=1 GOARCH=amd64 $(MAKE) vmalert-local-with-goarch
 
 vmalert-arm:
-	CGO_ENABLED=0 GOOS=linux GOARCH=arm GO111MODULE=on go build -mod=vendor -ldflags "$(GO_BUILDINFO)" -o bin/vmalert-arm ./app/vmalert
+	CGO_ENABLED=0 GOARCH=arm $(MAKE) vmalert-local-with-goarch
 
 vmalert-arm64:
-	CGO_ENABLED=0 GOOS=linux GOARCH=arm64 GO111MODULE=on go build -mod=vendor -ldflags "$(GO_BUILDINFO)" -o bin/vmalert-arm64 ./app/vmalert
+	CGO_ENABLED=0 GOARCH=arm64 $(MAKE) vmalert-local-with-goarch
 
 vmalert-ppc64le:
-	CGO_ENABLED=0 GOOS=linux GOARCH=ppc64le GO111MODULE=on go build -mod=vendor -ldflags "$(GO_BUILDINFO)" -o bin/vmalert-ppc64le ./app/vmalert
+	CGO_ENABLED=0 GOARCH=ppc64le $(MAKE) vmalert-local-with-goarch
 
 vmalert-386:
-	CGO_ENABLED=0 GOOS=linux GOARCH=386 GO111MODULE=on go build -mod=vendor -ldflags "$(GO_BUILDINFO)" -o bin/vmalert-386 ./app/vmalert
+	CGO_ENABLED=0 GOARCH=386 $(MAKE) vmalert-local-with-goarch
+
+vmalert-local-with-goarch:
+	APP_NAME=vmalert $(MAKE) app-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

app/vmalert/README.md

@@ -1,21 +1,35 @@
-## VM Alert
+# vmalert
 
-`vmalert` executes a list of given MetricsQL expressions (rules) and
-sends alerts to [Alert Manager](https://github.com/prometheus/alertmanager).   
+`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 `-datasource.url`. For sending alerting notifications
+vmalert relies on [Alertmanager]((https://github.com/prometheus/alertmanager)) configured via `-notifier.url` flag.
+Recording rules results are persisted via [remote write](https://prometheus.io/docs/prometheus/latest/storage/#remote-storage-integrations)
+protocol and require `-remoteWrite.url` to be configured.
+Vmalert 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)
- expressions validation;
+* 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);
+* Integration with [Alertmanager](https://github.com/prometheus/alertmanager) starting from [Alertmanager v0.16.0-aplha](https://github.com/prometheus/alertmanager/releases/tag/v0.16.0-alpha.0);
+* 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.
 
-### TODO:
-* Configuration hot reload.
+## Limitations
+* `vmalert` execute queries against remote datasource which has reliability risks because of the network.
+It is recommended to configure alerts thresholds and rules expressions with the understanding that network 
+requests may fail;
+* by default, rules execution is sequential within one group, but persistence of execution results to remote
+storage is asynchronous. Hence, user shouldn't rely on chaining of recording rules when result of previous
+recording rule is reused in the next one;
 
-### QuickStart
+## QuickStart
 
 To build `vmalert` from sources:
 ```
@@ -23,98 +37,850 @@ git clone https://github.com/VictoriaMetrics/VictoriaMetrics
 cd VictoriaMetrics
 make vmalert
 ```
-The build binary will be placed to `VictoriaMetrics/bin` folder.
+The build binary will be placed in `VictoriaMetrics/bin` folder.
 
 To start using `vmalert` you will need the following things:
-* list of alert rules - PromQL/MetricsQL expressions to execute;
-* datasource address - reachable VictoriaMetrics instance for rules execution;
-* notifier address - reachable Alertmanager instance for processing, 
-aggregating alerts and sending notifications.
+* list of rules - PromQL/MetricsQL expressions to execute;
+* datasource address - reachable MetricsQL endpoint to run queries against;
+* notifier address [optional] - reachable [Alert Manager](https://github.com/prometheus/alertmanager) instance for processing,
+aggregating alerts, and sending notifications. Please note, notifier address also supports Consul Service Discovery via 
+[config file](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/app/vmalert/notifier/config.go).
+* remote write address [optional] - [remote write](https://prometheus.io/docs/prometheus/latest/storage/#remote-storage-integrations)
+  compatible storage to persist rules and alerts state info;
+* remote read address [optional] - MetricsQL compatible datasource to restore alerts state from.
 
 Then configure `vmalert` accordingly:
 ```
-./bin/vmalert -rule=alert.rules \
-		-datasource.url=http://localhost:8428 \
-        -notifier.url=http://localhost:9093
+./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 (required if alerting rules are used)
+    -notifier.url=http://127.0.0.1:9093 \    # AlertManager replica URL
+    -remoteWrite.url=http://localhost:8428 \ # Remote write compatible storage to persist rules and alerts state info (required if recording rules are used)
+    -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
 ```
 
-Example for `.rules` file may be found [here](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/app/vmalert/testdata/rules0-good.rules)
+Note there's a separate `remoteRead.url` to allow writing results of
+alerting/recording rules into a different storage than the initial data that's
+queried. This allows using `vmalert` to aggregate data from a short-term,
+high-frequency, high-cardinality storage into a long-term storage with
+decreased cardinality and a bigger interval between samples.
 
-`vmalert` runs evaluation for every group in a separate goroutine.
-Rules in group evaluated one-by-one sequentially. 
+See the full list of configuration flags in [configuration](#configuration) section.
 
-`vmalert` also runs a web-server (`-httpListenAddr`) for serving metrics and alerts endpoints:
+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 a `group` and every configuration file may contain arbitrary number of groups:
+```yaml
+groups:
+  [ - <rule_group> ]
+```
+
+### Groups
+
+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 = -evaluationInterval flag ]
+
+# 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" type is used.
+[ type: <string> ]
+
+# Warning: DEPRECATED
+# Please use `params` instead:
+#   params:
+#     extra_label: ["job=nodeexporter", "env=prod"]
+extra_filter_labels:
+  [ <labelname>: <labelvalue> ... ]
+
+# Optional list of HTTP URL parameters
+# applied for all rules requests within a group
+# For example:
+#  params:
+#    nocache: ["1"]                # disable caching for vmselect
+#    denyPartialResponse: ["true"] # fail if one or more vmstorage nodes returned an error
+#    extra_label: ["env=dev"]      # apply additional label filter "env=dev" for all requests 
+# see more details at https://docs.victoriametrics.com#prometheus-querying-api-enhancements
+params:
+  [ <string>: [<string>, ...]]
+
+# Optional list of labels added to every rule within a group.
+# It has priority over the external labels.
+# Labels are commonly used for adding environment
+# or tenant-specific tag.
+labels:
+  [ <labelname>: <labelvalue> ... ]
+
+rules:
+  [ - <rule> ... ]
+```
+
+### 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 allow defining alert conditions via `expr` field and to send notifications to
+[Alertmanager](https://github.com/prometheus/alertmanager) if execution result is not empty.
+* [recording](https://prometheus.io/docs/prometheus/latest/configuration/recording_rules/) -
+Recording rules allow defining `expr` which result will be then 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 defining duplicates - rules with the same combination of name, expression, and labels
+within one group.
+
+#### Alerting rules
+
+The syntax for alerting rule is the following:
+```yaml
+# The name of the alert. Must be a valid metric name.
+alert: <string>
+
+# The expression to evaluate. The expression language depends on the type value.
+# By default PromQL/MetricsQL expression is used. If group.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 been 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.
+labels:
+  [ <labelname>: <tmpl_string> ]
+
+# Annotations to add to each alert.
+annotations:
+  [ <labelname>: <tmpl_string> ]
+```
+
+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 expression to evaluate. The expression language depends on the type value.
+# By default MetricsQL expression is used. If group.type="graphite", then the expression
+# must contain valid Graphite expression.
+expr: <string>
+
+# Labels to add or overwrite before storing the result.
+labels:
+  [ <labelname>: <labelvalue> ]
+```
+
+For recording rules to work `-remoteWrite.url` must be specified.
+
+
+### Alerts state on restarts
+
+`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 maybe queried from VM just as any other time series.
+The state is 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
+from configured address by querying time series with name `ALERTS_FOR_STATE`.
+
+Both flags are required for proper state restoration. Restore process may fail if time series are missing
+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.
+
+
+### Multitenancy
+
+There are the following approaches exist 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/products/enterprise/) 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`.
+`vmalert` automatically adds the specified tenant to urls per each recording rule in this case.
+
+If `-clusterMode` is enabled and the `tenant` in a particular group is missing, then the tenant value
+is obtained from `-defaultTenant.prometheus` or `-defaultTenant.graphite` depending on the `type` of the group.
+
+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).
+
+### Topology examples
+
+The following sections are showing how `vmalert` may be used and configured 
+for different scenarios. 
+
+Please note, not all flags in examples are required: 
+* `-remoteWrite.url` and `-remoteRead.url` are optional and are needed only if
+you have recording rules or want to store [alerts state](#alerts-state-on-restarts) on `vmalert` restarts;
+* `-notifier.url` is optional and is needed only if you have alerting rules.
+
+#### Single-node VictoriaMetrics
+
+The simplest configuration where one single-node VM server is used for
+rules execution, storing recording rules results and alerts state.
+
+`vmalert` configuration flags:
+```
+./bin/vmalert -rule=rules.yml  \                    # Path to the file with rules configuration. Supports wildcard
+    -datasource.url=http://victoriametrics:8428 \   # VM-single addr for executing rules expressions
+    -remoteWrite.url=http://victoriametrics:8428 \  # VM-single addr to persist alerts state and recording rules results
+    -remoteRead.url=http://victoriametrics:8428 \   # VM-single addr for restoring alerts state after restart
+    -notifier.url=http://alertmanager:9093          # AlertManager addr to send alerts when they trigger
+```
+
+<img alt="vmalert single" width="500" src="vmalert_single.png">
+
+
+#### Cluster VictoriaMetrics
+
+In [cluster mode](https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html)
+VictoriaMetrics has separate components for writing and reading path:
+`vminsert` and `vmselect` components respectively. `vmselect` is used for executing rules expressions
+and `vminsert` is used to persist recording rules results and alerts state.
+Cluster mode could have multiple `vminsert` and `vmselect` components. 
+
+`vmalert` configuration flags:
+```
+./bin/vmalert -rule=rules.yml  \                                # Path to the file with rules configuration. Supports wildcard
+    -datasource.url=http://vmselect:8481/select/0/prometheus    # vmselect addr for executing rules expressions
+    -remoteWrite.url=http://vminsert:8480/insert/0/prometheuss  # vminsert addr to persist alerts state and recording rules results
+    -remoteRead.url=http://vmselect:8481/select/0/prometheus    # vmselect addr for restoring alerts state after restart
+    -notifier.url=http://alertmanager:9093                      # AlertManager addr to send alerts when they trigger
+```
+
+<img alt="vmalert cluster" src="vmalert_cluster.png">
+
+In case when you want to spread the load on these components - add balancers before them and configure
+`vmalert` with balancer's addresses. Please, see more about VM's cluster architecture
+[here](https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html#architecture-overview).
+
+#### HA vmalert
+
+For HA user can run multiple identically configured `vmalert` instances.
+It means all of them will execute the same rules, write state and results to
+the same destinations, and send alert notifications to multiple configured
+Alertmanagers.
+
+`vmalert` configuration flags:
+```
+./bin/vmalert -rule=rules.yml \                   # Path to the file with rules configuration. Supports wildcard
+    -datasource.url=http://victoriametrics:8428 \   # VM-single addr for executing rules expressions
+    -remoteWrite.url=http://victoriametrics:8428 \  # VM-single addr to persist alerts state and recording rules results
+    -remoteRead.url=http://victoriametrics:8428 \   # VM-single addr for restoring alerts state after restart
+    -notifier.url=http://alertmanager1:9093 \       # Multiple AlertManager addresses to send alerts when they trigger
+    -notifier.url=http://alertmanagerN:9093         # The same alert will be sent to all configured notifiers
+```
+
+<img alt="vmalert ha" width="800px" src="vmalert_ha.png">
+
+To avoid recording rules results and alerts state duplication in VictoriaMetrics server
+don't forget to configure [deduplication](https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html#deduplication).
+
+Alertmanager will automatically deduplicate alerts with identical labels, so ensure that
+all `vmalert`s are having the same config.
+
+Don't forget to configure [cluster mode](https://prometheus.io/docs/alerting/latest/alertmanager/)
+for Alertmanagers for better reliability.
+
+This example uses single-node VM server for the sake of simplicity. 
+Check how to replace it with [cluster VictoriaMetrics](#cluster-victoriametrics) if needed. 
+
+
+#### Downsampling and aggregation via vmalert
+
+The following example shows how to build a topology where `vmalert` will process data from one cluster
+and write results into another. Such clusters may be called as "hot" (low retention,
+high-speed disks, used for operative monitoring) and "cold" (long term retention,
+slower/cheaper disks, low resolution data). With help of `vmalert`, user can setup
+recording rules to process raw data from "hot" cluster (by applying additional transformations
+or reducing resolution) and push results to "cold" cluster.
+
+`vmalert` configuration flags:
+```
+./bin/vmalert -rule=downsampling-rules.yml \                                        # Path to the file with rules configuration. Supports wildcard
+    -datasource.url=http://raw-cluster-vmselect:8481/select/0/prometheus            # vmselect addr for executing recordi ng rules expressions
+    -remoteWrite.url=http://aggregated-cluster-vminsert:8480/insert/0/prometheuss   # vminsert addr to persist recording rules results
+```
+
+<img alt="vmalert multi cluster" src="vmalert_multicluster.png">
+
+Please note, [replay](#rules-backfilling) feature may be used for transforming historical data.
+
+Flags `-remoteRead.url` and `-notifier.url` are omitted since we assume only recording rules are used.
+
+See also [downsampling docs](https://docs.victoriametrics.com/#downsampling).
+
+
+### Web
+
+`vmalert` runs a web-server (`-httpListenAddr`) for serving metrics and alerts endpoints:
+* `http://<vmalert-addr>` - UI;
+* `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.
 
-`vmalert` may be configured with `-remotewrite` flag to write alerts state in form of timeseries
-via remote write protocol. Alerts state will be written as `ALERTS` timeseries. These timeseries
-may be used to recover alerts state on `vmalert` restarts if `-remoteread` is configured.
+
+## 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 the query type.
+
+## Rules backfilling
+
+vmalert supports alerting and recording rules backfilling (aka `replay`). In replay mode vmalert
+can read the same rules configuration as normal, 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 is 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.
+Vmalert automatically disables caching on VictoriaMetrics side by sending `nocache=1` param. It allows
+to prevent cache pollution and unwanted time range boundaries adjustment during backfilling.
+
+#### Recording rules
+
+The result of recording rules `replay` should match with results of normal rules evaluation.
+
+#### Alerting rules
+
+The 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 fewer 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
+## Monitoring
+
+`vmalert` exports various metrics in Prometheus exposition format at `http://vmalert-host:8880/metrics` page.
+We recommend setting up regular scraping of this page either through `vmagent` or by Prometheus so that the exported
+metrics may be analyzed later.
+
+Use the official [Grafana dashboard](https://grafana.com/grafana/dashboards/14950) for `vmalert` overview. Graphs on this dashboard contain useful hints - hover the `i` icon at the top left corner of each graph in order to read it.
+If you have suggestions for improvements or have found a bug - please open an issue on github or add
+a review to the dashboard.
+
+
+## Configuration
+
+### Flags
+
+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:
 ```
-Usage of vmalert:
+  -clusterMode
+    	If clusterMode is enabled, then vmalert automatically adds the tenant specified in config groups to -datasource.url, -remoteWrite.url and -remoteRead.url. See https://docs.victoriametrics.com/vmalert.html#multitenancy
+  -configCheckInterval duration
+    	Interval for checking for changes in '-rule' or '-notifier.config' files. By default the checking is disabled. Send SIGHUP signal in order to force config check for changes.
+  -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.passwordFile string
+    	Optional path to basic auth password to use for -datasource.url
   -datasource.basicAuth.username string
-        Optional basic auth username for -datasource.url
+    	Optional basic auth username for -datasource.url
+  -datasource.bearerToken string
+    	Optional bearer auth token to use for -datasource.url.
+  -datasource.bearerTokenFile string
+    	Optional path to bearer token file to use for -datasource.url.
+  -datasource.lookback duration
+    	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 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
+  -datasource.tlsCertFile string
+    	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
+  -datasource.tlsKeyFile string
+    	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
   -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
+  -defaultTenant.graphite string
+    	Default tenant for Graphite alerting groups. See https://docs.victoriametrics.com/vmalert.html#multitenancy
+  -defaultTenant.prometheus string
+    	Default tenant for Prometheus alerting groups. See https://docs.victoriametrics.com/vmalert.html#multitenancy
+  -disableAlertgroupLabel
+    	Whether to disable adding group's Name as label to generated alerts and time series.
+  -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. See https://docs.victoriametrics.com/#environment-variables for more details
+  -envflag.prefix string
+    	Prefix for environment variables if -envflag.enable is set
+  -eula
+    	By specifying this flag, you confirm that you have an enterprise license and accept the EULA https://victoriametrics.com/assets/VM_EULA.pdf
   -evaluationInterval duration
-        How often to evaluate the rules. Default 1m (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|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 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 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 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 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")
-  -notifier.url string
-        Prometheus alertmanager URL. Required parameter. e.g. http://127.0.0.1:9093
-  -remoteread.basicAuth.password string
-        Optional basic auth password for -remoteread.url
-  -remoteread.basicAuth.username string
-        Optional basic auth username for -remoteread.url
-  -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)
-  -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
-  -remotewrite.basicAuth.password string
-        Optional basic auth password for -remotewrite.url
-  -remotewrite.basicAuth.username string
-        Optional basic auth username for -remotewrite.url
-  -remotewrite.url string
-        Optional URL to Victoria Metrics or VMInsert where to persist alerts state in form of timeseries. E.g. http://127.0.0.1:8428
-  -rule value
-        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.
+    	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, 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
+  -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 must be passed via authKey query arg. It overrides httpAuth.* settings
+  -notifier.basicAuth.password array
+    	Optional basic auth password for -notifier.url
+    	Supports an array of values separated by comma or specified via multiple flags.
+  -notifier.basicAuth.passwordFile array
+    	Optional path to basic auth password file 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 -notifier.url
+    	Supports an array of values separated by comma or specified via multiple flags.
+  -notifier.config string
+    	Path to configuration file for notifiers
+  -notifier.suppressDuplicateTargetErrors
+    	Whether to suppress 'duplicate target' errors during discovery
+  -notifier.tlsCAFile array
+    	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 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 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 an array of values separated by comma or specified via multiple flags.
+  -notifier.url array
+    	Prometheus alertmanager URL, 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 must be passed via authKey query arg. It overrides httpAuth.* settings
+  -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.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)
+  -remoteRead.basicAuth.password string
+    	Optional basic auth password for -remoteRead.url
+  -remoteRead.basicAuth.passwordFile string
+    	Optional path to basic auth password to use for -remoteRead.url
+  -remoteRead.basicAuth.username string
+    	Optional basic auth username for -remoteRead.url
+  -remoteRead.bearerToken string
+    	Optional bearer auth token to use for -remoteRead.url.
+  -remoteRead.bearerTokenFile string
+    	Optional path to bearer token file to use for -remoteRead.url.
+  -remoteRead.disablePathAppend
+    	Whether to disable automatic appending of '/api/v1/query' path to the configured -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)
+  -remoteRead.tlsCAFile string
+    	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
+  -remoteRead.tlsInsecureSkipVerify
+    	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
+  -remoteRead.tlsServerName string
+    	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 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. See also -remoteRead.disablePathAppend
+  -remoteWrite.basicAuth.password string
+    	Optional basic auth password for -remoteWrite.url
+  -remoteWrite.basicAuth.passwordFile string
+    	Optional path to basic auth password to use for -remoteWrite.url
+  -remoteWrite.basicAuth.username string
+    	Optional basic auth username for -remoteWrite.url
+  -remoteWrite.bearerToken string
+    	Optional bearer auth token to use for -remoteWrite.url.
+  -remoteWrite.bearerTokenFile string
+    	Optional path to bearer token file to use for -remoteWrite.url.
+  -remoteWrite.concurrency int
+    	Defines number of writers for concurrent writing into remote querier (default 1)
+  -remoteWrite.disablePathAppend
+    	Whether to disable automatic appending of '/api/v1/write' path to the configured -remoteWrite.url.
+  -remoteWrite.flushInterval duration
+    	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)
+  -remoteWrite.maxQueueSize int
+    	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
+  -remoteWrite.tlsCertFile string
+    	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
+  -remoteWrite.tlsKeyFile string
+    	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
+  -remoteWrite.url string
+    	Optional URL to VictoriaMetrics or vminsert where to persist alerts state and recording rules results in form of timeseries. For example, if -remoteWrite.url=http://127.0.0.1:8428 is specified, then the alerts state will be written to http://127.0.0.1:8428/api/v1/write . See also -remoteWrite.disablePathAppend
+  -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 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. DEPRECATED - see '-configCheckInterval' instead
+  -rule.maxResolveDuration duration
+    	Limits the maximum duration for automatic alert expiration, which is by default equal to 3 evaluation intervals of the parent group.
+  -rule.validateExpressions
+    	Whether to validate rules expressions via MetricsQL engine (default true)
   -rule.validateTemplates
-        Indicates 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
+  -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. The provided certificate file is automatically re-read every second, so it can be dynamically updated
+  -tlsKeyFile string
+    	Path to file with TLS key. Used only if -tls is set. The provided key file is automatically re-read every second, so it can be dynamically updated
+  -version
+    	Show VictoriaMetrics version
 ```
 
-Pass `-help` to `vmalert` in order to see the full list of supported 
-command-line flags with their descriptions.
+### Hot config reload
+`vmalert` supports "hot" config reload via the following methods:
+* send SIGHUP signal to `vmalert` process;
+* send GET request to `/-/reload` endpoint;
+* configure `-configCheckInterval` flag for periodic reload
+on config change.
 
