docs/CHANGELOG.md: cut v1.66.2

They were broken in the commit 00cbb099b6

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1644

.github/ISSUE_TEMPLATE/bug_report.md

@@ -4,14 +4,14 @@ about: Create a report to help us improve
 title: ''
 labels: ''
 assignees: ''
-
 ---
 
 **Describe the bug**
 A clear and concise description of what the bug is.
-It would be great [upgrading](https://victoriametrics.github.io/#how-to-upgrade) to [the latest avaialble release](https://github.com/VictoriaMetrics/VictoriaMetrics/releases)
+It would be a great [upgrading](https://docs.victoriametrics.com/#how-to-upgrade) 
+to [the latest available release](https://github.com/VictoriaMetrics/VictoriaMetrics/releases)
 and verifying whether the bug is reproducible there.
-It is also recommended reading [troubleshooting docs](https://victoriametrics.github.io/#troubleshooting).
+It is also recommended reading [troubleshooting docs](https://docs.victoriametrics.com/#troubleshooting).
 
 **To Reproduce**
 Steps to reproduce the behavior.
@@ -19,9 +19,22 @@ Steps to reproduce the behavior.
 **Expected behavior**
 A clear and concise description of what you expected to happen.
 
+**Logs**
+Check if any warnings or errors were logged by VictoriaMetrics components
+or components in communication with VictoriaMetrics (e.g. Prometheus, Grafana).
+
 **Screenshots**
 If applicable, add screenshots to help explain your problem.
 
+For VictoriaMetrics health-state issues please provide full-length screenshots 
+of Grafana dashboards if possible:
+* [Grafana dashboard for single-node VictoriaMetrics](https://grafana.com/dashboards/10229)
+* [Grafana dashboard for VictoriaMetrics cluster](https://grafana.com/grafana/dashboards/11176)
+
+See how to setup monitoring here:
+* [monitoring for single-node VictoriaMetrics](https://docs.victoriametrics.com/#monitoring)
+* [montioring for VictoriaMetrics cluster](https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html#monitoring)
+
 **Version**
 The line returned when passing `--version` command line flag to binary. For example:
 ```
@@ -30,15 +43,5 @@ victoria-metrics-20190730-121249-heads-single-node-0-g671d9e55
 ```
 
 **Used command-line flags**
-Command-line flags are listed as `flag{name="httpListenAddr", value=":443"} 1` lines at `/metrics` page.
-See the following docs for details:
+Please provide applied command-line flags used for running VictoriaMetrics and its components. 
 
-* [monitoring for single-node VictoriaMetrics](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/README.md#monitoring)
-* [montioring for VictoriaMetrics cluster](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/cluster/README.md#monitoring)
-
-**Additional context**
-Add any other context about the problem here such as error logs from VictoriaMetrics and Prometheus,
-`/metrics` output, screenshots from the official Grafana dashboards for VictoriaMetrics:
-
-* [Grafana dashboard for single-node VictoriaMetrics](https://grafana.com/dashboards/10229)
-* [Grafana dashboard for VictoriaMetrics cluster](https://grafana.com/grafana/dashboards/11176)

.github/dependabot.yml

@@ -0,0 +1,26 @@
+version: 2
+updates:
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "daily"
+  - package-ecosystem: "gomod"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+  - package-ecosystem: "bundler"
+    directory: "/docs"
+    schedule:
+      interval: "daily"
+  - package-ecosystem: "gomod"
+    directory: "/app/vmui/packages/vmui/web"
+    schedule:
+      interval: "weekly"
+  - package-ecosystem: "docker"
+    directory: "/"
+    schedule:
+      interval: "daily"
+  - package-ecosystem: "npm"
+    directory: "/app/vmui"
+    schedule:
+      interval: "weekly"

.github/workflows/check-licenses.yml

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

.github/workflows/github-pages.yml

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

.github/workflows/main.yml

@@ -16,7 +16,7 @@ jobs:
       - name: Setup Go
         uses: actions/setup-go@main
         with:
-          go-version: 1.15
+          go-version: 1.16
         id: go
       - name: Dependencies
         run: |
@@ -58,9 +58,9 @@ jobs:
           GOOS=darwin go build -mod=vendor ./app/vmbackup
           GOOS=darwin go build -mod=vendor ./app/vmrestore
           GOOS=darwin go build -mod=vendor ./app/vmctl
+          CGO_ENABLED=0 GOOS=windows go build -mod=vendor ./app/vmagent
       - name: Publish coverage
-        uses: codecov/codecov-action@v1.0.6
+        uses: codecov/codecov-action@v2.1.0
         with:
-          token: ${{secrets.CODECOV_TOKEN}}
           file: ./coverage.txt
 

.github/workflows/wiki.yml

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

.gitignore

@@ -15,3 +15,7 @@
 /package/temp-rpm-*
 /package/*.deb
 /package/*.rpm
+.DS_store
+Gemfile.lock
+/_site
+_site

.wwhrd.yml

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

CODE_OF_CONDUCT.md

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

Makefile

@@ -1,5 +1,6 @@
 PKG_PREFIX := github.com/VictoriaMetrics/VictoriaMetrics
 
+DATEINFO_TAG ?= $(shell date -u +'%Y%m%d-%H%M%S')
 BUILDINFO_TAG ?= $(shell echo $$(git describe --long --all | tr '/' '-')$$( \
 	      git diff-index --quiet HEAD -- || echo '-dirty-'$$(git diff-index -u HEAD | openssl sha1 | cut -c 10-17)))
 
@@ -8,7 +9,7 @@ ifeq ($(PKG_TAG),)
 PKG_TAG := $(BUILDINFO_TAG)
 endif
 
-GO_BUILDINFO = -X '$(PKG_PREFIX)/lib/buildinfo.Version=$(APP_NAME)-$(shell date -u +'%Y%m%d-%H%M%S')-$(BUILDINFO_TAG)'
+GO_BUILDINFO = -X '$(PKG_PREFIX)/lib/buildinfo.Version=$(APP_NAME)-$(DATEINFO_TAG)-$(BUILDINFO_TAG)'
 
 .PHONY: $(MAKECMDGOALS)
 
@@ -53,6 +54,14 @@ vmutils: \
 	vmrestore \
 	vmctl
 
+vmutils-pure: \
+	vmagent-pure \
+	vmalert-pure \
+	vmauth-pure \
+	vmbackup-pure \
+	vmrestore-pure \
+	vmctl-pure
+
 vmutils-arm64: \
 	vmagent-arm64 \
 	vmalert-arm64 \
@@ -61,6 +70,20 @@ vmutils-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
@@ -71,11 +94,15 @@ release: \
 
 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
 
@@ -85,11 +112,13 @@ release-victoria-metrics-generic: victoria-metrics-$(GOARCH)-prod
 			victoria-metrics-$(GOARCH)-prod \
 		&& sha256sum victoria-metrics-$(GOARCH)-$(PKG_TAG).tar.gz \
 			victoria-metrics-$(GOARCH)-prod \
-			| sed s/-$(GOARCH)// > victoria-metrics-$(GOARCH)-$(PKG_TAG)_checksums.txt
+			| sed s/-$(GOARCH)-prod/-prod/ > victoria-metrics-$(GOARCH)-$(PKG_TAG)_checksums.txt
 
 release-vmutils: \
 	release-vmutils-amd64 \
-	release-vmutils-arm64
+	release-vmutils-arm64 \
+	release-vmutils-arm \
+	release-vmutils-windows-amd64
 
 release-vmutils-amd64:
 	GOARCH=amd64 $(MAKE) release-vmutils-generic
@@ -97,6 +126,12 @@ release-vmutils-amd64:
 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-$(GOARCH)-prod \
@@ -119,7 +154,25 @@ release-vmutils-generic: \
 			vmbackup-$(GOARCH)-prod \
 			vmrestore-$(GOARCH)-prod \
 			vmctl-$(GOARCH)-prod \
-			| sed s/-$(GOARCH)// > vmutils-$(GOARCH)-$(PKG_TAG)_checksums.txt
+			| sed s/-$(GOARCH)-prod/-prod/ > vmutils-$(GOARCH)-$(PKG_TAG)_checksums.txt
+
+release-vmutils-windows-generic: \
+	vmagent-windows-$(GOARCH)-prod \
+	vmalert-windows-$(GOARCH)-prod \
+	vmauth-windows-$(GOARCH)-prod \
+	vmctl-windows-$(GOARCH)-prod
+	cd bin && \
+		zip vmutils-windows-$(GOARCH)-$(PKG_TAG).zip \
+			vmagent-windows-$(GOARCH)-prod.exe \
+			vmalert-windows-$(GOARCH)-prod.exe \
+			vmauth-windows-$(GOARCH)-prod.exe \
+			vmctl-windows-$(GOARCH)-prod.exe \
+		&& sha256sum vmutils-windows-$(GOARCH)-$(PKG_TAG).zip \
+			vmagent-windows-$(GOARCH)-prod.exe \
+			vmalert-windows-$(GOARCH)-prod.exe \
+			vmauth-windows-$(GOARCH)-prod.exe \
+			vmctl-windows-$(GOARCH)-prod.exe \
+			> vmutils-windows-$(GOARCH)-$(PKG_TAG)_checksums.txt
 
 pprof-cpu:
 	go tool pprof -trim_path=github.com/VictoriaMetrics/VictoriaMetrics@ $(PPROF_FILE)
@@ -137,7 +190,7 @@ lint: install-golint
 	golint app/...
 
 install-golint:
-	which golint || go install golang.org/x/lint/golint
+	which golint || GO111MODULE=off go get golang.org/x/lint/golint
 
 errcheck: install-errcheck
 	errcheck -exclude=errcheck_excludes.txt ./lib/...
@@ -152,7 +205,7 @@ errcheck: install-errcheck
 	errcheck -exclude=errcheck_excludes.txt ./app/vmctl/...
 
 install-errcheck:
-	which errcheck || go install github.com/kisielk/errcheck
+	which errcheck || GO111MODULE=off go get github.com/kisielk/errcheck
 
 check-all: fmt vet lint errcheck golangci-lint
 
@@ -194,24 +247,43 @@ app-local-pure:
 app-local-with-goarch:
 	GO111MODULE=on go build $(RACE) -mod=vendor -ldflags "$(GO_BUILDINFO)" -o bin/$(APP_NAME)-$(GOARCH)$(RACE) $(PKG_PREFIX)/app/$(APP_NAME)
 
+app-local-windows-with-goarch:
+	CGO_ENABLED=0 GO111MODULE=on go build $(RACE) -mod=vendor -ldflags "$(GO_BUILDINFO)" -o bin/$(APP_NAME)-windows-$(GOARCH)$(RACE).exe $(PKG_PREFIX)/app/$(APP_NAME)
+
 quicktemplate-gen: install-qtc
 	qtc
 
 install-qtc:
-	which qtc || go install github.com/valyala/quicktemplate/qtc
+	which qtc || GO111MODULE=off go get github.com/valyala/quicktemplate/qtc
 
 
 golangci-lint: install-golangci-lint
 	golangci-lint run --exclude '(SA4003|SA1019|SA5011):' -D errcheck -D structcheck --timeout 2m
 
 install-golangci-lint:
-	which golangci-lint || curl -sSfL https://raw.githubusercontent.com/golangci/golangci-lint/master/install.sh | sh -s -- -b $(shell go env GOPATH)/bin v1.29.0
+	which golangci-lint || curl -sSfL https://raw.githubusercontent.com/golangci/golangci-lint/master/install.sh | sh -s -- -b $(shell go env GOPATH)/bin v1.40.1
 
+install-wwhrd:
+	which wwhrd || GO111MODULE=off go get github.com/frapposelli/wwhrd
+
+check-licenses: install-wwhrd
+	wwhrd check -f .wwhrd.yml
+
+copy-docs:
+	echo "---\nsort: ${ORDER}\n---\n" > ${DST}
+	cat ${SRC} >> ${DST}
+
+# Copies docs for all components and adds the order tag.
+# Cluster docs are supposed to be ordered as 9th.
+# For The rest of docs is ordered manually.t
 docs-sync:
-	cp app/vmagent/README.md docs/vmagent.md
-	cp app/vmalert/README.md docs/vmalert.md
-	cp app/vmauth/README.md docs/vmauth.md
-	cp app/vmbackup/README.md docs/vmbackup.md
-	cp app/vmrestore/README.md docs/vmrestore.md
-	cp app/vmctl/README.md docs/vmctl.md
-	cp README.md docs/Single-server-VictoriaMetrics.md
+	cp README.md docs/README.md
+	SRC=README.md DST=docs/Single-server-VictoriaMetrics.md ORDER=1 $(MAKE) copy-docs
+	SRC=app/vmagent/README.md DST=docs/vmagent.md ORDER=3 $(MAKE) copy-docs
+	SRC=app/vmalert/README.md DST=docs/vmalert.md ORDER=4 $(MAKE) copy-docs
+	SRC=app/vmauth/README.md DST=docs/vmauth.md ORDER=5 $(MAKE) copy-docs
+	SRC=app/vmbackup/README.md DST=docs/vmbackup.md ORDER=6 $(MAKE) copy-docs
+	SRC=app/vmrestore/README.md DST=docs/vmrestore.md ORDER=7 $(MAKE) copy-docs
+	SRC=app/vmctl/README.md DST=docs/vmctl.md ORDER=8 $(MAKE) copy-docs
+	SRC=app/vmgateway/README.md DST=docs/vmgateway.md ORDER=9 $(MAKE) copy-docs
+	SRC=app/vmbackupmanager/README.md DST=docs/vmbackupmanager.md ORDER=10 $(MAKE) copy-docs

app/victoria-metrics/main.go

@@ -3,10 +3,8 @@ package main
 import (
 	"flag"
 	"fmt"
-	"io"
 	"net/http"
 	"os"
-	"path"
 	"time"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vminsert"
@@ -26,9 +24,8 @@ import (
 
 var (
 	httpListenAddr    = flag.String("httpListenAddr", ":8428", "TCP address to listen for http connections")
-	minScrapeInterval = flag.Duration("dedup.minScrapeInterval", 0, "Remove superflouos samples from time series if they are located closer to each other than this duration. "+
-		"This may be useful for reducing overhead when multiple identically configured Prometheus instances write data to the same VictoriaMetrics. "+
-		"Deduplication is disabled if the -dedup.minScrapeInterval is 0")
+	minScrapeInterval = flag.Duration("dedup.minScrapeInterval", 0, "Leave only the first sample in every time series per each discrete interval "+
+		"equal to -dedup.minScrapeInterval > 0. See https://docs.victoriametrics.com/#deduplication for details")
 	dryRun = flag.Bool("dryRun", false, "Whether to check only -promscrape.config and then exit. "+
 		"Unknown config entries are allowed in -promscrape.config by default. This can be changed with -promscrape.config.strictParse")
 )
@@ -86,14 +83,20 @@ 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{
+		if r.Method != "GET" {
+			return false
+		}
+		fmt.Fprintf(w, "<h2>Single-node VictoriaMetrics</h2></br>")
+		fmt.Fprintf(w, "See docs at <a href='https://docs.victoriametrics.com/'>https://docs.victoriametrics.com/</a></br>")
+		fmt.Fprintf(w, "Useful endpoints:</br>")
+		httpserver.WriteAPIHelp(w, [][2]string{
+			{"/vmui", "Web UI"},
 			{"/targets", "discovered targets list"},
 			{"/api/v1/targets", "advanced information about discovered targets in JSON format"},
 			{"/metrics", "available service metrics"},
 			{"/api/v1/status/tsdb", "tsdb status page"},
+			{"/api/v1/status/top_queries", "top queries"},
+			{"/api/v1/status/active_queries", "active queries"},
 		})
 		return true
 	}
@@ -109,20 +112,11 @@ 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/
+See the docs at https://docs.victoriametrics.com/
 `
 	flagutil.Usage(s)
 }

app/victoria-metrics/main_test.go

@@ -22,7 +22,6 @@ import (
 	"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"
@@ -149,7 +148,7 @@ func setUp() {
 }
 
 func processFlags() {
-	envflag.Parse()
+	flag.Parse()
 	for _, fv := range []struct {
 		flag  string
 		value string

app/victoria-metrics/multiarch/Dockerfile

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

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

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

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

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

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

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

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

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

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

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

app/vmagent/Makefile

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

app/vmagent/csvimport/request_handler.go

@@ -5,32 +5,35 @@ import (
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/common"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
 	parserCommon "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
 	parser "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/csvimport"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
 	"github.com/VictoriaMetrics/metrics"
 )
 
 var (
-	rowsInserted  = metrics.NewCounter(`vmagent_rows_inserted_total{type="csvimport"}`)
-	rowsPerInsert = metrics.NewHistogram(`vmagent_rows_per_insert{type="csvimport"}`)
+	rowsInserted       = metrics.NewCounter(`vmagent_rows_inserted_total{type="csvimport"}`)
+	rowsTenantInserted = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_rows_total{type="csvimport"}`)
+	rowsPerInsert      = metrics.NewHistogram(`vmagent_rows_per_insert{type="csvimport"}`)
 )
 
 // InsertHandler processes csv data from req.
-func InsertHandler(req *http.Request) error {
+func InsertHandler(at *auth.Token, req *http.Request) error {
 	extraLabels, err := parserCommon.GetExtraLabels(req)
 	if err != nil {
 		return err
 	}
 	return writeconcurrencylimiter.Do(func() error {
 		return parser.ParseStream(req, func(rows []parser.Row) error {
-			return insertRows(rows, extraLabels)
+			return insertRows(at, rows, extraLabels)
 		})
 	})
 }
 
-func insertRows(rows []parser.Row, extraLabels []prompbmarshal.Label) error {
+func insertRows(at *auth.Token, rows []parser.Row, extraLabels []prompbmarshal.Label) error {
 	ctx := common.GetPushCtx()
 	defer common.PutPushCtx(ctx)
 
@@ -64,8 +67,11 @@ func insertRows(rows []parser.Row, extraLabels []prompbmarshal.Label) error {
 	ctx.WriteRequest.Timeseries = tssDst
 	ctx.Labels = labels
 	ctx.Samples = samples
-	remotewrite.Push(&ctx.WriteRequest)
+	remotewrite.PushWithAuthToken(at, &ctx.WriteRequest)
 	rowsInserted.Add(len(rows))
+	if at != nil {
+		rowsTenantInserted.Get(at).Add(len(rows))
+	}
 	rowsPerInsert.Update(float64(len(rows)))
 	return nil
 }

app/vmagent/influx/request_handler.go

@@ -8,34 +8,37 @@ import (
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/common"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/cgroup"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
 	parserCommon "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
 	parser "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/influx"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
 	"github.com/VictoriaMetrics/metrics"
 )
 
 var (
-	measurementFieldSeparator = flag.String("influxMeasurementFieldSeparator", "_", "Separator for '{measurement}{separator}{field_name}' metric name when inserted via Influx line protocol")
-	skipSingleField           = flag.Bool("influxSkipSingleField", false, "Uses '{measurement}' instead of '{measurement}{separator}{field_name}' for metic name if Influx line contains only a single field")
+	measurementFieldSeparator = flag.String("influxMeasurementFieldSeparator", "_", "Separator for '{measurement}{separator}{field_name}' metric name when inserted via InfluxDB line protocol")
+	skipSingleField           = flag.Bool("influxSkipSingleField", false, "Uses '{measurement}' instead of '{measurement}{separator}{field_name}' for metic name if InfluxDB line contains only a single field")
 	skipMeasurement           = flag.Bool("influxSkipMeasurement", false, "Uses '{field_name}' as a metric name while ignoring '{measurement}' and '-influxMeasurementFieldSeparator'")
 )
 
 var (
-	rowsInserted  = metrics.NewCounter(`vmagent_rows_inserted_total{type="influx"}`)
-	rowsPerInsert = metrics.NewHistogram(`vmagent_rows_per_insert{type="influx"}`)
+	rowsInserted       = metrics.NewCounter(`vmagent_rows_inserted_total{type="influx"}`)
+	rowsTenantInserted = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_rows_total{type="influx"}`)
+	rowsPerInsert      = metrics.NewHistogram(`vmagent_rows_per_insert{type="influx"}`)
 )
 
 // InsertHandlerForReader processes remote write for influx line protocol.
 //
 // See https://github.com/influxdata/telegraf/tree/master/plugins/inputs/socket_listener/
-func InsertHandlerForReader(r io.Reader) error {
+func InsertHandlerForReader(r io.Reader, isGzipped bool) error {
 	return writeconcurrencylimiter.Do(func() error {
-		return parser.ParseStream(r, false, "", "", func(db string, rows []parser.Row) error {
-			return insertRows(db, rows, nil)
+		return parser.ParseStream(r, isGzipped, "", "", func(db string, rows []parser.Row) error {
+			return insertRows(nil, db, rows, nil)
 		})
 	})
 }
@@ -43,7 +46,7 @@ func InsertHandlerForReader(r io.Reader) error {
 // InsertHandlerForHTTP processes remote write for influx line protocol.
 //
 // See https://github.com/influxdata/influxdb/blob/4cbdc197b8117fee648d62e2e5be75c6575352f0/tsdb/README.md
-func InsertHandlerForHTTP(req *http.Request) error {
+func InsertHandlerForHTTP(at *auth.Token, req *http.Request) error {
 	extraLabels, err := parserCommon.GetExtraLabels(req)
 	if err != nil {
 		return err
@@ -55,12 +58,12 @@ func InsertHandlerForHTTP(req *http.Request) error {
 		// 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, func(db string, rows []parser.Row) error {
-			return insertRows(db, rows, extraLabels)
+			return insertRows(at, db, rows, extraLabels)
 		})
 	})
 }
 
-func insertRows(db string, rows []parser.Row, extraLabels []prompbmarshal.Label) error {
+func insertRows(at *auth.Token, db string, rows []parser.Row, extraLabels []prompbmarshal.Label) error {
 	ctx := getPushCtx()
 	defer putPushCtx(ctx)
 
@@ -96,7 +99,8 @@ func insertRows(db string, rows []parser.Row, extraLabels []prompbmarshal.Label)
 		if !*skipMeasurement {
 			ctx.metricGroupBuf = append(ctx.metricGroupBuf, r.Measurement...)
 		}
-		skipFieldKey := len(r.Fields) == 1 && *skipSingleField
+		// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1139
+		skipFieldKey := len(r.Measurement) > 0 && len(r.Fields) == 1 && *skipSingleField
 		if len(ctx.metricGroupBuf) > 0 && !skipFieldKey {
 			ctx.metricGroupBuf = append(ctx.metricGroupBuf, *measurementFieldSeparator...)
 		}
@@ -129,8 +133,11 @@ func insertRows(db string, rows []parser.Row, extraLabels []prompbmarshal.Label)
 	ctx.ctx.Labels = labels
 	ctx.ctx.Samples = samples
 	ctx.commonLabels = commonLabels
-	remotewrite.Push(&ctx.ctx.WriteRequest)
+	remotewrite.PushWithAuthToken(at, &ctx.ctx.WriteRequest)
 	rowsInserted.Add(rowsTotal)
+	if at != nil {
+		rowsTenantInserted.Get(at).Add(rowsTotal)
+	}
 	rowsPerInsert.Update(float64(rowsTotal))
 
 	return nil

app/vmagent/main.go

@@ -3,6 +3,7 @@ package main
 import (
 	"flag"
 	"fmt"
+	"io"
 	"net/http"
 	"os"
 	"strings"
@@ -19,10 +20,12 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/promremotewrite"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/vmimport"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/buildinfo"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/envflag"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/influxutils"
 	graphiteserver "github.com/VictoriaMetrics/VictoriaMetrics/lib/ingestserver/graphite"
 	influxserver "github.com/VictoriaMetrics/VictoriaMetrics/lib/ingestserver/influx"
 	opentsdbserver "github.com/VictoriaMetrics/VictoriaMetrics/lib/ingestserver/opentsdb"
@@ -39,8 +42,8 @@ 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. "+
-		"This flag isn't needed when ingesting data over HTTP - just send it to `http://<vmagent>:8429/write`")
+	influxListenAddr = flag.String("influxListenAddr", "", "TCP and UDP address to listen for InfluxDB line protocol data. Usually :8189 must be set. Doesn't work if empty. "+
+		"This flag isn't needed when ingesting data over HTTP - just send it to http://<vmagent>:8429/write")
 	graphiteListenAddr = flag.String("graphiteListenAddr", "", "TCP and UDP address to listen for Graphite plaintext data. Usually :2003 must be set. Doesn't work if empty")
 	opentsdbListenAddr = flag.String("opentsdbListenAddr", "", "TCP and UDP address to listen for OpentTSDB metrics. "+
 		"Telnet put messages and HTTP /api/put messages are simultaneously served on TCP port. "+
@@ -91,7 +94,9 @@ func main() {
 	common.StartUnmarshalWorkers()
 	writeconcurrencylimiter.Init()
 	if len(*influxListenAddr) > 0 {
-		influxServer = influxserver.MustStart(*influxListenAddr, influx.InsertHandlerForReader)
+		influxServer = influxserver.MustStart(*influxListenAddr, func(r io.Reader) error {
+			return influx.InsertHandlerForReader(r, false)
+		})
 	}
 	if len(*graphiteListenAddr) > 0 {
 		graphiteServer = graphiteserver.MustStart(*graphiteListenAddr, graphite.InsertHandler)
@@ -144,70 +149,80 @@ func main() {
 
 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")
+		if r.Method != "GET" {
+			return false
+		}
+		fmt.Fprintf(w, "<h2>vmagent</h2>")
+		fmt.Fprintf(w, "See docs at <a href='https://docs.victoriametrics.com/vmagent.html'>https://docs.victoriametrics.com/vmagent.html</a></br>")
+		fmt.Fprintf(w, "Useful endpoints:</br>")
+		httpserver.WriteAPIHelp(w, [][2]string{
+			{"/targets", "discovered targets list"},
+			{"/api/v1/targets", "advanced information about discovered targets in JSON format"},
+			{"/metrics", "available service metrics"},
+			{"/-/reload", "reload configuration"},
+		})
 		return true
 	}
+
 	path := strings.Replace(r.URL.Path, "//", "/", -1)
 	switch path {
 	case "/api/v1/write":
 		prometheusWriteRequests.Inc()
-		if err := promremotewrite.InsertHandler(r); err != nil {
+		if err := promremotewrite.InsertHandler(nil, r); err != nil {
 			prometheusWriteErrors.Inc()
-			httpserver.Errorf(w, r, "error in %q: %s", r.URL.Path, err)
+			httpserver.Errorf(w, r, "%s", err)
 			return true
 		}
 		w.WriteHeader(http.StatusNoContent)
 		return true
 	case "/api/v1/import":
 		vmimportRequests.Inc()
-		if err := vmimport.InsertHandler(r); err != nil {
+		if err := vmimport.InsertHandler(nil, r); err != nil {
 			vmimportErrors.Inc()
-			httpserver.Errorf(w, r, "error in %q: %s", r.URL.Path, err)
+			httpserver.Errorf(w, r, "%s", err)
 			return true
 		}
 		w.WriteHeader(http.StatusNoContent)
 		return true
 	case "/api/v1/import/csv":
 		csvimportRequests.Inc()
-		if err := csvimport.InsertHandler(r); err != nil {
+		if err := csvimport.InsertHandler(nil, r); err != nil {
 			csvimportErrors.Inc()
-			httpserver.Errorf(w, r, "error in %q: %s", r.URL.Path, err)
+			httpserver.Errorf(w, r, "%s", err)
 			return true
 		}
 		w.WriteHeader(http.StatusNoContent)
 		return true
 	case "/api/v1/import/prometheus":
 		prometheusimportRequests.Inc()
-		if err := prometheusimport.InsertHandler(r); err != nil {
+		if err := prometheusimport.InsertHandler(nil, r); err != nil {
 			prometheusimportErrors.Inc()
-			httpserver.Errorf(w, r, "error in %q: %s", r.URL.Path, err)
+			httpserver.Errorf(w, r, "%s", err)
 			return true
 		}
 		w.WriteHeader(http.StatusNoContent)
 		return true
 	case "/api/v1/import/native":
 		nativeimportRequests.Inc()
-		if err := native.InsertHandler(r); err != nil {
+		if err := native.InsertHandler(nil, r); err != nil {
 			nativeimportErrors.Inc()
-			httpserver.Errorf(w, r, "error in %q: %s", r.URL.Path, err)
+			httpserver.Errorf(w, r, "%s", err)
 			return true
 		}
 		w.WriteHeader(http.StatusNoContent)
 		return true
 	case "/write", "/api/v2/write":
 		influxWriteRequests.Inc()
-		if err := influx.InsertHandlerForHTTP(r); err != nil {
+		if err := influx.InsertHandlerForHTTP(nil, r); err != nil {
 			influxWriteErrors.Inc()
-			httpserver.Errorf(w, r, "error in %q: %s", r.URL.Path, err)
+			httpserver.Errorf(w, r, "%s", err)
 			return true
 		}
 		w.WriteHeader(http.StatusNoContent)
 		return true
 	case "/query":
-		// Emulate fake response for influx query.
-		// This is required for TSBS benchmark.
 		influxQueryRequests.Inc()
-		fmt.Fprintf(w, `{"results":[{"series":[{"values":[]}]}]}`)
+		influxutils.WriteDatabaseNames(w)
 		return true
 	case "/targets":
 		promscrapeTargetsRequests.Inc()
@@ -235,9 +250,92 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 		}
 		return true
 	}
+	if remotewrite.MultitenancyEnabled() {
+		return processMultitenantRequest(w, r, path)
+	}
 	return false
 }
 
+func processMultitenantRequest(w http.ResponseWriter, r *http.Request, path string) bool {
+	p, err := httpserver.ParsePath(path)
+	if err != nil {
+		// Cannot parse multitenant path. Skip it - probably it will be parsed later.
+		return false
+	}
+	if p.Prefix != "insert" {
+		httpserver.Errorf(w, r, `unsupported multitenant prefix: %q; expected "insert"`, p.Prefix)
+		return true
+	}
+	at, err := auth.NewToken(p.AuthToken)
+	if err != nil {
+		httpserver.Errorf(w, r, "cannot obtain auth token: %s", err)
+		return true
+	}
+	switch p.Suffix {
+	case "prometheus/", "prometheus", "prometheus/api/v1/write":
+		prometheusWriteRequests.Inc()
+		if err := promremotewrite.InsertHandler(at, r); err != nil {
+			prometheusWriteErrors.Inc()
+			httpserver.Errorf(w, r, "%s", err)
+			return true
+		}
+		w.WriteHeader(http.StatusNoContent)
+		return true
+	case "prometheus/api/v1/import":
+		vmimportRequests.Inc()
+		if err := vmimport.InsertHandler(at, r); err != nil {
+			vmimportErrors.Inc()
+			httpserver.Errorf(w, r, "%s", err)
+			return true
+		}
+		w.WriteHeader(http.StatusNoContent)
+		return true
+	case "prometheus/api/v1/import/csv":
+		csvimportRequests.Inc()
+		if err := csvimport.InsertHandler(at, r); err != nil {
+			csvimportErrors.Inc()
+			httpserver.Errorf(w, r, "%s", err)
+			return true
+		}
+		w.WriteHeader(http.StatusNoContent)
+		return true
+	case "prometheus/api/v1/import/prometheus":
+		prometheusimportRequests.Inc()
+		if err := prometheusimport.InsertHandler(at, r); err != nil {
+			prometheusimportErrors.Inc()
+			httpserver.Errorf(w, r, "%s", err)
+			return true
+		}
+		w.WriteHeader(http.StatusNoContent)
+		return true
+	case "prometheus/api/v1/import/native":
+		nativeimportRequests.Inc()
+		if err := native.InsertHandler(at, r); err != nil {
+			nativeimportErrors.Inc()
+			httpserver.Errorf(w, r, "%s", err)
+			return true
+		}
+		w.WriteHeader(http.StatusNoContent)
+		return true
+	case "influx/write", "influx/api/v2/write":
+		influxWriteRequests.Inc()
+		if err := influx.InsertHandlerForHTTP(at, r); err != nil {
+			influxWriteErrors.Inc()
+			httpserver.Errorf(w, r, "%s", err)
+			return true
+		}
+		w.WriteHeader(http.StatusNoContent)
+		return true
+	case "influx/query":
+		influxQueryRequests.Inc()
+		influxutils.WriteDatabaseNames(w)
+		return true
+	default:
+		httpserver.Errorf(w, r, "unsupported multitenant path suffix: %q", p.Suffix)
+		return true
+	}
+}
+
 var (
 	prometheusWriteRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/api/v1/write", protocol="promremotewrite"}`)
 	prometheusWriteErrors   = metrics.NewCounter(`vmagent_http_request_errors_total{path="/api/v1/write", protocol="promremotewrite"}`)
@@ -269,7 +367,7 @@ 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 .
+See the docs at https://docs.victoriametrics.com/vmagent.html .
 `
 	flagutil.Usage(s)
 }

app/vmagent/multiarch/Dockerfile

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

app/vmagent/native/request_handler.go

@@ -5,36 +5,39 @@ import (
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/common"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
 	parserCommon "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
 	parser "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/native"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
 	"github.com/VictoriaMetrics/metrics"
 )
 
 var (
-	rowsInserted  = metrics.NewCounter(`vmagent_rows_inserted_total{type="native"}`)
-	rowsPerInsert = metrics.NewHistogram(`vmagent_rows_per_insert{type="native"}`)
+	rowsInserted       = metrics.NewCounter(`vmagent_rows_inserted_total{type="native"}`)
+	rowsTenantInserted = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_rows_total{type="native"}`)
+	rowsPerInsert      = metrics.NewHistogram(`vmagent_rows_per_insert{type="native"}`)
 )
 
 // InsertHandler processes `/api/v1/import` request.
 //
 // See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/6
-func InsertHandler(req *http.Request) error {
+func InsertHandler(at *auth.Token, req *http.Request) error {
 	extraLabels, err := parserCommon.GetExtraLabels(req)
 	if err != nil {
 		return err
 	}
 	return writeconcurrencylimiter.Do(func() error {
 		return parser.ParseStream(req, func(block *parser.Block) error {
-			return insertRows(block, extraLabels)
+			return insertRows(at, block, extraLabels)
 		})
 	})
 }
 
-func insertRows(block *parser.Block, extraLabels []prompbmarshal.Label) error {
+func insertRows(at *auth.Token, block *parser.Block, extraLabels []prompbmarshal.Label) error {
 	ctx := common.GetPushCtx()
 	defer common.PutPushCtx(ctx)
 
