docs/CHANGELOG.md: cut v1.57.1

See 9b4e608199

.github/ISSUE_TEMPLATE/bug_report.md

@@ -9,9 +9,12 @@ assignees: ''
 
 **Describe the bug**
 A clear and concise description of what the bug is.
+It would be great [upgrading](https://victoriametrics.github.io/#how-to-upgrade) to [the latest avaialble release](https://github.com/VictoriaMetrics/VictoriaMetrics/releases)
+and verifying whether the bug is reproducible there.
+It is also recommended reading [troubleshooting docs](https://victoriametrics.github.io/#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.

.github/workflows/main.yml

@@ -14,17 +14,15 @@ 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: 1.16
         id: go
       - name: Dependencies
-        env:
-          GO111MODULE: on
         run: |
           go get -u golang.org/x/lint/golint
           go get -u github.com/kisielk/errcheck
-          curl -sSfL https://raw.githubusercontent.com/golangci/golangci-lint/master/install.sh | sh -s -- -b $(go env GOPATH)/bin v1.27.0
+          curl -sSfL https://raw.githubusercontent.com/golangci/golangci-lint/master/install.sh | sh -s -- -b $(go env GOPATH)/bin v1.29.0
       - name: Code checkout
         uses: actions/checkout@master
       - name: Build
@@ -43,7 +41,24 @@ 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
         with:

CODE_OF_CONDUCT_RU.md

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

LICENSE

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

Makefile

@@ -10,13 +10,16 @@ endif
 
 GO_BUILDINFO = -X '$(PKG_PREFIX)/lib/buildinfo.Version=$(APP_NAME)-$(shell date -u +'%Y%m%d-%H%M%S')-$(BUILDINFO_TAG)'
 
+.PHONY: $(MAKECMDGOALS)
+
 all: \
 	victoria-metrics-prod \
 	vmagent-prod \
 	vmalert-prod \
 	vmauth-prod \
 	vmbackup-prod \
-	vmrestore-prod
+	vmrestore-prod \
+	vmctl-prod
 
 include app/*/Makefile
 include deployment/*/Makefile
@@ -30,7 +33,8 @@ publish: \
 	publish-vmalert \
 	publish-vmauth \
 	publish-vmbackup \
-	publish-vmrestore
+	publish-vmrestore \
+	publish-vmctl
 
 package: \
 	package-victoria-metrics \
@@ -38,31 +42,128 @@ package: \
 	package-vmalert \
 	package-vmauth \
 	package-vmbackup \
-	package-vmrestore
+	package-vmrestore \
+	package-vmctl
 
 vmutils: \
 	vmagent \
 	vmalert \
 	vmauth \
 	vmbackup \
-	vmrestore
+	vmrestore \
+	vmctl
+
+vmutils-arm64: \
+	vmagent-arm64 \
+	vmalert-arm64 \
+	vmauth-arm64 \
+	vmbackup-arm64 \
+	vmrestore-arm64 \
+	vmctl-arm64
+
+vmutils-arm: \
+	vmagent-arm \
+	vmalert-arm \
+	vmauth-arm \
+	vmbackup-arm \
+	vmrestore-arm \
+	vmctl-arm
+
+vmutils-windows-amd64: \
+	vmagent-windows-amd64 \
+	vmalert-windows-amd64 \
+	vmauth-windows-amd64 \
+	vmctl-windows-amd64
+
+release-snap:
+	snapcraft
+	snapcraft upload "victoriametrics_$(PKG_TAG)_multi.snap" --release beta,edge,candidate
 
 release: \
 	release-victoria-metrics \
 	release-vmutils
 
-release-victoria-metrics: victoria-metrics-prod
-	cd bin && tar czf victoria-metrics-$(PKG_TAG).tar.gz victoria-metrics-prod && \
-		sha256sum victoria-metrics-$(PKG_TAG).tar.gz > victoria-metrics-$(PKG_TAG)_checksums.txt
+release-victoria-metrics: \
+	release-victoria-metrics-amd64 \
+	release-victoria-metrics-arm \
+	release-victoria-metrics-arm64
+
+release-victoria-metrics-amd64:
+	GOARCH=amd64 $(MAKE) release-victoria-metrics-generic
+
+release-victoria-metrics-arm:
+	GOARCH=arm $(MAKE) release-victoria-metrics-generic
+
+release-victoria-metrics-arm64:
+	GOARCH=arm64 $(MAKE) release-victoria-metrics-generic
+
+release-victoria-metrics-generic: victoria-metrics-$(GOARCH)-prod
+	cd bin && \
+		tar --transform="flags=r;s|-$(GOARCH)||" -czf victoria-metrics-$(GOARCH)-$(PKG_TAG).tar.gz \
+			victoria-metrics-$(GOARCH)-prod \
+		&& sha256sum victoria-metrics-$(GOARCH)-$(PKG_TAG).tar.gz \
+			victoria-metrics-$(GOARCH)-prod \
+			| sed s/-$(GOARCH)// > victoria-metrics-$(GOARCH)-$(PKG_TAG)_checksums.txt
 
 release-vmutils: \
-	vmagent-prod \
-	vmalert-prod \
-	vmauth-prod \
-	vmbackup-prod \
-	vmrestore-prod
-	cd bin && tar czf vmutils-$(PKG_TAG).tar.gz vmagent-prod vmalert-prod vmauth-prod vmbackup-prod vmrestore-prod && \
-		sha256sum vmutils-$(PKG_TAG).tar.gz > vmutils-$(PKG_TAG)_checksums.txt
+	release-vmutils-amd64 \
+	release-vmutils-arm64 \
+	release-vmutils-arm \
+	release-vmutils-windows-amd64
+
+release-vmutils-amd64:
+	GOARCH=amd64 $(MAKE) release-vmutils-generic
+
+release-vmutils-arm64:
+	GOARCH=arm64 $(MAKE) release-vmutils-generic
+
+release-vmutils-arm:
+	GOARCH=arm $(MAKE) release-vmutils-generic
+
+release-vmutils-windows-amd64:
+	GOARCH=amd64 $(MAKE) release-vmutils-windows-generic
+
+release-vmutils-generic: \
+	vmagent-$(GOARCH)-prod \
+	vmalert-$(GOARCH)-prod \
+	vmauth-$(GOARCH)-prod \
+	vmbackup-$(GOARCH)-prod \
+	vmrestore-$(GOARCH)-prod \
+	vmctl-$(GOARCH)-prod
+	cd bin && \
+		tar --transform="flags=r;s|-$(GOARCH)||" -czf vmutils-$(GOARCH)-$(PKG_TAG).tar.gz \
+			vmagent-$(GOARCH)-prod \
+			vmalert-$(GOARCH)-prod \
+			vmauth-$(GOARCH)-prod \
+			vmbackup-$(GOARCH)-prod \
+			vmrestore-$(GOARCH)-prod \
+			vmctl-$(GOARCH)-prod \
+		&& sha256sum vmutils-$(GOARCH)-$(PKG_TAG).tar.gz \
+			vmagent-$(GOARCH)-prod \
+			vmalert-$(GOARCH)-prod \
+			vmauth-$(GOARCH)-prod \
+			vmbackup-$(GOARCH)-prod \
+			vmrestore-$(GOARCH)-prod \
+			vmctl-$(GOARCH)-prod \
+			| sed s/-$(GOARCH)// > vmutils-$(GOARCH)-$(PKG_TAG)_checksums.txt
+
+release-vmutils-windows-generic: \
+	vmagent-windows-$(GOARCH)-prod \
+	vmalert-windows-$(GOARCH)-prod \
+	vmauth-windows-$(GOARCH)-prod \
+	vmctl-windows-$(GOARCH)-prod
+	cd bin && \
+		zip vmutils-windows-$(GOARCH)-$(PKG_TAG).zip \
+			vmagent-windows-$(GOARCH)-prod.exe \
+			vmalert-windows-$(GOARCH)-prod.exe \
+			vmauth-windows-$(GOARCH)-prod.exe \
+			vmctl-windows-$(GOARCH)-prod.exe \
+		&& sha256sum vmutils-windows-$(GOARCH)-$(PKG_TAG).zip \
+			vmagent-windows-$(GOARCH)-prod.exe \
+			vmalert-windows-$(GOARCH)-prod.exe \
+			vmauth-windows-$(GOARCH)-prod.exe \
+			vmctl-windows-$(GOARCH)-prod.exe \
+			> vmutils-windows-$(GOARCH)-$(PKG_TAG)_checksums.txt
 
 pprof-cpu:
 	go tool pprof -trim_path=github.com/VictoriaMetrics/VictoriaMetrics@ $(PPROF_FILE)
@@ -80,7 +181,7 @@ lint: install-golint
 	golint app/...
 
 install-golint:
-	which golint || GO111MODULE=off go get -u golang.org/x/lint/golint
+	which golint || go install golang.org/x/lint/golint
 
 errcheck: install-errcheck
 	errcheck -exclude=errcheck_excludes.txt ./lib/...
@@ -92,9 +193,10 @@ 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 || go install github.com/kisielk/errcheck
 
 check-all: fmt vet lint errcheck golangci-lint
 
@@ -122,8 +224,8 @@ 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 +235,30 @@ 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 || go install 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 v1.29.0
+
+docs-sync:
+	cp app/vmagent/README.md docs/vmagent.md
+	cp app/vmalert/README.md docs/vmalert.md
+	cp app/vmauth/README.md docs/vmauth.md
+	cp app/vmbackup/README.md docs/vmbackup.md
+	cp app/vmrestore/README.md docs/vmrestore.md
+	cp app/vmctl/README.md docs/vmctl.md
+	cp README.md docs/Single-server-VictoriaMetrics.md

app/victoria-metrics/Makefile

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

app/victoria-metrics/main.go

@@ -2,19 +2,25 @@ package main
 
 import (
 	"flag"
+	"fmt"
+	"io"
 	"net/http"
 	"os"
+	"path"
 	"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"
 )
 
@@ -23,18 +29,33 @@ var (
 	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")
+	dryRun = flag.Bool("dryRun", false, "Whether to check only -promscrape.config and then exit. "+
+		"Unknown config entries are allowed in -promscrape.config by default. This can be changed with -promscrape.config.strictParse")
 )
 
 func main() {
 	// Write flags and help message to stdout, since it is easier to grep or pipe.
 	flag.CommandLine.SetOutput(os.Stdout)
+	flag.Usage = usage
 	envflag.Parse()
 	buildinfo.Init()
 	logger.Init()
+
+	if promscrape.IsDryRun() {
+		*dryRun = true
+	}
+	if *dryRun {
+		if err := promscrape.CheckConfig(); err != nil {
+			logger.Fatalf("error when checking -promscrape.config: %s", err)
+		}
+		logger.Infof("-promscrape.config is ok; exitting with 0 status code")
+		return
+	}
+
 	logger.Infof("starting VictoriaMetrics at %q...", *httpListenAddr)
 	startTime := time.Now()
 	storage.SetMinScrapeIntervalForDeduplication(*minScrapeInterval)
-	vmstorage.Init()
+	vmstorage.Init(promql.ResetRollupResultCacheIfNeeded)
 	vmselect.Init()
 	vminsert.Init()
 	startSelfScraper()
@@ -64,6 +85,18 @@ func main() {
 }
 
 func requestHandler(w http.ResponseWriter, r *http.Request) bool {
+	if r.URL.Path == "/" {
+		fmt.Fprintf(w, "<h2>Single-node VictoriaMetrics.</h2></br>")
+		fmt.Fprintf(w, "See docs at <a href='https://victoriametrics.github.io/'>https://victoriametrics.github.io/</a></br>")
+		fmt.Fprintf(w, "Useful endpoints: </br>")
+		writeAPIHelp(w, [][]string{
+			{"/targets", "discovered targets list"},
+			{"/api/v1/targets", "advanced information about discovered targets in JSON format"},
+			{"/metrics", "available service metrics"},
+			{"/api/v1/status/tsdb", "tsdb status page"},
+		})
+		return true
+	}
 	if vminsert.RequestHandler(w, r) {
 		return true
 	}
@@ -75,3 +108,21 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 	}
 	return false
 }
+
+func writeAPIHelp(w io.Writer, pathList [][]string) {
+	pathPrefix := httpserver.GetPathPrefix()
+	for _, p := range pathList {
+		p, doc := p[0], p[1]
+		p = path.Join(pathPrefix, p)
+		fmt.Fprintf(w, "<a href='%s'>%q</a> - %s<br/>", p, p, doc)
+	}
+}
+
+func usage() {
+	const s = `
+victoria-metrics is a time series database and monitoring solution.
+
+See the docs at https://victoriametrics.github.io/
+`
+	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"]]}
       ]}}
 }

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/name-plus-negative-filter.json

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

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

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

app/victoria-metrics/testdata/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

@@ -59,19 +59,28 @@ run-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
+
+vmagent-windows-amd64-prod:
+	APP_NAME=vmagent $(MAKE) app-via-docker-windows-amd64

app/vmagent/README.md

@@ -1,46 +1,49 @@
 ## vmagent
 
-`vmagent` is a tiny but brave agent, which helps you collect metrics from various sources
-and stores them in [VictoriaMetrics](https://github.com/VictoriaMetrics/VictoriaMetrics)
-or any other Prometheus-compatible storage system that supports the `remote_write` protocol.
+`vmagent` is a tiny but mighty agent which helps you collect metrics from various sources
+and store them in [VictoriaMetrics](https://github.com/VictoriaMetrics/VictoriaMetrics)
+or any other Prometheus-compatible storage systems that support the `remote_write` protocol.
 
 <img alt="vmagent" src="vmagent.png">
 
 
-### Motivation
+## Motivation
 
 While VictoriaMetrics provides an efficient solution to store and observe metrics, our users needed something fast
-and RAM friendly to scrape metrics from Prometheus-compatible exporters to VictoriaMetrics.
-Also, we found that users’ infrastructure are snowflakes - no two are alike, and we decided to add more flexibility
-to `vmagent` (like the ability to push metrics instead of pulling them). We did our best and plan to do even more.
+and RAM friendly to scrape metrics from Prometheus-compatible exporters into VictoriaMetrics.
+Also, we found that our user's infrastructure are like snowflakes in that no two are alike. Therefore we decided to add more flexibility
+to `vmagent` such as the ability to push metrics instead of pulling them. We did our best and will continue to improve vmagent.
 
 
-### Features
+## Features
 
-* Can be used as drop-in replacement for Prometheus for scraping targets such as [node_exporter](https://github.com/prometheus/node_exporter).
+* Can be used as a drop-in replacement for Prometheus for scraping targets such as [node_exporter](https://github.com/prometheus/node_exporter).
   See [Quick Start](#quick-start) for details.
 * Can add, remove and modify labels (aka tags) via Prometheus relabeling. Can filter data before sending it to remote storage. See [these docs](#relabeling) for details.
-* Accepts data via all the ingestion protocols supported by VictoriaMetrics:
-  * Influx line protocol via `http://<vmagent>:8429/write`. See [these docs](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/README.md#how-to-send-data-from-influxdb-compatible-agents-such-as-telegraf).
-  * Graphite plaintext protocol if `-graphiteListenAddr` command-line flag is set. See [these docs](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/README.md#how-to-send-data-from-graphite-compatible-agents-such-as-statsd).
-  * OpenTSDB telnet and http protocols if `-opentsdbListenAddr` command-line flag is set. See [these docs](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/README.md#how-to-send-data-from-opentsdb-compatible-agents).
+* Accepts data via all ingestion protocols supported by VictoriaMetrics:
+  * Influx line protocol via `http://<vmagent>:8429/write`. See [these docs](https://victoriametrics.github.io/Single-server-VictoriaMetrics.html#how-to-send-data-from-influxdb-compatible-agents-such-as-telegraf).
+  * Graphite plaintext protocol if `-graphiteListenAddr` command-line flag is set. See [these docs](https://victoriametrics.github.io/Single-server-VictoriaMetrics.html#how-to-send-data-from-graphite-compatible-agents-such-as-statsd).
+  * OpenTSDB telnet and http protocols if `-opentsdbListenAddr` command-line flag is set. See [these docs](https://victoriametrics.github.io/Single-server-VictoriaMetrics.html#how-to-send-data-from-opentsdb-compatible-agents).
   * Prometheus remote write protocol via `http://<vmagent>:8429/api/v1/write`.
-  * JSON lines import protocol via `http://<vmagent>:8429/api/v1/import`. See [these docs](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/README.md#how-to-import-time-series-data).
-  * Arbitrary CSV data via `http://<vmagent>:8429/api/v1/import/csv`. See [these docs](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/README.md#how-to-import-csv-data).
+  * JSON lines import protocol via `http://<vmagent>:8429/api/v1/import`. See [these docs](https://victoriametrics.github.io/Single-server-VictoriaMetrics.html#how-to-import-data-in-json-line-format).
+  * Native data import protocol via `http://<vmagent>:8429/api/v1/import/native`. See [these docs](https://victoriametrics.github.io/Single-server-VictoriaMetrics.html#how-to-import-data-in-native-format).
+  * Data in Prometheus exposition format. See [these docs](https://victoriametrics.github.io/Single-server-VictoriaMetrics.html#how-to-import-data-in-prometheus-exposition-format) for details.
+  * Arbitrary CSV data via `http://<vmagent>:8429/api/v1/import/csv`. See [these docs](https://victoriametrics.github.io/Single-server-VictoriaMetrics.html#how-to-import-csv-data).
 * Can replicate collected metrics simultaneously to multiple remote storage systems.
-* Works in environments with unstable connections to remote storage. If the remote storage is unavailable, the collected metrics
-  are buffered at `-remoteWrite.tmpDataPath`. The buffered metrics are sent to remote storage as soon as connection
-  to remote storage is recovered. The maximum disk usage for the buffer can be limited with `-remoteWrite.maxDiskUsagePerURL`.
-* Uses lower amounts of RAM, CPU, disk IO and network bandwidth compared to Prometheus.
+* Works smoothly in environments with unstable connections to remote storage. If the remote storage is unavailable, the collected metrics
+  are buffered at `-remoteWrite.tmpDataPath`. The buffered metrics are sent to remote storage as soon as the connection
+  to the remote storage is repaired. The maximum disk usage for the buffer can be limited with `-remoteWrite.maxDiskUsagePerURL`.
+* Uses lower amounts of RAM, CPU, disk IO and network bandwidth compared with Prometheus.
+* Scrape targets can be spread among multiple `vmagent` instances when big number of targets must be scraped. See [these docs](#scraping-big-number-of-targets) for details.
 
 
-### Quick Start
+## Quick Start
 
-Just download `vmutils-*` archive from [releases page](https://github.com/VictoriaMetrics/VictoriaMetrics/releases), unpack it
-and pass the following flags to `vmagent` binary in order to start scraping Prometheus targets:
+Please download `vmutils-*` archive from [releases page](https://github.com/VictoriaMetrics/VictoriaMetrics/releases), unpack it
+and configure the following flags to the `vmagent` binary in order to start scraping Prometheus targets:
 
-* `-promscrape.config` with the path to Prometheus config file (it is usually located at `/etc/prometheus/prometheus.yml`)
-* `-remoteWrite.url` with the remote storage endpoint such as VictoriaMetrics. The `-remoteWrite.url` argument can be specified multiple times in order to replicate data concurrently to an arbitrary amount of remote storage systems.
+* `-promscrape.config` with the path to Prometheus config file (usually located at `/etc/prometheus/prometheus.yml`)
+* `-remoteWrite.url` with the remote storage endpoint such as VictoriaMetrics, the `-remoteWrite.url` argument can be specified multiple times to replicate data concurrently to an arbitrary number of remote storage systems.
 
 Example command line:
 
@@ -48,138 +51,180 @@ Example command line:
 /path/to/vmagent -promscrape.config=/path/to/prometheus.yml -remoteWrite.url=https://victoria-metrics-host:8428/api/v1/write
 ```
 
-If you only need to collect Influx data, then the following is sufficient:
+If you only need to collect Influx data, then the following command is sufficient:
 
 ```
 /path/to/vmagent -remoteWrite.url=https://victoria-metrics-host:8428/api/v1/write
 ```
 
-Then send Influx data to `http://vmagent-host:8429`. See [these docs](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/README.md#how-to-send-data-from-influxdb-compatible-agents-such-as-telegraf) for more details.
+Then send Influx data to `http://vmagent-host:8429`. See [these docs](https://victoriametrics.github.io/Single-server-VictoriaMetrics.html#how-to-send-data-from-influxdb-compatible-agents-such-as-telegraf) for more details.
 
 `vmagent` is also available in [docker images](https://hub.docker.com/r/victoriametrics/vmagent/tags).
 
-Pass `-help` to `vmagent` in order to see the full list of supported command-line flags with their descriptions.
+Pass `-help` to `vmagent` in order to see [the full list of supported command-line flags with their descriptions](#advanced-usage).
 
 
-### Use cases
+## Configuration update
+
+`vmagent` should be restarted in order to update config options set via command-line args.
+
+`vmagent` supports multiple approaches for reloading configs from updated config files such as `-promscrape.config`, `-remoteWrite.relabelConfig` and `-remoteWrite.urlRelabelConfig`:
+
+* Sending `SUGHUP` signal to `vmagent` process:
+  ```bash
+  kill -SIGHUP `pidof vmagent`
+  ```
+
+* Sending HTTP request to `http://vmagent:8429/-/reload` endpoint.
+
+There is also `-promscrape.configCheckInterval` command-line option, which can be used for automatic reloading configs from updated `-promscrape.config` file.
 
 
-#### IoT and Edge monitoring
+## Use cases
 
-`vmagent` can run and collect metrics in IoT and industrial networks with unreliable or scheduled connections to the remote storage.
+
+### IoT and Edge monitoring
+
+`vmagent` can run and collect metrics in IoT and industrial networks with unreliable or scheduled connections to their remote storage.
 It buffers the collected data in local files until the connection to remote storage becomes available and then sends the buffered
-data to the remote storage. It re-tries sending the data to remote storage on any errors.
+data to the remote storage. It re-tries sending the data to remote storage until any errors are resolved.
 The maximum buffer size can be limited with `-remoteWrite.maxDiskUsagePerURL`.
 
-`vmagent` works on various architectures from IoT world - 32-bit arm, 64-bit arm, ppc64, 386, amd64.
+`vmagent` works on various architectures from the IoT world - 32-bit arm, 64-bit arm, ppc64, 386, amd64.
 See [the corresponding Makefile rules](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/app/vmagent/Makefile) for details.
 
 
-#### Drop-in replacement for Prometheus
+### Drop-in replacement for Prometheus
 
-If you use Prometheus only for scraping metrics from various targets and forwarding these metrics to remote storage,
-then `vmagent` can replace such Prometheus setup. Usually `vmagent` requires lower amounts of RAM, CPU and network bandwidth comparing to Prometheus for such a setup.
+If you use Prometheus only for scraping metrics from various targets and forwarding those metrics to remote storage
+then `vmagent` can replace Prometheus. Typically, `vmagent` requires lower amounts of RAM, CPU and network bandwidth compared with Prometheus.
 See [these docs](#how-to-collect-metrics-in-prometheus-format) for details.
 
 
-#### Replication and high availability
+### Replication and high availability
 
 `vmagent` replicates the collected metrics among multiple remote storage instances configured via `-remoteWrite.url` args.
-If a single remote storage instance temporarily is out of service, then the collected data remains available in another remote storage instances.
-`vmagent` buffers the collected data in files at `-remoteWrite.tmpDataPath` until the remote storage becomes available again.
-Then it sends the buffered data to the remote storage in order to prevent data gaps in the remote storage.
+If a single remote storage instance temporarily is out of service, then the collected data remains available in another remote storage instance.
+`vmagent` buffers the collected data in files at `-remoteWrite.tmpDataPath` until the remote storage becomes available again and then it sends the buffered data to the remote storage in order to prevent data gaps.
 
 
-#### Relabeling and filtering
+### Relabeling and filtering
 
-`vmagent` can add, remove or update labels on the collected data before sending it to remote storage. Additionally,
+`vmagent` can add, remove or update labels on the collected data before sending it to the remote storage. Additionally,
 it can remove unwanted samples via Prometheus-like relabeling before sending the collected data to remote storage.
-See [these docs](#relabeling) for details.
+Please see [these docs](#relabeling) for details.
 
 
-#### Splitting data streams among multiple systems
+### Splitting data streams among multiple systems
 
 `vmagent` supports splitting the collected data between muliple destinations with the help of `-remoteWrite.urlRelabelConfig`,
-which is applied independently for each configured `-remoteWrite.url` destination. For instance, it is possible to replicate or split
-data among long-term remote storage, short-term remote storage and real-time analytical system [built on top of Kafka](https://github.com/Telefonica/prometheus-kafka-adapter).
-Note that each destination can receive its own subset of the collected data thanks to per-destination relabeling via `-remoteWrite.urlRelabelConfig`.
+which is applied independently for each configured `-remoteWrite.url` destination. For example, it is possible to replicate or split
+data among long-term remote storage, short-term remote storage and a real-time analytical system [built on top of Kafka](https://github.com/Telefonica/prometheus-kafka-adapter).
+Note that each destination can receive it's own subset of the collected data due to per-destination relabeling via `-remoteWrite.urlRelabelConfig`.
 
 
-#### Prometheus remote_write proxy
+### Prometheus remote_write proxy
 
-`vmagent` may be used as a proxy for Prometheus data sent via Prometheus `remote_write` protocol. It can accept data via `remote_write` API
-at `/api/v1/write` endpoint, apply relabeling and filtering and then proxy it to another `remote_write` systems.
+`vmagent` can be used as a proxy for Prometheus data sent via Prometheus `remote_write` protocol. It can accept data via the `remote_write` API
+at the`/api/v1/write` endpoint. Then apply relabeling and filtering and proxy it to another `remote_write` system .
 The `vmagent` can be configured to encrypt the incoming `remote_write` requests with `-tls*` command-line flags.
-Additionally, Basic Auth can be enabled for the incoming `remote_write` requests with `-httpAuth.*` command-line flags.
+Also, Basic Auth can be enabled for the incoming `remote_write` requests with `-httpAuth.*` command-line flags.
 
 
+### remote_write for clustered version
 
-### How to collect metrics in Prometheus format
+While `vmagent` can accept data in several supported protocols (OpenTSDB, Influx, Prometheus, Graphite) and scrape data from various targets, writes are always peformed in Promethes remote_write protocol. Therefore for the [clustered version](https://victoriametrics.github.io/Cluster-VictoriaMetrics.html), `-remoteWrite.url` the command-line flag should be configured as `<schema>://<vminsert-host>:8480/insert/<customer-id>/prometheus/api/v1/write`
 
-Pass the path to `prometheus.yml` to `-promscrape.config` command-line flag. `vmagent` takes into account the following
+
+## How to collect metrics in Prometheus format
+
+Specify the path to `prometheus.yml` file via `-promscrape.config` command-line flag. `vmagent` takes into account the following
 sections from [Prometheus config file](https://prometheus.io/docs/prometheus/latest/configuration/configuration/):
 
 * `global`
 * `scrape_configs`
 
-All the other sections are ignored, including [remote_write](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#remote_write) section.
-Use `-remoteWrite.*` command-line flags instead for configuring remote write settings.
+All other sections are ignored, including the [remote_write](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#remote_write) section.
+Use `-remoteWrite.*` command-line flag instead for configuring remote write settings.
 
 The following scrape types in [scrape_config](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#scrape_config) section are supported:
 
-* `static_configs` - for scraping statically defined targets. See [these docs](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#static_config) for details.
-* `file_sd_configs` - for scraping targets defined in external files aka file-based service discover.
-  See [these docs](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#file_sd_config) for details.
+* `static_configs` - is for scraping statically defined targets. See [these docs](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#static_config) for details.
+* `file_sd_configs` - is for scraping targets defined in external files (aka file-based service discover).
+  See [these docs](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#file_sd_config) for details
 * `kubernetes_sd_configs` - for scraping targets in Kubernetes (k8s).
   See [kubernetes_sd_config](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#kubernetes_sd_config) for details.
-* `ec2_sd_configs` - for scraping targets in Amazon EC2.
+* `ec2_sd_configs` - is for scraping targets in Amazon EC2.
   See [ec2_sd_config](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#ec2_sd_config) for details.
-  `vmagent` doesn't support `role_arn` config param yet.
-* `gce_sd_configs` - for scraping targets in Google Compute Engine (GCE).
+  `vmagent` doesn't support the `profile` config param yet.
+* `gce_sd_configs` - is for scraping targets in Google Compute Engine (GCE).
   See [gce_sd_config](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#gce_sd_config) for details.
   `vmagent` provides the following additional functionality for `gce_sd_config`:
-  * if `project` arg is missing, then `vmagent` uses the project for the instance where it runs;
-  * if `zone` arg is missing, then `vmagent` uses the zone for the instance where it runs;
-  * if `zone` arg equals to `"*"`, then `vmagent` discovers all the zones for the given project;
-  * `zone` may contain arbitrary number of zones, i.e. `zone: [us-east1-a, us-east1-b]`.
-* `consul_sd_configs` - for scraping targets registered in Consul.
+  * if `project` arg is missing then `vmagent` uses the project for the instance where it runs;
+  * if `zone` arg is missing then `vmagent` uses the zone for the instance where it runs;
+  * if `zone` arg is equal to `"*"`, then `vmagent` discovers all the zones for the given project;
+  * `zone` may contain an arbitrary number of zones, i.e. `zone: [us-east1-a, us-east1-b]`.
+* `consul_sd_configs` - is for scraping the targets registered in Consul.
   See [consul_sd_config](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#consul_sd_config) for details.
-* `dns_sd_configs` - for scraping targets discovered from DNS records (SRV, A and AAAA).
+* `dns_sd_configs` - is for scraping targets discovered from DNS records (SRV, A and AAAA).
   See [dns_sd_config](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#dns_sd_config) for details.
+* `openstack_sd_configs` - is for scraping OpenStack targets.
+  See [openstack_sd_config](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#openstack_sd_config) for details.
+  [OpenStack identity API v3](https://docs.openstack.org/api-ref/identity/v3/) is supported only.
+* `dockerswarm_sd_configs` - is for scraping Docker Swarm targets.
+  See [dockerswarm_sd_config](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#dockerswarm_sd_config) for details.
+* `eureka_sd_configs` - is for scraping targets registered in [Netflix Eureka](https://github.com/Netflix/eureka).
+  See [eureka_sd_config](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#eureka_sd_config) for details.
 
-Note that `vmagent` doesn't support `refresh_interval` option these scrape configs. Use the corresponding `-promscrape.*CheckInterval`
+Please file feature requests to [our issue tracker](https://github.com/VictoriaMetrics/VictoriaMetrics/issues) if you need other service discovery mechanisms to be supported by `vmagent`.
+
+`vmagent` also support the following additional options in `scrape_config` section:
+
+* `disable_compression: true` - to disable response compression on a per-job basis. By default `vmagent` requests compressed responses from scrape targets
+  to save network bandwidth.
+* `disable_keepalive: true` - to disable [HTTP keep-alive connections](https://en.wikipedia.org/wiki/HTTP_persistent_connection) on a per-job basis.
+  By default, `vmagent` uses keep-alive connections to scrape targets to reduce overhead on connection re-establishing.
+* `stream_parse: true` - for scraping targets in a streaming manner. This may be useful for targets exporting big number of metrics.
+
+Note that `vmagent` doesn't support `refresh_interval` option for these scrape configs. Use the corresponding `-promscrape.*CheckInterval`
 command-line flag instead. For example, `-promscrape.consulSDCheckInterval=60s` sets `refresh_interval` for all the `consul_sd_configs`
-entries to 60s. Run `vmagent -help` in order to see default values for `-promscrape.*CheckInterval` flags.
+entries to 60s. Run `vmagent -help` in order to see default values for the `-promscrape.*CheckInterval` flags.
+
+The file pointed by `-promscrape.config` may contain `%{ENV_VAR}` placeholders which are substituted by the corresponding `ENV_VAR` environment variable values.
 
 
-File feature requests at [our issue tracker](https://github.com/VictoriaMetrics/VictoriaMetrics/issues) if you need other service discovery mechanisms to be supported by `vmagent`.
+## Adding labels to metrics
+
+Labels can be added to metrics by the following mechanisms:
+
+* The `global -> external_labels` section in `-promscrape.config` file. These labels are added only to metrics scraped from targets configured in the `-promscrape.config` file. They aren't added to metrics collected via other [data ingestion protocols](https://victoriametrics.github.io/#how-to-import-time-series-data).
+* The `-remoteWrite.label` command-line flag. These labels are added to all the collected metrics before sending them to `-remoteWrite.url`. For example, the following command will start `vmagent`, which will add `{datacenter="foobar"}` label to all the metrics pushed to all the configured remote storage systems (all the `-remoteWrite.url` flag values):
+
+```
+/path/to/vmagent -remoteWrite.label=datacenter=foobar ...
+```
 
 
-### Adding labels to metrics
-
-Labels can be added to metrics via the following mechanisms:
-
-* Via `global -> external_labels` section in `-promscrape.config` file. These labels are added only to metrics scraped from targets configured in `-promscrape.config` file.
-* Via `-remoteWrite.label` command-line flag. These labels are added to all the collected metrics before sending them to `-remoteWrite.url`.
-
-
-### Relabeling
+## Relabeling
 
 `vmagent` supports [Prometheus relabeling](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config).
-Additionally it provides the following extra actions:
+and also provides the following actions:
 
-* `replace_all`: replaces all the occurences of `regex` in the values of `source_labels` with the `replacement` and stores the result in the `target_label`.
-* `labelmap_all`: replaces all the occurences of `regex` in all the label names with the `replacement`.
+* `replace_all`: replaces all of the occurences of `regex` in the values of `source_labels` with the `replacement` and stores the results in the `target_label`.
+* `labelmap_all`: replaces all of the occurences of `regex` in all the label names with the `replacement`.
+* `keep_if_equal`: keeps the entry if all the label values from `source_labels` are equal.
+* `drop_if_equal`: drops the entry if all the label values from `source_labels` are equal.
 
 The relabeling can be defined in the following places:
 
-* At `scrape_config -> relabel_configs` section in `-promscrape.config` file. This relabeling is applied to target labels.
-* At `scrape_config -> metric_relabel_configs` section in `-promscrape.config` file. This relabeling is applied to all the scraped metrics in the given `scrape_config`.
-* At `-remoteWrite.relabelConfig` file. This relabeling is aplied to all the collected metrics before sending them to remote storage.
-* At `-remoteWrite.urlRelabelConfig` files. This relabeling is applied to metrics before sending them to the corresponding `-remoteWrite.url`.
+* At the `scrape_config -> relabel_configs` section in `-promscrape.config` file. This relabeling is applied to target labels.
+* At the `scrape_config -> metric_relabel_configs` section in `-promscrape.config` file. This relabeling is applied to all the scraped metrics in the given `scrape_config`.
+* At the `-remoteWrite.relabelConfig` file. This relabeling is aplied to all the collected metrics before sending them to remote storage.
+* At the `-remoteWrite.urlRelabelConfig` files. This relabeling is applied to metrics before sending them to the corresponding `-remoteWrite.url`.
 
-Read more about relabeling in the following articles:
+You can read more about relabeling in the following articles:
 
+* [How to use Relabeling in Prometheus and VictoriaMetrics](https://valyala.medium.com/how-to-use-relabeling-in-prometheus-and-victoriametrics-8b90fc22c4b2)
 * [Life of a label](https://www.robustperception.io/life-of-a-label)
 * [Discarding targets and timeseries with relabeling](https://www.robustperception.io/relabelling-can-discard-targets-timeseries-and-alerts)
 * [Dropping labels at scrape time](https://www.robustperception.io/dropping-metrics-at-scrape-time-with-prometheus)
@@ -187,72 +232,240 @@ Read more about relabeling in the following articles:
 * [relabel_configs vs metric_relabel_configs](https://www.robustperception.io/relabel_configs-vs-metric_relabel_configs)
 
 
-### Monitoring
+## Scraping big number of targets
 
-`vmagent` exports various metrics in Prometheus exposition format at `http://vmagent-host:8429/metrics` page. It is recommended setting up regular scraping of this page
-either via `vmagent` itself or via Prometheus, so the exported metrics could be analyzed later.
+A single `vmagent` instance can scrape tens of thousands of scrape targets. Sometimes this isn't enough due to limitations on CPU, network, RAM, etc.
+In this case scrape targets can be split among multiple `vmagent` instances (aka `vmagent` horizontal scaling and clustering).
+Each `vmagent` instance in the cluster must use identical `-promscrape.config` files with distinct `-promscrape.cluster.memberNum` values.
+The flag value must be in the range `0 ... N-1`, where `N` is the number of `vmagent` instances in the cluster.
+The number of `vmagent` instances in the cluster must be passed to `-promscrape.cluster.membersCount` command-line flag. For example, the following commands
+spread scrape targets among a cluster of two `vmagent` instances:
 
-`vmagent` also exports target statuses at `http://vmagent-host:8429/targets` page in plaintext format.
+```
+/path/to/vmagent -promscrape.cluster.membersCount=2 -promscrape.cluster.memberNum=0 -promscrape.config=/path/to/config.yml ...
+/path/to/vmagent -promscrape.cluster.membersCount=2 -promscrape.cluster.memberNum=1 -promscrape.config=/path/to/config.yml ...
+```
+
+By default each scrape target is scraped only by a single `vmagent` instance in the cluster. If there is a need for replicating scrape targets among multiple `vmagent` instances,
+then `-promscrape.cluster.replicationFactor` command-line flag must be set to the desired number of replicas. For example, the following commands
+start a cluster of three `vmagent` instances, where each target is scraped by two `vmagent` instances:
+
+```
+/path/to/vmagent -promscrape.cluster.membersCount=3 -promscrape.cluster.replicationFactor=2 -promscrape.cluster.memberNum=0 -promscrape.config=/path/to/config.yml ...
+/path/to/vmagent -promscrape.cluster.membersCount=3 -promscrape.cluster.replicationFactor=2 -promscrape.cluster.memberNum=1 -promscrape.config=/path/to/config.yml ...
+/path/to/vmagent -promscrape.cluster.membersCount=3 -promscrape.cluster.replicationFactor=2 -promscrape.cluster.memberNum=2 -promscrape.config=/path/to/config.yml ...
+```
+
+If each target is scraped by multiple `vmagent` instances, then data deduplication must be enabled at remote storage pointed by `-remoteWrite.url`.
+See [these docs](https://victoriametrics.github.io/#deduplication) for details.
 
 
-### Troubleshooting
+## Scraping targets via a proxy
 
-* It is recommended increasing the maximum number of open files in the system (`ulimit -n`) when scraping big number of targets,
-  since `vmagent` establishes at least a single TCP connection per each target.
+`vmagent` supports scraping targets via http and https proxies. Proxy address must be specified in `proxy_url` option. For example, the following scrape config instructs
+target scraping via https proxy at `https://proxy-addr:1234`:
 
-* When `vmagent` scrapes many unreliable targets, it can flood error log with scrape errors. These errors can be suppressed
-  by passing `-promscrape.suppressScrapeErrors` command-line flag to `vmagent`. The most recent scrape error per each target can be observed at `http://vmagent-host:8429/targets`.
+```yml
+scrape_configs:
+- job_name: foo
+  proxy_url: https://proxy-addr:1234
+```
 
-* It is recommended to increase `-remoteWrite.queues` if `vmagent` collects more than 100K samples per second
-  and `vmagent_remotewrite_pending_data_bytes` metric exported at `http://vmagent-host:8429/metrics` page constantly grows.
+Proxy can be configured with the following optional settings:
 
-* `vmagent` buffers scraped data at `-remoteWrite.tmpDataPath` directory until it is sent to `-remoteWrite.url`.
-  The directory can grow large when remote storage is unavailable for extended periods of time and if `-remoteWrite.maxDiskUsagePerURL` isn't set.
-  If you don't want to send all the data from the directory to remote storage, simply stop `vmagent` and delete the directory.
+* `proxy_bearer_token` and `proxy_bearer_token_file` for Bearer token authorization
+* `proxy_basic_auth` for Basic authorization. See [these docs](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#scrape_config).
+* `proxy_tls_config` for TLS config. See [these docs](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#tls_config).
 
+For example:
 
-### How to build from sources
-
-It is recommended using [binary releases](https://github.com/VictoriaMetrics/VictoriaMetrics/releases) - `vmagent` is located in `vmutils-*` archives there.
-
-
-#### Development build
-
-1. [Install Go](https://golang.org/doc/install). The minimum supported version is Go 1.13.
-2. Run `make vmagent` from the root folder of the repository.
-   It builds `vmagent` binary and puts it into the `bin` folder.
-
-#### Production build
-
-1. [Install docker](https://docs.docker.com/install/).
-2. Run `make vmagent-prod` from the root folder of the repository.
-   It builds `vmagent-prod` binary and puts it into the `bin` folder.
-
-#### Building docker images
-
-Run `make package-vmagent`. It builds `victoriametrics/vmagent:<PKG_TAG>` docker image locally.
-`<PKG_TAG>` is auto-generated image tag, which depends on source code in the repository.
-The `<PKG_TAG>` may be manually set via `PKG_TAG=foobar make package-vmagent`.
-
-By default the image is built on top of `scratch` image. It is possible to build the package on top of any other base image
-by setting it via `<ROOT_IMAGE>` environment variable. For example, the following command builds the image on top of `alpine:3.11` image:
-
-```bash
-ROOT_IMAGE=alpine:3.11 make package-vmagent
+```yml
+scrape_configs:
+- job_name: foo
+  proxy_url: https://proxy-addr:1234
+  proxy_basic_auth:
+    username: foobar
+    password: secret
+  proxy_tls_config:
+    insecure_skip_verify: true
+    cert_file: /path/to/cert
+    key_file: /path/to/key
+    ca_file: /path/to/ca
+    server_name: real-server-name
 ```
 