-To reload configuration without `vmalert` restart send SIGHUP signal
-or send GET request to `/-/reload` endpoint.
+### URL params
 
-### Contributing
+To set additional URL params for `datasource.url`, `remoteWrite.url` or `remoteRead.url`
+just add them in address: `-datasource.url=http://localhost:8428?nocache=1`.
+
+To set additional URL params for specific [group of rules](#Groups) modify
+the `params` group:
+```yaml
+groups:
+  - name: TestGroup
+    params:
+      denyPartialResponse: ["true"]
+      extra_label: ["env=dev"]
+```
+Please note, `params` are used only for executing rules expressions (requests to `datasource.url`).
+If there would be a conflict between URL params set in `datasource.url` flag and params in group definition
+the latter will have higher priority.
+
+### Notifier configuration file
+
+Notifier also supports configuration via file specified with flag `notifier.config`:
+```
+./bin/vmalert -rule=app/vmalert/config/testdata/rules.good.rules \
+		-datasource.url=http://localhost:8428 \
+		-notifier.config=app/vmalert/notifier/testdata/consul.good.yaml
+```
+
+The configuration file allows to configure static notifiers or discover notifiers via 
+[Consul](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#consul_sd_config).
+For example:
+```
+static_configs: 
+  - targets:
+      - localhost:9093
+      - localhost:9095
+
+consul_sd_configs:
+  - server: localhost:8500
+    services:
+      - alertmanager
+```
+
+The list of configured or discovered Notifiers can be explored via [UI](#Web).
+
+The configuration file [specification](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/app/vmalert/notifier/config.go)
+is the following:
+```
+# Per-target Notifier timeout when pushing alerts.
+[ timeout: <duration> | default = 10s ]
+
+# Prefix for the HTTP path alerts are pushed to.
+[ path_prefix: <path> | default = / ]
+
+# Configures the protocol scheme used for requests.
+[ scheme: <scheme> | default = http ]
+
+# Sets the `Authorization` header on every request with the
+# configured username and password.
+# password and password_file are mutually exclusive.
+basic_auth:
+  [ username: <string> ]
+  [ password: <secret> ]
+  [ password_file: <string> ]
+
+# Optional `Authorization` header configuration.
+authorization:
+  # Sets the authentication type.
+  [ type: <string> | default: Bearer ]
+  # Sets the credentials. It is mutually exclusive with
+  # `credentials_file`.
+  [ credentials: <secret> ]
+  # Sets the credentials to the credentials read from the configured file.
+  # It is mutually exclusive with `credentials`.
+  [ credentials_file: <filename> ]
+
+# Configures the scrape request's TLS settings.
+# see https://prometheus.io/docs/prometheus/latest/configuration/configuration/#tls_config
+tls_config:
+  [ <tls_config> ]
+
+# List of labeled statically configured Notifiers.
+static_configs:
+  targets:
+    [ - '<host>' ]
+
+# List of Consul service discovery configurations.
+# See https://prometheus.io/docs/prometheus/latest/configuration/configuration/#consul_sd_config
+consul_sd_configs:
+  [ - <consul_sd_config> ... ]
+
+# List of relabel configurations.
+# Supports the same relabeling features as the rest of VictoriaMetrics components.
+# See https://docs.victoriametrics.com/vmagent.html#relabeling
+relabel_configs:
+  [ - <relabel_config> ... ]
+
+```
+
+The configuration file can be [hot-reloaded](#hot-config-reload).
+
+
+## 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
+
+It is recommended using
+[binary releases](https://github.com/VictoriaMetrics/VictoriaMetrics/releases)
+- `vmalert` is located in `vmutils-*` archives there.
+
+
+### Development build
+
+1. [Install Go](https://golang.org/doc/install). The minimum supported version is Go 1.17.
+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
+
+1. [Install docker](https://docs.docker.com/install/).
+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 may run on Raspberry Pi or on [energy-efficient ARM servers](https://blog.cloudflare.com/arm-takes-wing/).
+
+### Development ARM build
+
+1. [Install Go](https://golang.org/doc/install). The minimum supported version is Go 1.17.
+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
+
+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](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

@@ -0,0 +1,531 @@
+package main
+
+import (
+	"context"
+	"fmt"
+	"hash/fnv"
+	"sort"
+	"strconv"
+	"sync"
+	"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"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
+)
+
+// AlertingRule is basic alert entity
+type AlertingRule struct {
+	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
+	// stores list of active alerts
+	alerts map[uint64]*notifier.Alert
+	// stores last moment of time Exec was called
+	lastExecTime time.Time
+	// stores last error that happened in Exec func
+	// resets on every successful Exec
+	// may be used as Health state
+	lastExecError error
+	// stores the number of samples returned during
+	// the last evaluation
+	lastExecSamples int
+
+	metrics *alertingRuleMetrics
+}
+
+type alertingRuleMetrics struct {
+	errors  *utils.Gauge
+	pending *utils.Gauge
+	active  *utils.Gauge
+	samples *utils.Gauge
+}
+
+func newAlertingRule(qb datasource.QuerierBuilder, group *Group, cfg config.Rule) *AlertingRule {
+	ar := &AlertingRule{
+		Type:         group.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:     &group.Type,
+			EvaluationInterval: group.Interval,
+			QueryParams:        group.Params,
+		}),
+		alerts:  make(map[uint64]*notifier.Alert),
+		metrics: &alertingRuleMetrics{},
+	}
+
+	labels := fmt.Sprintf(`alertname=%q, group=%q, id="%d"`, ar.Name, group.Name, ar.ID())
+	ar.metrics.pending = utils.GetOrCreateGauge(fmt.Sprintf(`vmalert_alerts_pending{%s}`, labels),
+		func() float64 {
+			ar.mu.RLock()
+			defer ar.mu.RUnlock()
+			var num int
+			for _, a := range ar.alerts {
+				if a.State == notifier.StatePending {
+					num++
+				}
+			}
+			return float64(num)
+		})
+	ar.metrics.active = utils.GetOrCreateGauge(fmt.Sprintf(`vmalert_alerts_firing{%s}`, labels),
+		func() float64 {
+			ar.mu.RLock()
+			defer ar.mu.RUnlock()
+			var num int
+			for _, a := range ar.alerts {
+				if a.State == notifier.StateFiring {
+					num++
+				}
+			}
+			return float64(num)
+		})
+	ar.metrics.errors = utils.GetOrCreateGauge(fmt.Sprintf(`vmalert_alerting_rules_error{%s}`, labels),
+		func() float64 {
+			ar.mu.RLock()
+			defer ar.mu.RUnlock()
+			if ar.lastExecError == nil {
+				return 0
+			}
+			return 1
+		})
+	ar.metrics.samples = utils.GetOrCreateGauge(fmt.Sprintf(`vmalert_alerting_rules_last_evaluation_samples{%s}`, labels),
+		func() float64 {
+			ar.mu.RLock()
+			defer ar.mu.RUnlock()
+			return float64(ar.lastExecSamples)
+		})
+	return ar
+}
+
+// Close unregisters rule metrics
+func (ar *AlertingRule) Close() {
+	ar.metrics.active.Unregister()
+	ar.metrics.pending.Unregister()
+	ar.metrics.errors.Unregister()
+	ar.metrics.samples.Unregister()
+}
+
+// String implements Stringer interface
+func (ar *AlertingRule) String() string {
+	return ar.Name
+}
+
+// ID returns unique Rule ID
+// within the parent Group.
+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 {
+		// set additional labels to identify group and rule Name
+		if ar.Name != "" {
+			s.SetLabel(alertNameLabel, ar.Name)
+		}
+		if !*disableAlertGroupLabel && ar.GroupName != "" {
+			s.SetLabel(alertGroupNameLabel, ar.GroupName)
+		}
+		// 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{}
+		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
+				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) ([]prompbmarshal.TimeSeries, error) {
+	qMetrics, err := ar.q.Query(ctx, ar.Expr)
+	ar.mu.Lock()
+	defer ar.mu.Unlock()
+
+	ar.lastExecError = err
+	ar.lastExecTime = time.Now()
+	ar.lastExecSamples = len(qMetrics)
+	if err != nil {
+		return nil, fmt.Errorf("failed to execute query %q: %w", ar.Expr, err)
+	}
+
+	for h, a := range ar.alerts {
+		// cleanup inactive alerts from previous Exec
+		if a.State == notifier.StateInactive {
+			delete(ar.alerts, h)
+		}
+	}
+
+	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 {
+		// set additional labels to identify group and rule name
+		if ar.Name != "" {
+			m.SetLabel(alertNameLabel, ar.Name)
+		}
+		if !*disableAlertGroupLabel && ar.GroupName != "" {
+			m.SetLabel(alertGroupNameLabel, ar.GroupName)
+		}
+		// 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
+			// conflicting with the metric labels
+			return nil, fmt.Errorf("labels %v: %w", m.Labels, errDuplicate)
+		}
+		updated[h] = struct{}{}
+		if a, ok := ar.alerts[h]; ok {
+			if a.Value != m.Values[0] {
+				// update Value field with latest value
+				a.Value = m.Values[0]
+				// and re-exec template since Value can be used
+				// in annotations
+				a.Annotations, err = a.ExecTemplate(qFn, ar.Annotations)
+				if err != nil {
+					return nil, err
+				}
+			}
+			continue
+		}
+		a, err := ar.newAlert(m, ar.lastExecTime, qFn)
+		if err != nil {
+			ar.lastExecError = err
+			return nil, fmt.Errorf("failed to create alert: %w", err)
+		}
+		a.ID = h
+		a.State = notifier.StatePending
+		ar.alerts[h] = a
+	}
+
+	for h, a := range ar.alerts {
+		// if alert wasn't updated in this iteration
+		// means it is resolved already
+		if _, ok := updated[h]; !ok {
+			if a.State == notifier.StatePending {
+				// alert was in Pending state - it is not
+				// active anymore
+				delete(ar.alerts, h)
+				continue
+			}
+			a.State = notifier.StateInactive
+			continue
+		}
+		if a.State == notifier.StatePending && time.Since(a.Start) >= ar.For {
+			a.State = notifier.StateFiring
+			alertsFired.Inc()
+		}
+	}
+	return ar.toTimeSeries(ar.lastExecTime.Unix()), nil
+}
+
+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 {
+			continue
+		}
+		ts := ar.alertToTimeSeries(a, timestamp)
+		tss = append(tss, ts...)
+	}
+	return tss
+}
+
+// UpdateWith copies all significant fields.
+// alerts state isn't copied since
+// it should be updated in next 2 Execs
+func (ar *AlertingRule) UpdateWith(r Rule) error {
+	nr, ok := r.(*AlertingRule)
+	if !ok {
+		return fmt.Errorf("BUG: attempt to update alerting rule with wrong type %#v", r)
+	}
+	ar.Expr = nr.Expr
+	ar.For = nr.For
+	ar.Labels = nr.Labels
+	ar.Annotations = nr.Annotations
+	ar.EvalInterval = nr.EvalInterval
+	ar.q = nr.q
+	return nil
+}
+
+// TODO: consider hashing algorithm in VM
+func hash(m datasource.Metric) uint64 {
+	hash := fnv.New64a()
+	labels := m.Labels
+	sort.Slice(labels, func(i, j int) bool {
+		return labels[i].Name < labels[j].Name
+	})
+	for _, l := range labels {
+		// drop __name__ to be consistent with Prometheus alerting
+		if l.Name == "__name__" {
+			continue
+		}
+		hash.Write([]byte(l.Name))
+		hash.Write([]byte(l.Value))
+		hash.Write([]byte("\xff"))
+	}
+	return hash.Sum64()
+}
+
+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.Values[0],
+		Start:   start,
+		Expr:    ar.Expr,
+	}
+	for _, l := range m.Labels {
+		// drop __name__ to be consistent with Prometheus alerting
+		if l.Name == "__name__" {
+			continue
+		}
+		a.Labels[l.Name] = l.Value
+	}
+	var err error
+	a.Annotations, err = a.ExecTemplate(qFn, ar.Annotations)
+	return a, err
+}
+
+// AlertAPI generates APIAlert object from alert by its id(hash)
+func (ar *AlertingRule) AlertAPI(id uint64) *APIAlert {
+	ar.mu.RLock()
+	defer ar.mu.RUnlock()
+	a, ok := ar.alerts[id]
+	if !ok {
+		return nil
+	}
+	return ar.newAlertAPI(*a)
+}
+
+// RuleAPI returns Rule representation in form
+// of APIAlertingRule
+func (ar *AlertingRule) RuleAPI() APIAlertingRule {
+	var lastErr string
+	if ar.lastExecError != nil {
+		lastErr = ar.lastExecError.Error()
+	}
+	return 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(),
+		LastError:   lastErr,
+		LastSamples: ar.lastExecSamples,
+		LastExec:    ar.lastExecTime,
+		Labels:      ar.Labels,
+		Annotations: ar.Annotations,
+	}
+}
+
+// AlertsAPI generates list of APIAlert objects from existing alerts
+func (ar *AlertingRule) AlertsAPI() []*APIAlert {
+	var alerts []*APIAlert
+	ar.mu.RLock()
+	for _, a := range ar.alerts {
+		alerts = append(alerts, ar.newAlertAPI(*a))
+	}
+	ar.mu.RUnlock()
+	return alerts
+}
+
+func (ar *AlertingRule) newAlertAPI(a notifier.Alert) *APIAlert {
+	aa := &APIAlert{
+		// encode as strings to avoid rounding
+		ID:      fmt.Sprintf("%d", a.ID),
+		GroupID: fmt.Sprintf("%d", a.GroupID),
+		RuleID:  fmt.Sprintf("%d", ar.RuleID),
+
+		Name:        a.Name,
+		Expression:  ar.Expr,
+		Labels:      a.Labels,
+		Annotations: a.Annotations,
+		State:       a.State.String(),
+		ActiveAt:    a.Start,
+		Restored:    a.Restored,
+		Value:       strconv.FormatFloat(a.Value, 'f', -1, 32),
+	}
+	if alertURLGeneratorFn != nil {
+		aa.SourceLink = alertURLGeneratorFn(a)
+	}
+	return aa
+}
+
+const (
+	// alertMetricName is the metric name for synthetic alert timeseries.
+	alertMetricName = "ALERTS"
+	// alertForStateMetricName is the metric name for 'for' state of alert.
+	alertForStateMetricName = "ALERTS_FOR_STATE"
+
+	// alertNameLabel is the label name indicating the name of an alert.
+	alertNameLabel = "alertname"
+	// alertStateLabel is the label name indicating the state of an alert.
+	alertStateLabel = "alertstate"
+
+	// alertGroupNameLabel defines the label name attached for generated time series.
+	// attaching this label may be disabled via `-disableAlertgroupLabel` flag.
+	alertGroupNameLabel = "alertgroup"
+)
+
+// alertToTimeSeries converts the given alert with the given timestamp to timeseries
+func (ar *AlertingRule) alertToTimeSeries(a *notifier.Alert, timestamp int64) []prompbmarshal.TimeSeries {
+	var tss []prompbmarshal.TimeSeries
+	tss = append(tss, alertToTimeSeries(a, timestamp))
+	if ar.For > 0 {
+		tss = append(tss, alertForToTimeSeries(a, timestamp))
+	}
+	return tss
+}
+
+func alertToTimeSeries(a *notifier.Alert, timestamp int64) prompbmarshal.TimeSeries {
+	labels := make(map[string]string)
+	for k, v := range a.Labels {
+		labels[k] = v
+	}
+	labels["__name__"] = alertMetricName
+	labels[alertStateLabel] = a.State.String()
+	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(a *notifier.Alert, timestamp int64) prompbmarshal.TimeSeries {
+	labels := make(map[string]string)
+	for k, v := range a.Labels {
+		labels[k] = v
+	}
+	labels["__name__"] = alertForStateMetricName
+	return newTimeSeries([]float64{float64(a.Start.Unix())}, []int64{timestamp}, labels)
+}
+
+// Restore restores the state of active alerts basing on previously written time series.
+// Restore restores only Start field. Field State will be always Pending and supposed
+// to be updated on next Exec, as well as Value field.
+// Only rules with For > 0 will be restored.
+func (ar *AlertingRule) Restore(ctx context.Context, q datasource.Querier, lookback time.Duration, labels map[string]string) error {
+	if q == nil {
+		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 {
+		labelsFilter += fmt.Sprintf(",%s=%q", k, v)
+	}
+
+	// Get the last data point in range via MetricsQL `last_over_time`.
+	// We don't use plain PromQL since Prometheus doesn't support
+	// remote write protocol which is used for state persistence in vmalert.
+	expr := fmt.Sprintf("last_over_time(%s{alertname=%q%s}[%ds])",
+		alertForStateMetricName, ar.Name, labelsFilter, int(lookback.Seconds()))
+	qMetrics, err := q.Query(ctx, expr)
+	if err != nil {
+		return err
+	}
+
+	for _, m := range qMetrics {
+		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)
+		}
+		a.ID = hash(m)
+		a.State = notifier.StatePending
+		a.Restored = true
+		ar.alerts[a.ID] = a
+		logger.Infof("alert %q (%d) restored to state at %v", a.Name, a.ID, a.Start)
+	}
+	return nil
+}

app/vmalert/alerting_test.go

@@ -0,0 +1,795 @@
+package main
+
+import (
+	"context"
+	"errors"
+	"reflect"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
+)
+
+func TestAlertingRule_ToTimeSeries(t *testing.T) {
+	timestamp := time.Now()
+	testCases := []struct {
+		rule  *AlertingRule
+		alert *notifier.Alert
+		expTS []prompbmarshal.TimeSeries
+	}{
+		{
+			newTestAlertingRule("instant", 0),
+			&notifier.Alert{State: notifier.StateFiring},
+			[]prompbmarshal.TimeSeries{
+				newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()}, map[string]string{
+					"__name__":      alertMetricName,
+					alertStateLabel: notifier.StateFiring.String(),
+				}),
+			},
+		},
+		{
+			newTestAlertingRule("instant extra labels", 0),
+			&notifier.Alert{State: notifier.StateFiring, Labels: map[string]string{
+				"job":      "foo",
+				"instance": "bar",
+			}},
+			[]prompbmarshal.TimeSeries{
+				newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()}, map[string]string{
+					"__name__":      alertMetricName,
+					alertStateLabel: notifier.StateFiring.String(),
+					"job":           "foo",
+					"instance":      "bar",
+				}),
+			},
+		},
+		{
+			newTestAlertingRule("instant labels override", 0),
+			&notifier.Alert{State: notifier.StateFiring, Labels: map[string]string{
+				alertStateLabel: "foo",
+				"__name__":      "bar",
+			}},
+			[]prompbmarshal.TimeSeries{
+				newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()}, map[string]string{
+					"__name__":      alertMetricName,
+					alertStateLabel: notifier.StateFiring.String(),
+				}),
+			},
+		},
+		{
+			newTestAlertingRule("for", time.Second),
+			&notifier.Alert{State: notifier.StateFiring, Start: timestamp.Add(time.Second)},
+			[]prompbmarshal.TimeSeries{
+				newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()}, map[string]string{
+					"__name__":      alertMetricName,
+					alertStateLabel: notifier.StateFiring.String(),
+				}),
+				newTimeSeries([]float64{float64(timestamp.Add(time.Second).Unix())},
+					[]int64{timestamp.UnixNano()},
+					map[string]string{
+						"__name__": alertForStateMetricName,
+					}),
+			},
+		},
+		{
+			newTestAlertingRule("for pending", 10*time.Second),
+			&notifier.Alert{State: notifier.StatePending, Start: timestamp.Add(time.Second)},
+			[]prompbmarshal.TimeSeries{
+				newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()}, map[string]string{
+					"__name__":      alertMetricName,
+					alertStateLabel: notifier.StatePending.String(),
+				}),
+				newTimeSeries([]float64{float64(timestamp.Add(time.Second).Unix())},
+					[]int64{timestamp.UnixNano()},
+					map[string]string{
+						"__name__": alertForStateMetricName,
+					}),
+			},
+		},
+	}
+	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.Unix())
+			if err := compareTimeSeries(t, tc.expTS, tss); err != nil {
+				t.Fatalf("timeseries missmatch: %s", err)
+			}
+		})
+	}
+}
+
+func TestAlertingRule_Exec(t *testing.T) {
+	const defaultStep = 5 * time.Millisecond
+	type testAlert struct {
+		labels []string
+		alert  *notifier.Alert
+	}
+	testCases := []struct {
+		rule      *AlertingRule
+		steps     [][]datasource.Metric
+		expAlerts []testAlert
+	}{
+		{
+			newTestAlertingRule("empty", 0),
+			[][]datasource.Metric{},
+			nil,
+		},
+		{
+			newTestAlertingRule("empty labels", 0),
+			[][]datasource.Metric{
+				{datasource.Metric{Values: []float64{1}, Timestamps: []int64{1}}},
+			},
+			[]testAlert{
+				{alert: &notifier.Alert{State: notifier.StateFiring}},
+			},
+		},
+		{
+			newTestAlertingRule("single-firing", 0),
+			[][]datasource.Metric{
+				{metricWithLabels(t, "name", "foo")},
+			},
+			[]testAlert{
+				{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateFiring}},
+			},
+		},
+		{
+			newTestAlertingRule("single-firing=>inactive", 0),
+			[][]datasource.Metric{
+				{metricWithLabels(t, "name", "foo")},
+				{},
+			},
+			[]testAlert{
+				{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateInactive}},
+			},
+		},
+		{
+			newTestAlertingRule("single-firing=>inactive=>firing", 0),
+			[][]datasource.Metric{
+				{metricWithLabels(t, "name", "foo")},
+				{},
+				{metricWithLabels(t, "name", "foo")},
+			},
+			[]testAlert{
+				{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateFiring}},
+			},
+		},
+		{
+			newTestAlertingRule("single-firing=>inactive=>firing=>inactive", 0),
+			[][]datasource.Metric{
+				{metricWithLabels(t, "name", "foo")},
+				{},
+				{metricWithLabels(t, "name", "foo")},
+				{},
+			},
+			[]testAlert{
+				{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateInactive}},
+			},
+		},
+		{
+			newTestAlertingRule("single-firing=>inactive=>firing=>inactive=>empty", 0),
+			[][]datasource.Metric{
+				{metricWithLabels(t, "name", "foo")},
+				{},
+				{metricWithLabels(t, "name", "foo")},
+				{},
+				{},
+			},
+			nil,
+		},
+		{
+			newTestAlertingRule("single-firing=>inactive=>firing=>inactive=>empty=>firing", 0),
+			[][]datasource.Metric{
+				{metricWithLabels(t, "name", "foo")},
+				{},
+				{metricWithLabels(t, "name", "foo")},
+				{},
+				{},
+				{metricWithLabels(t, "name", "foo")},
+			},
+			[]testAlert{
+				{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateFiring}},
+			},
+		},
+		{
+			newTestAlertingRule("multiple-firing", 0),
+			[][]datasource.Metric{
+				{
+					metricWithLabels(t, "name", "foo"),
+					metricWithLabels(t, "name", "foo1"),
+					metricWithLabels(t, "name", "foo2"),
+				},
+			},
+			[]testAlert{
+				{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateFiring}},
+				{labels: []string{"name", "foo1"}, alert: &notifier.Alert{State: notifier.StateFiring}},
+				{labels: []string{"name", "foo2"}, alert: &notifier.Alert{State: notifier.StateFiring}},
+			},
+		},
+		{
+			newTestAlertingRule("multiple-steps-firing", 0),
+			[][]datasource.Metric{
+				{metricWithLabels(t, "name", "foo")},
+				{metricWithLabels(t, "name", "foo1")},
+				{metricWithLabels(t, "name", "foo2")},
+			},
+			// 1: fire first alert
+			// 2: fire second alert, set first inactive
+			// 3: fire third alert, set second inactive, delete first one
+			[]testAlert{
+				{labels: []string{"name", "foo1"}, alert: &notifier.Alert{State: notifier.StateInactive}},
+				{labels: []string{"name", "foo2"}, alert: &notifier.Alert{State: notifier.StateFiring}},
+			},
+		},
+		{
+			newTestAlertingRule("for-pending", time.Minute),
+			[][]datasource.Metric{
+				{metricWithLabels(t, "name", "foo")},
+			},
+			[]testAlert{
+				{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StatePending}},
+			},
+		},
+		{
+			newTestAlertingRule("for-fired", defaultStep),
+			[][]datasource.Metric{
+				{metricWithLabels(t, "name", "foo")},
+				{metricWithLabels(t, "name", "foo")},
+			},
+			[]testAlert{
+				{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateFiring}},
+			},
+		},
+		{
+			newTestAlertingRule("for-pending=>empty", time.Second),
+			[][]datasource.Metric{
+				{metricWithLabels(t, "name", "foo")},
+				{metricWithLabels(t, "name", "foo")},
+				// empty step to reset and delete pending alerts
+				{},
+			},
+			nil,
+		},
+		{
+			newTestAlertingRule("for-pending=>firing=>inactive", defaultStep),
+			[][]datasource.Metric{
+				{metricWithLabels(t, "name", "foo")},
+				{metricWithLabels(t, "name", "foo")},
+				// empty step to reset pending alerts
+				{},
+			},
+			[]testAlert{
+				{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateInactive}},
+			},
+		},
+		{
+			newTestAlertingRule("for-pending=>firing=>inactive=>pending", defaultStep),
+			[][]datasource.Metric{
+				{metricWithLabels(t, "name", "foo")},
+				{metricWithLabels(t, "name", "foo")},
+				// empty step to reset pending alerts
+				{},
+				{metricWithLabels(t, "name", "foo")},
+			},
+			[]testAlert{
+				{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StatePending}},
+			},
+		},
+		{
+			newTestAlertingRule("for-pending=>firing=>inactive=>pending=>firing", defaultStep),
+			[][]datasource.Metric{
+				{metricWithLabels(t, "name", "foo")},
+				{metricWithLabels(t, "name", "foo")},
+				// empty step to reset pending alerts
+				{},
+				{metricWithLabels(t, "name", "foo")},
+				{metricWithLabels(t, "name", "foo")},
+			},
+			[]testAlert{
+				{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateFiring}},
+			},
+		},
+	}
+	fakeGroup := Group{Name: "TestRule_Exec"}
+	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()); err != nil {
+					t.Fatalf("unexpected err: %s", err)
+				}
+				// artificial delay between applying steps
+				time.Sleep(defaultStep)
+			}
+			if len(tc.rule.alerts) != len(tc.expAlerts) {
+				t.Fatalf("expected %d alerts; got %d", len(tc.expAlerts), len(tc.rule.alerts))
+			}
+			expAlerts := make(map[uint64]*notifier.Alert)
+			for _, ta := range tc.expAlerts {
+				labels := ta.labels
+				labels = append(labels, alertNameLabel)
+				labels = append(labels, tc.rule.Name)
+				h := hash(metricWithLabels(t, labels...))
+				expAlerts[h] = ta.alert
+			}
+			for key, exp := range expAlerts {
+				got, ok := tc.rule.alerts[key]
+				if !ok {
+					t.Fatalf("expected to have key %d", key)
+				}
+				if got.State != exp.State {
+					t.Fatalf("expected state %d; got %d", exp.State, got.State)
+				}
+			}
+		})
+	}
+}
+
+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 {
+					a := tc.expAlerts[j]
+					if a.Labels == nil {
+						a.Labels = make(map[string]string)
+					}
+					a.Labels[alertNameLabel] = tc.rule.Name
+					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
+		metrics   []datasource.Metric
+		expAlerts map[uint64]*notifier.Alert
+	}{
+		{
+			newTestRuleWithLabels("no extra labels"),
+			[]datasource.Metric{
+				metricWithValueAndLabels(t, float64(time.Now().Truncate(time.Hour).Unix()),
+					"__name__", alertForStateMetricName,
+				),
+			},
+			map[uint64]*notifier.Alert{
+				hash(datasource.Metric{}): {State: notifier.StatePending,
+					Start: time.Now().Truncate(time.Hour)},
+			},
+		},
+		{
+			newTestRuleWithLabels("metric labels"),
+			[]datasource.Metric{
+				metricWithValueAndLabels(t, float64(time.Now().Truncate(time.Hour).Unix()),
+					"__name__", alertForStateMetricName,
+					alertNameLabel, "metric labels",
+					alertGroupNameLabel, "groupID",
+					"foo", "bar",
+					"namespace", "baz",
+				),
+			},
+			map[uint64]*notifier.Alert{
+				hash(metricWithLabels(t,
+					alertNameLabel, "metric labels",
+					alertGroupNameLabel, "groupID",
+					"foo", "bar",
+					"namespace", "baz",
+				)): {State: notifier.StatePending,
+					Start: time.Now().Truncate(time.Hour)},
+			},
+		},
+		{
+			newTestRuleWithLabels("rule labels", "source", "vm"),
+			[]datasource.Metric{
+				metricWithValueAndLabels(t, float64(time.Now().Truncate(time.Hour).Unix()),
+					"__name__", alertForStateMetricName,
+					"foo", "bar",
+					"namespace", "baz",
+					// extra labels set by rule
+					"source", "vm",
+				),
+			},
+			map[uint64]*notifier.Alert{
+				hash(metricWithLabels(t,
+					"foo", "bar",
+					"namespace", "baz",
+					"source", "vm",
+				)): {State: notifier.StatePending,
+					Start: time.Now().Truncate(time.Hour)},
+			},
+		},
+		{
+			newTestRuleWithLabels("multiple alerts"),
+			[]datasource.Metric{
+				metricWithValueAndLabels(t, float64(time.Now().Truncate(time.Hour).Unix()),
+					"__name__", alertForStateMetricName,
+					"host", "localhost-1",
+				),
+				metricWithValueAndLabels(t, float64(time.Now().Truncate(2*time.Hour).Unix()),
+					"__name__", alertForStateMetricName,
+					"host", "localhost-2",
+				),
+				metricWithValueAndLabels(t, float64(time.Now().Truncate(3*time.Hour).Unix()),
+					"__name__", alertForStateMetricName,
+					"host", "localhost-3",
+				),
+			},
+			map[uint64]*notifier.Alert{
+				hash(metricWithLabels(t, "host", "localhost-1")): {State: notifier.StatePending,
+					Start: time.Now().Truncate(time.Hour)},
+				hash(metricWithLabels(t, "host", "localhost-2")): {State: notifier.StatePending,
+					Start: time.Now().Truncate(2 * time.Hour)},
+				hash(metricWithLabels(t, "host", "localhost-3")): {State: notifier.StatePending,
+					Start: time.Now().Truncate(3 * time.Hour)},
+			},
+		},
+	}
+	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.Restore(context.TODO(), fq, time.Hour, nil); err != nil {
+				t.Fatalf("unexpected err: %s", err)
+			}
+			if len(tc.rule.alerts) != len(tc.expAlerts) {
+				t.Fatalf("expected %d alerts; got %d", len(tc.expAlerts), len(tc.rule.alerts))
+			}
+			for key, exp := range tc.expAlerts {
+				got, ok := tc.rule.alerts[key]
+				if !ok {
+					t.Fatalf("expected to have key %d", key)
+				}
+				if got.State != exp.State {
+					t.Fatalf("expected state %d; got %d", exp.State, got.State)
+				}
+				if got.Start != exp.Start {
+					t.Fatalf("expected Start %v; got %v", exp.Start, got.Start)
+				}
+			}
+		})
+	}
+}
+
+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())
+	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())
+	if !errors.Is(err, errDuplicate) {
+		t.Fatalf("expected to have %s error; got %s", errDuplicate, err)
+	}
+
+	fq.reset()
+
+	expErr := "connection reset by peer"
+	fq.setErr(errors.New(expErr))
+	_, err = ar.Exec(context.TODO())
+	if err == nil {
+		t.Fatalf("expected to get err; got nil")
+	}
+	if !strings.Contains(err.Error(), expErr) {
+		t.Fatalf("expected to get err %q; got %q insterad", expErr, err)
+	}
+}
+
+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, alertNameLabel, "common", "region", "east", "instance", "foo")): {
+					Annotations: map[string]string{},
+					Labels: map[string]string{
+						alertNameLabel: "common",
+						"region":       "east",
+						"instance":     "foo",
+					},
+				},
+				hash(metricWithLabels(t, alertNameLabel, "common", "region", "east", "instance", "bar")): {
+					Annotations: map[string]string{},
+					Labels: map[string]string{
+						alertNameLabel: "common",
+						"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, alertNameLabel, "override label", "region", "east", "instance", "foo")): {
+					Labels: map[string]string{
+						alertNameLabel: "override label",
+						"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, alertNameLabel, "override label", "region", "east", "instance", "bar")): {
+					Labels: map[string]string{
+						alertNameLabel: "override label",
+						"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"`,
+					},
+				},
+			},
+		},
+		{
+			&AlertingRule{
+				Name:      "ExtraTemplating",
+				GroupName: "Testing",
+				Labels: map[string]string{
+					"name":     "alert_{{ $labels.alertname }}",
+					"group":    "group_{{ $labels.alertgroup }}",
+					"instance": "{{ $labels.instance }}",
+				},
+				Annotations: map[string]string{
+					"summary":     `Alert "{{ $labels.alertname }}({{ $labels.alertgroup }})" for instance {{ $labels.instance }}`,
+					"description": `Alert "{{ $labels.name }}({{ $labels.group }})" for instance {{ $labels.instance }}`,
+				},
+				alerts: make(map[uint64]*notifier.Alert),
+			},
+			[]datasource.Metric{
+				metricWithValueAndLabels(t, 1, "instance", "foo"),
+			},
+			map[uint64]*notifier.Alert{
+				hash(metricWithLabels(t, alertNameLabel, "ExtraTemplating",
+					"name", "alert_ExtraTemplating",
+					alertGroupNameLabel, "Testing",
+					"group", "group_Testing",
+					"instance", "foo")): {
+					Labels: map[string]string{
+						alertNameLabel:      "ExtraTemplating",
+						"name":              "alert_ExtraTemplating",
+						alertGroupNameLabel: "Testing",
+						"group":             "group_Testing",
+						"instance":          "foo",
+					},
+					Annotations: map[string]string{
+						"summary":     `Alert "ExtraTemplating(Testing)" for instance foo`,
+						"description": `Alert "alert_ExtraTemplating(group_Testing)" for instance foo`,
+					},
+				},
+			},
+		},
+	}
+	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)
+	for i := 0; i < len(labels); i += 2 {
+		r.Labels[labels[i]] = labels[i+1]
+	}
+	return r
+}
+
+func newTestAlertingRule(name string, waitFor time.Duration) *AlertingRule {
+	return &AlertingRule{Name: name, alerts: make(map[uint64]*notifier.Alert), For: waitFor, EvalInterval: waitFor}
+}