@@ -42,6 +45,9 @@ func insertRows(block *parser.Block, extraLabels []prompbmarshal.Label) error {
 	// since relabeling can prevent from inserting the rows.
 	rowsLen := len(block.Values)
 	rowsInserted.Add(rowsLen)
+	if at != nil {
+		rowsTenantInserted.Get(at).Add(rowsLen)
+	}
 	rowsPerInsert.Update(float64(rowsLen))
 
 	tssDst := ctx.WriteRequest.Timeseries[:0]
@@ -80,6 +86,6 @@ func insertRows(block *parser.Block, extraLabels []prompbmarshal.Label) error {
 	ctx.WriteRequest.Timeseries = tssDst
 	ctx.Labels = labels
 	ctx.Samples = samples
-	remotewrite.Push(&ctx.WriteRequest)
+	remotewrite.PushWithAuthToken(at, &ctx.WriteRequest)
 	return nil
 }

app/vmagent/prometheusimport/request_handler.go

@@ -1,24 +1,28 @@
 package prometheusimport
 
 import (
+	"io"
 	"net/http"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/common"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
 	parserCommon "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
 	parser "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/prometheus"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
 	"github.com/VictoriaMetrics/metrics"
 )
 
 var (
-	rowsInserted  = metrics.NewCounter(`vmagent_rows_inserted_total{type="prometheus"}`)
-	rowsPerInsert = metrics.NewHistogram(`vmagent_rows_per_insert{type="prometheus"}`)
+	rowsInserted       = metrics.NewCounter(`vmagent_rows_inserted_total{type="prometheus"}`)
+	rowsTenantInserted = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_rows_total{type="prometheus"}`)
+	rowsPerInsert      = metrics.NewHistogram(`vmagent_rows_per_insert{type="prometheus"}`)
 )
 
 // InsertHandler processes `/api/v1/import/prometheus` request.
-func InsertHandler(req *http.Request) error {
+func InsertHandler(at *auth.Token, req *http.Request) error {
 	extraLabels, err := parserCommon.GetExtraLabels(req)
 	if err != nil {
 		return err
@@ -30,12 +34,21 @@ func InsertHandler(req *http.Request) error {
 	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)
+			return insertRows(at, rows, extraLabels)
 		}, nil)
 	})
 }
 
-func insertRows(rows []parser.Row, extraLabels []prompbmarshal.Label) error {
+// InsertHandlerForReader processes metrics from given reader with optional gzip format
+func InsertHandlerForReader(r io.Reader, isGzipped bool) error {
+	return writeconcurrencylimiter.Do(func() error {
+		return parser.ParseStream(r, 0, isGzipped, func(rows []parser.Row) error {
+			return insertRows(nil, rows, nil)
+		}, nil)
+	})
+}
+
+func insertRows(at *auth.Token, rows []parser.Row, extraLabels []prompbmarshal.Label) error {
 	ctx := common.GetPushCtx()
 	defer common.PutPushCtx(ctx)
 
@@ -69,8 +82,11 @@ func insertRows(rows []parser.Row, extraLabels []prompbmarshal.Label) error {
 	ctx.WriteRequest.Timeseries = tssDst
 	ctx.Labels = labels
 	ctx.Samples = samples
-	remotewrite.Push(&ctx.WriteRequest)
+	remotewrite.PushWithAuthToken(at, &ctx.WriteRequest)
 	rowsInserted.Add(len(rows))
+	if at != nil {
+		rowsTenantInserted.Get(at).Add(len(rows))
+	}
 	rowsPerInsert.Update(float64(len(rows)))
 	return nil
 }

app/vmagent/promremotewrite/request_handler.go

@@ -1,38 +1,51 @@
 package promremotewrite
 
 import (
+	"io"
 	"net/http"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/common"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
 	parserCommon "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
 	parser "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/promremotewrite"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
 	"github.com/VictoriaMetrics/metrics"
 )
 
 var (
-	rowsInserted  = metrics.NewCounter(`vmagent_rows_inserted_total{type="promremotewrite"}`)
-	rowsPerInsert = metrics.NewHistogram(`vmagent_rows_per_insert{type="promremotewrite"}`)
+	rowsInserted       = metrics.NewCounter(`vmagent_rows_inserted_total{type="promremotewrite"}`)
+	rowsTenantInserted = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_rows_total{type="promremotewrite"}`)
+	rowsPerInsert      = metrics.NewHistogram(`vmagent_rows_per_insert{type="promremotewrite"}`)
 )
 
 // InsertHandler processes remote write for prometheus.
-func InsertHandler(req *http.Request) error {
+func InsertHandler(at *auth.Token, req *http.Request) error {
 	extraLabels, err := parserCommon.GetExtraLabels(req)
 	if err != nil {
 		return err
 	}
 	return writeconcurrencylimiter.Do(func() error {
-		return parser.ParseStream(req, func(tss []prompb.TimeSeries) error {
-			return insertRows(tss, extraLabels)
+		return parser.ParseStream(req.Body, func(tss []prompb.TimeSeries) error {
+			return insertRows(at, tss, extraLabels)
 		})
 	})
 }
 
-func insertRows(timeseries []prompb.TimeSeries, extraLabels []prompbmarshal.Label) error {
+// InsertHandlerForReader processes metrics from given reader
+func InsertHandlerForReader(r io.Reader) error {
+	return writeconcurrencylimiter.Do(func() error {
+		return parser.ParseStream(r, func(tss []prompb.TimeSeries) error {
+			return insertRows(nil, tss, nil)
+		})
+	})
+}
+
+func insertRows(at *auth.Token, timeseries []prompb.TimeSeries, extraLabels []prompbmarshal.Label) error {
 	ctx := common.GetPushCtx()
 	defer common.PutPushCtx(ctx)
 
@@ -68,8 +81,11 @@ func insertRows(timeseries []prompb.TimeSeries, extraLabels []prompbmarshal.Labe
 	ctx.WriteRequest.Timeseries = tssDst
 	ctx.Labels = labels
 	ctx.Samples = samples
-	remotewrite.Push(&ctx.WriteRequest)
+	remotewrite.PushWithAuthToken(at, &ctx.WriteRequest)
 	rowsInserted.Add(rowsTotal)
+	if at != nil {
+		rowsTenantInserted.Get(at).Add(rowsTotal)
+	}
 	rowsPerInsert.Update(float64(rowsTotal))
 	return nil
 }

app/vmagent/remotewrite/client.go

@@ -2,8 +2,6 @@ package remotewrite
 
 import (
 	"bytes"
-	"crypto/tls"
-	"encoding/base64"
 	"fmt"
 	"io/ioutil"
 	"net/http"
@@ -42,17 +40,35 @@ var (
 		"If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url")
 	basicAuthPassword = flagutil.NewArray("remoteWrite.basicAuth.password", "Optional basic auth password to use for -remoteWrite.url. "+
 		"If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url")
+	basicAuthPasswordFile = flagutil.NewArray("remoteWrite.basicAuth.passwordFile", "Optional path to basic auth password to use for -remoteWrite.url. "+
+		"The file is re-read every second. "+
+		"If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url")
 	bearerToken = flagutil.NewArray("remoteWrite.bearerToken", "Optional bearer auth token to use for -remoteWrite.url. "+
 		"If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url")
+	bearerTokenFile = flagutil.NewArray("remoteWrite.bearerTokenFile", "Optional path to bearer token file to use for -remoteWrite.url. "+
+		"The token is re-read from the file every second. "+
+		"If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url")
+
+	oauth2ClientID = flagutil.NewArray("remoteWrite.oauth2.clientID", "Optional OAuth2 clientID to use for -remoteWrite.url. "+
+		"If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url")
+	oauth2ClientSecret = flagutil.NewArray("remoteWrite.oauth2.clientSecret", "Optional OAuth2 clientSecret to use for -remoteWrite.url. "+
+		"If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url")
+	oauth2ClientSecretFile = flagutil.NewArray("remoteWrite.oauth2.clientSecretFile", "Optional OAuth2 clientSecretFile to use for -remoteWrite.url. "+
+		"If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url")
+	oauth2TokenURL = flagutil.NewArray("remoteWrite.oauth2.tokenUrl", "Optional OAuth2 tokenURL to use for -remoteWrite.url. "+
+		"If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url")
+	oauth2Scopes = flagutil.NewArray("remoteWrite.oauth2.scopes", "Optional OAuth2 scopes to use for -remoteWrite.url. Scopes must be delimited by ';'. "+
+		"If multiple args are set, then they are applied independently for the corresponding -remoteWrite.url")
 )
 
 type client struct {
 	sanitizedURL   string
 	remoteWriteURL string
-	authHeader     string
 	fq             *persistentqueue.FastQueue
 	hc             *http.Client
 
+	authCfg *promauth.Config
+
 	rl rateLimiter
 
 	bytesSent       *metrics.Counter
@@ -62,16 +78,18 @@ type client struct {
 	errorsCount     *metrics.Counter
 	packetsDropped  *metrics.Counter
 	retriesCount    *metrics.Counter
+	sendDuration    *metrics.FloatCounter
 
 	wg     sync.WaitGroup
 	stopCh chan struct{}
 }
 
 func newClient(argIdx int, remoteWriteURL, sanitizedURL string, fq *persistentqueue.FastQueue, concurrency int) *client {
-	tlsCfg, err := getTLSConfig(argIdx)
+	authCfg, err := getAuthConfig(argIdx)
 	if err != nil {
-		logger.Panicf("FATAL: cannot initialize TLS config: %s", err)
+		logger.Panicf("FATAL: cannot initialize auth config: %s", err)
 	}
+	tlsCfg := authCfg.NewTLSConfig()
 	tr := &http.Transport{
 		Dial:                statDial,
 		TLSClientConfig:     tlsCfg,
@@ -92,26 +110,10 @@ func newClient(argIdx int, remoteWriteURL, sanitizedURL string, fq *persistentqu
 		}
 		tr.Proxy = http.ProxyURL(urlProxy)
 	}
-	authHeader := ""
-	username := basicAuthUsername.GetOptionalArg(argIdx)
-	password := basicAuthPassword.GetOptionalArg(argIdx)
-	if len(username) > 0 || len(password) > 0 {
-		// See https://en.wikipedia.org/wiki/Basic_access_authentication
-		token := username + ":" + password
-		token64 := base64.StdEncoding.EncodeToString([]byte(token))
-		authHeader = "Basic " + token64
-	}
-	token := bearerToken.GetOptionalArg(argIdx)
-	if len(token) > 0 {
-		if authHeader != "" {
-			logger.Fatalf("`-remoteWrite.bearerToken`=%q cannot be set when `-remoteWrite.basicAuth.*` flags are set", token)
-		}
-		authHeader = "Bearer " + token
-	}
 	c := &client{
 		sanitizedURL:   sanitizedURL,
 		remoteWriteURL: remoteWriteURL,
-		authHeader:     authHeader,
+		authCfg:        authCfg,
 		fq:             fq,
 		hc: &http.Client{
 			Transport: tr,
@@ -132,6 +134,7 @@ func newClient(argIdx int, remoteWriteURL, sanitizedURL string, fq *persistentqu
 	c.errorsCount = metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_errors_total{url=%q}`, c.sanitizedURL))
 	c.packetsDropped = metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_packets_dropped_total{url=%q}`, c.sanitizedURL))
 	c.retriesCount = metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_retries_count_total{url=%q}`, c.sanitizedURL))
+	c.sendDuration = metrics.GetOrCreateFloatCounter(fmt.Sprintf(`vmagent_remotewrite_send_duration_seconds_total{url=%q}`, c.sanitizedURL))
 	for i := 0; i < concurrency; i++ {
 		c.wg.Add(1)
 		go func() {
@@ -149,58 +152,94 @@ func (c *client) MustStop() {
 	logger.Infof("stopped client for -remoteWrite.url=%q", c.sanitizedURL)
 }
 
-func getTLSConfig(argIdx int) (*tls.Config, error) {
-	c := &promauth.TLSConfig{
+func getAuthConfig(argIdx int) (*promauth.Config, error) {
+	username := basicAuthUsername.GetOptionalArg(argIdx)
+	password := basicAuthPassword.GetOptionalArg(argIdx)
+	passwordFile := basicAuthPasswordFile.GetOptionalArg(argIdx)
+	var basicAuthCfg *promauth.BasicAuthConfig
+	if username != "" || password != "" || passwordFile != "" {
+		basicAuthCfg = &promauth.BasicAuthConfig{
+			Username:     username,
+			Password:     password,
+			PasswordFile: passwordFile,
+		}
+	}
+
+	token := bearerToken.GetOptionalArg(argIdx)
+	tokenFile := bearerTokenFile.GetOptionalArg(argIdx)
+
+	var oauth2Cfg *promauth.OAuth2Config
+	clientSecret := oauth2ClientSecret.GetOptionalArg(argIdx)
+	clientSecretFile := oauth2ClientSecretFile.GetOptionalArg(argIdx)
+	if clientSecretFile != "" || clientSecret != "" {
+		oauth2Cfg = &promauth.OAuth2Config{
+			ClientID:         oauth2ClientID.GetOptionalArg(argIdx),
+			ClientSecret:     clientSecret,
+			ClientSecretFile: clientSecretFile,
+			TokenURL:         oauth2TokenURL.GetOptionalArg(argIdx),
+			Scopes:           strings.Split(oauth2Scopes.GetOptionalArg(argIdx), ";"),
+		}
+	}
+
+	tlsCfg := &promauth.TLSConfig{
 		CAFile:             tlsCAFile.GetOptionalArg(argIdx),
 		CertFile:           tlsCertFile.GetOptionalArg(argIdx),
 		KeyFile:            tlsKeyFile.GetOptionalArg(argIdx),
 		ServerName:         tlsServerName.GetOptionalArg(argIdx),
 		InsecureSkipVerify: tlsInsecureSkipVerify.GetOptionalArg(argIdx),
 	}
-	if c.CAFile == "" && c.CertFile == "" && c.KeyFile == "" && c.ServerName == "" && !c.InsecureSkipVerify {
-		return nil, nil
-	}
-	cfg, err := promauth.NewConfig(".", nil, "", "", c)
+
+	authCfg, err := promauth.NewConfig(".", nil, basicAuthCfg, token, tokenFile, oauth2Cfg, tlsCfg)
 	if err != nil {
-		return nil, fmt.Errorf("cannot populate TLS config: %w", err)
+		return nil, fmt.Errorf("cannot populate OAuth2 config for remoteWrite idx: %d, err: %w", argIdx, err)
 	}
-	tlsCfg := cfg.NewTLSConfig()
-	return tlsCfg, nil
+	return authCfg, nil
 }
 
 func (c *client) runWorker() {
 	var ok bool
 	var block []byte
-	ch := make(chan struct{})
+	ch := make(chan bool, 1)
 	for {
 		block, ok = c.fq.MustReadBlock(block[:0])
 		if !ok {
 			return
 		}
 		go func() {
-			c.sendBlock(block)
-			ch <- struct{}{}
+			startTime := time.Now()
+			ch <- c.sendBlock(block)
+			c.sendDuration.Add(time.Since(startTime).Seconds())
 		}()
 		select {
-		case <-ch:
-			// The block has been sent successfully
-			continue
+		case ok := <-ch:
+			if ok {
+				// The block has been sent successfully
+				continue
+			}
+			// Return unsent block to the queue.
+			c.fq.MustWriteBlock(block)
+			return
 		case <-c.stopCh:
 			// c must be stopped. Wait for a while in the hope the block will be sent.
 			graceDuration := 5 * time.Second
 			select {
-			case <-ch:
-				// The block has been sent successfully.
+			case ok := <-ch:
+				if !ok {
+					// Return unsent block to the queue.
+					c.fq.MustWriteBlock(block)
+				}
 			case <-time.After(graceDuration):
-				logger.Errorf("couldn't sent block with size %d bytes to %q in %.3f seconds during shutdown; dropping it",
-					len(block), c.sanitizedURL, graceDuration.Seconds())
+				// Return unsent block to the queue.
+				c.fq.MustWriteBlock(block)
 			}
 			return
 		}
 	}
 }
 
-func (c *client) sendBlock(block []byte) {
+// sendBlock returns false only if c.stopCh is closed.
+// Otherwise it tries sending the block to remote storage indefinitely.
+func (c *client) sendBlock(block []byte) bool {
 	c.rl.register(len(block), c.stopCh)
 	retryDuration := time.Second
 	retriesCount := 0
@@ -217,8 +256,8 @@ again:
 	h.Set("Content-Type", "application/x-protobuf")
 	h.Set("Content-Encoding", "snappy")
 	h.Set("X-Prometheus-Remote-Write-Version", "0.1.0")
-	if c.authHeader != "" {
-		req.Header.Set("Authorization", c.authHeader)
+	if ah := c.authCfg.GetAuthHeader(); ah != "" {
+		req.Header.Set("Authorization", ah)
 	}
 
 	startTime := time.Now()
@@ -230,13 +269,13 @@ again:
 		if retryDuration > time.Minute {
 			retryDuration = time.Minute
 		}
-		logger.Errorf("couldn't send a block with size %d bytes to %q: %s; re-sending the block in %.3f seconds",
+		logger.Warnf("couldn't send a block with size %d bytes to %q: %s; re-sending the block in %.3f seconds",
 			len(block), c.sanitizedURL, err, retryDuration.Seconds())
 		t := timerpool.Get(retryDuration)
 		select {
 		case <-c.stopCh:
 			timerpool.Put(t)
-			return
+			return false
 		case <-t.C:
 			timerpool.Put(t)
 		}
@@ -247,18 +286,16 @@ again:
 	if statusCode/100 == 2 {
 		_ = resp.Body.Close()
 		c.requestsOKCount.Inc()
-		return
+		return true
 	}
 	metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_requests_total{url=%q, status_code="%d"}`, c.sanitizedURL, statusCode)).Inc()
-	if statusCode == 409 {
-		// Just drop block on 409 status code like Prometheus does.
+	if statusCode == 409 || statusCode == 400 {
+		// Just drop block on 409 and 400 status codes like Prometheus does.
 		// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/873
-		body, _ := ioutil.ReadAll(resp.Body)
+		// and https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1149
 		_ = resp.Body.Close()
-		logger.Errorf("unexpected status code received when sending a block with size %d bytes to %q: #%d; dropping the block like Prometheus does; "+
-			"response body=%q", len(block), c.sanitizedURL, statusCode, body)
 		c.packetsDropped.Inc()
-		return
+		return true
 	}
 
 	// Unexpected status code returned
@@ -279,7 +316,7 @@ again:
 	select {
 	case <-c.stopCh:
 		timerpool.Put(t)
-		return
+		return false
 	case <-t.C:
 		timerpool.Put(t)
 	}
@@ -290,6 +327,9 @@ again:
 type rateLimiter struct {
 	perSecondLimit int64
 
+	// mu protects budget and deadline from concurrent access.
+	mu sync.Mutex
+
 	// The current budget. It is increased by perSecondLimit every second.
 	budget int64
 
@@ -304,9 +344,12 @@ func (rl *rateLimiter) register(dataLen int, stopCh <-chan struct{}) {
 	if limit <= 0 {
 		return
 	}
+
+	rl.mu.Lock()
+	defer rl.mu.Unlock()
+
 	for rl.budget <= 0 {
-		now := time.Now()
-		if d := rl.deadline.Sub(now); d > 0 {
+		if d := time.Until(rl.deadline); d > 0 {
 			rl.limitReached.Inc()
 			t := timerpool.Get(d)
 			select {
@@ -318,7 +361,7 @@ func (rl *rateLimiter) register(dataLen int, stopCh <-chan struct{}) {
 			}
 		}
 		rl.budget += limit
-		rl.deadline = now.Add(time.Second)
+		rl.deadline = time.Now().Add(time.Second)
 	}
 	rl.budget -= int64(dataLen)
 }

app/vmagent/remotewrite/pendingseries.go

@@ -19,8 +19,7 @@ import (
 
 var (
 	flushInterval = flag.Duration("remoteWrite.flushInterval", time.Second, "Interval for flushing the data to remote storage. "+
-		"Higher value reduces network bandwidth usage at the cost of delayed push of scraped data to remote storage. "+
-		"Minimum supported interval is 1 second")
+		"This option takes effect only when less than 10K data points per second are pushed to -remoteWrite.url")
 	maxUnpackedBlockSize = flagutil.NewBytes("remoteWrite.maxBlockSize", 8*1024*1024, "The maximum size in bytes of unpacked request to send to remote storage. "+
 		"It shouldn't exceed -maxInsertRequestSize from VictoriaMetrics")
 )
@@ -28,6 +27,9 @@ var (
 // the maximum number of rows to send per each block.
 const maxRowsPerBlock = 10000
 
+// the maximum number of labels to send per each block.
+const maxLabelsPerBlock = 10 * maxRowsPerBlock
+
 type pendingSeries struct {
 	mu sync.Mutex
 	wr writeRequest
@@ -154,7 +156,7 @@ func (wr *writeRequest) push(src []prompbmarshal.TimeSeries) {
 	for i := range src {
 		tssDst = append(tssDst, prompbmarshal.TimeSeries{})
 		wr.copyTimeSeries(&tssDst[len(tssDst)-1], &src[i])
-		if len(wr.samples) >= maxRowsPerBlock {
+		if len(wr.samples) >= maxRowsPerBlock || len(wr.labels) >= maxLabelsPerBlock {
 			wr.tss = tssDst
 			wr.flush()
 			tssDst = wr.tss

app/vmagent/remotewrite/relabel.go

@@ -14,10 +14,15 @@ import (
 
 var (
 	unparsedLabelsGlobal = flagutil.NewArray("remoteWrite.label", "Optional label in the form 'name=value' to add to all the metrics before sending them to -remoteWrite.url. "+
-		"Pass multiple -remoteWrite.label flags in order to add multiple flags to metrics before sending them to remote storage")
+		"Pass multiple -remoteWrite.label flags in order to add multiple labels to metrics before sending them to remote storage")
 	relabelConfigPathGlobal = flag.String("remoteWrite.relabelConfig", "", "Optional path to file with relabel_config entries. These entries are applied to all the metrics "+
-		"before sending them to -remoteWrite.url. See https://victoriametrics.github.io/vmagent.html#relabeling for details")
+		"before sending them to -remoteWrite.url. See https://docs.victoriametrics.com/vmagent.html#relabeling for details")
+	relabelDebugGlobal = flag.Bool("remoteWrite.relabelDebug", false, "Whether to log metrics before and after relabeling with -remoteWrite.relabelConfig. "+
+		"If the -remoteWrite.relabelDebug is enabled, then the metrics aren't sent to remote storage. This is useful for debugging the relabeling configs")
 	relabelConfigPaths = flagutil.NewArray("remoteWrite.urlRelabelConfig", "Optional path to relabel config for the corresponding -remoteWrite.url")
+	relabelDebug       = flagutil.NewArrayBool("remoteWrite.urlRelabelDebug", "Whether to log metrics before and after relabeling with -remoteWrite.urlRelabelConfig. "+
+		"If the -remoteWrite.urlRelabelDebug is enabled, then the metrics aren't sent to the corresponding -remoteWrite.url. "+
+		"This is useful for debugging the relabeling configs")
 )
 
 var labelsGlobal []prompbmarshal.Label
@@ -31,23 +36,23 @@ func CheckRelabelConfigs() error {
 func loadRelabelConfigs() (*relabelConfigs, error) {
 	var rcs relabelConfigs
 	if *relabelConfigPathGlobal != "" {
-		global, err := promrelabel.LoadRelabelConfigs(*relabelConfigPathGlobal)
+		global, err := promrelabel.LoadRelabelConfigs(*relabelConfigPathGlobal, *relabelDebugGlobal)
 		if err != nil {
 			return nil, fmt.Errorf("cannot load -remoteWrite.relabelConfig=%q: %w", *relabelConfigPathGlobal, err)
 		}
 		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))
+	if len(*relabelConfigPaths) > (len(*remoteWriteURLs) + len(*remoteWriteMultitenantURLs)) {
+		return nil, fmt.Errorf("too many -remoteWrite.urlRelabelConfig args: %d; it mustn't exceed the number of -remoteWrite.url or -remoteWrite.multitenantURL args: %d",
+			len(*relabelConfigPaths), (len(*remoteWriteURLs) + len(*remoteWriteMultitenantURLs)))
 	}
-	rcs.perURL = make([][]promrelabel.ParsedRelabelConfig, len(*remoteWriteURLs))
+	rcs.perURL = make([]*promrelabel.ParsedConfigs, (len(*remoteWriteURLs) + len(*remoteWriteMultitenantURLs)))
 	for i, path := range *relabelConfigPaths {
 		if len(path) == 0 {
 			// Skip empty relabel config.
 			continue
 		}
-		prc, err := promrelabel.LoadRelabelConfigs(path)
+		prc, err := promrelabel.LoadRelabelConfigs(path, relabelDebug.GetOptionalArg(i))
 		if err != nil {
 			return nil, fmt.Errorf("cannot load relabel configs from -remoteWrite.urlRelabelConfig=%q: %w", path, err)
 		}
@@ -57,8 +62,8 @@ func loadRelabelConfigs() (*relabelConfigs, error) {
 }
 
 type relabelConfigs struct {
-	global []promrelabel.ParsedRelabelConfig
-	perURL [][]promrelabel.ParsedRelabelConfig
+	global *promrelabel.ParsedConfigs
+	perURL []*promrelabel.ParsedConfigs
 }
 
 // initLabelsGlobal must be called after parsing command-line flags.
@@ -79,8 +84,8 @@ func initLabelsGlobal() {
 	}
 }
 
-func (rctx *relabelCtx) applyRelabeling(tss []prompbmarshal.TimeSeries, extraLabels []prompbmarshal.Label, prcs []promrelabel.ParsedRelabelConfig) []prompbmarshal.TimeSeries {
-	if len(extraLabels) == 0 && len(prcs) == 0 {
+func (rctx *relabelCtx) applyRelabeling(tss []prompbmarshal.TimeSeries, extraLabels []prompbmarshal.Label, pcs *promrelabel.ParsedConfigs) []prompbmarshal.TimeSeries {
+	if len(extraLabels) == 0 && pcs.Len() == 0 {
 		// Nothing to change.
 		return tss
 	}
@@ -100,7 +105,7 @@ func (rctx *relabelCtx) applyRelabeling(tss []prompbmarshal.TimeSeries, extraLab
 				labels = append(labels, *extraLabel)
 			}
 		}
-		labels = promrelabel.ApplyRelabelConfigs(labels, labelsLen, prcs, true)
+		labels = pcs.Apply(labels, labelsLen, true)
 		if len(labels) == labelsLen {
 			// Drop the current time series, since relabeling removed all the labels.
 			continue

app/vmagent/remotewrite/remotewrite.go

@@ -3,9 +3,14 @@ package remotewrite
 import (
 	"flag"
 	"fmt"
+	"strconv"
 	"sync"
 	"sync/atomic"
+	"time"
 
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bloomfilter"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/cgroup"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
@@ -13,6 +18,8 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/persistentqueue"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/procutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
 	"github.com/VictoriaMetrics/metrics"
 	xxhash "github.com/cespare/xxhash/v2"
 )
@@ -20,10 +27,14 @@ import (
 var (
 	remoteWriteURLs = flagutil.NewArray("remoteWrite.url", "Remote storage URL to write data to. It must support Prometheus remote_write API. "+
 		"It is recommended using VictoriaMetrics as remote storage. Example url: http://<victoriametrics-host>:8428/api/v1/write . "+
-		"Pass multiple -remoteWrite.url flags in order to write data concurrently to multiple remote storage systems")
-	tmpDataPath = flag.String("remoteWrite.tmpDataPath", "vmagent-remotewrite-data", "Path to directory where temporary data for remote write component is stored")
-	queues      = flag.Int("remoteWrite.queues", 4, "The number of concurrent queues to each -remoteWrite.url. Set more queues if default number of queues "+
-		"isn't enough for sending high volume of collected data to remote storage")
+		"Pass multiple -remoteWrite.url flags in order to replicate data to multiple remote storage systems. See also -remoteWrite.multitenantURL")
+	remoteWriteMultitenantURLs = flagutil.NewArray("remoteWrite.multitenantURL", "Base path for multitenant remote storage URL to write data to. "+
+		"See https://docs.victoriametrics.com/vmagent.html#multitenancy for details. Example url: http://<vminsert>:8480 . "+
+		"Pass multiple -remoteWrite.multitenantURL flags in order to replicate data to multiple remote storage systems. See also -remoteWrite.url")
+	tmpDataPath = flag.String("remoteWrite.tmpDataPath", "vmagent-remotewrite-data", "Path to directory where temporary data for remote write component is stored. "+
+		"See also -remoteWrite.maxDiskUsagePerURL")
+	queues = flag.Int("remoteWrite.queues", cgroup.AvailableCPUs()*2, "The number of concurrent queues to each -remoteWrite.url. Set more queues if default number of queues "+
+		"isn't enough for sending high volume of collected data to remote storage. Default value is 2 * numberOfAvailableCPUs")
 	showRemoteWriteURL = flag.Bool("remoteWrite.showURL", false, "Whether to show -remoteWrite.url in the exported metrics. "+
 		"It is hidden by default, since it can contain sensitive info such as auth key")
 	maxPendingBytesPerURL = flagutil.NewBytes("remoteWrite.maxDiskUsagePerURL", 0, "The maximum file-based buffer size in bytes at -remoteWrite.tmpDataPath "+
@@ -37,16 +48,39 @@ var (
 		"Examples: -remoteWrite.roundDigits=2 would round 1.236 to 1.24, while -remoteWrite.roundDigits=-1 would round 126.78 to 130. "+
 		"By default digits rounding is disabled. Set it to 100 for disabling it for a particular remote storage. "+
 		"This option may be used for improving data compression for the stored metrics")
+	sortLabels = flag.Bool("sortLabels", false, `Whether to sort labels for incoming samples before writing them to all the configured remote storage systems. `+
+		`This may be needed for reducing memory usage at remote storage when the order of labels in incoming samples is random. `+
+		`For example, if m{k1="v1",k2="v2"} may be sent as m{k2="v2",k1="v1"}`+
+		`Enabled sorting for labels can slow down ingestion performance a bit`)
+	maxHourlySeries = flag.Int("remoteWrite.maxHourlySeries", 0, "The maximum number of unique series vmagent can send to remote storage systems during the last hour. "+
+		"Excess series are logged and dropped. This can be useful for limiting series cardinality. See https://docs.victoriametrics.com/vmagent.html#cardinality-limiter")
+	maxDailySeries = flag.Int("remoteWrite.maxDailySeries", 0, "The maximum number of unique series vmagent can send to remote storage systems during the last 24 hours. "+
+		"Excess series are logged and dropped. This can be useful for limiting series churn rate. See https://docs.victoriametrics.com/vmagent.html#cardinality-limiter")
 )
 
-var rwctxs []*remoteWriteCtx
+var (
+	// rwctxsDefault contains statically populated entries when -remoteWrite.url is specified.
+	rwctxsDefault []*remoteWriteCtx
+
+	// rwctxsMap contains dynamically populated entries when -remoteWrite.multitenantURL is specified.
+	rwctxsMap     = make(map[tenantmetrics.TenantID][]*remoteWriteCtx)
+	rwctxsMapLock sync.Mutex
+
+	// Data without tenant id is written to defaultAuthToken if -remoteWrite.multitenantURL is specified.
+	defaultAuthToken = &auth.Token{}
+)
+
+// MultitenancyEnabled returns true if -remoteWrite.multitenantURL is specified.
+func MultitenancyEnabled() bool {
+	return len(*remoteWriteMultitenantURLs) > 0
+}
 
 // Contains the current relabelConfigs.
 var allRelabelConfigs atomic.Value
 
 // maxQueues limits the maximum value for `-remoteWrite.queues`. There is no sense in setting too high value,
 // since it may lead to high memory usage due to big number of buffers.
-var maxQueues = cgroup.AvailableCPUs() * 4
+var maxQueues = cgroup.AvailableCPUs() * 16
 
 // InitSecretFlags must be called after flag.Parse and before any logging.
 func InitSecretFlags() {
@@ -62,8 +96,29 @@ func InitSecretFlags() {
 //
 // Stop must be called for graceful shutdown.
 func Init() {
-	if len(*remoteWriteURLs) == 0 {
-		logger.Fatalf("at least one `-remoteWrite.url` command-line flag must be set")
+	if len(*remoteWriteURLs) == 0 && len(*remoteWriteMultitenantURLs) == 0 {
+		logger.Fatalf("at least one `-remoteWrite.url` or `-remoteWrite.multitenantURL` command-line flag must be set")
+	}
+	if len(*remoteWriteURLs) > 0 && len(*remoteWriteMultitenantURLs) > 0 {
+		logger.Fatalf("cannot set both `-remoteWrite.url` and `-remoteWrite.multitenantURL` command-line flags")
+	}
+	if *maxHourlySeries > 0 {
+		hourlySeriesLimiter = bloomfilter.NewLimiter(*maxHourlySeries, time.Hour)
+		_ = metrics.NewGauge(`vmagent_hourly_series_limit_max_series`, func() float64 {
+			return float64(hourlySeriesLimiter.MaxItems())
+		})
+		_ = metrics.NewGauge(`vmagent_hourly_series_limit_current_series`, func() float64 {
+			return float64(hourlySeriesLimiter.CurrentItems())
+		})
+	}
+	if *maxDailySeries > 0 {
+		dailySeriesLimiter = bloomfilter.NewLimiter(*maxDailySeries, 24*time.Hour)
+		_ = metrics.NewGauge(`vmagent_daily_series_limit_max_series`, func() float64 {
+			return float64(dailySeriesLimiter.MaxItems())
+		})
+		_ = metrics.NewGauge(`vmagent_daily_series_limit_current_series`, func() float64 {
+			return float64(dailySeriesLimiter.CurrentItems())
+		})
 	}
 	if *queues > maxQueues {
 		*queues = maxQueues
@@ -72,33 +127,23 @@ func Init() {
 		*queues = 1
 	}
 	initLabelsGlobal()
+
+	// Register SIGHUP handler for config reload before loadRelabelConfigs.
+	// This guarantees that the config will be re-read if the signal arrives just after loadRelabelConfig.
+	// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1240
+	sighupCh := procutil.NewSighupChan()
+
 	rcs, err := loadRelabelConfigs()
 	if err != nil {
 		logger.Fatalf("cannot load relabel configs: %s", err)
 	}
 	allRelabelConfigs.Store(rcs)
 
-	maxInmemoryBlocks := memory.Allowed() / len(*remoteWriteURLs) / maxRowsPerBlock / 100
-	if maxInmemoryBlocks > 200 {
-		// There is no much sense in keeping higher number of blocks in memory,
-		// since this means that the producer outperforms consumer and the queue
-		// will continue growing. It is better storing the queue to file.
-		maxInmemoryBlocks = 200
-	}
-	if maxInmemoryBlocks < 2 {
-		maxInmemoryBlocks = 2
-	}
-	for i, remoteWriteURL := range *remoteWriteURLs {
-		sanitizedURL := fmt.Sprintf("%d:secret-url", i+1)
-		if *showRemoteWriteURL {
-			sanitizedURL = fmt.Sprintf("%d:%s", i+1, remoteWriteURL)
-		}
-		rwctx := newRemoteWriteCtx(i, remoteWriteURL, maxInmemoryBlocks, sanitizedURL)
-		rwctxs = append(rwctxs, rwctx)
+	if len(*remoteWriteURLs) > 0 {
+		rwctxsDefault = newRemoteWriteCtxs(nil, *remoteWriteURLs)
 	}
 
 	// Start config reloader.
-	sighupCh := procutil.NewSighupChan()
 	configReloaderWG.Add(1)
 	go func() {
 		defer configReloaderWG.Done()
@@ -120,6 +165,37 @@ func Init() {
 	}()
 }
 