 
-### Profiling
+## Monitoring
+
+`vmagent` exports various metrics in Prometheus exposition format at `http://vmagent-host:8429/metrics` page. We recommend setting up regular scraping of this page
+either through `vmagent` itself or by Prometheus so that the exported metrics may be analyzed later.
+Use official [Grafana dashboard](https://grafana.com/grafana/dashboards/12683) for `vmagent` state overview.
+If you have suggestions for improvements or have found a bug - please open an issue on github or add a review to the dashboard.
+
+`vmagent` also exports the status for various targets at the following handlers:
+
+* `http://vmagent-host:8429/targets`. This handler returns human-readable status for every active target.
+This page is easy to query from the command line with `wget`, `curl` or similar tools.
+It accepts optional `show_original_labels=1` query arg which shows the original labels per each target before applying the relabeling.
+This information may be useful for debugging target relabeling.
+* `http://vmagent-host:8429/api/v1/targets`. This handler returns data compatible with [the corresponding page from Prometheus API](https://prometheus.io/docs/prometheus/latest/querying/api/#targets).
+
+* `http://vmagent-host:8429/ready`. This handler returns http 200 status code when `vmagent` finishes it's initialization for all service_discovery configs.
+It may be useful to perform `vmagent` rolling update without any scrape loss.
+
+
+## Troubleshooting
+
+* We recommend you [set up the official Grafana dashboard](#monitoring) in order to monitor the state of `vmagent'.
+
+* We recommend you increase the maximum number of open files in the system (`ulimit -n`) when scraping a big number of targets,
+  as `vmagent` establishes at least a single TCP connection per target.
+
+* When `vmagent` scrapes many unreliable targets, it can flood the error log with scrape errors. These errors can be suppressed
+  by passing `-promscrape.suppressScrapeErrors` command-line flag to `vmagent`. The most recent scrape error per each target can be observed at `http://vmagent-host:8429/targets`
+  and `http://vmagent-host:8429/api/v1/targets`.
+
+* The `/api/v1/targets` page could be useful for debugging relabeling process for scrape targets.
+  This page contains original labels for targets dropped during relabeling (see "droppedTargets" section in the page output). By default the `-promscrape.maxDroppedTargets` targets are shown here. If your setup drops more targets during relabeling, then increase `-promscrape.maxDroppedTargets` command-line flag value to see all the dropped targets. Note that tracking each dropped target requires up to 10Kb of RAM. Therefore big values for `-promscrape.maxDroppedTargets` may result in increased memory usage if a big number of scrape targets are dropped during relabeling.
+
+* If `vmagent` scrapes a big number of targets then the `-promscrape.dropOriginalLabels` command-line option may be passed to `vmagent` in order to reduce memory usage.
+  This option drops `"discoveredLabels"` and `"droppedTargets"` lists at `/api/v1/targets` page, which may result in reduced debuggability for improperly configured per-target relabeling.
+
+* If `vmagent` scrapes targets with millions of metrics per target (for example, when scraping [federation endpoints](https://prometheus.io/docs/prometheus/latest/federation/)),
+  we recommend enabling `stream parsing mode` in order to reduce memory usage during scraping. This mode may be enabled either globally for all of the scrape targets
+  by passing `-promscrape.streamParse` command-line flag or on a per-scrape target basis with `stream_parse: true` option. For example:
+
+  ```yml
+  scrape_configs:
+  - job_name: 'big-federate'
+    stream_parse: true
+    static_configs:
+    - targets:
+      - big-prometeus1
+      - big-prometeus2
+    honor_labels: true
+    metrics_path: /federate
+    params:
+      'match[]': ['{__name__!=""}']
+  ```
+
+  Note that `sample_limit` option doesn't work if stream parsing is enabled because the parsed data is pushed to remote storage as soon as it is parsed. Therefore the `sample_limit` option
+ doesn't make sense during stream parsing.
+
+* We recommend you increase `-remoteWrite.queues` if `vmagent_remotewrite_pending_data_bytes` metric exported at `http://vmagent-host:8429/metrics` page grows constantly.
+
+* If you see gaps in the data pushed by `vmagent` to remote storage when `-remoteWrite.maxDiskUsagePerURL` is set, try increasing `-remoteWrite.queues`.
+  Such gaps may appear because `vmagent` cannot keep up with sending the collected data to remote storage. Therefore it starts dropping the buffered data
+  if the on-disk buffer size exceeds `-remoteWrite.maxDiskUsagePerURL`.
+
+* `vmagent` drops data blocks if remote storage replies with `400 Bad Request` and `409 Conflict` HTTP responses. The number of dropped blocks can be monitored via `vmagent_remotewrite_packets_dropped_total` metric exported at [/metrics page](#monitoring).
+
+* Use `-remoteWrite.queues=1` when `-remoteWrite.url` points to remote storage, which doesn't accept out-of-order samples (aka data backfilling). Such storage systems include Prometheus, Cortex and Thanos.
+
+* `vmagent` buffers scraped data at the `-remoteWrite.tmpDataPath` directory until it is sent to `-remoteWrite.url`.
+  The directory can grow large when remote storage is unavailable for extended periods of time and if `-remoteWrite.maxDiskUsagePerURL` isn't set.
+  If you don't want to send all the data from the directory to remote storage then simply stop `vmagent` and delete the directory.
+
+* By default `vmagent` masks `-remoteWrite.url` with `secret-url` values in logs and at `/metrics` page because
+  the url may contain sensitive information such as auth tokens or passwords.
+  Pass `-remoteWrite.showURL` command-line flag when starting `vmagent` in order to see all the valid urls.
+
+* By default `vmagent` evenly spreads scrape load in time. If a particular scrape target must be scraped at the beginning of some interval,
+  then `scrape_align_interval` option  must be used. For example, the following config aligns hourly scrapes to the beginning of hour:
+
+  ```yml
+  scrape_configs:
+  - job_name: foo
+    scrape_interval: 1h
+    scrape_align_interval: 1h
+  ```
+
+* By default `vmagent` evenly spreads scrape load in time. If a particular scrape target must be scraped at specific offset, then `scrape_offset` option must be used.
+  For example, the following config instructs `vmagent` to scrape the target at 10 seconds of every minute:
+
+  ```yml
+  scrape_configs:
+  - job_name: foo
+    scrape_interval: 1m
+    scrape_offset: 10s
+  ```
+
+* If you see `skipping duplicate scrape target with identical labels` errors when scraping Kubernetes pods, then it is likely these pods listen to multiple ports
+  or they use an init container. These errors can either be fixed or suppressed with the `-promscrape.suppressDuplicateScrapeTargetErrors` command-line flag.
+  See the available options below if you prefer fixing the root cause of the error:
+
+  The following relabeling rule may be added to `relabel_configs` section in order to filter out pods with unneeded ports:
+  ```yml
+  - action: keep_if_equal
+    source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_port, __meta_kubernetes_pod_container_port_number]
+  ```
+
+  The following relabeling rule may be added to `relabel_configs` section in order to filter out init container pods:
+  ```yml
+  - action: drop
+    source_labels: [__meta_kubernetes_pod_container_init]
+    regex: true
+  ```
+
+
+## How to build from sources
+
+We recommend using [binary releases](https://github.com/VictoriaMetrics/VictoriaMetrics/releases) - `vmagent` is located in the `vmutils-*` archives .
+
+
+### Development build
+
+1. [Install Go](https://golang.org/doc/install). The minimum supported version is Go 1.15.
+2. Run `make vmagent` from the root folder of [the repository](https://github.com/VictoriaMetrics/VictoriaMetrics).
+   It builds the `vmagent` binary and puts it into the `bin` folder.
+
+### Production build
+
+1. [Install docker](https://docs.docker.com/install/).
+2. Run `make vmagent-prod` from the root folder of [the repository](https://github.com/VictoriaMetrics/VictoriaMetrics).
+   It builds `vmagent-prod` binary and puts it into the `bin` folder.
+
+### Building docker images
+
+Run `make package-vmagent`. It builds `victoriametrics/vmagent:<PKG_TAG>` docker image locally.
+`<PKG_TAG>` is an auto-generated image tag, which depends on source code in [the repository](https://github.com/VictoriaMetrics/VictoriaMetrics).
+The `<PKG_TAG>` may be manually set via `PKG_TAG=foobar make package-vmagent`.
+
+The base docker image is [alpine](https://hub.docker.com/_/alpine) but it is possible to use any other base image
+by setting it via `<ROOT_IMAGE>` environment variable. For example, the following command builds the image on top of [scratch](https://hub.docker.com/_/scratch) image:
+
+```bash
+ROOT_IMAGE=scratch make package-vmagent
+```
+
+### 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 1.15.
+2. Run `make vmagent-arm` or `make vmagent-arm64` from the root folder of [the repository](https://github.com/VictoriaMetrics/VictoriaMetrics)
+   It builds `vmagent-arm` or `vmagent-arm64` binary respectively and puts it into the `bin` folder.
+
+### Production ARM build
+
+1. [Install docker](https://docs.docker.com/install/).
+2. Run `make vmagent-arm-prod` or `make vmagent-arm64-prod` from the root folder of [the repository](https://github.com/VictoriaMetrics/VictoriaMetrics).
+   It builds `vmagent-arm-prod` or `vmagent-arm64-prod` binary respectively and puts it into the `bin` folder.
+
+
+## Profiling
 
 `vmagent` provides handlers for collecting the following [Go profiles](https://blog.golang.org/profiling-go-programs):
 
-* Memory profile. It can be collected with the following command:
+* Memory profile can be collected with the following command:
 
 ```bash
 curl -s http://<vmagent-host>:8429/debug/pprof/heap > mem.pprof
 ```
 