app/vmalert/config.go

@@ -1,73 +0,0 @@
-package main
-
-import (
-	"fmt"
-	"gopkg.in/yaml.v2"
-	"io/ioutil"
-	"path/filepath"
-	"strings"
-
-	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
-)
-
-// Parse parses rule configs from given file patterns
-func Parse(pathPatterns []string, validateAnnotations bool) ([]Group, error) {
-	var fp []string
-	for _, pattern := range pathPatterns {
-		matches, err := filepath.Glob(pattern)
-		if err != nil {
-			return nil, fmt.Errorf("error reading file patther %s:%v", pattern, err)
-		}
-		fp = append(fp, matches...)
-	}
-	var groups []Group
-	for _, file := range fp {
-		groupsNames := map[string]struct{}{}
-		gr, err := parseFile(file)
-		if err != nil {
-			return nil, fmt.Errorf("file %s: %w", file, err)
-		}
-		for _, g := range gr {
-			if _, ok := groupsNames[g.Name]; ok {
-				return nil, fmt.Errorf("one file can not contain groups with the same name %s, filepath:%s", g.Name, file)
-			}
-			g.File = file
-			g.done = make(chan struct{})
-			g.finished = make(chan struct{})
-
-			groupsNames[g.Name] = struct{}{}
-			for _, rule := range g.Rules {
-				if err = rule.Validate(); err != nil {
-					return nil, fmt.Errorf("invalid rule filepath: %s, group %s: %w", file, g.Name, err)
-				}
-				if validateAnnotations {
-					if err = notifier.ValidateTemplates(rule.Annotations); err != nil {
-						return nil, fmt.Errorf("invalid annotations filepath: %s, group %s: %w", file, g.Name, err)
-					}
-					if err = notifier.ValidateTemplates(rule.Labels); err != nil {
-						return nil, fmt.Errorf("invalid labels filepath: %s, group %s: %w", file, g.Name, err)
-					}
-				}
-				rule.group = g
-				rule.alerts = make(map[uint64]*notifier.Alert)
-			}
-			groups = append(groups, g)
-		}
-	}
-	if len(groups) < 1 {
-		return nil, fmt.Errorf("no groups found in %s", strings.Join(pathPatterns, ";"))
-	}
-	return groups, nil
-}
-
-func parseFile(path string) ([]Group, error) {
-	data, err := ioutil.ReadFile(path)
-	if err != nil {
-		return nil, fmt.Errorf("error reading alert rule file: %w", err)
-	}
-	g := struct {
-		Groups []Group `yaml:"groups"`
-	}{}
-	err = yaml.Unmarshal(data, &g)
-	return g.Groups, err
-}

app/vmalert/config/config.go

@@ -0,0 +1,282 @@
+package config
+
+import (
+	"crypto/md5"
+	"fmt"
+	"hash/fnv"
+	"io/ioutil"
+	"net/url"
+	"path/filepath"
+	"sort"
+	"strings"
+
+	"gopkg.in/yaml.v2"
+
+	"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/VictoriaMetrics/lib/promutils"
+)
+
+// 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    promutils.Duration `yaml:"interval"`
+	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
+	// DEPRECATED: use Params field instead
+	ExtraFilterLabels map[string]string `yaml:"extra_filter_labels"`
+	// Labels is a set of label value pairs, that will be added to every rule.
+	// It has priority over the external labels.
+	Labels map[string]string `yaml:"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
+	// Optional HTTP URL parameters added to each rule request
+	Params url.Values `yaml:"params"`
+
+	// Catches all undefined fields and must be empty after parsing.
+	XXX map[string]interface{} `yaml:",inline"`
+}
+
+// UnmarshalYAML implements the yaml.Unmarshaler interface.
+func (g *Group) UnmarshalYAML(unmarshal func(interface{}) error) error {
+	type group Group
+	if err := unmarshal((*group)(g)); err != nil {
+		return err
+	}
+	b, err := yaml.Marshal(g)
+	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())
+	}
+
+	// backward compatibility with deprecated `ExtraFilterLabels` param
+	if len(g.ExtraFilterLabels) > 0 {
+		if g.Params == nil {
+			g.Params = url.Values{}
+		}
+		// Sort extraFilters for consistent order for query args across runs.
+		extraFilters := make([]string, 0, len(g.ExtraFilterLabels))
+		for k, v := range g.ExtraFilterLabels {
+			extraFilters = append(extraFilters, fmt.Sprintf("%s=%s", k, v))
+		}
+		sort.Strings(extraFilters)
+		for _, extraFilter := range extraFilters {
+			g.Params.Add("extra_label", extraFilter)
+		}
+	}
+
+	h := md5.New()
+	h.Write(b)
+	g.Checksum = fmt.Sprintf("%x", h.Sum(nil))
+	return nil
+}
+
+// Validate check for internal Group or Rule configuration errors
+func (g *Group) Validate(validateAnnotations, validateExpressions bool) error {
+	if g.Name == "" {
+		return fmt.Errorf("group name must be set")
+	}
+
+	uniqueRules := map[uint64]struct{}{}
+	for _, r := range g.Rules {
+		ruleName := r.Record
+		if r.Alert != "" {
+			ruleName = r.Alert
+		}
+		if _, ok := uniqueRules[r.ID]; ok {
+			return fmt.Errorf("rule %q duplicate", ruleName)
+		}
+		uniqueRules[r.ID] = struct{}{}
+		if err := r.Validate(); err != nil {
+			return fmt.Errorf("invalid rule %q.%q: %w", g.Name, ruleName, err)
+		}
+		if validateExpressions {
+			// its needed only for tests.
+			// because correct types must be inherited after unmarshalling.
+			exprValidator := g.Type.ValidateExpr
+			if err := exprValidator(r.Expr); err != nil {
+				return fmt.Errorf("invalid expression for rule %q.%q: %w", g.Name, ruleName, err)
+			}
+		}
+		if validateAnnotations {
+			if err := notifier.ValidateTemplates(r.Annotations); err != nil {
+				return fmt.Errorf("invalid annotations for rule %q.%q: %w", g.Name, ruleName, err)
+			}
+			if err := notifier.ValidateTemplates(r.Labels); err != nil {
+				return fmt.Errorf("invalid labels for rule %q.%q: %w", g.Name, ruleName, err)
+			}
+		}
+	}
+	return checkOverflow(g.XXX, fmt.Sprintf("group %q", g.Name))
+}
+
+// Rule describes entity that represent either
+// 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         promutils.Duration `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"`
+}
+
+// UnmarshalYAML implements the yaml.Unmarshaler interface.
+func (r *Rule) UnmarshalYAML(unmarshal func(interface{}) error) error {
+	type rule Rule
+	if err := unmarshal((*rule)(r)); err != nil {
+		return err
+	}
+	r.ID = HashRule(*r)
+	return nil
+}
+
+// Name returns Rule name according to its type
+func (r *Rule) Name() string {
+	if r.Record != "" {
+		return r.Record
+	}
+	return r.Alert
+}
+
+// HashRule hashes significant Rule fields into
+// unique hash that supposed to define Rule uniqueness
+func HashRule(r Rule) uint64 {
+	h := fnv.New64a()
+	h.Write([]byte(r.Expr))
+	if r.Record != "" {
+		h.Write([]byte("recording"))
+		h.Write([]byte(r.Record))
+	} else {
+		h.Write([]byte("alerting"))
+		h.Write([]byte(r.Alert))
+	}
+	kv := sortMap(r.Labels)
+	for _, i := range kv {
+		h.Write([]byte(i.key))
+		h.Write([]byte(i.value))
+		h.Write([]byte("\xff"))
+	}
+	return h.Sum64()
+}
+
+// Validate check for Rule configuration errors
+func (r *Rule) Validate() error {
+	if (r.Record == "" && r.Alert == "") || (r.Record != "" && r.Alert != "") {
+		return fmt.Errorf("either `record` or `alert` must be set")
+	}
+	if r.Expr == "" {
+		return fmt.Errorf("expression can't be empty")
+	}
+	return checkOverflow(r.XXX, "rule")
+}
+
+// Parse parses rule configs from given file patterns
+func Parse(pathPatterns []string, validateAnnotations, validateExpressions bool) ([]Group, error) {
+	var fp []string
+	for _, pattern := range pathPatterns {
+		matches, err := filepath.Glob(pattern)
+		if err != nil {
+			return nil, fmt.Errorf("error reading file pattern %s: %w", pattern, err)
+		}
+		fp = append(fp, matches...)
+	}
+	errGroup := new(utils.ErrGroup)
+	var isExtraFilterLabelsUsed bool
+	var groups []Group
+	for _, file := range fp {
+		uniqueGroups := map[string]struct{}{}
+		gr, err := parseFile(file)
+		if err != nil {
+			errGroup.Add(fmt.Errorf("failed to parse file %q: %w", file, err))
+			continue
+		}
+		for _, g := range gr {
+			if err := g.Validate(validateAnnotations, validateExpressions); err != nil {
+				errGroup.Add(fmt.Errorf("invalid group %q in file %q: %w", g.Name, file, err))
+				continue
+			}
+			if _, ok := uniqueGroups[g.Name]; ok {
+				errGroup.Add(fmt.Errorf("group name %q duplicate in file %q", g.Name, file))
+				continue
+			}
+			uniqueGroups[g.Name] = struct{}{}
+			g.File = file
+			if len(g.ExtraFilterLabels) > 0 {
+				isExtraFilterLabelsUsed = true
+			}
+			groups = append(groups, g)
+		}
+	}
+	if err := errGroup.Err(); err != nil {
+		return nil, err
+	}
+	if len(groups) < 1 {
+		logger.Warnf("no groups found in %s", strings.Join(pathPatterns, ";"))
+	}
+	if isExtraFilterLabelsUsed {
+		logger.Warnf("field `extra_filter_labels` is deprecated - use `params` instead")
+	}
+	return groups, nil
+}
+
+func parseFile(path string) ([]Group, error) {
+	data, err := ioutil.ReadFile(path)
+	if err != nil {
+		return nil, fmt.Errorf("error reading alert rule file: %w", err)
+	}
+	data = envtemplate.Replace(data)
+	g := struct {
+		Groups []Group `yaml:"groups"`
+		// Catches all undefined fields and must be empty after parsing.
+		XXX map[string]interface{} `yaml:",inline"`
+	}{}
+	err = yaml.Unmarshal(data, &g)
+	if err != nil {
+		return nil, err
+	}
+	return g.Groups, checkOverflow(g.XXX, "config")
+}
+
+func checkOverflow(m map[string]interface{}, ctx string) error {
+	if len(m) > 0 {
+		var keys []string
+		for k := range m {
+			keys = append(keys, k)
+		}
+		return fmt.Errorf("unknown fields in %s: %s", ctx, strings.Join(keys, ", "))
+	}
+	return nil
+}
+
+type item struct {
+	key, value string
+}
+
+func sortMap(m map[string]string) []item {
+	var kv []item
+	for k, v := range m {
+		kv = append(kv, item{key: k, value: v})
+	}
+	sort.Slice(kv, func(i, j int) bool {
+		return kv[i].key < kv[j].key
+	})
+	return kv
+}

app/vmalert/config/config_test.go

@@ -0,0 +1,557 @@
+package config
+
+import (
+	"net/url"
+	"os"
+	"strings"
+	"testing"
+	"time"
+
+	"gopkg.in/yaml.v2"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promutils"
+)
+
+func TestMain(m *testing.M) {
+	u, _ := url.Parse("https://victoriametrics.com/path")
+	notifier.InitTemplateFunc(u)
+	os.Exit(m.Run())
+}
+
+func TestParseGood(t *testing.T) {
+	if _, err := Parse([]string{"testdata/*good.rules", "testdata/dir/*good.*"}, true, true); err != nil {
+		t.Errorf("error parsing files %s", err)
+	}
+}
+
+func TestParseBad(t *testing.T) {
+	testCases := []struct {
+		path   []string
+		expErr string
+	}{
+		{
+			[]string{"testdata/rules0-bad.rules"},
+			"unexpected token",
+		},
+		{
+			[]string{"testdata/dir/rules0-bad.rules"},
+			"error parsing annotation",
+		},
+		{
+			[]string{"testdata/dir/rules1-bad.rules"},
+			"duplicate in file",
+		},
+		{
+			[]string{"testdata/dir/rules2-bad.rules"},
+			"function \"unknown\" not defined",
+		},
+		{
+			[]string{"testdata/dir/rules3-bad.rules"},
+			"either `record` or `alert` must be set",
+		},
+		{
+			[]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)
+		if err == nil {
+			t.Errorf("expected to get error")
+			return
+		}
+		if !strings.Contains(err.Error(), tc.expErr) {
+			t.Errorf("expected err to contain %q; got %q instead", tc.expErr, err)
+		}
+	}
+}
+
+func TestRule_Validate(t *testing.T) {
+	if err := (&Rule{}).Validate(); err == nil {
+		t.Errorf("expected empty name error")
+	}
+	if err := (&Rule{Alert: "alert"}).Validate(); err == nil {
+		t.Errorf("expected empty expr error")
+	}
+	if err := (&Rule{Alert: "alert", Expr: "test>0"}).Validate(); err != nil {
+		t.Errorf("expected valid rule; got %s", err)
+	}
+}
+
+func TestGroup_Validate(t *testing.T) {
+	testCases := []struct {
+		group               *Group
+		rules               []Rule
+		validateAnnotations bool
+		validateExpressions bool
+		expErr              string
+	}{
+		{
+			group:  &Group{},
+			expErr: "group name must be set",
+		},
+		{
+			group: &Group{Name: "test",
+				Rules: []Rule{
+					{
+						Record: "record",
+						Expr:   "up | 0",
+					},
+				},
+			},
+			expErr: "",
+		},
+		{
+			group: &Group{Name: "test",
+				Rules: []Rule{
+					{
+						Record: "record",
+						Expr:   "up | 0",
+					},
+				},
+			},
+			expErr:              "invalid expression",
+			validateExpressions: true,
+		},
+		{
+			group: &Group{Name: "test",
+				Rules: []Rule{
+					{
+						Alert: "alert",
+						Expr:  "up == 1",
+						Labels: map[string]string{
+							"summary": "{{ value|query }}",
+						},
+					},
+				},
+			},
+			expErr: "",
+		},
+		{
+			group: &Group{Name: "test",
+				Rules: []Rule{
+					{
+						Alert: "alert",
+						Expr:  "up == 1",
+						Labels: map[string]string{
+							"summary": `
+{{ with printf "node_memory_MemTotal{job='node',instance='%s'}" "localhost" | query }}
+  {{ . | first | value | humanize1024 }}B
+{{ end }}`,
+						},
+					},
+				},
+			},
+			validateAnnotations: true,
+		},
+		{
+			group: &Group{Name: "test",
+				Rules: []Rule{
+					{
+						Alert: "alert",
+						Expr:  "up == 1",
+					},
+					{
+						Alert: "alert",
+						Expr:  "up == 1",
+					},
+				},
+			},
+			expErr: "duplicate",
+		},
+		{
+			group: &Group{Name: "test",
+				Rules: []Rule{
+					{Alert: "alert", Expr: "up == 1", Labels: map[string]string{
+						"summary": "{{ value|query }}",
+					}},
+					{Alert: "alert", Expr: "up == 1", Labels: map[string]string{
+						"summary": "{{ value|query }}",
+					}},
+				},
+			},
+			expErr: "duplicate",
+		},
+		{
+			group: &Group{Name: "test",
+				Rules: []Rule{
+					{Record: "record", Expr: "up == 1", Labels: map[string]string{
+						"summary": "{{ value|query }}",
+					}},
+					{Record: "record", Expr: "up == 1", Labels: map[string]string{
+						"summary": "{{ value|query }}",
+					}},
+				},
+			},
+			expErr: "duplicate",
+		},
+		{
+			group: &Group{Name: "test",
+				Rules: []Rule{
+					{Alert: "alert", Expr: "up == 1", Labels: map[string]string{
+						"summary": "{{ value|query }}",
+					}},
+					{Alert: "alert", Expr: "up == 1", Labels: map[string]string{
+						"description": "{{ value|query }}",
+					}},
+				},
+			},
+			expErr: "",
+		},
+		{
+			group: &Group{Name: "test",
+				Rules: []Rule{
+					{Record: "alert", Expr: "up == 1", Labels: map[string]string{
+						"summary": "{{ value|query }}",
+					}},
+					{Alert: "alert", Expr: "up == 1", Labels: map[string]string{
+						"summary": "{{ value|query }}",
+					}},
+				},
+			},
+			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:  promutils.NewDuration(10 * time.Millisecond),
+					},
+					{
+						Expr: "sum(up == 0 ) by (host)",
+					},
+				},
+			},
+		},
+		{
+			group: &Group{
+				Name: "test graphite prometheus bad expr",
+				Type: datasource.NewGraphiteType(),
+				Rules: []Rule{
+					{
+						Expr: "sum(up == 0 ) by (host)",
+						For:  promutils.NewDuration(10 * time.Millisecond),
+					},
+					{
+						Expr: "sumSeries(time('foo.bar',10))",
+					},
+				},
+			},
+			expErr: "invalid rule",
+		},
+	}
+	for _, tc := range testCases {
+		err := tc.group.Validate(tc.validateAnnotations, tc.validateExpressions)
+		if err == nil {
+			if tc.expErr != "" {
+				t.Errorf("expected to get err %q; got nil insted", tc.expErr)
+			}
+			continue
+		}
+		if !strings.Contains(err.Error(), tc.expErr) {
+			t.Errorf("expected err to contain %q; got %q instead", tc.expErr, err)
+		}
+	}
+}
+
+func TestHashRule(t *testing.T) {
+	testCases := []struct {
+		a, b  Rule
+		equal bool
+	}{
+		{
+			Rule{Record: "record", Expr: "up == 1"},
+			Rule{Record: "record", Expr: "up == 1"},
+			true,
+		},
+		{
+			Rule{Alert: "alert", Expr: "up == 1"},
+			Rule{Alert: "alert", Expr: "up == 1"},
+			true,
+		},
+		{
+			Rule{Alert: "alert", Expr: "up == 1", Labels: map[string]string{
+				"foo": "bar",
+				"baz": "foo",
+			}},
+			Rule{Alert: "alert", Expr: "up == 1", Labels: map[string]string{
+				"foo": "bar",
+				"baz": "foo",
+			}},
+			true,
+		},
+		{
+			Rule{Alert: "alert", Expr: "up == 1", Labels: map[string]string{
+				"foo": "bar",
+				"baz": "foo",
+			}},
+			Rule{Alert: "alert", Expr: "up == 1", Labels: map[string]string{
+				"baz": "foo",
+				"foo": "bar",
+			}},
+			true,
+		},
+		{
+			Rule{Alert: "record", Expr: "up == 1"},
+			Rule{Alert: "record", Expr: "up == 1"},
+			true,
+		},
+		{
+			Rule{Alert: "alert", Expr: "up == 1", For: promutils.NewDuration(time.Minute)},
+			Rule{Alert: "alert", Expr: "up == 1"},
+			true,
+		},
+		{
+			Rule{Alert: "record", Expr: "up == 1"},
+			Rule{Record: "record", Expr: "up == 1"},
+			false,
+		},
+		{
+			Rule{Record: "record", Expr: "up == 1"},
+			Rule{Record: "record", Expr: "up == 2"},
+			false,
+		},
+		{
+			Rule{Alert: "alert", Expr: "up == 1", Labels: map[string]string{
+				"foo": "bar",
+				"baz": "foo",
+			}},
+			Rule{Alert: "alert", Expr: "up == 1", Labels: map[string]string{
+				"baz": "foo",
+				"foo": "baz",
+			}},
+			false,
+		},
+		{
+			Rule{Alert: "alert", Expr: "up == 1", Labels: map[string]string{
+				"foo": "bar",
+				"baz": "foo",
+			}},
+			Rule{Alert: "alert", Expr: "up == 1", Labels: map[string]string{
+				"baz": "foo",
+			}},
+			false,
+		},
+		{
+			Rule{Alert: "alert", Expr: "up == 1", Labels: map[string]string{
+				"foo": "bar",
+				"baz": "foo",
+			}},
+			Rule{Alert: "alert", Expr: "up == 1"},
+			false,
+		},
+	}
+	for i, tc := range testCases {
+		aID, bID := HashRule(tc.a), HashRule(tc.b)
+		if tc.equal != (aID == bID) {
+			t.Fatalf("missmatch for rule %d", i)
+		}
+	}
+}
+
+func TestGroupChecksum(t *testing.T) {
+	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)
+`, `
+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)
+`)
+	})
+
+	t.Run("`for` change", 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)
+`)
+	})
+	t.Run("`interval` change", func(t *testing.T) {
+		f(t, `
+name: TestGroup
+interval: 2s
+rules:
+  - alert: ExampleAlertWithFor
+    expr: sum by(job) (up == 1)
+`, `
+name: TestGroup
+interval: 4s
+rules:
+  - alert: ExampleAlertWithFor
+    expr: sum by(job) (up == 1)
+`)
+	})
+	t.Run("`concurrency` change", func(t *testing.T) {
+		f(t, `
+name: TestGroup
+concurrency: 2
+rules:
+  - alert: ExampleAlertWithFor
+    expr: sum by(job) (up == 1)
+`, `
+name: TestGroup
+concurrency: 16
+rules:
+  - alert: ExampleAlertWithFor
+    expr: sum by(job) (up == 1)
+`)
+	})
+
+	t.Run("`params` change", func(t *testing.T) {
+		f(t, `
+name: TestGroup
+params:
+    nocache: ["1"]
+rules:
+  - alert: foo
+    expr: sum by(job) (up == 1)
+`, `
+name: TestGroup
+params:
+    nocache: ["0"]
+rules:
+  - alert: foo
+    expr: sum by(job) (up == 1)
+`)
+	})
+}
+
+func TestGroupParams(t *testing.T) {
+	f := func(t *testing.T, data string, expParams url.Values) {
+		t.Helper()
+		var g Group
+		if err := yaml.Unmarshal([]byte(data), &g); err != nil {
+			t.Fatalf("failed to unmarshal: %s", err)
+		}
+		got, exp := g.Params.Encode(), expParams.Encode()
+		if got != exp {
+			t.Fatalf("expected to have %q; got %q", exp, got)
+		}
+	}
+
+	t.Run("no params", func(t *testing.T) {
+		f(t, `
+name: TestGroup
+rules:
+  - alert: ExampleAlertAlwaysFiring
+    expr: sum by(job) (up == 1)
+`, url.Values{})
+	})
+
+	t.Run("params", func(t *testing.T) {
+		f(t, `
+name: TestGroup
+params:
+  nocache: ["1"]
+  denyPartialResponse: ["true"]
+rules:
+  - alert: ExampleAlertAlwaysFiring
+    expr: sum by(job) (up == 1)
+`, url.Values{"nocache": {"1"}, "denyPartialResponse": {"true"}})
+	})
+
+	t.Run("extra labels", func(t *testing.T) {
+		f(t, `
+name: TestGroup
+extra_filter_labels:
+  job: victoriametrics
+  env: prod
+rules:
+  - alert: ExampleAlertAlwaysFiring
+    expr: sum by(job) (up == 1)
+`, url.Values{"extra_label": {"env=prod", "job=victoriametrics"}})
+	})
+
+	t.Run("extra labels and params", func(t *testing.T) {
+		f(t, `
+name: TestGroup
+extra_filter_labels:
+  job: victoriametrics
+params:
+  nocache: ["1"]
+  extra_label: ["env=prod"]
+rules:
+  - alert: ExampleAlertAlwaysFiring
+    expr: sum by(job) (up == 1)
+`, url.Values{"nocache": {"1"}, "extra_label": {"env=prod", "job=victoriametrics"}})
+	})
+}