+func newRemoteWriteCtxs(at *auth.Token, urls []string) []*remoteWriteCtx {
+	if len(urls) == 0 {
+		logger.Panicf("BUG: urls must be non-empty")
+	}
+
+	maxInmemoryBlocks := memory.Allowed() / len(urls) / maxRowsPerBlock / 100
+	if maxInmemoryBlocks > 400 {
+		// There is no much sense in keeping higher number of blocks in memory,
+		// since this means that the producer outperforms consumer and the queue
+		// will continue growing. It is better storing the queue to file.
+		maxInmemoryBlocks = 400
+	}
+	if maxInmemoryBlocks < 2 {
+		maxInmemoryBlocks = 2
+	}
+	rwctxs := make([]*remoteWriteCtx, len(urls))
+	for i, remoteWriteURL := range urls {
+		sanitizedURL := fmt.Sprintf("%d:secret-url", i+1)
+		if at != nil {
+			// Construct full remote_write url for the given tenant according to https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html#url-format
+			remoteWriteURL = fmt.Sprintf("%s/insert/%d:%d/prometheus/api/v1/write", remoteWriteURL, at.AccountID, at.ProjectID)
+			sanitizedURL = fmt.Sprintf("%s:%d:%d", sanitizedURL, at.AccountID, at.ProjectID)
+		}
+		if *showRemoteWriteURL {
+			sanitizedURL = fmt.Sprintf("%d:%s", i+1, remoteWriteURL)
+		}
+		rwctxs[i] = newRemoteWriteCtx(i, remoteWriteURL, maxInmemoryBlocks, sanitizedURL)
+	}
+	return rwctxs
+}
+
 var stopCh = make(chan struct{})
 var configReloaderWG sync.WaitGroup
 
@@ -130,31 +206,79 @@ func Stop() {
 	close(stopCh)
 	configReloaderWG.Wait()
 
-	for _, rwctx := range rwctxs {
+	for _, rwctx := range rwctxsDefault {
 		rwctx.MustStop()
 	}
-	rwctxs = nil
+	rwctxsDefault = nil
+
+	// There is no need in locking rwctxsMapLock here, since nobody should call Push during the Stop call.
+	for _, rwctxs := range rwctxsMap {
+		for _, rwctx := range rwctxs {
+			rwctx.MustStop()
+		}
+	}
+	rwctxsMap = nil
+
+	if sl := hourlySeriesLimiter; sl != nil {
+		sl.MustStop()
+	}
+	if sl := dailySeriesLimiter; sl != nil {
+		sl.MustStop()
+	}
 }
 
 // Push sends wr to remote storage systems set via `-remoteWrite.url`.
 //
 // Note that wr may be modified by Push due to relabeling and rounding.
 func Push(wr *prompbmarshal.WriteRequest) {
+	PushWithAuthToken(nil, wr)
+}
+
+// PushWithAuthToken sends wr to remote storage systems set via `-remoteWrite.multitenantURL`.
+//
+// Note that wr may be modified by Push due to relabeling and rounding.
+func PushWithAuthToken(at *auth.Token, wr *prompbmarshal.WriteRequest) {
+	if at == nil && len(*remoteWriteMultitenantURLs) > 0 {
+		// Write data to default tenant if at isn't set while -remoteWrite.multitenantURL is set.
+		at = defaultAuthToken
+	}
+	var rwctxs []*remoteWriteCtx
+	if at == nil {
+		rwctxs = rwctxsDefault
+	} else {
+		if len(*remoteWriteMultitenantURLs) == 0 {
+			logger.Panicf("BUG: remoteWriteMultitenantURLs must be non-empty for non-nil at")
+		}
+		rwctxsMapLock.Lock()
+		tenantID := tenantmetrics.TenantID{
+			AccountID: at.AccountID,
+			ProjectID: at.ProjectID,
+		}
+		rwctxs = rwctxsMap[tenantID]
+		if rwctxs == nil {
+			rwctxs = newRemoteWriteCtxs(at, *remoteWriteMultitenantURLs)
+			rwctxsMap[tenantID] = rwctxs
+		}
+		rwctxsMapLock.Unlock()
+	}
+
 	var rctx *relabelCtx
 	rcs := allRelabelConfigs.Load().(*relabelConfigs)
-	prcsGlobal := rcs.global
-	if len(prcsGlobal) > 0 || len(labelsGlobal) > 0 {
+	pcsGlobal := rcs.global
+	if pcsGlobal.Len() > 0 || len(labelsGlobal) > 0 {
 		rctx = getRelabelCtx()
 	}
 	tss := wr.Timeseries
 	for len(tss) > 0 {
 		// Process big tss in smaller blocks in order to reduce the maximum memory usage
 		samplesCount := 0
+		labelsCount := 0
 		i := 0
 		for i < len(tss) {
 			samplesCount += len(tss[i].Samples)
+			labelsCount += len(tss[i].Labels)
 			i++
-			if samplesCount > maxRowsPerBlock {
+			if samplesCount >= maxRowsPerBlock || labelsCount >= maxLabelsPerBlock {
 				break
 			}
 		}
@@ -167,11 +291,15 @@ func Push(wr *prompbmarshal.WriteRequest) {
 		}
 		if rctx != nil {
 			tssBlockLen := len(tssBlock)
-			tssBlock = rctx.applyRelabeling(tssBlock, labelsGlobal, prcsGlobal)
+			tssBlock = rctx.applyRelabeling(tssBlock, labelsGlobal, pcsGlobal)
 			globalRelabelMetricsDropped.Add(tssBlockLen - len(tssBlock))
 		}
-		for _, rwctx := range rwctxs {
-			rwctx.Push(tssBlock)
+		sortLabelsIfNeeded(tssBlock)
+		tssBlock = limitSeriesCardinality(tssBlock)
+		if len(tssBlock) > 0 {
+			for _, rwctx := range rwctxs {
+				rwctx.Push(tssBlock)
+			}
 		}
 		if rctx != nil {
 			rctx.reset()
@@ -182,6 +310,87 @@ func Push(wr *prompbmarshal.WriteRequest) {
 	}
 }
 
+// sortLabelsIfNeeded sorts labels if -sortLabels command-line flag is set.
+func sortLabelsIfNeeded(tss []prompbmarshal.TimeSeries) {
+	if !*sortLabels {
+		return
+	}
+	for i := range tss {
+		promrelabel.SortLabels(tss[i].Labels)
+	}
+}
+
+func limitSeriesCardinality(tss []prompbmarshal.TimeSeries) []prompbmarshal.TimeSeries {
+	if hourlySeriesLimiter == nil && dailySeriesLimiter == nil {
+		return tss
+	}
+	dst := make([]prompbmarshal.TimeSeries, 0, len(tss))
+	for i := range tss {
+		labels := tss[i].Labels
+		h := getLabelsHash(labels)
+		if hourlySeriesLimiter != nil && !hourlySeriesLimiter.Add(h) {
+			hourlySeriesLimitRowsDropped.Add(len(tss[i].Samples))
+			logSkippedSeries(labels, "-remoteWrite.maxHourlySeries", hourlySeriesLimiter.MaxItems())
+			continue
+		}
+		if dailySeriesLimiter != nil && !dailySeriesLimiter.Add(h) {
+			dailySeriesLimitRowsDropped.Add(len(tss[i].Samples))
+			logSkippedSeries(labels, "-remoteWrite.maxDailySeries", dailySeriesLimiter.MaxItems())
+			continue
+		}
+		dst = append(dst, tss[i])
+	}
+	return dst
+}
+
+var (
+	hourlySeriesLimiter *bloomfilter.Limiter
+	dailySeriesLimiter  *bloomfilter.Limiter
+
+	hourlySeriesLimitRowsDropped = metrics.NewCounter(`vmagent_hourly_series_limit_rows_dropped_total`)
+	dailySeriesLimitRowsDropped  = metrics.NewCounter(`vmagent_daily_series_limit_rows_dropped_total`)
+)
+
+func getLabelsHash(labels []prompbmarshal.Label) uint64 {
+	bb := labelsHashBufPool.Get()
+	b := bb.B[:0]
+	for _, label := range labels {
+		b = append(b, label.Name...)
+		b = append(b, label.Value...)
+	}
+	h := xxhash.Sum64(b)
+	bb.B = b
+	labelsHashBufPool.Put(bb)
+	return h
+}
+
+var labelsHashBufPool bytesutil.ByteBufferPool
+
+func logSkippedSeries(labels []prompbmarshal.Label, flagName string, flagValue int) {
+	select {
+	case <-logSkippedSeriesTicker.C:
+		logger.Warnf("skip series %s because %s=%d reached", labelsToString(labels), flagName, flagValue)
+	default:
+	}
+}
+
+var logSkippedSeriesTicker = time.NewTicker(5 * time.Second)
+
+func labelsToString(labels []prompbmarshal.Label) string {
+	var b []byte
+	b = append(b, '{')
+	for i, label := range labels {
+		b = append(b, label.Name...)
+		b = append(b, '=')
+		b = strconv.AppendQuote(b, label.Value)
+		if i+1 < len(labels) {
+			b = append(b, ',')
+		}
+	}
+	b = append(b, '}')
+	return string(b)
+}
+
 var globalRelabelMetricsDropped = metrics.NewCounter("vmagent_remotewrite_global_relabel_metrics_dropped_total")
 
 type remoteWriteCtx struct {
@@ -207,7 +416,13 @@ func newRemoteWriteCtx(argIdx int, remoteWriteURL string, maxInmemoryBlocks int,
 	c := newClient(argIdx, remoteWriteURL, sanitizedURL, fq, *queues)
 	sf := significantFigures.GetOptionalArgOrDefault(argIdx, 0)
 	rd := roundDigits.GetOptionalArgOrDefault(argIdx, 100)
-	pss := make([]*pendingSeries, *queues)
+	pssLen := *queues
+	if n := cgroup.AvailableCPUs(); pssLen > n {
+		// There is no sense in running more than availableCPUs concurrent pendingSeries,
+		// since every pendingSeries can saturate up to a single CPU.
+		pssLen = n
+	}
+	pss := make([]*pendingSeries, pssLen)
 	for i := range pss {
 		pss[i] = newPendingSeries(fq.MustWriteBlock, sf, rd)
 	}
@@ -227,10 +442,11 @@ func (rwctx *remoteWriteCtx) MustStop() {
 	}
 	rwctx.idx = 0
 	rwctx.pss = nil
-	rwctx.fq.MustClose()
-	rwctx.fq = nil
+	rwctx.fq.UnblockAllReaders()
 	rwctx.c.MustStop()
 	rwctx.c = nil
+	rwctx.fq.MustClose()
+	rwctx.fq = nil
 
 	rwctx.relabelMetricsDropped = nil
 }
@@ -239,8 +455,8 @@ func (rwctx *remoteWriteCtx) Push(tss []prompbmarshal.TimeSeries) {
 	var rctx *relabelCtx
 	var v *[]prompbmarshal.TimeSeries
 	rcs := allRelabelConfigs.Load().(*relabelConfigs)
-	prcs := rcs.perURL[rwctx.idx]
-	if len(prcs) > 0 {
+	pcs := rcs.perURL[rwctx.idx]
+	if pcs.Len() > 0 {
 		rctx = getRelabelCtx()
 		// Make a copy of tss before applying relabeling in order to prevent
 		// from affecting time series for other remoteWrite.url configs.
@@ -249,7 +465,7 @@ func (rwctx *remoteWriteCtx) Push(tss []prompbmarshal.TimeSeries) {
 		v = tssRelabelPool.Get().(*[]prompbmarshal.TimeSeries)
 		tss = append(*v, tss...)
 		tssLen := len(tss)
-		tss = rctx.applyRelabeling(tss, nil, prcs)
+		tss = rctx.applyRelabeling(tss, nil, pcs)
 		rwctx.relabelMetricsDropped.Add(tssLen - len(tss))
 	}
 	pss := rwctx.pss

app/vmagent/remotewrite/statconn.go

@@ -1,9 +1,7 @@
 package remotewrite
 
 import (
-	"fmt"
 	"net"
-	"strings"
 	"sync/atomic"
 	"time"
 
@@ -11,13 +9,8 @@ import (
 	"github.com/VictoriaMetrics/metrics"
 )
 
-func statDial(network, addr string) (conn net.Conn, err error) {
-	if !strings.HasPrefix(network, "tcp") {
-		return nil, fmt.Errorf("unexpected network passed to statDial: %q; it must start from `tcp`", network)
-	}
-	if !netutil.TCP6Enabled() {
-		network = "tcp4"
-	}
+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 {

app/vmagent/vmimport/request_handler.go

@@ -1,40 +1,54 @@
 package vmimport
 
 import (
+	"io"
 	"net/http"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/common"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
 	parserCommon "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
 	parser "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/vmimport"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
 	"github.com/VictoriaMetrics/metrics"
 )
 
 var (
-	rowsInserted  = metrics.NewCounter(`vmagent_rows_inserted_total{type="vmimport"}`)
-	rowsPerInsert = metrics.NewHistogram(`vmagent_rows_per_insert{type="vmimport"}`)
+	rowsInserted       = metrics.NewCounter(`vmagent_rows_inserted_total{type="vmimport"}`)
+	rowsTenantInserted = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_rows_total{type="vmimport"}`)
+	rowsPerInsert      = metrics.NewHistogram(`vmagent_rows_per_insert{type="vmimport"}`)
 )
 
 // InsertHandler processes `/api/v1/import` request.
 //
 // See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/6
-func InsertHandler(req *http.Request) error {
+func InsertHandler(at *auth.Token, req *http.Request) error {
 	extraLabels, err := parserCommon.GetExtraLabels(req)
 	if err != nil {
 		return err
 	}
 	return writeconcurrencylimiter.Do(func() error {
-		return parser.ParseStream(req, func(rows []parser.Row) error {
-			return insertRows(rows, extraLabels)
+		isGzipped := req.Header.Get("Content-Encoding") == "gzip"
+		return parser.ParseStream(req.Body, isGzipped, func(rows []parser.Row) error {
+			return insertRows(at, rows, extraLabels)
 		})
 	})
 }
 
-func insertRows(rows []parser.Row, extraLabels []prompbmarshal.Label) error {
+// InsertHandlerForReader processes metrics from given reader
+func InsertHandlerForReader(r io.Reader, isGzipped bool) error {
+	return writeconcurrencylimiter.Do(func() error {
+		return parser.ParseStream(r, isGzipped, func(rows []parser.Row) error {
+			return insertRows(nil, rows, nil)
+		})
+	})
+}
+
+func insertRows(at *auth.Token, rows []parser.Row, extraLabels []prompbmarshal.Label) error {
 	ctx := common.GetPushCtx()
 	defer common.PutPushCtx(ctx)
 
@@ -74,8 +88,11 @@ func insertRows(rows []parser.Row, extraLabels []prompbmarshal.Label) error {
 	ctx.WriteRequest.Timeseries = tssDst
 	ctx.Labels = labels
 	ctx.Samples = samples
-	remotewrite.Push(&ctx.WriteRequest)
+	remotewrite.PushWithAuthToken(at, &ctx.WriteRequest)
 	rowsInserted.Add(rowsTotal)
+	if at != nil {
+		rowsTenantInserted.Get(at).Add(rowsTotal)
+	}
 	rowsPerInsert.Update(float64(rowsTotal))
 	return nil
 }

app/vmalert/Makefile

@@ -56,6 +56,7 @@ test-vmalert:
 	go test -v -race -cover ./app/vmalert/datasource
 	go test -v -race -cover ./app/vmalert/notifier
 	go test -v -race -cover ./app/vmalert/config
+	go test -v -race -cover ./app/vmalert/remotewrite
 
 run-vmalert: vmalert
 	./bin/vmalert -rule=app/vmalert/config/testdata/rules2-good.rules \
@@ -66,7 +67,17 @@ run-vmalert: vmalert
 		-remoteRead.url=http://localhost:8428 \
 		-external.label=cluster=east-1 \
 		-external.label=replica=a \
-		-evaluationInterval=3s
+		-evaluationInterval=3s \
+		-rule.configCheckInterval=10s
+
+replay-vmalert: vmalert
+	./bin/vmalert -rule=app/vmalert/config/testdata/rules-replay-good.rules \
+		-datasource.url=http://localhost:8428 \
+		-remoteWrite.url=http://localhost:8428 \
+		-external.label=cluster=east-1 \
+		-external.label=replica=a \
+		-replay.timeFrom=2021-05-11T07:21:43Z \
+		-replay.timeTo=2021-05-29T18:40:43Z
 
 vmalert-amd64:
 	CGO_ENABLED=1 GOARCH=amd64 $(MAKE) vmalert-local-with-goarch
@@ -88,3 +99,9 @@ vmalert-local-with-goarch:
 
 vmalert-pure:
 	APP_NAME=vmalert $(MAKE) app-local-pure
+
+vmalert-windows-amd64:
+	GOARCH=amd64 APP_NAME=vmalert $(MAKE) app-local-windows-with-goarch
+
+vmalert-windows-amd64-prod:
+	APP_NAME=vmalert $(MAKE) app-via-docker-windows-amd64

app/vmalert/README.md

@@ -1,30 +1,31 @@
-## vmalert
+# vmalert
 
-`vmalert` executes a list of given [alerting](https://prometheus.io/docs/prometheus/latest/configuration/alerting_rules/)
+`vmalert` executes a list of the given [alerting](https://prometheus.io/docs/prometheus/latest/configuration/alerting_rules/)
 or [recording](https://prometheus.io/docs/prometheus/latest/configuration/recording_rules/)
-rules against configured address.
+rules against configured address. It is heavily inspired by [Prometheus](https://prometheus.io/docs/alerting/latest/overview/)
+implementation and aims to be compatible with its syntax.
 
-### Features:
+## Features
 * Integration with [VictoriaMetrics](https://github.com/VictoriaMetrics/VictoriaMetrics) TSDB;
-* VictoriaMetrics [MetricsQL](https://victoriametrics.github.io/MetricsQL.html)
+* VictoriaMetrics [MetricsQL](https://docs.victoriametrics.com/MetricsQL.html)
  support and expressions validation;
 * Prometheus [alerting rules definition format](https://prometheus.io/docs/prometheus/latest/configuration/alerting_rules/#defining-alerting-rules)
  support;
 * Integration with [Alertmanager](https://github.com/prometheus/alertmanager);
-* Keeps the alerts [state on restarts](https://github.com/VictoriaMetrics/VictoriaMetrics/tree/master/app/vmalert#alerts-state-on-restarts);
-* Graphite datasource can be used for alerting and recording rules. See [these docs](#graphite) for details.
+* Keeps the alerts [state on restarts](#alerts-state-on-restarts);
+* Graphite datasource can be used for alerting and recording rules. See [these docs](#graphite);
+* Recording and Alerting rules backfilling (aka `replay`). See [these docs](#rules-backfilling);
 * Lightweight without extra dependencies.
 
-### Limitations:
-* `vmalert` execute queries against remote datasource which has reliability risks because of network. 
+## Limitations
+* `vmalert` execute queries against remote datasource which has reliability risks because of network.
 It is recommended to configure alerts thresholds and rules expressions with understanding that network request
 may fail;
 * by default, rules execution is sequential within one group, but persisting of execution results to remote
 storage is asynchronous. Hence, user shouldn't rely on recording rules chaining when result of previous
 recording rule is reused in next one;
-* `vmalert` has no UI, just an API for getting groups and rules statuses.
 
-### QuickStart
+## QuickStart
 
 To build `vmalert` from sources:
 ```
@@ -37,75 +38,94 @@ The build binary will be placed to `VictoriaMetrics/bin` folder.
 To start using `vmalert` you will need the following things:
 * list of rules - PromQL/MetricsQL expressions to execute;
 * datasource address - reachable VictoriaMetrics instance for rules execution;
-* notifier address - reachable [Alert Manager](https://github.com/prometheus/alertmanager) instance for processing, 
+* notifier address - reachable [Alert Manager](https://github.com/prometheus/alertmanager) instance for processing,
 aggregating alerts and sending notifications.
-* remote write address - [remote write](https://prometheus.io/docs/prometheus/latest/storage/#remote-storage-integrations)
-compatible storage address for storing recording rules results and alerts state in for of timeseries. This is optional.
+* remote write address [optional] - [remote write](https://prometheus.io/docs/prometheus/latest/storage/#remote-storage-integrations)
+compatible storage address for storing recording rules results and alerts state in for of timeseries.
 
 Then configure `vmalert` accordingly:
 ```
-./bin/vmalert -rule=alert.rules \
+./bin/vmalert -rule=alert.rules \            # Path to the file with rules configuration. Supports wildcard
     -datasource.url=http://localhost:8428 \  # PromQL compatible datasource
     -notifier.url=http://localhost:9093 \    # AlertManager URL
     -notifier.url=http://127.0.0.1:9093 \    # AlertManager replica URL
-    -remoteWrite.url=http://localhost:8428 \ # remote write compatible storage to persist rules
-    -remoteRead.url=http://localhost:8428 \  # PromQL compatible datasource to restore alerts state from
+    -remoteWrite.url=http://localhost:8428 \ # Remote write compatible storage to persist rules
+    -remoteRead.url=http://localhost:8428 \  # MetricsQL compatible datasource to restore alerts state from
     -external.label=cluster=east-1 \         # External label to be applied for each rule
-    -external.label=replica=a \              # Multiple external labels may be set
-    -evaluationInterval=3s                   # Default evaluation interval if not specified in rules group
+    -external.label=replica=a                # Multiple external labels may be set
 ```
 
-If you run multiple `vmalert` services for the same datastore or AlertManager - do not forget
-to specify different `external.label` flags in order to define which `vmalert` generated rules or alerts. 
+See the fill list of configuration flags in [configuration](#configuration) section.
 
-Configuration for [recording](https://prometheus.io/docs/prometheus/latest/configuration/recording_rules/) 
-and [alerting](https://prometheus.io/docs/prometheus/latest/configuration/alerting_rules/) rules is very 
-similar to Prometheus rules and configured using YAML. Configuration examples may be found 
+If you run multiple `vmalert` services for the same datastore or AlertManager - do not forget
+to specify different `external.label` flags in order to define which `vmalert` generated rules or alerts.
+
+Configuration for [recording](https://prometheus.io/docs/prometheus/latest/configuration/recording_rules/)
+and [alerting](https://prometheus.io/docs/prometheus/latest/configuration/alerting_rules/) rules is very
+similar to Prometheus rules and configured using YAML. Configuration examples may be found
 in [testdata](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/app/vmalert/config/testdata) folder.
-Every `rule` belongs to `group` and every configuration file may contain arbitrary number of groups:
+Every `rule` belongs to a `group` and every configuration file may contain arbitrary number of groups:
 ```yaml
 groups:
   [ - <rule_group> ]
 ```
 
-#### Groups
+### Groups
 
-Each group has following attributes:
+Each group has the following attributes:
 ```yaml
 # The name of the group. Must be unique within a file.
 name: <string>
 
 # How often rules in the group are evaluated.
-[ interval: <duration> | default = global.evaluation_interval ]
+[ interval: <duration> | default = -evaluationInterval flag ]
 
-# How many rules execute at once. Increasing concurrency may speed
-# up round execution speed. 
+# How many rules execute at once within a group. Increasing concurrency may speed
+# up round execution speed.
 [ concurrency: <integer> | default = 1 ]
 
 # Optional type for expressions inside the rules. Supported values: "graphite" and "prometheus".
 # By default "prometheus" rule type is used.
 [ type: <string> ]
 
+# Optional list of label filters applied to every rule's
+# request withing a group. Is compatible only with VM datasource.
+# See more details at https://docs.victoriametrics.com#prometheus-querying-api-enhancements
+extra_filter_labels:
+  [ <labelname>: <labelvalue> ... ]
+
+# Optional list of labels added to every rule within a group.
+# It has priority over the external labels.
+# Labels are commonly used for adding environment
+# or tenant-specific tag.
+labels:
+  [ <labelname>: <labelvalue> ... ]
+
 rules:
   [ - <rule> ... ]
 ```
 
-#### Rules
+### Rules
+
+Every rule contains `expr` field for [PromQL](https://prometheus.io/docs/prometheus/latest/querying/basics/)
+or [MetricsQL](https://docs.victoriametrics.com/MetricsQL.html) expression. Vmalert will execute the configured
+expression and then act according to the Rule type.
 
 There are two types of Rules:
-* [alerting](https://prometheus.io/docs/prometheus/latest/configuration/alerting_rules/) - 
-Alerting rules allows to define alert conditions via [MetricsQL](https://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.
+* [alerting](https://prometheus.io/docs/prometheus/latest/configuration/alerting_rules/) -
+Alerting rules allows to define alert conditions via `expr` field and to send notifications
+[Alertmanager](https://github.com/prometheus/alertmanager) if execution result is not empty.
+* [recording](https://prometheus.io/docs/prometheus/latest/configuration/recording_rules/) -
+Recording rules allows to define `expr` which result will be than backfilled to configured
+`-remoteWrite.url`. Recording rules are used to precompute frequently needed or computationally
+expensive expressions and save their result as a new set of time series.
 
 `vmalert` forbids to define duplicates - rules with the same combination of name, expression and labels
-within one group. 
+within one group.
 
-##### Alerting rules
+#### Alerting rules
 
-The syntax for alerting rule is following:
+The syntax for alerting rule is the following:
 ```yaml
 # The name of the alert. Must be a valid metric name.
 alert: <string>
@@ -115,12 +135,14 @@ alert: <string>
 [ 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
+# By default PromQL/MetricsQL expression is used. If type="graphite", then the expression
 # must contain valid Graphite expression.
 expr: <string>
 
 # Alerts are considered firing once they have been returned for this long.
 # Alerts which have not yet fired for long enough are considered pending.
+# If param is omitted or set to 0 then alerts will be immediately considered
+# as firing once they return.
 [ for: <duration> | default = 0s ]
 
 # Labels to add or overwrite for each alert.
@@ -130,9 +152,14 @@ labels:
 # Annotations to add to each alert.
 annotations:
   [ <labelname>: <tmpl_string> ]
-``` 
+```
 
-##### Recording rules
+It is allowed to use [Go templating](https://golang.org/pkg/text/template/) in annotations
+to format data, iterate over it or execute expressions.
+Additionally, `vmalert` provides some extra templating functions
+listed [here](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/app/vmalert/notifier/template_func.go).
+
+#### Recording rules
 
 The syntax for recording rules is following:
 ```yaml
@@ -153,57 +180,215 @@ labels:
   [ <labelname>: <labelvalue> ]
 ```
 
-For recording rules to work `-remoteWrite.url` must specified.
+For recording rules to work `-remoteWrite.url` must be specified.
 
 
-#### Alerts state on restarts
+### Alerts state on restarts
 
-`vmalert` has no local storage, so alerts state is stored in the process memory. Hence, after reloading of `vmalert` 
+`vmalert` has no local storage, so alerts state is stored in the process memory. Hence, after restart of `vmalert`
 the process alerts state will be lost. To avoid this situation, `vmalert` should be configured via the following flags:
-* `-remoteWrite.url` - URL to VictoriaMetrics (Single) or VMInsert (Cluster). `vmalert` will persist alerts state 
-into the configured address in the form of time series named `ALERTS` and `ALERTS_FOR_STATE` via remote-write protocol. 
-These are regular time series and may be queried from VM just as any other time series. 
+* `-remoteWrite.url` - URL to VictoriaMetrics (Single) or vminsert (Cluster). `vmalert` will persist alerts state
+into the configured address in the form of time series named `ALERTS` and `ALERTS_FOR_STATE` via remote-write protocol.
+These are regular time series and may be queried from VM just as any other time series.
 The state stored to the configured address on every rule evaluation.
-* `-remoteRead.url` - URL to VictoriaMetrics (Single) or VMSelect (Cluster). `vmalert` will try to restore alerts state 
+* `-remoteRead.url` - URL to VictoriaMetrics (Single) or vmselect (Cluster). `vmalert` will try to restore alerts state
 from configured address by querying time series with name `ALERTS_FOR_STATE`.
 
 Both flags are required for the proper state restoring. Restore process may fail if time series are missing
-in configured `-remoteRead.url`, weren't updated in the last `1h` or received state doesn't match current `vmalert` 
-rules configuration.
+in configured `-remoteRead.url`, weren't updated in the last `1h` (controlled by `-remoteRead.lookback`)
+or received state doesn't match current `vmalert` rules configuration.
 
 
-#### WEB
+### Multitenancy
+
+There are the following approaches for alerting and recording rules across
+[multiple tenants](https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html#multitenancy):
+
+* To run a separate `vmalert` instance per each tenant.
+  The corresponding tenant must be specified in `-datasource.url` command-line flag
+  according to [these docs](https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html#url-format).
+  For example, `/path/to/vmalert -datasource.url=http://vmselect:8481/select/123/prometheus`
+  would run alerts against `AccountID=123`. For recording rules the `-remoteWrite.url` command-line
+  flag must contain the url for the specific tenant as well.
+  For example, `-remoteWrite.url=http://vminsert:8480/insert/123/prometheus` would write recording
+  rules to `AccountID=123`.
+
+* To specify `tenant` parameter per each alerting and recording group if
+  [enterprise version of vmalert](https://victoriametrics.com/enterprise.html) is used
+  with `-clusterMode` command-line flag. For example:
+
+```yaml
+groups:
+- name: rules_for_tenant_123
+  tenant: "123"
+  rules:
+    # Rules for accountID=123
+
+- name: rules_for_tenant_456:789
+  tenant: "456:789"
+  rules:
+    # Rules for accountID=456, projectID=789
+```
+
+If `-clusterMode` is enabled, then `-datasource.url`, `-remoteRead.url` and `-remoteWrite.url` must
+contain only the hostname without tenant id. For example: `-datasource.url=http://vmselect:8481`.
+`vmalert` automatically adds the specified tenant to urls per each recording rule in this case.
+
+The enterprise version of vmalert is available in `vmutils-*-enterprise.tar.gz` files
+at [release page](https://github.com/VictoriaMetrics/VictoriaMetrics/releases) and in `*-enterprise`
+tags at [Docker Hub](https://hub.docker.com/r/victoriametrics/vmalert/tags).
+
+
+### WEB
 
 `vmalert` runs a web-server (`-httpListenAddr`) for serving metrics and alerts endpoints:
+* `http://<vmalert-addr>` - UI;
 * `http://<vmalert-addr>/api/v1/groups` - list of all loaded groups and rules;
 * `http://<vmalert-addr>/api/v1/alerts` - list of all active alerts;
-* `http://<vmalert-addr>/api/v1/<groupName>/<alertID>/status" ` - get alert status by ID.
+* `http://<vmalert-addr>/api/v1/<groupID>/<alertID>/status" ` - get alert status by ID.
 Used as alert source in AlertManager.
 * `http://<vmalert-addr>/metrics` - application metrics.
 * `http://<vmalert-addr>/-/reload` - hot configuration reload.
 
 
-### Graphite
+## Graphite
 
 vmalert sends requests to `<-datasource.url>/render?format=json` during evaluation of alerting and recording rules
 if the corresponding group or rule contains `type: "graphite"` config option. It is expected that the `<-datasource.url>/render`
 implements [Graphite Render API](https://graphite.readthedocs.io/en/stable/render_api.html) for `format=json`.
+When using vmalert with both `graphite` and `prometheus` rules configured against cluster version of VM do not forget
+to set `-datasource.appendTypePrefix` flag to `true`, so vmalert can adjust URL prefix automatically based on query type.
+
+## Rules backfilling
+
+vmalert supports alerting and recording rules backfilling (aka `replay`). In replay mode vmalert
+can read the same rules configuration as normally, evaluate them on the given time range and backfill
+results via remote write to the configured storage. vmalert supports any PromQL/MetricsQL compatible
+data source for backfilling.
+
+### How it works
+
+In `replay` mode vmalert works as a cli-tool and exits immediately after work is done.
+To run vmalert in `replay` mode:
+```
+./bin/vmalert -rule=path/to/your.rules \        # path to files with rules you usually use with vmalert
+    -datasource.url=http://localhost:8428 \     # PromQL/MetricsQL compatible datasource
+    -remoteWrite.url=http://localhost:8428 \    # remote write compatible storage to persist results
+    -replay.timeFrom=2021-05-11T07:21:43Z \     # time from begin replay
+    -replay.timeTo=2021-05-29T18:40:43Z         # time to finish replay
+```
+
+The output of the command will look like the following:
+```
+Replay mode:
+from:   2021-05-11 07:21:43 +0000 UTC   # set by -replay.timeFrom
+to:     2021-05-29 18:40:43 +0000 UTC   # set by -replay.timeTo
+max data points per request: 1000       # set by -replay.maxDatapointsPerQuery
+
+Group "ReplayGroup"
+interval:       1m0s
+requests to make:       27
+max range per request:  16h40m0s
+> Rule "type:vm_cache_entries:rate5m" (ID: 1792509946081842725)
+27 / 27 [----------------------------------------------------------------------------------------------------] 100.00% 78 p/s
+> Rule "go_cgo_calls_count:rate5m" (ID: 17958425467471411582)
+27 / 27 [-----------------------------------------------------------------------------------------------------] 100.00% ? p/s
+
+Group "vmsingleReplay"
+interval:       30s
+requests to make:       54
+max range per request:  8h20m0s
+> Rule "RequestErrorsToAPI" (ID: 17645863024999990222)
+54 / 54 [-----------------------------------------------------------------------------------------------------] 100.00% ? p/s
+> Rule "TooManyLogs" (ID: 9042195394653477652)
+54 / 54 [-----------------------------------------------------------------------------------------------------] 100.00% ? p/s
+2021-06-07T09:59:12.098Z        info    app/vmalert/replay.go:68        replay finished! Imported 511734 samples
+```
+
+In `replay` mode all groups are executed sequentially one-by-one. Rules within the group are
+executed sequentially as well (`concurrency` setting is ignored). Vmalert sends rule's expression
+to [/query_range](https://prometheus.io/docs/prometheus/latest/querying/api/#range-queries) endpoint
+of the configured `-datasource.url`. Returned data then processed according to the rule type and
+backfilled to `-remoteWrite.url` via [Remote Write protocol](https://prometheus.io/docs/prometheus/latest/storage/#remote-storage-integrations).
+Vmalert respects `evaluationInterval` value set by flag or per-group during the replay.
+Vmalert automatically disables caching on VictoriaMetrics side by sending `nocache=1` param. It allows
+to prevent cache pollution and unwanted time range boundaries adjustment during backfilling.
+
+#### Recording rules
+
+Result of recording rules `replay` should match with results of normal rules evaluation.
+
+#### Alerting rules
+
+Result of alerting rules `replay` is time series reflecting [alert's state](#alerts-state-on-restarts).
+To see if `replayed` alert has fired in the past use the following PromQL/MetricsQL expression:
+```
+ALERTS{alertname="your_alertname", alertstate="firing"}
+```
+Execute the query against storage which was used for `-remoteWrite.url` during the `replay`.
+
+### Additional configuration
+
+There are following non-required `replay` flags:
+
+* `-replay.maxDatapointsPerQuery` - the max number of data points expected to receive in one request.
+In two words, it affects the max time range for every `/query_range` request. The higher the value,
+the less requests will be issued during `replay`.
+* `-replay.ruleRetryAttempts` - when datasource fails to respond vmalert will make this number of retries
+per rule before giving up.
+* `-replay.rulesDelay` - delay between sequential rules execution. Important in cases if there are chaining
+(rules which depend on each other) rules. It is expected, that remote storage will be able to persist
+previously accepted data during the delay, so data will be available for the subsequent queries.
+Keep it equal or bigger than `-remoteWrite.flushInterval`.
+
+See full description for these flags in `./vmalert --help`.
+
+### Limitations
+
+* Graphite engine isn't supported yet;
+* `query` template function is disabled for performance reasons (might be changed in future);
 
 
-### Configuration
+## Monitoring
+
+`vmalert` exports various metrics in Prometheus exposition format at `http://vmalert-host:8880/metrics` page. 
+We recommend setting up regular scraping of this page either through `vmagent` or by Prometheus so that the exported 
+metrics may be analyzed later.
+
+Use official [Grafana dashboard](https://grafana.com/grafana/dashboards/14950) for `vmalert` 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.
+
+
+## Configuration
+
+Pass `-help` to `vmalert` in order to see the full list of supported
+command-line flags with their descriptions.
 