-* CPU profile. It can be collected with the following command:
+* CPU profile can be collected with the following command:
 
 ```bash
 curl -s http://<vmagent-host>:8429/debug/pprof/profile > cpu.pprof
@@ -261,3 +474,240 @@ curl -s http://<vmagent-host>:8429/debug/pprof/profile > cpu.pprof
 The command for collecting CPU profile waits for 30 seconds before returning.
 
 The collected profiles may be analyzed with [go tool pprof](https://github.com/google/pprof).
+
+
+## Advanced usage
+
+`vmagent` can be fine-tuned with various command-line flags. Run `./vmagent -help` in order to see the full list of these flags with their desciptions and default values:
+
+```
+./vmagent -help
+
+vmagent collects metrics data via popular data ingestion protocols and routes them to VictoriaMetrics.
+
+See the docs at https://victoriametrics.github.io/vmagent.html .
+
+  -csvTrimTimestamp duration
+    	Trim timestamps when importing csv data to this duration. Minimum practical duration is 1ms. Higher duration (i.e. 1s) may be used for reducing disk space usage for timestamp data (default 1ms)
+  -dryRun
+    	Whether to check only config files without running vmagent. The following files are checked: -promscrape.config, -remoteWrite.relabelConfig, -remoteWrite.urlRelabelConfig . Unknown config entries are allowed in -promscrape.config by default. This can be changed with -promscrape.config.strictParse
+  -enableTCP6
+    	Whether to enable IPv6 for listening and dialing. By default only IPv4 TCP and UDP is used
+  -envflag.enable
+    	Whether to enable reading flags from environment variables additionally to command line. Command line flag values have priority over values from environment vars. Flags are read only from command line if this flag isn't set
+  -envflag.prefix string
+    	Prefix for environment variables if -envflag.enable is set
+  -fs.disableMmap
+    	Whether to use pread() instead of mmap() for reading data files. By default mmap() is used for 64-bit arches and pread() is used for 32-bit arches, since they cannot read data files bigger than 2^32 bytes in memory. mmap() is usually faster for reading small data chunks than pread()
+  -graphiteListenAddr string
+    	TCP and UDP address to listen for Graphite plaintext data. Usually :2003 must be set. Doesn't work if empty
+  -graphiteTrimTimestamp duration
+    	Trim timestamps for Graphite data to this duration. Minimum practical duration is 1s. Higher duration (i.e. 1m) may be used for reducing disk space usage for timestamp data (default 1s)
+  -http.connTimeout duration
+    	Incoming http connections are closed after the configured timeout. This may help spreading incoming load among a cluster of services behind load balancer. Note that the real timeout may be bigger by up to 10% as a protection from Thundering herd problem (default 2m0s)
+  -http.disableResponseCompression
+    	Disable compression of HTTP responses for saving 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)
+  -http.pathPrefix string
+    	An optional prefix to add to all the paths handled by http server. For example, if '-http.pathPrefix=/foo/bar' is set, then all the http requests will be handled on '/foo/bar/*' paths. This may be useful for proxied requests. See https://www.robustperception.io/using-external-urls-and-proxies-with-prometheus
+  -http.shutdownDelay duration
+    	Optional delay before http server shutdown. During this dealy the servier returns non-OK responses from /health page, so load balancers can route new requests to other servers
+  -httpAuth.password string
+    	Password for HTTP Basic Auth. The authentication is disabled if -httpAuth.username is empty
+  -httpAuth.username string
+    	Username for HTTP Basic Auth. The authentication is disabled if empty. See also -httpAuth.password
+  -httpListenAddr string
+    	TCP address to listen for http connections. Set this flag to empty value in order to disable listening on any port. This mode may be useful for running multiple vmagent instances on the same server. Note that /targets and /metrics pages aren't available if -httpListenAddr='' (default ":8429")
+  -import.maxLineLen size
+    	The maximum length in bytes of a single line accepted by /api/v1/import; the line length can be limited with 'max_rows_per_line' query arg passed to /api/v1/export
+    	Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 104857600)
+  -influx.databaseNames array
+    	Comma-separated list of database names to return from /query and /influx/query API. This can be needed for accepting data from Telegraf plugins such as https://github.com/fangli/fluent-plugin-influxdb
+    	Supports array of values separated by comma or specified via multiple flags.
+  -influx.maxLineSize size
+    	The maximum size in bytes for a single Influx line during parsing
+    	Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 262144)
+  -influxListenAddr string
+    	TCP and UDP address to listen for Influx line protocol data. Usually :8189 must be set. Doesn't work if empty. This flag isn't needed when ingesting data over HTTP - just send it to http://<vmagent>:8429/write
+  -influxMeasurementFieldSeparator string
+    	Separator for '{measurement}{separator}{field_name}' metric name when inserted via Influx line protocol (default "_")
+  -influxSkipMeasurement
+    	Uses '{field_name}' as a metric name while ignoring '{measurement}' and '-influxMeasurementFieldSeparator'
+  -influxSkipSingleField
+    	Uses '{measurement}' instead of '{measurement}{separator}{field_name}' for metic name if Influx line contains only a single field
+  -influxTrimTimestamp duration
+    	Trim timestamps for Influx line protocol data to this duration. Minimum practical duration is 1ms. Higher duration (i.e. 1s) may be used for reducing disk space usage for timestamp data (default 1ms)
+  -insert.maxQueueDuration duration
+    	The maximum duration for waiting in the queue for insert requests due to -maxConcurrentInserts (default 1m0s)
+  -loggerDisableTimestamps
+    	Whether to disable writing timestamps in logs
+  -loggerErrorsPerSecondLimit int
+    	Per-second limit on the number of ERROR messages. If more than the given number of errors are emitted per second, then the remaining errors are suppressed. Zero value disables 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 value disables the rate limit
+  -maxConcurrentInserts int
+    	The maximum number of concurrent inserts. Default value should work for most cases, since it minimizes the overhead for concurrent inserts. This option is tigthly coupled with -insert.maxQueueDuration (default 16)
+  -maxInsertRequestSize size
+    	The maximum size in bytes of a single Prometheus remote_write API request
+    	Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 33554432)
+  -memory.allowedBytes size
+    	Allowed size of system memory VictoriaMetrics caches may occupy. This option overrides -memory.allowedPercent if set to non-zero value. Too low value may increase cache miss rate, which usually results in higher CPU and disk IO usage. Too high value may evict too much data from OS page cache, which will result in higher disk IO usage
+    	Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 0)
+  -memory.allowedPercent float
+    	Allowed percent of system memory VictoriaMetrics caches may occupy. See also -memory.allowedBytes. Too low value may increase cache miss rate, which usually results in higher CPU and disk IO usage. Too high value may evict too much data from OS page cache, which will result in higher disk IO usage (default 60)
+  -metricsAuthKey string
+    	Auth key for /metrics. It overrides httpAuth settings
+  -opentsdbHTTPListenAddr string
+    	TCP address to listen for OpentTSDB HTTP put requests. Usually :4242 must be set. Doesn't work if empty
+  -opentsdbListenAddr string
+    	TCP and UDP address to listen for OpentTSDB metrics. Telnet put messages and HTTP /api/put messages are simultaneously served on TCP port. Usually :4242 must be set. Doesn't work if empty
+  -opentsdbTrimTimestamp duration
+    	Trim timestamps for OpenTSDB 'telnet put' data to this duration. Minimum practical duration is 1s. Higher duration (i.e. 1m) may be used for reducing disk space usage for timestamp data (default 1s)
+  -opentsdbhttp.maxInsertRequestSize size
+    	The maximum size of OpenTSDB HTTP put request
+    	Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 33554432)
+  -opentsdbhttpTrimTimestamp duration
+    	Trim timestamps for OpenTSDB HTTP data to this duration. Minimum practical duration is 1ms. Higher duration (i.e. 1s) may be used for reducing disk space usage for timestamp data (default 1ms)
+  -pprofAuthKey string
+    	Auth key for /debug/pprof. It overrides httpAuth settings
+  -promscrape.cluster.memberNum int
+    	The number of number in the cluster of scrapers. It must be an unique value in the range 0 ... promscrape.cluster.membersCount-1 across scrapers in the cluster
+  -promscrape.cluster.membersCount int
+    	The number of members in a cluster of scrapers. Each member must have an unique -promscrape.cluster.memberNum in the range 0 ... promscrape.cluster.membersCount-1 . Each member then scrapes roughly 1/N of all the targets. By default cluster scraping is disabled, i.e. a single scraper scrapes all the targets
+  -promscrape.cluster.replicationFactor int
+    	The number of members in the cluster, which scrape the same targets. If the replication factor is greater than 2, then the deduplication must be enabled at remote storage side. See https://victoriametrics.github.io/#deduplication (default 1)
+  -promscrape.config string
+    	Optional path to Prometheus config file with 'scrape_configs' section containing targets to scrape. See https://victoriametrics.github.io/#how-to-scrape-prometheus-exporters-such-as-node-exporter for details
+  -promscrape.config.dryRun
+    	Checks -promscrape.config file for errors and unsupported fields and then exits. Returns non-zero exit code on parsing errors and emits these errors to stderr. See also -promscrape.config.strictParse command-line flag. Pass -loggerLevel=ERROR if you don't need to see info messages in the output.
+  -promscrape.config.strictParse
+    	Whether to allow only supported fields in -promscrape.config . By default unsupported fields are silently skipped
+  -promscrape.configCheckInterval duration
+    	Interval for checking for changes in '-promscrape.config' file. By default the checking is disabled. Send SIGHUP signal in order to force config check for changes
+  -promscrape.consul.waitTime duration
+    	Wait time used by Consul service discovery. Default value is used if not set
+  -promscrape.consulSDCheckInterval duration
+    	Interval for checking for changes in Consul. This works only if consul_sd_configs is configured in '-promscrape.config' file. See https://prometheus.io/docs/prometheus/latest/configuration/configuration/#consul_sd_config for details (default 30s)
+  -promscrape.disableCompression
+    	Whether to disable sending 'Accept-Encoding: gzip' request headers to all the scrape targets. This may reduce CPU usage on scrape targets at the cost of higher network bandwidth utilization. It is possible to set 'disable_compression: true' individually per each 'scrape_config' section in '-promscrape.config' for fine grained control
+  -promscrape.disableKeepAlive
+    	Whether to disable HTTP keep-alive connections when scraping all the targets. This may be useful when targets has no support for HTTP keep-alive connection. It is possible to set 'disable_keepalive: true' individually per each 'scrape_config' section in '-promscrape.config' for fine grained control. Note that disabling HTTP keep-alive may increase load on both vmagent and scrape targets
+  -promscrape.discovery.concurrency int
+    	The maximum number of concurrent requests to Prometheus autodiscovery API (Consul, Kubernetes, etc.) (default 100)
+  -promscrape.discovery.concurrentWaitTime duration
+    	The maximum duration for waiting to perform API requests if more than -promscrape.discovery.concurrency requests are simultaneously performed (default 1m0s)
+  -promscrape.dnsSDCheckInterval duration
+    	Interval for checking for changes in dns. This works only if dns_sd_configs is configured in '-promscrape.config' file. See https://prometheus.io/docs/prometheus/latest/configuration/configuration/#dns_sd_config for details (default 30s)
+  -promscrape.dockerswarmSDCheckInterval duration
+    	Interval for checking for changes in dockerswarm. This works only if dockerswarm_sd_configs is configured in '-promscrape.config' file. See https://prometheus.io/docs/prometheus/latest/configuration/configuration/#dockerswarm_sd_config for details (default 30s)
+  -promscrape.dropOriginalLabels
+    	Whether to drop original labels for scrape targets at /targets and /api/v1/targets pages. This may be needed for reducing memory usage when original labels for big number of scrape targets occupy big amounts of memory. Note that this reduces debuggability for improper per-target relabeling configs
+  -promscrape.ec2SDCheckInterval duration
+    	Interval for checking for changes in ec2. This works only if ec2_sd_configs is configured in '-promscrape.config' file. See https://prometheus.io/docs/prometheus/latest/configuration/configuration/#ec2_sd_config for details (default 1m0s)
+  -promscrape.eurekaSDCheckInterval duration
+    	Interval for checking for changes in eureka. This works only if eureka_sd_configs is configured in '-promscrape.config' file. See https://prometheus.io/docs/prometheus/latest/configuration/configuration/#eureka_sd_config for details (default 30s)
+  -promscrape.fileSDCheckInterval duration
+    	Interval for checking for changes in 'file_sd_config'. See https://prometheus.io/docs/prometheus/latest/configuration/configuration/#file_sd_config for details (default 30s)
+  -promscrape.gceSDCheckInterval duration
+    	Interval for checking for changes in gce. This works only if gce_sd_configs is configured in '-promscrape.config' file. See https://prometheus.io/docs/prometheus/latest/configuration/configuration/#gce_sd_config for details (default 1m0s)
+  -promscrape.kubernetes.apiServerTimeout duration
+    	How frequently to reload the full state from Kuberntes API server (default 30m0s)
+  -promscrape.kubernetesSDCheckInterval duration
+    	Interval for checking for changes in Kubernetes API server. This works only if kubernetes_sd_configs is configured in '-promscrape.config' file. See https://prometheus.io/docs/prometheus/latest/configuration/configuration/#kubernetes_sd_config for details (default 30s)
+  -promscrape.maxDroppedTargets int
+    	The maximum number of droppedTargets to show at /api/v1/targets page. Increase this value if your setup drops more scrape targets during relabeling and you need investigating labels for all the dropped targets. Note that the increased number of tracked dropped targets may result in increased memory usage (default 1000)
+  -promscrape.maxScrapeSize size
+    	The maximum size of scrape response in bytes to process from Prometheus targets. Bigger responses are rejected
+    	Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 16777216)
+  -promscrape.openstackSDCheckInterval duration
+    	Interval for checking for changes in openstack API server. This works only if openstack_sd_configs is configured in '-promscrape.config' file. See https://prometheus.io/docs/prometheus/latest/configuration/configuration/#openstack_sd_config for details (default 30s)
+  -promscrape.streamParse
+    	Whether to enable stream parsing for metrics obtained from scrape targets. This may be useful for reducing memory usage when millions of metrics are exposed per each scrape target. It is posible to set 'stream_parse: true' individually per each 'scrape_config' section in '-promscrape.config' for fine grained control
+  -promscrape.suppressDuplicateScrapeTargetErrors
+    	Whether to suppress 'duplicate scrape target' errors; see https://victoriametrics.github.io/vmagent.html#troubleshooting for details
+  -promscrape.suppressScrapeErrors
+    	Whether to suppress scrape errors logging. The last error for each target is always available at '/targets' page even if scrape errors logging is suppressed
+  -remoteWrite.basicAuth.password array
+    	Optional basic auth password to use for -remoteWrite.url. If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url
+    	Supports array of values separated by comma or specified via multiple flags.
+  -remoteWrite.basicAuth.username array
+    	Optional basic auth username to use for -remoteWrite.url. If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url
+    	Supports array of values separated by comma or specified via multiple flags.
+  -remoteWrite.bearerToken array
+    	Optional bearer auth token to use for -remoteWrite.url. If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url
+    	Supports array of values separated by comma or specified via multiple flags.
+  -remoteWrite.flushInterval duration
+    	Interval for flushing the data to remote storage. This option takes effect only when less than 10K data points per second are pushed to -remoteWrite.url (default 1s)
+  -remoteWrite.label array
+    	Optional label in the form 'name=value' to add to all the metrics before sending them to -remoteWrite.url. Pass multiple -remoteWrite.label flags in order to add multiple labels to metrics before sending them to remote storage
+    	Supports array of values separated by comma or specified via multiple flags.
+  -remoteWrite.maxBlockSize size
+    	The maximum size in bytes of unpacked request to send to remote storage. It shouldn't exceed -maxInsertRequestSize from VictoriaMetrics
+    	Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 8388608)
+  -remoteWrite.maxDiskUsagePerURL size
+    	The maximum file-based buffer size in bytes at -remoteWrite.tmpDataPath for each -remoteWrite.url. When buffer size reaches the configured maximum, then old data is dropped when adding new data to the buffer. Buffered data is stored in ~500MB chunks, so the minimum practical value for this flag is 500000000. Disk usage is unlimited if the value is set to 0
+    	Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 0)
+  -remoteWrite.proxyURL array
+    	Optional proxy URL for writing data to -remoteWrite.url. Supported proxies: http, https, socks5. Example: -remoteWrite.proxyURL=socks5://proxy:1234
+    	Supports array of values separated by comma or specified via multiple flags.
+  -remoteWrite.queues int
+    	The number of concurrent queues to each -remoteWrite.url. Set more queues if default number of queues isn't enough for sending high volume of collected data to remote storage (default 4)
+  -remoteWrite.rateLimit array
+    	Optional rate limit in bytes per second for data sent to -remoteWrite.url. By default the rate limit is disabled. It can be useful for limiting load on remote storage when big amounts of buffered data is sent after temporary unavailability of the remote storage
+    	Supports array of values separated by comma or specified via multiple flags.
+  -remoteWrite.relabelConfig string
+    	Optional path to file with relabel_config entries. These entries are applied to all the metrics before sending them to -remoteWrite.url. See https://victoriametrics.github.io/vmagent.html#relabeling for details
+  -remoteWrite.roundDigits array
+    	Round metric values to this number of decimal digits after the point before writing them to remote storage. Examples: -remoteWrite.roundDigits=2 would round 1.236 to 1.24, while -remoteWrite.roundDigits=-1 would round 126.78 to 130. By default digits rounding is disabled. Set it to 100 for disabling it for a particular remote storage. This option may be used for improving data compression for the stored metrics
+    	Supports array of values separated by comma or specified via multiple flags.
+  -remoteWrite.sendTimeout array
+    	Timeout for sending a single block of data to -remoteWrite.url
+    	Supports array of values separated by comma or specified via multiple flags.
+  -remoteWrite.showURL
+    	Whether to show -remoteWrite.url in the exported metrics. It is hidden by default, since it can contain sensitive info such as auth key
+  -remoteWrite.significantFigures array
+    	The number of significant figures to leave in metric values before writing them to remote storage. See https://en.wikipedia.org/wiki/Significant_figures . Zero value saves all the significant figures. This option may be used for improving data compression for the stored metrics. See also -remoteWrite.roundDigits
+    	Supports array of values separated by comma or specified via multiple flags.
+  -remoteWrite.tlsCAFile array
+    	Optional path to TLS CA file to use for verifying connections to -remoteWrite.url. By default system CA is used. If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url
+    	Supports array of values separated by comma or specified via multiple flags.
+  -remoteWrite.tlsCertFile array
+    	Optional path to client-side TLS certificate file to use when connecting to -remoteWrite.url. If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url
+    	Supports array of values separated by comma or specified via multiple flags.
+  -remoteWrite.tlsInsecureSkipVerify array
+    	Whether to skip tls verification when connecting to -remoteWrite.url
+    	Supports array of values separated by comma or specified via multiple flags.
+  -remoteWrite.tlsKeyFile array
+    	Optional path to client-side TLS certificate key to use when connecting to -remoteWrite.url. If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url
+    	Supports array of values separated by comma or specified via multiple flags.
+  -remoteWrite.tlsServerName array
+    	Optional TLS server name to use for connections to -remoteWrite.url. By default the server name from -remoteWrite.url is used. If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url
+    	Supports array of values separated by comma or specified via multiple flags.
+  -remoteWrite.tmpDataPath string
+    	Path to directory where temporary data for remote write component is stored. See also -remoteWrite.maxDiskUsagePerURL (default "vmagent-remotewrite-data")
+  -remoteWrite.url array
+    	Remote storage URL to write data to. It must support Prometheus remote_write API. It is recommended using VictoriaMetrics as remote storage. Example url: http://<victoriametrics-host>:8428/api/v1/write . Pass multiple -remoteWrite.url flags in order to write data concurrently to multiple remote storage systems
+    	Supports array of values separated by comma or specified via multiple flags.
+  -remoteWrite.urlRelabelConfig array
+    	Optional path to relabel config for the corresponding -remoteWrite.url
+    	Supports array of values separated by comma or specified via multiple flags.
+  -tls
+    	Whether to enable TLS (aka HTTPS) for incoming requests. -tlsCertFile and -tlsKeyFile must be set if -tls is set
+  -tlsCertFile string
+    	Path to file with TLS certificate. Used only if -tls is set. Prefer ECDSA certs instead of RSA certs, since RSA certs are slow
+  -tlsKeyFile string
+    	Path to file with TLS key. Used only if -tls is set
+  -version
+    	Show VictoriaMetrics version
+```

app/vmagent/common/push_ctx.go

@@ -1,10 +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

@@ -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/csvimport"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
 	"github.com/VictoriaMetrics/metrics"
@@ -18,12 +19,18 @@ var (
 
 // InsertHandler processes csv data from req.
 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)
 
@@ -44,6 +51,7 @@ 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/influx/request_handler.go

@@ -4,13 +4,15 @@ import (
 	"flag"
 	"io"
 	"net/http"
-	"runtime"
 	"sync"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/common"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/cgroup"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
+	parserCommon "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
 	parser "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/influx"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
 	"github.com/VictoriaMetrics/metrics"
@@ -19,6 +21,7 @@ import (
 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")
+	skipMeasurement           = flag.Bool("influxSkipMeasurement", false, "Uses '{field_name}' as a metric name while ignoring '{measurement}' and '-influxMeasurementFieldSeparator'")
 )
 
 var (
@@ -31,7 +34,9 @@ var (
 // See https://github.com/influxdata/telegraf/tree/master/plugins/inputs/socket_listener/
 func InsertHandlerForReader(r io.Reader) error {
 	return writeconcurrencylimiter.Do(func() error {
-		return parser.ParseStream(r, false, "", "", insertRows)
+		return parser.ParseStream(r, false, "", "", func(db string, rows []parser.Row) error {
+			return insertRows(db, rows, nil)
+		})
 	})
 }
 
@@ -39,17 +44,23 @@ func InsertHandlerForReader(r io.Reader) error {
 //
 // See https://github.com/influxdata/influxdb/blob/4cbdc197b8117fee648d62e2e5be75c6575352f0/tsdb/README.md
 func InsertHandlerForHTTP(req *http.Request) error {
+	extraLabels, err := parserCommon.GetExtraLabels(req)
+	if err != nil {
+		return err
+	}
 	return writeconcurrencylimiter.Do(func() error {
 		isGzipped := req.Header.Get("Content-Encoding") == "gzip"
 		q := req.URL.Query()
 		precision := q.Get("precision")
 		// Read db tag from https://docs.influxdata.com/influxdb/v1.7/tools/api/#write-http-endpoint
 		db := q.Get("db")
-		return parser.ParseStream(req.Body, isGzipped, precision, db, insertRows)
+		return parser.ParseStream(req.Body, isGzipped, precision, db, func(db string, rows []parser.Row) error {
+			return insertRows(db, rows, extraLabels)
+		})
 	})
 }
 
-func insertRows(db string, rows []parser.Row) error {
+func insertRows(db string, rows []parser.Row, extraLabels []prompbmarshal.Label) error {
 	ctx := getPushCtx()
 	defer putPushCtx(ctx)
 
@@ -61,26 +72,32 @@ 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
+				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",
 				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...)
 		}
@@ -107,7 +124,6 @@ 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
@@ -131,12 +147,8 @@ 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 +176,4 @@ func putPushCtx(ctx *pushCtx) {
 }
 
 var pushCtxPool sync.Pool
-var pushCtxPoolCh = make(chan *pushCtx, runtime.GOMAXPROCS(-1))
+var pushCtxPoolCh = make(chan *pushCtx, cgroup.AvailableCPUs())

app/vmagent/main.go

@@ -6,19 +6,24 @@ import (
 	"net/http"
 	"os"
 	"strings"
+	"sync/atomic"
 	"time"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/csvimport"
 	"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/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"
@@ -26,6 +31,7 @@ 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"
 )
@@ -34,14 +40,16 @@ 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 Influx line protocol data. Usually :8189 must be set. Doesn't work if empty. "+
+		"This flag isn't needed when ingesting data over HTTP - just send it to http://<vmagent>:8429/write")
 	graphiteListenAddr = flag.String("graphiteListenAddr", "", "TCP and UDP address to listen for Graphite plaintext data. Usually :2003 must be set. Doesn't work if empty")
 	opentsdbListenAddr = flag.String("opentsdbListenAddr", "", "TCP and UDP address to listen for OpentTSDB metrics. "+
 		"Telnet put messages and HTTP /api/put messages are simultaneously served on TCP port. "+
 		"Usually :4242 must be set. Doesn't work if empty")
 	opentsdbHTTPListenAddr = flag.String("opentsdbHTTPListenAddr", "", "TCP address to listen for OpentTSDB HTTP put requests. Usually :4242 must be set. Doesn't work if empty")
 	dryRun                 = flag.Bool("dryRun", false, "Whether to check only config files without running vmagent. The following files are checked: "+
-		"-promscrape.config, -remoteWrite.relabelConfig, -remoteWrite.urlRelabelConfig . See also -promscrape.config.dryRun")
+		"-promscrape.config, -remoteWrite.relabelConfig, -remoteWrite.urlRelabelConfig . "+
+		"Unknown config entries are allowed in -promscrape.config by default. This can be changed with -promscrape.config.strictParse")
 )
 
 var (
@@ -54,19 +62,25 @@ 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 *dryRun {
-		if err := flag.Set("promscrape.config.strictParse", "true"); err != nil {
-			logger.Panicf("BUG: cannot set promscrape.config.strictParse=true: %s", err)
+	if promscrape.IsDryRun() {
+		if err := promscrape.CheckConfig(); err != nil {
+			logger.Fatalf("error when checking -promscrape.config: %s", err)
 		}
+		logger.Infof("-promscrape.config is ok; exitting with 0 status code")
+		return
+	}
+	if *dryRun {
 		if err := remotewrite.CheckRelabelConfigs(); err != nil {
 			logger.Fatalf("error when checking relabel configs: %s", err)
 		}
 		if err := promscrape.CheckConfig(); err != nil {
-			logger.Fatalf("error when checking Prometheus config: %s", err)
+			logger.Fatalf("error when checking -promscrape.config: %s", err)
 		}
 		logger.Infof("all the configs are ok; exitting with 0 status code")
 		return
@@ -75,6 +89,7 @@ func main() {
 	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)
@@ -122,19 +137,24 @@ 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 == "/" {
+		fmt.Fprintf(w, "vmagent - see docs at https://victoriametrics.github.io/vmagent.html")
+		return true
+	}
 	path := strings.Replace(r.URL.Path, "//", "/", -1)
 	switch path {
 	case "/api/v1/write":
 		prometheusWriteRequests.Inc()
 		if err := promremotewrite.InsertHandler(r); err != nil {
 			prometheusWriteErrors.Inc()
-			httpserver.Errorf(w, "error in %q: %s", r.URL.Path, err)
+			httpserver.Errorf(w, r, "error in %q: %s", r.URL.Path, err)
 			return true
 		}
 		w.WriteHeader(http.StatusNoContent)
@@ -143,7 +163,7 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 		vmimportRequests.Inc()
 		if err := vmimport.InsertHandler(r); err != nil {
 			vmimportErrors.Inc()
-			httpserver.Errorf(w, "error in %q: %s", r.URL.Path, err)
+			httpserver.Errorf(w, r, "error in %q: %s", r.URL.Path, err)
 			return true
 		}
 		w.WriteHeader(http.StatusNoContent)
@@ -152,7 +172,25 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 		csvimportRequests.Inc()
 		if err := csvimport.InsertHandler(r); err != nil {
 			csvimportErrors.Inc()
-			httpserver.Errorf(w, "error in %q: %s", r.URL.Path, err)
+			httpserver.Errorf(w, r, "error in %q: %s", r.URL.Path, err)
+			return true
+		}
+		w.WriteHeader(http.StatusNoContent)
+		return true
+	case "/api/v1/import/prometheus":
+		prometheusimportRequests.Inc()
+		if err := prometheusimport.InsertHandler(r); err != nil {
+			prometheusimportErrors.Inc()
+			httpserver.Errorf(w, r, "error in %q: %s", r.URL.Path, err)
+			return true
+		}
+		w.WriteHeader(http.StatusNoContent)
+		return true
+	case "/api/v1/import/native":
+		nativeimportRequests.Inc()
+		if err := native.InsertHandler(r); err != nil {
+			nativeimportErrors.Inc()
+			httpserver.Errorf(w, r, "error in %q: %s", r.URL.Path, err)
 			return true
 		}
 		w.WriteHeader(http.StatusNoContent)
@@ -161,27 +199,40 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 		influxWriteRequests.Inc()
 		if err := influx.InsertHandlerForHTTP(r); err != nil {
 			influxWriteErrors.Inc()
-			httpserver.Errorf(w, "error in %q: %s", r.URL.Path, err)
+			httpserver.Errorf(w, r, "error in %q: %s", r.URL.Path, err)
 			return true
 		}
 		w.WriteHeader(http.StatusNoContent)
 		return true
 	case "/query":
-		// Emulate fake response for influx query.
-		// This is required for TSBS benchmark.
 		influxQueryRequests.Inc()
-		fmt.Fprintf(w, `{"results":[{"series":[{"values":[]}]}]}`)
+		influxutils.WriteDatabaseNames(w)
 		return true
 	case "/targets":
 		promscrapeTargetsRequests.Inc()
-		w.Header().Set("Content-Type", "text/plain")
-		promscrape.WriteHumanReadableTargetsStatus(w)
+		promscrape.WriteHumanReadableTargetsStatus(w, r)
+		return true
+	case "/api/v1/targets":
+		promscrapeAPIV1TargetsRequests.Inc()
+		w.Header().Set("Content-Type", "application/json; charset=utf-8")
+		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
 	}
 	return false
 }
@@ -196,12 +247,28 @@ 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"}`)
 
+	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"}`)
+
+	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"}`)
+
 	influxWriteRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/write", protocol="influx"}`)
 	influxWriteErrors   = metrics.NewCounter(`vmagent_http_request_errors_total{path="/write", protocol="influx"}`)
 
 	influxQueryRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/query", protocol="influx"}`)
 
-	promscrapeTargetsRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/targets"}`)
+	promscrapeTargetsRequests      = metrics.NewCounter(`vmagent_http_requests_total{path="/targets"}`)
+	promscrapeAPIV1TargetsRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/api/v1/targets"}`)
 
 	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://victoriametrics.github.io/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 +1,85 @@
+package native
+
+import (
+	"net/http"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/common"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/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/writeconcurrencylimiter"
+	"github.com/VictoriaMetrics/metrics"
+)
+
+var (
+	rowsInserted  = metrics.NewCounter(`vmagent_rows_inserted_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(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(block, extraLabels)
+		})
+	})
+}
+
+func insertRows(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)
+	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.Push(&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 +1,76 @@
+package prometheusimport
+
+import (
+	"net/http"
+
+	"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/prometheus"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
+	"github.com/VictoriaMetrics/metrics"
+)
+
+var (
+	rowsInserted  = metrics.NewCounter(`vmagent_rows_inserted_total{type="prometheus"}`)
+	rowsPerInsert = metrics.NewHistogram(`vmagent_rows_per_insert{type="prometheus"}`)
+)
+
+// InsertHandler processes `/api/v1/import/prometheus` request.
+func InsertHandler(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(rows, extraLabels)
+		}, nil)
+	})
+}
+
+func insertRows(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.Push(&ctx.WriteRequest)
+	rowsInserted.Add(len(rows))
+	rowsPerInsert.Update(float64(len(rows)))
+	return nil
+}

app/vmagent/promremotewrite/request_handler.go

@@ -8,6 +8,7 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
+	parserCommon "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
 	parser "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/promremotewrite"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
 	"github.com/VictoriaMetrics/metrics"
@@ -20,12 +21,18 @@ var (
 
 // InsertHandler processes remote write for prometheus.
 func InsertHandler(req *http.Request) error {
+	extraLabels, err := parserCommon.GetExtraLabels(req)
+	if err != nil {
+		return err
+	}
 	return writeconcurrencylimiter.Do(func() error {
-		return parser.ParseStream(req, insertRows)
+		return parser.ParseStream(req, func(tss []prompb.TimeSeries) error {
+			return insertRows(tss, extraLabels)
+		})
 	})
 }
 
-func insertRows(timeseries []prompb.TimeSeries) error {
+func insertRows(timeseries []prompb.TimeSeries, extraLabels []prompbmarshal.Label) error {
 	ctx := common.GetPushCtx()
 	defer common.PutPushCtx(ctx)
 
@@ -35,6 +42,7 @@ 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 +51,7 @@ func insertRows(timeseries []prompb.TimeSeries) error {
 				Value: bytesutil.ToUnsafeString(label.Value),
 			})
 		}
+		labels = append(labels, extraLabels...)
 		samplesLen := len(samples)
 		for i := range ts.Samples {
 			sample := &ts.Samples[i]
@@ -55,7 +64,6 @@ func insertRows(timeseries []prompb.TimeSeries) error {
 			Labels:  labels[labelsLen:],
 			Samples: samples[samplesLen:],
 		})
-		rowsTotal += len(ts.Samples)
 	}
 	ctx.WriteRequest.Timeseries = tssDst
 	ctx.Labels = labels

app/vmagent/remotewrite/client.go

@@ -1,10 +1,13 @@
 package remotewrite
 
 import (
+	"bytes"
 	"crypto/tls"
 	"encoding/base64"
-	"flag"
 	"fmt"
+	"io/ioutil"
+	"net/http"
+	"net/url"
 	"strings"
 	"sync"
 	"time"
@@ -13,14 +16,19 @@ 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. "+
@@ -39,24 +47,51 @@ var (
 )
 
 type client struct {
-	urlLabelValue  string
+	sanitizedURL   string
 	remoteWriteURL string
-	host           string
-	requestURI     string
 	authHeader     string
 	fq             *persistentqueue.FastQueue
-	hc             *fasthttp.HostClient
+	hc             *http.Client
 
+	rl rateLimiter
+
+	bytesSent       *metrics.Counter
+	blocksSent      *metrics.Counter
 	requestDuration *metrics.Histogram
 	requestsOKCount *metrics.Counter
 	errorsCount     *metrics.Counter
+	packetsDropped  *metrics.Counter
 	retriesCount    *metrics.Counter
 
 	wg     sync.WaitGroup
 	stopCh chan struct{}
 }
 
-func newClient(argIdx int, remoteWriteURL, urlLabelValue string, fq *persistentqueue.FastQueue, concurrency int) *client {
+func newClient(argIdx int, remoteWriteURL, sanitizedURL string, fq *persistentqueue.FastQueue, concurrency int) *client {
+	tlsCfg, err := getTLSConfig(argIdx)
+	if err != nil {
+		logger.Panicf("FATAL: cannot initialize TLS config: %s", err)
+	}
+	tr := &http.Transport{
+		Dial:                statDial,
+		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)
+		}
+		urlProxy, err := url.Parse(pURL)
+		if err != nil {
+			logger.Fatalf("cannot parse -remoteWrite.proxyURL=%q: %s", pURL, err)
+		}
+		tr.Proxy = http.ProxyURL(urlProxy)
+	}
 	authHeader := ""
 	username := basicAuthUsername.GetOptionalArg(argIdx)
 	password := basicAuthPassword.GetOptionalArg(argIdx)
@@ -69,72 +104,34 @@ func newClient(argIdx int, remoteWriteURL, urlLabelValue string, fq *persistentq
 	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)
+			logger.Fatalf("`-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",
-		Dial:                statDial,
-		IsTLS:               isTLS,
-		TLSConfig:           tlsCfg,
-		MaxConns:            maxConns,
-		MaxIdleConnDuration: 10 * readTimeout,
-		ReadTimeout:         readTimeout,
-		WriteTimeout:        writeTimeout,
-		MaxResponseBodySize: 1024 * 1024,
-	}
 	c := &client{
-		urlLabelValue:  urlLabelValue,
+		sanitizedURL:   sanitizedURL,
 		remoteWriteURL: remoteWriteURL,
-		host:           host,
-		requestURI:     requestURI,
 		authHeader:     authHeader,
 		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))
+	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))
 	for i := 0; i < concurrency; i++ {
 		c.wg.Add(1)
 		go func() {
@@ -142,27 +139,30 @@ func newClient(argIdx int, remoteWriteURL, urlLabelValue string, fq *persistentq
 			c.runWorker()
 		}()
 	}
-	logger.Infof("initialized client for -remoteWrite.url=%q", c.remoteWriteURL)
+	logger.Infof("initialized client for -remoteWrite.url=%q", c.sanitizedURL)
 	return c
 }
 
 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{
+	c := &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)
+	if c.CAFile == "" && c.CertFile == "" && c.KeyFile == "" && c.ServerName == "" && !c.InsecureSkipVerify {
+		return nil, nil
+	}
+	cfg, err := promauth.NewConfig(".", nil, "", "", c)
 	if err != nil {
-		return nil, fmt.Errorf("cannot populate TLS config: %s", err)
+		return nil, fmt.Errorf("cannot populate TLS config: %w", err)
 	}
 	tlsCfg := cfg.NewTLSConfig()
 	return tlsCfg, nil
@@ -171,62 +171,67 @@ func getTLSConfig(argIdx int) (*tls.Config, error) {
 func (c *client) runWorker() {
 	var ok bool
 	var block []byte
-	ch := make(chan struct{})
+	ch := make(chan bool, 1)
 	for {
 		block, ok = c.fq.MustReadBlock(block[:0])
 		if !ok {
 			return
 		}
 		go func() {
-			c.sendBlock(block)
-			ch <- struct{}{}
+			ch <- c.sendBlock(block)
 		}()
 		select {
-		case <-ch:
-			// The block has been sent successfully
-			continue
+		case ok := <-ch:
+			if ok {
+				// The block has been sent successfully
+				continue
+			}
+			// Return unsent block to the queue.
+			c.fq.MustWriteBlock(block)
+			return
 		case <-c.stopCh:
 			// c must be stopped. Wait for a while in the hope the block will be sent.
 			graceDuration := 5 * time.Second
 			select {
-			case <-ch:
-				// The block has been sent successfully.
+			case ok := <-ch:
+				if !ok {
+					// Return unsent block to the queue.
+					c.fq.MustWriteBlock(block)
+				}
 			case <-time.After(graceDuration):
-				logger.Errorf("couldn't sent block with size %d bytes to %q in %.3f seconds during shutdown; dropping it",
-					len(block), c.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")
+// sendBlock returns false only if c.stopCh is closed.
+// Otherwise it tries sending the block to remote storage indefinitely.
+func (c *client) sendBlock(block []byte) bool {
+	c.rl.register(len(block), c.stopCh)
+	retryDuration := time.Second
+	retriesCount := 0
+	c.bytesSent.Add(len(block))
+	c.blocksSent.Inc()
+
+again:
+	req, err := http.NewRequest("POST", c.remoteWriteURL, bytes.NewBuffer(block))
+	if err != nil {
+		logger.Panicf("BUG: unexected 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 c.authHeader != "" {
 		req.Header.Set("Authorization", c.authHeader)
 	}
-	req.SetBody(block)
-
-	retryDuration := time.Second
-	resp := fasthttp.AcquireResponse()
-
-again:
-	select {
-	case <-c.stopCh:
-		fasthttp.ReleaseRequest(req)
-		fasthttp.ReleaseResponse(resp)
-		return
-	default:
-	}
 
 	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()
@@ -235,40 +240,100 @@ again:
 			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
+			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 {
+		// Just drop block on 409 status code like Prometheus does.
+		// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/873
+		// drop block on 400 status code,
+		// not expected that remote server will be able to handle it on retry
+		// should fix 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

@@ -3,21 +3,24 @@ package remotewrite
 import (
 	"flag"
 	"sync"
+	"sync/atomic"
 	"time"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/decimal"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/fasttime"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/persistentqueue"
 	"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. "+
-		"Minimum supported interval is 1 second")
-	maxUnpackedBlockSize = flag.Int("remoteWrite.maxBlockSize", 32*1024*1024, "The maximum size in bytes of unpacked request to send to remote storage. "+
+		"This option takes effect only when less than 10K data points per second are pushed to -remoteWrite.url")
+	maxUnpackedBlockSize = flagutil.NewBytes("remoteWrite.maxBlockSize", 8*1024*1024, "The maximum size in bytes of unpacked request to send to remote storage. "+
 		"It shouldn't exceed -maxInsertRequestSize from VictoriaMetrics")
 )
 
@@ -32,9 +35,11 @@ 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() {
@@ -68,7 +73,7 @@ func (ps *pendingSeries) periodicFlusher() {
 		case <-ps.stopCh:
 			mustStop = true
 		case <-ticker.C:
-			if fasttime.UnixTimestamp()-ps.wr.lastFlushTime < uint64(flushSeconds) {
+			if fasttime.UnixTimestamp()-atomic.LoadUint64(&ps.wr.lastFlushTime) < uint64(flushSeconds) {
 				continue
 			}
 		}
@@ -79,10 +84,20 @@ func (ps *pendingSeries) periodicFlusher() {
 }
 
 type writeRequest struct {
-	wr            prompbmarshal.WriteRequest
-	pushBlock     func(block []byte)
+	// 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
 
 	labels  []prompbmarshal.Label
@@ -91,6 +106,8 @@ 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 {
@@ -100,11 +117,7 @@ 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]
@@ -113,18 +126,35 @@ func (wr *writeRequest) reset() {
 
 func (wr *writeRequest) flush() {
 	wr.wr.Timeseries = wr.tss
-	wr.lastFlushTime = fasttime.UnixTimestamp()
+	wr.adjustSampleValues()
+	atomic.StoreUint64(&wr.lastFlushTime, fasttime.UnixTimestamp())
 	pushWriteRequest(&wr.wr, wr.pushBlock)
 	wr.reset()
 }
 
+func (wr *writeRequest) adjustSampleValues() {
+	samples := wr.samples
+	if n := wr.significantFigures; n > 0 {
+		for i := range samples {
+			s := &samples[i]
+			s.Value = decimal.RoundToSignificantFigures(s.Value, n)
+		}
+	}
+	if n := wr.roundDigits; n < 100 {
+		for i := range samples {
+			s := &samples[i]
+			s.Value = decimal.RoundToDecimalDigits(s.Value, n)
+		}
+	}
+}
+
 func (wr *writeRequest) push(src []prompbmarshal.TimeSeries) {
 	tssDst := wr.tss
 	for i := range src {
 		tssDst = append(tssDst, prompbmarshal.TimeSeries{})
-		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) >= maxRowsPerBlock {
+			wr.tss = tssDst
 			wr.flush()
 			tssDst = wr.tss
 		}
@@ -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 +14,73 @@ import (
 
 var (
 	unparsedLabelsGlobal = flagutil.NewArray("remoteWrite.label", "Optional label in the form 'name=value' to add to all the metrics before sending them to -remoteWrite.url. "+
-		"Pass multiple -remoteWrite.label flags in order to add multiple flags to metrics before sending them to remote storage")
+		"Pass multiple -remoteWrite.label flags in order to add multiple labels to metrics before sending them to remote storage")
 	relabelConfigPathGlobal = flag.String("remoteWrite.relabelConfig", "", "Optional path to file with relabel_config entries. These entries are applied to all the metrics "+
-		"before sending them to -remoteWrite.url. See https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config for details")
+		"before sending them to -remoteWrite.url. See https://victoriametrics.github.io/vmagent.html#relabeling for details")
+	relabelConfigPaths = flagutil.NewArray("remoteWrite.urlRelabelConfig", "Optional path to relabel config for the corresponding -remoteWrite.url")
 )
 
 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)
+		if err != nil {
+			return nil, fmt.Errorf("cannot load -remoteWrite.relabelConfig=%q: %w", *relabelConfigPathGlobal, err)
+		}
+		rcs.global = global
+	}
+	if len(*relabelConfigPaths) > len(*remoteWriteURLs) {
+		return nil, fmt.Errorf("too many -remoteWrite.urlRelabelConfig args: %d; it mustn't exceed the number of -remoteWrite.url args: %d",
+			len(*relabelConfigPaths), len(*remoteWriteURLs))
+	}
+	rcs.perURL = make([]*promrelabel.ParsedConfigs, len(*remoteWriteURLs))
+	for i, path := range *relabelConfigPaths {
+		if len(path) == 0 {
+			// Skip empty relabel config.
+			continue
+		}
+		prc, err := promrelabel.LoadRelabelConfigs(path)
+		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 +100,7 @@ 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 +120,7 @@ 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 +3,16 @@ package remotewrite
 import (
 	"flag"
 	"fmt"
+	"sync"
 	"sync/atomic"
 
+	"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/metrics"
 	xxhash "github.com/cespare/xxhash/v2"
 )
@@ -20,35 +21,42 @@ 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 "+
+	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", 4, "The number of concurrent queues to each -remoteWrite.url. Set more queues if default number of queues "+
 		"isn't enough for sending high volume of collected data to remote storage")
 	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")
 )
 
-// CheckRelabelConfigs checks -remoteWrite.relabelConfig and -remoteWrite.urlRelabelConfig.
-func CheckRelabelConfigs() error {
-	if *relabelConfigPathGlobal != "" {
-		if _, err := promrelabel.LoadRelabelConfigs(*relabelConfigPathGlobal); err != nil {
-			return fmt.Errorf("cannot load -remoteWrite.relabelConfig=%q: %s", *relabelConfigPathGlobal, err)
-		}
-	}
-	for _, path := range *relabelConfigPaths {
-		if _, err := promrelabel.LoadRelabelConfigs(path); err != nil {
-			return fmt.Errorf("cannot load relabel configs from -remoteWrite.urlRelabelConfig=%q: %s", path, err)
-		}
-	}
-	return nil
-}
-
 var rwctxs []*remoteWriteCtx
 
+// 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() * 4
+
+// 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.
 //
 // It must be called after flag.Parse().
@@ -56,14 +64,20 @@ 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")
+		logger.Fatalf("at least one `-remoteWrite.url` command-line flag must be set")
 	}
-
-	if !*showRemoteWriteURL {
-		// remoteWrite.url can contain authentication codes, so hide it at `/metrics` output.
-		httpserver.RegisterSecretFlag("remoteWrite.url")
+	if *queues > maxQueues {
+		*queues = maxQueues
 	}
-	initRelabelGlobal()
+	if *queues <= 0 {
+		*queues = 1
+	}
+	initLabelsGlobal()
+	rcs, err := loadRelabelConfigs()
+	if err != nil {
+		logger.Fatalf("cannot load relabel configs: %s", err)
+	}
+	allRelabelConfigs.Store(rcs)
 
 	maxInmemoryBlocks := memory.Allowed() / len(*remoteWriteURLs) / maxRowsPerBlock / 100
 	if maxInmemoryBlocks > 200 {
@@ -76,23 +90,47 @@ func Init() {
 		maxInmemoryBlocks = 2
 	}
 	for i, remoteWriteURL := range *remoteWriteURLs {
-		relabelConfigPath := ""
-		if i < len(*relabelConfigPaths) {
-			relabelConfigPath = (*relabelConfigPaths)[i]
-		}
-		urlLabelValue := fmt.Sprintf("secret-url-%d", i+1)
+		sanitizedURL := fmt.Sprintf("%d:secret-url", i+1)
 		if *showRemoteWriteURL {
-			urlLabelValue = remoteWriteURL
+			sanitizedURL = fmt.Sprintf("%d:%s", i+1, remoteWriteURL)
 		}
-		rwctx := newRemoteWriteCtx(i, remoteWriteURL, relabelConfigPath, maxInmemoryBlocks, urlLabelValue)
+		rwctx := newRemoteWriteCtx(i, remoteWriteURL, maxInmemoryBlocks, sanitizedURL)
 		rwctxs = append(rwctxs, rwctx)
 	}
+
+	// Start config reloader.
+	sighupCh := procutil.NewSighupChan()
+	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")
+		}
+	}()
 }
 
+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() {
+	close(stopCh)
+	configReloaderWG.Wait()
+
 	for _, rwctx := range rwctxs {
 		rwctx.MustStop()
 	}
@@ -101,25 +139,36 @@ func Stop() {
 
 // Push sends wr to remote storage systems set via `-remoteWrite.url`.
 //
-// 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) {
 	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
 	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
+		i := 0
+		for i < len(tss) {
+			samplesCount += len(tss[i].Samples)
+			i++
+			if samplesCount > maxRowsPerBlock {
+				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 {
@@ -137,47 +186,39 @@ func Push(wr *prompbmarshal.WriteRequest) {
 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 {
+func newRemoteWriteCtx(argIdx int, remoteWriteURL string, maxInmemoryBlocks int, sanitizedURL 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 {
+	path := fmt.Sprintf("%s/persistent-queue/%d_%016X", *tmpDataPath, argIdx+1, h)
+	fq := persistentqueue.MustOpenFastQueue(path, sanitizedURL, maxInmemoryBlocks, maxPendingBytesPerURL.N)
+	_ = metrics.GetOrCreateGauge(fmt.Sprintf(`vmagent_remotewrite_pending_data_bytes{path=%q, url=%q}`, path, 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}`, path, 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)
-		}
-	}
+	c := newClient(argIdx, remoteWriteURL, sanitizedURL, fq, *queues)
+	sf := significantFigures.GetOptionalArgOrDefault(argIdx, 0)
+	rd := roundDigits.GetOptionalArgOrDefault(argIdx, 100)
 	pss := make([]*pendingSeries, *queues)
 	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}`, path, sanitizedURL)),
 	}
 }
 
@@ -185,35 +226,47 @@ 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

@@ -6,7 +6,9 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/common"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/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/writeconcurrencylimiter"
 	"github.com/VictoriaMetrics/metrics"
@@ -21,12 +23,18 @@ var (
 //
 // See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/6
 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)
 
@@ -36,6 +44,7 @@ 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 +53,12 @@ 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{
@@ -58,7 +70,6 @@ func insertRows(rows []parser.Row) error {
 			Labels:  labels[labelsLen:],
 			Samples: samples[samplesLen:],
 		})
-		rowsTotal += len(values)
 	}
 	ctx.WriteRequest.Timeseries = tssDst
 	ctx.Labels = labels

app/vmalert/Makefile

@@ -55,29 +55,42 @@ test-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
 
 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 \
+		-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
 
 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
+
+vmalert-windows-amd64-prod:
+	APP_NAME=vmalert $(MAKE) app-via-docker-windows-amd64

app/vmalert/README.md

@@ -1,19 +1,28 @@
-## 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 given [alerting](https://prometheus.io/docs/prometheus/latest/configuration/alerting_rules/)
+or [recording](https://prometheus.io/docs/prometheus/latest/configuration/recording_rules/)
+rules against configured address.
 
 ### Features:
 * Integration with [VictoriaMetrics](https://github.com/VictoriaMetrics/VictoriaMetrics) TSDB;
-* VictoriaMetrics [MetricsQL](https://github.com/VictoriaMetrics/VictoriaMetrics/wiki/MetricsQL)
- expressions validation;
+* VictoriaMetrics [MetricsQL](https://victoriametrics.github.io/MetricsQL.html)
+ support and expressions validation;
 * Prometheus [alerting rules definition format](https://prometheus.io/docs/prometheus/latest/configuration/alerting_rules/#defining-alerting-rules)
  support;
 * Integration with [Alertmanager](https://github.com/prometheus/alertmanager);
+* Keeps the alerts [state on restarts](https://github.com/VictoriaMetrics/VictoriaMetrics/tree/master/app/vmalert#alerts-state-on-restarts);
+* Graphite datasource can be used for alerting and recording rules. See [these docs](#graphite) for details.
 * Lightweight without extra dependencies.
 
-### TODO:
-* Support recording rules.
+### Limitations:
+* `vmalert` execute queries against remote datasource which has reliability risks because of network.
+It is recommended to configure alerts thresholds and rules expressions with understanding that network request
+may fail;
+* by default, rules execution is sequential within one group, but persisting of execution results to remote
+storage is asynchronous. Hence, user shouldn't rely on recording rules chaining when result of previous
+recording rule is reused in next one;
+* `vmalert` has no UI, just an API for getting groups and rules statuses.
 
 ### QuickStart
 
@@ -26,90 +35,341 @@ make vmalert
 The build binary will be placed to `VictoriaMetrics/bin` folder.
 
 To start using `vmalert` you will need the following things:
-* list of alert rules - PromQL/MetricsQL expressions to execute;
+* list of rules - PromQL/MetricsQL expressions to execute;
 * datasource address - reachable VictoriaMetrics instance for rules execution;
-* notifier address - reachable Alertmanager instance for processing, 
+* notifier address - reachable [Alert Manager](https://github.com/prometheus/alertmanager) instance for processing,
 aggregating alerts and sending notifications.
+* remote write address - [remote write](https://prometheus.io/docs/prometheus/latest/storage/#remote-storage-integrations)
+compatible storage address for storing recording rules results and alerts state in for of timeseries. This is optional.
 
 Then configure `vmalert` accordingly:
 ```
 ./bin/vmalert -rule=alert.rules \
-		-datasource.url=http://localhost:8428 \
-        -notifier.url=http://localhost:9093
+    -datasource.url=http://localhost:8428 \  # PromQL compatible datasource
+    -notifier.url=http://localhost:9093 \    # AlertManager URL
+    -notifier.url=http://127.0.0.1:9093 \    # AlertManager replica URL
+    -remoteWrite.url=http://localhost:8428 \ # remote write compatible storage to persist rules
+    -remoteRead.url=http://localhost:8428 \  # PromQL compatible datasource to restore alerts state from
+    -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)
+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.
 