app/vmalert/config/testdata/dir/rules0-good.rules

@@ -6,6 +6,7 @@ groups:
         expr: vm_rows > 0
         labels:
           label: bar
+          expr: "{{ $expr|queryEscape }}"
         annotations:
           summary: "{{ $value|humanize }}"
           description: "{{$labels}}"

app/vmalert/config/testdata/dir/rules1-good.rules

@@ -1,5 +1,7 @@
 groups:
   - name: duplicatedGroupDiffFiles
+    labels:
+       dc: gcp
     rules:
       - alert: VMRows
         for: 5m
@@ -9,5 +11,3 @@ groups:
         annotations:
           summary: "{{ $value }}"
           description: "{{$labels}}"
-
-

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/dir/rules3-bad.rules

@@ -0,0 +1,5 @@
+groups:
+  - name: group
+    rules:
+      - for: 5m
+        expr: vm_rows > 0

app/vmalert/config/testdata/dir/rules4-bad.rules

@@ -0,0 +1,7 @@
+groups:
+  - name: group
+    rules:
+      - alert: rows
+        record: record
+        for: 5m
+        expr: vm_rows > 0

app/vmalert/config/testdata/dir/rules5-bad.rules

@@ -0,0 +1,7 @@
+groups:
+  - name: group
+    rules:
+      - alert: rows
+        expr: vm_rows > 0
+      - record: rows
+        expr: sum(vm_rows)

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/rules0-good.rules

@@ -1,5 +1,8 @@
 groups:
   - name: groupGorSingleAlert
+    params:
+      nocache: ["1"]
+      denyPartialResponse: ["true"]
     rules:
       - alert: VMRows
         for: 10s

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

@@ -0,0 +1,52 @@
+groups:
+  - name: TestGroup
+    interval: 2s
+    concurrency: 2
+    extra_filter_labels: # deprecated param, use `params` instead
+        job: victoriametrics
+    params:
+      denyPartialResponse: ["true"]
+      extra_label: ["env=dev"]
+    rules:
+      - alert: Conns
+        expr: sum(vm_tcplistener_conns) by(instance) > 1
+        for: 3m
+        annotations:
+          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!
+          external: cluster-{{ $externalLabels.cluster }}; replica-{{ $externalLabels.replica }}
+          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:
+          recording: true
+      - record: code:requests:rate5m
+        expr: sum(rate(promhttp_metric_handler_requests_total[5m])) by (code)
+        labels:
+          env: dev
+          recording: true
+      - record: code:requests:rate5m
+        expr: sum(rate(promhttp_metric_handler_requests_total[5m])) by (code)
+        labels:
+          env: staging
+          recording: true
+      - record: successful_requests:ratio_rate5m
+        labels:
+          recording: true
+        expr: |2
+            sum(code:requests:rate5m{code="200"})
+          /
+            sum(code:requests:rate5m)

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

@@ -0,0 +1,23 @@
+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}}"

app/vmalert/config/testdata/rules4-good.rules

@@ -0,0 +1,8 @@
+groups:
+  - name: TestEmptyRules
+    interval: 2s
+    concurrency: 2
+    rules:
+
+  - name: TestNoRules
+    type: prometheus

app/vmalert/config_test.go

@@ -1,39 +0,0 @@
-package main
-
-import (
-	"net/url"
-	"os"
-	"testing"
-
-	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
-)
-
-func TestMain(m *testing.M) {
-	u, _ := url.Parse("https://victoriametrics.com/path")
-	notifier.InitTemplateFunc(u)
-	os.Exit(m.Run())
-}
-
-func TestParseGood(t *testing.T) {
-	if _, err := Parse([]string{"testdata/*good.rules", "testdata/dir/*good.*"}, true); err != nil {
-		t.Errorf("error parsing files %s", err)
-	}
-}
-
-func TestParseBad(t *testing.T) {
-	if _, err := Parse([]string{"testdata/rules0-bad.rules"}, true); err == nil {
-		t.Errorf("expected syntaxt error")
-	}
-	if _, err := Parse([]string{"testdata/dir/rules0-bad.rules"}, true); err == nil {
-		t.Errorf("expected template annotation error")
-	}
-	if _, err := Parse([]string{"testdata/dir/rules1-bad.rules"}, true); err == nil {
-		t.Errorf("expected same group error")
-	}
-	if _, err := Parse([]string{"testdata/dir/rules2-bad.rules"}, true); err == nil {
-		t.Errorf("expected template label error")
-	}
-	if _, err := Parse([]string{"testdata/*.yaml"}, true); err == nil {
-		t.Errorf("expected empty group")
-	}
-}

app/vmalert/datasource/datasource.go

@@ -1,20 +1,62 @@
 package datasource
 
-import "context"
+import (
+	"context"
+	"net/url"
+	"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
+	QueryParams        url.Values
 }
 
 // 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
+// by the given key and label
+func (m *Metric) SetLabel(key, value string) {
+	for i, l := range m.Labels {
+		if l.Name == key {
+			m.Labels[i].Value = value
+			return
+		}
+	}
+	m.AddLabel(key, value)
+}
+
+// AddLabel appends the given label to the label set
+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

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

@@ -0,0 +1,82 @@
+package datasource
+
+import (
+	"flag"
+	"fmt"
+	"net/http"
+	"net/url"
+	"strings"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/utils"
+)
+
+var (
+	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")
+	basicAuthPasswordFile = flag.String("datasource.basicAuth.passwordFile", "", "Optional path to basic auth password to use for -datasource.url")
+	bearerToken           = flag.String("datasource.bearerToken", "", "Optional bearer auth token to use for -datasource.url.")
+	bearerTokenFile       = flag.String("datasource.bearerTokenFile", "", "Optional path to bearer token file to use 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`)
+
+	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.`)
+)
+
+// Param represents an HTTP GET param
+type Param struct {
+	Key, Value string
+}
+
+// Init creates a Querier from provided flag values.
+// Provided extraParams will be added as GET params for
+// each request.
+func Init(extraParams url.Values) (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.MaxIdleConnsPerHost = *maxIdleConnections
+	if tr.MaxIdleConns != 0 && tr.MaxIdleConns < tr.MaxIdleConnsPerHost {
+		tr.MaxIdleConns = tr.MaxIdleConnsPerHost
+	}
+
+	if extraParams == nil {
+		extraParams = url.Values{}
+	}
+	if *roundDigits > 0 {
+		extraParams.Set("round_digits", fmt.Sprintf("%d", *roundDigits))
+	}
+
+	authCfg, err := utils.AuthConfig(*basicAuthUsername, *basicAuthPassword, *basicAuthPasswordFile, *bearerToken, *bearerTokenFile)
+	if err != nil {
+		return nil, fmt.Errorf("failed to configure auth: %w", err)
+	}
+
+	return &VMStorage{
+		c:                &http.Client{Transport: tr},
+		authCfg:          authCfg,
+		datasourceURL:    strings.TrimSuffix(*addr, "/"),
+		appendTypePrefix: *appendTypePrefix,
+		lookBack:         *lookBack,
+		queryStep:        *queryStep,
+		dataSourceType:   NewPrometheusType(),
+		extraParams:      extraParams,
+	}, nil
+}

app/vmalert/datasource/type.go

@@ -0,0 +1,91 @@
+package datasource
+
+import (
+	"fmt"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmselect/graphiteql"
+	"github.com/VictoriaMetrics/metricsql"
+)
+
+// Type represents data source type
+type Type struct {
+	name string
+}
+
+// NewPrometheusType returns prometheus datasource type
+func NewPrometheusType() Type {
+	return Type{
+		name: "prometheus",
+	}
+}
+
+// NewGraphiteType returns graphite datasource type
+func NewGraphiteType() Type {
+	return Type{
+		name: "graphite",
+	}
+}
+
+// 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 "prometheus"
+	}
+	return t.name
+}
+
+// ValidateExpr validates query expression with datasource ql.
+func (t *Type) ValidateExpr(expr string) error {
+	switch t.String() {
+	case "graphite":
+		if _, err := graphiteql.Parse(expr); err != nil {
+			return fmt.Errorf("bad graphite expr: %q, err: %w", expr, err)
+		}
+	case "prometheus":
+		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
+	}
+	if s == "" {
+		s = "prometheus"
+	}
+	switch s {
+	case "graphite", "prometheus":
+	default:
+		return fmt.Errorf("unknown datasource type=%q, want %q or %q", s, "prometheus", "graphite")
+	}
+	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

@@ -2,102 +2,157 @@ package datasource
 
 import (
 	"context"
-	"encoding/json"
 	"fmt"
 	"io/ioutil"
 	"net/http"
 	"net/url"
-	"strconv"
 	"strings"
+	"time"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promauth"
 )
 
-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: %s", res, res.TV[1], err)
-		}
-		m.Labels = nil
-		for k, v := range r.Data.Result[i].Labels {
-			m.Labels = append(m.Labels, Label{Name: k, Value: v})
-		}
-		m.Timestamp = int64(res.TV[0].(float64))
-		m.Value = f
-		ms = append(ms, m)
-	}
-	return ms, nil
-}
-
-const queryPath = "/api/v1/query?query="
-
 // VMStorage represents vmstorage entity with ability to read and write metrics
 type VMStorage struct {
-	c                            *http.Client
-	queryURL                     string
-	basicAuthUser, basicAuthPass string
+	c                *http.Client
+	authCfg          *promauth.Config
+	datasourceURL    string
+	appendTypePrefix bool
+	lookBack         time.Duration
+	queryStep        time.Duration
+
+	dataSourceType     Type
+	evaluationInterval time.Duration
+	extraParams        url.Values
+	disablePathAppend  bool
 }
 
-// NewVMStorage is a constructor for VMStorage
-func NewVMStorage(baseURL, basicAuthUser, basicAuthPass string, c *http.Client) *VMStorage {
+// Clone makes clone of VMStorage, shares http client.
+func (s *VMStorage) Clone() *VMStorage {
 	return &VMStorage{
-		c:             c,
-		basicAuthUser: basicAuthUser,
-		basicAuthPass: basicAuthPass,
-		queryURL:      strings.TrimSuffix(baseURL, "/") + queryPath,
+		c:                 s.c,
+		authCfg:           s.authCfg,
+		datasourceURL:     s.datasourceURL,
+		lookBack:          s.lookBack,
+		queryStep:         s.queryStep,
+		appendTypePrefix:  s.appendTypePrefix,
+		dataSourceType:    s.dataSourceType,
+		disablePathAppend: s.disablePathAppend,
 	}
 }
 
-// Query reads metrics from datasource by given query
+// ApplyParams - changes given querier params.
+func (s *VMStorage) ApplyParams(params QuerierParams) *VMStorage {
+	if params.DataSourceType != nil {
+		s.dataSourceType = *params.DataSourceType
+	}
+	s.evaluationInterval = params.EvaluationInterval
+	s.extraParams = params.QueryParams
+	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 string, authCfg *promauth.Config, lookBack time.Duration, queryStep time.Duration, appendTypePrefix bool, c *http.Client, disablePathAppend bool) *VMStorage {
+	return &VMStorage{
+		c:                 c,
+		authCfg:           authCfg,
+		datasourceURL:     strings.TrimSuffix(baseURL, "/"),
+		appendTypePrefix:  appendTypePrefix,
+		lookBack:          lookBack,
+		queryStep:         queryStep,
+		dataSourceType:    NewPrometheusType(),
+		disablePathAppend: disablePathAppend,
+	}
+}
+
+// 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"
-	)
-	req, err := http.NewRequest("POST", s.queryURL+url.QueryEscape(query), nil)
+	req, err := s.newRequestPOST()
+	if err != nil {
+		return nil, err
+	}
+
+	ts := time.Now()
+	switch s.dataSourceType.String() {
+	case "prometheus":
+		s.setPrometheusInstantReqParams(req, query, ts)
+	case "graphite":
+		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 != "prometheus" {
+		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 != "prometheus" {
+		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.Redacted(), 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.Redacted(), 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
 	}
 	req.Header.Set("Content-Type", "application/json")
-	if s.basicAuthPass != "" {
-		req.SetBasicAuth(s.basicAuthUser, s.basicAuthPass)
+	if s.authCfg != nil {
+		if auth := s.authCfg.GetAuthHeader(); auth != "" {
+			req.Header.Set("Authorization", auth)
+		}
 	}
-	resp, err := s.c.Do(req.WithContext(ctx))
-	if err != nil {
-		return nil, fmt.Errorf("error getting response from %s:%s", req.URL, err)
-	}
-	defer func() { _ = resp.Body.Close() }()
-	if resp.StatusCode != http.StatusOK {
-		body, _ := ioutil.ReadAll(resp.Body)
-		return nil, fmt.Errorf("datasource returns unxeprected response code %d for %s with err %s. Reponse body %s", resp.StatusCode, req.URL, err, body)
-	}
-	r := &response{}
-	if err := json.NewDecoder(resp.Body).Decode(r); err != nil {
-		return nil, fmt.Errorf("error parsing metrics for %s:%s", 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("unkown status:%s, Expected success or error ", r.Status)
-	}
-	if r.Data.ResultType != rtVector {
-		return nil, fmt.Errorf("unkown restul type:%s. Expected vector", r.Data.ResultType)
-	}
-	return r.metrics()
+	return req, nil
 }

app/vmalert/datasource/vm_graphite_api.go

@@ -0,0 +1,75 @@
+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.Redacted(), 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()
+	for k, vs := range s.extraParams {
+		if q.Has(k) { // extraParams are prior to params in URL
+			q.Del(k)
+		}
+		for _, v := range vs {
+			q.Add(k, v)
+		}
+	}
+	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 +1,173 @@
+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.Redacted(), err)
+	}
+	if r.Status == statusError {
+		return nil, fmt.Errorf("response error, query: %s, errorType: %s, error: %s", req.URL.Redacted(), 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
+	}
+	if !s.disablePathAppend {
+		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
+	}
+	if !s.disablePathAppend {
+		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()
+	for k, vs := range s.extraParams {
+		if q.Has(k) { // extraParams are prior to params in URL
+			q.Del(k)
+		}
+		for _, v := range vs {
+			q.Add(k, v)
+		}
+	}
+	q.Set("query", query)
+	if s.evaluationInterval > 0 { // set step as evaluationInterval by default
+		// always convert to seconds to keep compatibility with older
+		// Prometheus versions. See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1943
+		q.Set("step", fmt.Sprintf("%ds", int(s.evaluationInterval.Seconds())))
+	}
+	if s.queryStep > 0 { // override step with user-specified value
+		// always convert to seconds to keep compatibility with older
+		// Prometheus versions. See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1943
+		q.Set("step", fmt.Sprintf("%ds", int(s.queryStep.Seconds())))
+	}
+	r.URL.RawQuery = q.Encode()
+}

app/vmalert/datasource/vm_test.go

@@ -2,24 +2,44 @@ package datasource
 
 import (
 	"context"
+	"fmt"
 	"net/http"
 	"net/http/httptest"
+	"net/url"
+	"reflect"
+	"strconv"
+	"strings"
 	"testing"
+	"time"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promauth"
 )
 
 var (
 	ctx           = context.Background()
 	basicAuthName = "foo"
 	basicAuthPass = "bar"
-	query         = "vm_rows"
+	baCfg         = &promauth.BasicAuthConfig{
+		Username: basicAuthName,
+		Password: promauth.NewSecret(basicAuthPass),
+	}
+	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 {
@@ -29,7 +49,14 @@ func TestVMSelectQuery(t *testing.T) {
 			t.Errorf("expected %s:%s as basic auth got %s:%s", basicAuthName, basicAuthPass, name, pass)
 		}
 		if r.URL.Query().Get("query") != query {
-			t.Errorf("exptected %s in query param, got %s", query, r.URL.Query().Get("query"))
+			t.Errorf("expected %s in query param, got %s", query, r.URL.Query().Get("query"))
+		}
+		timeParam := r.URL.Query().Get("time")
+		if timeParam == "" {
+			t.Errorf("expected 'time' in query param, got nil instead")
+		}
+		if _, err := strconv.ParseInt(timeParam, 10, 64); err != nil {
+			t.Errorf("failed to parse 'time' query param: %s", err)
 		}
 		switch c {
 		case 0:
@@ -46,48 +73,463 @@ 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, srv.Client())
-	if _, err := am.Query(ctx, query); err == nil {
+
+	authCfg, err := promauth.NewConfig(".", nil, baCfg, "", "", nil, nil)
+	if err != nil {
+		t.Fatalf("unexpected: %s", err)
+	}
+	s := NewVMStorage(srv.URL, authCfg, time.Minute, 0, false, srv.Client(), false)
+
+	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 {
-		t.Fatalf("expected unkown status got 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("exptected 1 metric  got %d in %+v", len(m), m)
+		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()
+
+	authCfg, err := promauth.NewConfig(".", nil, baCfg, "", "", nil, nil)
+	if err != nil {
+		t.Fatalf("unexpected: %s", err)
+	}
+	s := NewVMStorage(srv.URL, authCfg, time.Minute, 0, false, srv.Client(), false)
+
+	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)
+	}
+	if len(m) != 1 {
+		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) {
+	authCfg, err := promauth.NewConfig(".", nil, baCfg, "", "", nil, nil)
+	if err != nil {
+		t.Fatalf("unexpected: %s", err)
+	}
+	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 path with disablePathAppend",
+			false,
+			&VMStorage{
+				dataSourceType:    NewPrometheusType(),
+				disablePathAppend: true,
+			},
+			func(t *testing.T, r *http.Request) {
+				checkEqualString(t, "", 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 prefix with disablePathAppend",
+			false,
+			&VMStorage{
+				dataSourceType:    NewPrometheusType(),
+				appendTypePrefix:  true,
+				disablePathAppend: true,
+			},
+			func(t *testing.T, r *http.Request) {
+				checkEqualString(t, prometheusPrefix, 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 path with disablePathAppend",
+			true,
+			&VMStorage{
+				dataSourceType:    NewPrometheusType(),
+				disablePathAppend: true,
+			},
+			func(t *testing.T, r *http.Request) {
+				checkEqualString(t, "", 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)
+			},
+		},
+		{
+			"prometheus range prefix with disablePathAppend",
+			true,
+			&VMStorage{
+				dataSourceType:    NewPrometheusType(),
+				appendTypePrefix:  true,
+				disablePathAppend: true,
+			},
+			func(t *testing.T, r *http.Request) {
+				checkEqualString(t, prometheusPrefix, 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{authCfg: authCfg},
+			func(t *testing.T, r *http.Request) {
+				u, p, _ := r.BasicAuth()
+				checkEqualString(t, "foo", u)
+				checkEqualString(t, "bar", p)
+			},
+		},
+		{
+			"basic auth range",
+			true,
+			&VMStorage{authCfg: authCfg},
+			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=%ds&time=%d", query, int(time.Minute.Seconds()), timestamp.Unix())
+				checkEqualString(t, exp, r.URL.RawQuery)
+			},
+		},
+		{
+			"step to seconds",
+			false,
+			&VMStorage{
+				evaluationInterval: 3 * time.Hour,
+			},
+			func(t *testing.T, r *http.Request) {
+				evalInterval := 3 * time.Hour
+				tt := timestamp.Truncate(evalInterval)
+				exp := fmt.Sprintf("query=%s&step=%ds&time=%d", query, int(evalInterval.Seconds()), tt.Unix())
+				checkEqualString(t, exp, r.URL.RawQuery)
+			},
+		},
+		{
+			"prometheus extra params",
+			false,
+			&VMStorage{
+				extraParams: url.Values{"round_digits": {"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)
+			},
+		},
+		{
+			"prometheus extra params range",
+			true,
+			&VMStorage{
+				extraParams: url.Values{
+					"nocache":      {"1"},
+					"max_lookback": {"1h"},
+				},
+			},
+			func(t *testing.T, r *http.Request) {
+				exp := fmt.Sprintf("end=%d&max_lookback=1h&nocache=1&query=%s&start=%d",
+					timestamp.Unix(), query, timestamp.Unix())
+				checkEqualString(t, exp, r.URL.RawQuery)
+			},
+		},
+		{
+			"graphite extra params",
+			false,
+			&VMStorage{
+				dataSourceType: NewGraphiteType(),
+				extraParams: url.Values{
+					"nocache":      {"1"},
+					"max_lookback": {"1h"},
+				},
+			},
+			func(t *testing.T, r *http.Request) {
+				exp := fmt.Sprintf("format=json&from=-5min&max_lookback=1h&nocache=1&target=%s&until=now", query)
+				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.String() {
+			case "prometheus":
+				if tc.queryRange {
+					tc.vm.setPrometheusRangeReqParams(req, query, timestamp, timestamp)
+				} else {
+					tc.vm.setPrometheusInstantReqParams(req, query, timestamp)
+				}
+			case "graphite":
+				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: \n%q; \ngot: \n%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