 The shortlist of configuration flags is the following:
 ```
+  -datasource.appendTypePrefix
+    	Whether to add type prefix to -datasource.url based on the query type. Set to true if sending different query types to the vmselect URL.
   -datasource.basicAuth.password string
     	Optional basic auth password for -datasource.url
+  -datasource.basicAuth.passwordFile string
+    	Optional path to basic auth password to use for -datasource.url
   -datasource.basicAuth.username string
     	Optional basic auth username for -datasource.url
+  -datasource.bearerToken string
+    	Optional bearer auth token to use for -datasource.url.
+  -datasource.bearerTokenFile string
+    	Optional path to bearer token file to use for -datasource.url.
   -datasource.lookback duration
-    	Lookback defines how far to look into past when evaluating queries. For example, if datasource.lookback=5m then param "time" with value now()-5m will be added to every query.
+    	Lookback defines how far into the past to look when evaluating queries. For example, if the datasource.lookback=5m then param "time" with value now()-5m will be added to every query.
   -datasource.maxIdleConnections int
-    	Defines the number of idle (keep-alive connections) to configured datasource.Consider to set this value equal to the value: groups_total * group.concurrency. Too low value may result into high number of sockets in TIME_WAIT state. (default 100)
+    	Defines the number of idle (keep-alive connections) to each configured datasource. Consider setting this value equal to the value: groups_total * group.concurrency. Too low a value may result in a high number of sockets in TIME_WAIT state. (default 100)
+  -datasource.queryStep duration
+    	queryStep defines how far a value can fallback to when evaluating queries. For example, if datasource.queryStep=15s then param "step" with value "15s" will be added to every query.If queryStep isn't specified, rule's evaluationInterval will be used instead.
+  -datasource.roundDigits int
+    	Adds "round_digits" GET param to datasource requests. In VM "round_digits" limits the number of digits after the decimal point in response values.
   -datasource.tlsCAFile string
-    	Optional path to TLS CA file to use for verifying connections to -datasource.url. By default system CA is used
+    	Optional path to TLS CA file to use for verifying connections to -datasource.url. By default, system CA is used
   -datasource.tlsCertFile string
     	Optional path to client-side TLS certificate file to use when connecting to -datasource.url
   -datasource.tlsInsecureSkipVerify
@@ -211,39 +396,43 @@ The shortlist of configuration flags is the following:
   -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
+    	Optional TLS server name to use for connections to -datasource.url. By default, the server name from -datasource.url is used
   -datasource.url string
-    	Victoria Metrics or VMSelect url. Required parameter. E.g. http://127.0.0.1:8428
+    	VictoriaMetrics or vmselect url. Required parameter. E.g. http://127.0.0.1:8428
+  -disableAlertgroupLabel
+    	Whether to disable adding group's name as label to generated alerts and time series.
   -dryRun -rule
     	Whether to check only config files without running vmalert. The rules file are validated. The -rule flag must be specified.
   -enableTCP6
-    	Whether to enable IPv6 for listening and dialing. By default only IPv4 TCP is used
+    	Whether to enable IPv6 for listening and dialing. By default only IPv4 TCP and UDP is used
   -envflag.enable
-    	Whether to enable reading flags from environment variables additionally to command line. Command line flag values have priority over values from environment vars. Flags are read only from command line if this flag isn't set
+    	Whether to enable reading flags from environment variables additionally to command line. Command line flag values have priority over values from environment vars. Flags are read only from command line if this flag isn't set. See https://docs.victoriametrics.com/#environment-variables for more details
   -envflag.prefix string
     	Prefix for environment variables if -envflag.enable is set
   -evaluationInterval duration
     	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\": \"{{$expr|quotesEscape|crlfEscape|pathEscape}}\"},{\"mode\":\"Metrics\"},{\"ui\":[true,true,true,\"none\"]}]'.If empty '/api/v1/:groupID/alertID/status' is used
+    	eg. 'explore?orgId=1&left=[\"now-1h\",\"now\",\"VictoriaMetrics\",{\"expr\": \"{{$expr|quotesEscape|crlfEscape|queryEscape}}\"},{\"mode\":\"Metrics\"},{\"ui\":[true,true,true,\"none\"]}]'.If empty '/api/v1/:groupID/alertID/status' is used
   -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.
+    	Supports an array of values separated by comma or specified via multiple flags.
   -external.url string
     	External URL is used as alert's source for sent alerts to the notifier
+  -fs.disableMmap
+    	Whether to use pread() instead of mmap() for reading data files. By default mmap() is used for 64-bit arches and pread() is used for 32-bit arches, since they cannot read data files bigger than 2^32 bytes in memory. mmap() is usually faster for reading small data chunks than pread()
   -http.connTimeout duration
-    	Incoming http connections are closed after the configured timeout. This may help spreading incoming load among a cluster of services behind load balancer. Note that the real timeout may be bigger by up to 10% as a protection from Thundering herd problem (default 2m0s)
+    	Incoming http connections are closed after the configured timeout. This may help to spread the incoming load among a cluster of services behind a load balancer. Please note that the real timeout may be bigger by up to 10% as a protection against the thundering herd problem (default 2m0s)
   -http.disableResponseCompression
-    	Disable compression of HTTP responses for saving CPU resources. By default compression is enabled to save network bandwidth
+    	Disable compression of HTTP responses to save CPU resources. By default compression is enabled to save network bandwidth
   -http.idleConnTimeout duration
     	Timeout for incoming idle http connections (default 1m0s)
   -http.maxGracefulShutdownDuration duration
-    	The maximum duration for graceful shutdown of HTTP server. Highly loaded server may require increased value for graceful shutdown (default 7s)
+    	The maximum duration for a graceful shutdown of the HTTP server. A highly loaded server may require increased value for a graceful shutdown (default 7s)
   -http.pathPrefix string
     	An optional prefix to add to all the paths handled by http server. For example, if '-http.pathPrefix=/foo/bar' is set, then all the http requests will be handled on '/foo/bar/*' paths. This may be useful for proxied requests. See https://www.robustperception.io/using-external-urls-and-proxies-with-prometheus
   -http.shutdownDelay duration
-    	Optional delay before http server shutdown. During this dealy the servier returns non-OK responses from /health page, so load balancers can route new requests to other servers
+    	Optional delay before http server shutdown. During this delay, the server returns non-OK responses from /health page, so load balancers can route new requests to other servers
   -httpAuth.password string
     	Password for HTTP Basic Auth. The authentication is disabled if -httpAuth.username is empty
   -httpAuth.username string
@@ -253,52 +442,62 @@ The shortlist of configuration flags is the following:
   -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
+    	Per-second limit on the number of ERROR messages. If more than the given number of errors are emitted per second, the remaining errors are suppressed. Zero values disable the rate limit
   -loggerFormat string
     	Format for logs. Possible values: default, json (default "default")
   -loggerLevel string
     	Minimum level of errors to log. Possible values: INFO, WARN, ERROR, FATAL, PANIC (default "INFO")
   -loggerOutput string
     	Output for the logs. Supported values: stderr, stdout (default "stderr")
+  -loggerTimezone string
+    	Timezone to use for timestamps in logs. Timezone must be a valid IANA Time Zone. For example: America/New_York, Europe/Berlin, Etc/GMT+3 or Local (default "UTC")
   -loggerWarnsPerSecondLimit int
-    	Per-second limit on the number of WARN messages. If more than the given number of warns are emitted per second, then the remaining warns are suppressed. Zero value disables the rate limit
-  -memory.allowedBytes value
-    	Allowed size of system memory VictoriaMetrics caches may occupy. This option overrides -memory.allowedPercent if set to non-zero value. Too low value may increase cache miss rate, which usually results in higher CPU and disk IO usage. Too high value may evict too much data from OS page cache, which will result in higher disk IO usage
-    	Supports the following optional suffixes for values: KB, MB, GB, KiB, MiB, GiB (default 0)
+    	Per-second limit on the number of WARN messages. If more than the given number of warns are emitted per second, then the remaining warns are suppressed. Zero values disable the rate limit
+  -memory.allowedBytes size
+    	Allowed size of system memory VictoriaMetrics caches may occupy. This option overrides -memory.allowedPercent if set to a non-zero value. Too low a value may increase the cache miss rate usually resulting in higher CPU and disk IO usage. Too high a value may evict too much data from OS page cache resulting in higher disk IO usage
+    	Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 0)
   -memory.allowedPercent float
-    	Allowed percent of system memory VictoriaMetrics caches may occupy. See also -memory.allowedBytes. Too low value may increase cache miss rate, which usually results in higher CPU and disk IO usage. Too high value may evict too much data from OS page cache, which will result in higher disk IO usage (default 60)
+    	Allowed percent of system memory VictoriaMetrics caches may occupy. See also -memory.allowedBytes. Too low a value may increase cache miss rate usually resulting in higher CPU and disk IO usage. Too high a value may evict too much data from OS page cache which will result in higher disk IO usage (default 60)
   -metricsAuthKey string
     	Auth key for /metrics. It overrides httpAuth settings
   -notifier.basicAuth.password array
     	Optional basic auth password for -notifier.url
-    	Supports array of values separated by comma or specified via multiple flags.
+    	Supports an array of values separated by comma or specified via multiple flags.
   -notifier.basicAuth.username array
     	Optional basic auth username for -notifier.url
-    	Supports array of values separated by comma or specified via multiple flags.
+    	Supports an array of values separated by comma or specified via multiple flags.
   -notifier.tlsCAFile array
     	Optional path to TLS CA file to use for verifying connections to -notifier.url. By default system CA is used
-    	Supports array of values separated by comma or specified via multiple flags.
+    	Supports an array of values separated by comma or specified via multiple flags.
   -notifier.tlsCertFile array
     	Optional path to client-side TLS certificate file to use when connecting to -notifier.url
-    	Supports array of values separated by comma or specified via multiple flags.
+    	Supports an array of values separated by comma or specified via multiple flags.
   -notifier.tlsInsecureSkipVerify array
     	Whether to skip tls verification when connecting to -notifier.url
     	Supports array of values separated by comma or specified via multiple flags.
   -notifier.tlsKeyFile array
     	Optional path to client-side TLS certificate key to use when connecting to -notifier.url
-    	Supports array of values separated by comma or specified via multiple flags.
+    	Supports an array of values separated by comma or specified via multiple flags.
   -notifier.tlsServerName array
     	Optional TLS server name to use for connections to -notifier.url. By default the server name from -notifier.url is used
-    	Supports array of values separated by comma or specified via multiple flags.
+    	Supports an array of values separated by comma or specified via multiple flags.
   -notifier.url array
     	Prometheus alertmanager URL. Required parameter. e.g. http://127.0.0.1:9093
-    	Supports array of values separated by comma or specified via multiple flags.
+    	Supports an 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
+  -remoteRead.basicAuth.passwordFile string
+    	Optional path to basic auth password to use for -remoteRead.url
   -remoteRead.basicAuth.username string
     	Optional basic auth username for -remoteRead.url
+  -remoteRead.bearerToken string
+    	Optional bearer auth token to use for -remoteRead.url.
+  -remoteRead.bearerTokenFile string
+    	Optional path to bearer token file to use for -remoteRead.url.
+  -remoteRead.ignoreRestoreErrors
+    	Whether to ignore errors from remote storage when restoring alerts state on startup. (default true)
   -remoteRead.lookback duration
     	Lookback defines how far to look into past for alerts timeseries. For example, if lookback=1h then range from now() to now()-1h will be scanned. (default 1h0m0s)
   -remoteRead.tlsCAFile string
@@ -312,13 +511,21 @@ The shortlist of configuration flags is the following:
   -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 VictoriaMetrics or vmselect that will be used to restore alerts state. This configuration makes sense only if vmalert was configured with `remoteWrite.url` before and has been successfully persisted its state. E.g. http://127.0.0.1:8428
   -remoteWrite.basicAuth.password string
     	Optional basic auth password for -remoteWrite.url
+  -remoteWrite.basicAuth.passwordFile string
+    	Optional path to basic auth password to use for -remoteWrite.url
   -remoteWrite.basicAuth.username string
     	Optional basic auth username for -remoteWrite.url
+  -remoteWrite.bearerToken string
+    	Optional bearer auth token to use for -remoteWrite.url.
+  -remoteWrite.bearerTokenFile string
+    	Optional path to bearer token file to use for -remoteWrite.url.
   -remoteWrite.concurrency int
     	Defines number of writers for concurrent writing into remote querier (default 1)
+  -remoteWrite.disablePathAppend
+    	Whether to disable automatic appending of '/api/v1/write' path to the configured -remoteWrite.url.
   -remoteWrite.flushInterval duration
     	Defines interval of flushes to remote write endpoint (default 5s)
   -remoteWrite.maxBatchSize int
@@ -336,16 +543,30 @@ The shortlist of configuration flags is the following:
   -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 and recording rules results in form of timeseries. E.g. http://127.0.0.1:8428
+    	Optional URL to VictoriaMetrics or vminsert where to persist alerts state and recording rules results in form of timeseries. For example, if -remoteWrite.url=http://127.0.0.1:8428 is specified, then the alerts state will be written to http://127.0.0.1:8428/api/v1/write . See also -remoteWrite.disablePathAppend
+  -replay.maxDatapointsPerQuery int
+    	Max number of data points expected in one request. The higher the value, the less requests will be made during replay. (default 1000)
+  -replay.ruleRetryAttempts int
+    	Defines how many retries to make before giving up on rule if request for it returns an error. (default 5)
+  -replay.rulesDelay duration
+    	Delay between rules evaluation within the group. Could be important if there are chained rules inside of the groupand processing need to wait for previous rule results to be persisted by remote storage before evaluating the next rule.Keep it equal or bigger than -remoteWrite.flushInterval. (default 1s)
+  -replay.timeFrom string
+    	The time filter in RFC3339 format to select time series with timestamp equal or higher than provided value. E.g. '2020-01-01T20:07:00Z'
+  -replay.timeTo string
+    	The time filter in RFC3339 format to select timeseries with timestamp equal or lower than provided value. E.g. '2020-01-01T20:07:00Z'
   -rule array
-    	Path to the file with alert rules. 
-    	Supports patterns. Flag can be specified multiple times. 
+    	Path to the file with alert rules.
+    	Supports patterns. Flag can be specified multiple times.
     	Examples:
     	 -rule="/path/to/file". Path to a single file with alerting rules
-    	 -rule="dir/*.yaml" -rule="/*.yaml". Relative path to all .yaml files in "dir" folder, 
+    	 -rule="dir/*.yaml" -rule="/*.yaml". Relative path to all .yaml files in "dir" folder,
     	absolute path to all .yaml files in root.
     	Rule files may contain %{ENV_VAR} placeholders, which are substituted by the corresponding env vars.
-    	Supports array of values separated by comma or specified via multiple flags.
+    	Supports an array of values separated by comma or specified via multiple flags.
+  -rule.configCheckInterval duration
+    	Interval for checking for changes in '-rule' files. By default the checking is disabled. Send SIGHUP signal in order to force config check for changes
+  -rule.maxResolveDuration duration
+    	Limits the maximum duration for automatic alert expiration, which is by default equal to 3 evaluation intervals of the parent group.
   -rule.validateExpressions
     	Whether to validate rules expressions via MetricsQL engine (default true)
   -rule.validateTemplates
@@ -353,57 +574,57 @@ The shortlist of configuration flags is the following:
   -tls
     	Whether to enable TLS (aka HTTPS) for incoming requests. -tlsCertFile and -tlsKeyFile must be set if -tls is set
   -tlsCertFile string
-    	Path to file with TLS certificate. Used only if -tls is set. Prefer ECDSA certs instead of RSA certs, since RSA certs are slow
+    	Path to file with TLS certificate. Used only if -tls is set. Prefer ECDSA certs instead of RSA certs as RSA certs are slower
   -tlsKeyFile string
     	Path to file with TLS key. Used only if -tls is set
   -version
     	Show VictoriaMetrics version
 ```
 
-Pass `-help` to `vmalert` in order to see the full list of supported 
-command-line flags with their descriptions.
+`vmalert` supports "hot" config reload via the following methods:
+* send SIGHUP signal to `vmalert` process;
+* send GET request to `/-/reload` endpoint;
+* configure `-rule.configCheckInterval` flag for periodic reload
+on config change.
 
-To reload configuration without `vmalert` restart send SIGHUP signal
-or send GET request to `/-/reload` endpoint.
-
-### Contributing
+## Contributing
 
 `vmalert` is mostly designed and built by VictoriaMetrics community.
-Feel free to share your experience and ideas for improving this 
+Feel free to share your experience and ideas for improving this
 software. Please keep simplicity as the main priority.
 
-### How to build from sources
+## How to build from sources
 
-It is recommended using 
-[binary releases](https://github.com/VictoriaMetrics/VictoriaMetrics/releases) 
+It is recommended using
+[binary releases](https://github.com/VictoriaMetrics/VictoriaMetrics/releases)
 - `vmalert` is located in `vmutils-*` archives there.
 
 
-#### Development build
+### Development build
 
-1. [Install Go](https://golang.org/doc/install). The minimum supported version is Go 1.13.
-2. Run `make vmalert` from the root folder of the repository.
+1. [Install Go](https://golang.org/doc/install). The minimum supported version is Go 1.16.
+2. Run `make vmalert` from the root folder of [the repository](https://github.com/VictoriaMetrics/VictoriaMetrics).
    It builds `vmalert` binary and puts it into the `bin` folder.
 
-#### Production build
+### Production build
 
 1. [Install docker](https://docs.docker.com/install/).
-2. Run `make vmalert-prod` from the root folder of the repository.
+2. Run `make vmalert-prod` from the root folder of [the repository](https://github.com/VictoriaMetrics/VictoriaMetrics).
    It builds `vmalert-prod` binary and puts it into the `bin` folder.
 
 
-#### ARM build
+### ARM build
 
 ARM build may run on Raspberry Pi or on [energy-efficient ARM servers](https://blog.cloudflare.com/arm-takes-wing/).
 
-#### Development ARM build
+### Development ARM build
 
-1. [Install Go](https://golang.org/doc/install). The minimum supported version is Go 1.13.
-2. Run `make vmalert-arm` or `make vmalert-arm64` from the root folder of the repository.
+1. [Install Go](https://golang.org/doc/install). The minimum supported version is Go 1.16.
+2. Run `make vmalert-arm` or `make vmalert-arm64` from the root folder of [the repository](https://github.com/VictoriaMetrics/VictoriaMetrics).
    It builds `vmalert-arm` or `vmalert-arm64` binary respectively and puts it into the `bin` folder.
 
-#### Production ARM build
+### Production ARM build
 
 1. [Install docker](https://docs.docker.com/install/).
-2. Run `make vmalert-arm-prod` or `make vmalert-arm64-prod` from the root folder of the repository.
+2. Run `make vmalert-arm-prod` or `make vmalert-arm64-prod` from the root folder of [the repository](https://github.com/VictoriaMetrics/VictoriaMetrics).
    It builds `vmalert-arm-prod` or `vmalert-arm64-prod` binary respectively and puts it into the `bin` folder.

app/vmalert/alerting.go

@@ -19,15 +19,18 @@ import (
 
 // 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
+	Type         datasource.Type
+	RuleID       uint64
+	Name         string
+	Expr         string
+	For          time.Duration
+	Labels       map[string]string
+	Annotations  map[string]string
+	GroupID      uint64
+	GroupName    string
+	EvalInterval time.Duration
+
+	q datasource.Querier
 
 	// guard status fields
 	mu sync.RWMutex
@@ -39,6 +42,9 @@ type AlertingRule struct {
 	// resets on every successful Exec
 	// may be used as Health state
 	lastExecError error
+	// stores the number of samples returned during
+	// the last evaluation
+	lastExecSamples int
 
 	metrics *alertingRuleMetrics
 }
@@ -47,28 +53,35 @@ type alertingRuleMetrics struct {
 	errors  *gauge
 	pending *gauge
 	active  *gauge
+	samples *gauge
 }
 
-func newAlertingRule(group *Group, cfg config.Rule) *AlertingRule {
+func newAlertingRule(qb datasource.QuerierBuilder, 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{},
+		Type:         cfg.Type,
+		RuleID:       cfg.ID,
+		Name:         cfg.Alert,
+		Expr:         cfg.Expr,
+		For:          cfg.For.Duration(),
+		Labels:       cfg.Labels,
+		Annotations:  cfg.Annotations,
+		GroupID:      group.ID(),
+		GroupName:    group.Name,
+		EvalInterval: group.Interval,
+		q: qb.BuildWithParams(datasource.QuerierParams{
+			DataSourceType:     &cfg.Type,
+			EvaluationInterval: group.Interval,
+			ExtraLabels:        group.ExtraFilterLabels,
+		}),
+		alerts:  make(map[uint64]*notifier.Alert),
+		metrics: &alertingRuleMetrics{},
 	}
 
 	labels := fmt.Sprintf(`alertname=%q, group=%q, id="%d"`, ar.Name, group.Name, ar.ID())
 	ar.metrics.pending = getOrCreateGauge(fmt.Sprintf(`vmalert_alerts_pending{%s}`, labels),
 		func() float64 {
-			ar.mu.Lock()
-			defer ar.mu.Unlock()
+			ar.mu.RLock()
+			defer ar.mu.RUnlock()
 			var num int
 			for _, a := range ar.alerts {
 				if a.State == notifier.StatePending {
@@ -79,8 +92,8 @@ func newAlertingRule(group *Group, cfg config.Rule) *AlertingRule {
 		})
 	ar.metrics.active = getOrCreateGauge(fmt.Sprintf(`vmalert_alerts_firing{%s}`, labels),
 		func() float64 {
-			ar.mu.Lock()
-			defer ar.mu.Unlock()
+			ar.mu.RLock()
+			defer ar.mu.RUnlock()
 			var num int
 			for _, a := range ar.alerts {
 				if a.State == notifier.StateFiring {
@@ -89,15 +102,21 @@ func newAlertingRule(group *Group, cfg config.Rule) *AlertingRule {
 			}
 			return float64(num)
 		})
-	ar.metrics.errors = getOrCreateGauge(fmt.Sprintf(`vmalert_alerts_error{%s}`, labels),
+	ar.metrics.errors = getOrCreateGauge(fmt.Sprintf(`vmalert_alerting_rules_error{%s}`, labels),
 		func() float64 {
-			ar.mu.Lock()
-			defer ar.mu.Unlock()
+			ar.mu.RLock()
+			defer ar.mu.RUnlock()
 			if ar.lastExecError == nil {
 				return 0
 			}
 			return 1
 		})
+	ar.metrics.samples = getOrCreateGauge(fmt.Sprintf(`vmalert_alerting_rules_last_evaluation_samples{%s}`, labels),
+		func() float64 {
+			ar.mu.RLock()
+			defer ar.mu.RUnlock()
+			return float64(ar.lastExecSamples)
+		})
 	return ar
 }
 
@@ -106,6 +125,7 @@ func (ar *AlertingRule) Close() {
 	metrics.UnregisterMetric(ar.metrics.active.name)
 	metrics.UnregisterMetric(ar.metrics.pending.name)
 	metrics.UnregisterMetric(ar.metrics.errors.name)
+	metrics.UnregisterMetric(ar.metrics.samples.name)
 }
 
 // String implements Stringer interface
@@ -119,15 +139,73 @@ func (ar *AlertingRule) ID() uint64 {
 	return ar.RuleID
 }
 
+// ExecRange executes alerting rule on the given time range similarly to Exec.
+// It doesn't update internal states of the Rule and meant to be used just
+// to get time series for backfilling.
+// It returns ALERT and ALERT_FOR_STATE time series as result.
+func (ar *AlertingRule) ExecRange(ctx context.Context, start, end time.Time) ([]prompbmarshal.TimeSeries, error) {
+	series, err := ar.q.QueryRange(ctx, ar.Expr, start, end)
+	if err != nil {
+		return nil, err
+	}
+	var result []prompbmarshal.TimeSeries
+	qFn := func(query string) ([]datasource.Metric, error) {
+		return nil, fmt.Errorf("`query` template isn't supported in replay mode")
+	}
+	for _, s := range series {
+		// extra labels could contain templates, so we expand them first
+		labels, err := expandLabels(s, qFn, ar)
+		if err != nil {
+			return nil, fmt.Errorf("failed to expand labels: %s", err)
+		}
+		for k, v := range labels {
+			// apply extra labels to datasource
+			// so the hash key will be consistent on restore
+			s.SetLabel(k, v)
+		}
+
+		a, err := ar.newAlert(s, time.Time{}, qFn) // initial alert
+		if err != nil {
+			return nil, fmt.Errorf("failed to create alert: %s", err)
+		}
+		if ar.For == 0 { // if alert is instant
+			a.State = notifier.StateFiring
+			for i := range s.Values {
+				result = append(result, ar.alertToTimeSeries(a, s.Timestamps[i])...)
+			}
+			continue
+		}
+
+		// if alert with For > 0
+		prevT := time.Time{}
+		//activeAt := time.Time{}
+		for i := range s.Values {
+			at := time.Unix(s.Timestamps[i], 0)
+			if at.Sub(prevT) > ar.EvalInterval {
+				// reset to Pending if there are gaps > EvalInterval between DPs
+				a.State = notifier.StatePending
+				//activeAt = at
+				a.Start = at
+			} else if at.Sub(a.Start) >= ar.For {
+				a.State = notifier.StateFiring
+			}
+			prevT = at
+			result = append(result, ar.alertToTimeSeries(a, s.Timestamps[i])...)
+		}
+	}
+	return result, nil
+}
+
 // Exec executes AlertingRule expression via the given Querier.
 // Based on the Querier results AlertingRule maintains notifier.Alerts
-func (ar *AlertingRule) Exec(ctx context.Context, q datasource.Querier, series bool) ([]prompbmarshal.TimeSeries, error) {
-	qMetrics, err := q.Query(ctx, ar.Expr, ar.Type)
+func (ar *AlertingRule) Exec(ctx context.Context) ([]prompbmarshal.TimeSeries, error) {
+	qMetrics, err := ar.q.Query(ctx, ar.Expr)
 	ar.mu.Lock()
 	defer ar.mu.Unlock()
 
 	ar.lastExecError = err
 	ar.lastExecTime = time.Now()
+	ar.lastExecSamples = len(qMetrics)
 	if err != nil {
 		return nil, fmt.Errorf("failed to execute query %q: %w", ar.Expr, err)
 	}
@@ -139,7 +217,7 @@ func (ar *AlertingRule) Exec(ctx context.Context, q datasource.Querier, series b
 		}
 	}
 
-	qFn := func(query string) ([]datasource.Metric, error) { return q.Query(ctx, query, ar.Type) }
+	qFn := func(query string) ([]datasource.Metric, error) { return ar.q.Query(ctx, query) }
 	updated := make(map[uint64]struct{})
 	// update list of active alerts
 	for _, m := range qMetrics {
@@ -161,9 +239,9 @@ func (ar *AlertingRule) Exec(ctx context.Context, q datasource.Querier, series b
 		}
 		updated[h] = struct{}{}
 		if a, ok := ar.alerts[h]; ok {
-			if a.Value != m.Value {
+			if a.Value != m.Values[0] {
 				// update Value field with latest value
-				a.Value = m.Value
+				a.Value = m.Values[0]
 				// and re-exec template since Value can be used
 				// in annotations
 				a.Annotations, err = a.ExecTemplate(qFn, ar.Annotations)
@@ -201,10 +279,7 @@ func (ar *AlertingRule) Exec(ctx context.Context, q datasource.Querier, series b
 			alertsFired.Inc()
 		}
 	}
-	if series {
-		return ar.toTimeSeries(ar.lastExecTime), nil
-	}
-	return nil, nil
+	return ar.toTimeSeries(ar.lastExecTime.Unix()), nil
 }
 
 func expandLabels(m datasource.Metric, q notifier.QueryFn, ar *AlertingRule) (map[string]string, error) {
@@ -214,13 +289,13 @@ func expandLabels(m datasource.Metric, q notifier.QueryFn, ar *AlertingRule) (ma
 	}
 	tpl := notifier.AlertTplData{
 		Labels: metricLabels,
-		Value:  m.Value,
+		Value:  m.Values[0],
 		Expr:   ar.Expr,
 	}
 	return notifier.ExecTemplate(q, ar.Labels, tpl)
 }
 
-func (ar *AlertingRule) toTimeSeries(timestamp time.Time) []prompbmarshal.TimeSeries {
+func (ar *AlertingRule) toTimeSeries(timestamp int64) []prompbmarshal.TimeSeries {
 	var tss []prompbmarshal.TimeSeries
 	for _, a := range ar.alerts {
 		if a.State == notifier.StateInactive {
@@ -244,6 +319,8 @@ func (ar *AlertingRule) UpdateWith(r Rule) error {
 	ar.For = nr.For
 	ar.Labels = nr.Labels
 	ar.Annotations = nr.Annotations
+	ar.EvalInterval = nr.EvalInterval
+	ar.q = nr.q
 	return nil
 }
 
@@ -271,13 +348,15 @@ func (ar *AlertingRule) newAlert(m datasource.Metric, start time.Time, qFn notif
 		GroupID: ar.GroupID,
 		Name:    ar.Name,
 		Labels:  map[string]string{},
-		Value:   m.Value,
+		Value:   m.Values[0],
 		Start:   start,
 		Expr:    ar.Expr,
 	}
 	// label defined here to make override possible by
 	// time series labels.
-	a.Labels[alertGroupNameLabel] = ar.GroupName
+	if !*disableAlertGroupLabel && ar.GroupName != "" {
+		a.Labels[alertGroupNameLabel] = ar.GroupName
+	}
 	for _, l := range m.Labels {
 		// drop __name__ to be consistent with Prometheus alerting
 		if l.Name == "__name__" {
@@ -317,6 +396,7 @@ func (ar *AlertingRule) RuleAPI() APIAlertingRule {
 		Expression:  ar.Expr,
 		For:         ar.For.String(),
 		LastError:   lastErr,
+		LastSamples: ar.lastExecSamples,
 		LastExec:    ar.lastExecTime,
 		Labels:      ar.Labels,
 		Annotations: ar.Annotations,
@@ -339,6 +419,7 @@ func (ar *AlertingRule) newAlertAPI(a notifier.Alert) *APIAlert {
 		// encode as strings to avoid rounding
 		ID:      fmt.Sprintf("%d", a.ID),
 		GroupID: fmt.Sprintf("%d", a.GroupID),
+		RuleID:  fmt.Sprintf("%d", ar.RuleID),
 
 		Name:        a.Name,
 		Expression:  ar.Expr,
@@ -346,7 +427,7 @@ func (ar *AlertingRule) newAlertAPI(a notifier.Alert) *APIAlert {
 		Annotations: a.Annotations,
 		State:       a.State.String(),
 		ActiveAt:    a.Start,
-		Value:       strconv.FormatFloat(a.Value, 'e', -1, 64),
+		Value:       strconv.FormatFloat(a.Value, 'f', -1, 32),
 	}
 }
 
@@ -366,7 +447,7 @@ const (
 )
 
 // alertToTimeSeries converts the given alert with the given timestamp to timeseries
-func (ar *AlertingRule) alertToTimeSeries(a *notifier.Alert, timestamp time.Time) []prompbmarshal.TimeSeries {
+func (ar *AlertingRule) alertToTimeSeries(a *notifier.Alert, timestamp int64) []prompbmarshal.TimeSeries {
 	var tss []prompbmarshal.TimeSeries
 	tss = append(tss, alertToTimeSeries(ar.Name, a, timestamp))
 	if ar.For > 0 {
@@ -375,7 +456,7 @@ func (ar *AlertingRule) alertToTimeSeries(a *notifier.Alert, timestamp time.Time
 	return tss
 }
 
-func alertToTimeSeries(name string, a *notifier.Alert, timestamp time.Time) prompbmarshal.TimeSeries {
+func alertToTimeSeries(name string, a *notifier.Alert, timestamp int64) prompbmarshal.TimeSeries {
 	labels := make(map[string]string)
 	for k, v := range a.Labels {
 		labels[k] = v
@@ -383,19 +464,19 @@ func alertToTimeSeries(name string, a *notifier.Alert, timestamp time.Time) prom
 	labels["__name__"] = alertMetricName
 	labels[alertNameLabel] = name
 	labels[alertStateLabel] = a.State.String()
-	return newTimeSeries(1, labels, timestamp)
+	return newTimeSeries([]float64{1}, []int64{timestamp}, labels)
 }
 
 // alertForToTimeSeries returns a timeseries that represents
 // state of active alerts, where value is time when alert become active
-func alertForToTimeSeries(name string, a *notifier.Alert, timestamp time.Time) prompbmarshal.TimeSeries {
+func alertForToTimeSeries(name string, a *notifier.Alert, timestamp int64) prompbmarshal.TimeSeries {
 	labels := make(map[string]string)
 	for k, v := range a.Labels {
 		labels[k] = v
 	}
 	labels["__name__"] = alertForStateMetricName
 	labels[alertNameLabel] = name
-	return newTimeSeries(float64(a.Start.Unix()), labels, timestamp)
+	return newTimeSeries([]float64{float64(a.Start.Unix())}, []int64{timestamp}, labels)
 }
 
 // Restore restores the state of active alerts basing on previously written timeseries.
@@ -407,7 +488,7 @@ func (ar *AlertingRule) Restore(ctx context.Context, q datasource.Querier, lookb
 		return fmt.Errorf("querier is nil")
 	}
 
-	qFn := func(query string) ([]datasource.Metric, error) { return q.Query(ctx, query, ar.Type) }
+	qFn := func(query string) ([]datasource.Metric, error) { return ar.q.Query(ctx, query) }
 
 	// account for external labels in filter
 	var labelsFilter string
@@ -420,7 +501,7 @@ func (ar *AlertingRule) Restore(ctx context.Context, q datasource.Querier, lookb
 	// 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)
+	qMetrics, err := q.Query(ctx, expr)
 	if err != nil {
 		return err
 	}
@@ -437,7 +518,7 @@ func (ar *AlertingRule) Restore(ctx context.Context, q datasource.Querier, lookb
 			m.Labels = append(m.Labels, l)
 		}
 