-`vmalert` runs evaluation for every group in a separate goroutine.
-Rules in group evaluated one-by-one sequentially. 
+Configuration for [recording](https://prometheus.io/docs/prometheus/latest/configuration/recording_rules/)
+and [alerting](https://prometheus.io/docs/prometheus/latest/configuration/alerting_rules/) rules is very
+similar to Prometheus rules and configured using YAML. Configuration examples may be found
+in [testdata](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/app/vmalert/config/testdata) folder.
+Every `rule` belongs to `group` and every configuration file may contain arbitrary number of groups:
+```yaml
+groups:
+  [ - <rule_group> ]
+```
 
-`vmalert` also runs a web-server (`-httpListenAddr`) for serving metrics and alerts endpoints:
+#### Groups
+
+Each group has following attributes:
+```yaml
+# The name of the group. Must be unique within a file.
+name: <string>
+
+# How often rules in the group are evaluated.
+[ interval: <duration> | default = global.evaluation_interval ]
+
+# How many rules execute at once. Increasing concurrency may speed
+# up round execution speed.
+[ concurrency: <integer> | default = 1 ]
+
+# Optional type for expressions inside the rules. Supported values: "graphite" and "prometheus".
+# By default "prometheus" rule type is used.
+[ type: <string> ]
+
+rules:
+  [ - <rule> ... ]
+```
+
+#### Rules
+
+There are two types of Rules:
+* [alerting](https://prometheus.io/docs/prometheus/latest/configuration/alerting_rules/) -
+Alerting rules allows to define alert conditions via [MetricsQL](https://victoriametrics.github.io/MetricsQL.html)
+and to send notifications about firing alerts to [Alertmanager](https://github.com/prometheus/alertmanager).
+* [recording](https://prometheus.io/docs/prometheus/latest/configuration/recording_rules/) -
+Recording rules allow you to precompute frequently needed or computationally expensive expressions
+and save their result as a new set of time series.
+
+`vmalert` forbids to define duplicates - rules with the same combination of name, expression and labels
+within one group.
+
+##### Alerting rules
+
+The syntax for alerting rule is following:
+```yaml
+# The name of the alert. Must be a valid metric name.
+alert: <string>
+
+# Optional type for the rule. Supported values: "graphite", "prometheus".
+# By default "prometheus" rule type is used.
+[ type: <string> ]
+
+# The expression to evaluate. The expression language depends on the type value.
+# By default MetricsQL expression is used. If type="graphite", then the expression
+# must contain valid Graphite expression.
+expr: <string>
+
+# Alerts are considered firing once they have been returned for this long.
+# Alerts which have not yet fired for long enough are considered pending.
+[ 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> ]
+```
+
+##### 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>
+
+# Optional type for the rule. Supported values: "graphite", "prometheus".
+# By default "prometheus" rule type is used.
+[ type: <string> ]
+
+# The expression to evaluate. The expression language depends on the type value.
+# By default MetricsQL expression is used. If type="graphite", then the expression
+# must contain valid Graphite expression.
+expr: <string>
+
+# Labels to add or overwrite before storing the result.
+labels:
+  [ <labelname>: <labelvalue> ]
+```
+
+For recording rules to work `-remoteWrite.url` must specified.
+
+
+#### Alerts state on restarts
+
+`vmalert` has no local storage, so alerts state is stored in the process memory. Hence, after reloading of `vmalert`
+the process alerts state will be lost. To avoid this situation, `vmalert` should be configured via the following flags:
+* `-remoteWrite.url` - URL to VictoriaMetrics (Single) or VMInsert (Cluster). `vmalert` will persist alerts state
+into the configured address in the form of time series named `ALERTS` and `ALERTS_FOR_STATE` via remote-write protocol.
+These are regular time series and may be queried from VM just as any other time series.
+The state stored to the configured address on every rule evaluation.
+* `-remoteRead.url` - URL to VictoriaMetrics (Single) or VMSelect (Cluster). `vmalert` will try to restore alerts state
+from configured address by querying time series with name `ALERTS_FOR_STATE`.
+
+Both flags are required for the proper state restoring. Restore process may fail if time series are missing
+in configured `-remoteRead.url`, weren't updated in the last `1h` or received state doesn't match current `vmalert`
+rules configuration.
+
+
+#### WEB
+
+`vmalert` runs a web-server (`-httpListenAddr`) for serving metrics and alerts endpoints:
+* `http://<vmalert-addr>/api/v1/groups` - list of all loaded groups and rules;
 * `http://<vmalert-addr>/api/v1/alerts` - list of all active alerts;
-* `http://<vmalert-addr>/api/v1/<groupName>/<alertID>/status" ` - get alert status by ID.
+* `http://<vmalert-addr>/api/v1/<groupID>/<alertID>/status" ` - get alert status by ID.
 Used as alert source in AlertManager.
 * `http://<vmalert-addr>/metrics` - application metrics.
 * `http://<vmalert-addr>/-/reload` - hot configuration reload.
 
-`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 query type.
 
 
 ### Configuration
 
 The shortlist of configuration flags is the following:
 ```
-Usage of vmalert:
+  -datasource.appendTypePrefix
+    	Whether to add type prefix to -datasource.url based on the query type. Set to true if sending different query types to VMSelect URL.
   -datasource.basicAuth.password string
-        Optional basic auth password for -datasource.url
+    	Optional basic auth password for -datasource.url
   -datasource.basicAuth.username string
-        Optional basic auth username for -datasource.url
+    	Optional basic auth username for -datasource.url
+  -datasource.lookback duration
+    	Lookback defines how far to look into past when evaluating queries. For example, if datasource.lookback=5m then param "time" with value now()-5m will be added to every query.
+  -datasource.maxIdleConnections int
+    	Defines the number of idle (keep-alive connections) to configured datasource.Consider to set this value equal to the value: groups_total * group.concurrency. Too low value may result into high number of sockets in TIME_WAIT state. (default 100)
+  -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.
+  -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
+    	Victoria Metrics or VMSelect url. Required parameter. E.g. http://127.0.0.1:8428
+  -dryRun -rule
+    	Whether to check only config files without running vmalert. The rules file are validated. The -rule flag must be specified.
   -enableTCP6
-        Whether to enable IPv6 for listening and dialing. By default only IPv4 TCP is used
+    	Whether to enable IPv6 for listening and dialing. By default only IPv4 TCP is used
+  -envflag.enable
+    	Whether to enable reading flags from environment variables additionally to command line. Command line flag values have priority over values from environment vars. Flags are read only from command line if this flag isn't set
+  -envflag.prefix string
+    	Prefix for environment variables if -envflag.enable is set
   -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 array of values separated by comma or specified via multiple flags.
   -external.url string
-        External URL is used as alert's source for sent alerts to the notifier
+    	External URL is used as alert's source for sent alerts to the notifier
+  -fs.disableMmap
+    	Whether to use pread() instead of mmap() for reading data files. By default mmap() is used for 64-bit arches and pread() is used for 32-bit arches, since they cannot read data files bigger than 2^32 bytes in memory. mmap() is usually faster for reading small data chunks than pread()
+  -http.connTimeout duration
+    	Incoming http connections are closed after the configured timeout. This may help spreading incoming load among a cluster of services behind load balancer. Note that the real timeout may be bigger by up to 10% as a protection from Thundering herd problem (default 2m0s)
+  -http.disableResponseCompression
+    	Disable compression of HTTP responses for saving 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 graceful shutdown of HTTP server. Highly loaded server may require increased value for graceful shutdown (default 7s)
+  -http.pathPrefix string
+    	An optional prefix to add to all the paths handled by http server. For example, if '-http.pathPrefix=/foo/bar' is set, then all the http requests will be handled on '/foo/bar/*' paths. This may be useful for proxied requests. See https://www.robustperception.io/using-external-urls-and-proxies-with-prometheus
+  -http.shutdownDelay duration
+    	Optional delay before http server shutdown. During this dealy the servier returns non-OK responses from /health page, so load balancers can route new requests to other servers
   -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
+    	Address to listen for http connections (default ":8880")
+  -loggerDisableTimestamps
+    	Whether to disable writing timestamps in logs
+  -loggerErrorsPerSecondLimit int
+    	Per-second limit on the number of ERROR messages. If more than the given number of errors are emitted per second, then the remaining errors are suppressed. Zero value disables the rate limit
+  -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 value disables the rate limit
+  -memory.allowedBytes size
+    	Allowed size of system memory VictoriaMetrics caches may occupy. This option overrides -memory.allowedPercent if set to non-zero value. Too low value may increase cache miss rate, which usually results in higher CPU and disk IO usage. Too high value may evict too much data from OS page cache, which will result in higher disk IO usage
+    	Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 0)
+  -memory.allowedPercent float
+    	Allowed percent of system memory VictoriaMetrics caches may occupy. See also -memory.allowedBytes. Too low value may increase cache miss rate, which usually results in higher CPU and disk IO usage. Too high value may evict too much data from OS page cache, which will result in higher disk IO usage (default 60)
+  -metricsAuthKey string
+    	Auth key for /metrics. It overrides httpAuth settings
+  -notifier.basicAuth.password array
+    	Optional basic auth password for -notifier.url
+    	Supports array of values separated by comma or specified via multiple flags.
+  -notifier.basicAuth.username array
+    	Optional basic auth username for -notifier.url
+    	Supports array of values separated by comma or specified via multiple flags.
+  -notifier.tlsCAFile array
+    	Optional path to TLS CA file to use for verifying connections to -notifier.url. By default system CA is used
+    	Supports array of values separated by comma or specified via multiple flags.
+  -notifier.tlsCertFile array
+    	Optional path to client-side TLS certificate file to use when connecting to -notifier.url
+    	Supports array of values separated by comma or specified via multiple flags.
+  -notifier.tlsInsecureSkipVerify array
+    	Whether to skip tls verification when connecting to -notifier.url
+    	Supports array of values separated by comma or specified via multiple flags.
+  -notifier.tlsKeyFile array
+    	Optional path to client-side TLS certificate key to use when connecting to -notifier.url
+    	Supports array of values separated by comma or specified via multiple flags.
+  -notifier.tlsServerName array
+    	Optional TLS server name to use for connections to -notifier.url. By default the server name from -notifier.url is used
+    	Supports array of values separated by comma or specified via multiple flags.
+  -notifier.url array
+    	Prometheus alertmanager URL. Required parameter. e.g. http://127.0.0.1:9093
+    	Supports array of values separated by comma or specified via multiple flags.
+  -pprofAuthKey string
+    	Auth key for /debug/pprof. It overrides httpAuth settings
   -remoteRead.basicAuth.password string
-        Optional basic auth password for -remoteRead.url
+    	Optional basic auth password for -remoteRead.url
   -remoteRead.basicAuth.username string
-        Optional basic auth username for -remoteRead.url
+    	Optional basic auth username for -remoteRead.url
   -remoteRead.lookback duration
-        Lookback defines how far to look into past for alerts timeseries. For example, if lookback=1h then range from now() to now()-1h will be scanned. (default 1h0m0s)
+    	Lookback defines how far to look into past for alerts timeseries. For example, if lookback=1h then range from now() to now()-1h will be scanned. (default 1h0m0s)
+  -remoteRead.tlsCAFile string
+    	Optional path to TLS CA file to use for verifying connections to -remoteRead.url. By default system CA is used
+  -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 Victoria Metrics or VMSelect that will be used to restore alerts state. This configuration makes sense only if vmalert was configured with `remoteWrite.url` before and has been successfully persisted its state. E.g. http://127.0.0.1:8428
+    	Optional URL to 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
+    	Optional basic auth password for -remoteWrite.url
   -remoteWrite.basicAuth.username string
-        Optional basic auth username for -remoteWrite.url
-  -remoteWrite.maxQueueSize
-	    Defines the max number of pending datapoints to remote write endpoint
+    	Optional basic auth username for -remoteWrite.url
+  -remoteWrite.concurrency int
+    	Defines number of writers for concurrent writing into remote querier (default 1)
+  -remoteWrite.flushInterval duration
+    	Defines interval of flushes to remote write endpoint (default 5s)
+  -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 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.
+    	Optional URL to Victoria Metrics or VMInsert where to persist alerts state and recording rules results in form of timeseries. E.g. http://127.0.0.1:8428
+  -rule array
+    	Path to the file with alert rules.
+    	Supports patterns. Flag can be specified multiple times.
+    	Examples:
+    	 -rule="/path/to/file". Path to a single file with alerting rules
+    	 -rule="dir/*.yaml" -rule="/*.yaml". Relative path to all .yaml files in "dir" folder,
+    	absolute path to all .yaml files in root.
+    	Rule files may contain %{ENV_VAR} placeholders, which are substituted by the corresponding env vars.
+    	Supports array of values separated by comma or specified via multiple flags.
+  -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, since RSA certs are slow
+  -tlsKeyFile string
+    	Path to file with TLS key. Used only if -tls is set
+  -version
+    	Show VictoriaMetrics version
 ```
 
-Pass `-help` to `vmalert` in order to see the full list of supported 
+Pass `-help` to `vmalert` in order to see the full list of supported
 command-line flags with their descriptions.
 
 To reload configuration without `vmalert` restart send SIGHUP signal
@@ -118,24 +378,41 @@ or send GET request to `/-/reload` endpoint.
 ### 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) 
+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 1.13.
-2. Run `make vmalert` from the root folder of the repository.
+1. [Install Go](https://golang.org/doc/install). The minimum supported version is Go 1.15.
+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.
+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 1.15.
+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 +1,450 @@
+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/lib/logger"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
+	"github.com/VictoriaMetrics/metrics"
+)
+
+// 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
+
+	// 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
+
+	metrics *alertingRuleMetrics
+}
+
+type alertingRuleMetrics struct {
+	errors  *gauge
+	pending *gauge
+	active  *gauge
+}
+
+func newAlertingRule(group *Group, cfg config.Rule) *AlertingRule {
+	ar := &AlertingRule{
+		Type:        cfg.Type,
+		RuleID:      cfg.ID,
+		Name:        cfg.Alert,
+		Expr:        cfg.Expr,
+		For:         cfg.For.Duration(),
+		Labels:      cfg.Labels,
+		Annotations: cfg.Annotations,
+		GroupID:     group.ID(),
+		GroupName:   group.Name,
+		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 = getOrCreateGauge(fmt.Sprintf(`vmalert_alerts_pending{%s}`, labels),
+		func() float64 {
+			ar.mu.Lock()
+			defer ar.mu.Unlock()
+			var num int
+			for _, a := range ar.alerts {
+				if a.State == notifier.StatePending {
+					num++
+				}
+			}
+			return float64(num)
+		})
+	ar.metrics.active = getOrCreateGauge(fmt.Sprintf(`vmalert_alerts_firing{%s}`, labels),
+		func() float64 {
+			ar.mu.Lock()
+			defer ar.mu.Unlock()
+			var num int
+			for _, a := range ar.alerts {
+				if a.State == notifier.StateFiring {
+					num++
+				}
+			}
+			return float64(num)
+		})
+	ar.metrics.errors = getOrCreateGauge(fmt.Sprintf(`vmalert_alerts_error{%s}`, labels),
+		func() float64 {
+			ar.mu.Lock()
+			defer ar.mu.Unlock()
+			if ar.lastExecError == nil {
+				return 0
+			}
+			return 1
+		})
+	return ar
+}
+
+// Close unregisters rule metrics
+func (ar *AlertingRule) Close() {
+	metrics.UnregisterMetric(ar.metrics.active.name)
+	metrics.UnregisterMetric(ar.metrics.pending.name)
+	metrics.UnregisterMetric(ar.metrics.errors.name)
+}
+
+// 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
+}
+
+// Exec executes AlertingRule expression via the given Querier.
+// Based on the Querier results AlertingRule maintains notifier.Alerts
+func (ar *AlertingRule) Exec(ctx context.Context, q datasource.Querier, series bool) ([]prompbmarshal.TimeSeries, error) {
+	qMetrics, err := q.Query(ctx, ar.Expr, ar.Type)
+	ar.mu.Lock()
+	defer ar.mu.Unlock()
+
+	ar.lastExecError = err
+	ar.lastExecTime = time.Now()
+	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 q.Query(ctx, query, ar.Type) }
+	updated := make(map[uint64]struct{})
+	// update list of active alerts
+	for _, m := range qMetrics {
+		// 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.Value {
+				// update Value field with latest value
+				a.Value = m.Value
+				// 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()
+		}
+	}
+	if series {
+		return ar.toTimeSeries(ar.lastExecTime), nil
+	}
+	return nil, 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.Value,
+		Expr:   ar.Expr,
+	}
+	return notifier.ExecTemplate(q, ar.Labels, tpl)
+}
+
+func (ar *AlertingRule) toTimeSeries(timestamp time.Time) []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
+	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.Value,
+		Start:   start,
+		Expr:    ar.Expr,
+	}
+	// label defined here to make override possible by
+	// time series labels.
+	a.Labels[alertGroupNameLabel] = ar.GroupName
+	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,
+		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 {
+	return &APIAlert{
+		// encode as strings to avoid rounding
+		ID:      fmt.Sprintf("%d", a.ID),
+		GroupID: fmt.Sprintf("%d", a.GroupID),
+
+		Name:        a.Name,
+		Expression:  ar.Expr,
+		Labels:      a.Labels,
+		Annotations: a.Annotations,
+		State:       a.State.String(),
+		ActiveAt:    a.Start,
+		Value:       strconv.FormatFloat(a.Value, 'e', -1, 64),
+	}
+}
+
+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.
+	alertGroupNameLabel = "alertgroup"
+)
+
+// alertToTimeSeries converts the given alert with the given timestamp to timeseries
+func (ar *AlertingRule) alertToTimeSeries(a *notifier.Alert, timestamp time.Time) []prompbmarshal.TimeSeries {
+	var tss []prompbmarshal.TimeSeries
+	tss = append(tss, alertToTimeSeries(ar.Name, a, timestamp))
+	if ar.For > 0 {
+		tss = append(tss, alertForToTimeSeries(ar.Name, a, timestamp))
+	}
+	return tss
+}
+
+func alertToTimeSeries(name string, a *notifier.Alert, timestamp time.Time) prompbmarshal.TimeSeries {
+	labels := make(map[string]string)
+	for k, v := range a.Labels {
+		labels[k] = v
+	}
+	labels["__name__"] = alertMetricName
+	labels[alertNameLabel] = name
+	labels[alertStateLabel] = a.State.String()
+	return newTimeSeries(1, labels, timestamp)
+}
+
+// alertForToTimeSeries returns a timeseries that represents
+// state of active alerts, where value is time when alert become active
+func alertForToTimeSeries(name string, a *notifier.Alert, timestamp time.Time) prompbmarshal.TimeSeries {
+	labels := make(map[string]string)
+	for k, v := range a.Labels {
+		labels[k] = v
+	}
+	labels["__name__"] = alertForStateMetricName
+	labels[alertNameLabel] = name
+	return newTimeSeries(float64(a.Start.Unix()), labels, timestamp)
+}
+
+// Restore restores the state of active alerts basing on previously written timeseries.
+// 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 q.Query(ctx, query, ar.Type) }
+
+	// 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, ar.Type)
+	if err != nil {
+		return err
+	}
+
+	for _, m := range qMetrics {
+		labels := m.Labels
+		m.Labels = make([]datasource.Label, 0)
+		// drop all extra labels, so hash key will
+		// be identical to time series received in Exec
+		for _, l := range labels {
+			if l.Name == alertNameLabel || l.Name == alertGroupNameLabel {
+				continue
+			}
+			m.Labels = append(m.Labels, l)
+		}
+
+		a, err := ar.newAlert(m, time.Unix(int64(m.Value), 0), qFn)
+		if err != nil {
+			return fmt.Errorf("failed to create alert: %w", err)
+		}
+		a.ID = hash(m)
+		a.State = notifier.StatePending
+		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

@@ -2,7 +2,9 @@ package main
 
 import (
 	"context"
-	"sync"
+	"errors"
+	"reflect"
+	"strings"
 	"testing"
 	"time"
 