@@ -4,162 +4,391 @@ import (
 	"context"
 	"fmt"
 	"hash/fnv"
+	"net/url"
+	"sync"
 	"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/remotewrite"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/utils"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
 	"github.com/VictoriaMetrics/metrics"
 )
 
 // Group is an entity for grouping rules
 type Group struct {
-	Name  string
-	File  string
-	Rules []*Rule
+	mu          sync.RWMutex
+	Name        string
+	File        string
+	Rules       []Rule
+	Type        datasource.Type
+	Interval    time.Duration
+	Concurrency int
+	Checksum    string
 
-	done     chan struct{}
-	finished chan struct{}
+	Labels map[string]string
+	Params url.Values
+
+	doneCh     chan struct{}
+	finishedCh chan struct{}
+	// channel accepts new Group obj
+	// which supposed to update current group
+	updateCh chan *Group
+
+	metrics *groupMetrics
+}
+
+type groupMetrics struct {
+	iterationTotal    *utils.Counter
+	iterationDuration *utils.Summary
+}
+
+func newGroupMetrics(name, file string) *groupMetrics {
+	m := &groupMetrics{}
+	labels := fmt.Sprintf(`group=%q, file=%q`, name, file)
+	m.iterationTotal = utils.GetOrCreateCounter(fmt.Sprintf(`vmalert_iteration_total{%s}`, labels))
+	m.iterationDuration = utils.GetOrCreateSummary(fmt.Sprintf(`vmalert_iteration_duration_seconds{%s}`, labels))
+	return m
+}
+
+// merges group rule labels into result map
+// set2 has priority over set1.
+func mergeLabels(groupName, ruleName string, set1, set2 map[string]string) map[string]string {
+	r := map[string]string{}
+	for k, v := range set1 {
+		r[k] = v
+	}
+	for k, v := range set2 {
+		if prevV, ok := r[k]; ok {
+			logger.Infof("label %q=%q for rule %q.%q overwritten with external label %q=%q",
+				k, prevV, groupName, ruleName, k, v)
+		}
+		r[k] = v
+	}
+	return r
+}
+
+func newGroup(cfg config.Group, qb datasource.QuerierBuilder, defaultInterval time.Duration, labels map[string]string) *Group {
+	g := &Group{
+		Type:        cfg.Type,
+		Name:        cfg.Name,
+		File:        cfg.File,
+		Interval:    cfg.Interval.Duration(),
+		Concurrency: cfg.Concurrency,
+		Checksum:    cfg.Checksum,
+		Params:      cfg.Params,
+		Labels:      cfg.Labels,
+
+		doneCh:     make(chan struct{}),
+		finishedCh: make(chan struct{}),
+		updateCh:   make(chan *Group),
+	}
+	g.metrics = newGroupMetrics(g.Name, g.File)
+	if g.Interval == 0 {
+		g.Interval = defaultInterval
+	}
+	if g.Concurrency < 1 {
+		g.Concurrency = 1
+	}
+	rules := make([]Rule, len(cfg.Rules))
+	for i, r := range cfg.Rules {
+		var extraLabels map[string]string
+		// apply external labels
+		if len(labels) > 0 {
+			extraLabels = labels
+		}
+		// apply group labels, it has priority on external labels
+		if len(cfg.Labels) > 0 {
+			extraLabels = mergeLabels(g.Name, r.Name(), extraLabels, g.Labels)
+		}
+		// apply rules labels, it has priority on other labels
+		if len(extraLabels) > 0 {
+			r.Labels = mergeLabels(g.Name, r.Name(), extraLabels, r.Labels)
+		}
+
+		rules[i] = g.newRule(qb, r)
+	}
+	g.Rules = rules
+	return g
+}
+
+func (g *Group) newRule(qb datasource.QuerierBuilder, rule config.Rule) Rule {
+	if rule.Alert != "" {
+		return newAlertingRule(qb, g, rule)
+	}
+	return newRecordingRule(qb, g, rule)
 }
 
 // ID return unique group ID that consists of
-// rules file and group name
-func (g Group) ID() uint64 {
+// rules file and group Name
+func (g *Group) ID() uint64 {
+	g.mu.RLock()
+	defer g.mu.RUnlock()
+
 	hash := fnv.New64a()
 	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 all group rules with For > 0
-func (g *Group) Restore(ctx context.Context, q datasource.Querier, lookback time.Duration) error {
+// Restore restores alerts state for group rules
+func (g *Group) Restore(ctx context.Context, qb datasource.QuerierBuilder, lookback time.Duration, labels map[string]string) error {
+	labels = mergeLabels(g.Name, "", labels, g.Labels)
 	for _, rule := range g.Rules {
-		if rule.For == 0 {
-			return nil
+		rr, ok := rule.(*AlertingRule)
+		if !ok {
+			continue
 		}
-		if err := rule.Restore(ctx, q, lookback); err != nil {
-			return fmt.Errorf("error while restoring rule %q: %s", rule.Name, err)
+		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)
 		}
 	}
 	return nil
 }
 
 // updateWith updates existing group with
-// passed group object.
-func (g *Group) updateWith(newGroup Group) {
-	rulesRegistry := make(map[string]*Rule)
+// passed group object. This function ignores group
+// evaluation interval change. It supposed to be updated
+// in group.start function.
+// Not thread-safe.
+func (g *Group) updateWith(newGroup *Group) error {
+	rulesRegistry := make(map[uint64]Rule)
 	for _, nr := range newGroup.Rules {
-		rulesRegistry[nr.id()] = nr
+		rulesRegistry[nr.ID()] = nr
 	}
 
 	for i, or := range g.Rules {
-		nr, ok := rulesRegistry[or.id()]
+		nr, ok := rulesRegistry[or.ID()]
 		if !ok {
 			// old rule is not present in the new list
-			// and must be removed
-			or = nil
-			g.Rules = append(g.Rules[:i], g.Rules[i+1:]...)
+			// so we mark it for removing
+			g.Rules[i].Close()
+			g.Rules[i] = nil
 			continue
 		}
-
-		// copy all significant fields.
-		// alerts state isn't copied since
-		// it should be updated in next 2 Evals
-		or.For = nr.For
-		or.Expr = nr.Expr
-		or.Labels = nr.Labels
-		or.Annotations = nr.Annotations
-		delete(rulesRegistry, nr.id())
+		if err := or.UpdateWith(nr); err != nil {
+			return err
+		}
+		delete(rulesRegistry, nr.ID())
 	}
 
+	var newRules []Rule
+	for _, r := range g.Rules {
+		if r == nil {
+			// skip nil rules
+			continue
+		}
+		newRules = append(newRules, r)
+	}
+	// add the rest of rules from registry
 	for _, nr := range rulesRegistry {
-		g.Rules = append(g.Rules, nr)
+		newRules = append(newRules, nr)
 	}
+	// note that g.Interval is not updated here
+	// so the value can be compared later in
+	// group.Start function
+	g.Type = newGroup.Type
+	g.Concurrency = newGroup.Concurrency
+	g.Params = newGroup.Params
+	g.Labels = newGroup.Labels
+	g.Checksum = newGroup.Checksum
+	g.Rules = newRules
+	return nil
 }
 
-var (
-	iterationTotal    = metrics.NewCounter(`vmalert_iteration_total`)
-	iterationDuration = metrics.NewSummary(`vmalert_iteration_duration_seconds`)
-
-	execTotal    = metrics.NewCounter(`vmalert_execution_total`)
-	execErrors   = metrics.NewCounter(`vmalert_execution_errors_total`)
-	execDuration = metrics.NewSummary(`vmalert_execution_duration_seconds`)
-
-	alertsFired      = metrics.NewCounter(`vmalert_alerts_fired_total`)
-	alertsSent       = metrics.NewCounter(`vmalert_alerts_sent_total`)
-	alertsSendErrors = metrics.NewCounter(`vmalert_alerts_send_errors_total`)
-
-	remoteWriteSent   = metrics.NewCounter(`vmalert_remotewrite_sent_total`)
-	remoteWriteErrors = metrics.NewCounter(`vmalert_remotewrite_errors_total`)
-)
-
 func (g *Group) close() {
-	if g.done == nil {
+	if g.doneCh == nil {
 		return
 	}
-	close(g.done)
-	<-g.finished
+	close(g.doneCh)
+	<-g.finishedCh
+
+	g.metrics.iterationDuration.Unregister()
+	g.metrics.iterationTotal.Unregister()
+	for _, rule := range g.Rules {
+		rule.Close()
+	}
 }
 
-func (g *Group) start(ctx context.Context, interval time.Duration,
-	querier datasource.Querier, nr notifier.Notifier, rw *remotewrite.Client) {
-	logger.Infof("group %q started", g.Name)
-	t := time.NewTicker(interval)
+var skipRandSleepOnGroupStart bool
+
+func (g *Group) start(ctx context.Context, nts func() []notifier.Notifier, rw *remotewrite.Client) {
+	defer func() { close(g.finishedCh) }()
+
+	// Spread group rules evaluation over time in order to reduce load on VictoriaMetrics.
+	if !skipRandSleepOnGroupStart {
+		randSleep := uint64(float64(g.Interval) * (float64(g.ID()) / (1 << 64)))
+		sleepOffset := uint64(time.Now().UnixNano()) % uint64(g.Interval)
+		if randSleep < sleepOffset {
+			randSleep += uint64(g.Interval)
+		}
+		randSleep -= sleepOffset
+		sleepTimer := time.NewTimer(time.Duration(randSleep))
+		select {
+		case <-ctx.Done():
+			sleepTimer.Stop()
+			return
+		case <-g.doneCh:
+			sleepTimer.Stop()
+			return
+		case <-sleepTimer.C:
+		}
+	}
+
+	logger.Infof("group %q started; interval=%v; concurrency=%d", g.Name, g.Interval, g.Concurrency)
+	e := &executor{rw: rw, notifiers: nts}
+	t := time.NewTicker(g.Interval)
 	defer t.Stop()
 	for {
 		select {
 		case <-ctx.Done():
 			logger.Infof("group %q: context cancelled", g.Name)
-			close(g.finished)
 			return
-		case <-g.done:
+		case <-g.doneCh:
 			logger.Infof("group %q: received stop signal", g.Name)
-			close(g.finished)
 			return
+		case ng := <-g.updateCh:
+			g.mu.Lock()
+			err := g.updateWith(ng)
+			if err != nil {
+				logger.Errorf("group %q: failed to update: %s", g.Name, err)
+				g.mu.Unlock()
+				continue
+			}
+			if g.Interval != ng.Interval {
+				g.Interval = ng.Interval
+				t.Stop()
+				t = time.NewTicker(g.Interval)
+			}
+			g.mu.Unlock()
+			logger.Infof("group %q re-started; interval=%v; concurrency=%d", g.Name, g.Interval, g.Concurrency)
 		case <-t.C:
-			iterationTotal.Inc()
+			g.metrics.iterationTotal.Inc()
 			iterationStart := time.Now()
-			for _, rule := range g.Rules {
-				execTotal.Inc()
-
-				execStart := time.Now()
-				err := rule.Exec(ctx, querier)
-				execDuration.UpdateDuration(execStart)
-
-				if err != nil {
-					execErrors.Inc()
-					logger.Errorf("failed to execute rule %q.%q: %s", g.Name, rule.Name, err)
-					continue
-				}
-
-				var alertsToSend []notifier.Alert
-				for _, a := range rule.alerts {
-					if a.State != notifier.StatePending {
-						alertsToSend = append(alertsToSend, *a)
-					}
-					if a.State == notifier.StateInactive || rw == nil {
-						continue
-					}
-					tss := rule.AlertToTimeSeries(a, execStart)
-					for _, ts := range tss {
-						remoteWriteSent.Inc()
-						if err := rw.Push(ts); err != nil {
-							remoteWriteErrors.Inc()
-							logger.Errorf("failed to push timeseries to remotewrite: %s", err)
-						}
-					}
-				}
-				if len(alertsToSend) > 0 {
-					alertsSent.Add(len(alertsToSend))
-					if err := nr.Send(ctx, alertsToSend); err != nil {
-						alertsSendErrors.Inc()
-						logger.Errorf("failed to send alert for rule %q.%q: %s", g.Name, rule.Name, err)
+			if len(g.Rules) > 0 {
+				resolveDuration := getResolveDuration(g.Interval)
+				errs := e.execConcurrently(ctx, g.Rules, g.Concurrency, resolveDuration)
+				for err := range errs {
+					if err != nil {
+						logger.Errorf("group %q: %s", g.Name, err)
 					}
 				}
 			}
-			iterationDuration.UpdateDuration(iterationStart)
+			g.metrics.iterationDuration.UpdateDuration(iterationStart)
 		}
 	}
 }
+
+// resolveDuration for alerts is equal to 3 interval evaluations
+// so in case if vmalert stops sending updates for some reason,
+// notifier could automatically resolve the alert.
+func getResolveDuration(groupInterval time.Duration) time.Duration {
+	resolveInterval := groupInterval * 3
+	if *maxResolveDuration > 0 && (resolveInterval > *maxResolveDuration) {
+		return *maxResolveDuration
+	}
+	return resolveInterval
+}
+
+type executor struct {
+	notifiers func() []notifier.Notifier
+	rw        *remotewrite.Client
+}
+
+func (e *executor) execConcurrently(ctx context.Context, rules []Rule, concurrency int, resolveDuration time.Duration) chan error {
+	res := make(chan error, len(rules))
+	if concurrency == 1 {
+		// fast path
+		for _, rule := range rules {
+			res <- e.exec(ctx, rule, resolveDuration)
+		}
+		close(res)
+		return res
+	}
+
+	sem := make(chan struct{}, concurrency)
+	go func() {
+		wg := sync.WaitGroup{}
+		for _, rule := range rules {
+			sem <- struct{}{}
+			wg.Add(1)
+			go func(r Rule) {
+				res <- e.exec(ctx, r, resolveDuration)
+				<-sem
+				wg.Done()
+			}(rule)
+		}
+		wg.Wait()
+		close(res)
+	}()
+	return res
+}
+
+var (
+	alertsFired = metrics.NewCounter(`vmalert_alerts_fired_total`)
+
+	execTotal  = metrics.NewCounter(`vmalert_execution_total`)
+	execErrors = metrics.NewCounter(`vmalert_execution_errors_total`)
+
+	remoteWriteErrors = metrics.NewCounter(`vmalert_remotewrite_errors_total`)
+	remoteWriteTotal  = metrics.NewCounter(`vmalert_remotewrite_total`)
+)
+
+func (e *executor) exec(ctx context.Context, rule Rule, resolveDuration time.Duration) error {
+	execTotal.Inc()
+
+	tss, err := rule.Exec(ctx)
+	if err != nil {
+		execErrors.Inc()
+		return fmt.Errorf("rule %q: failed to execute: %w", rule, err)
+	}
+
+	if len(tss) > 0 && e.rw != nil {
+		for _, ts := range tss {
+			remoteWriteTotal.Inc()
+			if err := e.rw.Push(ts); err != nil {
+				remoteWriteErrors.Inc()
+				return fmt.Errorf("rule %q: remote write failure: %w", rule, err)
+			}
+		}
+	}
+
+	ar, ok := rule.(*AlertingRule)
+	if !ok {
+		return nil
+	}
+	var alerts []notifier.Alert
+	for _, a := range ar.alerts {
+		switch a.State {
+		case notifier.StateFiring:
+			a.End = time.Now().Add(resolveDuration)
+			alerts = append(alerts, *a)
+		case notifier.StateInactive:
+			// set End to execStart to notify
+			// that it was just resolved
+			a.End = time.Now()
+			alerts = append(alerts, *a)
+		}
+	}
+	if len(alerts) < 1 {
+		return nil
+	}
+
+	errGr := new(utils.ErrGroup)
+	for _, nt := range e.notifiers() {
+		if err := nt.Send(ctx, alerts); err != nil {
+			errGr.Add(fmt.Errorf("rule %q: failed to send alerts to addr %q: %w", rule, nt.Addr(), err))
+		}
+	}
+	return errGr.Err()
+}

app/vmalert/group_test.go

@@ -2,32 +2,39 @@ package main
 
 import (
 	"context"
-	"reflect"
+	"fmt"
 	"sort"
-	"sync"
 	"testing"
 	"time"
 
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/config"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promutils"
 )
 
+func init() {
+	// Disable rand sleep on group start during tests in order to speed up test execution.
+	// Rand sleep is needed only in prod code.
+	skipRandSleepOnGroupStart = true
+}
+
 func TestUpdateWith(t *testing.T) {
 	testCases := []struct {
 		name         string
-		currentRules []*Rule
-		newRules     []*Rule
+		currentRules []config.Rule
+		newRules     []config.Rule
 	}{
 		{
 			"new rule",
-			[]*Rule{},
-			[]*Rule{{Name: "bar"}},
+			nil,
+			[]config.Rule{{Alert: "bar"}},
 		},
 		{
-			"update rule",
-			[]*Rule{{
-				Name: "foo",
-				Expr: "up > 0",
-				For:  time.Second,
+			"update alerting rule",
+			[]config.Rule{{
+				Alert: "foo",
+				Expr:  "up > 0",
+				For:   promutils.NewDuration(time.Second),
 				Labels: map[string]string{
 					"bar": "baz",
 				},
@@ -36,10 +43,10 @@ func TestUpdateWith(t *testing.T) {
 					"description": "{{$labels}}",
 				},
 			}},
-			[]*Rule{{
-				Name: "bar",
-				Expr: "up > 10",
-				For:  time.Second,
+			[]config.Rule{{
+				Alert: "foo",
+				Expr:  "up > 10",
+				For:   promutils.NewDuration(time.Second),
 				Labels: map[string]string{
 					"baz": "bar",
 				},
@@ -48,43 +55,97 @@ func TestUpdateWith(t *testing.T) {
 				},
 			}},
 		},
+		{
+			"update recording rule",
+			[]config.Rule{{
+				Record: "foo",
+				Expr:   "max(up)",
+				Labels: map[string]string{
+					"bar": "baz",
+				},
+			}},
+			[]config.Rule{{
+				Record: "foo",
+				Expr:   "min(up)",
+				Labels: map[string]string{
+					"baz": "bar",
+				},
+			}},
+		},
 		{
 			"empty rule",
-			[]*Rule{{Name: "foo"}},
-			[]*Rule{},
+			[]config.Rule{{Alert: "foo"}, {Record: "bar"}},
+			nil,
 		},
 		{
 			"multiple rules",
-			[]*Rule{{Name: "foo"}, {Name: "bar"}, {Name: "baz"}},
-			[]*Rule{{Name: "foo"}, {Name: "baz"}},
+			[]config.Rule{
+				{Alert: "bar"},
+				{Alert: "baz"},
+				{Alert: "foo"},
+			},
+			[]config.Rule{
+				{Alert: "baz"},
+				{Record: "foo"},
+			},
+		},
+		{
+			"replace rule",
+			[]config.Rule{{Alert: "foo1"}},
+			[]config.Rule{{Alert: "foo2"}},
+		},
+		{
+			"replace multiple rules",
+			[]config.Rule{
+				{Alert: "foo1"},
+				{Record: "foo2"},
+				{Alert: "foo3"},
+			},
+			[]config.Rule{
+				{Alert: "foo3"},
+				{Alert: "foo4"},
+				{Record: "foo5"},
+			},
 		},
 	}
 
 	for _, tc := range testCases {
 		t.Run(tc.name, func(t *testing.T) {
-			g := &Group{Rules: tc.currentRules}
-			g.updateWith(Group{Rules: tc.newRules})
+			g := &Group{Name: "test"}
+			qb := &fakeQuerier{}
+			for _, r := range tc.currentRules {
+				r.ID = config.HashRule(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(qb, r))
+			}
+
+			err := g.updateWith(ng)
+			if err != nil {
+				t.Fatal(err)
+			}
 
 			if len(g.Rules) != len(tc.newRules) {
 				t.Fatalf("expected to have %d rules; got: %d",
 					len(g.Rules), len(tc.newRules))
 			}
+			sort.Slice(g.Rules, func(i, j int) bool {
+				return g.Rules[i].ID() < g.Rules[j].ID()
+			})
+			sort.Slice(ng.Rules, func(i, j int) bool {
+				return ng.Rules[i].ID() < ng.Rules[j].ID()
+			})
 			for i, r := range g.Rules {
-				got, want := r, tc.newRules[i]
-				if got.Name != want.Name {
-					t.Fatalf("expected to have rule %q; got %q", want.Name, got.Name)
+				got, want := r, ng.Rules[i]
+				if got.ID() != want.ID() {
+					t.Fatalf("expected to have rule %q; got %q", want, got)
 				}
-				if got.Expr != want.Expr {
-					t.Fatalf("expected to have expression %q; got %q", want.Expr, got.Expr)
-				}
-				if got.For != want.For {
-					t.Fatalf("expected to have for %q; got %q", want.For, got.For)
-				}
-				if !reflect.DeepEqual(got.Annotations, want.Annotations) {
-					t.Fatalf("expected to have annotations %#v; got %#v", want.Annotations, got.Annotations)
-				}
-				if !reflect.DeepEqual(got.Labels, want.Labels) {
-					t.Fatalf("expected to have labels %#v; got %#v", want.Labels, got.Labels)
+				if err := compareRules(t, got, want); err != nil {
+					t.Fatalf("comparsion error: %s", err)
 				}
 			}
 		})
@@ -93,40 +154,65 @@ func TestUpdateWith(t *testing.T) {
 
 func TestGroupStart(t *testing.T) {
 	// TODO: make parsing from string instead of file
-	groups, err := Parse([]string{"testdata/rules1-good.rules"}, true)
+	groups, err := config.Parse([]string{"config/testdata/rules1-good.rules"}, true, true)
 	if err != nil {
 		t.Fatalf("failed to parse rules: %s", err)
 	}
-	g := groups[0]
-
-	fn := &fakeNotifier{}
+	const evalInterval = time.Millisecond
 	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]
-	alert1, err := r.newAlert(m1)
+	r := g.Rules[0].(*AlertingRule)
+	alert1, err := r.newAlert(m1, time.Now(), nil)
 	if err != nil {
 		t.Fatalf("faield to create alert: %s", err)
 	}
 	alert1.State = notifier.StateFiring
-	alert1.ID = hash(m1)
+	// add external label
+	alert1.Labels["cluster"] = "east-1"
+	// add rule labels - see config/testdata/rules1-good.rules
+	alert1.Labels["label"] = "bar"
+	alert1.Labels["host"] = inst1
+	// add service labels
+	alert1.Labels[alertNameLabel] = alert1.Name
+	alert1.Labels[alertGroupNameLabel] = g.Name
+	var labels1 []string
+	for k, v := range alert1.Labels {
+		labels1 = append(labels1, k, v)
+	}
+	alert1.ID = hash(metricWithLabels(t, labels1...))
 
-	alert2, err := r.newAlert(m2)
+	alert2, err := r.newAlert(m2, time.Now(), nil)
 	if err != nil {
 		t.Fatalf("faield to create alert: %s", err)
 	}
 	alert2.State = notifier.StateFiring
-	alert2.ID = hash(m2)
+	// add external label
+	alert2.Labels["cluster"] = "east-1"
+	// add rule labels - see config/testdata/rules1-good.rules
+	alert2.Labels["label"] = "bar"
+	alert2.Labels["host"] = inst2
+	// add service labels
+	alert2.Labels[alertNameLabel] = alert2.Name
+	alert2.Labels[alertGroupNameLabel] = g.Name
+	var labels2 []string
+	for k, v := range alert2.Labels {
+		labels2 = append(labels2, k, v)
+	}
+	alert2.ID = hash(metricWithLabels(t, labels2...))
 