-		a, err := ar.newAlert(m, time.Unix(int64(m.Value), 0), qFn)
+		a, err := ar.newAlert(m, time.Unix(int64(m.Values[0]), 0), qFn)
 		if err != nil {
 			return fmt.Errorf("failed to create alert: %w", err)
 		}

app/vmalert/alerting_test.go

@@ -24,11 +24,11 @@ func TestAlertingRule_ToTimeSeries(t *testing.T) {
 			newTestAlertingRule("instant", 0),
 			&notifier.Alert{State: notifier.StateFiring},
 			[]prompbmarshal.TimeSeries{
-				newTimeSeries(1, map[string]string{
+				newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()}, map[string]string{
 					"__name__":      alertMetricName,
 					alertStateLabel: notifier.StateFiring.String(),
 					alertNameLabel:  "instant",
-				}, timestamp),
+				}),
 			},
 		},
 		{
@@ -38,13 +38,13 @@ func TestAlertingRule_ToTimeSeries(t *testing.T) {
 				"instance": "bar",
 			}},
 			[]prompbmarshal.TimeSeries{
-				newTimeSeries(1, map[string]string{
+				newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()}, map[string]string{
 					"__name__":      alertMetricName,
 					alertStateLabel: notifier.StateFiring.String(),
 					alertNameLabel:  "instant extra labels",
 					"job":           "foo",
 					"instance":      "bar",
-				}, timestamp),
+				}),
 			},
 		},
 		{
@@ -54,48 +54,52 @@ func TestAlertingRule_ToTimeSeries(t *testing.T) {
 				"__name__":      "bar",
 			}},
 			[]prompbmarshal.TimeSeries{
-				newTimeSeries(1, map[string]string{
+				newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()}, map[string]string{
 					"__name__":      alertMetricName,
 					alertStateLabel: notifier.StateFiring.String(),
 					alertNameLabel:  "instant labels override",
-				}, timestamp),
+				}),
 			},
 		},
 		{
 			newTestAlertingRule("for", time.Second),
 			&notifier.Alert{State: notifier.StateFiring, Start: timestamp.Add(time.Second)},
 			[]prompbmarshal.TimeSeries{
-				newTimeSeries(1, map[string]string{
+				newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()}, map[string]string{
 					"__name__":      alertMetricName,
 					alertStateLabel: notifier.StateFiring.String(),
 					alertNameLabel:  "for",
-				}, timestamp),
-				newTimeSeries(float64(timestamp.Add(time.Second).Unix()), map[string]string{
-					"__name__":     alertForStateMetricName,
-					alertNameLabel: "for",
-				}, timestamp),
+				}),
+				newTimeSeries([]float64{float64(timestamp.Add(time.Second).Unix())},
+					[]int64{timestamp.UnixNano()},
+					map[string]string{
+						"__name__":     alertForStateMetricName,
+						alertNameLabel: "for",
+					}),
 			},
 		},
 		{
 			newTestAlertingRule("for pending", 10*time.Second),
 			&notifier.Alert{State: notifier.StatePending, Start: timestamp.Add(time.Second)},
 			[]prompbmarshal.TimeSeries{
-				newTimeSeries(1, map[string]string{
+				newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()}, map[string]string{
 					"__name__":      alertMetricName,
 					alertStateLabel: notifier.StatePending.String(),
 					alertNameLabel:  "for pending",
-				}, timestamp),
-				newTimeSeries(float64(timestamp.Add(time.Second).Unix()), map[string]string{
-					"__name__":     alertForStateMetricName,
-					alertNameLabel: "for pending",
-				}, timestamp),
+				}),
+				newTimeSeries([]float64{float64(timestamp.Add(time.Second).Unix())},
+					[]int64{timestamp.UnixNano()},
+					map[string]string{
+						"__name__":     alertForStateMetricName,
+						alertNameLabel: "for pending",
+					}),
 			},
 		},
 	}
 	for _, tc := range testCases {
 		t.Run(tc.rule.Name, func(t *testing.T) {
 			tc.rule.alerts[tc.alert.ID] = tc.alert
-			tss := tc.rule.toTimeSeries(timestamp)
+			tss := tc.rule.toTimeSeries(timestamp.Unix())
 			if err := compareTimeSeries(t, tc.expTS, tss); err != nil {
 				t.Fatalf("timeseries missmatch: %s", err)
 			}
@@ -118,7 +122,7 @@ func TestAlertingRule_Exec(t *testing.T) {
 		{
 			newTestAlertingRule("empty labels", 0),
 			[][]datasource.Metric{
-				{datasource.Metric{}},
+				{datasource.Metric{Values: []float64{1}, Timestamps: []int64{1}}},
 			},
 			map[uint64]*notifier.Alert{
 				hash(datasource.Metric{}): {State: notifier.StateFiring},
@@ -294,11 +298,12 @@ func TestAlertingRule_Exec(t *testing.T) {
 	for _, tc := range testCases {
 		t.Run(tc.rule.Name, func(t *testing.T) {
 			fq := &fakeQuerier{}
+			tc.rule.q = fq
 			tc.rule.GroupID = fakeGroup.ID()
 			for _, step := range tc.steps {
 				fq.reset()
 				fq.add(step...)
-				if _, err := tc.rule.Exec(context.TODO(), fq, false); err != nil {
+				if _, err := tc.rule.Exec(context.TODO()); err != nil {
 					t.Fatalf("unexpected err: %s", err)
 				}
 				// artificial delay between applying steps
@@ -320,6 +325,166 @@ func TestAlertingRule_Exec(t *testing.T) {
 	}
 }
 
+func TestAlertingRule_ExecRange(t *testing.T) {
+	testCases := []struct {
+		rule      *AlertingRule
+		data      []datasource.Metric
+		expAlerts []*notifier.Alert
+	}{
+		{
+			newTestAlertingRule("empty", 0),
+			[]datasource.Metric{},
+			nil,
+		},
+		{
+			newTestAlertingRule("empty labels", 0),
+			[]datasource.Metric{
+				{Values: []float64{1}, Timestamps: []int64{1}},
+			},
+			[]*notifier.Alert{
+				{State: notifier.StateFiring},
+			},
+		},
+		{
+			newTestAlertingRule("single-firing", 0),
+			[]datasource.Metric{
+				metricWithLabels(t, "name", "foo"),
+			},
+			[]*notifier.Alert{
+				{
+					Labels: map[string]string{"name": "foo"},
+					State:  notifier.StateFiring,
+				},
+			},
+		},
+		{
+			newTestAlertingRule("single-firing-on-range", 0),
+			[]datasource.Metric{
+				{Values: []float64{1, 1, 1}, Timestamps: []int64{1e3, 2e3, 3e3}},
+			},
+			[]*notifier.Alert{
+				{State: notifier.StateFiring},
+				{State: notifier.StateFiring},
+				{State: notifier.StateFiring},
+			},
+		},
+		{
+			newTestAlertingRule("for-pending", time.Second),
+			[]datasource.Metric{
+				{Values: []float64{1, 1, 1}, Timestamps: []int64{1, 3, 5}},
+			},
+			[]*notifier.Alert{
+				{State: notifier.StatePending, Start: time.Unix(1, 0)},
+				{State: notifier.StatePending, Start: time.Unix(3, 0)},
+				{State: notifier.StatePending, Start: time.Unix(5, 0)},
+			},
+		},
+		{
+			newTestAlertingRule("for-firing", 3*time.Second),
+			[]datasource.Metric{
+				{Values: []float64{1, 1, 1}, Timestamps: []int64{1, 3, 5}},
+			},
+			[]*notifier.Alert{
+				{State: notifier.StatePending, Start: time.Unix(1, 0)},
+				{State: notifier.StatePending, Start: time.Unix(1, 0)},
+				{State: notifier.StateFiring, Start: time.Unix(1, 0)},
+			},
+		},
+		{
+			newTestAlertingRule("for=>pending=>firing=>pending=>firing=>pending", time.Second),
+			[]datasource.Metric{
+				{Values: []float64{1, 1, 1, 1, 1}, Timestamps: []int64{1, 2, 5, 6, 20}},
+			},
+			[]*notifier.Alert{
+				{State: notifier.StatePending, Start: time.Unix(1, 0)},
+				{State: notifier.StateFiring, Start: time.Unix(1, 0)},
+				{State: notifier.StatePending, Start: time.Unix(5, 0)},
+				{State: notifier.StateFiring, Start: time.Unix(5, 0)},
+				{State: notifier.StatePending, Start: time.Unix(20, 0)},
+			},
+		},
+		{
+			newTestAlertingRule("multi-series-for=>pending=>pending=>firing", 3*time.Second),
+			[]datasource.Metric{
+				{Values: []float64{1, 1, 1}, Timestamps: []int64{1, 3, 5}},
+				{Values: []float64{1, 1}, Timestamps: []int64{1, 5},
+					Labels: []datasource.Label{{Name: "foo", Value: "bar"}},
+				},
+			},
+			[]*notifier.Alert{
+				{State: notifier.StatePending, Start: time.Unix(1, 0)},
+				{State: notifier.StatePending, Start: time.Unix(1, 0)},
+				{State: notifier.StateFiring, Start: time.Unix(1, 0)},
+				//
+				{State: notifier.StatePending, Start: time.Unix(1, 0),
+					Labels: map[string]string{
+						"foo": "bar",
+					}},
+				{State: notifier.StatePending, Start: time.Unix(5, 0),
+					Labels: map[string]string{
+						"foo": "bar",
+					}},
+			},
+		},
+		{
+			newTestRuleWithLabels("multi-series-firing", "source", "vm"),
+			[]datasource.Metric{
+				{Values: []float64{1, 1}, Timestamps: []int64{1, 100}},
+				{Values: []float64{1, 1}, Timestamps: []int64{1, 5},
+					Labels: []datasource.Label{{Name: "foo", Value: "bar"}},
+				},
+			},
+			[]*notifier.Alert{
+				{State: notifier.StateFiring, Labels: map[string]string{
+					"source": "vm",
+				}},
+				{State: notifier.StateFiring, Labels: map[string]string{
+					"source": "vm",
+				}},
+				//
+				{State: notifier.StateFiring, Labels: map[string]string{
+					"foo":    "bar",
+					"source": "vm",
+				}},
+				{State: notifier.StateFiring, Labels: map[string]string{
+					"foo":    "bar",
+					"source": "vm",
+				}},
+			},
+		},
+	}
+	fakeGroup := Group{Name: "TestRule_ExecRange"}
+	for _, tc := range testCases {
+		t.Run(tc.rule.Name, func(t *testing.T) {
+			fq := &fakeQuerier{}
+			tc.rule.q = fq
+			tc.rule.GroupID = fakeGroup.ID()
+			fq.add(tc.data...)
+			gotTS, err := tc.rule.ExecRange(context.TODO(), time.Now(), time.Now())
+			if err != nil {
+				t.Fatalf("unexpected err: %s", err)
+			}
+			var expTS []prompbmarshal.TimeSeries
+			var j int
+			for _, series := range tc.data {
+				for _, timestamp := range series.Timestamps {
+					expTS = append(expTS, tc.rule.alertToTimeSeries(tc.expAlerts[j], timestamp)...)
+					j++
+				}
+			}
+			if len(gotTS) != len(expTS) {
+				t.Fatalf("expected %d time series; got %d", len(expTS), len(gotTS))
+			}
+			for i := range expTS {
+				got, exp := gotTS[i], expTS[i]
+				if !reflect.DeepEqual(got, exp) {
+					t.Fatalf("%d: expected \n%v but got \n%v", i, exp, got)
+				}
+			}
+		})
+	}
+}
+
 func TestAlertingRule_Restore(t *testing.T) {
 	testCases := []struct {
 		rule      *AlertingRule
@@ -410,6 +575,7 @@ func TestAlertingRule_Restore(t *testing.T) {
 		t.Run(tc.rule.Name, func(t *testing.T) {
 			fq := &fakeQuerier{}
 			tc.rule.GroupID = fakeGroup.ID()
+			tc.rule.q = fq
 			fq.add(tc.metrics...)
 			if err := tc.rule.Restore(context.TODO(), fq, time.Hour, nil); err != nil {
 				t.Fatalf("unexpected err: %s", err)
@@ -437,17 +603,18 @@ func TestAlertingRule_Exec_Negative(t *testing.T) {
 	fq := &fakeQuerier{}
 	ar := newTestAlertingRule("test", 0)
 	ar.Labels = map[string]string{"job": "test"}
+	ar.q = fq
 
 	// successful attempt
 	fq.add(metricWithValueAndLabels(t, 1, "__name__", "foo", "job", "bar"))
-	_, err := ar.Exec(context.TODO(), fq, false)
+	_, err := ar.Exec(context.TODO())
 	if err != nil {
 		t.Fatal(err)
 	}
 
 	// label `job` will collide with rule extra label and will make both time series equal
 	fq.add(metricWithValueAndLabels(t, 1, "__name__", "foo", "job", "baz"))
-	_, err = ar.Exec(context.TODO(), fq, false)
+	_, err = ar.Exec(context.TODO())
 	if !errors.Is(err, errDuplicate) {
 		t.Fatalf("expected to have %s error; got %s", errDuplicate, err)
 	}
@@ -456,7 +623,7 @@ func TestAlertingRule_Exec_Negative(t *testing.T) {
 
 	expErr := "connection reset by peer"
 	fq.setErr(errors.New(expErr))
-	_, err = ar.Exec(context.TODO(), fq, false)
+	_, err = ar.Exec(context.TODO())
 	if err == nil {
 		t.Fatalf("expected to get err; got nil")
 	}
@@ -481,17 +648,15 @@ func TestAlertingRule_Template(t *testing.T) {
 				hash(metricWithLabels(t, "region", "east", "instance", "foo")): {
 					Annotations: map[string]string{},
 					Labels: map[string]string{
-						alertGroupNameLabel: "",
-						"region":            "east",
-						"instance":          "foo",
+						"region":   "east",
+						"instance": "foo",
 					},
 				},
 				hash(metricWithLabels(t, "region", "east", "instance", "bar")): {
 					Annotations: map[string]string{},
 					Labels: map[string]string{
-						alertGroupNameLabel: "",
-						"region":            "east",
-						"instance":          "bar",
+						"region":   "east",
+						"instance": "bar",
 					},
 				},
 			},
@@ -516,9 +681,8 @@ func TestAlertingRule_Template(t *testing.T) {
 			map[uint64]*notifier.Alert{
 				hash(metricWithLabels(t, "region", "east", "instance", "foo")): {
 					Labels: map[string]string{
-						alertGroupNameLabel: "",
-						"instance":          "foo",
-						"region":            "east",
+						"instance": "foo",
+						"region":   "east",
 					},
 					Annotations: map[string]string{
 						"summary":     `Too high connection number for "foo" for region east`,
@@ -527,9 +691,8 @@ func TestAlertingRule_Template(t *testing.T) {
 				},
 				hash(metricWithLabels(t, "region", "east", "instance", "bar")): {
 					Labels: map[string]string{
-						alertGroupNameLabel: "",
-						"instance":          "bar",
-						"region":            "east",
+						"instance": "bar",
+						"region":   "east",
 					},
 					Annotations: map[string]string{
 						"summary":     `Too high connection number for "bar" for region east`,
@@ -544,8 +707,9 @@ func TestAlertingRule_Template(t *testing.T) {
 		t.Run(tc.rule.Name, func(t *testing.T) {
 			fq := &fakeQuerier{}
 			tc.rule.GroupID = fakeGroup.ID()
+			tc.rule.q = fq
 			fq.add(tc.metrics...)
-			if _, err := tc.rule.Exec(context.TODO(), fq, false); err != nil {
+			if _, err := tc.rule.Exec(context.TODO()); err != nil {
 				t.Fatalf("unexpected err: %s", err)
 			}
 			for hash, expAlert := range tc.expAlerts {
@@ -575,5 +739,5 @@ func newTestRuleWithLabels(name string, labels ...string) *AlertingRule {
 }
 
 func newTestAlertingRule(name string, waitFor time.Duration) *AlertingRule {
-	return &AlertingRule{Name: name, alerts: make(map[uint64]*notifier.Alert), For: waitFor}
+	return &AlertingRule{Name: name, alerts: make(map[uint64]*notifier.Alert), For: waitFor, EvalInterval: waitFor}
 }

app/vmalert/config/config.go

@@ -8,7 +8,6 @@ import (
 	"path/filepath"
 	"sort"
 	"strings"
-	"time"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
 
@@ -16,7 +15,6 @@ import (
 	"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"
 )
 
@@ -25,10 +23,17 @@ import (
 type Group struct {
 	Type        datasource.Type `yaml:"type,omitempty"`
 	File        string
-	Name        string        `yaml:"name"`
-	Interval    time.Duration `yaml:"interval,omitempty"`
-	Rules       []Rule        `yaml:"rules"`
-	Concurrency int           `yaml:"concurrency"`
+	Name        string             `yaml:"name"`
+	Interval    utils.PromDuration `yaml:"interval"`
+	Rules       []Rule             `yaml:"rules"`
+	Concurrency int                `yaml:"concurrency"`
+	// ExtraFilterLabels is a list label filters applied to every rule
+	// request withing a group. Is compatible only with VM datasources.
+	// See https://docs.victoriametrics.com#prometheus-querying-api-enhancements
+	ExtraFilterLabels map[string]string `yaml:"extra_filter_labels"`
+	// Labels is a set of label value pairs, that will be added to every rule.
+	// It has priority over the external labels.
+	Labels map[string]string `yaml:"labels"`
 	// Checksum stores the hash of yaml definition for this group.
 	// May be used to detect any changes like rules re-ordering etc.
 	Checksum string
@@ -115,54 +120,18 @@ func (g *Group) Validate(validateAnnotations, validateExpressions bool) error {
 // 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"`
+	Type        datasource.Type    `yaml:"type,omitempty"`
+	Record      string             `yaml:"record,omitempty"`
+	Alert       string             `yaml:"alert,omitempty"`
+	Expr        string             `yaml:"expr"`
+	For         utils.PromDuration `yaml:"for"`
+	Labels      map[string]string  `yaml:"labels,omitempty"`
+	Annotations map[string]string  `yaml:"annotations,omitempty"`
 
 	// Catches all undefined fields and must be empty after parsing.
 	XXX map[string]interface{} `yaml:",inline"`
 }
 
-// PromDuration is Prometheus duration.
-type PromDuration struct {
-	milliseconds int64
-}
-
-// NewPromDuration returns PromDuration for given d.
-func NewPromDuration(d time.Duration) PromDuration {
-	return PromDuration{
-		milliseconds: d.Milliseconds(),
-	}
-}
-
-// 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

app/vmalert/config/config_test.go

@@ -8,10 +8,9 @@ import (
 	"time"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
-
-	"gopkg.in/yaml.v2"
-
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/utils"
+	"gopkg.in/yaml.v2"
 )
 
 func TestMain(m *testing.M) {
@@ -264,7 +263,7 @@ func TestGroup_Validate(t *testing.T) {
 				Rules: []Rule{
 					{
 						Expr: "sumSeries(time('foo.bar',10))",
-						For:  PromDuration{milliseconds: 10},
+						For:  utils.NewPromDuration(10 * time.Millisecond),
 					},
 					{
 						Expr: "sum(up == 0 ) by (host)",
@@ -280,7 +279,7 @@ func TestGroup_Validate(t *testing.T) {
 				Rules: []Rule{
 					{
 						Expr: "sum(up == 0 ) by (host)",
-						For:  PromDuration{milliseconds: 10},
+						For:  utils.NewPromDuration(10 * time.Millisecond),
 					},
 					{
 						Expr: "sumSeries(time('foo.bar',10))",
@@ -348,7 +347,7 @@ func TestHashRule(t *testing.T) {
 			true,
 		},
 		{
-			Rule{Alert: "alert", Expr: "up == 1", For: NewPromDuration(time.Minute)},
+			Rule{Alert: "alert", Expr: "up == 1", For: utils.NewPromDuration(time.Minute)},
 			Rule{Alert: "alert", Expr: "up == 1"},
 			true,
 		},
@@ -437,7 +436,7 @@ rules:
 `)
 	})
 
-	t.Run("Ok, `for` must change cs", func(t *testing.T) {
+	t.Run("`for` change", func(t *testing.T) {
 		f(t, `
 name: TestGroup
 rules:
@@ -451,5 +450,34 @@ rules:
     expr: sum by(job) (up == 1)
 `)
 	})
-
+	t.Run("`interval` change", func(t *testing.T) {
+		f(t, `
+name: TestGroup
+interval: 2s
+rules:
+  - alert: ExampleAlertWithFor
+    expr: sum by(job) (up == 1)
+`, `
+name: TestGroup
+interval: 4s
+rules:
+  - alert: ExampleAlertWithFor
+    expr: sum by(job) (up == 1)
+`)
+	})
+	t.Run("`concurrency` change", func(t *testing.T) {
+		f(t, `
+name: TestGroup
+concurrency: 2
+rules:
+  - alert: ExampleAlertWithFor
+    expr: sum by(job) (up == 1)
+`, `
+name: TestGroup
+concurrency: 16
+rules:
+  - alert: ExampleAlertWithFor
+    expr: sum by(job) (up == 1)
+`)
+	})
 }

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

@@ -3,6 +3,8 @@ groups:
     interval: 2s
     concurrency: 2
     type: prometheus
+    labels:
+      cluster: main
     rules:
       - alert: up
         expr: up == 0

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

@@ -1,5 +1,7 @@
 groups:
   - name: duplicatedGroupDiffFiles
+    labels:
+       dc: gcp
     rules:
       - alert: VMRows
         for: 5m

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

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

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

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

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

@@ -2,6 +2,8 @@ groups:
   - name: TestGroup
     interval: 2s
     concurrency: 2
+    extra_filter_labels:
+        job: victoriametrics
     rules:
       - alert: Conns
         expr: sum(vm_tcplistener_conns) by(instance) > 1

app/vmalert/datasource/datasource.go

@@ -2,21 +2,33 @@ package datasource
 
 import (
 	"context"
+	"time"
 )
 
-// Querier interface wraps Query method which
-// executes given query and returns list of Metrics
-// as result
+// Querier interface wraps Query and QueryRange methods
 type Querier interface {
-	Query(ctx context.Context, query string, engine Type) ([]Metric, error)
+	Query(ctx context.Context, query string) ([]Metric, error)
+	QueryRange(ctx context.Context, query string, from, to time.Time) ([]Metric, error)
+}
+
+// QuerierBuilder builds Querier with given params.
+type QuerierBuilder interface {
+	BuildWithParams(params QuerierParams) Querier
+}
+
+// QuerierParams params for Querier.
+type QuerierParams struct {
+	DataSourceType     *Type
+	EvaluationInterval time.Duration
+	// see https://docs.victoriametrics.com/#prometheus-querying-api-enhancements
+	ExtraLabels map[string]string
 }
 
 // Metric is the basic entity which should be return by datasource
-// It represents single data point with full list of labels
 type Metric struct {
-	Labels    []Label
-	Timestamp int64
-	Value     float64
+	Labels     []Label
+	Timestamps []int64
+	Values     []float64
 }
 
 // SetLabel adds or updates existing one label

app/vmalert/datasource/datasource_test.go

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

app/vmalert/datasource/init.go

@@ -4,42 +4,75 @@ import (
 	"flag"
 	"fmt"
 	"net/http"
+	"strings"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/utils"
 )
 
 var (
-	addr = flag.String("datasource.url", "", "Victoria Metrics or VMSelect url. Required parameter."+
-		" E.g. http://127.0.0.1:8428")
-	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")
+	addr = flag.String("datasource.url", "", "VictoriaMetrics or vmselect url. Required parameter. "+
+		"E.g. http://127.0.0.1:8428")
+	appendTypePrefix      = flag.Bool("datasource.appendTypePrefix", false, "Whether to add type prefix to -datasource.url based on the query type. Set to true if sending different query types to the vmselect URL.")
+	basicAuthUsername     = flag.String("datasource.basicAuth.username", "", "Optional basic auth username for -datasource.url")
+	basicAuthPassword     = flag.String("datasource.basicAuth.password", "", "Optional basic auth password for -datasource.url")
+	basicAuthPasswordFile = flag.String("datasource.basicAuth.passwordFile", "", "Optional path to basic auth password to use for -datasource.url")
+	bearerToken           = flag.String("datasource.bearerToken", "", "Optional bearer auth token to use for -datasource.url.")
+	bearerTokenFile       = flag.String("datasource.bearerTokenFile", "", "Optional path to bearer token file to use for -datasource.url.")
 
 	tlsInsecureSkipVerify = flag.Bool("datasource.tlsInsecureSkipVerify", false, "Whether to skip tls verification when connecting to -datasource.url")
 	tlsCertFile           = flag.String("datasource.tlsCertFile", "", "Optional path to client-side TLS certificate file to use when connecting to -datasource.url")
 	tlsKeyFile            = flag.String("datasource.tlsKeyFile", "", "Optional path to client-side TLS certificate key to use when connecting to -datasource.url")
-	tlsCAFile             = flag.String("datasource.tlsCAFile", "", "Optional path to TLS CA file to use for verifying connections to -datasource.url. "+
-		"By default system CA is used")
-	tlsServerName = flag.String("datasource.tlsServerName", "", "Optional TLS server name to use for connections to -datasource.url. "+
-		"By default the server name from -datasource.url is used")
+	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.")
+	lookBack  = flag.Duration("datasource.lookback", 0, `Lookback defines how far into the past to look when evaluating queries. For example, if the datasource.lookback=5m then param "time" with value now()-5m will be added to every query.`)
 	queryStep = flag.Duration("datasource.queryStep", 0, "queryStep defines how far a value can fallback to when evaluating queries. "+
-		"For example, if datasource.queryStep=15s then param \"step\" with value \"15s\" will be added to every query.")
-	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.")
+		"For example, if datasource.queryStep=15s then param \"step\" with value \"15s\" will be added to every query."+
+		"If queryStep isn't specified, rule's evaluationInterval will be used instead.")
+	maxIdleConnections = flag.Int("datasource.maxIdleConnections", 100, `Defines the number of idle (keep-alive connections) to each configured datasource. Consider setting this value equal to the value: groups_total * group.concurrency. Too low a value may result in a high number of sockets in TIME_WAIT state.`)
+	roundDigits        = flag.Int("datasource.roundDigits", 0, `Adds "round_digits" GET param to datasource requests. `+
+		`In VM "round_digits" limits the number of digits after the decimal point in response values.`)
 )
 
+// Param represents an HTTP GET param
+type Param struct {
+	Key, Value string
+}
+
 // Init creates a Querier from provided flag values.
-func Init() (Querier, error) {
+// Provided extraParams will be added as GET params to
+// each request.
+func Init(extraParams []Param) (QuerierBuilder, error) {
 	if *addr == "" {
 		return nil, fmt.Errorf("datasource.url is empty")
 	}
+
 	tr, err := utils.Transport(*addr, *tlsCertFile, *tlsKeyFile, *tlsCAFile, *tlsServerName, *tlsInsecureSkipVerify)
 	if err != nil {
 		return nil, fmt.Errorf("failed to create transport: %w", err)
 	}
-	tr.MaxIdleConns = *maxIdleConnections
-	c := &http.Client{Transport: tr}
-	return NewVMStorage(*addr, *basicAuthUsername, *basicAuthPassword, *lookBack, *queryStep, c), nil
+	tr.MaxIdleConnsPerHost = *maxIdleConnections
+
+	if *roundDigits > 0 {
+		extraParams = append(extraParams, Param{
+			Key:   "round_digits",
+			Value: fmt.Sprintf("%d", *roundDigits),
+		})
+	}
+
+	authCfg, err := utils.AuthConfig(*basicAuthUsername, *basicAuthPassword, *basicAuthPasswordFile, *bearerToken, *bearerTokenFile)
+	if err != nil {
+		return nil, fmt.Errorf("failed to configure auth: %w", err)
+	}
+
+	return &VMStorage{
+		c:                &http.Client{Transport: tr},
+		authCfg:          authCfg,
+		datasourceURL:    strings.TrimSuffix(*addr, "/"),
+		appendTypePrefix: *appendTypePrefix,
+		lookBack:         *lookBack,
+		queryStep:        *queryStep,
+		dataSourceType:   NewPrometheusType(),
+		extraParams:      extraParams,
+	}, nil
 }

app/vmalert/datasource/vm.go

@@ -2,194 +2,156 @@ package datasource
 
 import (
 	"context"
-	"encoding/json"
 	"fmt"
 	"io/ioutil"
 	"net/http"
-	"strconv"
 	"strings"
 	"time"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promauth"
 )
 
-type response struct {
-	Status string `json:"status"`
-	Data   struct {
-		ResultType string `json:"resultType"`
-		Result     []struct {
-			Labels map[string]string `json:"metric"`
-			TV     [2]interface{}    `json:"value"`
-		} `json:"result"`
-	} `json:"data"`
-	ErrorType string `json:"errorType"`
-	Error     string `json:"error"`
-}
-
-func (r response) metrics() ([]Metric, error) {
-	var ms []Metric
-	var m Metric
-	var f float64
-	var err error
-	for i, res := range r.Data.Result {
-		f, err = strconv.ParseFloat(res.TV[1].(string), 64)
-		if err != nil {
-			return nil, fmt.Errorf("metric %v, unable to parse float64 from %s: %w", res, res.TV[1], err)
-		}
-		m.Labels = nil
-		for k, v := range r.Data.Result[i].Labels {
-			m.AddLabel(k, v)
-		}
-		m.Timestamp = int64(res.TV[0].(float64))
-		m.Value = f
-		ms = append(ms, m)
-	}
-	return ms, nil
-}
-
-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
-	datasourceURL string
-	basicAuthUser string
-	basicAuthPass string
-	lookBack      time.Duration
-	queryStep     time.Duration
+	c                *http.Client
+	authCfg          *promauth.Config
+	datasourceURL    string
+	appendTypePrefix bool
+	lookBack         time.Duration
+	queryStep        time.Duration
+
+	dataSourceType     Type
+	evaluationInterval time.Duration
+	extraLabels        []string
+	extraParams        []Param
 }
 
-const queryPath = "/api/v1/query"
-const graphitePath = "/render"
+// Clone makes clone of VMStorage, shares http client.
+func (s *VMStorage) Clone() *VMStorage {
+	return &VMStorage{
+		c:                s.c,
+		authCfg:          s.authCfg,
+		datasourceURL:    s.datasourceURL,
+		lookBack:         s.lookBack,
+		queryStep:        s.queryStep,
+		appendTypePrefix: s.appendTypePrefix,
+		dataSourceType:   s.dataSourceType,
+	}
+}
+
+// ApplyParams - changes given querier params.
+func (s *VMStorage) ApplyParams(params QuerierParams) *VMStorage {
+	if params.DataSourceType != nil {
+		s.dataSourceType = *params.DataSourceType
+	}
+	s.evaluationInterval = params.EvaluationInterval
+	for k, v := range params.ExtraLabels {
+		s.extraLabels = append(s.extraLabels, fmt.Sprintf("%s=%s", k, v))
+	}
+	return s
+}
+
+// BuildWithParams - implements interface.
+func (s *VMStorage) BuildWithParams(params QuerierParams) Querier {
+	return s.Clone().ApplyParams(params)
+}
 
 // NewVMStorage is a constructor for VMStorage
-func NewVMStorage(baseURL, basicAuthUser, basicAuthPass string, lookBack time.Duration, queryStep time.Duration, c *http.Client) *VMStorage {
+func NewVMStorage(baseURL string, authCfg *promauth.Config, lookBack time.Duration, queryStep time.Duration, appendTypePrefix bool, c *http.Client) *VMStorage {
 	return &VMStorage{
-		c:             c,
-		basicAuthUser: basicAuthUser,
-		basicAuthPass: basicAuthPass,
-		datasourceURL: strings.TrimSuffix(baseURL, "/"),
-		lookBack:      lookBack,
-		queryStep:     queryStep,
+		c:                c,
+		authCfg:          authCfg,
+		datasourceURL:    strings.TrimSuffix(baseURL, "/"),
+		appendTypePrefix: appendTypePrefix,
+		lookBack:         lookBack,
+		queryStep:        queryStep,
+		dataSourceType:   NewPrometheusType(),
 	}
 }
 
-// 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 {
+// Query executes the given query and returns parsed response
+func (s *VMStorage) Query(ctx context.Context, query string) ([]Metric, error) {
+	req, err := s.newRequestPOST()
+	if err != nil {
+		return nil, err
+	}
+
+	ts := time.Now()
+	switch s.dataSourceType.name {
 	case "", prometheusType:
-		return s.queryDataSource(ctx, query, s.setPrometheusReqParams, parsePrometheusResponse)
+		s.setPrometheusInstantReqParams(req, query, ts)
 	case graphiteType:
-		return s.queryDataSource(ctx, query, s.setGraphiteReqParams, parseGraphiteResponse)
+		s.setGraphiteReqParams(req, query, ts)
 	default:
-		return nil, fmt.Errorf("engine not found: %q", dataSourceType)
+		return nil, fmt.Errorf("engine not found: %q", s.dataSourceType.name)
 	}
+
+	resp, err := s.do(ctx, req)
+	if err != nil {
+		return nil, err
+	}
+	defer func() {
+		_ = resp.Body.Close()
+	}()
+
+	parseFn := parsePrometheusResponse
+	if s.dataSourceType.name != prometheusType {
+		parseFn = parseGraphiteResponse
+	}
+	return parseFn(req, resp)
 }
 