@@ -11,30 +13,15 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
 )
 
-func TestRule_Validate(t *testing.T) {
-	if err := (&Rule{}).Validate(); err == nil {
-		t.Errorf("exptected empty name error")
-	}
-	if err := (&Rule{Name: "alert"}).Validate(); err == nil {
-		t.Errorf("exptected empty expr error")
-	}
-	if err := (&Rule{Name: "alert", Expr: "test{"}).Validate(); err == nil {
-		t.Errorf("exptected invalid expr error")
-	}
-	if err := (&Rule{Name: "alert", Expr: "test>0"}).Validate(); err != nil {
-		t.Errorf("exptected valid rule got %s", err)
-	}
-}
-
-func TestRule_AlertToTimeSeries(t *testing.T) {
+func TestAlertingRule_ToTimeSeries(t *testing.T) {
 	timestamp := time.Now()
 	testCases := []struct {
-		rule  *Rule
+		rule  *AlertingRule
 		alert *notifier.Alert
 		expTS []prompbmarshal.TimeSeries
 	}{
 		{
-			newTestRule("instant", 0),
+			newTestAlertingRule("instant", 0),
 			&notifier.Alert{State: notifier.StateFiring},
 			[]prompbmarshal.TimeSeries{
 				newTimeSeries(1, map[string]string{
@@ -45,7 +32,7 @@ func TestRule_AlertToTimeSeries(t *testing.T) {
 			},
 		},
 		{
-			newTestRule("instant extra labels", 0),
+			newTestAlertingRule("instant extra labels", 0),
 			&notifier.Alert{State: notifier.StateFiring, Labels: map[string]string{
 				"job":      "foo",
 				"instance": "bar",
@@ -61,7 +48,7 @@ func TestRule_AlertToTimeSeries(t *testing.T) {
 			},
 		},
 		{
-			newTestRule("instant labels override", 0),
+			newTestAlertingRule("instant labels override", 0),
 			&notifier.Alert{State: notifier.StateFiring, Labels: map[string]string{
 				alertStateLabel: "foo",
 				"__name__":      "bar",
@@ -75,7 +62,7 @@ func TestRule_AlertToTimeSeries(t *testing.T) {
 			},
 		},
 		{
-			newTestRule("for", time.Second),
+			newTestAlertingRule("for", time.Second),
 			&notifier.Alert{State: notifier.StateFiring, Start: timestamp.Add(time.Second)},
 			[]prompbmarshal.TimeSeries{
 				newTimeSeries(1, map[string]string{
@@ -90,7 +77,7 @@ func TestRule_AlertToTimeSeries(t *testing.T) {
 			},
 		},
 		{
-			newTestRule("for pending", 10*time.Second),
+			newTestAlertingRule("for pending", 10*time.Second),
 			&notifier.Alert{State: notifier.StatePending, Start: timestamp.Add(time.Second)},
 			[]prompbmarshal.TimeSeries{
 				newTimeSeries(1, map[string]string{
@@ -107,58 +94,29 @@ func TestRule_AlertToTimeSeries(t *testing.T) {
 	}
 	for _, tc := range testCases {
 		t.Run(tc.rule.Name, func(t *testing.T) {
-			tss := tc.rule.AlertToTimeSeries(tc.alert, timestamp)
-			if len(tc.expTS) != len(tss) {
-				t.Fatalf("expected number of timeseries %d; got %d", len(tc.expTS), len(tss))
-			}
-			for i := range tc.expTS {
-				expTS, gotTS := tc.expTS[i], tss[i]
-				if len(expTS.Samples) != len(gotTS.Samples) {
-					t.Fatalf("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 {
-						t.Errorf("expected value %.2f; got %.2f", exp.Value, got.Value)
-					}
-					if got.Timestamp != exp.Timestamp {
-						t.Errorf("expected timestamp %d; got %d", exp.Timestamp, got.Timestamp)
-					}
-				}
-				if len(expTS.Labels) != len(gotTS.Labels) {
-					t.Fatalf("expected number of labels %d; got %d", len(expTS.Labels), len(gotTS.Labels))
-				}
-				for i, exp := range expTS.Labels {
-					got := gotTS.Labels[i]
-					if got.Name != exp.Name {
-						t.Errorf("expected label name %q; got %q", exp.Name, got.Name)
-					}
-					if got.Value != exp.Value {
-						t.Errorf("expected label value %q; got %q", exp.Value, got.Value)
-					}
-				}
+			tc.rule.alerts[tc.alert.ID] = tc.alert
+			tss := tc.rule.toTimeSeries(timestamp)
+			if err := compareTimeSeries(t, tc.expTS, tss); err != nil {
+				t.Fatalf("timeseries missmatch: %s", err)
 			}
 		})
 	}
 }
 
-func newTestRule(name string, waitFor time.Duration) *Rule {
-	return &Rule{Name: name, alerts: make(map[uint64]*notifier.Alert), For: waitFor}
-}
-
-func TestRule_Exec(t *testing.T) {
+func TestAlertingRule_Exec(t *testing.T) {
+	const defaultStep = 5 * time.Millisecond
 	testCases := []struct {
-		rule      *Rule
+		rule      *AlertingRule
 		steps     [][]datasource.Metric
 		expAlerts map[uint64]*notifier.Alert
 	}{
 		{
-			newTestRule("empty", 0),
+			newTestAlertingRule("empty", 0),
 			[][]datasource.Metric{},
 			map[uint64]*notifier.Alert{},
 		},
 		{
-			newTestRule("empty labels", 0),
+			newTestAlertingRule("empty labels", 0),
 			[][]datasource.Metric{
 				{datasource.Metric{}},
 			},
@@ -167,7 +125,7 @@ func TestRule_Exec(t *testing.T) {
 			},
 		},
 		{
-			newTestRule("single-firing", 0),
+			newTestAlertingRule("single-firing", 0),
 			[][]datasource.Metric{
 				{metricWithLabels(t, "name", "foo")},
 			},
@@ -176,7 +134,7 @@ func TestRule_Exec(t *testing.T) {
 			},
 		},
 		{
-			newTestRule("single-firing=>inactive", 0),
+			newTestAlertingRule("single-firing=>inactive", 0),
 			[][]datasource.Metric{
 				{metricWithLabels(t, "name", "foo")},
 				{},
@@ -186,7 +144,7 @@ func TestRule_Exec(t *testing.T) {
 			},
 		},
 		{
-			newTestRule("single-firing=>inactive=>firing", 0),
+			newTestAlertingRule("single-firing=>inactive=>firing", 0),
 			[][]datasource.Metric{
 				{metricWithLabels(t, "name", "foo")},
 				{},
@@ -197,7 +155,7 @@ func TestRule_Exec(t *testing.T) {
 			},
 		},
 		{
-			newTestRule("single-firing=>inactive=>firing=>inactive", 0),
+			newTestAlertingRule("single-firing=>inactive=>firing=>inactive", 0),
 			[][]datasource.Metric{
 				{metricWithLabels(t, "name", "foo")},
 				{},
@@ -209,7 +167,7 @@ func TestRule_Exec(t *testing.T) {
 			},
 		},
 		{
-			newTestRule("single-firing=>inactive=>firing=>inactive=>empty", 0),
+			newTestAlertingRule("single-firing=>inactive=>firing=>inactive=>empty", 0),
 			[][]datasource.Metric{
 				{metricWithLabels(t, "name", "foo")},
 				{},
@@ -220,7 +178,7 @@ func TestRule_Exec(t *testing.T) {
 			map[uint64]*notifier.Alert{},
 		},
 		{
-			newTestRule("single-firing=>inactive=>firing=>inactive=>empty=>firing", 0),
+			newTestAlertingRule("single-firing=>inactive=>firing=>inactive=>empty=>firing", 0),
 			[][]datasource.Metric{
 				{metricWithLabels(t, "name", "foo")},
 				{},
@@ -234,7 +192,7 @@ func TestRule_Exec(t *testing.T) {
 			},
 		},
 		{
-			newTestRule("multiple-firing", 0),
+			newTestAlertingRule("multiple-firing", 0),
 			[][]datasource.Metric{
 				{
 					metricWithLabels(t, "name", "foo"),
@@ -249,7 +207,7 @@ func TestRule_Exec(t *testing.T) {
 			},
 		},
 		{
-			newTestRule("multiple-steps-firing", 0),
+			newTestAlertingRule("multiple-steps-firing", 0),
 			[][]datasource.Metric{
 				{metricWithLabels(t, "name", "foo")},
 				{metricWithLabels(t, "name", "foo1")},
@@ -264,20 +222,7 @@ func TestRule_Exec(t *testing.T) {
 			},
 		},
 		{
-			newTestRule("duplicate", 0),
-			[][]datasource.Metric{
-				{
-					// metrics with the same labelset should result in one alert
-					metricWithLabels(t, "name", "foo", "type", "bar"),
-					metricWithLabels(t, "type", "bar", "name", "foo"),
-				},
-			},
-			map[uint64]*notifier.Alert{
-				hash(metricWithLabels(t, "name", "foo", "type", "bar")): {State: notifier.StateFiring},
-			},
-		},
-		{
-			newTestRule("for-pending", time.Minute),
+			newTestAlertingRule("for-pending", time.Minute),
 			[][]datasource.Metric{
 				{metricWithLabels(t, "name", "foo")},
 			},
@@ -286,7 +231,7 @@ func TestRule_Exec(t *testing.T) {
 			},
 		},
 		{
-			newTestRule("for-fired", time.Millisecond),
+			newTestAlertingRule("for-fired", defaultStep),
 			[][]datasource.Metric{
 				{metricWithLabels(t, "name", "foo")},
 				{metricWithLabels(t, "name", "foo")},
@@ -296,7 +241,7 @@ func TestRule_Exec(t *testing.T) {
 			},
 		},
 		{
-			newTestRule("for-pending=>empty", time.Second),
+			newTestAlertingRule("for-pending=>empty", time.Second),
 			[][]datasource.Metric{
 				{metricWithLabels(t, "name", "foo")},
 				{metricWithLabels(t, "name", "foo")},
@@ -306,7 +251,7 @@ func TestRule_Exec(t *testing.T) {
 			map[uint64]*notifier.Alert{},
 		},
 		{
-			newTestRule("for-pending=>firing=>inactive", time.Millisecond),
+			newTestAlertingRule("for-pending=>firing=>inactive", defaultStep),
 			[][]datasource.Metric{
 				{metricWithLabels(t, "name", "foo")},
 				{metricWithLabels(t, "name", "foo")},
@@ -318,7 +263,7 @@ func TestRule_Exec(t *testing.T) {
 			},
 		},
 		{
-			newTestRule("for-pending=>firing=>inactive=>pending", time.Millisecond),
+			newTestAlertingRule("for-pending=>firing=>inactive=>pending", defaultStep),
 			[][]datasource.Metric{
 				{metricWithLabels(t, "name", "foo")},
 				{metricWithLabels(t, "name", "foo")},
@@ -331,7 +276,7 @@ func TestRule_Exec(t *testing.T) {
 			},
 		},
 		{
-			newTestRule("for-pending=>firing=>inactive=>pending=>firing", time.Millisecond),
+			newTestAlertingRule("for-pending=>firing=>inactive=>pending=>firing", defaultStep),
 			[][]datasource.Metric{
 				{metricWithLabels(t, "name", "foo")},
 				{metricWithLabels(t, "name", "foo")},
@@ -349,15 +294,15 @@ func TestRule_Exec(t *testing.T) {
 	for _, tc := range testCases {
 		t.Run(tc.rule.Name, func(t *testing.T) {
 			fq := &fakeQuerier{}
-			tc.rule.group = fakeGroup
+			tc.rule.GroupID = fakeGroup.ID()
 			for _, step := range tc.steps {
 				fq.reset()
 				fq.add(step...)
-				if err := tc.rule.Exec(context.TODO(), fq); err != nil {
+				if _, err := tc.rule.Exec(context.TODO(), fq, false); err != nil {
 					t.Fatalf("unexpected err: %s", err)
 				}
 				// artificial delay between applying steps
-				time.Sleep(time.Millisecond)
+				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))
@@ -375,49 +320,9 @@ func TestRule_Exec(t *testing.T) {
 	}
 }
 
-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{}
-	for i := 0; i < len(labels); i += 2 {
-		m.Labels = append(m.Labels, datasource.Label{
-			Name:  labels[i],
-			Value: labels[i+1],
-		})
-	}
-	return m
-}
-
-type fakeQuerier struct {
-	sync.Mutex
-	metrics []datasource.Metric
-}
-
-func (fq *fakeQuerier) reset() {
-	fq.Lock()
-	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) Query(_ context.Context, _ string) ([]datasource.Metric, error) {
-	fq.Lock()
-	cpy := make([]datasource.Metric, len(fq.metrics))
-	copy(cpy, fq.metrics)
-	fq.Unlock()
-	return cpy, nil
-}
-
-func TestRule_Restore(t *testing.T) {
+func TestAlertingRule_Restore(t *testing.T) {
 	testCases := []struct {
-		rule      *Rule
+		rule      *AlertingRule
 		metrics   []datasource.Metric
 		expAlerts map[uint64]*notifier.Alert
 	}{
@@ -440,6 +345,7 @@ func TestRule_Restore(t *testing.T) {
 				metricWithValueAndLabels(t, float64(time.Now().Truncate(time.Hour).Unix()),
 					"__name__", alertForStateMetricName,
 					alertNameLabel, "",
+					alertGroupNameLabel, "groupID",
 					"foo", "bar",
 					"namespace", "baz",
 				),
@@ -460,7 +366,7 @@ func TestRule_Restore(t *testing.T) {
 					alertNameLabel, "",
 					"foo", "bar",
 					"namespace", "baz",
-					// following pair supposed to be dropped
+					// extra labels set by rule
 					"source", "vm",
 				),
 			},
@@ -468,6 +374,7 @@ func TestRule_Restore(t *testing.T) {
 				hash(metricWithLabels(t,
 					"foo", "bar",
 					"namespace", "baz",
+					"source", "vm",
 				)): {State: notifier.StatePending,
 					Start: time.Now().Truncate(time.Hour)},
 			},
@@ -502,9 +409,9 @@ func TestRule_Restore(t *testing.T) {
 	for _, tc := range testCases {
 		t.Run(tc.rule.Name, func(t *testing.T) {
 			fq := &fakeQuerier{}
-			tc.rule.group = fakeGroup
+			tc.rule.GroupID = fakeGroup.ID()
 			fq.add(tc.metrics...)
-			if err := tc.rule.Restore(context.TODO(), fq, time.Hour); err != nil {
+			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) {
@@ -526,8 +433,140 @@ func TestRule_Restore(t *testing.T) {
 	}
 }
 
-func newTestRuleWithLabels(name string, labels ...string) *Rule {
-	r := newTestRule(name, 0)
+func TestAlertingRule_Exec_Negative(t *testing.T) {
+	fq := &fakeQuerier{}
+	ar := newTestAlertingRule("test", 0)
+	ar.Labels = map[string]string{"job": "test"}
+
+	// successful attempt
+	fq.add(metricWithValueAndLabels(t, 1, "__name__", "foo", "job", "bar"))
+	_, err := ar.Exec(context.TODO(), fq, false)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	// label `job` will collide with rule extra label and will make both time series equal
+	fq.add(metricWithValueAndLabels(t, 1, "__name__", "foo", "job", "baz"))
+	_, err = ar.Exec(context.TODO(), fq, false)
+	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(), fq, false)
+	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, "region", "east", "instance", "foo")): {
+					Annotations: map[string]string{},
+					Labels: map[string]string{
+						alertGroupNameLabel: "",
+						"region":            "east",
+						"instance":          "foo",
+					},
+				},
+				hash(metricWithLabels(t, "region", "east", "instance", "bar")): {
+					Annotations: map[string]string{},
+					Labels: map[string]string{
+						alertGroupNameLabel: "",
+						"region":            "east",
+						"instance":          "bar",
+					},
+				},
+			},
+		},
+		{
+			&AlertingRule{
+				Name: "override label",
+				Labels: map[string]string{
+					"instance": "{{ $labels.instance }}",
+					"region":   "east",
+				},
+				Annotations: map[string]string{
+					"summary":     `Too high connection number for "{{ $labels.instance }}" for region {{ $labels.region }}`,
+					"description": `It is {{ $value }} connections for "{{ $labels.instance }}"`,
+				},
+				alerts: make(map[uint64]*notifier.Alert),
+			},
+			[]datasource.Metric{
+				metricWithValueAndLabels(t, 2, "instance", "foo"),
+				metricWithValueAndLabels(t, 10, "instance", "bar"),
+			},
+			map[uint64]*notifier.Alert{
+				hash(metricWithLabels(t, "region", "east", "instance", "foo")): {
+					Labels: map[string]string{
+						alertGroupNameLabel: "",
+						"instance":          "foo",
+						"region":            "east",
+					},
+					Annotations: map[string]string{
+						"summary":     `Too high connection number for "foo" for region east`,
+						"description": `It is 2 connections for "foo"`,
+					},
+				},
+				hash(metricWithLabels(t, "region", "east", "instance", "bar")): {
+					Labels: map[string]string{
+						alertGroupNameLabel: "",
+						"instance":          "bar",
+						"region":            "east",
+					},
+					Annotations: map[string]string{
+						"summary":     `Too high connection number for "bar" for region east`,
+						"description": `It is 10 connections for "bar"`,
+					},
+				},
+			},
+		},
+	}
+	fakeGroup := Group{Name: "TestRule_Exec"}
+	for _, tc := range testCases {
+		t.Run(tc.rule.Name, func(t *testing.T) {
+			fq := &fakeQuerier{}
+			tc.rule.GroupID = fakeGroup.ID()
+			fq.add(tc.metrics...)
+			if _, err := tc.rule.Exec(context.TODO(), fq, false); 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]
@@ -535,9 +574,6 @@ func newTestRuleWithLabels(name string, labels ...string) *Rule {
 	return r
 }
 
-func metricWithValueAndLabels(t *testing.T, value float64, labels ...string) datasource.Metric {
-	t.Helper()
-	m := metricWithLabels(t, labels...)
-	m.Value = value
-	return m
+func newTestAlertingRule(name string, waitFor time.Duration) *AlertingRule {
+	return &AlertingRule{Name: name, alerts: make(map[uint64]*notifier.Alert), For: waitFor}
 }

app/vmalert/config.go

@@ -1,74 +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.doneCh = make(chan struct{})
-			g.finishedCh = make(chan struct{})
-			g.updateCh = make(chan Group)
-
-			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 +1,301 @@
+package config
+
+import (
+	"crypto/md5"
+	"fmt"
+	"hash/fnv"
+	"io/ioutil"
+	"path/filepath"
+	"sort"
+	"strings"
+	"time"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/utils"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/envtemplate"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
+	"github.com/VictoriaMetrics/metricsql"
+	"gopkg.in/yaml.v2"
+)
+
+// Group contains list of Rules grouped into
+// entity with one name and evaluation interval
+type Group struct {
+	Type        datasource.Type `yaml:"type,omitempty"`
+	File        string
+	Name        string        `yaml:"name"`
+	Interval    time.Duration `yaml:"interval,omitempty"`
+	Rules       []Rule        `yaml:"rules"`
+	Concurrency int           `yaml:"concurrency"`
+	// Checksum stores the hash of yaml definition for this group.
+	// May be used to detect any changes like rules re-ordering etc.
+	Checksum string
+
+	// 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())
+	}
+	// update rules with empty type.
+	for i, r := range g.Rules {
+		if r.Type.Get() == "" {
+			r.Type.Set(g.Type)
+			r.ID = HashRule(r)
+			g.Rules[i] = r
+		}
+	}
+
+	h := md5.New()
+	h.Write(b)
+	g.Checksum = fmt.Sprintf("%x", h.Sum(nil))
+	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")
+	}
+	if len(g.Rules) == 0 {
+		return fmt.Errorf("group %q can't contain no rules", g.Name)
+	}
+
+	uniqueRules := map[uint64]struct{}{}
+	for _, r := range g.Rules {
+		ruleName := r.Record
+		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 r.Type.Get() != "" {
+				exprValidator = r.Type.ValidateExpr
+			}
+			if err := exprValidator(r.Expr); err != nil {
+				return fmt.Errorf("invalid expression for rule %q.%q: %w", g.Name, ruleName, err)
+			}
+		}
+		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
+	Type        datasource.Type   `yaml:"type,omitempty"`
+	Record      string            `yaml:"record,omitempty"`
+	Alert       string            `yaml:"alert,omitempty"`
+	Expr        string            `yaml:"expr"`
+	For         PromDuration      `yaml:"for"`
+	Labels      map[string]string `yaml:"labels,omitempty"`
+	Annotations map[string]string `yaml:"annotations,omitempty"`
+
+	// Catches all undefined fields and must be empty after parsing.
+	XXX map[string]interface{} `yaml:",inline"`
+}
+
+// PromDuration is Prometheus duration.
+type PromDuration struct {
+	milliseconds int64
+}
+
+// NewPromDuration returns PromDuration for given d.
+func NewPromDuration(d time.Duration) PromDuration {
+	return PromDuration{
+		milliseconds: d.Milliseconds(),
+	}
+}
+
+// MarshalYAML implements yaml.Marshaler interface.
+func (pd PromDuration) MarshalYAML() (interface{}, error) {
+	return pd.Duration().String(), nil
+}
+
+// UnmarshalYAML implements yaml.Unmarshaler interface.
+func (pd *PromDuration) UnmarshalYAML(unmarshal func(interface{}) error) error {
+	var s string
+	if err := unmarshal(&s); err != nil {
+		return err
+	}
+	ms, err := metricsql.DurationValue(s, 0)
+	if err != nil {
+		return err
+	}
+	pd.milliseconds = ms
+	return nil
+}
+
+// Duration returns duration for pd.
+func (pd *PromDuration) Duration() time.Duration {
+	return time.Duration(pd.milliseconds) * time.Millisecond
+}
+
+// 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))
+	}
+	h.Write([]byte(r.Type.Get()))
+	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 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
+			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, ";"))
+	}
+	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 +1,455 @@
+package config
+
+import (
+	"net/url"
+	"os"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
+
+	"gopkg.in/yaml.v2"
+
+	"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, 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"},
+			expErr: "contain no rules",
+		},
+		{
+			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:  PromDuration{milliseconds: 10},
+					},
+					{
+						Expr: "sum(up == 0 ) by (host)",
+						Type: datasource.NewPrometheusType(),
+					},
+				},
+			},
+		},
+		{
+			group: &Group{
+				Name: "test graphite prometheus bad expr",
+				Type: datasource.NewGraphiteType(),
+				Rules: []Rule{
+					{
+						Expr: "sum(up == 0 ) by (host)",
+						For:  PromDuration{milliseconds: 10},
+					},
+					{
+						Expr: "sumSeries(time('foo.bar',10))",
+						Type: datasource.NewPrometheusType(),
+					},
+				},
+			},
+			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: NewPromDuration(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("Ok, `for` must change cs", func(t *testing.T) {
+		f(t, `
+name: TestGroup
+rules:
+  - alert: ExampleAlertWithFor
+    expr: sum by(job) (up == 1)
+    for: 5m
+`, `
+name: TestGroup
+rules:
+  - alert: ExampleAlertWithFor
+    expr: sum by(job) (up == 1)
+`)
+	})
+
+}

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

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

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

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

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

@@ -9,5 +9,3 @@ 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/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 +1,46 @@
+groups:
+  - name: TestGroup
+    interval: 2s
+    concurrency: 2
+    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!
+          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 +1,30 @@
+groups:
+  - name: TestGroup
+    interval: 2s
+    concurrency: 2
+    type: graphite
+    rules:
+      - alert: Conns
+        expr: filterSeries(sumSeries(host.receiver.interface.cons),'last','>', 500)
+        for: 3m
+        annotations:
+          summary: Too high connection number for {{$labels.instance}}
+          description: "It is {{ $value }} connections for {{$labels.instance}}"
+  - name: TestGroupPromMixed
+    interval: 2s
+    concurrency: 2
+    type: prometheus
+    rules:
+      - alert: Conns
+        expr: sum(vm_tcplistener_conns) by (instance) > 1
+        for: 3m
+        annotations:
+          summary: Too high connection number for {{$labels.instance}}
+          description: "It is {{ $value }} connections for {{$labels.instance}}"
+      - alert: HostDown
+        type: graphite
+        expr: filterSeries(sumSeries(host.receiver.interface.up),'last','=', 0)
+        for: 3m
+        annotations:
+          summary: Too high connection number for {{$labels.instance}}
+          description: "It is {{ $value }} connections for {{$labels.instance}}"

app/vmalert/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

@@ -1,12 +1,14 @@
 package datasource
 
-import "context"
+import (
+	"context"
+)
 
 // Querier interface wraps Query method which
 // executes given query and returns list of Metrics
 // as result
 type Querier interface {
-	Query(ctx context.Context, query string) ([]Metric, error)
+	Query(ctx context.Context, query string, engine Type) ([]Metric, error)
 }
 
 // Metric is the basic entity which should be return by datasource
@@ -17,6 +19,34 @@ type Metric struct {
 	Value     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
 type Label struct {
 	Name  string

app/vmalert/datasource/init.go

@@ -0,0 +1,46 @@
+package datasource
+
+import (
+	"flag"
+	"fmt"
+	"net/http"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/utils"
+)
+
+var (
+	addr = flag.String("datasource.url", "", "Victoria Metrics or VMSelect url. Required parameter."+
+		" E.g. http://127.0.0.1:8428")
+	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 VMSelect URL.")
+	basicAuthUsername = flag.String("datasource.basicAuth.username", "", "Optional basic auth username for -datasource.url")
+	basicAuthPassword = flag.String("datasource.basicAuth.password", "", "Optional basic auth password for -datasource.url")
+
+	tlsInsecureSkipVerify = flag.Bool("datasource.tlsInsecureSkipVerify", false, "Whether to skip tls verification when connecting to -datasource.url")
+	tlsCertFile           = flag.String("datasource.tlsCertFile", "", "Optional path to client-side TLS certificate file to use when connecting to -datasource.url")
+	tlsKeyFile            = flag.String("datasource.tlsKeyFile", "", "Optional path to client-side TLS certificate key to use when connecting to -datasource.url")
+	tlsCAFile             = flag.String("datasource.tlsCAFile", "", "Optional path to TLS CA file to use for verifying connections to -datasource.url. "+
+		"By default system CA is used")
+	tlsServerName = flag.String("datasource.tlsServerName", "", "Optional TLS server name to use for connections to -datasource.url. "+
+		"By default the server name from -datasource.url is used")
+
+	lookBack = flag.Duration("datasource.lookback", 0, "Lookback defines how far to look into past when evaluating queries. "+
+		"For example, if datasource.lookback=5m then param \"time\" with value now()-5m will be added to every query.")
+	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.")
+	maxIdleConnections = flag.Int("datasource.maxIdleConnections", 100, "Defines the number of idle (keep-alive connections) to configured datasource."+
+		"Consider to set this value equal to the value: groups_total * group.concurrency. Too low value may result into high number of sockets in TIME_WAIT state.")
+)
+
+// Init creates a Querier from provided flag values.
+func Init() (Querier, error) {
+	if *addr == "" {
+		return nil, fmt.Errorf("datasource.url is empty")
+	}
+	tr, err := utils.Transport(*addr, *tlsCertFile, *tlsKeyFile, *tlsCAFile, *tlsServerName, *tlsInsecureSkipVerify)
+	if err != nil {
+		return nil, fmt.Errorf("failed to create transport: %w", err)
+	}
+	tr.MaxIdleConns = *maxIdleConnections
+	c := &http.Client{Transport: tr}
+	return NewVMStorage(*addr, *basicAuthUsername, *basicAuthPassword, *lookBack, *queryStep, *appendTypePrefix, c), nil
+}

app/vmalert/datasource/type.go

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

app/vmalert/datasource/vm.go

@@ -6,9 +6,9 @@ import (
 	"fmt"
 	"io/ioutil"
 	"net/http"
-	"net/url"
 	"strconv"
 	"strings"
+	"time"
 )
 
 type response struct {
@@ -32,11 +32,11 @@ func (r response) metrics() ([]Metric, 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)
+			return nil, fmt.Errorf("metric %v, unable to parse float64 from %s: %w", res, res.TV[1], err)
 		}
 		m.Labels = nil
 		for k, v := range r.Data.Result[i].Labels {
-			m.Labels = append(m.Labels, Label{Name: k, Value: v})
+			m.AddLabel(k, v)
 		}
 		m.Timestamp = int64(res.TV[0].(float64))
 		m.Value = f
@@ -45,59 +45,162 @@ func (r response) metrics() ([]Metric, error) {
 	return ms, nil
 }
 
-const queryPath = "/api/v1/query?query="
+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.Value = last[0]
+		m.Timestamp = int64(last[1])
+		for k, v := range res.Tags {
+			m.AddLabel(k, v)
+		}
+		ms = append(ms, m)
+	}
+	return ms
+}
 
 // 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
+	datasourceURL    string
+	basicAuthUser    string
+	basicAuthPass    string
+	appendTypePrefix bool
+	lookBack         time.Duration
+	queryStep        time.Duration
 }
 
+const queryPath = "/api/v1/query"
+const graphitePath = "/render"
+
+const prometheusPrefix = "/prometheus"
+const graphitePrefix = "/graphite"
+
 // NewVMStorage is a constructor for VMStorage
-func NewVMStorage(baseURL, basicAuthUser, basicAuthPass string, c *http.Client) *VMStorage {
+func NewVMStorage(baseURL, basicAuthUser, basicAuthPass string, lookBack time.Duration, queryStep time.Duration, appendTypePrefix bool, c *http.Client) *VMStorage {
 	return &VMStorage{
-		c:             c,
-		basicAuthUser: basicAuthUser,
-		basicAuthPass: basicAuthPass,
-		queryURL:      strings.TrimSuffix(baseURL, "/") + queryPath,
+		c:                c,
+		basicAuthUser:    basicAuthUser,
+		basicAuthPass:    basicAuthPass,
+		datasourceURL:    strings.TrimSuffix(baseURL, "/"),
+		appendTypePrefix: appendTypePrefix,
+		lookBack:         lookBack,
+		queryStep:        queryStep,
 	}
 }
 