-	const evalInterval = time.Millisecond
 	finished := make(chan struct{})
 	fs.add(m1)
 	fs.add(m2)
 	go func() {
-		g.start(context.Background(), evalInterval, fs, fn, nil)
+		g.start(context.Background(), func() []notifier.Notifier { return []notifier.Notifier{fn} }, nil)
 		close(finished)
 	}()
 
@@ -153,51 +239,26 @@ func TestGroupStart(t *testing.T) {
 	<-finished
 }
 
-func compareAlerts(t *testing.T, as, bs []notifier.Alert) {
-	t.Helper()
-	if len(as) != len(bs) {
-		t.Fatalf("expected to have length %d; got %d", len(as), len(bs))
+func TestResolveDuration(t *testing.T) {
+	testCases := []struct {
+		groupInterval time.Duration
+		maxDuration   time.Duration
+		expected      time.Duration
+	}{
+		{time.Minute, 0, 3 * time.Minute},
+		{3 * time.Minute, 0, 9 * time.Minute},
+		{time.Minute, 2 * time.Minute, 2 * time.Minute},
+		{0, 0, 0},
 	}
-	sort.Slice(as, func(i, j int) bool {
-		return as[i].ID < as[j].ID
-	})
-	sort.Slice(bs, func(i, j int) bool {
-		return bs[i].ID < bs[j].ID
-	})
-	for i := range as {
-		a, b := as[i], bs[i]
-		if a.Name != b.Name {
-			t.Fatalf("expected t have Name %q; got %q", a.Name, b.Name)
-		}
-		if a.State != b.State {
-			t.Fatalf("expected t have State %q; got %q", a.State, b.State)
-		}
-		if a.Value != b.Value {
-			t.Fatalf("expected t have Value %f; got %f", a.Value, b.Value)
-		}
-		if !reflect.DeepEqual(a.Annotations, b.Annotations) {
-			t.Fatalf("expected to have annotations %#v; got %#v", a.Annotations, b.Annotations)
-		}
-		if !reflect.DeepEqual(a.Labels, b.Labels) {
-			t.Fatalf("expected to have labels %#v; got %#v", a.Labels, b.Labels)
-		}
+	defaultResolveDuration := *maxResolveDuration
+	defer func() { *maxResolveDuration = defaultResolveDuration }()
+	for _, tc := range testCases {
+		t.Run(fmt.Sprintf("%v-%v-%v", tc.groupInterval, tc.expected, tc.maxDuration), func(t *testing.T) {
+			*maxResolveDuration = tc.maxDuration
+			got := getResolveDuration(tc.groupInterval)
+			if got != tc.expected {
+				t.Errorf("expected to have %v; got %v", tc.expected, got)
+			}
+		})
 	}
 }
-
-type fakeNotifier struct {
-	sync.Mutex
-	alerts []notifier.Alert
-}
-
-func (fn *fakeNotifier) Send(_ context.Context, alerts []notifier.Alert) error {
-	fn.Lock()
-	defer fn.Unlock()
-	fn.alerts = alerts
-	return nil
-}
-
-func (fn *fakeNotifier) getAlerts() []notifier.Alert {
-	fn.Lock()
-	defer fn.Unlock()
-	return fn.alerts
-}

app/vmalert/helpers_test.go

@@ -0,0 +1,254 @@
+package main
+
+import (
+	"context"
+	"fmt"
+	"reflect"
+	"sort"
+	"sync"
+	"testing"
+	"time"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
+)
+
+type fakeQuerier struct {
+	sync.Mutex
+	metrics []datasource.Metric
+	err     error
+}
+
+func (fq *fakeQuerier) setErr(err error) {
+	fq.Lock()
+	fq.err = err
+	fq.Unlock()
+}
+
+func (fq *fakeQuerier) reset() {
+	fq.Lock()
+	fq.err = nil
+	fq.metrics = fq.metrics[:0]
+	fq.Unlock()
+}
+
+func (fq *fakeQuerier) add(metrics ...datasource.Metric) {
+	fq.Lock()
+	fq.metrics = append(fq.metrics, metrics...)
+	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()
+	if fq.err != nil {
+		return nil, fq.err
+	}
+	cp := make([]datasource.Metric, len(fq.metrics))
+	copy(cp, fq.metrics)
+	return cp, nil
+}
+
+type fakeNotifier struct {
+	sync.Mutex
+	alerts []notifier.Alert
+}
+
+func (*fakeNotifier) Close()       {}
+func (*fakeNotifier) Addr() string { return "" }
+func (fn *fakeNotifier) Send(_ context.Context, alerts []notifier.Alert) error {
+	fn.Lock()
+	defer fn.Unlock()
+	fn.alerts = alerts
+	return nil
+}
+
+func (fn *fakeNotifier) getAlerts() []notifier.Alert {
+	fn.Lock()
+	defer fn.Unlock()
+	return fn.alerts
+}
+
+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.Values = values
+	for i := range values {
+		m.Timestamps = append(m.Timestamps, int64(i))
+	}
+	return m
+}
+
+func metricWithLabels(t *testing.T, labels ...string) datasource.Metric {
+	t.Helper()
+	if len(labels) == 0 || len(labels)%2 != 0 {
+		t.Fatalf("expected to get even number of labels")
+	}
+	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],
+			Value: labels[i+1],
+		})
+	}
+	return m
+}
+
+func compareGroups(t *testing.T, a, b *Group) {
+	t.Helper()
+	if a.Name != b.Name {
+		t.Fatalf("expected group name %q; got %q", a.Name, b.Name)
+	}
+	if a.File != b.File {
+		t.Fatalf("expected group %q file name %q; got %q", a.Name, a.File, b.File)
+	}
+	if a.Interval != b.Interval {
+		t.Fatalf("expected group %q interval %v; got %v", a.Name, a.Interval, b.Interval)
+	}
+	if len(a.Rules) != len(b.Rules) {
+		t.Fatalf("expected group %s to have %d rules; got: %d",
+			a.Name, len(a.Rules), len(b.Rules))
+	}
+	for i, r := range a.Rules {
+		got, want := r, b.Rules[i]
+		if a.ID() != b.ID() {
+			t.Fatalf("expected to have rule %q; got %q", want.ID(), got.ID())
+		}
+		if err := compareRules(t, want, got); err != nil {
+			t.Fatalf("comparsion error: %s", err)
+		}
+	}
+}
+
+func compareRules(t *testing.T, a, b Rule) error {
+	t.Helper()
+	switch v := a.(type) {
+	case *AlertingRule:
+		br, ok := b.(*AlertingRule)
+		if !ok {
+			return fmt.Errorf("rule %q supposed to be of type AlertingRule", b.ID())
+		}
+		return compareAlertingRules(t, v, br)
+	case *RecordingRule:
+		br, ok := b.(*RecordingRule)
+		if !ok {
+			return fmt.Errorf("rule %q supposed to be of type RecordingRule", b.ID())
+		}
+		return compareRecordingRules(t, v, br)
+	default:
+		return fmt.Errorf("unexpected rule type received %T", a)
+	}
+}
+
+func compareRecordingRules(t *testing.T, a, b *RecordingRule) error {
+	t.Helper()
+	if a.Expr != b.Expr {
+		return fmt.Errorf("expected to have expression %q; got %q", a.Expr, b.Expr)
+	}
+	if !reflect.DeepEqual(a.Labels, b.Labels) {
+		return fmt.Errorf("expected to have labels %#v; got %#v", a.Labels, b.Labels)
+	}
+	return nil
+}
+
+func compareAlertingRules(t *testing.T, a, b *AlertingRule) error {
+	t.Helper()
+	if a.Expr != b.Expr {
+		return fmt.Errorf("expected to have expression %q; got %q", a.Expr, b.Expr)
+	}
+	if a.For != b.For {
+		return fmt.Errorf("expected to have for %q; got %q", a.For, b.For)
+	}
+	if !reflect.DeepEqual(a.Annotations, b.Annotations) {
+		return fmt.Errorf("expected to have annotations %#v; got %#v", a.Annotations, b.Annotations)
+	}
+	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
+}
+
+func compareTimeSeries(t *testing.T, a, b []prompbmarshal.TimeSeries) error {
+	t.Helper()
+	if len(a) != len(b) {
+		return fmt.Errorf("expected number of timeseries %d; got %d", len(a), len(b))
+	}
+	for i := range a {
+		expTS, gotTS := a[i], b[i]
+		if len(expTS.Samples) != len(gotTS.Samples) {
+			return fmt.Errorf("expected number of samples %d; got %d", len(expTS.Samples), len(gotTS.Samples))
+		}
+		for i, exp := range expTS.Samples {
+			got := gotTS.Samples[i]
+			if got.Value != exp.Value {
+				return fmt.Errorf("expected value %.2f; got %.2f", exp.Value, got.Value)
+			}
+			// timestamp validation isn't always correct for now.
+			// this must be improved with time mock.
+			/*if got.Timestamp != exp.Timestamp {
+				return fmt.Errorf("expected timestamp %d; got %d", exp.Timestamp, got.Timestamp)
+			}*/
+		}
+		if len(expTS.Labels) != len(gotTS.Labels) {
+			return fmt.Errorf("expected number of labels %d (%v); got %d (%v)",
+				len(expTS.Labels), expTS.Labels, len(gotTS.Labels), gotTS.Labels)
+		}
+		for i, exp := range expTS.Labels {
+			got := gotTS.Labels[i]
+			if got.Name != exp.Name {
+				return fmt.Errorf("expected label name %q; got %q", exp.Name, got.Name)
+			}
+			if got.Value != exp.Value {
+				return fmt.Errorf("expected label value %q; got %q", exp.Value, got.Value)
+			}
+		}
+	}
+	return nil
+}
+
+func compareAlerts(t *testing.T, as, bs []notifier.Alert) {
+	t.Helper()
+	if len(as) != len(bs) {
+		t.Fatalf("expected to have length %d; got %d", len(as), len(bs))
+	}
+	sort.Slice(as, func(i, j int) bool {
+		return as[i].ID < as[j].ID
+	})
+	sort.Slice(bs, func(i, j int) bool {
+		return bs[i].ID < bs[j].ID
+	})
+	for i := range as {
+		a, b := as[i], bs[i]
+		if a.Name != b.Name {
+			t.Fatalf("expected t have Name %q; got %q", a.Name, b.Name)
+		}
+		if a.State != b.State {
+			t.Fatalf("expected t have State %q; got %q", a.State, b.State)
+		}
+		if a.Value != b.Value {
+			t.Fatalf("expected t have Value %f; got %f", a.Value, b.Value)
+		}
+		if !reflect.DeepEqual(a.Annotations, b.Annotations) {
+			t.Fatalf("expected to have annotations %#v; got %#v", a.Annotations, b.Annotations)
+		}
+		if !reflect.DeepEqual(a.Labels, b.Labels) {
+			t.Fatalf("expected to have labels %#v; got %#v", a.Labels, b.Labels)
+		}
+	}
+}

app/vmalert/main.go

@@ -4,17 +4,20 @@ import (
 	"context"
 	"flag"
 	"fmt"
-	"net/http"
 	"net/url"
 	"os"
+	"strconv"
 	"strings"
 	"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/remoteread"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/remotewrite"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/buildinfo"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/envflag"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/fasttime"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
@@ -23,100 +26,125 @@ 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, 
-absolute path to all .yaml files in root.`)
-	validateTemplates = flag.Bool("rule.validateTemplates", true, "Indicates to validate annotation and label templates")
-	httpListenAddr    = flag.String("httpListenAddr", ":8880", "Address to listen for http connections")
+ -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.`)
 
-	datasourceURL = flag.String("datasource.url", "", "Victoria Metrics or VMSelect url. Required parameter."+
-		" E.g. http://127.0.0.1:8428")
-	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")
+	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. DEPRECATED - see '-configCheckInterval' instead")
 
-	remoteWriteURL = flag.String("remotewrite.url", "", "Optional URL to Victoria Metrics or VMInsert where to persist alerts state"+
-		" in form of timeseries. E.g. http://127.0.0.1:8428")
-	remoteWriteUsername = flag.String("remotewrite.basicAuth.username", "", "Optional basic auth username for -remotewrite.url")
-	remoteWritePassword = flag.String("remotewrite.basicAuth.password", "", "Optional basic auth password for -remotewrite.url")
+	configCheckInterval = flag.Duration("configCheckInterval", 0, "Interval for checking for changes in '-rule' or '-notifier.config' files. "+
+		"By default the checking is disabled. Send SIGHUP signal in order to force config check for changes.")
 
-	remoteReadURL = 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")
-	remoteReadUsername = flag.String("remoteread.basicAuth.username", "", "Optional basic auth username for -remoteread.url")
-	remoteReadPassword = flag.String("remoteread.basicAuth.password", "", "Optional basic auth password for -remoteread.url")
-	remoteReadLookBack = flag.Duration("remoteread.lookback", time.Hour, "Lookback defines how far to look into past for alerts timeseries."+
+	httpListenAddr     = flag.String("httpListenAddr", ":8880", "Address to listen for http connections")
+	evaluationInterval = flag.Duration("evaluationInterval", time.Minute, "How often to evaluate the rules")
+
+	validateTemplates   = flag.Bool("rule.validateTemplates", true, "Whether to validate annotation and label templates")
+	validateExpressions = flag.Bool("rule.validateExpressions", true, "Whether to validate rules expressions via MetricsQL engine")
+	maxResolveDuration  = flag.Duration("rule.maxResolveDuration", 0, "Limits the maximum duration for automatic alert expiration, "+
+		"which is by default equal to 3 evaluation intervals of the parent group.")
+	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|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.")
 
-	evaluationInterval = flag.Duration("evaluationInterval", time.Minute, "How often to evaluate the rules. Default 1m")
-	notifierURL        = flag.String("notifier.url", "", "Prometheus alertmanager URL. Required parameter. e.g. http://127.0.0.1:9093")
-	externalURL        = flag.String("external.url", "", "External URL is used as alert's source for sent alerts to the notifier")
+	disableAlertGroupLabel = flag.Bool("disableAlertgroupLabel", false, "Whether to disable adding group's Name as label to generated alerts and time series.")
+
+	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.")
 )
 
+var alertURLGeneratorFn notifier.AlertURLGenerator
+
 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()
-	checkFlags()
-	ctx, cancel := context.WithCancel(context.Background())
+
+	if *dryRun {
+		u, _ := url.Parse("https://victoriametrics.com/")
+		notifier.InitTemplateFunc(u)
+		groups, err := config.Parse(*rulePath, true, true)
+		if err != nil {
+			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
+	}
+
 	eu, err := getExternalURL(*externalURL, *httpListenAddr, httpserver.IsTLS())
 	if err != nil {
-		logger.Fatalf("can not get external url: %s ", err)
+		logger.Fatalf("failed to init `external.url`: %s", err)
 	}
 	notifier.InitTemplateFunc(eu)
-
-	manager := &manager{
-		groups:  make(map[uint64]*Group),
-		storage: datasource.NewVMStorage(*datasourceURL, *basicAuthUsername, *basicAuthPassword, &http.Client{}),
-		notifier: notifier.NewAlertManager(*notifierURL, func(group, alert string) string {
-			return fmt.Sprintf("%s/api/v1/%s/%s/status", eu, group, alert)
-		}, &http.Client{}),
+	alertURLGeneratorFn, err = getAlertURLGenerator(eu, *externalAlertSource, *validateTemplates)
+	if err != nil {
+		logger.Fatalf("failed to init `external.alert.source`: %s", err)
 	}
-	if *remoteWriteURL != "" {
-		c, err := remotewrite.NewClient(ctx, remotewrite.Config{
-			Addr:          *remoteWriteURL,
-			FlushInterval: *evaluationInterval,
-			BasicAuthUser: *remoteWriteUsername,
-			BasicAuthPass: *remoteWritePassword,
-		})
+
+	if *replayFrom != "" || *replayTo != "" {
+		rw, err := remotewrite.Init(context.Background())
 		if err != nil {
-			logger.Fatalf("failed to init remotewrite client: %s", err)
+			logger.Fatalf("failed to init remoteWrite: %s", err)
 		}
-		manager.rw = c
-	}
-	if *remoteReadURL != "" {
-		manager.rr = datasource.NewVMStorage(*remoteReadURL, *remoteReadUsername, *remoteReadPassword, &http.Client{})
+		if rw == nil {
+			logger.Fatalf("remoteWrite.url can't be empty in replay mode")
+		}
+		notifier.InitTemplateFunc(eu)
+		groupsCfg, err := config.Parse(*rulePath, *validateTemplates, *validateExpressions)
+		if err != nil {
+			logger.Fatalf("cannot parse configuration file: %s", err)
+		}
+		// prevent queries from caching and boundaries aligning
+		// when querying VictoriaMetrics datasource.
+		q, err := datasource.Init(url.Values{"nocache": {"1"}})
+		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
 	}
 
-	if err := manager.start(ctx, *rulePath, *validateTemplates); err != nil {
+	ctx, cancel := context.WithCancel(context.Background())
+	manager, err := newManager(ctx)
+	if err != nil {
+		logger.Fatalf("failed to init: %s", err)
+	}
+
+	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)
+	}
+
+	// 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()
+
+	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(uint64(time.Now().UnixNano()) / 1e9)
-		sigHup := procutil.NewSighupChan()
-		for {
-			<-sigHup
-			configReloads.Inc()
-			logger.Infof("SIGHUP received. Going to reload rules %q ...", *rulePath)
-			if err := manager.update(ctx, *rulePath, *validateTemplates, false); err != nil {
-				configReloadErrors.Inc()
-				configSuccess.Set(0)
-				logger.Errorf("error while reloading rules: %s", err)
-				continue
-			}
-			configSuccess.Set(1)
-			configTimestamp.Set(uint64(time.Now().UnixNano()) / 1e9)
-			logger.Infof("Rules reloaded successfully from %q", *rulePath)
-		}
-	}()
+	go configReload(ctx, manager, groupsCfg, sighupCh)
 
 	rh := &requestHandler{m: manager}
-	go httpserver.Serve(*httpListenAddr, (rh).handler)
+	go httpserver.Serve(*httpListenAddr, rh.handler)
 
 	sig := procutil.WaitForSigterm()
 	logger.Infof("service received signal %s", sig)
@@ -134,6 +162,49 @@ var (
 	configTimestamp    = metrics.NewCounter(`vmalert_config_last_reload_success_timestamp_seconds`)
 )
 
+func newManager(ctx context.Context) (*manager, error) {
+	q, err := datasource.Init(nil)
+	if err != nil {
+		return nil, fmt.Errorf("failed to init datasource: %w", err)
+	}
+
+	labels := make(map[string]string, 0)
+	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)
+		}
+		labels[s[:n]] = s[n+1:]
+	}
+
+	nts, err := notifier.Init(alertURLGeneratorFn, labels, *externalURL)
+	if err != nil {
+		return nil, fmt.Errorf("failed to init notifier: %w", err)
+	}
+	manager := &manager{
+		groups:         make(map[uint64]*Group),
+		querierBuilder: q,
+		notifiers:      nts,
+		labels:         labels,
+	}
+	rw, err := remotewrite.Init(ctx)
+	if err != nil {
+		return nil, fmt.Errorf("failed to init remoteWrite: %w", err)
+	}
+	manager.rw = rw
+
+	rr, err := remoteread.Init()
+	if err != nil {
+		return nil, fmt.Errorf("failed to init remoteRead: %w", err)
+	}
+	manager.rr = rr
+
+	return manager, nil
+}
+
 func getExternalURL(externalURL, httpListenAddr string, isSecure bool) (*url.URL, error) {
 	if externalURL != "" {
 		return url.Parse(externalURL)
@@ -153,13 +224,106 @@ func getExternalURL(externalURL, httpListenAddr string, isSecure bool) (*url.URL
 	return url.Parse(fmt.Sprintf("%s%s%s", schema, hname, port))
 }
 
-func checkFlags() {
-	if *notifierURL == "" {
-		flag.PrintDefaults()
-		logger.Fatalf("notifier.url is empty")
+func getAlertURLGenerator(externalURL *url.URL, externalAlertSource string, validateTemplate bool) (notifier.AlertURLGenerator, error) {
+	if externalAlertSource == "" {
+		return func(alert notifier.Alert) string {
+			return fmt.Sprintf("%s/api/v1/%s/%s/status", externalURL, strconv.FormatUint(alert.GroupID, 10), strconv.FormatUint(alert.ID, 10))
+		}, nil
 	}
-	if *datasourceURL == "" {
-		flag.PrintDefaults()
-		logger.Fatalf("datasource.url is empty")
+	if validateTemplate {
+		if err := notifier.ValidateTemplates(map[string]string{
+			"tpl": externalAlertSource,
+		}); err != nil {
+			return nil, fmt.Errorf("error validating source template %s: %w", externalAlertSource, err)
+		}
+	}
+	m := map[string]string{
+		"tpl": externalAlertSource,
+	}
+	return func(alert notifier.Alert) string {
+		templated, err := alert.ExecTemplate(nil, m)
+		if err != nil {
+			logger.Errorf("can not exec source template %s", err)
+		}
+		return fmt.Sprintf("%s/%s", externalURL, templated["tpl"])
+	}, nil
+}
+
+func usage() {
+	const s = `
+vmalert processes alerts and recording rules.
+
+See the docs at https://docs.victoriametrics.com/vmalert.html .
+`
+	flagutil.Usage(s)
+}
+
+func configReload(ctx context.Context, m *manager, groupsCfg []config.Group, sighupCh <-chan os.Signal) {
+	var configCheckCh <-chan time.Time
+	checkInterval := *configCheckInterval
+	if checkInterval == 0 && *rulesCheckInterval > 0 {
+		logger.Warnf("flag `rule.configCheckInterval` is deprecated - use `configCheckInterval` instead")
+		checkInterval = *rulesCheckInterval
+	}
+	if checkInterval > 0 {
+		ticker := time.NewTicker(checkInterval)
+		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:
+		}
+		if err := notifier.Reload(); err != nil {
+			configReloadErrors.Inc()
+			configSuccess.Set(0)
+			logger.Errorf("failed to reload notifier config: %s", err)
+			continue
+		}
+		newGroupsCfg, err := config.Parse(*rulePath, *validateTemplates, *validateExpressions)
+		if err != nil {
+			configReloadErrors.Inc()
+			configSuccess.Set(0)
+			logger.Errorf("cannot parse configuration file: %s", err)
+			continue
+		}
+		if configsEqual(newGroupsCfg, groupsCfg) {
+			// set success to 1 since previous reload
+			// could have been unsuccessful
+			configSuccess.Set(1)
+			// config didn't change - skip it
+			continue
+		}
+		if err := m.update(ctx, newGroupsCfg, false); err != nil {
+			configReloadErrors.Inc()
+			configSuccess.Set(0)
+			logger.Errorf("error while reloading rules: %s", err)
+			continue
+		}
+		groupsCfg = newGroupsCfg
+		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

@@ -0,0 +1,160 @@
+package main
+
+import (
+	"context"
+	"fmt"
+	"io/ioutil"
+	"net/url"
+	"os"
+	"testing"
+	"time"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/remotewrite"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/procutil"
+)
+
+func TestGetExternalURL(t *testing.T) {
+	expURL := "https://vicotriametrics.com/path"
+	u, err := getExternalURL(expURL, "", false)
+	if err != nil {
+		t.Errorf("unexpected error %s", err)
+	}
+	if u.String() != expURL {
+		t.Errorf("unexpected url want %s, got %s", expURL, u.String())
+	}
+	h, _ := os.Hostname()
+	expURL = fmt.Sprintf("https://%s:4242", h)
+	u, err = getExternalURL("", "0.0.0.0:4242", true)
+	if err != nil {
+		t.Errorf("unexpected error %s", err)
+	}
+	if u.String() != expURL {
+		t.Errorf("unexpected url want %s, got %s", expURL, u.String())
+	}
+}
+
+func TestGetAlertURLGenerator(t *testing.T) {
+	testAlert := notifier.Alert{GroupID: 42, ID: 2, Value: 4}
+	u, _ := url.Parse("https://victoriametrics.com/path")
+	fn, err := getAlertURLGenerator(u, "", false)
+	if err != nil {
+		t.Errorf("unexpected error %s", err)
+	}
+	if exp := "https://victoriametrics.com/path/api/v1/42/2/status"; exp != fn(testAlert) {
+		t.Errorf("unexpected url want %s, got %s", exp, fn(testAlert))
+	}
+	_, err = getAlertURLGenerator(nil, "foo?{{invalid}}", true)
+	if err == nil {
+		t.Errorf("expected tempalte validation error got nil")
+	}
+	fn, err = getAlertURLGenerator(u, "foo?query={{$value}}", true)
+	if err != nil {
+		t.Errorf("unexpected error %s", err)
+	}
+	if exp := "https://victoriametrics.com/path/foo?query=4"; exp != fn(testAlert) {
+		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())
+
+	m := &manager{
+		querierBuilder: &fakeQuerier{},
+		groups:         make(map[uint64]*Group),
+		labels:         map[string]string{},
+		notifiers:      func() []notifier.Notifier { return []notifier.Notifier{&fakeNotifier{}} },
+		rw:             &remotewrite.Client{},
+	}
+
+	syncCh := make(chan struct{})
+	sighupCh := procutil.NewSighupChan()
+	go func() {
+		configReload(ctx, m, nil, sighupCh)
+		close(syncCh)
+	}()
+
+	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)
+	}
+
+	cancel()
+	<-syncCh
+}
+
+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

@@ -3,29 +3,34 @@ package main
 import (
 	"context"
 	"fmt"
-	"strings"
+	"net/url"
+	"sort"
 	"sync"
 
+	"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/remotewrite"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
 )
 
+// manager controls group states
 type manager struct {
-	storage  datasource.Querier
-	notifier notifier.Notifier
+	querierBuilder datasource.QuerierBuilder
+	notifiers      func() []notifier.Notifier
 
 	rw *remotewrite.Client
-	rr datasource.Querier
+	// remote read builder.
+	rr datasource.QuerierBuilder
 
-	wg sync.WaitGroup
+	wg     sync.WaitGroup
+	labels map[string]string
 
 	groupsMu sync.RWMutex
 	groups   map[uint64]*Group
 }
 
-// AlertAPI generates APIAlert object from alert by its id(hash)
+// AlertAPI generates APIAlert object from alert by its ID(hash)
 func (m *manager) AlertAPI(gID, aID uint64) (*APIAlert, error) {
 	m.groupsMu.RLock()
 	defer m.groupsMu.RUnlock()
@@ -35,15 +40,19 @@ func (m *manager) AlertAPI(gID, aID uint64) (*APIAlert, error) {
 		return nil, fmt.Errorf("can't find group with id %q", gID)
 	}
 	for _, rule := range g.Rules {
-		if apiAlert := rule.AlertAPI(aID); apiAlert != nil {
+		ar, ok := rule.(*AlertingRule)
+		if !ok {
+			continue
+		}
+		if apiAlert := ar.AlertAPI(aID); apiAlert != nil {
 			return apiAlert, nil
 		}
 	}
-	return nil, fmt.Errorf("can't func alert with id %q in group %q", aID, g.Name)
+	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, validate bool) error {
-	return m.update(ctx, path, validate, true)
+func (m *manager) start(ctx context.Context, groupsCfg []config.Group) error {
+	return m.update(ctx, groupsCfg, true)
 }
 
 func (m *manager) close() {
@@ -56,10 +65,13 @@ func (m *manager) close() {
 	m.wg.Wait()
 }
 