-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) {
+// QueryRange executes the given query on the given time range.
+// For Prometheus type see https://prometheus.io/docs/prometheus/latest/querying/api/#range-queries
+// Graphite type isn't supported.
+func (s *VMStorage) QueryRange(ctx context.Context, query string, start, end time.Time) ([]Metric, error) {
+	if s.dataSourceType.name != prometheusType {
+		return nil, fmt.Errorf("%q is not supported for QueryRange", s.dataSourceType.name)
+	}
+	req, err := s.newRequestPOST()
+	if err != nil {
+		return nil, err
+	}
+	if start.IsZero() {
+		return nil, fmt.Errorf("start param is missing")
+	}
+	if end.IsZero() {
+		return nil, fmt.Errorf("end param is missing")
+	}
+	s.setPrometheusRangeReqParams(req, query, start, end)
+	resp, err := s.do(ctx, req)
+	if err != nil {
+		return nil, err
+	}
+	defer func() {
+		_ = resp.Body.Close()
+	}()
+	return parsePrometheusResponse(req, resp)
+}
+
+func (s *VMStorage) do(ctx context.Context, req *http.Request) (*http.Response, error) {
+	resp, err := s.c.Do(req.WithContext(ctx))
+	if err != nil {
+		return nil, fmt.Errorf("error getting response from %s: %w", req.URL, err)
+	}
+	if resp.StatusCode != http.StatusOK {
+		body, _ := ioutil.ReadAll(resp.Body)
+		_ = resp.Body.Close()
+		return nil, fmt.Errorf("unexpected response code %d for %s. Response body %s", resp.StatusCode, req.URL, body)
+	}
+	return resp, nil
+}
+
+func (s *VMStorage) newRequestPOST() (*http.Request, error) {
 	req, err := http.NewRequest("POST", s.datasourceURL, nil)
 	if err != nil {
 		return nil, err
 	}
 	req.Header.Set("Content-Type", "application/json; charset=utf-8")
-	if s.basicAuthPass != "" {
-		req.SetBasicAuth(s.basicAuthUser, s.basicAuthPass)
+	if s.authCfg != nil {
+		if auth := s.authCfg.GetAuthHeader(); auth != "" {
+			req.Header.Set("Authorization", auth)
+		}
 	}
-	setReqParams(req, query)
-	resp, err := s.c.Do(req.WithContext(ctx))
-	if err != nil {
-		return nil, fmt.Errorf("error getting response from %s: %w", req.URL, err)
-	}
-	defer func() { _ = resp.Body.Close() }()
-	if resp.StatusCode != http.StatusOK {
-		body, _ := ioutil.ReadAll(resp.Body)
-		return nil, fmt.Errorf("datasource returns unexpected response code %d for %s. Response body %s", resp.StatusCode, req.URL, body)
-	}
-	return processResponse(req, resp)
-}
-
-func (s *VMStorage) setPrometheusReqParams(r *http.Request, query string) {
-	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) {
-	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 prometheus metrics for %s: %w", req.URL, err)
-	}
-	if r.Status == statusError {
-		return nil, fmt.Errorf("response error, query: %s, errorType: %s, error: %s", req.URL, r.ErrorType, r.Error)
-	}
-	if r.Status != statusSuccess {
-		return nil, fmt.Errorf("unknown status: %s, Expected success or error ", r.Status)
-	}
-	if r.Data.ResultType != rtVector {
-		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
+	return req, nil
 }

app/vmalert/datasource/vm_graphite_api.go

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

app/vmalert/datasource/vm_prom_api.go

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

app/vmalert/datasource/vm_test.go

@@ -2,22 +2,31 @@ package datasource
 
 import (
 	"context"
+	"fmt"
 	"net/http"
 	"net/http/httptest"
+	"reflect"
 	"strconv"
+	"strings"
 	"testing"
 	"time"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promauth"
 )
 
 var (
 	ctx           = context.Background()
 	basicAuthName = "foo"
 	basicAuthPass = "bar"
-	query         = "vm_rows"
-	queryRender   = "constantLine(10)"
+	baCfg         = &promauth.BasicAuthConfig{
+		Username: basicAuthName,
+		Password: basicAuthPass,
+	}
+	query       = "vm_rows"
+	queryRender = "constantLine(10)"
 )
 
-func TestVMSelectQuery(t *testing.T) {
+func TestVMInstantQuery(t *testing.T) {
 	mux := http.NewServeMux()
 	mux.HandleFunc("/", func(_ http.ResponseWriter, _ *http.Request) {
 		t.Errorf("should not be called")
@@ -63,32 +72,141 @@ func TestVMSelectQuery(t *testing.T) {
 		case 5:
 			w.Write([]byte(`{"status":"success","data":{"resultType":"matrix"}}`))
 		case 6:
-			w.Write([]byte(`{"status":"success","data":{"resultType":"vector","result":[{"metric":{"__name__":"vm_rows"},"value":[1583786142,"13763"]}]}}`))
+			w.Write([]byte(`{"status":"success","data":{"resultType":"vector","result":[{"metric":{"__name__":"vm_rows"},"value":[1583786142,"13763"]},{"metric":{"__name__":"vm_requests"},"value":[1583786140,"2000"]}]}}`))
 		}
 	})
 
 	srv := httptest.NewServer(mux)
 	defer srv.Close()
-	am := NewVMStorage(srv.URL, basicAuthName, basicAuthPass, time.Minute, 0, srv.Client())
-	if _, err := am.Query(ctx, query, NewPrometheusType()); err == nil {
+
+	authCfg, err := promauth.NewConfig(".", nil, baCfg, "", "", nil, nil)
+	if err != nil {
+		t.Fatalf("unexpected: %s", err)
+	}
+	s := NewVMStorage(srv.URL, authCfg, time.Minute, 0, false, srv.Client())
+
+	p := NewPrometheusType()
+	pq := s.BuildWithParams(QuerierParams{DataSourceType: &p, EvaluationInterval: 15 * time.Second})
+
+	if _, err := pq.Query(ctx, query); err == nil {
 		t.Fatalf("expected connection error got nil")
 	}
-	if _, err := am.Query(ctx, query, NewPrometheusType()); err == nil {
+	if _, err := pq.Query(ctx, query); err == nil {
 		t.Fatalf("expected invalid response status error got nil")
 	}
-	if _, err := am.Query(ctx, query, NewPrometheusType()); err == nil {
+	if _, err := pq.Query(ctx, query); err == nil {
 		t.Fatalf("expected response body error got nil")
 	}
-	if _, err := am.Query(ctx, query, NewPrometheusType()); err == nil {
+	if _, err := pq.Query(ctx, query); err == nil {
 		t.Fatalf("expected error status got nil")
 	}
-	if _, err := am.Query(ctx, query, NewPrometheusType()); err == nil {
+	if _, err := pq.Query(ctx, query); err == nil {
 		t.Fatalf("expected unknown status got nil")
 	}
-	if _, err := am.Query(ctx, query, NewPrometheusType()); err == nil {
+	if _, err := pq.Query(ctx, query); err == nil {
 		t.Fatalf("expected non-vector resultType error  got nil")
 	}
-	m, err := am.Query(ctx, query, NewPrometheusType())
+	m, err := pq.Query(ctx, query)
+	if err != nil {
+		t.Fatalf("unexpected %s", err)
+	}
+	if len(m) != 2 {
+		t.Fatalf("expected 2 metrics got %d in %+v", len(m), m)
+	}
+	expected := []Metric{
+		{
+			Labels:     []Label{{Value: "vm_rows", Name: "__name__"}},
+			Timestamps: []int64{1583786142},
+			Values:     []float64{13763},
+		},
+		{
+			Labels:     []Label{{Value: "vm_requests", Name: "__name__"}},
+			Timestamps: []int64{1583786140},
+			Values:     []float64{2000},
+		},
+	}
+	if !reflect.DeepEqual(m, expected) {
+		t.Fatalf("unexpected metric %+v want %+v", m, expected)
+	}
+
+	g := NewGraphiteType()
+	gq := s.BuildWithParams(QuerierParams{DataSourceType: &g})
+
+	m, err = gq.Query(ctx, queryRender)
+	if err != nil {
+		t.Fatalf("unexpected %s", err)
+	}
+	if len(m) != 1 {
+		t.Fatalf("expected 1 metric  got %d in %+v", len(m), m)
+	}
+	exp := Metric{
+		Labels:     []Label{{Value: "constantLine(10)", Name: "name"}},
+		Timestamps: []int64{1611758403},
+		Values:     []float64{10},
+	}
+	if !reflect.DeepEqual(m[0], exp) {
+		t.Fatalf("unexpected metric %+v want %+v", m[0], expected)
+	}
+}
+
+func TestVMRangeQuery(t *testing.T) {
+	mux := http.NewServeMux()
+	mux.HandleFunc("/", func(_ http.ResponseWriter, _ *http.Request) {
+		t.Errorf("should not be called")
+	})
+	c := -1
+	mux.HandleFunc("/api/v1/query_range", func(w http.ResponseWriter, r *http.Request) {
+		c++
+		if r.Method != http.MethodPost {
+			t.Errorf("expected POST method got %s", r.Method)
+		}
+		if name, pass, _ := r.BasicAuth(); name != basicAuthName || pass != basicAuthPass {
+			t.Errorf("expected %s:%s as basic auth got %s:%s", basicAuthName, basicAuthPass, name, pass)
+		}
+		if r.URL.Query().Get("query") != query {
+			t.Errorf("expected %s in query param, got %s", query, r.URL.Query().Get("query"))
+		}
+		startTS := r.URL.Query().Get("start")
+		if startTS == "" {
+			t.Errorf("expected 'start' in query param, got nil instead")
+		}
+		if _, err := strconv.ParseInt(startTS, 10, 64); err != nil {
+			t.Errorf("failed to parse 'start' query param: %s", err)
+		}
+		endTS := r.URL.Query().Get("end")
+		if endTS == "" {
+			t.Errorf("expected 'end' in query param, got nil instead")
+		}
+		if _, err := strconv.ParseInt(endTS, 10, 64); err != nil {
+			t.Errorf("failed to parse 'end' query param: %s", err)
+		}
+		switch c {
+		case 0:
+			w.Write([]byte(`{"status":"success","data":{"resultType":"matrix","result":[{"metric":{"__name__":"vm_rows"},"values":[[1583786142,"13763"]]}]}}`))
+		}
+	})
+
+	srv := httptest.NewServer(mux)
+	defer srv.Close()
+
+	authCfg, err := promauth.NewConfig(".", nil, baCfg, "", "", nil, nil)
+	if err != nil {
+		t.Fatalf("unexpected: %s", err)
+	}
+	s := NewVMStorage(srv.URL, authCfg, time.Minute, 0, false, srv.Client())
+
+	p := NewPrometheusType()
+	pq := s.BuildWithParams(QuerierParams{DataSourceType: &p, EvaluationInterval: 15 * time.Second})
+
+	_, err = pq.QueryRange(ctx, query, time.Now(), time.Time{})
+	expectError(t, err, "is missing")
+
+	_, err = pq.QueryRange(ctx, query, time.Time{}, time.Now())
+	expectError(t, err, "is missing")
+
+	start, end := time.Now().Add(-time.Minute), time.Now()
+
+	m, err := pq.QueryRange(ctx, query, start, end)
 	if err != nil {
 		t.Fatalf("unexpected %s", err)
 	}
@@ -96,32 +214,275 @@ func TestVMSelectQuery(t *testing.T) {
 		t.Fatalf("expected 1 metric  got %d in %+v", len(m), m)
 	}
 	expected := Metric{
-		Labels:    []Label{{Value: "vm_rows", Name: "__name__"}},
-		Timestamp: 1583786142,
-		Value:     13763,
+		Labels:     []Label{{Value: "vm_rows", Name: "__name__"}},
+		Timestamps: []int64{1583786142},
+		Values:     []float64{13763},
 	}
-	if m[0].Timestamp != expected.Timestamp &&
-		m[0].Value != expected.Value &&
-		m[0].Labels[0].Value != expected.Labels[0].Value &&
-		m[0].Labels[0].Name != expected.Labels[0].Name {
+	if !reflect.DeepEqual(m[0], expected) {
 		t.Fatalf("unexpected metric %+v want %+v", m[0], expected)
 	}
-	m, err = am.Query(ctx, queryRender, NewGraphiteType())
+
+	g := NewGraphiteType()
+	gq := s.BuildWithParams(QuerierParams{DataSourceType: &g})
+
+	_, err = gq.QueryRange(ctx, queryRender, start, end)
+	expectError(t, err, "is not supported")
+}
+
+func TestRequestParams(t *testing.T) {
+	authCfg, err := promauth.NewConfig(".", nil, baCfg, "", "", nil, nil)
 	if err != nil {
-		t.Fatalf("unexpected %s", err)
+		t.Fatalf("unexpected: %s", err)
 	}
-	if len(m) != 1 {
-		t.Fatalf("expected 1 metric  got %d in %+v", len(m), m)
+	query := "up"
+	timestamp := time.Date(2001, 2, 3, 4, 5, 6, 0, time.UTC)
+	testCases := []struct {
+		name       string
+		queryRange bool
+		vm         *VMStorage
+		checkFn    func(t *testing.T, r *http.Request)
+	}{
+		{
+			"prometheus path",
+			false,
+			&VMStorage{
+				dataSourceType: NewPrometheusType(),
+			},
+			func(t *testing.T, r *http.Request) {
+				checkEqualString(t, prometheusInstantPath, r.URL.Path)
+			},
+		},
+		{
+			"prometheus prefix",
+			false,
+			&VMStorage{
+				dataSourceType:   NewPrometheusType(),
+				appendTypePrefix: true,
+			},
+			func(t *testing.T, r *http.Request) {
+				checkEqualString(t, prometheusPrefix+prometheusInstantPath, r.URL.Path)
+			},
+		},
+		{
+			"prometheus range path",
+			true,
+			&VMStorage{
+				dataSourceType: NewPrometheusType(),
+			},
+			func(t *testing.T, r *http.Request) {
+				checkEqualString(t, prometheusRangePath, r.URL.Path)
+			},
+		},
+		{
+			"prometheus range prefix",
+			true,
+			&VMStorage{
+				dataSourceType:   NewPrometheusType(),
+				appendTypePrefix: true,
+			},
+			func(t *testing.T, r *http.Request) {
+				checkEqualString(t, prometheusPrefix+prometheusRangePath, r.URL.Path)
+			},
+		},
+		{
+			"graphite path",
+			false,
+			&VMStorage{
+				dataSourceType: NewGraphiteType(),
+			},
+			func(t *testing.T, r *http.Request) {
+				checkEqualString(t, graphitePath, r.URL.Path)
+			},
+		},
+		{
+			"graphite prefix",
+			false,
+			&VMStorage{
+				dataSourceType:   NewGraphiteType(),
+				appendTypePrefix: true,
+			},
+			func(t *testing.T, r *http.Request) {
+				checkEqualString(t, graphitePrefix+graphitePath, r.URL.Path)
+			},
+		},
+		{
+			"default params",
+			false,
+			&VMStorage{},
+			func(t *testing.T, r *http.Request) {
+				exp := fmt.Sprintf("query=%s&time=%d", query, timestamp.Unix())
+				checkEqualString(t, exp, r.URL.RawQuery)
+			},
+		},
+		{
+			"default range params",
+			true,
+			&VMStorage{},
+			func(t *testing.T, r *http.Request) {
+				exp := fmt.Sprintf("end=%d&query=%s&start=%d", timestamp.Unix(), query, timestamp.Unix())
+				checkEqualString(t, exp, r.URL.RawQuery)
+			},
+		},
+		{
+			"basic auth",
+			false,
+			&VMStorage{authCfg: authCfg},
+			func(t *testing.T, r *http.Request) {
+				u, p, _ := r.BasicAuth()
+				checkEqualString(t, "foo", u)
+				checkEqualString(t, "bar", p)
+			},
+		},
+		{
+			"basic auth range",
+			true,
+			&VMStorage{authCfg: authCfg},
+			func(t *testing.T, r *http.Request) {
+				u, p, _ := r.BasicAuth()
+				checkEqualString(t, "foo", u)
+				checkEqualString(t, "bar", p)
+			},
+		},
+		{
+			"lookback",
+			false,
+			&VMStorage{
+				lookBack: time.Minute,
+			},
+			func(t *testing.T, r *http.Request) {
+				exp := fmt.Sprintf("query=%s&time=%d", query, timestamp.Add(-time.Minute).Unix())
+				checkEqualString(t, exp, r.URL.RawQuery)
+			},
+		},
+		{
+			"evaluation interval",
+			false,
+			&VMStorage{
+				evaluationInterval: 15 * time.Second,
+			},
+			func(t *testing.T, r *http.Request) {
+				evalInterval := 15 * time.Second
+				tt := timestamp.Truncate(evalInterval)
+				exp := fmt.Sprintf("query=%s&step=%v&time=%d", query, evalInterval, tt.Unix())
+				checkEqualString(t, exp, r.URL.RawQuery)
+			},
+		},
+		{
+			"lookback + evaluation interval",
+			false,
+			&VMStorage{
+				lookBack:           time.Minute,
+				evaluationInterval: 15 * time.Second,
+			},
+			func(t *testing.T, r *http.Request) {
+				evalInterval := 15 * time.Second
+				tt := timestamp.Add(-time.Minute)
+				tt = tt.Truncate(evalInterval)
+				exp := fmt.Sprintf("query=%s&step=%v&time=%d", query, evalInterval, tt.Unix())
+				checkEqualString(t, exp, r.URL.RawQuery)
+			},
+		},
+		{
+			"step override",
+			false,
+			&VMStorage{
+				queryStep: time.Minute,
+			},
+			func(t *testing.T, r *http.Request) {
+				exp := fmt.Sprintf("query=%s&step=%v&time=%d", query, time.Minute, timestamp.Unix())
+				checkEqualString(t, exp, r.URL.RawQuery)
+			},
+		},
+		{
+			"round digits",
+			false,
+			&VMStorage{
+				extraParams: []Param{{"round_digits", "10"}},
+			},
+			func(t *testing.T, r *http.Request) {
+				exp := fmt.Sprintf("query=%s&round_digits=10&time=%d", query, timestamp.Unix())
+				checkEqualString(t, exp, r.URL.RawQuery)
+			},
+		},
+		{
+			"extra labels",
+			false,
+			&VMStorage{
+				extraLabels: []string{
+					"env=prod",
+					"query=es=cape",
+				},
+			},
+			func(t *testing.T, r *http.Request) {
+				exp := fmt.Sprintf("extra_label=env%%3Dprod&extra_label=query%%3Des%%3Dcape&query=%s&time=%d", query, timestamp.Unix())
+				checkEqualString(t, exp, r.URL.RawQuery)
+			},
+		},
+		{
+			"extra labels range",
+			true,
+			&VMStorage{
+				extraLabels: []string{
+					"env=prod",
+					"query=es=cape",
+				},
+			},
+			func(t *testing.T, r *http.Request) {
+				exp := fmt.Sprintf("end=%d&extra_label=env%%3Dprod&extra_label=query%%3Des%%3Dcape&query=%s&start=%d",
+					timestamp.Unix(), query, timestamp.Unix())
+				checkEqualString(t, exp, r.URL.RawQuery)
+			},
+		},
+		{
+			"extra params",
+			false,
+			&VMStorage{
+				extraParams: []Param{
+					{Key: "nocache", Value: "1"},
+					{Key: "max_lookback", Value: "1h"},
+				},
+			},
+			func(t *testing.T, r *http.Request) {
+				exp := fmt.Sprintf("max_lookback=1h&nocache=1&query=%s&time=%d", query, timestamp.Unix())
+				checkEqualString(t, exp, r.URL.RawQuery)
+			},
+		},
 	}
-	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)
+
+	for _, tc := range testCases {
+		t.Run(tc.name, func(t *testing.T) {
+			req, err := tc.vm.newRequestPOST()
+			if err != nil {
+				t.Fatalf("unexpected error: %s", err)
+			}
+			switch tc.vm.dataSourceType.name {
+			case "", prometheusType:
+				if tc.queryRange {
+					tc.vm.setPrometheusRangeReqParams(req, query, timestamp, timestamp)
+				} else {
+					tc.vm.setPrometheusInstantReqParams(req, query, timestamp)
+				}
+			case graphiteType:
+				tc.vm.setGraphiteReqParams(req, query, timestamp)
+			}
+			tc.checkFn(t, req)
+		})
+	}
+}
+
+func checkEqualString(t *testing.T, exp, got string) {
+	t.Helper()
+	if got != exp {
+		t.Errorf("expected to get %q; got %q", exp, got)
+	}
+}
+
+func expectError(t *testing.T, err error, exp string) {
+	t.Helper()
+	if err == nil {
+		t.Errorf("expected non-nil error")
+	}
+	if !strings.Contains(err.Error(), exp) {
+		t.Errorf("expected error %q to contain %q", err, exp)
 	}
 }

app/vmalert/group.go

@@ -27,6 +27,9 @@ type Group struct {
 	Concurrency int
 	Checksum    string
 
+	ExtraFilterLabels map[string]string
+	Labels            map[string]string
+
 	doneCh     chan struct{}
 	finishedCh chan struct{}
 	// channel accepts new Group obj
@@ -49,17 +52,37 @@ func newGroupMetrics(name, file string) *groupMetrics {
 	return m
 }
 
-func newGroup(cfg config.Group, defaultInterval time.Duration, labels map[string]string) *Group {
+// merges group rule labels into result map
+// set2 has priority over set1.
+func mergeLabels(groupName, ruleName string, set1, set2 map[string]string) map[string]string {
+	r := map[string]string{}
+	for k, v := range set1 {
+		r[k] = v
+	}
+	for k, v := range set2 {
+		if prevV, ok := r[k]; ok {
+			logger.Infof("label %q=%q for rule %q.%q overwritten with external label %q=%q",
+				k, prevV, groupName, ruleName, k, v)
+		}
+		r[k] = v
+	}
+	return r
+}
+
+func newGroup(cfg config.Group, qb datasource.QuerierBuilder, defaultInterval time.Duration, labels map[string]string) *Group {
 	g := &Group{
-		Type:        cfg.Type,
-		Name:        cfg.Name,
-		File:        cfg.File,
-		Interval:    cfg.Interval,
-		Concurrency: cfg.Concurrency,
-		Checksum:    cfg.Checksum,
-		doneCh:      make(chan struct{}),
-		finishedCh:  make(chan struct{}),
-		updateCh:    make(chan *Group),
+		Type:              cfg.Type,
+		Name:              cfg.Name,
+		File:              cfg.File,
+		Interval:          cfg.Interval.Duration(),
+		Concurrency:       cfg.Concurrency,
+		Checksum:          cfg.Checksum,
+		ExtraFilterLabels: cfg.ExtraFilterLabels,
+		Labels:            cfg.Labels,
+
+		doneCh:     make(chan struct{}),
+		finishedCh: make(chan struct{}),
+		updateCh:   make(chan *Group),
 	}
 	g.metrics = newGroupMetrics(g.Name, g.File)
 	if g.Interval == 0 {
@@ -70,28 +93,31 @@ func newGroup(cfg config.Group, defaultInterval time.Duration, labels map[string
 	}
 	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
+		var extraLabels map[string]string
+		// apply external labels
+		if len(labels) > 0 {
+			extraLabels = labels
 		}
-		rules[i] = g.newRule(r)
+		// apply group labels, it has priority on external labels
+		if len(cfg.Labels) > 0 {
+			extraLabels = mergeLabels(g.Name, r.Name(), extraLabels, g.Labels)
+		}
+		// apply rules labels, it has priority on other labels
+		if len(extraLabels) > 0 {
+			r.Labels = mergeLabels(g.Name, r.Name(), extraLabels, r.Labels)
+		}
+
+		rules[i] = g.newRule(qb, r)
 	}
 	g.Rules = rules
 	return g
 }
 
-func (g *Group) newRule(rule config.Rule) Rule {
+func (g *Group) newRule(qb datasource.QuerierBuilder, rule config.Rule) Rule {
 	if rule.Alert != "" {
-		return newAlertingRule(g, rule)
+		return newAlertingRule(qb, g, rule)
 	}
-	return newRecordingRule(g, rule)
+	return newRecordingRule(qb, g, rule)
 }
 
 // ID return unique group ID that consists of
@@ -106,7 +132,8 @@ func (g *Group) ID() uint64 {
 }
 
 // Restore restores alerts state for group rules
-func (g *Group) Restore(ctx context.Context, q datasource.Querier, lookback time.Duration, labels map[string]string) error {
+func (g *Group) Restore(ctx context.Context, qb datasource.QuerierBuilder, lookback time.Duration, labels map[string]string) error {
+	labels = mergeLabels(g.Name, "", labels, g.Labels)
 	for _, rule := range g.Rules {
 		rr, ok := rule.(*AlertingRule)
 		if !ok {
@@ -115,6 +142,9 @@ func (g *Group) Restore(ctx context.Context, q datasource.Querier, lookback time
 		if rr.For < 1 {
 			continue
 		}
+		// ignore g.ExtraFilterLabels on purpose, so it
+		// won't affect the restore procedure.
+		q := qb.BuildWithParams(datasource.QuerierParams{})
 		if err := rr.Restore(ctx, q, lookback, labels); err != nil {
 			return fmt.Errorf("error while restoring rule %q: %w", rule, err)
 		}
@@ -160,19 +190,18 @@ func (g *Group) updateWith(newGroup *Group) error {
 	for _, nr := range rulesRegistry {
 		newRules = append(newRules, nr)
 	}
+	// note that g.Interval is not updated here
+	// so the value can be compared later in
+	// group.Start function
 	g.Type = newGroup.Type
 	g.Concurrency = newGroup.Concurrency
+	g.ExtraFilterLabels = newGroup.ExtraFilterLabels
+	g.Labels = newGroup.Labels
 	g.Checksum = newGroup.Checksum
 	g.Rules = newRules
 	return nil
 }
 
-var (
-	alertsFired      = metrics.NewCounter(`vmalert_alerts_fired_total`)
-	alertsSent       = metrics.NewCounter(`vmalert_alerts_sent_total`)
-	alertsSendErrors = metrics.NewCounter(`vmalert_alerts_send_errors_total`)
-)
-
 func (g *Group) close() {
 	if g.doneCh == nil {
 		return
@@ -189,7 +218,7 @@ func (g *Group) close() {
 
 var skipRandSleepOnGroupStart bool
 
-func (g *Group) start(ctx context.Context, querier datasource.Querier, nts []notifier.Notifier, rw *remotewrite.Client) {
+func (g *Group) start(ctx context.Context, nts []notifier.Notifier, rw *remotewrite.Client) {
 	defer func() { close(g.finishedCh) }()
 
 	// Spread group rules evaluation over time in order to reduce load on VictoriaMetrics.
@@ -213,7 +242,16 @@ func (g *Group) start(ctx context.Context, querier datasource.Querier, nts []not
 	}
 
 	logger.Infof("group %q started; interval=%v; concurrency=%d", g.Name, g.Interval, g.Concurrency)
-	e := &executor{querier, nts, rw}
+	e := &executor{rw: rw}
+	for _, nt := range nts {
+		ent := eNotifier{
+			Notifier:         nt,
+			alertsSent:       getOrCreateCounter(fmt.Sprintf("vmalert_alerts_sent_total{addr=%q}", nt.Addr())),
+			alertsSendErrors: getOrCreateCounter(fmt.Sprintf("vmalert_alerts_send_errors_total{addr=%q}", nt.Addr())),
+		}
+		e.notifiers = append(e.notifiers, ent)
+	}
+
 	t := time.NewTicker(g.Interval)
 	defer t.Stop()
 	for {
@@ -242,8 +280,8 @@ func (g *Group) start(ctx context.Context, querier datasource.Querier, nts []not
 		case <-t.C:
 			g.metrics.iterationTotal.Inc()
 			iterationStart := time.Now()
-
-			errs := e.execConcurrently(ctx, g.Rules, g.Concurrency, g.Interval)
+			resolveDuration := getResolveDuration(g.Interval)
+			errs := e.execConcurrently(ctx, g.Rules, g.Concurrency, resolveDuration)
 			for err := range errs {
 				if err != nil {
 					logger.Errorf("group %q: %s", g.Name, err)
@@ -255,23 +293,34 @@ func (g *Group) start(ctx context.Context, querier datasource.Querier, nts []not
 	}
 }
 
+// resolveDuration for alerts is equal to 3 interval evaluations
+// so in case if vmalert stops sending updates for some reason,
+// notifier could automatically resolve the alert.
+func getResolveDuration(groupInterval time.Duration) time.Duration {
+	resolveInterval := groupInterval * 3
+	if *maxResolveDuration > 0 && (resolveInterval > *maxResolveDuration) {
+		return *maxResolveDuration
+	}
+	return resolveInterval
+}
+
 type executor struct {
-	querier   datasource.Querier
-	notifiers []notifier.Notifier
+	notifiers []eNotifier
 	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
-	}
+type eNotifier struct {
+	notifier.Notifier
+	alertsSent       *counter
+	alertsSendErrors *counter
+}
 
+func (e *executor) execConcurrently(ctx context.Context, rules []Rule, concurrency int, resolveDuration time.Duration) chan error {
+	res := make(chan error, len(rules))
 	if concurrency == 1 {
 		// fast path
 		for _, rule := range rules {
-			res <- e.exec(ctx, rule, returnSeries, interval)
+			res <- e.exec(ctx, rule, resolveDuration)
 		}
 		close(res)
 		return res
@@ -284,7 +333,7 @@ func (e *executor) execConcurrently(ctx context.Context, rules []Rule, concurren
 			sem <- struct{}{}
 			wg.Add(1)
 			go func(r Rule) {
-				res <- e.exec(ctx, r, returnSeries, interval)
+				res <- e.exec(ctx, r, resolveDuration)
 				<-sem
 				wg.Done()
 			}(rule)
@@ -296,21 +345,18 @@ func (e *executor) execConcurrently(ctx context.Context, rules []Rule, concurren
 }
 
 var (
-	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`)
+
+	execTotal  = metrics.NewCounter(`vmalert_execution_total`)
+	execErrors = metrics.NewCounter(`vmalert_execution_errors_total`)
 
 	remoteWriteErrors = metrics.NewCounter(`vmalert_remotewrite_errors_total`)
 )
 
-func (e *executor) exec(ctx context.Context, rule Rule, returnSeries bool, interval time.Duration) error {
+func (e *executor) exec(ctx context.Context, rule Rule, resolveDuration time.Duration) error {
 	execTotal.Inc()
-	execStart := time.Now()
-	defer func() {
-		execDuration.UpdateDuration(execStart)
-	}()
 
-	tss, err := rule.Exec(ctx, e.querier, returnSeries)
+	tss, err := rule.Exec(ctx)
 	if err != nil {
 		execErrors.Inc()
 		return fmt.Errorf("rule %q: failed to execute: %w", rule, err)
@@ -333,10 +379,7 @@ func (e *executor) exec(ctx context.Context, rule Rule, returnSeries bool, inter
 	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)
+			a.End = time.Now().Add(resolveDuration)
 			alerts = append(alerts, *a)
 		case notifier.StateInactive:
 			// set End to execStart to notify
@@ -349,11 +392,11 @@ func (e *executor) exec(ctx context.Context, rule Rule, returnSeries bool, inter
 		return nil
 	}
 
-	alertsSent.Add(len(alerts))
 	errGr := new(utils.ErrGroup)
 	for _, nt := range e.notifiers {
+		nt.alertsSent.Add(len(alerts))
 		if err := nt.Send(ctx, alerts); err != nil {
-			alertsSendErrors.Inc()
+			nt.alertsSendErrors.Inc()
 			errGr.Add(fmt.Errorf("rule %q: failed to send alerts: %w", rule, err))
 		}
 	}

app/vmalert/group_test.go

@@ -2,12 +2,15 @@ package main
 
 import (
 	"context"
+	"fmt"
 	"sort"
 	"testing"
 	"time"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/config"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/utils"
 )
 
 func init() {
@@ -32,7 +35,7 @@ func TestUpdateWith(t *testing.T) {
 			[]config.Rule{{
 				Alert: "foo",
 				Expr:  "up > 0",
-				For:   config.NewPromDuration(time.Second),
+				For:   utils.NewPromDuration(time.Second),
 				Labels: map[string]string{
 					"bar": "baz",
 				},
@@ -44,7 +47,7 @@ func TestUpdateWith(t *testing.T) {
 			[]config.Rule{{
 				Alert: "foo",
 				Expr:  "up > 10",
-				For:   config.NewPromDuration(time.Second),
+				For:   utils.NewPromDuration(time.Second),
 				Labels: map[string]string{
 					"baz": "bar",
 				},
@@ -105,20 +108,32 @@ func TestUpdateWith(t *testing.T) {
 				{Record: "foo5"},
 			},
 		},
+		{
+			"update datasource type",
+			[]config.Rule{
+				{Alert: "foo1", Type: datasource.NewPrometheusType()},
+				{Alert: "foo3", Type: datasource.NewGraphiteType()},
+			},
+			[]config.Rule{
+				{Alert: "foo1", Type: datasource.NewGraphiteType()},
+				{Alert: "foo10", Type: datasource.NewPrometheusType()},
+			},
+		},
 	}
 
 	for _, tc := range testCases {
 		t.Run(tc.name, func(t *testing.T) {
 			g := &Group{Name: "test"}
+			qb := &fakeQuerier{}
 			for _, r := range tc.currentRules {
 				r.ID = config.HashRule(r)
-				g.Rules = append(g.Rules, g.newRule(r))
+				g.Rules = append(g.Rules, g.newRule(qb, r))
 			}
 
 			ng := &Group{Name: "test"}
 			for _, r := range tc.newRules {
 				r.ID = config.HashRule(r)
-				ng.Rules = append(ng.Rules, ng.newRule(r))
+				ng.Rules = append(ng.Rules, ng.newRule(qb, r))
 			}
 
 			err := g.updateWith(ng)
@@ -156,11 +171,11 @@ func TestGroupStart(t *testing.T) {
 		t.Fatalf("failed to parse rules: %s", err)
 	}
 	const evalInterval = time.Millisecond
-	g := newGroup(groups[0], evalInterval, map[string]string{"cluster": "east-1"})
-	g.Concurrency = 2
-
-	fn := &fakeNotifier{}
 	fs := &fakeQuerier{}
+	fn := &fakeNotifier{}
+
+	g := newGroup(groups[0], fs, evalInterval, map[string]string{"cluster": "east-1"})
+	g.Concurrency = 2
 
 	const inst1, inst2, job = "foo", "bar", "baz"
 	m1 := metricWithLabels(t, "instance", inst1, "job", job)
@@ -195,7 +210,7 @@ func TestGroupStart(t *testing.T) {
 	fs.add(m1)
 	fs.add(m2)
 	go func() {
-		g.start(context.Background(), fs, []notifier.Notifier{fn}, nil)
+		g.start(context.Background(), []notifier.Notifier{fn}, nil)
 		close(finished)
 	}()
 
@@ -221,3 +236,27 @@ func TestGroupStart(t *testing.T) {
 	g.close()
 	<-finished
 }
+
+func TestResolveDuration(t *testing.T) {
+	testCases := []struct {
+		groupInterval time.Duration
+		maxDuration   time.Duration
+		expected      time.Duration
+	}{
+		{time.Minute, 0, 3 * time.Minute},
+		{3 * time.Minute, 0, 9 * time.Minute},
+		{time.Minute, 2 * time.Minute, 2 * time.Minute},
+		{0, 0, 0},
+	}
+	defaultResolveDuration := *maxResolveDuration
+	defer func() { *maxResolveDuration = defaultResolveDuration }()
+	for _, tc := range testCases {
+		t.Run(fmt.Sprintf("%v-%v-%v", tc.groupInterval, tc.expected, tc.maxDuration), func(t *testing.T) {
+			*maxResolveDuration = tc.maxDuration
+			got := getResolveDuration(tc.groupInterval)
+			if got != tc.expected {
+				t.Errorf("expected to have %v; got %v", tc.expected, got)
+			}
+		})
+	}
+}

app/vmalert/helpers_test.go

@@ -7,6 +7,7 @@ import (
 	"sort"
 	"sync"
 	"testing"
+	"time"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
@@ -38,7 +39,15 @@ func (fq *fakeQuerier) add(metrics ...datasource.Metric) {
 	fq.Unlock()
 }
 
-func (fq *fakeQuerier) Query(_ context.Context, _ string, _ datasource.Type) ([]datasource.Metric, error) {
+func (fq *fakeQuerier) BuildWithParams(_ datasource.QuerierParams) datasource.Querier {
+	return fq
+}
+
+func (fq *fakeQuerier) QueryRange(ctx context.Context, q string, _, _ time.Time) ([]datasource.Metric, error) {
+	return fq.Query(ctx, q)
+}
+
+func (fq *fakeQuerier) Query(_ context.Context, _ string) ([]datasource.Metric, error) {
 	fq.Lock()
 	defer fq.Unlock()
 	if fq.err != nil {
@@ -54,6 +63,7 @@ type fakeNotifier struct {
 	alerts []notifier.Alert
 }
 