-// Query reads metrics from datasource by given query
-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)
+// Query reads metrics from datasource by given query and type
+func (s *VMStorage) Query(ctx context.Context, query string, dataSourceType Type) ([]Metric, error) {
+	switch dataSourceType.name {
+	case "", prometheusType:
+		return s.queryDataSource(ctx, query, s.setPrometheusReqParams, parsePrometheusResponse)
+	case graphiteType:
+		return s.queryDataSource(ctx, query, s.setGraphiteReqParams, parseGraphiteResponse)
+	default:
+		return nil, fmt.Errorf("engine not found: %q", dataSourceType)
+	}
+}
+
+func (s *VMStorage) queryDataSource(
+	ctx context.Context,
+	query string,
+	setReqParams func(r *http.Request, query string),
+	processResponse func(r *http.Request, resp *http.Response,
+	) ([]Metric, error)) ([]Metric, error) {
+	req, err := http.NewRequest("POST", s.datasourceURL, nil)
 	if err != nil {
 		return nil, err
 	}
-	req.Header.Set("Content-Type", "application/json")
+	req.Header.Set("Content-Type", "application/json; charset=utf-8")
 	if s.basicAuthPass != "" {
 		req.SetBasicAuth(s.basicAuthUser, s.basicAuthPass)
 	}
+	setReqParams(req, query)
 	resp, err := s.c.Do(req.WithContext(ctx))
 	if err != nil {
-		return nil, fmt.Errorf("error getting response from %s:%s", req.URL, err)
+		return nil, fmt.Errorf("error getting response from %s: %w", req.URL, err)
 	}
 	defer func() { _ = resp.Body.Close() }()
 	if resp.StatusCode != http.StatusOK {
 		body, _ := ioutil.ReadAll(resp.Body)
-		return nil, fmt.Errorf("datasource returns unxeprected response code %d for %s with err %s. Reponse body %s", resp.StatusCode, req.URL, err, body)
+		return nil, fmt.Errorf("datasource returns unexpected response code %d for %s. Response body %s", resp.StatusCode, req.URL, body)
 	}
+	return processResponse(req, resp)
+}
+
+func (s *VMStorage) setPrometheusReqParams(r *http.Request, query string) {
+	if s.appendTypePrefix {
+		r.URL.Path += prometheusPrefix
+	}
+	r.URL.Path += queryPath
+	q := r.URL.Query()
+	q.Set("query", query)
+	if s.lookBack > 0 {
+		lookBack := time.Now().Add(-s.lookBack)
+		q.Set("time", fmt.Sprintf("%d", lookBack.Unix()))
+	}
+	if s.queryStep > 0 {
+		q.Set("step", s.queryStep.String())
+	}
+	r.URL.RawQuery = q.Encode()
+}
+
+func (s *VMStorage) setGraphiteReqParams(r *http.Request, query string) {
+	if s.appendTypePrefix {
+		r.URL.Path += graphitePrefix
+	}
+	r.URL.Path += graphitePath
+	q := r.URL.Query()
+	q.Set("format", "json")
+	q.Set("target", query)
+	from := "-5min"
+	if s.lookBack > 0 {
+		lookBack := time.Now().Add(-s.lookBack)
+		from = strconv.FormatInt(lookBack.Unix(), 10)
+	}
+	q.Set("from", from)
+	q.Set("until", "now")
+	r.URL.RawQuery = q.Encode()
+}
+
+const (
+	statusSuccess, statusError, rtVector = "success", "error", "vector"
+)
+
+func parsePrometheusResponse(req *http.Request, resp *http.Response) ([]Metric, error) {
 	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)
+		return nil, fmt.Errorf("error parsing prometheus metrics for %s: %w", req.URL, err)
 	}
 	if r.Status == statusError {
 		return nil, fmt.Errorf("response error, query: %s, errorType: %s, error: %s", req.URL, r.ErrorType, r.Error)
 	}
 	if r.Status != statusSuccess {
-		return nil, fmt.Errorf("unkown status:%s, Expected success or error ", r.Status)
+		return nil, fmt.Errorf("unknown 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 nil, fmt.Errorf("unknown result type:%s. Expected vector", r.Data.ResultType)
 	}
 	return r.metrics()
 }
+
+func parseGraphiteResponse(req *http.Request, resp *http.Response) ([]Metric, error) {
+	r := &graphiteResponse{}
+	if err := json.NewDecoder(resp.Body).Decode(r); err != nil {
+		return nil, fmt.Errorf("error parsing graphite metrics for %s: %w", req.URL, err)
+	}
+	return r.metrics(), nil
+}

app/vmalert/datasource/vm_test.go

@@ -4,7 +4,9 @@ import (
 	"context"
 	"net/http"
 	"net/http/httptest"
+	"strconv"
 	"testing"
+	"time"
 )
 
 var (
@@ -12,6 +14,7 @@ var (
 	basicAuthName = "foo"
 	basicAuthPass = "bar"
 	query         = "vm_rows"
+	queryRender   = "constantLine(10)"
 )
 
 func TestVMSelectQuery(t *testing.T) {
@@ -20,6 +23,13 @@ func TestVMSelectQuery(t *testing.T) {
 		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 +39,14 @@ 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:
@@ -52,31 +69,31 @@ func TestVMSelectQuery(t *testing.T) {
 
 	srv := httptest.NewServer(mux)
 	defer srv.Close()
-	am := NewVMStorage(srv.URL, basicAuthName, basicAuthPass, srv.Client())
-	if _, err := am.Query(ctx, query); err == nil {
+	am := NewVMStorage(srv.URL, basicAuthName, basicAuthPass, time.Minute, 0, false, srv.Client())
+	if _, err := am.Query(ctx, query, NewPrometheusType()); err == nil {
 		t.Fatalf("expected connection error got nil")
 	}
-	if _, err := am.Query(ctx, query); err == nil {
+	if _, err := am.Query(ctx, query, NewPrometheusType()); err == nil {
 		t.Fatalf("expected invalid response status error got nil")
 	}
-	if _, err := am.Query(ctx, query); err == nil {
+	if _, err := am.Query(ctx, query, NewPrometheusType()); err == nil {
 		t.Fatalf("expected response body error got nil")
 	}
-	if _, err := am.Query(ctx, query); err == nil {
+	if _, err := am.Query(ctx, query, NewPrometheusType()); 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 := am.Query(ctx, query, NewPrometheusType()); err == nil {
+		t.Fatalf("expected unknown status got nil")
 	}
-	if _, err := am.Query(ctx, query); err == nil {
+	if _, err := am.Query(ctx, query, NewPrometheusType()); err == nil {
 		t.Fatalf("expected non-vector resultType error  got nil")
 	}
-	m, err := am.Query(ctx, query)
+	m, err := am.Query(ctx, query, NewPrometheusType())
 	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)
 	}
 	expected := Metric{
 		Labels:    []Label{{Value: "vm_rows", Name: "__name__"}},
@@ -89,5 +106,22 @@ func TestVMSelectQuery(t *testing.T) {
 		m[0].Labels[0].Name != expected.Labels[0].Name {
 		t.Fatalf("unexpected metric %+v want %+v", m[0], expected)
 	}
-
+	m, err = am.Query(ctx, queryRender, NewGraphiteType())
+	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: "constantLine(10)", Name: "name"}},
+		Timestamp: 1611758403,
+		Value:     10,
+	}
+	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 {
+		t.Fatalf("unexpected metric %+v want %+v", m[0], expected)
+	}
 }

app/vmalert/group.go

@@ -4,26 +4,94 @@ import (
 	"context"
 	"fmt"
 	"hash/fnv"
+	"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
 
 	doneCh     chan struct{}
 	finishedCh chan struct{}
 	// channel accepts new Group obj
 	// which supposed to update current group
-	updateCh chan Group
+	updateCh chan *Group
+
+	metrics *groupMetrics
+}
+
+type groupMetrics struct {
+	iterationTotal    *counter
+	iterationDuration *summary
+}
+
+func newGroupMetrics(name, file string) *groupMetrics {
+	m := &groupMetrics{}
+	labels := fmt.Sprintf(`group=%q, file=%q`, name, file)
+	m.iterationTotal = getOrCreateCounter(fmt.Sprintf(`vmalert_iteration_total{%s}`, labels))
+	m.iterationDuration = getOrCreateSummary(fmt.Sprintf(`vmalert_iteration_duration_seconds{%s}`, labels))
+	return m
+}
+
+func newGroup(cfg config.Group, defaultInterval time.Duration, labels map[string]string) *Group {
+	g := &Group{
+		Type:        cfg.Type,
+		Name:        cfg.Name,
+		File:        cfg.File,
+		Interval:    cfg.Interval,
+		Concurrency: cfg.Concurrency,
+		Checksum:    cfg.Checksum,
+		doneCh:      make(chan struct{}),
+		finishedCh:  make(chan struct{}),
+		updateCh:    make(chan *Group),
+	}
+	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 {
+		// override rule labels with external labels
+		for k, v := range labels {
+			if prevV, ok := r.Labels[k]; ok {
+				logger.Infof("label %q=%q for rule %q.%q overwritten with external label %q=%q",
+					k, prevV, g.Name, r.Name(), k, v)
+			}
+			if r.Labels == nil {
+				r.Labels = map[string]string{}
+			}
+			r.Labels[k] = v
+		}
+		rules[i] = g.newRule(r)
+	}
+	g.Rules = rules
+	return g
+}
+
+func (g *Group) newRule(rule config.Rule) Rule {
+	if rule.Alert != "" {
+		return newAlertingRule(g, rule)
+	}
+	return newRecordingRule(g, rule)
 }
 
 // ID return unique group ID that consists of
@@ -33,51 +101,54 @@ func (g *Group) ID() uint64 {
 	hash.Write([]byte(g.File))
 	hash.Write([]byte("\xff"))
 	hash.Write([]byte(g.Name))
+	hash.Write([]byte(g.Type.Get()))
 	return hash.Sum64()
 }
 
-// Restore restores alerts state for 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, q datasource.Querier, lookback time.Duration, labels map[string]string) error {
 	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
+		}
+		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.
+// 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) {
-	rulesRegistry := make(map[string]*Rule)
+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
 			// 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 Execs
-		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
+	var newRules []Rule
 	for _, r := range g.Rules {
 		if r == nil {
 			// skip nil rules
@@ -89,23 +160,17 @@ func (g *Group) updateWith(newGroup Group) {
 	for _, nr := range rulesRegistry {
 		newRules = append(newRules, nr)
 	}
+	g.Type = newGroup.Type
+	g.Concurrency = newGroup.Concurrency
+	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() {
@@ -114,84 +179,183 @@ func (g *Group) close() {
 	}
 	close(g.doneCh)
 	<-g.finishedCh
+
+	metrics.UnregisterMetric(g.metrics.iterationDuration.name)
+	metrics.UnregisterMetric(g.metrics.iterationTotal.name)
+	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, querier datasource.Querier, nts []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(uint32(g.ID())) / (1 << 32)))
+		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{querier, nts, rw}
+	t := time.NewTicker(g.Interval)
 	defer t.Stop()
 	for {
 		select {
 		case <-ctx.Done():
 			logger.Infof("group %q: context cancelled", g.Name)
-			close(g.finishedCh)
 			return
 		case <-g.doneCh:
 			logger.Infof("group %q: received stop signal", g.Name)
-			close(g.finishedCh)
 			return
 		case ng := <-g.updateCh:
-			g.updateWith(ng)
+			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)
 
+			errs := e.execConcurrently(ctx, g.Rules, g.Concurrency, g.Interval)
+			for err := range errs {
 				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 {
-					switch a.State {
-					case notifier.StateFiring:
-						// set End to execStart + 3 intervals
-						// so notifier can resolve it automatically if `vmalert`
-						// won't be able to send resolve for some reason
-						a.End = execStart.Add(3 * interval)
-						alertsToSend = append(alertsToSend, *a)
-						pushToRW(rw, rule, a, execStart)
-					case notifier.StatePending:
-						pushToRW(rw, rule, a, execStart)
-					case notifier.StateInactive:
-						// set End to execStart to notify
-						// that it was just resolved
-						a.End = execStart
-						alertsToSend = append(alertsToSend, *a)
-					}
-				}
-				if len(alertsToSend) == 0 {
-					continue
-				}
-				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)
+					logger.Errorf("group %q: %s", g.Name, err)
 				}
 			}
-			iterationDuration.UpdateDuration(iterationStart)
+
+			g.metrics.iterationDuration.UpdateDuration(iterationStart)
 		}
 	}
 }
 
-func pushToRW(rw *remotewrite.Client, rule *Rule, a *notifier.Alert, timestamp time.Time) {
-	if rw == nil {
-		return
+type executor struct {
+	querier   datasource.Querier
+	notifiers []notifier.Notifier
+	rw        *remotewrite.Client
+}
+
+func (e *executor) execConcurrently(ctx context.Context, rules []Rule, concurrency int, interval time.Duration) chan error {
+	res := make(chan error, len(rules))
+	var returnSeries bool
+	if e.rw != nil {
+		returnSeries = true
 	}
-	tss := rule.AlertToTimeSeries(a, timestamp)
-	remoteWriteSent.Add(len(tss))
-	for _, ts := range tss {
-		if err := rw.Push(ts); err != nil {
-			remoteWriteErrors.Inc()
-			logger.Errorf("failed to push timeseries to remotewrite: %s", err)
+
+	if concurrency == 1 {
+		// fast path
+		for _, rule := range rules {
+			res <- e.exec(ctx, rule, returnSeries, interval)
+		}
+		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, returnSeries, interval)
+				<-sem
+				wg.Done()
+			}(rule)
+		}
+		wg.Wait()
+		close(res)
+	}()
+	return res
+}
+
+var (
+	execTotal    = metrics.NewCounter(`vmalert_execution_total`)
+	execErrors   = metrics.NewCounter(`vmalert_execution_errors_total`)
+	execDuration = metrics.NewSummary(`vmalert_execution_duration_seconds`)
+
+	remoteWriteErrors = metrics.NewCounter(`vmalert_remotewrite_errors_total`)
+)
+
+func (e *executor) exec(ctx context.Context, rule Rule, returnSeries bool, interval time.Duration) error {
+	execTotal.Inc()
+	execStart := time.Now()
+	defer func() {
+		execDuration.UpdateDuration(execStart)
+	}()
+
+	tss, err := rule.Exec(ctx, e.querier, returnSeries)
+	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 {
+			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:
+			// set End to execStart + 3 intervals
+			// so notifier can resolve it automatically if `vmalert`
+			// won't be able to send resolve for some reason
+			a.End = time.Now().Add(3 * interval)
+			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
+	}
+
+	alertsSent.Add(len(alerts))
+	errGr := new(utils.ErrGroup)
+	for _, nt := range e.notifiers {
+		if err := nt.Send(ctx, alerts); err != nil {
+			alertsSendErrors.Inc()
+			errGr.Add(fmt.Errorf("rule %q: failed to send alerts: %w", rule, err))
+		}
+	}
+	return errGr.Err()
 }

app/vmalert/group_test.go

@@ -2,33 +2,37 @@ package main
 
 import (
 	"context"
-	"reflect"
 	"sort"
-	"sync"
 	"testing"
 	"time"
 
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/config"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
 )
 
+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
-		// rules must be sorted by name
-		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:   config.NewPromDuration(time.Second),
 				Labels: map[string]string{
 					"bar": "baz",
 				},
@@ -37,10 +41,10 @@ func TestUpdateWith(t *testing.T) {
 					"description": "{{$labels}}",
 				},
 			}},
-			[]*Rule{{
-				Name: "bar",
-				Expr: "up > 10",
-				For:  time.Second,
+			[]config.Rule{{
+				Alert: "foo",
+				Expr:  "up > 10",
+				For:   config.NewPromDuration(time.Second),
 				Labels: map[string]string{
 					"baz": "bar",
 				},
@@ -49,56 +53,96 @@ 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: "bar"}, {Name: "baz"}, {Name: "foo"}},
-			[]*Rule{{Name: "baz"}, {Name: "foo"}},
+			[]config.Rule{
+				{Alert: "bar"},
+				{Alert: "baz"},
+				{Alert: "foo"},
+			},
+			[]config.Rule{
+				{Alert: "baz"},
+				{Record: "foo"},
+			},
 		},
 		{
 			"replace rule",
-			[]*Rule{{Name: "foo1"}},
-			[]*Rule{{Name: "foo2"}},
+			[]config.Rule{{Alert: "foo1"}},
+			[]config.Rule{{Alert: "foo2"}},
 		},
 		{
 			"replace multiple rules",
-			[]*Rule{{Name: "foo1"}, {Name: "foo2"}},
-			[]*Rule{{Name: "foo3"}, {Name: "foo4"}},
+			[]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"}
+			for _, r := range tc.currentRules {
+				r.ID = config.HashRule(r)
+				g.Rules = append(g.Rules, g.newRule(r))
+			}
+
+			ng := &Group{Name: "test"}
+			for _, r := range tc.newRules {
+				r.ID = config.HashRule(r)
+				ng.Rules = append(ng.Rules, ng.newRule(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].Name < g.Rules[j].Name
+				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)
 				}
 			}
 		})
@@ -107,11 +151,13 @@ 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]
+	const evalInterval = time.Millisecond
+	g := newGroup(groups[0], evalInterval, map[string]string{"cluster": "east-1"})
+	g.Concurrency = 2
 
 	fn := &fakeNotifier{}
 	fs := &fakeQuerier{}
@@ -120,27 +166,36 @@ func TestGroupStart(t *testing.T) {
 	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
+	// 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
 	alert1.ID = hash(m1)
 
-	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
+	// 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
 	alert2.ID = hash(m2)
 
-	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(), fs, []notifier.Notifier{fn}, nil)
 		close(finished)
 	}()
 
@@ -166,52 +221,3 @@ func TestGroupStart(t *testing.T) {
 	g.close()
 	<-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))
-	}
-	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)
-		}
-	}
-}
-
-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 +1,232 @@
+package main
+
+import (
+	"context"
+	"fmt"
+	"reflect"
+	"sort"
+	"sync"
+	"testing"
+
+	"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) Query(_ context.Context, _ string, _ datasource.Type) ([]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 (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 {
+	t.Helper()
+	m := metricWithLabels(t, labels...)
+	m.Value = value
+	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{}
+	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)
+	}
+	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; got %d", len(expTS.Labels), len(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

@@ -4,14 +4,16 @@ 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"
@@ -24,78 +26,57 @@ 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")
+	httpListenAddr     = flag.String("httpListenAddr", ":8880", "Address to listen for http connections")
+	evaluationInterval = flag.Duration("evaluationInterval", time.Minute, "How often to evaluate the rules")
 
-	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")
-	remoteWriteMaxQueueSize = flag.Int("remoteWrite.maxQueueSize", 10e3, "Defines the max number of pending datapoints to remote write endpoint")
+	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")
+	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.")
 
-	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."+
 		" For example, if lookback=1h then range from now() to now()-1h will be scanned.")
 
-	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")
+	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.")
 )
 
 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())
-	eu, err := getExternalURL(*externalURL, *httpListenAddr, httpserver.IsTLS())
-	if err != nil {
-		logger.Fatalf("can not get 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{}),
-	}
-	if *remoteWriteURL != "" {
-		c, err := remotewrite.NewClient(ctx, remotewrite.Config{
-			Addr:          *remoteWriteURL,
-			MaxQueueSize:  *remoteWriteMaxQueueSize,
-			FlushInterval: *evaluationInterval,
-			BasicAuthUser: *remoteWriteUsername,
-			BasicAuthPass: *remoteWritePassword,
-		})
+	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 init remotewrite client: %s", err)
+			logger.Fatalf(err.Error())
 		}
-		manager.rw = c
+		if len(groups) == 0 {
+			logger.Fatalf("No rules for validation. Please specify path to file(s) with alerting and/or recording rules using `-rule` flag")
+		}
+		return
 	}
-	if *remoteReadURL != "" {
-		manager.rr = datasource.NewVMStorage(*remoteReadURL, *remoteReadUsername, *remoteReadPassword, &http.Client{})
+	ctx, cancel := context.WithCancel(context.Background())
+	manager, err := newManager(ctx)
+	if err != nil {
+		logger.Fatalf("failed to init: %s", err)
 	}
-
-	if err := manager.start(ctx, *rulePath, *validateTemplates); err != nil {
+	if err := manager.start(ctx, *rulePath, *validateTemplates, *validateExpressions); err != nil {
 		logger.Fatalf("failed to start: %s", err)
 	}
 
@@ -108,7 +89,7 @@ func main() {
 			<-sigHup
 			configReloads.Inc()
 			logger.Infof("SIGHUP received. Going to reload rules %q ...", *rulePath)
-			if err := manager.update(ctx, *rulePath, *validateTemplates, false); err != nil {
+			if err := manager.update(ctx, *rulePath, *validateTemplates, *validateExpressions, false); err != nil {
 				configReloadErrors.Inc()
 				configSuccess.Set(0)
 				logger.Errorf("error while reloading rules: %s", err)
@@ -139,6 +120,56 @@ var (
 	configTimestamp    = metrics.NewCounter(`vmalert_config_last_reload_success_timestamp_seconds`)
 )
 
+func newManager(ctx context.Context) (*manager, error) {
+	q, err := datasource.Init()
+	if err != nil {
+		return nil, fmt.Errorf("failed to init datasource: %w", err)
+	}
+	eu, err := getExternalURL(*externalURL, *httpListenAddr, httpserver.IsTLS())
+	if err != nil {
+		return nil, fmt.Errorf("failed to init `external.url`: %w", err)
+	}
+	notifier.InitTemplateFunc(eu)
+	aug, err := getAlertURLGenerator(eu, *externalAlertSource, *validateTemplates)
+	if err != nil {
+		return nil, fmt.Errorf("failed to init `external.alert.source`: %w", err)
+	}
+	nts, err := notifier.Init(aug)
+	if err != nil {
+		return nil, fmt.Errorf("failed to init notifier: %w", err)
+	}
+
+	manager := &manager{
+		groups:    make(map[uint64]*Group),
+		querier:   q,
+		notifiers: nts,
+		labels:    map[string]string{},
+	}
+	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
+
+	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)
+		}
+		manager.labels[s[:n]] = s[n+1:]
+	}
+	return manager, nil
+}
+
 func getExternalURL(externalURL, httpListenAddr string, isSecure bool) (*url.URL, error) {
 	if externalURL != "" {
 		return url.Parse(externalURL)
@@ -158,13 +189,36 @@ 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://victoriametrics.github.io/vmalert.html .
+`
+	flagutil.Usage(s)
 }

app/vmalert/main_test.go

@@ -0,0 +1,53 @@
+package main
+
+import (
+	"fmt"
+	"net/url"
+	"os"
+	"testing"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
+)
+
+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))
+	}
+}

app/vmalert/manager.go

@@ -6,26 +6,29 @@ import (
 	"strings"
 	"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
+	querier   datasource.Querier
+	notifiers []notifier.Notifier
 
 	rw *remotewrite.Client
 	rr datasource.Querier
 
-	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 +38,19 @@ 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, path []string, validateTpl, validateExpr bool) error {
+	return m.update(ctx, path, validateTpl, validateExpr, true)
 }
 
 func (m *manager) close() {
@@ -56,9 +63,9 @@ func (m *manager) close() {
 	m.wg.Wait()
 }
 
-func (m *manager) startGroup(ctx context.Context, group Group, restore bool) {
+func (m *manager) startGroup(ctx context.Context, group *Group, restore bool) {
 	if restore && m.rr != nil {
-		err := group.Restore(ctx, m.rr, *remoteReadLookBack)
+		err := group.Restore(ctx, m.rr, *remoteReadLookBack, m.labels)
 		if err != nil {
 			logger.Errorf("error while restoring state for group %q: %s", group.Name, err)
 		}
@@ -67,42 +74,86 @@ 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.querier, m.notifiers, m.rw)
 		m.wg.Done()
 	}()
-	m.groups[id] = &group
+	m.groups[id] = group
 }
 
-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)
+func (m *manager) update(ctx context.Context, path []string, validateTpl, validateExpr, restore bool) error {
+	logger.Infof("reading rules configuration file from %q", strings.Join(path, ";"))
+	groupsCfg, err := config.Parse(path, validateTpl, validateExpr)
 	if err != nil {
-		return fmt.Errorf("cannot parse configuration file: %s", err)
+		return fmt.Errorf("cannot parse configuration file: %w", err)
 	}
 
-	groupsRegistry := make(map[uint64]Group)
-	for _, ng := range newGroups {
+	groupsRegistry := make(map[uint64]*Group)
+	for _, cfg := range groupsCfg {
+		ng := newGroup(cfg, *evaluationInterval, m.labels)
 		groupsRegistry[ng.ID()] = ng
 	}
 
+	type updateItem struct {
+		old *Group
+		new *Group
+	}
+	var toUpdate []updateItem
+
 	m.groupsMu.Lock()
 	for _, og := range m.groups {
 		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.updateCh <- 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)
 	}
 	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,
+	}
+	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
+}

app/vmalert/manager_test.go

@@ -3,22 +3,32 @@ package main
 import (
 	"context"
 	"math/rand"
-	"strings"
+	"net/url"
+	"os"
 	"sync"
 	"testing"
 	"time"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
 )
 
-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)
+	err := m.update(context.Background(), path, true, true, false)
+	if err != nil {
+		t.Fatalf("expected to load succesfully with empty rules dir; got err instead: %v", err)
 	}
 }
 
@@ -27,17 +37,21 @@ func TestManagerUpdateError(t *testing.T) {
 // Should be executed with -race flag
 func TestManagerUpdateConcurrent(t *testing.T) {
 	m := &manager{
-		groups:   make(map[uint64]*Group),
-		storage:  &fakeQuerier{},
-		notifier: &fakeNotifier{},
+		groups:    make(map[uint64]*Group),
+		querier:   &fakeQuerier{},
+		notifiers: []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",
 	}
 	*evaluationInterval = time.Millisecond
-	if err := m.start(context.Background(), []string{paths[0]}, true); err != nil {
+	if err := m.start(context.Background(), []string{paths[0]}, true, true); err != nil {
 		t.Fatalf("failed to start: %s", err)
 	}
 
@@ -51,10 +65,7 @@ func TestManagerUpdateConcurrent(t *testing.T) {
 			for i := 0; i < iterations; i++ {
 				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)
-				}
+				_ = m.update(context.Background(), path, true, true, false)
 			}
 		}()
 	}
@@ -64,6 +75,53 @@ 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)",
+		}
+		ExampleAlertGraphite = &AlertingRule{
+			Name: "up graphite",
+			Expr: "filterSeries(time('host.1',20),'>','0')",
+			Type: datasource.NewGraphiteType(),
+			For:  defaultEvalInterval,
+		}
+		ExampleAlertGraphite2 = &AlertingRule{
+			Name: "up",
+			Expr: "filterSeries(time('host.2',20),'>','0')",
+			Type: datasource.NewGraphiteType(),
+			For:  defaultEvalInterval,
+		}
+	)
+
 	testCases := []struct {
 		name       string
 		initPath   string
@@ -72,64 +130,126 @@ 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{"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,
+					},
+				},
+			},
+		},
+		{
+			name:       "update prometheus to graphite type",
+			initPath:   "config/testdata/dir/rules-update0-good.rules",
+			updatePath: "config/testdata/dir/rules-update1-good.rules",
+			want: []*Group{
+				{
+					File:     "config/testdata/dir/rules-update1-good.rules",
+					Interval: defaultEvalInterval,
+					Type:     datasource.NewGraphiteType(),
+					Name:     "TestUpdateGroup",
+					Rules: []Rule{
+						ExampleAlertGraphite2,
+						ExampleAlertGraphite,
+					},
+				},
+			},
+		},
 	}
 	for _, tc := range testCases {
 		t.Run(tc.name, func(t *testing.T) {
 			ctx, cancel := context.WithCancel(context.TODO())
-			m := &manager{groups: make(map[uint64]*Group), storage: &fakeQuerier{}}
+			m := &manager{groups: make(map[uint64]*Group), querier: &fakeQuerier{}}
 			path := []string{tc.initPath}
-			if err := m.update(ctx, path, true, false); err != nil {
+			if err := m.update(ctx, path, true, true, false); err != nil {
 				t.Fatalf("failed to complete initial rules update: %s", err)
 			}
 
 			path = []string{tc.updatePath}
-			_ = m.update(ctx, path, true, false)
+			_ = m.update(ctx, path, true, true, false)
 			if len(tc.want) != len(m.groups) {
 				t.Fatalf("\nwant number of groups: %d;\ngot: %d ", len(tc.want), len(m.groups))
 			}
@@ -139,7 +259,7 @@ 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()
@@ -147,17 +267,3 @@ 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))
-	}
-	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)
-		}
-	}
-}

app/vmalert/metrics.go

@@ -0,0 +1,39 @@
+package main
+
+import "github.com/VictoriaMetrics/metrics"
+
+type gauge struct {
+	name string
+	*metrics.Gauge
+}
+
+func getOrCreateGauge(name string, f func() float64) *gauge {
+	return &gauge{
+		name:  name,
+		Gauge: metrics.GetOrCreateGauge(name, f),
+	}
+}
+
+type counter struct {
+	name string
+	*metrics.Counter
+}
+
+func getOrCreateCounter(name string) *counter {
+	return &counter{
+		name:    name,
+		Counter: metrics.GetOrCreateCounter(name),
+	}
+}
+
+type summary struct {
+	name string
+	*metrics.Summary
+}
+
+func getOrCreateSummary(name string) *summary {
+	return &summary{
+		name:    name,
+		Summary: metrics.GetOrCreateSummary(name),
+	}
+}

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

@@ -7,6 +7,8 @@ import (
 	"strings"
 	"text/template"
 	"time"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/utils"
 )
 
 // Alert the triggered alert
@@ -50,7 +52,8 @@ func (as AlertState) String() string {
 	return "inactive"
 }
 
-type alertTplData struct {
+// AlertTplData is used to execute templating
+type AlertTplData struct {
 	Labels map[string]string
 	Value  float64
 	Expr   string
@@ -58,50 +61,58 @@ type alertTplData struct {
 
 const tplHeader = `{{ $value := .Value }}{{ $labels := .Labels }}{{ $expr := .Expr }}`
 
-// ExecTemplate executes the Alert template for give
+// ExecTemplate executes the Alert template for given
 // map of annotations.
-func (a *Alert) ExecTemplate(annotations map[string]string) (map[string]string, error) {
-	tplData := alertTplData{Value: a.Value, Labels: a.Labels, Expr: a.Expr}
-	return templateAnnotations(annotations, tplHeader, tplData)
+// Every alert could have a different datasource, so function
+// requires a queryFunction as an argument.
+func (a *Alert) ExecTemplate(q QueryFn, annotations map[string]string) (map[string]string, error) {
+	tplData := AlertTplData{Value: a.Value, Labels: a.Labels, Expr: a.Expr}
+	return templateAnnotations(annotations, tplData, funcsWithQuery(q))
+}
+
+// ExecTemplate executes the given template for given annotations map.
+func ExecTemplate(q QueryFn, annotations map[string]string, tpl AlertTplData) (map[string]string, error) {
+	return templateAnnotations(annotations, tpl, funcsWithQuery(q))
 }
 
 // ValidateTemplates validate annotations for possible template error, uses empty data for template population
 func ValidateTemplates(annotations map[string]string) error {
-	_, err := templateAnnotations(annotations, tplHeader, alertTplData{
+	_, err := templateAnnotations(annotations, AlertTplData{
 		Labels: map[string]string{},
 		Value:  0,
-	})
+	}, tmplFunc)
 	return err
 }
 