-func (m *manager) startGroup(ctx context.Context, group Group, restore bool) {
-	if restore {
-		err := group.Restore(ctx, m.rr, *remoteReadLookBack)
+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)
 		}
 	}
@@ -67,43 +79,126 @@ func (m *manager) startGroup(ctx context.Context, group Group, restore bool) {
 	m.wg.Add(1)
 	id := group.ID()
 	go func() {
-		group.start(ctx, *evaluationInterval, m.storage, m.notifier, m.rw)
+		group.start(ctx, m.notifiers, m.rw)
 		m.wg.Done()
 	}()
-	m.groups[id] = &group
+	m.groups[id] = group
+	return nil
 }
 
-func (m *manager) update(ctx context.Context, path []string, validate, restore bool) error {
-	logger.Infof("reading alert rules configuration file from %q", strings.Join(path, ";"))
-	newGroups, err := Parse(path, validate)
-	if err != nil {
-		return fmt.Errorf("cannot parse configuration file: %s", err)
-	}
-
-	groupsRegistry := make(map[uint64]Group)
-	for _, ng := range newGroups {
+func (m *manager) update(ctx context.Context, groupsCfg []config.Group, restore bool) error {
+	var rrPresent, arPresent bool
+	groupsRegistry := make(map[uint64]*Group)
+	for _, cfg := range groupsCfg {
+		for _, r := range cfg.Rules {
+			if rrPresent && arPresent {
+				continue
+			}
+			if r.Record != "" {
+				rrPresent = true
+			}
+			if r.Alert != "" {
+				arPresent = true
+			}
+		}
+		ng := newGroup(cfg, m.querierBuilder, *evaluationInterval, m.labels)
 		groupsRegistry[ng.ID()] = ng
 	}
 
+	if rrPresent && m.rw == nil {
+		return fmt.Errorf("config contains recording rules but `-remoteWrite.url` isn't set")
+	}
+	if arPresent && m.notifiers == nil {
+		return fmt.Errorf("config contains alerting rules but neither `-notifier.url` nor `-notifier.config` aren't set")
+	}
+
+	type updateItem struct {
+		old *Group
+		new *Group
+	}
+	var toUpdate []updateItem
+
 	m.groupsMu.Lock()
 	for _, og := range m.groups {
-		id := og.ID()
-		ng, ok := groupsRegistry[id]
+		ng, ok := groupsRegistry[og.ID()]
 		if !ok {
-			// old group is not present in new list
-			// and must be stopped and deleted
+			// old group is not present in new list,
+			// so must be stopped and deleted
 			og.close()
 			delete(m.groups, og.ID())
 			og = nil
 			continue
 		}
-		og.updateWith(ng)
 		delete(groupsRegistry, ng.ID())
+		if og.Checksum != ng.Checksum {
+			toUpdate = append(toUpdate, updateItem{old: og, new: ng})
+		}
 	}
-
 	for _, ng := range groupsRegistry {
-		m.startGroup(ctx, ng, restore)
+		if err := m.startGroup(ctx, ng, restore); err != nil {
+			return err
+		}
 	}
 	m.groupsMu.Unlock()
+
+	if len(toUpdate) > 0 {
+		var wg sync.WaitGroup
+		for _, item := range toUpdate {
+			wg.Add(1)
+			go func(old *Group, new *Group) {
+				old.updateCh <- new
+				wg.Done()
+			}(item.old, item.new)
+		}
+		wg.Wait()
+	}
 	return nil
 }
+
+func (g *Group) toAPI() APIGroup {
+	g.mu.RLock()
+	defer g.mu.RUnlock()
+
+	ag := APIGroup{
+		// encode as string to avoid rounding
+		ID: fmt.Sprintf("%d", g.ID()),
+
+		Name:        g.Name,
+		Type:        g.Type.String(),
+		File:        g.File,
+		Interval:    g.Interval.String(),
+		Concurrency: g.Concurrency,
+		Params:      urlValuesToStrings(g.Params),
+		Labels:      g.Labels,
+	}
+	for _, r := range g.Rules {
+		switch v := r.(type) {
+		case *AlertingRule:
+			ag.AlertingRules = append(ag.AlertingRules, v.RuleAPI())
+		case *RecordingRule:
+			ag.RecordingRules = append(ag.RecordingRules, v.RuleAPI())
+		}
+	}
+	return ag
+}
+
+func urlValuesToStrings(values url.Values) []string {
+	if len(values) < 1 {
+		return nil
+	}
+
+	keys := make([]string, 0, len(values))
+	for k := range values {
+		keys = append(keys, k)
+	}
+	sort.Strings(keys)
+
+	var res []string
+	for _, k := range keys {
+		params := values[k]
+		for _, v := range params {
+			res = append(res, fmt.Sprintf("%s=%s", k, v))
+		}
+	}
+	return res
+}

app/vmalert/manager_test.go

@@ -3,22 +3,33 @@ package main
 import (
 	"context"
 	"math/rand"
+	"net/url"
+	"os"
 	"strings"
 	"sync"
 	"testing"
 	"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/remotewrite"
 )
 
-func TestManagerUpdateError(t *testing.T) {
+func TestMain(m *testing.M) {
+	u, _ := url.Parse("https://victoriametrics.com/path")
+	notifier.InitTemplateFunc(u)
+	os.Exit(m.Run())
+}
+
+// TestManagerEmptyRulesDir tests
+// successful cases of
+// 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, false)
-	if err == nil {
-		t.Fatalf("expected to have err; got nil instead")
-	}
-	expErr := "no groups found"
-	if !strings.Contains(err.Error(), expErr) {
-		t.Fatalf("expected to got err %s; got %s", expErr, err)
+	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)
 	}
 }
 
@@ -26,24 +37,42 @@ func TestManagerUpdateError(t *testing.T) {
 // execution of configuration update.
 // Should be executed with -race flag
 func TestManagerUpdateConcurrent(t *testing.T) {
-	m := &manager{groups: make(map[uint64]*Group)}
+	m := &manager{
+		groups:         make(map[uint64]*Group),
+		querierBuilder: &fakeQuerier{},
+		notifiers:      func() []notifier.Notifier { return []notifier.Notifier{&fakeNotifier{}} },
+	}
 	paths := []string{
-		"testdata/dir/rules0-good.rules",
-		"testdata/dir/rules1-good.rules",
-		"testdata/rules0-good.rules",
+		"config/testdata/dir/rules0-good.rules",
+		"config/testdata/dir/rules0-bad.rules",
+		"config/testdata/dir/rules1-good.rules",
+		"config/testdata/dir/rules1-bad.rules",
+		"config/testdata/rules0-good.rules",
+		"config/testdata/rules1-good.rules",
+		"config/testdata/rules2-good.rules",
+	}
+	evalInterval := *evaluationInterval
+	defer func() { *evaluationInterval = evalInterval }()
+	*evaluationInterval = time.Millisecond
+	cfg := loadCfg(t, []string{paths[0]}, true, true)
+	if err := m.start(context.Background(), cfg); err != nil {
+		t.Fatalf("failed to start: %s", err)
 	}
 
-	const n = 500
+	const workers = 500
+	const iterations = 10
 	wg := sync.WaitGroup{}
-	wg.Add(n)
-	for i := 0; i < n; i++ {
+	wg.Add(workers)
+	for i := 0; i < workers; i++ {
 		go func() {
 			defer wg.Done()
-			rnd := rand.Intn(len(paths))
-			path := []string{paths[rnd]}
-			err := m.update(context.Background(), path, true, false)
-			if err != nil {
-				t.Errorf("update error: %s", err)
+			for i := 0; i < iterations; i++ {
+				rnd := rand.Intn(len(paths))
+				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)
 			}
 		}()
 	}
@@ -53,6 +82,41 @@ func TestManagerUpdateConcurrent(t *testing.T) {
 // TestManagerUpdate tests sequential configuration
 // updates.
 func TestManagerUpdate(t *testing.T) {
+	const defaultEvalInterval = time.Second * 30
+	currentEvalInterval := *evaluationInterval
+	*evaluationInterval = defaultEvalInterval
+	defer func() {
+		*evaluationInterval = currentEvalInterval
+	}()
+
+	var (
+		VMRows = &AlertingRule{
+			Name: "VMRows",
+			Expr: "vm_rows > 0",
+			For:  10 * time.Second,
+			Labels: map[string]string{
+				"label": "bar",
+				"host":  "{{ $labels.instance }}",
+			},
+			Annotations: map[string]string{
+				"summary":     "{{ $value|humanize }}",
+				"description": "{{$labels}}",
+			},
+		}
+		Conns = &AlertingRule{
+			Name: "Conns",
+			Expr: "sum(vm_tcplistener_conns) by(instance) > 1",
+			Annotations: map[string]string{
+				"summary":     "Too high connection number for {{$labels.instance}}",
+				"description": "It is {{ $value }} connections for {{$labels.instance}}",
+			},
+		}
+		ExampleAlertAlwaysFiring = &AlertingRule{
+			Name: "ExampleAlertAlwaysFiring",
+			Expr: "sum by(job) (up == 1)",
+		}
+	)
+
 	testCases := []struct {
 		name       string
 		initPath   string
@@ -61,64 +125,116 @@ func TestManagerUpdate(t *testing.T) {
 	}{
 		{
 			name:       "update good rules",
-			initPath:   "testdata/rules0-good.rules",
-			updatePath: "testdata/dir/rules1-good.rules",
+			initPath:   "config/testdata/rules0-good.rules",
+			updatePath: "config/testdata/dir/rules1-good.rules",
 			want: []*Group{
 				{
-					File:  "testdata/dir/rules1-good.rules",
-					Name:  "duplicatedGroupDiffFiles",
-					Rules: []*Rule{newTestRule("VMRows", time.Second*10)},
+					File:     "config/testdata/dir/rules1-good.rules",
+					Name:     "duplicatedGroupDiffFiles",
+					Type:     datasource.NewPrometheusType(),
+					Interval: defaultEvalInterval,
+					Rules: []Rule{
+						&AlertingRule{
+							Name:   "VMRows",
+							Expr:   "vm_rows > 0",
+							For:    5 * time.Minute,
+							Labels: map[string]string{"dc": "gcp", "label": "bar"},
+							Annotations: map[string]string{
+								"summary":     "{{ $value }}",
+								"description": "{{$labels}}",
+							},
+						},
+					},
 				},
 			},
 		},
 		{
 			name:       "update good rules from 1 to 2 groups",
-			initPath:   "testdata/dir/rules1-good.rules",
-			updatePath: "testdata/rules0-good.rules",
+			initPath:   "config/testdata/dir/rules1-good.rules",
+			updatePath: "config/testdata/rules0-good.rules",
 			want: []*Group{
 				{
-					File: "testdata/rules0-good.rules",
-					Name: "groupGorSingleAlert", Rules: []*Rule{
-						newTestRule("VMRows", time.Second*10),
-					}},
+					File:     "config/testdata/rules0-good.rules",
+					Name:     "groupGorSingleAlert",
+					Type:     datasource.NewPrometheusType(),
+					Rules:    []Rule{VMRows},
+					Interval: defaultEvalInterval,
+				},
 				{
-					File: "testdata/rules0-good.rules",
-					Name: "TestGroup", Rules: []*Rule{
-						newTestRule("Conns", time.Duration(0)),
-						newTestRule("ExampleAlertAlwaysFiring", time.Duration(0)),
+					File:     "config/testdata/rules0-good.rules",
+					Interval: defaultEvalInterval,
+					Type:     datasource.NewPrometheusType(),
+					Name:     "TestGroup", Rules: []Rule{
+						Conns,
+						ExampleAlertAlwaysFiring,
 					}},
 			},
 		},
 		{
 			name:       "update with one bad rule file",
-			initPath:   "testdata/rules0-good.rules",
-			updatePath: "testdata/dir/rules2-bad.rules",
+			initPath:   "config/testdata/rules0-good.rules",
+			updatePath: "config/testdata/dir/rules2-bad.rules",
 			want: []*Group{
 				{
-					File: "testdata/rules0-good.rules",
-					Name: "groupGorSingleAlert", Rules: []*Rule{
-						newTestRule("VMRows", time.Second*10),
-					}},
+					File:     "config/testdata/rules0-good.rules",
+					Name:     "groupGorSingleAlert",
+					Type:     datasource.NewPrometheusType(),
+					Interval: defaultEvalInterval,
+					Rules:    []Rule{VMRows},
+				},
 				{
-					File: "testdata/rules0-good.rules",
-					Name: "TestGroup", Rules: []*Rule{
-						newTestRule("Conns", time.Duration(0)),
-						newTestRule("ExampleAlertAlwaysFiring", time.Duration(0)),
+					File:     "config/testdata/rules0-good.rules",
+					Interval: defaultEvalInterval,
+					Name:     "TestGroup",
+					Type:     datasource.NewPrometheusType(),
+					Rules: []Rule{
+						Conns,
+						ExampleAlertAlwaysFiring,
 					}},
 			},
 		},
+		{
+			name:       "update empty dir rules from 0 to 2 groups",
+			initPath:   "config/testdata/empty/*",
+			updatePath: "config/testdata/rules0-good.rules",
+			want: []*Group{
+				{
+					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,
+					},
+				},
+			},
+		},
 	}
 	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)}
-			path := []string{tc.initPath}
-			if err := m.update(ctx, path, true, false); err != nil {
+			m := &manager{
+				groups:         make(map[uint64]*Group),
+				querierBuilder: &fakeQuerier{},
+				notifiers:      func() []notifier.Notifier { return []notifier.Notifier{&fakeNotifier{}} },
+			}
+
+			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, 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))
 			}
@@ -128,7 +244,7 @@ func TestManagerUpdate(t *testing.T) {
 				if !ok {
 					t.Fatalf("expected to have group %q", wantG.Name)
 				}
-				compareGroups(t, gotG, wantG)
+				compareGroups(t, wantG, gotG)
 			}
 
 			cancel()
@@ -137,16 +253,85 @@ func TestManagerUpdate(t *testing.T) {
 	}
 }
 
-func compareGroups(t *testing.T, a, b *Group) {
-	t.Helper()
-	if len(a.Rules) != len(b.Rules) {
-		t.Fatalf("expected group %s to have %d rules; got: %d",
-			a.Name, len(a.Rules), len(b.Rules))
+func TestManagerUpdateNegative(t *testing.T) {
+	testCases := []struct {
+		notifiers []notifier.Notifier
+		rw        *remotewrite.Client
+		cfg       config.Group
+		expErr    string
+	}{
+		{
+			nil,
+			nil,
+			config.Group{Name: "Recording rule only",
+				Rules: []config.Rule{
+					{Record: "record", Expr: "max(up)"},
+				},
+			},
+			"contains recording rules",
+		},
+		{
+			nil,
+			nil,
+			config.Group{Name: "Alerting rule only",
+				Rules: []config.Rule{
+					{Alert: "alert", Expr: "up > 0"},
+				},
+			},
+			"contains alerting rules",
+		},
+		{
+			[]notifier.Notifier{&fakeNotifier{}},
+			nil,
+			config.Group{Name: "Recording and alerting rules",
+				Rules: []config.Rule{
+					{Alert: "alert1", Expr: "up > 0"},
+					{Alert: "alert2", Expr: "up > 0"},
+					{Record: "record", Expr: "max(up)"},
+				},
+			},
+			"contains recording rules",
+		},
+		{
+			nil,
+			&remotewrite.Client{},
+			config.Group{Name: "Recording and alerting rules",
+				Rules: []config.Rule{
+					{Record: "record1", Expr: "max(up)"},
+					{Record: "record2", Expr: "max(up)"},
+					{Alert: "alert", Expr: "up > 0"},
+				},
+			},
+			"contains alerting rules",
+		},
 	}
-	for i, r := range a.Rules {
-		got, want := r, b.Rules[i]
-		if got.Name != want.Name {
-			t.Fatalf("expected to have rule %q; got %q", want.Name, got.Name)
-		}
+
+	for _, tc := range testCases {
+		t.Run(tc.cfg.Name, func(t *testing.T) {
+			m := &manager{
+				groups:         make(map[uint64]*Group),
+				querierBuilder: &fakeQuerier{},
+				rw:             tc.rw,
+			}
+			if tc.notifiers != nil {
+				m.notifiers = func() []notifier.Notifier { return tc.notifiers }
+			}
+			err := m.update(context.Background(), []config.Group{tc.cfg}, false)
+			if err == nil {
+				t.Fatalf("expected to get error; got nil")
+			}
+			if !strings.Contains(err.Error(), tc.expErr) {
+				t.Fatalf("expected err to contain %q; got %q", tc.expErr, err)
+			}
+		})
 	}
 }
+
+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

@@ -7,21 +7,35 @@ import (
 	"strings"
 	"text/template"
 	"time"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/utils"
 )
 
 // Alert the triggered alert
 // TODO: Looks like alert name isn't unique
 type Alert struct {
-	GroupID     uint64
-	Name        string
-	Labels      map[string]string
+	// GroupID contains the ID of the parent rules group
+	GroupID uint64
+	// Name represents Alert name
+	Name string
+	// Labels is the list of label-value pairs attached to the Alert
+	Labels map[string]string
+	// Annotations is the list of annotations generated on Alert evaluation
 	Annotations map[string]string
-	State       AlertState
-
+	// State represents the current state of the Alert
+	State AlertState
+	// Expr contains expression that was executed to generate the Alert
+	Expr string
+	// Start defines the moment of time when Alert has triggered
 	Start time.Time
-	End   time.Time
+	// End defines the moment of time when Alert supposed to expire
+	End time.Time
+	// Value stores the value returned from evaluating expression from Expr field
 	Value float64
-	ID    uint64
+	// ID is the unique identifer for the Alert
+	ID uint64
+	// Restored is true if Alert was restored after restart
+	Restored bool
 }
 
 // AlertState type indicates the Alert state
@@ -49,57 +63,81 @@ 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
 }
 
-const tplHeader = `{{ $value := .Value }}{{ $labels := .Labels }}`
+var tplHeaders = []string{
+	"{{ $value := .Value }}",
+	"{{ $labels := .Labels }}",
+	"{{ $expr := .Expr }}",
+	"{{ $externalLabels := .ExternalLabels }}",
+	"{{ $externalURL := .ExternalURL }}",
+}
 
-// 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}
-	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 := errGroup{}
+	eg := new(utils.ErrGroup)
 	r := make(map[string]string, len(annotations))
+	tData := tplData{data, externalLabels, externalURL}
+	header := strings.Join(tplHeaders, "")
 	for key, text := range annotations {
-		r[key] = text
 		buf.Reset()
 		builder.Reset()
 		builder.Grow(len(header) + len(text))
 		builder.WriteString(header)
 		builder.WriteString(text)
-		if err := templateAnnotation(&buf, builder.String(), data); err != nil {
-			eg.errs = append(eg.errs, fmt.Sprintf("key %s, template %s:%s", key, text, err))
+		if err := templateAnnotation(&buf, builder.String(), tData, funcs); err != nil {
+			r[key] = text
+			eg.Add(fmt.Errorf("key %q, template %q: %w", key, text, err))
 			continue
 		}
 		r[key] = buf.String()
 	}
-	return r, eg.err()
+	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)
+type tplData struct {
+	AlertTplData
+	ExternalLabels map[string]string
+	ExternalURL    string
+}
+
+func templateAnnotation(dst io.Writer, text string, data tplData, 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)
+		return fmt.Errorf("error parsing annotation: %w", err)
 	}
 	if err = tpl.Execute(dst, data); err != nil {
-		return fmt.Errorf("error evaluating annotation template:%w", err)
+		return fmt.Errorf("error evaluating annotation template: %w", err)
 	}
 	return nil
 }

app/vmalert/notifier/alert_test.go

@@ -3,20 +3,36 @@ package notifier
 import (
 	"fmt"
 	"testing"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
 )
 
 func TestAlert_ExecTemplate(t *testing.T) {
+	extLabels := make(map[string]string, 0)
+	const (
+		extCluster = "prod"
+		extDC      = "east"
+		extURL     = "https://foo.bar"
+	)
+	extLabels["cluster"] = extCluster
+	extLabels["dc"] = extDC
+	_, err := Init(nil, extLabels, extURL)
+	checkErr(t, err)
+
 	testCases := []struct {
+		name        string
 		alert       *Alert
 		annotations map[string]string
 		expTpl      map[string]string
 	}{
 		{
+			name:        "empty-alert",
 			alert:       &Alert{},
 			annotations: map[string]string{},
 			expTpl:      map[string]string{},
 		},
 		{
+			name: "no-template",
 			alert: &Alert{
 				Value: 1e4,
 				Labels: map[string]string{
@@ -27,6 +43,7 @@ func TestAlert_ExecTemplate(t *testing.T) {
 			expTpl:      map[string]string{},
 		},
 		{
+			name: "label-template",
 			alert: &Alert{
 				Value: 1e4,
 				Labels: map[string]string{
@@ -43,11 +60,77 @@ func TestAlert_ExecTemplate(t *testing.T) {
 				"description": "It is 10000 connections for localhost",
 			},
 		},
+		{
+			name: "expression-template",
+			alert: &Alert{
+				Expr: `vm_rows{"label"="bar"}>0`,
+			},
+			annotations: map[string]string{
+				"exprEscapedQuery": "{{ $expr|quotesEscape|queryEscape }}",
+				"exprEscapedPath":  "{{ $expr|quotesEscape|pathEscape }}",
+			},
+			expTpl: map[string]string{
+				"exprEscapedQuery": "vm_rows%7B%5C%22label%5C%22%3D%5C%22bar%5C%22%7D%3E0",
+				"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;",
+			},
+		},
+		{
+			name: "external",
+			alert: &Alert{
+				Value: 1e4,
+				Labels: map[string]string{
+					"job":      "staging",
+					"instance": "localhost",
+				},
+			},
+			annotations: map[string]string{
+				"url":         "{{ $externalURL }}",
+				"summary":     "Issues with {{$labels.instance}} (dc-{{$externalLabels.dc}}) for job {{$labels.job}}",
+				"description": "It is {{ $value }} connections for {{$labels.instance}} (cluster-{{$externalLabels.cluster}})",
+			},
+			expTpl: map[string]string{
+				"url":         extURL,
+				"summary":     fmt.Sprintf("Issues with localhost (dc-%s) for job staging", extDC),
+				"description": fmt.Sprintf("It is 10000 connections for localhost (cluster-%s)", extCluster),
+			},
+		},
 	}
 
-	for i, tc := range testCases {
-		t.Run(fmt.Sprintf("%d", i), func(t *testing.T) {
-			tpl, err := tc.alert.ExecTemplate(tc.annotations)
+	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(qFn, tc.annotations)
 			if err != nil {
 				t.Fatal(err)
 			}

app/vmalert/notifier/alertmanager.go

@@ -6,28 +6,79 @@ import (
 	"fmt"
 	"io/ioutil"
 	"net/http"
-	"strings"
+	"time"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/utils"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promauth"
 )
 
 // AlertManager represents integration provider with Prometheus alert manager
 // https://github.com/prometheus/alertmanager
 type AlertManager struct {
-	alertURL string
-	argFunc  AlertURLGenerator
-	client   *http.Client
+	addr    string
+	argFunc AlertURLGenerator
+	client  *http.Client
+	timeout time.Duration
+
+	authCfg *promauth.Config
+
+	metrics *metrics
 }
 
+type metrics struct {
+	alertsSent       *utils.Counter
+	alertsSendErrors *utils.Counter
+}
+
+func newMetrics(addr string) *metrics {
+	return &metrics{
+		alertsSent:       utils.GetOrCreateCounter(fmt.Sprintf("vmalert_alerts_sent_total{addr=%q}", addr)),
+		alertsSendErrors: utils.GetOrCreateCounter(fmt.Sprintf("vmalert_alerts_send_errors_total{addr=%q}", addr)),
+	}
+}
+
+// Close is a destructor method for AlertManager
+func (am *AlertManager) Close() {
+	am.metrics.alertsSent.Unregister()
+	am.metrics.alertsSendErrors.Unregister()
+}
+
+// Addr returns address where alerts are sent.
+func (am AlertManager) Addr() string { return am.addr }
+
 // Send an alert or resolve message
 func (am *AlertManager) Send(ctx context.Context, alerts []Alert) error {
+	am.metrics.alertsSent.Add(len(alerts))
+	err := am.send(ctx, alerts)
+	if err != nil {
+		am.metrics.alertsSendErrors.Add(len(alerts))
+	}
+	return err
+}
+
+func (am *AlertManager) send(ctx context.Context, alerts []Alert) error {
 	b := &bytes.Buffer{}
 	writeamRequest(b, alerts, am.argFunc)
 