+func (*fakeNotifier) Addr() string { return "" }
 func (fn *fakeNotifier) Send(_ context.Context, alerts []notifier.Alert) error {
 	fn.Lock()
 	defer fn.Unlock()
@@ -68,9 +78,16 @@ func (fn *fakeNotifier) getAlerts() []notifier.Alert {
 }
 
 func metricWithValueAndLabels(t *testing.T, value float64, labels ...string) datasource.Metric {
+	return metricWithValuesAndLabels(t, []float64{value}, labels...)
+}
+
+func metricWithValuesAndLabels(t *testing.T, values []float64, labels ...string) datasource.Metric {
 	t.Helper()
 	m := metricWithLabels(t, labels...)
-	m.Value = value
+	m.Values = values
+	for i := range values {
+		m.Timestamps = append(m.Timestamps, int64(i))
+	}
 	return m
 }
 
@@ -79,7 +96,7 @@ func metricWithLabels(t *testing.T, labels ...string) datasource.Metric {
 	if len(labels) == 0 || len(labels)%2 != 0 {
 		t.Fatalf("expected to get even number of labels")
 	}
-	m := datasource.Metric{}
+	m := datasource.Metric{Values: []float64{1}, Timestamps: []int64{1}}
 	for i := 0; i < len(labels); i += 2 {
 		m.Labels = append(m.Labels, datasource.Label{
 			Name:  labels[i],
@@ -160,6 +177,9 @@ func compareAlertingRules(t *testing.T, a, b *AlertingRule) error {
 	if !reflect.DeepEqual(a.Labels, b.Labels) {
 		return fmt.Errorf("expected to have labels %#v; got %#v", a.Labels, b.Labels)
 	}
+	if a.Type.String() != b.Type.String() {
+		return fmt.Errorf("expected to have Type %#v; got %#v", a.Type.String(), b.Type.String())
+	}
 	return nil
 }
 

app/vmalert/main.go

@@ -26,27 +26,35 @@ import (
 )
 
 var (
-	rulePath = flagutil.NewArray("rule", `Path to the file with alert rules. 
-Supports patterns. Flag can be specified multiple times. 
+	rulePath = flagutil.NewArray("rule", `Path to the file with alert rules.
+Supports patterns. Flag can be specified multiple times.
 Examples:
  -rule="/path/to/file". Path to a single file with alerting rules
- -rule="dir/*.yaml" -rule="/*.yaml". Relative path to all .yaml files in "dir" folder, 
+ -rule="dir/*.yaml" -rule="/*.yaml". Relative path to all .yaml files in "dir" folder,
 absolute path to all .yaml files in root.
 Rule files may contain %{ENV_VAR} placeholders, which are substituted by the corresponding env vars.`)
 
+	rulesCheckInterval = flag.Duration("rule.configCheckInterval", 0, "Interval for checking for changes in '-rule' files. "+
+		"By default the checking is disabled. Send SIGHUP signal in order to force config check for changes")
+
 	httpListenAddr     = flag.String("httpListenAddr", ":8880", "Address to listen for http connections")
 	evaluationInterval = flag.Duration("evaluationInterval", time.Minute, "How often to evaluate the rules")
 
 	validateTemplates   = flag.Bool("rule.validateTemplates", true, "Whether to validate annotation and label templates")
 	validateExpressions = flag.Bool("rule.validateExpressions", true, "Whether to validate rules expressions via MetricsQL engine")
+	maxResolveDuration  = flag.Duration("rule.maxResolveDuration", 0, "Limits the maximum duration for automatic alert expiration, "+
+		"which is by default equal to 3 evaluation intervals of the parent group.")
 	externalURL         = flag.String("external.url", "", "External URL is used as alert's source for sent alerts to the notifier")
 	externalAlertSource = flag.String("external.alert.source", "", `External Alert Source allows to override the Source link for alerts sent to AlertManager for cases where you want to build a custom link to Grafana, Prometheus or any other service.
-eg. 'explore?orgId=1&left=[\"now-1h\",\"now\",\"VictoriaMetrics\",{\"expr\": \"{{$expr|quotesEscape|crlfEscape|pathEscape}}\"},{\"mode\":\"Metrics\"},{\"ui\":[true,true,true,\"none\"]}]'.If empty '/api/v1/:groupID/alertID/status' is used`)
+eg. 'explore?orgId=1&left=[\"now-1h\",\"now\",\"VictoriaMetrics\",{\"expr\": \"{{$expr|quotesEscape|crlfEscape|queryEscape}}\"},{\"mode\":\"Metrics\"},{\"ui\":[true,true,true,\"none\"]}]'.If empty '/api/v1/:groupID/alertID/status' is used`)
 	externalLabels = flagutil.NewArray("external.label", "Optional label in the form 'name=value' to add to all generated recording rules and alerts. "+
 		"Pass multiple -label flags in order to add multiple label sets.")
 
 	remoteReadLookBack = flag.Duration("remoteRead.lookback", time.Hour, "Lookback defines how far to look into past for alerts timeseries."+
 		" For example, if lookback=1h then range from now() to now()-1h will be scanned.")
+	remoteReadIgnoreRestoreErrors = flag.Bool("remoteRead.ignoreRestoreErrors", true, "Whether to ignore errors from remote storage when restoring alerts state on startup.")
+
+	disableAlertGroupLabel = flag.Bool("disableAlertgroupLabel", false, "Whether to disable adding group's name as label to generated alerts and time series.")
 
 	dryRun = flag.Bool("dryRun", false, "Whether to check only config files without running vmalert. The rules file are validated. The `-rule` flag must be specified.")
 )
@@ -64,42 +72,57 @@ func main() {
 		notifier.InitTemplateFunc(u)
 		groups, err := config.Parse(*rulePath, true, true)
 		if err != nil {
-			logger.Fatalf(err.Error())
+			logger.Fatalf("failed to parse %q: %s", *rulePath, err)
 		}
 		if len(groups) == 0 {
 			logger.Fatalf("No rules for validation. Please specify path to file(s) with alerting and/or recording rules using `-rule` flag")
 		}
 		return
 	}
+	if *replayFrom != "" || *replayTo != "" {
+		rw, err := remotewrite.Init(context.Background())
+		if err != nil {
+			logger.Fatalf("failed to init remoteWrite: %s", err)
+		}
+		eu, err := getExternalURL(*externalURL, *httpListenAddr, httpserver.IsTLS())
+		if err != nil {
+			logger.Fatalf("failed to init `external.url`: %s", err)
+		}
+		notifier.InitTemplateFunc(eu)
+		groupsCfg, err := config.Parse(*rulePath, *validateTemplates, *validateExpressions)
+		if err != nil {
+			logger.Fatalf("cannot parse configuration file: %s", err)
+		}
+		// prevent queries from caching and boundaries aligning
+		// when querying VictoriaMetrics datasource.
+		noCache := datasource.Param{Key: "nocache", Value: "1"}
+		q, err := datasource.Init([]datasource.Param{noCache})
+		if err != nil {
+			logger.Fatalf("failed to init datasource: %s", err)
+		}
+		if err := replay(groupsCfg, q, rw); err != nil {
+			logger.Fatalf("replay failed: %s", err)
+		}
+		return
+	}
+
 	ctx, cancel := context.WithCancel(context.Background())
 	manager, err := newManager(ctx)
 	if err != nil {
 		logger.Fatalf("failed to init: %s", err)
 	}
-	if err := manager.start(ctx, *rulePath, *validateTemplates, *validateExpressions); err != nil {
+
+	logger.Infof("reading rules configuration file from %q", strings.Join(*rulePath, ";"))
+	groupsCfg, err := config.Parse(*rulePath, *validateTemplates, *validateExpressions)
+	if err != nil {
+		logger.Fatalf("cannot parse configuration file: %s", err)
+	}
+
+	if err := manager.start(ctx, groupsCfg); err != nil {
 		logger.Fatalf("failed to start: %s", err)
 	}
 
-	go func() {
-		// init reload metrics with positive values to improve alerting conditions
-		configSuccess.Set(1)
-		configTimestamp.Set(fasttime.UnixTimestamp())
-		sigHup := procutil.NewSighupChan()
-		for {
-			<-sigHup
-			configReloads.Inc()
-			logger.Infof("SIGHUP received. Going to reload rules %q ...", *rulePath)
-			if err := manager.update(ctx, *rulePath, *validateTemplates, *validateExpressions, false); err != nil {
-				configReloadErrors.Inc()
-				configSuccess.Set(0)
-				logger.Errorf("error while reloading rules: %s", err)
-				continue
-			}
-			configSuccess.Set(1)
-			configTimestamp.Set(fasttime.UnixTimestamp())
-			logger.Infof("Rules reloaded successfully from %q", *rulePath)
-		}
-	}()
+	go configReload(ctx, manager, groupsCfg)
 
 	rh := &requestHandler{m: manager}
 	go httpserver.Serve(*httpListenAddr, rh.handler)
@@ -121,7 +144,7 @@ var (
 )
 
 func newManager(ctx context.Context) (*manager, error) {
-	q, err := datasource.Init()
+	q, err := datasource.Init(nil)
 	if err != nil {
 		return nil, fmt.Errorf("failed to init datasource: %w", err)
 	}
@@ -140,10 +163,10 @@ func newManager(ctx context.Context) (*manager, error) {
 	}
 
 	manager := &manager{
-		groups:    make(map[uint64]*Group),
-		querier:   q,
-		notifiers: nts,
-		labels:    map[string]string{},
+		groups:         make(map[uint64]*Group),
+		querierBuilder: q,
+		notifiers:      nts,
+		labels:         map[string]string{},
 	}
 	rw, err := remotewrite.Init(ctx)
 	if err != nil {
@@ -218,7 +241,71 @@ func usage() {
 	const s = `
 vmalert processes alerts and recording rules.
 
-See the docs at https://victoriametrics.github.io/vmalert.html .
+See the docs at https://docs.victoriametrics.com/vmalert.html .
 `
 	flagutil.Usage(s)
 }
+
+func configReload(ctx context.Context, m *manager, groupsCfg []config.Group) {
+	// Register SIGHUP handler for config re-read just before manager.start call.
+	// This guarantees that the config will be re-read if the signal arrives during manager.start call.
+	// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1240
+	sighupCh := procutil.NewSighupChan()
+
+	var configCheckCh <-chan time.Time
+	if *rulesCheckInterval > 0 {
+		ticker := time.NewTicker(*rulesCheckInterval)
+		configCheckCh = ticker.C
+		defer ticker.Stop()
+	}
+
+	// init reload metrics with positive values to improve alerting conditions
+	configSuccess.Set(1)
+	configTimestamp.Set(fasttime.UnixTimestamp())
+	for {
+		select {
+		case <-ctx.Done():
+			return
+		case <-sighupCh:
+			logger.Infof("SIGHUP received. Going to reload rules %q ...", *rulePath)
+			configReloads.Inc()
+		case <-configCheckCh:
+		}
+		newGroupsCfg, err := config.Parse(*rulePath, *validateTemplates, *validateExpressions)
+		if err != nil {
+			configReloadErrors.Inc()
+			configSuccess.Set(0)
+			logger.Errorf("cannot parse configuration file: %s", err)
+			continue
+		}
+		if configsEqual(newGroupsCfg, groupsCfg) {
+			// set success to 1 since previous reload
+			// could have been unsuccessful
+			configSuccess.Set(1)
+			// config didn't change - skip it
+			continue
+		}
+		groupsCfg = newGroupsCfg
+		if err := m.update(ctx, groupsCfg, false); err != nil {
+			configReloadErrors.Inc()
+			configSuccess.Set(0)
+			logger.Errorf("error while reloading rules: %s", err)
+			continue
+		}
+		configSuccess.Set(1)
+		configTimestamp.Set(fasttime.UnixTimestamp())
+		logger.Infof("Rules reloaded successfully from %q", *rulePath)
+	}
+}
+
+func configsEqual(a, b []config.Group) bool {
+	if len(a) != len(b) {
+		return false
+	}
+	for i := range a {
+		if a[i].Checksum != b[i].Checksum {
+			return false
+		}
+	}
+	return true
+}

app/vmalert/main_test.go

@@ -1,12 +1,16 @@
 package main
 
 import (
+	"context"
 	"fmt"
+	"io/ioutil"
 	"net/url"
 	"os"
 	"testing"
+	"time"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/procutil"
 )
 
 func TestGetExternalURL(t *testing.T) {
@@ -51,3 +55,102 @@ func TestGetAlertURLGenerator(t *testing.T) {
 		t.Errorf("unexpected url want %s, got %s", exp, fn(testAlert))
 	}
 }
+
+func TestConfigReload(t *testing.T) {
+	originalRulePath := *rulePath
+	defer func() {
+		*rulePath = originalRulePath
+	}()
+
+	const (
+		rules1 = `
+groups:
+  - name: group-1
+    rules:
+      - alert: ExampleAlertAlwaysFiring
+        expr: sum by(job) (up == 1)
+      - record: handler:requests:rate5m 
+        expr: sum(rate(prometheus_http_requests_total[5m])) by (handler)
+`
+		rules2 = `
+groups:
+  - name: group-1
+    rules:
+      - alert: ExampleAlertAlwaysFiring
+        expr: sum by(job) (up == 1)
+  - name: group-2
+    rules:
+      - record: handler:requests:rate5m 
+        expr: sum(rate(prometheus_http_requests_total[5m])) by (handler)
+`
+	)
+
+	f, err := ioutil.TempFile("", "")
+	if err != nil {
+		t.Fatal(err)
+	}
+	writeToFile(t, f.Name(), rules1)
+
+	*rulesCheckInterval = 200 * time.Millisecond
+	*rulePath = []string{f.Name()}
+	ctx, cancel := context.WithCancel(context.Background())
+
+	m := &manager{
+		querierBuilder: &fakeQuerier{},
+		groups:         make(map[uint64]*Group),
+		labels:         map[string]string{},
+	}
+
+	syncCh := make(chan struct{})
+	go func() {
+		configReload(ctx, m, nil)
+		close(syncCh)
+	}()
+
+	lenLocked := func(m *manager) int {
+		m.groupsMu.RLock()
+		defer m.groupsMu.RUnlock()
+		return len(m.groups)
+	}
+
+	time.Sleep(*rulesCheckInterval * 2)
+	groupsLen := lenLocked(m)
+	if groupsLen != 1 {
+		t.Fatalf("expected to have exactly 1 group loaded; got %d", groupsLen)
+	}
+
+	writeToFile(t, f.Name(), rules2)
+	time.Sleep(*rulesCheckInterval * 2)
+	groupsLen = lenLocked(m)
+	if groupsLen != 2 {
+		fmt.Println(m.groups)
+		t.Fatalf("expected to have exactly 2 groups loaded; got %d", groupsLen)
+	}
+
+	writeToFile(t, f.Name(), rules1)
+	procutil.SelfSIGHUP()
+	time.Sleep(*rulesCheckInterval / 2)
+	groupsLen = lenLocked(m)
+	if groupsLen != 1 {
+		t.Fatalf("expected to have exactly 1 group loaded; got %d", groupsLen)
+	}
+
+	writeToFile(t, f.Name(), `corrupted`)
+	procutil.SelfSIGHUP()
+	time.Sleep(*rulesCheckInterval / 2)
+	groupsLen = lenLocked(m)
+	if groupsLen != 1 { // should remain unchanged
+		t.Fatalf("expected to have exactly 1 group loaded; got %d", groupsLen)
+	}
+
+	cancel()
+	<-syncCh
+}
+
+func writeToFile(t *testing.T, file, b string) {
+	t.Helper()
+	err := ioutil.WriteFile(file, []byte(b), 0644)
+	if err != nil {
+		t.Fatal(err)
+	}
+}

app/vmalert/manager.go

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

app/vmalert/manager_test.go

@@ -9,8 +9,8 @@ import (
 	"testing"
 	"time"
 
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/config"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
-
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
 )
 
@@ -25,9 +25,8 @@ func TestMain(m *testing.M) {
 // starting with empty rules folder
 func TestManagerEmptyRulesDir(t *testing.T) {
 	m := &manager{groups: make(map[uint64]*Group)}
-	path := []string{"foo/bar"}
-	err := m.update(context.Background(), path, true, true, false)
-	if err != nil {
+	cfg := loadCfg(t, []string{"foo/bar"}, true, true)
+	if err := m.update(context.Background(), cfg, false); err != nil {
 		t.Fatalf("expected to load succesfully with empty rules dir; got err instead: %v", err)
 	}
 }
@@ -37,9 +36,9 @@ func TestManagerEmptyRulesDir(t *testing.T) {
 // Should be executed with -race flag
 func TestManagerUpdateConcurrent(t *testing.T) {
 	m := &manager{
-		groups:    make(map[uint64]*Group),
-		querier:   &fakeQuerier{},
-		notifiers: []notifier.Notifier{&fakeNotifier{}},
+		groups:         make(map[uint64]*Group),
+		querierBuilder: &fakeQuerier{},
+		notifiers:      []notifier.Notifier{&fakeNotifier{}},
 	}
 	paths := []string{
 		"config/testdata/dir/rules0-good.rules",
@@ -50,8 +49,11 @@ func TestManagerUpdateConcurrent(t *testing.T) {
 		"config/testdata/rules1-good.rules",
 		"config/testdata/rules2-good.rules",
 	}
+	evalInterval := *evaluationInterval
+	defer func() { *evaluationInterval = evalInterval }()
 	*evaluationInterval = time.Millisecond
-	if err := m.start(context.Background(), []string{paths[0]}, true, true); err != nil {
+	cfg := loadCfg(t, []string{paths[0]}, true, true)
+	if err := m.start(context.Background(), cfg); err != nil {
 		t.Fatalf("failed to start: %s", err)
 	}
 
@@ -64,8 +66,11 @@ func TestManagerUpdateConcurrent(t *testing.T) {
 			defer wg.Done()
 			for i := 0; i < iterations; i++ {
 				rnd := rand.Intn(len(paths))
-				path := []string{paths[rnd]}
-				_ = m.update(context.Background(), path, true, true, false)
+				cfg, err := config.Parse([]string{paths[rnd]}, true, true)
+				if err != nil { // update can fail and this is expected
+					continue
+				}
+				_ = m.update(context.Background(), cfg, false)
 			}
 		}()
 	}
@@ -143,7 +148,7 @@ func TestManagerUpdate(t *testing.T) {
 							Name:   "VMRows",
 							Expr:   "vm_rows > 0",
 							For:    5 * time.Minute,
-							Labels: map[string]string{"label": "bar"},
+							Labels: map[string]string{"dc": "gcp", "label": "bar"},
 							Annotations: map[string]string{
 								"summary":     "{{ $value }}",
 								"description": "{{$labels}}",
@@ -242,14 +247,17 @@ func TestManagerUpdate(t *testing.T) {
 	for _, tc := range testCases {
 		t.Run(tc.name, func(t *testing.T) {
 			ctx, cancel := context.WithCancel(context.TODO())
-			m := &manager{groups: make(map[uint64]*Group), querier: &fakeQuerier{}}
-			path := []string{tc.initPath}
-			if err := m.update(ctx, path, true, true, false); err != nil {
+			m := &manager{groups: make(map[uint64]*Group), querierBuilder: &fakeQuerier{}}
+
+			cfgInit := loadCfg(t, []string{tc.initPath}, true, true)
+			if err := m.update(ctx, cfgInit, false); err != nil {
 				t.Fatalf("failed to complete initial rules update: %s", err)
 			}
 
-			path = []string{tc.updatePath}
-			_ = m.update(ctx, path, true, true, false)
+			cfgUpdate, err := config.Parse([]string{tc.updatePath}, true, true)
+			if err == nil { // update can fail and that's expected
+				_ = m.update(ctx, cfgUpdate, false)
+			}
 			if len(tc.want) != len(m.groups) {
 				t.Fatalf("\nwant number of groups: %d;\ngot: %d ", len(tc.want), len(m.groups))
 			}
@@ -267,3 +275,12 @@ func TestManagerUpdate(t *testing.T) {
 		})
 	}
 }
+
+func loadCfg(t *testing.T, path []string, validateAnnotations, validateExpressions bool) []config.Group {
+	t.Helper()
+	cfg, err := config.Parse(path, validateAnnotations, validateExpressions)
+	if err != nil {
+		t.Fatal(err)
+	}
+	return cfg
+}

app/vmalert/multiarch/Dockerfile

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

app/vmalert/notifier/alert.go

@@ -14,17 +14,26 @@ import (
 // Alert the triggered alert
 // TODO: Looks like alert name isn't unique
 type Alert struct {
-	GroupID     uint64
-	Name        string
-	Labels      map[string]string
+	// GroupID contains the ID of the parent rules group
+	GroupID uint64
+	// Name represents Alert name
+	Name string
+	// Labels is the list of label-value pairs attached to the Alert
+	Labels map[string]string
+	// Annotations is the list of annotations generated on Alert evaluation
 	Annotations map[string]string
-	State       AlertState
-
-	Expr  string
+	// State represents the current state of the Alert
+	State AlertState
+	// Expr contains expression that was executed to generate the Alert
+	Expr string
+	// Start defines the moment of time when Alert has triggered
 	Start time.Time
-	End   time.Time
+	// End defines the moment of time when Alert supposed to expire
+	End time.Time
+	// Value stores the value returned from evaluating expression from Expr field
 	Value float64
-	ID    uint64
+	// ID is the unique identifer for the Alert
+	ID uint64
 }
 
 // AlertState type indicates the Alert state
@@ -90,13 +99,13 @@ func templateAnnotations(annotations map[string]string, data AlertTplData, funcs
 	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(tplHeader) + len(text))
 		builder.WriteString(tplHeader)
 		builder.WriteString(text)
 		if err := templateAnnotation(&buf, builder.String(), data, funcs); err != nil {
+			r[key] = text
 			eg.Add(fmt.Errorf("key %q, template %q: %w", key, text, err))
 			continue
 		}

app/vmalert/notifier/alert_test.go

@@ -83,14 +83,16 @@ func TestAlert_ExecTemplate(t *testing.T) {
 					{Name: "foo", Value: "bar"},
 					{Name: "baz", Value: "qux"},
 				},
-				Value: 1,
+				Values:     []float64{1},
+				Timestamps: []int64{1},
 			},
 			{
 				Labels: []datasource.Label{
 					{Name: "foo", Value: "garply"},
 					{Name: "baz", Value: "fred"},
 				},
-				Value: 2,
+				Values:     []float64{2},
+				Timestamps: []int64{1},
 			},
 		}, nil
 	}

app/vmalert/notifier/alertmanager.go

@@ -12,6 +12,7 @@ import (
 // AlertManager represents integration provider with Prometheus alert manager
 // https://github.com/prometheus/alertmanager
 type AlertManager struct {
+	addr          string
 	alertURL      string
 	basicAuthUser string
 	basicAuthPass string
@@ -19,6 +20,9 @@ type AlertManager struct {
 	client        *http.Client
 }
 
+// Addr returns address where alerts are sent.
+func (am AlertManager) Addr() string { return am.addr }
+
 // Send an alert or resolve message
 func (am *AlertManager) Send(ctx context.Context, alerts []Alert) error {
 	b := &bytes.Buffer{}
@@ -57,9 +61,10 @@ const alertManagerPath = "/api/v2/alerts"
 
 // NewAlertManager is a constructor for AlertManager
 func NewAlertManager(alertManagerURL, user, pass string, fn AlertURLGenerator, c *http.Client) *AlertManager {
-	addr := strings.TrimSuffix(alertManagerURL, "/") + alertManagerPath
+	url := strings.TrimSuffix(alertManagerURL, "/") + alertManagerPath
 	return &AlertManager{
-		alertURL:      addr,
+		addr:          alertManagerURL,
+		alertURL:      url,
 		argFunc:       fn,
 		client:        c,
 		basicAuthUser: user,

app/vmalert/notifier/alertmanager_test.go

@@ -10,6 +10,14 @@ import (
 	"time"
 )
 
+func TestAlertManager_Addr(t *testing.T) {
+	const addr = "http://localhost"
+	am := NewAlertManager(addr, "", "", nil, nil)
+	if am.Addr() != addr {
+		t.Errorf("expected to have %q; got %q", addr, am.Addr())
+	}
+}
+
 func TestAlertManager_Send(t *testing.T) {
 	const baUser, baPass = "foo", "bar"
 	mux := http.NewServeMux()

app/vmalert/notifier/notifier.go

@@ -2,7 +2,12 @@ package notifier
 
 import "context"
 
-// Notifier is common interface for alert manager provider
+// Notifier is a common interface for alert manager provider
 type Notifier interface {
+	// Send sends the given list of alerts.
+	// Returns an error if fails to send the alerts.
+	// Must unblock if the given ctx is cancelled.
 	Send(ctx context.Context, alerts []Alert) error
+	// Addr returns address where alerts are sent.
+	Addr() string
 }

app/vmalert/notifier/template_func.go

@@ -28,44 +28,73 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
 )
 
+// metric is private copy of datasource.Metric,
+// it is used for templating annotations,
+// Labels as map simplifies templates evaluation.
+type metric struct {
+	Labels    map[string]string
+	Timestamp int64
+	Value     float64
+}
+
+// datasourceMetricsToTemplateMetrics converts Metrics from datasource package to private copy for templating.
+func datasourceMetricsToTemplateMetrics(ms []datasource.Metric) []metric {
+	mss := make([]metric, 0, len(ms))
+	for _, m := range ms {
+		labelsMap := make(map[string]string, len(m.Labels))
+		for _, labelValue := range m.Labels {
+			labelsMap[labelValue.Name] = labelValue.Value
+		}
+		mss = append(mss, metric{
+			Labels:    labelsMap,
+			Timestamp: m.Timestamps[0],
+			Value:     m.Values[0]})
+	}
+	return mss
+}
+
 // QueryFn is used to wrap a call to datasource into simple-to-use function
 // for templating functions.
 type QueryFn func(query string) ([]datasource.Metric, error)
 
-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 = textTpl.FuncMap{
-		"args": func(args ...interface{}) map[string]interface{} {
-			result := make(map[string]interface{})
-			for i, a := range args {
-				result[fmt.Sprintf("arg%d", i)] = a
-			}
-			return result
-		},
+		/* Strings */
+
+		// reReplaceAll ReplaceAllString returns a copy of src, replacing matches of the Regexp with
+		// the replacement string repl. Inside repl, $ signs are interpreted as in Expand,
+		// so for instance $1 represents the text of the first submatch.
+		// alias for https://golang.org/pkg/regexp/#Regexp.ReplaceAllString
 		"reReplaceAll": func(pattern, repl, text string) string {
 			re := regexp.MustCompile(pattern)
 			return re.ReplaceAllString(text, repl)
 		},
-		"safeHtml": func(text string) htmlTpl.HTML {
-			return htmlTpl.HTML(text)
-		},
-		"match":   regexp.MatchString,
-		"title":   strings.Title,
+
+		// match reports whether the string s
+		// contains any match of the regular expression pattern.
+		// alias for https://golang.org/pkg/regexp/#MatchString
+		"match": regexp.MatchString,
+
+		// title returns a copy of the string s with all Unicode letters
+		// that begin words mapped to their Unicode title case.
+		// alias for https://golang.org/pkg/strings/#Title
+		"title": strings.Title,
+
+		// toUpper returns s with all Unicode letters mapped to their upper case.
+		// alias for https://golang.org/pkg/strings/#ToUpper
 		"toUpper": strings.ToUpper,
+
+		// toLower returns s with all Unicode letters mapped to their lower case.
+		// alias for https://golang.org/pkg/strings/#ToLower
 		"toLower": strings.ToLower,
+
+		/* Numbers */
+
+		// humanize converts given number to a human readable format
+		// by adding metric prefixes https://en.wikipedia.org/wiki/Metric_prefix
 		"humanize": func(v float64) string {
 			if v == 0 || math.IsNaN(v) || math.IsInf(v, 0) {
 				return fmt.Sprintf("%.4g", v)
@@ -91,6 +120,8 @@ func InitTemplateFunc(externalURL *url.URL) {
 			}
 			return fmt.Sprintf("%.4g%s", v, prefix)
 		},
+
+		// humanize1024 converts given number to a human readable format with 1024 as base
 		"humanize1024": func(v float64) string {
 			if math.Abs(v) <= 1 || math.IsNaN(v) || math.IsInf(v, 0) {
 				return fmt.Sprintf("%.4g", v)
@@ -105,6 +136,8 @@ func InitTemplateFunc(externalURL *url.URL) {
 			}
 			return fmt.Sprintf("%.4g%s", v, prefix)
 		},
+
+		// humanizeDuration converts given seconds to a human readable duration
 		"humanizeDuration": func(v float64) string {
 			if math.IsNaN(v) || math.IsInf(v, 0) {
 				return fmt.Sprintf("%.4g", v)
@@ -145,9 +178,13 @@ func InitTemplateFunc(externalURL *url.URL) {
 			}
 			return fmt.Sprintf("%.4g%ss", v, prefix)
 		},
+
+		// humanizePercentage converts given ratio value to a fraction of 100
 		"humanizePercentage": func(v float64) string {
 			return fmt.Sprintf("%.4g%%", v*100)
 		},
+
+		// humanizeTimestamp converts given timestamp to a human readable time equivalent
 		"humanizeTimestamp": func(v float64) string {
 			if math.IsNaN(v) || math.IsInf(v, 0) {
 				return fmt.Sprintf("%.4g", v)
@@ -155,48 +192,115 @@ func InitTemplateFunc(externalURL *url.URL) {
 			t := TimeFromUnixNano(int64(v * 1e9)).Time().UTC()
 			return fmt.Sprint(t)
 		},
-		"pathPrefix": func() string {
-			return externalURL.Path
-		},
+
+		/* URLs */
+
+		// externalURL returns value of `external.url` flag
 		"externalURL": func() string {
 			return externalURL.String()
 		},
+
+		// pathPrefix returns a Path segment from the URL value in `external.url` flag
+		"pathPrefix": func() string {
+			return externalURL.Path
+		},
+
+		// pathEscape escapes the string so it can be safely placed inside a URL path segment,
+		// replacing special characters (including /) with %XX sequences as needed.
+		// alias for https://golang.org/pkg/net/url/#PathEscape
 		"pathEscape": func(u string) string {
 			return url.PathEscape(u)
 		},
+
+		// queryEscape escapes the string so it can be safely placed
+		// inside a URL query.
+		// alias for https://golang.org/pkg/net/url/#QueryEscape
 		"queryEscape": func(q string) string {
 			return url.QueryEscape(q)
 		},
+
+		// crlfEscape replaces new line chars to skip URL encoding.
+		// see https://github.com/VictoriaMetrics/VictoriaMetrics/issues/890
 		"crlfEscape": func(q string) string {
 			q = strings.Replace(q, "\n", `\n`, -1)
 			return strings.Replace(q, "\r", `\r`, -1)
 		},
+
+		// quotesEscape escapes quote char
 		"quotesEscape": func(q string) string {
 			return strings.Replace(q, `"`, `\"`, -1)
 		},
-		// query 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) {
+
+		// query executes the MetricsQL/PromQL query against
+		// configured `datasource.url` address.
+		// For example, {{ query "foo" | first | value }} will
+		// execute "/api/v1/query?query=foo" request and will return
+		// the first value in response.
+		"query": func(q string) ([]metric, error) {
+			// query function supposed to be substituted at funcsWithQuery().
+			// it is present here only for validation purposes, when there is no
+			// provided datasource.
+			//
 			// return non-empty slice to pass validation with chained functions in template
 			// see issue #989 for details
-			return []datasource.Metric{{}}, nil
+			return []metric{{}}, nil
 		},
-		"first": func(metrics []datasource.Metric) (datasource.Metric, error) {
+
+		// first returns the first by order element from the given metrics list.
+		// usually used alongside with `query` template function.
+		"first": func(metrics []metric) (metric, error) {
 			if len(metrics) > 0 {
 				return metrics[0], nil
 			}
-			return datasource.Metric{}, errors.New("first() called on vector with no elements")
+			return metric{}, errors.New("first() called on vector with no elements")
 		},
-		"label": func(label string, m datasource.Metric) string {
-			return m.Label(label)
+
+		// label returns the value of the given label name for the given metric.
+		// usually used alongside with `query` template function.
+		"label": func(label string, m metric) string {
+			return m.Labels[label]
 		},
-		"value": func(m datasource.Metric) float64 {
+
+		// value returns the value of the given metric.
+		// usually used alongside with `query` template function.
+		"value": func(m metric) float64 {
 			return m.Value
 		},
+
+		/* Helpers */
+
+		// Converts a list of objects to a map with keys arg0, arg1 etc.
+		// This is intended to allow multiple arguments to be passed to templates.
+		"args": func(args ...interface{}) map[string]interface{} {
+			result := make(map[string]interface{})
+			for i, a := range args {
+				result[fmt.Sprintf("arg%d", i)] = a
+			}
+			return result
+		},
+
+		// safeHtml marks string as HTML not requiring auto-escaping.
+		"safeHtml": func(text string) htmlTpl.HTML {
+			return htmlTpl.HTML(text)
+		},
 	}
 }
 
+func funcsWithQuery(query QueryFn) textTpl.FuncMap {
+	fm := make(textTpl.FuncMap)
+	for k, fn := range tmplFunc {
+		fm[k] = fn
+	}
+	fm["query"] = func(q string) ([]metric, error) {
+		result, err := query(q)
+		if err != nil {
+			return nil, err
+		}
+		return datasourceMetricsToTemplateMetrics(result), nil
+	}
+	return fm
+}
+
 // Time is the number of milliseconds since the epoch
 // (1970-01-01 00:00 UTC) excluding leap seconds.
 type Time int64

app/vmalert/recording.go

@@ -3,8 +3,8 @@ package main
 import (
 	"context"
 	"fmt"
-	"hash/fnv"
 	"sort"
+	"strings"
 	"sync"
 	"time"
 
@@ -25,6 +25,8 @@ type RecordingRule struct {
 	Labels  map[string]string
 	GroupID uint64
 
+	q datasource.Querier
+
 	// guard status fields
 	mu sync.RWMutex
 	// stores last moment of time Exec was called
@@ -33,12 +35,16 @@ type RecordingRule struct {
 	// resets on every successful Exec
 	// may be used as Health state
 	lastExecError error
+	// stores the number of samples returned during
+	// the last evaluation
+	lastExecSamples int
 
 	metrics *recordingRuleMetrics
 }
 
 type recordingRuleMetrics struct {
-	errors *gauge
+	errors  *gauge
+	samples *gauge
 }
 
 // String implements Stringer interface
@@ -52,7 +58,7 @@ func (rr *RecordingRule) ID() uint64 {
 	return rr.RuleID
 }
 