-func templateAnnotations(annotations map[string]string, header string, data alertTplData) (map[string]string, error) {
+func templateAnnotations(annotations map[string]string, data AlertTplData, funcs template.FuncMap) (map[string]string, error) {
 	var builder strings.Builder
 	var buf bytes.Buffer
-	eg := errGroup{}
+	eg := new(utils.ErrGroup)
 	r := make(map[string]string, len(annotations))
 	for key, text := range annotations {
 		r[key] = text
 		buf.Reset()
 		builder.Reset()
-		builder.Grow(len(header) + len(text))
-		builder.WriteString(header)
+		builder.Grow(len(tplHeader) + len(text))
+		builder.WriteString(tplHeader)
 		builder.WriteString(text)
-		if err := templateAnnotation(&buf, builder.String(), data); err != nil {
-			eg.errs = append(eg.errs, fmt.Sprintf("key %s, template %s:%s", key, text, err))
+		if err := templateAnnotation(&buf, builder.String(), data, funcs); err != nil {
+			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)
+func templateAnnotation(dst io.Writer, text string, data AlertTplData, funcs template.FuncMap) error {
+	t := template.New("").Funcs(funcs).Option("missingkey=zero")
+	tpl, err := t.Parse(text)
 	if err != nil {
-		return fmt.Errorf("error parsing annotation:%w", err)
+		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

@@ -1,13 +1,12 @@
 package notifier
 
 import (
-	"net/url"
 	"testing"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
 )
 
 func TestAlert_ExecTemplate(t *testing.T) {
-	u, _ := url.Parse("https://victoriametrics.com/path")
-	InitTemplateFunc(u)
 	testCases := []struct {
 		name        string
 		alert       *Alert
@@ -63,11 +62,41 @@ func TestAlert_ExecTemplate(t *testing.T) {
 				"exprEscapedPath":  "vm_rows%7B%5C%22label%5C%22=%5C%22bar%5C%22%7D%3E0",
 			},
 		},
+		{
+			name:  "query",
+			alert: &Alert{Expr: `vm_rows{"label"="bar"}>0`},
+			annotations: map[string]string{
+				"summary": `{{ query "foo" | first | value }}`,
+				"desc":    `{{ range query "bar" }}{{ . | label "foo" }} {{ . | value }};{{ end }}`,
+			},
+			expTpl: map[string]string{
+				"summary": "1",
+				"desc":    "bar 1;garply 2;",
+			},
+		},
 	}
 
+	qFn := func(q string) ([]datasource.Metric, error) {
+		return []datasource.Metric{
+			{
+				Labels: []datasource.Label{
+					{Name: "foo", Value: "bar"},
+					{Name: "baz", Value: "qux"},
+				},
+				Value: 1,
+			},
+			{
+				Labels: []datasource.Label{
+					{Name: "foo", Value: "garply"},
+					{Name: "baz", Value: "fred"},
+				},
+				Value: 2,
+			},
+		}, nil
+	}
 	for _, tc := range testCases {
 		t.Run(tc.name, func(t *testing.T) {
-			tpl, err := tc.alert.ExecTemplate(tc.annotations)
+			tpl, err := tc.alert.ExecTemplate(qFn, tc.annotations)
 			if err != nil {
 				t.Fatal(err)
 			}

app/vmalert/notifier/alertmanager.go

@@ -12,9 +12,11 @@ import (
 // AlertManager represents integration provider with Prometheus alert manager
 // https://github.com/prometheus/alertmanager
 type AlertManager struct {
-	alertURL string
-	argFunc  AlertURLGenerator
-	client   *http.Client
+	alertURL      string
+	basicAuthUser string
+	basicAuthPass string
+	argFunc       AlertURLGenerator
+	client        *http.Client
 }
 
 // Send an alert or resolve message
@@ -26,8 +28,11 @@ func (am *AlertManager) Send(ctx context.Context, alerts []Alert) error {
 	if err != nil {
 		return err
 	}
-	req.Header.Set("Content-Type", "application/json")
+	req.Header.Set("Content-Type", "application/json; charset=utf-8")
 	req = req.WithContext(ctx)
+	if am.basicAuthPass != "" {
+		req.SetBasicAuth(am.basicAuthUser, am.basicAuthPass)
+	}
 	resp, err := am.client.Do(req)
 	if err != nil {
 		return err
@@ -38,7 +43,7 @@ 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.alertURL, err)
 		}
 		return fmt.Errorf("invalid SC %d from %q; response body: %s", resp.StatusCode, am.alertURL, string(body))
 	}
@@ -46,15 +51,18 @@ func (am *AlertManager) Send(ctx context.Context, alerts []Alert) error {
 }
 
 // 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 {
+func NewAlertManager(alertManagerURL, user, pass string, fn AlertURLGenerator, c *http.Client) *AlertManager {
+	addr := strings.TrimSuffix(alertManagerURL, "/") + alertManagerPath
 	return &AlertManager{
-		alertURL: strings.TrimSuffix(alertManagerURL, "/") + alertManagerPath,
-		argFunc:  fn,
-		client:   c,
+		alertURL:      addr,
+		argFunc:       fn,
+		client:        c,
+		basicAuthUser: user,
+		basicAuthPass: pass,
 	}
 }

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

@@ -6,126 +6,125 @@ package notifier
 
 //line app/vmalert/notifier/alertmanager_request.qtpl:1
 import (
-	"strconv"
 	"time"
 )
 
-//line app/vmalert/notifier/alertmanager_request.qtpl:7
+//line app/vmalert/notifier/alertmanager_request.qtpl:6
 import (
 	qtio422016 "io"
 
 	qt422016 "github.com/valyala/quicktemplate"
 )
 
-//line app/vmalert/notifier/alertmanager_request.qtpl:7
+//line app/vmalert/notifier/alertmanager_request.qtpl:6
 var (
 	_ = qtio422016.Copy
 	_ = qt422016.AcquireByteBuffer
 )
 
-//line app/vmalert/notifier/alertmanager_request.qtpl:7
-func streamamRequest(qw422016 *qt422016.Writer, alerts []Alert, generatorURL func(string, string) string) {
-//line app/vmalert/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 app/vmalert/notifier/alertmanager_request.qtpl:9
+//line app/vmalert/notifier/alertmanager_request.qtpl:8
 	for i, alert := range alerts {
-//line app/vmalert/notifier/alertmanager_request.qtpl:9
+//line app/vmalert/notifier/alertmanager_request.qtpl:8
 		qw422016.N().S(`{"startsAt":`)
-//line app/vmalert/notifier/alertmanager_request.qtpl:11
+//line app/vmalert/notifier/alertmanager_request.qtpl:10
 		qw422016.N().Q(alert.Start.Format(time.RFC3339Nano))
-//line app/vmalert/notifier/alertmanager_request.qtpl:11
+//line app/vmalert/notifier/alertmanager_request.qtpl:10
 		qw422016.N().S(`,"generatorURL":`)
-//line app/vmalert/notifier/alertmanager_request.qtpl:12
-		qw422016.N().Q(generatorURL(strconv.FormatUint(alert.GroupID, 10), strconv.FormatUint(alert.ID, 10)))
-//line app/vmalert/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 app/vmalert/notifier/alertmanager_request.qtpl:13
+//line app/vmalert/notifier/alertmanager_request.qtpl:12
 		if !alert.End.IsZero() {
-//line app/vmalert/notifier/alertmanager_request.qtpl:13
+//line app/vmalert/notifier/alertmanager_request.qtpl:12
 			qw422016.N().S(`"endsAt":`)
-//line app/vmalert/notifier/alertmanager_request.qtpl:14
+//line app/vmalert/notifier/alertmanager_request.qtpl:13
 			qw422016.N().Q(alert.End.Format(time.RFC3339Nano))
+//line app/vmalert/notifier/alertmanager_request.qtpl:13
+			qw422016.N().S(`,`)
 //line app/vmalert/notifier/alertmanager_request.qtpl:14
-			qw422016.N().S(`,`)
-//line app/vmalert/notifier/alertmanager_request.qtpl:15
 		}
-//line app/vmalert/notifier/alertmanager_request.qtpl:15
+//line app/vmalert/notifier/alertmanager_request.qtpl:14
 		qw422016.N().S(`"labels": {"alertname":`)
-//line app/vmalert/notifier/alertmanager_request.qtpl:17
+//line app/vmalert/notifier/alertmanager_request.qtpl:16
 		qw422016.N().Q(alert.Name)
-//line app/vmalert/notifier/alertmanager_request.qtpl:18
+//line app/vmalert/notifier/alertmanager_request.qtpl:17
 		for k, v := range alert.Labels {
-//line app/vmalert/notifier/alertmanager_request.qtpl:18
+//line app/vmalert/notifier/alertmanager_request.qtpl:17
 			qw422016.N().S(`,`)
-//line app/vmalert/notifier/alertmanager_request.qtpl:19
+//line app/vmalert/notifier/alertmanager_request.qtpl:18
 			qw422016.N().Q(k)
-//line app/vmalert/notifier/alertmanager_request.qtpl:19
+//line app/vmalert/notifier/alertmanager_request.qtpl:18
 			qw422016.N().S(`:`)
-//line app/vmalert/notifier/alertmanager_request.qtpl:19
+//line app/vmalert/notifier/alertmanager_request.qtpl:18
 			qw422016.N().Q(v)
-//line app/vmalert/notifier/alertmanager_request.qtpl:20
+//line app/vmalert/notifier/alertmanager_request.qtpl:19
 		}
-//line app/vmalert/notifier/alertmanager_request.qtpl:20
+//line app/vmalert/notifier/alertmanager_request.qtpl:19
 		qw422016.N().S(`},"annotations": {`)
-//line app/vmalert/notifier/alertmanager_request.qtpl:23
+//line app/vmalert/notifier/alertmanager_request.qtpl:22
 		c := len(alert.Annotations)
 
-//line app/vmalert/notifier/alertmanager_request.qtpl:24
+//line app/vmalert/notifier/alertmanager_request.qtpl:23
 		for k, v := range alert.Annotations {
-//line app/vmalert/notifier/alertmanager_request.qtpl:25
+//line app/vmalert/notifier/alertmanager_request.qtpl:24
 			c = c - 1
 
-//line app/vmalert/notifier/alertmanager_request.qtpl:26
+//line app/vmalert/notifier/alertmanager_request.qtpl:25
 			qw422016.N().Q(k)
-//line app/vmalert/notifier/alertmanager_request.qtpl:26
+//line app/vmalert/notifier/alertmanager_request.qtpl:25
 			qw422016.N().S(`:`)
-//line app/vmalert/notifier/alertmanager_request.qtpl:26
+//line app/vmalert/notifier/alertmanager_request.qtpl:25
 			qw422016.N().Q(v)
-//line app/vmalert/notifier/alertmanager_request.qtpl:26
+//line app/vmalert/notifier/alertmanager_request.qtpl:25
 			if c > 0 {
-//line app/vmalert/notifier/alertmanager_request.qtpl:26
+//line app/vmalert/notifier/alertmanager_request.qtpl:25
 				qw422016.N().S(`,`)
-//line app/vmalert/notifier/alertmanager_request.qtpl:26
+//line app/vmalert/notifier/alertmanager_request.qtpl:25
 			}
-//line app/vmalert/notifier/alertmanager_request.qtpl:27
+//line app/vmalert/notifier/alertmanager_request.qtpl:26
 		}
-//line app/vmalert/notifier/alertmanager_request.qtpl:27
+//line app/vmalert/notifier/alertmanager_request.qtpl:26
 		qw422016.N().S(`}}`)
-//line app/vmalert/notifier/alertmanager_request.qtpl:30
+//line app/vmalert/notifier/alertmanager_request.qtpl:29
 		if i != len(alerts)-1 {
-//line app/vmalert/notifier/alertmanager_request.qtpl:30
+//line app/vmalert/notifier/alertmanager_request.qtpl:29
 			qw422016.N().S(`,`)
-//line app/vmalert/notifier/alertmanager_request.qtpl:30
+//line app/vmalert/notifier/alertmanager_request.qtpl:29
 		}
-//line app/vmalert/notifier/alertmanager_request.qtpl:31
+//line app/vmalert/notifier/alertmanager_request.qtpl:30
 	}
-//line app/vmalert/notifier/alertmanager_request.qtpl:31
+//line app/vmalert/notifier/alertmanager_request.qtpl:30
 	qw422016.N().S(`]`)
-//line app/vmalert/notifier/alertmanager_request.qtpl:33
+//line app/vmalert/notifier/alertmanager_request.qtpl:32
 }
 
-//line app/vmalert/notifier/alertmanager_request.qtpl:33
-func writeamRequest(qq422016 qtio422016.Writer, alerts []Alert, generatorURL func(string, string) string) {
-//line app/vmalert/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 app/vmalert/notifier/alertmanager_request.qtpl:33
+//line app/vmalert/notifier/alertmanager_request.qtpl:32
 	streamamRequest(qw422016, alerts, generatorURL)
-//line app/vmalert/notifier/alertmanager_request.qtpl:33
+//line app/vmalert/notifier/alertmanager_request.qtpl:32
 	qt422016.ReleaseWriter(qw422016)
-//line app/vmalert/notifier/alertmanager_request.qtpl:33
+//line app/vmalert/notifier/alertmanager_request.qtpl:32
 }
 
-//line app/vmalert/notifier/alertmanager_request.qtpl:33
-func amRequest(alerts []Alert, generatorURL func(string, string) string) string {
-//line app/vmalert/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 app/vmalert/notifier/alertmanager_request.qtpl:33
+//line app/vmalert/notifier/alertmanager_request.qtpl:32
 	writeamRequest(qb422016, alerts, generatorURL)
-//line app/vmalert/notifier/alertmanager_request.qtpl:33
+//line app/vmalert/notifier/alertmanager_request.qtpl:32
 	qs422016 := string(qb422016.B)
-//line app/vmalert/notifier/alertmanager_request.qtpl:33
+//line app/vmalert/notifier/alertmanager_request.qtpl:32
 	qt422016.ReleaseByteBuffer(qb422016)
-//line app/vmalert/notifier/alertmanager_request.qtpl:33
+//line app/vmalert/notifier/alertmanager_request.qtpl:32
 	return qs422016
-//line app/vmalert/notifier/alertmanager_request.qtpl:33
+//line app/vmalert/notifier/alertmanager_request.qtpl:32
 }

app/vmalert/notifier/alertmanager_test.go

@@ -5,17 +5,27 @@ import (
 	"encoding/json"
 	"net/http"
 	"net/http/httptest"
+	"strconv"
 	"testing"
 	"time"
 )
 
 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)
@@ -42,23 +52,23 @@ 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
+	am := NewAlertManager(srv.URL, baUser, baPass, func(alert Alert) string {
+		return strconv.FormatUint(alert.GroupID, 10) + "/" + strconv.FormatUint(alert.ID, 10)
 	}, srv.Client())
 	if err := am.Send(context.Background(), []Alert{{}, {}}); err == nil {
 		t.Error("expected connection error got nil")

app/vmalert/notifier/init.go

@@ -0,0 +1,45 @@
+package notifier
+
+import (
+	"fmt"
+	"net/http"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/utils"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
+)
+
+var (
+	addrs             = flagutil.NewArray("notifier.url", "Prometheus alertmanager URL. Required parameter. e.g. http://127.0.0.1:9093")
+	basicAuthUsername = flagutil.NewArray("notifier.basicAuth.username", "Optional basic auth username for -notifier.url")
+	basicAuthPassword = flagutil.NewArray("notifier.basicAuth.password", "Optional basic auth password for -notifier.url")
+
+	tlsInsecureSkipVerify = flagutil.NewArrayBool("notifier.tlsInsecureSkipVerify", "Whether to skip tls verification when connecting to -notifier.url")
+	tlsCertFile           = flagutil.NewArray("notifier.tlsCertFile", "Optional path to client-side TLS certificate file to use when connecting to -notifier.url")
+	tlsKeyFile            = flagutil.NewArray("notifier.tlsKeyFile", "Optional path to client-side TLS certificate key to use when connecting to -notifier.url")
+	tlsCAFile             = flagutil.NewArray("notifier.tlsCAFile", "Optional path to TLS CA file to use for verifying connections to -notifier.url. "+
+		"By default system CA is used")
+	tlsServerName = flagutil.NewArray("notifier.tlsServerName", "Optional TLS server name to use for connections to -notifier.url. "+
+		"By default the server name from -notifier.url is used")
+)
+
+// Init creates a Notifier object based on provided flags.
+func Init(gen AlertURLGenerator) ([]Notifier, error) {
+	if len(*addrs) == 0 {
+		return nil, fmt.Errorf("at least one `-notifier.url` must be set")
+	}
+
+	var notifiers []Notifier
+	for i, addr := range *addrs {
+		cert, key := tlsCertFile.GetOptionalArg(i), tlsKeyFile.GetOptionalArg(i)
+		ca, serverName := tlsCAFile.GetOptionalArg(i), tlsServerName.GetOptionalArg(i)
+		tr, err := utils.Transport(addr, cert, key, ca, serverName, tlsInsecureSkipVerify.GetOptionalArg(i))
+		if err != nil {
+			return nil, fmt.Errorf("failed to create transport: %w", err)
+		}
+		user, pass := basicAuthUsername.GetOptionalArg(i), basicAuthPassword.GetOptionalArg(i)
+		am := NewAlertManager(addr, user, pass, gen, &http.Client{Transport: tr})
+		notifiers = append(notifiers, am)
+	}
+
+	return notifiers, nil
+}

app/vmalert/notifier/package_test.go

@@ -0,0 +1,13 @@
+package notifier
+
+import (
+	"net/url"
+	"os"
+	"testing"
+)
+
+func TestMain(m *testing.M) {
+	u, _ := url.Parse("https://victoriametrics.com/path")
+	InitTemplateFunc(u)
+	os.Exit(m.Run())
+}

app/vmalert/notifier/template_func.go

@@ -14,21 +14,40 @@
 package notifier
 
 import (
+	"errors"
 	"fmt"
-	html_template "html/template"
 	"math"
 	"net/url"
 	"regexp"
 	"strings"
-	text_template "text/template"
 	"time"
+
+	htmlTpl "html/template"
+	textTpl "text/template"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
 )
 
-var tmplFunc text_template.FuncMap
+// QueryFn is used to wrap a call to datasource into simple-to-use function
+// for templating functions.
+type QueryFn func(query string) ([]datasource.Metric, error)
 
-// InitTemplateFunc returns template helper functions
+func funcsWithQuery(query QueryFn) textTpl.FuncMap {
+	fm := make(textTpl.FuncMap)
+	for k, fn := range tmplFunc {
+		fm[k] = fn
+	}
+	fm["query"] = func(q string) ([]datasource.Metric, error) {
+		return query(q)
+	}
+	return fm
+}
+
+var tmplFunc textTpl.FuncMap
+
+// InitTemplateFunc initiates template helper functions
 func InitTemplateFunc(externalURL *url.URL) {
-	tmplFunc = text_template.FuncMap{
+	tmplFunc = textTpl.FuncMap{
 		"args": func(args ...interface{}) map[string]interface{} {
 			result := make(map[string]interface{})
 			for i, a := range args {
@@ -40,8 +59,8 @@ func InitTemplateFunc(externalURL *url.URL) {
 			re := regexp.MustCompile(pattern)
 			return re.ReplaceAllString(text, repl)
 		},
-		"safeHtml": func(text string) html_template.HTML {
-			return html_template.HTML(text)
+		"safeHtml": func(text string) htmlTpl.HTML {
+			return htmlTpl.HTML(text)
 		},
 		"match":   regexp.MatchString,
 		"title":   strings.Title,
@@ -148,9 +167,33 @@ func InitTemplateFunc(externalURL *url.URL) {
 		"queryEscape": func(q string) string {
 			return url.QueryEscape(q)
 		},
+		"crlfEscape": func(q string) string {
+			q = strings.Replace(q, "\n", `\n`, -1)
+			return strings.Replace(q, "\r", `\r`, -1)
+		},
 		"quotesEscape": func(q string) string {
 			return strings.Replace(q, `"`, `\"`, -1)
 		},
+		// query function supposed to be substituted at funcsWithQuery().
+		// it is present here only for validation purposes, when there is no
+		// provided datasource.
+		"query": func(q string) ([]datasource.Metric, error) {
+			// return non-empty slice to pass validation with chained functions in template
+			// see issue #989 for details
+			return []datasource.Metric{{}}, nil
+		},
+		"first": func(metrics []datasource.Metric) (datasource.Metric, error) {
+			if len(metrics) > 0 {
+				return metrics[0], nil
+			}
+			return datasource.Metric{}, errors.New("first() called on vector with no elements")
+		},
+		"label": func(label string, m datasource.Metric) string {
+			return m.Label(label)
+		},
+		"value": func(m datasource.Metric) float64 {
+			return m.Value
+		},
 	}
 }
 

app/vmalert/notifier/utils.go

@@ -1,21 +0,0 @@
-package notifier
-
-import (
-	"fmt"
-	"strings"
-)
-
-type errGroup struct {
-	errs []string
-}
-
-func (eg *errGroup) err() error {
-	if eg == nil || len(eg.errs) == 0 {
-		return nil
-	}
-	return eg
-}
-
-func (eg *errGroup) Error() string {
-	return fmt.Sprintf("errors:%s", strings.Join(eg.errs, "\n"))
-}

app/vmalert/recording.go

@@ -0,0 +1,173 @@
+package main
+
+import (
+	"context"
+	"fmt"
+	"hash/fnv"
+	"sort"
+	"sync"
+	"time"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/config"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
+	"github.com/VictoriaMetrics/metrics"
+)
+
+// RecordingRule is a Rule that supposed
+// to evaluate configured Expression and
+// return TimeSeries as result.
+type RecordingRule struct {
+	Type    datasource.Type
+	RuleID  uint64
+	Name    string
+	Expr    string
+	Labels  map[string]string
+	GroupID uint64
+
+	// guard status fields
+	mu sync.RWMutex
+	// 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
+
+	metrics *recordingRuleMetrics
+}
+
+type recordingRuleMetrics struct {
+	errors *gauge
+}
+
+// String implements Stringer interface
+func (rr *RecordingRule) String() string {
+	return rr.Name
+}
+
+// ID returns unique Rule ID
+// within the parent Group.
+func (rr *RecordingRule) ID() uint64 {
+	return rr.RuleID
+}
+
+func newRecordingRule(group *Group, cfg config.Rule) *RecordingRule {
+	rr := &RecordingRule{
+		Type:    cfg.Type,
+		RuleID:  cfg.ID,
+		Name:    cfg.Record,
+		Expr:    cfg.Expr,
+		Labels:  cfg.Labels,
+		GroupID: group.ID(),
+		metrics: &recordingRuleMetrics{},
+	}
+
+	labels := fmt.Sprintf(`recording=%q, group=%q, id="%d"`, rr.Name, group.Name, rr.ID())
+	rr.metrics.errors = getOrCreateGauge(fmt.Sprintf(`vmalert_recording_rules_error{%s}`, labels),
+		func() float64 {
+			rr.mu.Lock()
+			defer rr.mu.Unlock()
+			if rr.lastExecError == nil {
+				return 0
+			}
+			return 1
+		})
+	return rr
+}
+
+// Close unregisters rule metrics
+func (rr *RecordingRule) Close() {
+	metrics.UnregisterMetric(rr.metrics.errors.name)
+}
+
+// Exec executes RecordingRule expression via the given Querier.
+func (rr *RecordingRule) Exec(ctx context.Context, q datasource.Querier, series bool) ([]prompbmarshal.TimeSeries, error) {
+	if !series {
+		return nil, nil
+	}
+
+	qMetrics, err := q.Query(ctx, rr.Expr, rr.Type)
+	rr.mu.Lock()
+	defer rr.mu.Unlock()
+
+	rr.lastExecTime = time.Now()
+	rr.lastExecError = err
+	if err != nil {
+		return nil, fmt.Errorf("failed to execute query %q: %w", rr.Expr, err)
+	}
+
+	duplicates := make(map[uint64]prompbmarshal.TimeSeries, len(qMetrics))
+	var tss []prompbmarshal.TimeSeries
+	for _, r := range qMetrics {
+		ts := rr.toTimeSeries(r, rr.lastExecTime)
+		h := hashTimeSeries(ts)
+		if _, ok := duplicates[h]; ok {
+			rr.lastExecError = errDuplicate
+			return nil, errDuplicate
+		}
+		duplicates[h] = ts
+		tss = append(tss, ts)
+	}
+	return tss, nil
+}
+
+func hashTimeSeries(ts prompbmarshal.TimeSeries) uint64 {
+	hash := fnv.New64a()
+	labels := ts.Labels
+	sort.Slice(labels, func(i, j int) bool {
+		return labels[i].Name < labels[j].Name
+	})
+	for _, l := range labels {
+		hash.Write([]byte(l.Name))
+		hash.Write([]byte(l.Value))
+		hash.Write([]byte("\xff"))
+	}
+	return hash.Sum64()
+}
+
+func (rr *RecordingRule) toTimeSeries(m datasource.Metric, timestamp time.Time) prompbmarshal.TimeSeries {
+	labels := make(map[string]string)
+	for _, l := range m.Labels {
+		labels[l.Name] = l.Value
+	}
+	labels["__name__"] = rr.Name
+	// override existing labels with configured ones
+	for k, v := range rr.Labels {
+		labels[k] = v
+	}
+	return newTimeSeries(m.Value, labels, timestamp)
+}
+
+// UpdateWith copies all significant fields.
+// alerts state isn't copied since
+// it should be updated in next 2 Execs
+func (rr *RecordingRule) UpdateWith(r Rule) error {
+	nr, ok := r.(*RecordingRule)
+	if !ok {
+		return fmt.Errorf("BUG: attempt to update recroding rule with wrong type %#v", r)
+	}
+	rr.Expr = nr.Expr
+	rr.Labels = nr.Labels
+	return nil
+}
+
+// RuleAPI returns Rule representation in form
+// of APIRecordingRule
+func (rr *RecordingRule) RuleAPI() APIRecordingRule {
+	var lastErr string
+	if rr.lastExecError != nil {
+		lastErr = rr.lastExecError.Error()
+	}
+	return APIRecordingRule{
+		// encode as strings to avoid rounding
+		ID:         fmt.Sprintf("%d", rr.ID()),
+		GroupID:    fmt.Sprintf("%d", rr.GroupID),
+		Name:       rr.Name,
+		Type:       rr.Type.String(),
+		Expression: rr.Expr,
+		LastError:  lastErr,
+		LastExec:   rr.lastExecTime,
+		Labels:     rr.Labels,
+	}
+}

app/vmalert/recording_test.go

@@ -0,0 +1,121 @@
+package main
+
+import (
+	"context"
+	"errors"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
+)
+
+func TestRecoridngRule_ToTimeSeries(t *testing.T) {
+	timestamp := time.Now()
+	testCases := []struct {
+		rule    *RecordingRule
+		metrics []datasource.Metric
+		expTS   []prompbmarshal.TimeSeries
+	}{
+		{
+			&RecordingRule{Name: "foo"},
+			[]datasource.Metric{metricWithValueAndLabels(t, 10,
+				"__name__", "bar",
+			)},
+			[]prompbmarshal.TimeSeries{
+				newTimeSeries(10, map[string]string{
+					"__name__": "foo",
+				}, timestamp),
+			},
+		},
+		{
+			&RecordingRule{Name: "foobarbaz"},
+			[]datasource.Metric{
+				metricWithValueAndLabels(t, 1, "__name__", "foo", "job", "foo"),
+				metricWithValueAndLabels(t, 2, "__name__", "bar", "job", "bar"),
+				metricWithValueAndLabels(t, 3, "__name__", "baz", "job", "baz"),
+			},
+			[]prompbmarshal.TimeSeries{
+				newTimeSeries(1, map[string]string{
+					"__name__": "foobarbaz",
+					"job":      "foo",
+				}, timestamp),
+				newTimeSeries(2, map[string]string{
+					"__name__": "foobarbaz",
+					"job":      "bar",
+				}, timestamp),
+				newTimeSeries(3, map[string]string{
+					"__name__": "foobarbaz",
+					"job":      "baz",
+				}, timestamp),
+			},
+		},
+		{
+			&RecordingRule{Name: "job:foo", Labels: map[string]string{
+				"source": "test",
+			}},
+			[]datasource.Metric{
+				metricWithValueAndLabels(t, 2, "__name__", "foo", "job", "foo"),
+				metricWithValueAndLabels(t, 1, "__name__", "bar", "job", "bar")},
+			[]prompbmarshal.TimeSeries{
+				newTimeSeries(2, map[string]string{
+					"__name__": "job:foo",
+					"job":      "foo",
+					"source":   "test",
+				}, timestamp),
+				newTimeSeries(1, map[string]string{
+					"__name__": "job:foo",
+					"job":      "bar",
+					"source":   "test",
+				}, timestamp),
+			},
+		},
+	}
+	for _, tc := range testCases {
+		t.Run(tc.rule.Name, func(t *testing.T) {
+			fq := &fakeQuerier{}
+			fq.add(tc.metrics...)
+			tss, err := tc.rule.Exec(context.TODO(), fq, true)
+			if err != nil {
+				t.Fatalf("unexpected Exec err: %s", err)
+			}
+			if err := compareTimeSeries(t, tc.expTS, tss); err != nil {
+				t.Fatalf("timeseries missmatch: %s", err)
+			}
+		})
+	}
+}
+
+func TestRecoridngRule_ToTimeSeriesNegative(t *testing.T) {
+	rr := &RecordingRule{Name: "job:foo", Labels: map[string]string{
+		"job": "test",
+	}}
+
+	fq := &fakeQuerier{}
+	expErr := "connection reset by peer"
+	fq.setErr(errors.New(expErr))
+
+	_, err := rr.Exec(context.TODO(), fq, true)
+	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)
+	}
+
+	fq.reset()
+
+	// add metrics which differs only by `job` label
+	// which will be overridden by rule
+	fq.add(metricWithValueAndLabels(t, 1, "__name__", "foo", "job", "foo"))
+	fq.add(metricWithValueAndLabels(t, 2, "__name__", "foo", "job", "bar"))
+
+	_, err = rr.Exec(context.TODO(), fq, true)
+	if err == nil {
+		t.Fatalf("expected to get err; got nil")
+	}
+	if !strings.Contains(err.Error(), errDuplicate.Error()) {
+		t.Fatalf("expected to get err %q; got %q insterad", errDuplicate, err)
+	}
+}

app/vmalert/remoteread/init.go

@@ -0,0 +1,39 @@
+package remoteread
+
+import (
+	"flag"
+	"fmt"
+	"net/http"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/utils"
+)
+
+var (
+	addr = flag.String("remoteRead.url", "", "Optional URL to Victoria Metrics or VMSelect that will be used to restore alerts"+
+		" state. This configuration makes sense only if `vmalert` was configured with `remoteWrite.url` before and has been successfully persisted its state."+
+		" E.g. http://127.0.0.1:8428")
+	basicAuthUsername     = flag.String("remoteRead.basicAuth.username", "", "Optional basic auth username for -remoteRead.url")
+	basicAuthPassword     = flag.String("remoteRead.basicAuth.password", "", "Optional basic auth password for -remoteRead.url")
+	tlsInsecureSkipVerify = flag.Bool("remoteRead.tlsInsecureSkipVerify", false, "Whether to skip tls verification when connecting to -remoteRead.url")
+	tlsCertFile           = flag.String("remoteRead.tlsCertFile", "", "Optional path to client-side TLS certificate file to use when connecting to -remoteRead.url")
+	tlsKeyFile            = flag.String("remoteRead.tlsKeyFile", "", "Optional path to client-side TLS certificate key to use when connecting to -remoteRead.url")
+	tlsCAFile             = flag.String("remoteRead.tlsCAFile", "", "Optional path to TLS CA file to use for verifying connections to -remoteRead.url. "+
+		"By default system CA is used")
+	tlsServerName = flag.String("remoteRead.tlsServerName", "", "Optional TLS server name to use for connections to -remoteRead.url. "+
+		"By default the server name from -remoteRead.url is used")
+)
+
+// Init creates a Querier from provided flag values.
+// Returns nil if addr flag wasn't set.
+func Init() (datasource.Querier, error) {
+	if *addr == "" {
+		return nil, nil
+	}
+	tr, err := utils.Transport(*addr, *tlsCertFile, *tlsKeyFile, *tlsCAFile, *tlsServerName, *tlsInsecureSkipVerify)
+	if err != nil {
+		return nil, fmt.Errorf("failed to create transport: %w", err)
+	}
+	c := &http.Client{Transport: tr}
+	return datasource.NewVMStorage(*addr, *basicAuthUsername, *basicAuthPassword, 0, 0, false, c), nil
+}

app/vmalert/remotewrite/init.go

@@ -0,0 +1,54 @@
+package remotewrite
+
+import (
+	"context"
+	"flag"
+	"fmt"
+	"time"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/utils"
+)
+
+var (
+	addr = flag.String("remoteWrite.url", "", "Optional URL to Victoria Metrics or VMInsert where to persist alerts state"+
+		" and recording rules results in form of timeseries. E.g. http://127.0.0.1:8428")
+	basicAuthUsername = flag.String("remoteWrite.basicAuth.username", "", "Optional basic auth username for -remoteWrite.url")
+	basicAuthPassword = flag.String("remoteWrite.basicAuth.password", "", "Optional basic auth password for -remoteWrite.url")
+
+	maxQueueSize  = flag.Int("remoteWrite.maxQueueSize", 1e5, "Defines the max number of pending datapoints to remote write endpoint")
+	maxBatchSize  = flag.Int("remoteWrite.maxBatchSize", 1e3, "Defines defines max number of timeseries to be flushed at once")
+	concurrency   = flag.Int("remoteWrite.concurrency", 1, "Defines number of writers for concurrent writing into remote querier")
+	flushInterval = flag.Duration("remoteWrite.flushInterval", 5*time.Second, "Defines interval of flushes to remote write endpoint")
+
+	tlsInsecureSkipVerify = flag.Bool("remoteWrite.tlsInsecureSkipVerify", false, "Whether to skip tls verification when connecting to -remoteWrite.url")
+	tlsCertFile           = flag.String("remoteWrite.tlsCertFile", "", "Optional path to client-side TLS certificate file to use when connecting to -remoteWrite.url")
+	tlsKeyFile            = flag.String("remoteWrite.tlsKeyFile", "", "Optional path to client-side TLS certificate key to use when connecting to -remoteWrite.url")
+	tlsCAFile             = flag.String("remoteWrite.tlsCAFile", "", "Optional path to TLS CA file to use for verifying connections to -remoteWrite.url. "+
+		"By default system CA is used")
+	tlsServerName = flag.String("remoteWrite.tlsServerName", "", "Optional TLS server name to use for connections to -remoteWrite.url. "+
+		"By default the server name from -remoteWrite.url is used")
+)
+
+// Init creates Client object from given flags.
+// Returns nil if addr flag wasn't set.
+func Init(ctx context.Context) (*Client, error) {
+	if *addr == "" {
+		return nil, nil
+	}
+
+	t, err := utils.Transport(*addr, *tlsCertFile, *tlsKeyFile, *tlsCAFile, *tlsServerName, *tlsInsecureSkipVerify)
+	if err != nil {
+		return nil, fmt.Errorf("failed to create transport: %w", err)
+	}
+
+	return NewClient(ctx, Config{
+		Addr:          *addr,
+		Concurrency:   *concurrency,
+		MaxQueueSize:  *maxQueueSize,
+		MaxBatchSize:  *maxBatchSize,
+		FlushInterval: *flushInterval,
+		BasicAuthUser: *basicAuthUsername,
+		BasicAuthPass: *basicAuthPassword,
+		Transport:     t,
+	})
+}

app/vmalert/remotewrite/remotewrite.go

@@ -12,6 +12,7 @@ import (
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
+	"github.com/VictoriaMetrics/metrics"
 	"github.com/golang/snappy"
 )
 