-	req, err := http.NewRequest("POST", am.alertURL, b)
+	req, err := http.NewRequest("POST", am.addr, b)
 	if err != nil {
 		return err
 	}
 	req.Header.Set("Content-Type", "application/json")
+
+	if am.timeout > 0 {
+		var cancel context.CancelFunc
+		ctx, cancel = context.WithTimeout(ctx, am.timeout)
+		defer cancel()
+	}
+
 	req = req.WithContext(ctx)
+
+	if am.authCfg != nil {
+		if auth := am.authCfg.GetAuthHeader(); auth != "" {
+			req.Header.Set("Authorization", auth)
+		}
+	}
 	resp, err := am.client.Do(req)
 	if err != nil {
 		return err
@@ -38,23 +89,44 @@ func (am *AlertManager) Send(ctx context.Context, alerts []Alert) error {
 	if resp.StatusCode != http.StatusOK {
 		body, err := ioutil.ReadAll(resp.Body)
 		if err != nil {
-			return fmt.Errorf("failed to read response from %q: %s", am.alertURL, err)
+			return fmt.Errorf("failed to read response from %q: %w", am.addr, err)
 		}
-		return fmt.Errorf("invalid SC %d from %q; response body: %s", resp.StatusCode, am.alertURL, string(body))
+		return fmt.Errorf("invalid SC %d from %q; response body: %s", resp.StatusCode, am.addr, string(body))
 	}
 	return nil
 }
 
 // AlertURLGenerator returns URL to single alert by given name
-type AlertURLGenerator func(group, alert string) string
+type AlertURLGenerator func(Alert) string
 
 const alertManagerPath = "/api/v2/alerts"
 
 // NewAlertManager is a constructor for AlertManager
-func NewAlertManager(alertManagerURL string, fn AlertURLGenerator, c *http.Client) *AlertManager {
-	return &AlertManager{
-		alertURL: strings.TrimSuffix(alertManagerURL, "/") + alertManagerPath,
-		argFunc:  fn,
-		client:   c,
+func NewAlertManager(alertManagerURL string, fn AlertURLGenerator, authCfg promauth.HTTPClientConfig, timeout time.Duration) (*AlertManager, error) {
+	tls := &promauth.TLSConfig{}
+	if authCfg.TLSConfig != nil {
+		tls = authCfg.TLSConfig
 	}
+	tr, err := utils.Transport(alertManagerURL, tls.CertFile, tls.KeyFile, tls.CAFile, tls.ServerName, tls.InsecureSkipVerify)
+	if err != nil {
+		return nil, fmt.Errorf("failed to create transport: %w", err)
+	}
+
+	ba := &promauth.BasicAuthConfig{}
+	if authCfg.BasicAuth != nil {
+		ba = authCfg.BasicAuth
+	}
+	aCfg, err := utils.AuthConfig(ba.Username, ba.Password.String(), ba.PasswordFile, authCfg.BearerToken.String(), authCfg.BearerTokenFile)
+	if err != nil {
+		return nil, fmt.Errorf("failed to configure auth: %w", err)
+	}
+
+	return &AlertManager{
+		addr:    alertManagerURL,
+		argFunc: fn,
+		authCfg: aCfg,
+		client:  &http.Client{Transport: tr},
+		timeout: timeout,
+		metrics: newMetrics(alertManagerURL),
+	}, nil
 }

app/vmalert/notifier/alertmanager_request.qtpl

@@ -1,15 +1,14 @@
 {% import (
-    "strconv"
     "time"
 ) %}
 {% stripspace %}
 
-{% func amRequest(alerts []Alert, generatorURL func(string, string) string) %}
+{% func amRequest(alerts []Alert, generatorURL func(Alert) string) %}
 [
 {% for i, alert := range alerts %}
 {
-	"startsAt":{%q= alert.Start.Format(time.RFC3339Nano) %},
-	"generatorURL": {%q= generatorURL(strconv.FormatUint(alert.GroupID, 10), strconv.FormatUint(alert.ID, 10)) %},
+    "startsAt":{%q= alert.Start.Format(time.RFC3339Nano) %},
+    "generatorURL": {%q= generatorURL(alert) %},
     {% if !alert.End.IsZero() %}
     "endsAt":{%q= alert.End.Format(time.RFC3339Nano) %},
     {% endif %}

app/vmalert/notifier/alertmanager_request.qtpl.go

@@ -1,131 +1,130 @@
 // Code generated by qtc from "alertmanager_request.qtpl". DO NOT EDIT.
 // See https://github.com/valyala/quicktemplate for details.
 
-//line notifier/alertmanager_request.qtpl:1
+//line app/vmalert/notifier/alertmanager_request.qtpl:1
 package notifier
 
-//line notifier/alertmanager_request.qtpl:1
+//line app/vmalert/notifier/alertmanager_request.qtpl:1
 import (
-	"strconv"
 	"time"
 )
 
-//line notifier/alertmanager_request.qtpl:7
+//line app/vmalert/notifier/alertmanager_request.qtpl:6
 import (
 	qtio422016 "io"
 
 	qt422016 "github.com/valyala/quicktemplate"
 )
 
-//line notifier/alertmanager_request.qtpl:7
+//line app/vmalert/notifier/alertmanager_request.qtpl:6
 var (
 	_ = qtio422016.Copy
 	_ = qt422016.AcquireByteBuffer
 )
 
-//line notifier/alertmanager_request.qtpl:7
-func streamamRequest(qw422016 *qt422016.Writer, alerts []Alert, generatorURL func(string, string) string) {
-//line notifier/alertmanager_request.qtpl:7
+//line app/vmalert/notifier/alertmanager_request.qtpl:6
+func streamamRequest(qw422016 *qt422016.Writer, alerts []Alert, generatorURL func(Alert) string) {
+//line app/vmalert/notifier/alertmanager_request.qtpl:6
 	qw422016.N().S(`[`)
-//line notifier/alertmanager_request.qtpl:9
+//line app/vmalert/notifier/alertmanager_request.qtpl:8
 	for i, alert := range alerts {
-//line notifier/alertmanager_request.qtpl:9
+//line app/vmalert/notifier/alertmanager_request.qtpl:8
 		qw422016.N().S(`{"startsAt":`)
-//line notifier/alertmanager_request.qtpl:11
+//line app/vmalert/notifier/alertmanager_request.qtpl:10
 		qw422016.N().Q(alert.Start.Format(time.RFC3339Nano))
-//line notifier/alertmanager_request.qtpl:11
+//line app/vmalert/notifier/alertmanager_request.qtpl:10
 		qw422016.N().S(`,"generatorURL":`)
-//line notifier/alertmanager_request.qtpl:12
-		qw422016.N().Q(generatorURL(strconv.FormatUint(alert.GroupID, 10), strconv.FormatUint(alert.ID, 10)))
-//line notifier/alertmanager_request.qtpl:12
+//line app/vmalert/notifier/alertmanager_request.qtpl:11
+		qw422016.N().Q(generatorURL(alert))
+//line app/vmalert/notifier/alertmanager_request.qtpl:11
 		qw422016.N().S(`,`)
-//line notifier/alertmanager_request.qtpl:13
+//line app/vmalert/notifier/alertmanager_request.qtpl:12
 		if !alert.End.IsZero() {
-//line notifier/alertmanager_request.qtpl:13
+//line app/vmalert/notifier/alertmanager_request.qtpl:12
 			qw422016.N().S(`"endsAt":`)
-//line notifier/alertmanager_request.qtpl:14
+//line app/vmalert/notifier/alertmanager_request.qtpl:13
 			qw422016.N().Q(alert.End.Format(time.RFC3339Nano))
-//line notifier/alertmanager_request.qtpl:14
+//line app/vmalert/notifier/alertmanager_request.qtpl:13
 			qw422016.N().S(`,`)
-//line notifier/alertmanager_request.qtpl:15
+//line app/vmalert/notifier/alertmanager_request.qtpl:14
 		}
-//line notifier/alertmanager_request.qtpl:15
+//line app/vmalert/notifier/alertmanager_request.qtpl:14
 		qw422016.N().S(`"labels": {"alertname":`)
-//line notifier/alertmanager_request.qtpl:17
+//line app/vmalert/notifier/alertmanager_request.qtpl:16
 		qw422016.N().Q(alert.Name)
-//line notifier/alertmanager_request.qtpl:18
+//line app/vmalert/notifier/alertmanager_request.qtpl:17
 		for k, v := range alert.Labels {
-//line notifier/alertmanager_request.qtpl:18
+//line app/vmalert/notifier/alertmanager_request.qtpl:17
 			qw422016.N().S(`,`)
-//line notifier/alertmanager_request.qtpl:19
+//line app/vmalert/notifier/alertmanager_request.qtpl:18
 			qw422016.N().Q(k)
-//line notifier/alertmanager_request.qtpl:19
+//line app/vmalert/notifier/alertmanager_request.qtpl:18
 			qw422016.N().S(`:`)
-//line notifier/alertmanager_request.qtpl:19
+//line app/vmalert/notifier/alertmanager_request.qtpl:18
 			qw422016.N().Q(v)
-//line notifier/alertmanager_request.qtpl:20
+//line app/vmalert/notifier/alertmanager_request.qtpl:19
 		}
-//line notifier/alertmanager_request.qtpl:20
+//line app/vmalert/notifier/alertmanager_request.qtpl:19
 		qw422016.N().S(`},"annotations": {`)
-//line notifier/alertmanager_request.qtpl:23
+//line app/vmalert/notifier/alertmanager_request.qtpl:22
 		c := len(alert.Annotations)
 
-//line notifier/alertmanager_request.qtpl:24
+//line app/vmalert/notifier/alertmanager_request.qtpl:23
 		for k, v := range alert.Annotations {
-//line notifier/alertmanager_request.qtpl:25
+//line app/vmalert/notifier/alertmanager_request.qtpl:24
 			c = c - 1
 
-//line notifier/alertmanager_request.qtpl:26
+//line app/vmalert/notifier/alertmanager_request.qtpl:25
 			qw422016.N().Q(k)
-//line notifier/alertmanager_request.qtpl:26
+//line app/vmalert/notifier/alertmanager_request.qtpl:25
 			qw422016.N().S(`:`)
-//line notifier/alertmanager_request.qtpl:26
+//line app/vmalert/notifier/alertmanager_request.qtpl:25
 			qw422016.N().Q(v)
-//line notifier/alertmanager_request.qtpl:26
+//line app/vmalert/notifier/alertmanager_request.qtpl:25
 			if c > 0 {
-//line notifier/alertmanager_request.qtpl:26
+//line app/vmalert/notifier/alertmanager_request.qtpl:25
 				qw422016.N().S(`,`)
-//line notifier/alertmanager_request.qtpl:26
+//line app/vmalert/notifier/alertmanager_request.qtpl:25
 			}
-//line notifier/alertmanager_request.qtpl:27
+//line app/vmalert/notifier/alertmanager_request.qtpl:26
 		}
-//line notifier/alertmanager_request.qtpl:27
+//line app/vmalert/notifier/alertmanager_request.qtpl:26
 		qw422016.N().S(`}}`)
-//line notifier/alertmanager_request.qtpl:30
+//line app/vmalert/notifier/alertmanager_request.qtpl:29
 		if i != len(alerts)-1 {
-//line notifier/alertmanager_request.qtpl:30
+//line app/vmalert/notifier/alertmanager_request.qtpl:29
 			qw422016.N().S(`,`)
-//line notifier/alertmanager_request.qtpl:30
+//line app/vmalert/notifier/alertmanager_request.qtpl:29
 		}
-//line notifier/alertmanager_request.qtpl:31
+//line app/vmalert/notifier/alertmanager_request.qtpl:30
 	}
-//line notifier/alertmanager_request.qtpl:31
+//line app/vmalert/notifier/alertmanager_request.qtpl:30
 	qw422016.N().S(`]`)
-//line notifier/alertmanager_request.qtpl:33
+//line app/vmalert/notifier/alertmanager_request.qtpl:32
 }
 
-//line notifier/alertmanager_request.qtpl:33
-func writeamRequest(qq422016 qtio422016.Writer, alerts []Alert, generatorURL func(string, string) string) {
-//line notifier/alertmanager_request.qtpl:33
+//line app/vmalert/notifier/alertmanager_request.qtpl:32
+func writeamRequest(qq422016 qtio422016.Writer, alerts []Alert, generatorURL func(Alert) string) {
+//line app/vmalert/notifier/alertmanager_request.qtpl:32
 	qw422016 := qt422016.AcquireWriter(qq422016)
-//line notifier/alertmanager_request.qtpl:33
+//line app/vmalert/notifier/alertmanager_request.qtpl:32
 	streamamRequest(qw422016, alerts, generatorURL)
-//line notifier/alertmanager_request.qtpl:33
+//line app/vmalert/notifier/alertmanager_request.qtpl:32
 	qt422016.ReleaseWriter(qw422016)
-//line notifier/alertmanager_request.qtpl:33
+//line app/vmalert/notifier/alertmanager_request.qtpl:32
 }
 
-//line notifier/alertmanager_request.qtpl:33
-func amRequest(alerts []Alert, generatorURL func(string, string) string) string {
-//line notifier/alertmanager_request.qtpl:33
+//line app/vmalert/notifier/alertmanager_request.qtpl:32
+func amRequest(alerts []Alert, generatorURL func(Alert) string) string {
+//line app/vmalert/notifier/alertmanager_request.qtpl:32
 	qb422016 := qt422016.AcquireByteBuffer()
-//line notifier/alertmanager_request.qtpl:33
+//line app/vmalert/notifier/alertmanager_request.qtpl:32
 	writeamRequest(qb422016, alerts, generatorURL)
-//line notifier/alertmanager_request.qtpl:33
+//line app/vmalert/notifier/alertmanager_request.qtpl:32
 	qs422016 := string(qb422016.B)
-//line notifier/alertmanager_request.qtpl:33
+//line app/vmalert/notifier/alertmanager_request.qtpl:32
 	qt422016.ReleaseByteBuffer(qb422016)
-//line notifier/alertmanager_request.qtpl:33
+//line app/vmalert/notifier/alertmanager_request.qtpl:32
 	return qs422016
-//line notifier/alertmanager_request.qtpl:33
+//line app/vmalert/notifier/alertmanager_request.qtpl:32
 }

app/vmalert/notifier/alertmanager_test.go

@@ -5,17 +5,40 @@ import (
 	"encoding/json"
 	"net/http"
 	"net/http/httptest"
+	"strconv"
 	"testing"
 	"time"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promauth"
 )
 
+func TestAlertManager_Addr(t *testing.T) {
+	const addr = "http://localhost"
+	am, err := NewAlertManager(addr, nil, promauth.HTTPClientConfig{}, 0)
+	if err != nil {
+		t.Errorf("unexpected error: %s", err)
+	}
+	if am.Addr() != addr {
+		t.Errorf("expected to have %q; got %q", addr, am.Addr())
+	}
+}
+
 func TestAlertManager_Send(t *testing.T) {
+	const baUser, baPass = "foo", "bar"
 	mux := http.NewServeMux()
 	mux.HandleFunc("/", func(_ http.ResponseWriter, _ *http.Request) {
 		t.Errorf("should not be called")
 	})
 	c := -1
 	mux.HandleFunc(alertManagerPath, func(w http.ResponseWriter, r *http.Request) {
+		user, pass, ok := r.BasicAuth()
+		if !ok {
+			t.Errorf("unauthorized request")
+		}
+		if user != baUser || pass != baPass {
+			t.Errorf("wrong creds %q:%q; expected %q:%q",
+				user, pass, baUser, baPass)
+		}
 		c++
 		if r.Method != http.MethodPost {
 			t.Errorf("expected POST method got %s", r.Method)
@@ -42,24 +65,34 @@ func TestAlertManager_Send(t *testing.T) {
 				t.Errorf("expected 1 alert in array got %d", len(a))
 			}
 			if a[0].GeneratorURL != "0/0" {
-				t.Errorf("exptected 0/0 as generatorURL got %s", a[0].GeneratorURL)
+				t.Errorf("expected 0/0 as generatorURL got %s", a[0].GeneratorURL)
 			}
 			if a[0].Labels["alertname"] != "alert0" {
-				t.Errorf("exptected alert0 as alert name got %s", a[0].Labels["alertname"])
+				t.Errorf("expected alert0 as alert name got %s", a[0].Labels["alertname"])
 			}
 			if a[0].StartsAt.IsZero() {
-				t.Errorf("exptected non-zero start time")
+				t.Errorf("expected non-zero start time")
 			}
 			if a[0].EndAt.IsZero() {
-				t.Errorf("exptected non-zero end time")
+				t.Errorf("expected non-zero end time")
 			}
 		}
 	})
 	srv := httptest.NewServer(mux)
 	defer srv.Close()
-	am := NewAlertManager(srv.URL, func(group, name string) string {
-		return group + "/" + name
-	}, srv.Client())
+
+	aCfg := promauth.HTTPClientConfig{
+		BasicAuth: &promauth.BasicAuthConfig{
+			Username: baUser,
+			Password: promauth.NewSecret(baPass),
+		},
+	}
+	am, err := NewAlertManager(srv.URL+alertManagerPath, func(alert Alert) string {
+		return strconv.FormatUint(alert.GroupID, 10) + "/" + strconv.FormatUint(alert.ID, 10)
+	}, aCfg, 0)
+	if err != nil {
+		t.Errorf("unexpected error: %s", err)
+	}
 	if err := am.Send(context.Background(), []Alert{{}, {}}); err == nil {
 		t.Error("expected connection error got nil")
 	}

app/vmalert/notifier/config.go

@@ -0,0 +1,182 @@
+package notifier
+
+import (
+	"crypto/md5"
+	"fmt"
+	"gopkg.in/yaml.v2"
+	"io/ioutil"
+	"net/url"
+	"path"
+	"path/filepath"
+	"strings"
+	"time"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promauth"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promscrape/discovery/consul"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promutils"
+)
+
+// Config contains list of supported configuration settings
+// for Notifier
+type Config struct {
+	// Scheme defines the HTTP scheme for Notifier address
+	Scheme string `yaml:"scheme,omitempty"`
+	// PathPrefix is added to URL path before adding alertManagerPath value
+	PathPrefix string `yaml:"path_prefix,omitempty"`
+
+	// ConsulSDConfigs contains list of settings for service discovery via Consul
+	// see https://prometheus.io/docs/prometheus/latest/configuration/configuration/#consul_sd_config
+	ConsulSDConfigs []consul.SDConfig `yaml:"consul_sd_configs,omitempty"`
+	// StaticConfigs contains list of static targets
+	StaticConfigs []StaticConfig `yaml:"static_configs,omitempty"`
+
+	// HTTPClientConfig contains HTTP configuration for Notifier clients
+	HTTPClientConfig promauth.HTTPClientConfig `yaml:",inline"`
+	// RelabelConfigs contains list of relabeling rules
+	RelabelConfigs []promrelabel.RelabelConfig `yaml:"relabel_configs,omitempty"`
+
+	// The timeout used when sending alerts.
+	Timeout promutils.Duration `yaml:"timeout,omitempty"`
+
+	// Checksum stores the hash of yaml definition for the config.
+	// May be used to detect any changes to the config file.
+	Checksum string
+
+	// Catches all undefined fields and must be empty after parsing.
+	XXX map[string]interface{} `yaml:",inline"`
+
+	// This is set to the directory from where the config has been loaded.
+	baseDir string
+
+	// stores already parsed RelabelConfigs object
+	parsedRelabelConfigs *promrelabel.ParsedConfigs
+}
+
+// StaticConfig contains list of static targets in the following form:
+// 	targets:
+//  	[ - '<host>' ]
+type StaticConfig struct {
+	Targets []string `yaml:"targets"`
+}
+
+// UnmarshalYAML implements the yaml.Unmarshaler interface.
+func (cfg *Config) UnmarshalYAML(unmarshal func(interface{}) error) error {
+	type config Config
+	if err := unmarshal((*config)(cfg)); err != nil {
+		return err
+	}
+	if cfg.Scheme == "" {
+		cfg.Scheme = "http"
+	}
+	if cfg.Timeout.Duration() == 0 {
+		cfg.Timeout = promutils.NewDuration(time.Second * 10)
+	}
+	rCfg, err := promrelabel.ParseRelabelConfigs(cfg.RelabelConfigs, false)
+	if err != nil {
+		return fmt.Errorf("failed to parse relabeling config: %w", err)
+	}
+	cfg.parsedRelabelConfigs = rCfg
+
+	b, err := yaml.Marshal(cfg)
+	if err != nil {
+		return fmt.Errorf("failed to marshal configuration for checksum: %w", err)
+	}
+	h := md5.New()
+	h.Write(b)
+	cfg.Checksum = fmt.Sprintf("%x", h.Sum(nil))
+	return nil
+}
+
+func parseConfig(path string) (*Config, error) {
+	data, err := ioutil.ReadFile(path)
+	if err != nil {
+		return nil, fmt.Errorf("error reading config file: %w", err)
+	}
+	var cfg *Config
+	err = yaml.Unmarshal(data, &cfg)
+	if err != nil {
+		return nil, err
+	}
+	if len(cfg.XXX) > 0 {
+		var keys []string
+		for k := range cfg.XXX {
+			keys = append(keys, k)
+		}
+		return nil, fmt.Errorf("unknown fields in %s", strings.Join(keys, ", "))
+	}
+	absPath, err := filepath.Abs(path)
+	if err != nil {
+		return nil, fmt.Errorf("cannot obtain abs path for %q: %w", path, err)
+	}
+	cfg.baseDir = filepath.Dir(absPath)
+	return cfg, nil
+}
+
+func parseLabels(target string, metaLabels map[string]string, cfg *Config) (string, []prompbmarshal.Label, error) {
+	labels := mergeLabels(target, metaLabels, cfg)
+	labels = cfg.parsedRelabelConfigs.Apply(labels, 0, false)
+	labels = promrelabel.RemoveMetaLabels(labels[:0], labels)
+	// Remove references to already deleted labels, so GC could clean strings for label name and label value past len(labels).
+	// This should reduce memory usage when relabeling creates big number of temporary labels with long names and/or values.
+	// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/825 for details.
+	labels = append([]prompbmarshal.Label{}, labels...)
+
+	if len(labels) == 0 {
+		return "", nil, nil
+	}
+	schemeRelabeled := promrelabel.GetLabelValueByName(labels, "__scheme__")
+	if len(schemeRelabeled) == 0 {
+		schemeRelabeled = "http"
+	}
+	addressRelabeled := promrelabel.GetLabelValueByName(labels, "__address__")
+	if len(addressRelabeled) == 0 {
+		return "", nil, nil
+	}
+	if strings.Contains(addressRelabeled, "/") {
+		return "", nil, nil
+	}
+	addressRelabeled = addMissingPort(schemeRelabeled, addressRelabeled)
+	alertsPathRelabeled := promrelabel.GetLabelValueByName(labels, "__alerts_path__")
+	if !strings.HasPrefix(alertsPathRelabeled, "/") {
+		alertsPathRelabeled = "/" + alertsPathRelabeled
+	}
+	u := fmt.Sprintf("%s://%s%s", schemeRelabeled, addressRelabeled, alertsPathRelabeled)
+	if _, err := url.Parse(u); err != nil {
+		return "", nil, fmt.Errorf("invalid url %q for scheme=%q (%q), target=%q, metrics_path=%q (%q): %w",
+			u, cfg.Scheme, schemeRelabeled, target, addressRelabeled, alertsPathRelabeled, err)
+	}
+	return u, labels, nil
+}
+
+func addMissingPort(scheme, target string) string {
+	if strings.Contains(target, ":") {
+		return target
+	}
+	if scheme == "https" {
+		target += ":443"
+	} else {
+		target += ":80"
+	}
+	return target
+}
+
+func mergeLabels(target string, metaLabels map[string]string, cfg *Config) []prompbmarshal.Label {
+	// See https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config
+	m := make(map[string]string)
+	m["__address__"] = target
+	m["__scheme__"] = cfg.Scheme
+	m["__alerts_path__"] = path.Join("/", cfg.PathPrefix, alertManagerPath)
+	for k, v := range metaLabels {
+		m[k] = v
+	}
+	result := make([]prompbmarshal.Label, 0, len(m))
+	for k, v := range m {
+		result = append(result, prompbmarshal.Label{
+			Name:  k,
+			Value: v,
+		})
+	}
+	return result
+}

app/vmalert/notifier/config_test.go

@@ -0,0 +1,31 @@
+package notifier
+
+import (
+	"strings"
+	"testing"
+)
+
+func TestConfigParseGood(t *testing.T) {
+	f := func(path string) {
+		_, err := parseConfig(path)
+		checkErr(t, err)
+	}
+	f("testdata/mixed.good.yaml")
+	f("testdata/consul.good.yaml")
+	f("testdata/static.good.yaml")
+}
+
+func TestConfigParseBad(t *testing.T) {
+	f := func(path, expErr string) {
+		_, err := parseConfig(path)
+		if err == nil {
+			t.Fatalf("expected to get non-nil err for config %q", path)
+		}
+		if !strings.Contains(err.Error(), expErr) {
+			t.Errorf("expected err to contain %q; got %q instead", expErr, err)
+		}
+	}
+
+	f("testdata/unknownFields.bad.yaml", "unknown field")
+	f("non-existing-file", "error reading")
+}