@@ -38,22 +39,29 @@ type Config struct {
 	BasicAuthUser string
 	BasicAuthPass string
 
+	// Concurrency defines number of readers that
+	// concurrently read from the queue and flush data
+	Concurrency int
 	// MaxBatchSize defines max number of timeseries
 	// to be flushed at once
 	MaxBatchSize int
 	// MaxQueueSize defines max length of input queue
-	// populated by Push method
+	// populated by Push method.
+	// Push will be rejected once queue is full.
 	MaxQueueSize int
 	// FlushInterval defines time interval for flushing batches
 	FlushInterval time.Duration
 	// WriteTimeout defines timeout for HTTP write request
 	// to remote storage
 	WriteTimeout time.Duration
+	// Transport will be used by the underlying http.Client
+	Transport *http.Transport
 }
 
 const (
+	defaultConcurrency   = 4
 	defaultMaxBatchSize  = 1e3
-	defaultMaxQueueSize  = 100
+	defaultMaxQueueSize  = 1e5
 	defaultFlushInterval = 5 * time.Second
 	defaultWriteTimeout  = 30 * time.Second
 )
@@ -78,19 +86,30 @@ func NewClient(ctx context.Context, cfg Config) (*Client, error) {
 	if cfg.WriteTimeout == 0 {
 		cfg.WriteTimeout = defaultWriteTimeout
 	}
+	if cfg.Transport == nil {
+		cfg.Transport = http.DefaultTransport.(*http.Transport).Clone()
+	}
 	c := &Client{
 		c: &http.Client{
-			Timeout: cfg.WriteTimeout,
+			Timeout:   cfg.WriteTimeout,
+			Transport: cfg.Transport,
 		},
-		addr:          strings.TrimSuffix(cfg.Addr, "/") + writePath,
+		addr:          strings.TrimSuffix(cfg.Addr, "/"),
 		baUser:        cfg.BasicAuthUser,
 		baPass:        cfg.BasicAuthPass,
 		flushInterval: cfg.FlushInterval,
 		maxBatchSize:  cfg.MaxBatchSize,
+		maxQueueSize:  cfg.MaxQueueSize,
 		doneCh:        make(chan struct{}),
 		input:         make(chan prompbmarshal.TimeSeries, cfg.MaxQueueSize),
 	}
-	c.run(ctx)
+	cc := defaultConcurrency
+	if cfg.Concurrency > 0 {
+		cc = cfg.Concurrency
+	}
+	for i := 0; i < cc; i++ {
+		c.run(ctx)
+	}
 	return c, nil
 }
 
@@ -123,12 +142,12 @@ func (c *Client) Close() error {
 
 func (c *Client) run(ctx context.Context) {
 	ticker := time.NewTicker(c.flushInterval)
-	wr := prompbmarshal.WriteRequest{}
+	wr := &prompbmarshal.WriteRequest{}
 	shutdown := func() {
 		for ts := range c.input {
 			wr.Timeseries = append(wr.Timeseries, ts)
 		}
-		lastCtx, cancel := context.WithTimeout(context.Background(), time.Second*10)
+		lastCtx, cancel := context.WithTimeout(context.Background(), defaultWriteTimeout)
 		c.flush(lastCtx, wr)
 		cancel()
 	}
@@ -146,44 +165,83 @@ func (c *Client) run(ctx context.Context) {
 				return
 			case <-ticker.C:
 				c.flush(ctx, wr)
-				wr = prompbmarshal.WriteRequest{}
-			case ts := <-c.input:
+			case ts, ok := <-c.input:
+				if !ok {
+					continue
+				}
 				wr.Timeseries = append(wr.Timeseries, ts)
 				if len(wr.Timeseries) >= c.maxBatchSize {
 					c.flush(ctx, wr)
-					wr = prompbmarshal.WriteRequest{}
 				}
 			}
 		}
 	}()
 }
 
-func (c *Client) flush(ctx context.Context, wr prompbmarshal.WriteRequest) {
+var (
+	sentRows     = metrics.NewCounter(`vmalert_remotewrite_sent_rows_total`)
+	sentBytes    = metrics.NewCounter(`vmalert_remotewrite_sent_bytes_total`)
+	droppedRows  = metrics.NewCounter(`vmalert_remotewrite_dropped_rows_total`)
+	droppedBytes = metrics.NewCounter(`vmalert_remotewrite_dropped_bytes_total`)
+)
+
+// flush is a blocking function that marshals WriteRequest and sends
+// it to remote write endpoint. Flush performs limited amount of retries
+// if request fails.
+func (c *Client) flush(ctx context.Context, wr *prompbmarshal.WriteRequest) {
 	if len(wr.Timeseries) < 1 {
 		return
 	}
+	defer prompbmarshal.ResetWriteRequest(wr)
+
 	data, err := wr.Marshal()
 	if err != nil {
 		logger.Errorf("failed to marshal WriteRequest: %s", err)
 		return
 	}
-	req, err := http.NewRequest("POST", c.addr, bytes.NewReader(snappy.Encode(nil, data)))
+
+	const attempts = 5
+	b := snappy.Encode(nil, data)
+	for i := 0; i < attempts; i++ {
+		err := c.send(ctx, b)
+		if err == nil {
+			sentRows.Add(len(wr.Timeseries))
+			sentBytes.Add(len(b))
+			return
+		}
+
+		logger.Errorf("attempt %d to send request failed: %s", i+1, err)
+		// sleeping to avoid remote db hammering
+		time.Sleep(time.Second)
+		continue
+	}
+
+	droppedRows.Add(len(wr.Timeseries))
+	droppedBytes.Add(len(b))
+	logger.Errorf("all %d attempts to send request failed - dropping %d timeseries",
+		attempts, len(wr.Timeseries))
+}
+
+func (c *Client) send(ctx context.Context, data []byte) error {
+	r := bytes.NewReader(data)
+	req, err := http.NewRequest("POST", c.addr, r)
 	if err != nil {
-		logger.Errorf("failed to create new HTTP request: %s", err)
-		return
+		return fmt.Errorf("failed to create new HTTP request: %w", err)
 	}
 	if c.baPass != "" {
 		req.SetBasicAuth(c.baUser, c.baPass)
 	}
+	req.URL.Path += writePath
 	resp, err := c.c.Do(req.WithContext(ctx))
 	if err != nil {
-		logger.Errorf("error getting response from %s:%s", req.URL, err)
-		return
+		return fmt.Errorf("error while sending request to %s: %w; Data len %d(%d)",
+			req.URL, err, len(data), r.Size())
 	}
 	defer func() { _ = resp.Body.Close() }()
 	if resp.StatusCode != http.StatusNoContent {
 		body, _ := ioutil.ReadAll(resp.Body)
-		logger.Errorf("unexpected response code %d for %s. Response body %s", resp.StatusCode, req.URL, body)
-		return
+		return fmt.Errorf("unexpected response code %d for %s. Response body %q",
+			resp.StatusCode, req.URL, body)
 	}
+	return nil
 }

app/vmalert/remotewrite/remotewrite_test.go

@@ -0,0 +1,102 @@
+package remotewrite
+
+import (
+	"context"
+	"fmt"
+	"io/ioutil"
+	"math/rand"
+	"net/http"
+	"net/http/httptest"
+	"sync/atomic"
+	"testing"
+	"time"
+
+	"github.com/golang/snappy"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
+)
+
+func TestClient_Push(t *testing.T) {
+	testSrv := newRWServer()
+	cfg := Config{
+		Addr:         testSrv.URL,
+		MaxBatchSize: 100,
+	}
+	client, err := NewClient(context.Background(), cfg)
+	if err != nil {
+		t.Fatalf("failed to create client: %s", err)
+	}
+	const rowsN = 1e4
+	var sent int
+	for i := 0; i < rowsN; i++ {
+		s := prompbmarshal.TimeSeries{
+			Samples: []prompbmarshal.Sample{{
+				Value:     rand.Float64(),
+				Timestamp: time.Now().Unix(),
+			}},
+		}
+		err := client.Push(s)
+		if err == nil {
+			sent++
+		}
+	}
+	if sent == 0 {
+		t.Fatalf("0 series sent")
+	}
+	if err := client.Close(); err != nil {
+		t.Fatalf("failed to close client: %s", err)
+	}
+	got := testSrv.accepted()
+	if got != sent {
+		t.Fatalf("expected to have %d series; got %d", sent, got)
+	}
+}
+
+func newRWServer() *rwServer {
+	rw := &rwServer{}
+	rw.Server = httptest.NewServer(http.HandlerFunc(rw.handler))
+	return rw
+}
+
+type rwServer struct {
+	// WARN: ordering of fields is important for alignment!
+	// see https://golang.org/pkg/sync/atomic/#pkg-note-BUG
+	acceptedRows uint64
+	*httptest.Server
+}
+
+func (rw *rwServer) accepted() int {
+	return int(atomic.LoadUint64(&rw.acceptedRows))
+}
+
+func (rw *rwServer) err(w http.ResponseWriter, err error) {
+	w.WriteHeader(http.StatusBadRequest)
+	w.Write([]byte(err.Error()))
+}
+
+func (rw *rwServer) handler(w http.ResponseWriter, r *http.Request) {
+	if r.Method != http.MethodPost {
+		rw.err(w, fmt.Errorf("bad method %q", r.Method))
+		return
+	}
+	data, err := ioutil.ReadAll(r.Body)
+	if err != nil {
+		rw.err(w, fmt.Errorf("body read err: %w", err))
+		return
+	}
+	defer func() { _ = r.Body.Close() }()
+
+	b, err := snappy.Decode(nil, data)
+	if err != nil {
+		rw.err(w, fmt.Errorf("decode err: %w", err))
+		return
+	}
+	wr := &prompb.WriteRequest{}
+	if err := wr.Unmarshal(b); err != nil {
+		rw.err(w, fmt.Errorf("unmarhsal err: %w", err))
+		return
+	}
+	atomic.AddUint64(&rw.acceptedRows, uint64(len(wr.Timeseries)))
+	w.WriteHeader(http.StatusNoContent)
+}

app/vmalert/rule.go

@@ -3,338 +3,28 @@ package main
 import (
 	"context"
 	"errors"
-	"fmt"
-	"hash/fnv"
-	"sort"
-	"strconv"
-	"sync"
-	"time"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
-	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
-	"github.com/VictoriaMetrics/metricsql"
 )
 
-// Rule is basic alert entity
-type Rule struct {
-	Name        string            `yaml:"alert"`
-	Expr        string            `yaml:"expr"`
-	For         time.Duration     `yaml:"for"`
-	Labels      map[string]string `yaml:"labels"`
-	Annotations map[string]string `yaml:"annotations"`
-
-	group Group
-
-	// 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
+// Rule represents alerting or recording rule
+// that has unique ID, can be Executed and
+// updated with other Rule.
+type Rule interface {
+	// Returns unique ID that may be used for
+	// identifying this Rule among others.
+	ID() uint64
+	// Exec executes the rule with given context
+	// and Querier. If returnSeries is true, Exec
+	// may return TimeSeries as result of execution
+	Exec(ctx context.Context, q datasource.Querier, returnSeries bool) ([]prompbmarshal.TimeSeries, error)
+	// UpdateWith performs modification of current Rule
+	// with fields of the given Rule.
+	UpdateWith(Rule) error
+	// Close performs the shutdown procedures for rule
+	// such as metrics unregister
+	Close()
 }
 
-func (r *Rule) id() string {
-	return r.Name
-}
-
-// Validate validates rule
-func (r *Rule) Validate() error {
-	if r.Name == "" {
-		return errors.New("rule name can not be empty")
-	}
-	if r.Expr == "" {
-		return fmt.Errorf("expression for rule %q can't be empty", r.Name)
-	}
-	if _, err := metricsql.Parse(r.Expr); err != nil {
-		return fmt.Errorf("invalid expression for rule %q: %w", r.Name, err)
-	}
-	return nil
-}
-
-// Exec executes Rule expression via the given Querier.
-// Based on the Querier results Rule maintains notifier.Alerts
-func (r *Rule) Exec(ctx context.Context, q datasource.Querier) error {
-	qMetrics, err := q.Query(ctx, r.Expr)
-	r.mu.Lock()
-	defer r.mu.Unlock()
-
-	r.lastExecError = err
-	r.lastExecTime = time.Now()
-	if err != nil {
-		return fmt.Errorf("failed to execute query %q: %s", r.Expr, err)
-	}
-
-	for h, a := range r.alerts {
-		// cleanup inactive alerts from previous Exec
-		if a.State == notifier.StateInactive {
-			delete(r.alerts, h)
-		}
-	}
-
-	updated := make(map[uint64]struct{})
-	// update list of active alerts
-	for _, m := range qMetrics {
-		h := hash(m)
-		updated[h] = struct{}{}
-		if a, ok := r.alerts[h]; ok {
-			if a.Value != m.Value {
-				// update Value field with latest value
-				a.Value = m.Value
-				// and re-exec template since Value can be used
-				// in templates
-				err = r.template(a)
-				if err != nil {
-					return err
-				}
-			}
-			continue
-		}
-		a, err := r.newAlert(m)
-		if err != nil {
-			r.lastExecError = err
-			return fmt.Errorf("failed to create alert: %s", err)
-		}
-		a.ID = h
-		a.State = notifier.StatePending
-		r.alerts[h] = a
-	}
-
-	for h, a := range r.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(r.alerts, h)
-				continue
-			}
-			a.State = notifier.StateInactive
-			continue
-		}
-		if a.State == notifier.StatePending && time.Since(a.Start) >= r.For {
-			a.State = notifier.StateFiring
-			alertsFired.Inc()
-		}
-	}
-	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 (r *Rule) newAlert(m datasource.Metric) (*notifier.Alert, error) {
-	a := &notifier.Alert{
-		GroupID: r.group.ID(),
-		Name:    r.Name,
-		Labels:  map[string]string{},
-		Value:   m.Value,
-		Start:   time.Now(),
-		Expr:    r.Expr,
-		// TODO: support End time
-	}
-	for _, l := range m.Labels {
-		// drop __name__ to be consistent with Prometheus alerting
-		if l.Name == "__name__" {
-			continue
-		}
-		a.Labels[l.Name] = l.Value
-	}
-	return a, r.template(a)
-}
-
-func (r *Rule) template(a *notifier.Alert) error {
-	// 1. template rule labels with data labels
-	rLabels, err := a.ExecTemplate(r.Labels)
-	if err != nil {
-		return err
-	}
-
-	// 2. merge data labels and rule labels
-	// metric labels may be overridden by
-	// rule labels
-	for k, v := range rLabels {
-		a.Labels[k] = v
-	}
-
-	// 3. template merged labels
-	a.Labels, err = a.ExecTemplate(a.Labels)
-	if err != nil {
-		return err
-	}
-
-	a.Annotations, err = a.ExecTemplate(r.Annotations)
-	return err
-}
-
-// AlertAPI generates APIAlert object from alert by its id(hash)
-func (r *Rule) AlertAPI(id uint64) *APIAlert {
-	r.mu.RLock()
-	defer r.mu.RUnlock()
-	a, ok := r.alerts[id]
-	if !ok {
-		return nil
-	}
-	return r.newAlertAPI(*a)
-}
-
-// AlertsAPI generates list of APIAlert objects from existing alerts
-func (r *Rule) AlertsAPI() []*APIAlert {
-	var alerts []*APIAlert
-	r.mu.RLock()
-	for _, a := range r.alerts {
-		alerts = append(alerts, r.newAlertAPI(*a))
-	}
-	r.mu.RUnlock()
-	return alerts
-}
-
-func (r *Rule) newAlertAPI(a notifier.Alert) *APIAlert {
-	return &APIAlert{
-		// encode as strings to avoid rounding
-		ID:      fmt.Sprintf("%d", a.ID),
-		GroupID: fmt.Sprintf("%d", a.GroupID),
-
-		Name:        a.Name,
-		Expression:  r.Expr,
-		Labels:      a.Labels,
-		Annotations: a.Annotations,
-		State:       a.State.String(),
-		ActiveAt:    a.Start,
-		Value:       strconv.FormatFloat(a.Value, 'e', -1, 64),
-	}
-}
-
-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"
-)
-
-// AlertToTimeSeries converts the given alert with the given timestamp to timeseries
-func (r *Rule) AlertToTimeSeries(a *notifier.Alert, timestamp time.Time) []prompbmarshal.TimeSeries {
-	var tss []prompbmarshal.TimeSeries
-	tss = append(tss, alertToTimeSeries(r.Name, a, timestamp))
-	if r.For > 0 {
-		tss = append(tss, alertForToTimeSeries(r.Name, a, timestamp))
-	}
-	return tss
-}
-
-func alertToTimeSeries(name string, a *notifier.Alert, timestamp time.Time) prompbmarshal.TimeSeries {
-	labels := make(map[string]string)
-	for k, v := range a.Labels {
-		labels[k] = v
-	}
-	labels["__name__"] = alertMetricName
-	labels[alertNameLabel] = name
-	labels[alertStateLabel] = a.State.String()
-	return newTimeSeries(1, labels, timestamp)
-}
-
-// alertForToTimeSeries returns a timeseries that represents
-// state of active alerts, where value is time when alert become active
-func alertForToTimeSeries(name string, a *notifier.Alert, timestamp time.Time) prompbmarshal.TimeSeries {
-	labels := make(map[string]string)
-	for k, v := range a.Labels {
-		labels[k] = v
-	}
-	labels["__name__"] = alertForStateMetricName
-	labels[alertNameLabel] = name
-	return newTimeSeries(float64(a.Start.Unix()), labels, timestamp)
-}
-
-func newTimeSeries(value float64, labels map[string]string, timestamp time.Time) prompbmarshal.TimeSeries {
-	ts := prompbmarshal.TimeSeries{}
-	ts.Samples = append(ts.Samples, prompbmarshal.Sample{
-		Value:     value,
-		Timestamp: timestamp.UnixNano() / 1e6,
-	})
-	keys := make([]string, 0, len(labels))
-	for k := range labels {
-		keys = append(keys, k)
-	}
-	sort.Strings(keys)
-	for _, key := range keys {
-		ts.Labels = append(ts.Labels, prompbmarshal.Label{
-			Name:  key,
-			Value: labels[key],
-		})
-	}
-	return ts
-}
-
-// Restore restores the state of active alerts basing on previously written timeseries.
-// Restore restores only Start field. Field State will be always Pending and supposed
-// to be updated on next Exec, as well as Value field.
-func (r *Rule) Restore(ctx context.Context, q datasource.Querier, lookback time.Duration) error {
-	if q == nil {
-		return fmt.Errorf("querier is nil")
-	}
-
-	// Get the last datapoint 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}[%ds])",
-		alertForStateMetricName, r.Name, int(lookback.Seconds()))
-	qMetrics, err := q.Query(ctx, expr)
-	if err != nil {
-		return err
-	}
-
-	for _, m := range qMetrics {
-		labels := m.Labels
-		m.Labels = make([]datasource.Label, 0)
-		// drop all extra labels, so hash key will
-		// be identical to timeseries received in Exec
-		for _, l := range labels {
-			if l.Name == alertNameLabel {
-				continue
-			}
-			// drop all overridden labels
-			if _, ok := r.Labels[l.Name]; ok {
-				continue
-			}
-			m.Labels = append(m.Labels, l)
-		}
-
-		a, err := r.newAlert(m)
-		if err != nil {
-			return fmt.Errorf("failed to create alert: %s", err)
-		}
-		a.ID = hash(m)
-		a.State = notifier.StatePending
-		a.Start = time.Unix(int64(m.Value), 0)
-		r.alerts[a.ID] = a
-		logger.Infof("alert %q(%d) restored to state at %v", a.Name, a.ID, a.Start)
-	}
-	return nil
-}
+var errDuplicate = errors.New("result contains metrics with the same labelset after applying rule labels")

app/vmalert/utils.go

@@ -0,0 +1,28 @@
+package main
+
+import (
+	"sort"
+	"time"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
+)
+
+func newTimeSeries(value float64, labels map[string]string, timestamp time.Time) prompbmarshal.TimeSeries {
+	ts := prompbmarshal.TimeSeries{}
+	ts.Samples = append(ts.Samples, prompbmarshal.Sample{
+		Value:     value,
+		Timestamp: timestamp.UnixNano() / 1e6,
+	})
+	keys := make([]string, 0, len(labels))
+	for k := range labels {
+		keys = append(keys, k)
+	}
+	sort.Strings(keys)
+	for _, key := range keys {
+		ts.Labels = append(ts.Labels, prompbmarshal.Label{
+			Name:  key,
+			Value: labels[key],
+		})
+	}
+	return ts
+}

app/vmalert/utils/err_group.go

@@ -0,0 +1,43 @@
+package utils
+
+import (
+	"fmt"
+	"strings"
+)
+
+// ErrGroup accumulates multiple errors
+// and produces single error message.
+type ErrGroup struct {
+	errs []error
+}
+
+// Add adds a new error to group.
+// Isn't thread-safe.
+func (eg *ErrGroup) Add(err error) {
+	eg.errs = append(eg.errs, err)
+}
+
+// Err checks if group contains at least
+// one error.
+func (eg *ErrGroup) Err() error {
+	if eg == nil || len(eg.errs) == 0 {
+		return nil
+	}
+	return eg
+}
+
+// Error satisfies Error interface
+func (eg *ErrGroup) Error() string {
+	if len(eg.errs) == 0 {
+		return ""
+	}
+	var b strings.Builder
+	fmt.Fprintf(&b, "errors(%d): ", len(eg.errs))
+	for i, err := range eg.errs {
+		b.WriteString(err.Error())
+		if i != len(eg.errs)-1 {
+			b.WriteString("\n")
+		}
+	}
+	return b.String()
+}

app/vmalert/utils/err_group_test.go

@@ -0,0 +1,38 @@
+package utils
+
+import (
+	"errors"
+	"testing"
+)
+
+func TestErrGroup(t *testing.T) {
+	testCases := []struct {
+		errs []error
+		exp  string
+	}{
+		{nil, ""},
+		{[]error{errors.New("timeout")}, "errors(1): timeout"},
+		{
+			[]error{errors.New("timeout"), errors.New("deadline")},
+			"errors(2): timeout\ndeadline",
+		},
+	}
+	for _, tc := range testCases {
+		eg := new(ErrGroup)
+		for _, err := range tc.errs {
+			eg.Add(err)
+		}
+		if len(tc.errs) == 0 {
+			if eg.Err() != nil {
+				t.Fatalf("expected to get nil error")
+			}
+			continue
+		}
+		if eg.Err() == nil {
+			t.Fatalf("expected to get non-nil error")
+		}
+		if eg.Error() != tc.exp {
+			t.Fatalf("expected to have: \n%q\ngot:\n%q", tc.exp, eg.Error())
+		}
+	}
+}

app/vmalert/utils/tls.go

@@ -0,0 +1,58 @@
+package utils
+
+import (
+	"crypto/tls"
+	"crypto/x509"
+	"fmt"
+	"io/ioutil"
+	"net/http"
+	"strings"
+)
+
+// Transport creates http.Transport object based on provided URL.
+// Returns Transport with TLS configuration if URL contains `https` prefix
+func Transport(URL, certFile, keyFile, CAFile, serverName string, insecureSkipVerify bool) (*http.Transport, error) {
+	t := http.DefaultTransport.(*http.Transport).Clone()
+	if !strings.HasPrefix(URL, "https") {
+		return t, nil
+	}
+	tlsCfg, err := TLSConfig(certFile, keyFile, CAFile, serverName, insecureSkipVerify)
+	if err != nil {
+		return nil, err
+	}
+	t.TLSClientConfig = tlsCfg
+	return t, nil
+}
+
+// TLSConfig creates tls.Config object from provided arguments
+func TLSConfig(certFile, keyFile, CAFile, serverName string, insecureSkipVerify bool) (*tls.Config, error) {
+	var certs []tls.Certificate
+	if certFile != "" {
+		cert, err := tls.LoadX509KeyPair(certFile, keyFile)
+		if err != nil {
+			return nil, fmt.Errorf("cannot load TLS certificate from `cert_file`=%q, `key_file`=%q: %w", certFile, keyFile, err)
+		}
+
+		certs = []tls.Certificate{cert}
+	}
+
+	var rootCAs *x509.CertPool
+	if CAFile != "" {
+		pem, err := ioutil.ReadFile(CAFile)
+		if err != nil {
+			return nil, fmt.Errorf("cannot read `ca_file` %q: %w", CAFile, err)
+		}
+
+		rootCAs = x509.NewCertPool()
+		if !rootCAs.AppendCertsFromPEM(pem) {
+			return nil, fmt.Errorf("cannot parse data from `ca_file` %q", CAFile)
+		}
+	}
+
+	return &tls.Config{
+		Certificates:       certs,
+		InsecureSkipVerify: insecureSkipVerify,
+		RootCAs:            rootCAs,
+		ServerName:         serverName,
+	}, nil
+}

app/vmalert/utils/tls_test.go

@@ -0,0 +1,52 @@
+package utils
+
+import "testing"
+
+func TestTLSConfig(t *testing.T) {
+	var certFile, keyFile, CAFile, serverName string
+	var insecureSkipVerify bool
+	serverName = "test"
+	insecureSkipVerify = true
+	tlsCfg, err := TLSConfig(certFile, keyFile, CAFile, serverName, insecureSkipVerify)
+	if err != nil {
+		t.Errorf("unexpected error %s", err)
+	}
+	if tlsCfg == nil {
+		t.Errorf("expected tlsConfig to be set, got nil")
+	}
+	if tlsCfg.ServerName != serverName {
+		t.Errorf("unexpected ServerName, want %s, got %s", serverName, tlsCfg.ServerName)
+	}
+	if tlsCfg.InsecureSkipVerify != insecureSkipVerify {
+		t.Errorf("unexpected InsecureSkipVerify, want %v, got %v", insecureSkipVerify, tlsCfg.InsecureSkipVerify)
+	}
+	certFile = "/path/to/nonexisting/cert/file"
+	_, err = TLSConfig(certFile, keyFile, CAFile, serverName, insecureSkipVerify)
+	if err == nil {
+		t.Errorf("expected keypair error, got nil")
+	}
+	certFile = ""
+	CAFile = "/path/to/nonexisting/cert/file"
+	_, err = TLSConfig(certFile, keyFile, CAFile, serverName, insecureSkipVerify)
+	if err == nil {
+		t.Errorf("expected read error, got nil")
+	}
+}
+
+func TestTransport(t *testing.T) {
+	var certFile, keyFile, CAFile, serverName string
+	var insecureSkipVerify bool
+	URL := "http://victoriametrics.com"
+	_, err := Transport(URL, certFile, keyFile, CAFile, serverName, insecureSkipVerify)
+	if err != nil {
+		t.Errorf("unexpected error %s", err)
+	}
+	URL = "https://victoriametrics.com"
+	tr, err := Transport(URL, certFile, keyFile, CAFile, serverName, insecureSkipVerify)
+	if err != nil {
+		t.Errorf("unexpected error %s", err)
+	}
+	if tr.TLSClientConfig == nil {
+		t.Errorf("expected TLSClientConfig to be set, got nil")
+	}
+}