-func newRecordingRule(group *Group, cfg config.Rule) *RecordingRule {
+func newRecordingRule(qb datasource.QuerierBuilder, group *Group, cfg config.Rule) *RecordingRule {
 	rr := &RecordingRule{
 		Type:    cfg.Type,
 		RuleID:  cfg.ID,
@@ -61,72 +67,108 @@ func newRecordingRule(group *Group, cfg config.Rule) *RecordingRule {
 		Labels:  cfg.Labels,
 		GroupID: group.ID(),
 		metrics: &recordingRuleMetrics{},
+		q: qb.BuildWithParams(datasource.QuerierParams{
+			DataSourceType:     &cfg.Type,
+			EvaluationInterval: group.Interval,
+			ExtraLabels:        group.ExtraFilterLabels,
+		}),
 	}
 
 	labels := fmt.Sprintf(`recording=%q, group=%q, id="%d"`, rr.Name, group.Name, rr.ID())
 	rr.metrics.errors = getOrCreateGauge(fmt.Sprintf(`vmalert_recording_rules_error{%s}`, labels),
 		func() float64 {
-			rr.mu.Lock()
-			defer rr.mu.Unlock()
+			rr.mu.RLock()
+			defer rr.mu.RUnlock()
 			if rr.lastExecError == nil {
 				return 0
 			}
 			return 1
 		})
+	rr.metrics.samples = getOrCreateGauge(fmt.Sprintf(`vmalert_recording_rules_last_evaluation_samples{%s}`, labels),
+		func() float64 {
+			rr.mu.RLock()
+			defer rr.mu.RUnlock()
+			return float64(rr.lastExecSamples)
+		})
 	return rr
 }
 
 // Close unregisters rule metrics
 func (rr *RecordingRule) Close() {
 	metrics.UnregisterMetric(rr.metrics.errors.name)
+	metrics.UnregisterMetric(rr.metrics.samples.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
+// ExecRange executes recording rule on the given time range similarly to Exec.
+// It doesn't update internal states of the Rule and meant to be used just
+// to get time series for backfilling.
+func (rr *RecordingRule) ExecRange(ctx context.Context, start, end time.Time) ([]prompbmarshal.TimeSeries, error) {
+	series, err := rr.q.QueryRange(ctx, rr.Expr, start, end)
 	if err != nil {
-		return nil, fmt.Errorf("failed to execute query %q: %w", rr.Expr, err)
+		return nil, err
 	}
-
-	duplicates := make(map[uint64]prompbmarshal.TimeSeries, len(qMetrics))
+	duplicates := make(map[string]struct{}, len(series))
 	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
+	for _, s := range series {
+		ts := rr.toTimeSeries(s)
+		key := stringifyLabels(ts)
+		if _, ok := duplicates[key]; ok {
+			return nil, fmt.Errorf("original metric %v; resulting labels %q: %w", s.Labels, key, errDuplicate)
 		}
-		duplicates[h] = ts
+		duplicates[key] = struct{}{}
 		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"))
+// Exec executes RecordingRule expression via the given Querier.
+func (rr *RecordingRule) Exec(ctx context.Context) ([]prompbmarshal.TimeSeries, error) {
+	qMetrics, err := rr.q.Query(ctx, rr.Expr)
+	rr.mu.Lock()
+	defer rr.mu.Unlock()
+
+	rr.lastExecTime = time.Now()
+	rr.lastExecError = err
+	rr.lastExecSamples = len(qMetrics)
+	if err != nil {
+		return nil, fmt.Errorf("failed to execute query %q: %w", rr.Expr, err)
 	}
-	return hash.Sum64()
+
+	duplicates := make(map[string]struct{}, len(qMetrics))
+	var tss []prompbmarshal.TimeSeries
+	for _, r := range qMetrics {
+		ts := rr.toTimeSeries(r)
+		key := stringifyLabels(ts)
+		if _, ok := duplicates[key]; ok {
+			rr.lastExecError = errDuplicate
+			return nil, fmt.Errorf("original metric %v; resulting labels %q: %w", r, key, errDuplicate)
+		}
+		duplicates[key] = struct{}{}
+		tss = append(tss, ts)
+	}
+	return tss, nil
 }
 
-func (rr *RecordingRule) toTimeSeries(m datasource.Metric, timestamp time.Time) prompbmarshal.TimeSeries {
+func stringifyLabels(ts prompbmarshal.TimeSeries) string {
+	labels := ts.Labels
+	if len(labels) > 1 {
+		sort.Slice(labels, func(i, j int) bool {
+			return labels[i].Name < labels[j].Name
+		})
+	}
+	b := strings.Builder{}
+	for i, l := range labels {
+		b.WriteString(l.Name)
+		b.WriteString("=")
+		b.WriteString(l.Value)
+		if i != len(labels)-1 {
+			b.WriteString(",")
+		}
+	}
+	return b.String()
+}
+
+func (rr *RecordingRule) toTimeSeries(m datasource.Metric) prompbmarshal.TimeSeries {
 	labels := make(map[string]string)
 	for _, l := range m.Labels {
 		labels[l.Name] = l.Value
@@ -136,12 +178,10 @@ func (rr *RecordingRule) toTimeSeries(m datasource.Metric, timestamp time.Time)
 	for k, v := range rr.Labels {
 		labels[k] = v
 	}
-	return newTimeSeries(m.Value, labels, timestamp)
+	return newTimeSeries(m.Values, m.Timestamps, labels)
 }
 
 // UpdateWith copies all significant fields.
-// alerts state isn't copied since
-// it should be updated in next 2 Execs
 func (rr *RecordingRule) UpdateWith(r Rule) error {
 	nr, ok := r.(*RecordingRule)
 	if !ok {
@@ -149,6 +189,7 @@ func (rr *RecordingRule) UpdateWith(r Rule) error {
 	}
 	rr.Expr = nr.Expr
 	rr.Labels = nr.Labels
+	rr.q = nr.q
 	return nil
 }
 
@@ -161,13 +202,14 @@ func (rr *RecordingRule) RuleAPI() APIRecordingRule {
 	}
 	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,
+		ID:          fmt.Sprintf("%d", rr.ID()),
+		GroupID:     fmt.Sprintf("%d", rr.GroupID),
+		Name:        rr.Name,
+		Type:        rr.Type.String(),
+		Expression:  rr.Expr,
+		LastError:   lastErr,
+		LastSamples: rr.lastExecSamples,
+		LastExec:    rr.lastExecTime,
+		Labels:      rr.Labels,
 	}
 }

app/vmalert/recording_test.go

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

app/vmalert/remoteread/init.go

@@ -10,11 +10,15 @@ import (
 )
 
 var (
-	addr = flag.String("remoteRead.url", "", "Optional URL to Victoria Metrics or VMSelect that will be used to restore alerts"+
-		" state. This configuration makes sense only if `vmalert` was configured with `remoteWrite.url` before and has been successfully persisted its state."+
-		" E.g. http://127.0.0.1:8428")
+	addr = flag.String("remoteRead.url", "", "Optional URL to VictoriaMetrics or vmselect that will be used to restore alerts "+
+		"state. This configuration makes sense only if `vmalert` was configured with `remoteWrite.url` before and has been successfully persisted its state. "+
+		"E.g. http://127.0.0.1:8428")
 	basicAuthUsername     = flag.String("remoteRead.basicAuth.username", "", "Optional basic auth username for -remoteRead.url")
 	basicAuthPassword     = flag.String("remoteRead.basicAuth.password", "", "Optional basic auth password for -remoteRead.url")
+	basicAuthPasswordFile = flag.String("remoteRead.basicAuth.passwordFile", "", "Optional path to basic auth password to use for -remoteRead.url")
+	bearerToken           = flag.String("remoteRead.bearerToken", "", "Optional bearer auth token to use for -remoteRead.url.")
+	bearerTokenFile       = flag.String("remoteRead.bearerTokenFile", "", "Optional path to bearer token file to use 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")
@@ -26,7 +30,7 @@ var (
 
 // Init creates a Querier from provided flag values.
 // Returns nil if addr flag wasn't set.
-func Init() (datasource.Querier, error) {
+func Init() (datasource.QuerierBuilder, error) {
 	if *addr == "" {
 		return nil, nil
 	}
@@ -34,6 +38,10 @@ func Init() (datasource.Querier, error) {
 	if err != nil {
 		return nil, fmt.Errorf("failed to create transport: %w", err)
 	}
+	authCfg, err := utils.AuthConfig(*basicAuthUsername, *basicAuthPassword, *basicAuthPasswordFile, *bearerToken, *bearerTokenFile)
+	if err != nil {
+		return nil, fmt.Errorf("failed to configure auth: %w", err)
+	}
 	c := &http.Client{Transport: tr}
-	return datasource.NewVMStorage(*addr, *basicAuthUsername, *basicAuthPassword, 0, 0, c), nil
+	return datasource.NewVMStorage(*addr, authCfg, 0, 0, false, c), nil
 }

app/vmalert/remotewrite/init.go

@@ -10,10 +10,14 @@ import (
 )
 
 var (
-	addr = flag.String("remoteWrite.url", "", "Optional URL to Victoria Metrics or VMInsert where to persist alerts state"+
-		" and recording rules results in form of timeseries. E.g. http://127.0.0.1:8428")
-	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")
+	addr = flag.String("remoteWrite.url", "", "Optional URL to VictoriaMetrics or vminsert where to persist alerts state "+
+		"and recording rules results in form of timeseries. For example, if -remoteWrite.url=http://127.0.0.1:8428 is specified, "+
+		"then the alerts state will be written to http://127.0.0.1:8428/api/v1/write . See also -remoteWrite.disablePathAppend")
+	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")
+	basicAuthPasswordFile = flag.String("remoteWrite.basicAuth.passwordFile", "", "Optional path to basic auth password to use for -remoteWrite.url")
+	bearerToken           = flag.String("remoteWrite.bearerToken", "", "Optional bearer auth token to use for -remoteWrite.url.")
+	bearerTokenFile       = flag.String("remoteWrite.bearerTokenFile", "", "Optional path to bearer token file to use 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")
@@ -27,6 +31,7 @@ var (
 		"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")
+	disablePathAppend = flag.Bool("remoteWrite.disablePathAppend", false, "Whether to disable automatic appending of '/api/v1/write' path to the configured -remoteWrite.url.")
 )
 
 // Init creates Client object from given flags.
@@ -41,14 +46,19 @@ func Init(ctx context.Context) (*Client, error) {
 		return nil, fmt.Errorf("failed to create transport: %w", err)
 	}
 
+	authCfg, err := utils.AuthConfig(*basicAuthUsername, *basicAuthPassword, *basicAuthPasswordFile, *bearerToken, *bearerTokenFile)
+	if err != nil {
+		return nil, fmt.Errorf("failed to configure auth: %w", err)
+	}
+
 	return NewClient(ctx, Config{
-		Addr:          *addr,
-		Concurrency:   *concurrency,
-		MaxQueueSize:  *maxQueueSize,
-		MaxBatchSize:  *maxBatchSize,
-		FlushInterval: *flushInterval,
-		BasicAuthUser: *basicAuthUsername,
-		BasicAuthPass: *basicAuthPassword,
-		Transport:     t,
+		Addr:              *addr,
+		AuthCfg:           authCfg,
+		Concurrency:       *concurrency,
+		MaxQueueSize:      *maxQueueSize,
+		MaxBatchSize:      *maxBatchSize,
+		FlushInterval:     *flushInterval,
+		DisablePathAppend: *disablePathAppend,
+		Transport:         t,
 	})
 }

app/vmalert/remotewrite/remotewrite.go

@@ -6,26 +6,30 @@ import (
 	"fmt"
 	"io/ioutil"
 	"net/http"
+	"path"
 	"strings"
 	"sync"
 	"time"
 
+	"github.com/golang/snappy"
+
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promauth"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
 	"github.com/VictoriaMetrics/metrics"
-	"github.com/golang/snappy"
 )
 
 // Client is an asynchronous HTTP client for writing
 // timeseries via remote write protocol.
 type Client struct {
-	addr           string
-	c              *http.Client
-	input          chan prompbmarshal.TimeSeries
-	baUser, baPass string
-	flushInterval  time.Duration
-	maxBatchSize   int
-	maxQueueSize   int
+	addr              string
+	c                 *http.Client
+	authCfg           *promauth.Config
+	input             chan prompbmarshal.TimeSeries
+	flushInterval     time.Duration
+	maxBatchSize      int
+	maxQueueSize      int
+	disablePathAppend bool
 
 	wg     sync.WaitGroup
 	doneCh chan struct{}
@@ -34,10 +38,8 @@ type Client struct {
 // Config is config for remote write.
 type Config struct {
 	// Addr of remote storage
-	Addr string
-
-	BasicAuthUser string
-	BasicAuthPass string
+	Addr    string
+	AuthCfg *promauth.Config
 
 	// Concurrency defines number of readers that
 	// concurrently read from the queue and flush data
@@ -56,6 +58,8 @@ type Config struct {
 	WriteTimeout time.Duration
 	// Transport will be used by the underlying http.Client
 	Transport *http.Transport
+	// DisablePathAppend can be used to not automatically append '/api/v1/write' to the remote write url
+	DisablePathAppend bool
 }
 
 const (
@@ -89,24 +93,25 @@ func NewClient(ctx context.Context, cfg Config) (*Client, error) {
 	if cfg.Transport == nil {
 		cfg.Transport = http.DefaultTransport.(*http.Transport).Clone()
 	}
+	cc := defaultConcurrency
+	if cfg.Concurrency > 0 {
+		cc = cfg.Concurrency
+	}
 	c := &Client{
 		c: &http.Client{
 			Timeout:   cfg.WriteTimeout,
 			Transport: cfg.Transport,
 		},
-		addr:          strings.TrimSuffix(cfg.Addr, "/") + writePath,
-		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),
-	}
-	cc := defaultConcurrency
-	if cfg.Concurrency > 0 {
-		cc = cfg.Concurrency
+		addr:              strings.TrimSuffix(cfg.Addr, "/"),
+		authCfg:           cfg.AuthCfg,
+		flushInterval:     cfg.FlushInterval,
+		maxBatchSize:      cfg.MaxBatchSize,
+		maxQueueSize:      cfg.MaxQueueSize,
+		doneCh:            make(chan struct{}),
+		input:             make(chan prompbmarshal.TimeSeries, cfg.MaxQueueSize),
+		disablePathAppend: cfg.DisablePathAppend,
 	}
+
 	for i := 0; i < cc; i++ {
 		c.run(ctx)
 	}
@@ -179,10 +184,11 @@ func (c *Client) run(ctx context.Context) {
 }
 
 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`)
+	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`)
+	bufferFlushDuration = metrics.NewHistogram(`vmalert_remotewrite_flush_duration_seconds`)
 )
 
 // flush is a blocking function that marshals WriteRequest and sends
@@ -193,6 +199,7 @@ func (c *Client) flush(ctx context.Context, wr *prompbmarshal.WriteRequest) {
 		return
 	}
 	defer prompbmarshal.ResetWriteRequest(wr)
+	defer bufferFlushDuration.UpdateDuration(time.Now())
 
 	data, err := wr.Marshal()
 	if err != nil {
@@ -228,8 +235,13 @@ func (c *Client) send(ctx context.Context, data []byte) error {
 	if err != nil {
 		return fmt.Errorf("failed to create new HTTP request: %w", err)
 	}
-	if c.baPass != "" {
-		req.SetBasicAuth(c.baUser, c.baPass)
+	if c.authCfg != nil {
+		if auth := c.authCfg.GetAuthHeader(); auth != "" {
+			req.Header.Set("Authorization", auth)
+		}
+	}
+	if !c.disablePathAppend {
+		req.URL.Path = path.Join(req.URL.Path, writePath)
 	}
 	resp, err := c.c.Do(req.WithContext(ctx))
 	if err != nil {
@@ -237,7 +249,7 @@ func (c *Client) send(ctx context.Context, data []byte) error {
 			req.URL, err, len(data), r.Size())
 	}
 	defer func() { _ = resp.Body.Close() }()
-	if resp.StatusCode != http.StatusNoContent {
+	if resp.StatusCode != http.StatusNoContent && resp.StatusCode != http.StatusOK {
 		body, _ := ioutil.ReadAll(resp.Body)
 		return fmt.Errorf("unexpected response code %d for %s. Response body %q",
 			resp.StatusCode, req.URL, body)

app/vmalert/replay.go

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

app/vmalert/replay_test.go

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

app/vmalert/rule.go

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

app/vmalert/tpl/footer.qtpl

@@ -0,0 +1,36 @@
+{% func Footer() %}
+        </main>
+        <script src="https://cdn.jsdelivr.net/npm/bootstrap@5.0.2/dist/js/bootstrap.bundle.min.js" integrity="sha384-MrcW6ZMFYlzcLA8Nl+NtUVF0sA7MsXsP1UyJoMp4YLEuNSfAP+JcXn/tWtIaxVXM" crossorigin="anonymous"></script>
+        <script src="https://code.jquery.com/jquery-3.3.1.min.js"></script>
+        <script type="text/javascript">
+            function expandAll() {
+               $('.collapse').addClass('show');
+            }
+            function collapseAll() {
+               $('.collapse').removeClass('show');
+            }
+
+            $(document).ready(function() {
+              // prevent collapse logic on link click
+              $(".group-heading a").click(function(e) {
+                e.stopPropagation();
+              });
+
+              $(".group-heading").click(function(e) {
+                 let target = $(this).attr('data-bs-target');
+                 let el = $('#'+target);
+                  new bootstrap.Collapse(el, {
+                    toggle: true
+                  });
+              });
+
+              var hash = window.location.hash.substr(1);
+              let group = $('#'+hash);
+              if (group.length > 0) {
+                group.click();
+              }
+            });
+        </script>
+    </body>
+</html>
+{% endfunc %}

app/vmalert/tpl/footer.qtpl.go

@@ -0,0 +1,86 @@
+// Code generated by qtc from "footer.qtpl". DO NOT EDIT.
+// See https://github.com/valyala/quicktemplate for details.
+
+//line app/vmalert/tpl/footer.qtpl:1
+package tpl
+
+//line app/vmalert/tpl/footer.qtpl:1
+import (
+	qtio422016 "io"
+
+	qt422016 "github.com/valyala/quicktemplate"
+)
+
+//line app/vmalert/tpl/footer.qtpl:1
+var (
+	_ = qtio422016.Copy
+	_ = qt422016.AcquireByteBuffer
+)
+
+//line app/vmalert/tpl/footer.qtpl:1
+func StreamFooter(qw422016 *qt422016.Writer) {
+//line app/vmalert/tpl/footer.qtpl:1
+	qw422016.N().S(`
+        </main>
+        <script src="https://cdn.jsdelivr.net/npm/bootstrap@5.0.2/dist/js/bootstrap.bundle.min.js" integrity="sha384-MrcW6ZMFYlzcLA8Nl+NtUVF0sA7MsXsP1UyJoMp4YLEuNSfAP+JcXn/tWtIaxVXM" crossorigin="anonymous"></script>
+        <script src="https://code.jquery.com/jquery-3.3.1.min.js"></script>
+        <script type="text/javascript">
+            function expandAll() {
+               $('.collapse').addClass('show');
+            }
+            function collapseAll() {
+               $('.collapse').removeClass('show');
+            }
+
+            $(document).ready(function() {
+              // prevent collapse logic on link click
+              $(".group-heading a").click(function(e) {
+                e.stopPropagation();
+              });
+
+              $(".group-heading").click(function(e) {
+                 let target = $(this).attr('data-bs-target');
+                 let el = $('#'+target);
+                  new bootstrap.Collapse(el, {
+                    toggle: true
+                  });
+              });
+
+              var hash = window.location.hash.substr(1);
+              let group = $('#'+hash);
+              if (group.length > 0) {
+                group.click();
+              }
+            });
+        </script>
+    </body>
+</html>
+`)
+//line app/vmalert/tpl/footer.qtpl:36
+}
+
+//line app/vmalert/tpl/footer.qtpl:36
+func WriteFooter(qq422016 qtio422016.Writer) {
+//line app/vmalert/tpl/footer.qtpl:36
+	qw422016 := qt422016.AcquireWriter(qq422016)
+//line app/vmalert/tpl/footer.qtpl:36
+	StreamFooter(qw422016)
+//line app/vmalert/tpl/footer.qtpl:36
+	qt422016.ReleaseWriter(qw422016)
+//line app/vmalert/tpl/footer.qtpl:36
+}
+
+//line app/vmalert/tpl/footer.qtpl:36
+func Footer() string {
+//line app/vmalert/tpl/footer.qtpl:36
+	qb422016 := qt422016.AcquireByteBuffer()
+//line app/vmalert/tpl/footer.qtpl:36
+	WriteFooter(qb422016)
+//line app/vmalert/tpl/footer.qtpl:36
+	qs422016 := string(qb422016.B)
+//line app/vmalert/tpl/footer.qtpl:36
+	qt422016.ReleaseByteBuffer(qb422016)
+//line app/vmalert/tpl/footer.qtpl:36
+	return qs422016
+//line app/vmalert/tpl/footer.qtpl:36
+}

app/vmalert/tpl/header.qtpl

@@ -0,0 +1,43 @@
+{% func Header(title string, pages []NavItem) %}
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <title>vmalert{% if title != "" %} - {%s title %}{% endif %}</title>
+    <link href="https://cdn.jsdelivr.net/npm/bootstrap@5.0.2/dist/css/bootstrap.min.css" rel="stylesheet" integrity="sha384-EVSTQN3/azprG1Anm3QDgpJLIm9Nao0Yz1ztcQTwFspd3yD65VohhpuuCOmLASjC" crossorigin="anonymous">
+    <style>
+        body{
+          min-height: 75rem;
+          padding-top: 4.5rem;
+        }
+        pre {
+            overflow: scroll;
+            max-width: 600px;
+            min-height: 30px;
+        }
+        .group-heading {
+            cursor: pointer;
+            padding: 5px;
+            margin-top: 5px;
+            position: relative;
+        }
+        .group-heading .anchor {
+            position:absolute;
+            top:-60px;
+        }
+        .group-heading span {
+            float: right;
+            margin-left: 5px;
+            margin-right: 5px;
+        }
+         .group-heading:hover {
+            background-color: #f8f9fa!important;
+        }
+        .table .error-cell{
+            word-break: break-word;
+        }
+    </style>
+</head>
+<body>
+    {%= PrintNavItems(title, pages) %}
+    <main class="px-2">
+{% endfunc %}

app/vmalert/tpl/header.qtpl.go

@@ -0,0 +1,107 @@
+// Code generated by qtc from "header.qtpl". DO NOT EDIT.
+// See https://github.com/valyala/quicktemplate for details.
+
+//line app/vmalert/tpl/header.qtpl:1
+package tpl
+
+//line app/vmalert/tpl/header.qtpl:1
+import (
+	qtio422016 "io"
+
+	qt422016 "github.com/valyala/quicktemplate"
+)
+
+//line app/vmalert/tpl/header.qtpl:1
+var (
+	_ = qtio422016.Copy
+	_ = qt422016.AcquireByteBuffer
+)
+
+//line app/vmalert/tpl/header.qtpl:1
+func StreamHeader(qw422016 *qt422016.Writer, title string, pages []NavItem) {
+//line app/vmalert/tpl/header.qtpl:1
+	qw422016.N().S(`
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <title>vmalert`)
+//line app/vmalert/tpl/header.qtpl:5
+	if title != "" {
+//line app/vmalert/tpl/header.qtpl:5
+		qw422016.N().S(` - `)
+//line app/vmalert/tpl/header.qtpl:5
+		qw422016.E().S(title)
+//line app/vmalert/tpl/header.qtpl:5
+	}
+//line app/vmalert/tpl/header.qtpl:5
+	qw422016.N().S(`</title>
+    <link href="https://cdn.jsdelivr.net/npm/bootstrap@5.0.2/dist/css/bootstrap.min.css" rel="stylesheet" integrity="sha384-EVSTQN3/azprG1Anm3QDgpJLIm9Nao0Yz1ztcQTwFspd3yD65VohhpuuCOmLASjC" crossorigin="anonymous">
+    <style>
+        body{
+          min-height: 75rem;
+          padding-top: 4.5rem;
+        }
+        pre {
+            overflow: scroll;
+            max-width: 600px;
+            min-height: 30px;
+        }
+        .group-heading {
+            cursor: pointer;
+            padding: 5px;
+            margin-top: 5px;
+            position: relative;
+        }
+        .group-heading .anchor {
+            position:absolute;
+            top:-60px;
+        }
+        .group-heading span {
+            float: right;
+            margin-left: 5px;
+            margin-right: 5px;
+        }
+         .group-heading:hover {
+            background-color: #f8f9fa!important;
+        }
+        .table .error-cell{
+            word-break: break-word;
+        }
+    </style>
+</head>
+<body>
+    `)
+//line app/vmalert/tpl/header.qtpl:41
+	StreamPrintNavItems(qw422016, title, pages)
+//line app/vmalert/tpl/header.qtpl:41
+	qw422016.N().S(`
+    <main class="px-2">
+`)
+//line app/vmalert/tpl/header.qtpl:43
+}
+
+//line app/vmalert/tpl/header.qtpl:43
+func WriteHeader(qq422016 qtio422016.Writer, title string, pages []NavItem) {
+//line app/vmalert/tpl/header.qtpl:43
+	qw422016 := qt422016.AcquireWriter(qq422016)
+//line app/vmalert/tpl/header.qtpl:43
+	StreamHeader(qw422016, title, pages)
+//line app/vmalert/tpl/header.qtpl:43
+	qt422016.ReleaseWriter(qw422016)
+//line app/vmalert/tpl/header.qtpl:43
+}
+
+//line app/vmalert/tpl/header.qtpl:43
+func Header(title string, pages []NavItem) string {
+//line app/vmalert/tpl/header.qtpl:43
+	qb422016 := qt422016.AcquireByteBuffer()
+//line app/vmalert/tpl/header.qtpl:43
+	WriteHeader(qb422016, title, pages)
+//line app/vmalert/tpl/header.qtpl:43
+	qs422016 := string(qb422016.B)
+//line app/vmalert/tpl/header.qtpl:43
+	qt422016.ReleaseByteBuffer(qb422016)
+//line app/vmalert/tpl/header.qtpl:43
+	return qs422016
+//line app/vmalert/tpl/header.qtpl:43
+}

app/vmalert/tpl/nav.qtpl

@@ -0,0 +1,25 @@
+{% code
+type NavItem struct {
+	Name string
+	Url  string
+}
+%}
+
+{% func PrintNavItems(current string, items []NavItem) %}
+<nav class="navbar navbar-expand-md navbar-dark fixed-top bg-dark">
+  <div class="container-fluid">
+    <div class="collapse navbar-collapse" id="navbarCollapse">
+        <ul class="navbar-nav me-auto mb-2 mb-md-0">
+            {% for _, item := range items  %}
+                <li class="nav-item">
+                    <a class="nav-link{% if current == item.Name %} active{% endif %}" href="{%s item.Url %}">
+                        {%s item.Name %}
+                    </a>
+                </li>
+            {% endfor %}
+        </ul>
+  </div>
+</nav>
+{% endfunc %}
+
+

app/vmalert/tpl/nav.qtpl.go

@@ -0,0 +1,96 @@
+// Code generated by qtc from "nav.qtpl". DO NOT EDIT.
+// See https://github.com/valyala/quicktemplate for details.
+
+//line app/vmalert/tpl/nav.qtpl:1
+package tpl
+
+//line app/vmalert/tpl/nav.qtpl:1
+import (
+	qtio422016 "io"
+
+	qt422016 "github.com/valyala/quicktemplate"
+)
+
+//line app/vmalert/tpl/nav.qtpl:1
+var (
+	_ = qtio422016.Copy
+	_ = qt422016.AcquireByteBuffer
+)
+
+//line app/vmalert/tpl/nav.qtpl:2
+type NavItem struct {
+	Name string
+	Url  string
+}
+
+//line app/vmalert/tpl/nav.qtpl:8
+func StreamPrintNavItems(qw422016 *qt422016.Writer, current string, items []NavItem) {
+//line app/vmalert/tpl/nav.qtpl:8
+	qw422016.N().S(`
+<nav class="navbar navbar-expand-md navbar-dark fixed-top bg-dark">
+  <div class="container-fluid">
+    <div class="collapse navbar-collapse" id="navbarCollapse">
+        <ul class="navbar-nav me-auto mb-2 mb-md-0">
+            `)
+//line app/vmalert/tpl/nav.qtpl:13
+	for _, item := range items {
+//line app/vmalert/tpl/nav.qtpl:13
+		qw422016.N().S(`
+                <li class="nav-item">
+                    <a class="nav-link`)
+//line app/vmalert/tpl/nav.qtpl:15
+		if current == item.Name {
+//line app/vmalert/tpl/nav.qtpl:15
+			qw422016.N().S(` active`)
+//line app/vmalert/tpl/nav.qtpl:15
+		}
+//line app/vmalert/tpl/nav.qtpl:15
+		qw422016.N().S(`" href="`)
+//line app/vmalert/tpl/nav.qtpl:15
+		qw422016.E().S(item.Url)
+//line app/vmalert/tpl/nav.qtpl:15
+		qw422016.N().S(`">
+                        `)
+//line app/vmalert/tpl/nav.qtpl:16
+		qw422016.E().S(item.Name)
+//line app/vmalert/tpl/nav.qtpl:16
+		qw422016.N().S(`
+                    </a>
+                </li>
+            `)
+//line app/vmalert/tpl/nav.qtpl:19
+	}
+//line app/vmalert/tpl/nav.qtpl:19
+	qw422016.N().S(`
+        </ul>
+  </div>
+</nav>
+`)
+//line app/vmalert/tpl/nav.qtpl:23
+}
+
+//line app/vmalert/tpl/nav.qtpl:23
+func WritePrintNavItems(qq422016 qtio422016.Writer, current string, items []NavItem) {
+//line app/vmalert/tpl/nav.qtpl:23
+	qw422016 := qt422016.AcquireWriter(qq422016)
+//line app/vmalert/tpl/nav.qtpl:23
+	StreamPrintNavItems(qw422016, current, items)
+//line app/vmalert/tpl/nav.qtpl:23
+	qt422016.ReleaseWriter(qw422016)
+//line app/vmalert/tpl/nav.qtpl:23
+}
+
+//line app/vmalert/tpl/nav.qtpl:23
+func PrintNavItems(current string, items []NavItem) string {
+//line app/vmalert/tpl/nav.qtpl:23
+	qb422016 := qt422016.AcquireByteBuffer()
+//line app/vmalert/tpl/nav.qtpl:23
+	WritePrintNavItems(qb422016, current, items)
+//line app/vmalert/tpl/nav.qtpl:23
+	qs422016 := string(qb422016.B)
+//line app/vmalert/tpl/nav.qtpl:23
+	qt422016.ReleaseByteBuffer(qb422016)
+//line app/vmalert/tpl/nav.qtpl:23
+	return qs422016
+//line app/vmalert/tpl/nav.qtpl:23
+}

app/vmalert/utils.go

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

app/vmalert/utils/auth.go

@@ -0,0 +1,18 @@
+package utils
+
+import (
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promauth"
+)
+
+// AuthConfig returns promauth.Config based on the given params
+func AuthConfig(baUser, baPass, baFile, bearerToken, bearerTokenFile string) (*promauth.Config, error) {
+	var baCfg *promauth.BasicAuthConfig
+	if baUser != "" || baPass != "" || baFile != "" {
+		baCfg = &promauth.BasicAuthConfig{
+			Username:     baUser,
+			Password:     baPass,
+			PasswordFile: baFile,
+		}
+	}
+	return promauth.NewConfig(".", nil, baCfg, bearerToken, bearerTokenFile, nil, nil)
+}

app/vmalert/utils/prom_duration.go

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

app/vmalert/utils/tls_test.go

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

app/vmalert/web.go

@@ -4,40 +4,67 @@ import (
 	"encoding/json"
 	"fmt"
 	"net/http"
+	"path"
 	"sort"
 	"strconv"
 	"strings"
+	"sync"
 
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/tpl"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/procutil"
 )
 
+var (
+	once     = sync.Once{}
+	apiLinks [][2]string
+	navItems []tpl.NavItem
+)
+
+func initLinks() {
+	pathPrefix := httpserver.GetPathPrefix()
+	apiLinks = [][2]string{
+		{path.Join(pathPrefix, "api/v1/groups"), "list all loaded groups and rules"},
+		{path.Join(pathPrefix, "api/v1/alerts"), "list all active alerts"},
+		{path.Join(pathPrefix, "api/v1/groupID/alertID/status"), "get alert status by ID"},
+		{path.Join(pathPrefix, "metrics"), "list of application metrics"},
+		{path.Join(pathPrefix, "-/reload"), "reload configuration"},
+	}
+	navItems = []tpl.NavItem{
+		{Name: "vmalert", Url: path.Join(pathPrefix, "/")},
+		{Name: "Groups", Url: path.Join(pathPrefix, "groups")},
+		{Name: "Alerts", Url: path.Join(pathPrefix, "/alerts")},
+		{Name: "Docs", Url: "https://docs.victoriametrics.com/vmalert.html"},
+	}
+}
+
 type requestHandler struct {
 	m *manager
 }
 
-var pathList = [][]string{
-	{"/api/v1/groups", "list all loaded groups and rules"},
-	{"/api/v1/alerts", "list all active alerts"},
-	{"/api/v1/groupID/alertID/status", "get alert status by ID"},
-	// /metrics is served by httpserver by default
-	{"/metrics", "list of application metrics"},
-	{"/-/reload", "reload configuration"},
-}
-
 func (rh *requestHandler) handler(w http.ResponseWriter, r *http.Request) bool {
+	once.Do(func() {
+		initLinks()
+	})
+
 	switch r.URL.Path {
 	case "/":
-		for _, path := range pathList {
-			p, doc := path[0], path[1]
-			fmt.Fprintf(w, "<a href='%s'>%q</a> - %s<br/>", p, p, doc)
+		if r.Method != "GET" {
+			return false
 		}
+		WriteWelcome(w)
+		return true
+	case "/alerts":
+		WriteListAlerts(w, rh.groupAlerts())
+		return true
+	case "/groups":
+		WriteListGroups(w, rh.groups())
 		return true
 	case "/api/v1/groups":
 		data, err := rh.listGroups()
 		if err != nil {
-			httpserver.Errorf(w, r, "error in %q: %s", r.URL.Path, err)
+			httpserver.Errorf(w, r, "%s", err)
 			return true
 		}
 		w.Header().Set("Content-Type", "application/json; charset=utf-8")
@@ -46,7 +73,7 @@ func (rh *requestHandler) handler(w http.ResponseWriter, r *http.Request) bool {
 	case "/api/v1/alerts":
 		data, err := rh.listAlerts()
 		if err != nil {
-			httpserver.Errorf(w, r, "error in %q: %s", r.URL.Path, err)
+			httpserver.Errorf(w, r, "%s", err)
 			return true
 		}
 		w.Header().Set("Content-Type", "application/json; charset=utf-8")
@@ -61,14 +88,26 @@ func (rh *requestHandler) handler(w http.ResponseWriter, r *http.Request) bool {
 		if !strings.HasSuffix(r.URL.Path, "/status") {
 			return false
 		}
-		// /api/v1/<groupName>/<alertID>/status
-		data, err := rh.alert(r.URL.Path)
+		alert, err := rh.alertByPath(strings.TrimPrefix(r.URL.Path, "/api/v1/"))
 		if err != nil {
-			httpserver.Errorf(w, r, "error in %q: %s", r.URL.Path, err)
+			httpserver.Errorf(w, r, "%s", err)
 			return true
 		}
-		w.Header().Set("Content-Type", "application/json; charset=utf-8")
-		w.Write(data)
+
+		// /api/v1/<groupID>/<alertID>/status
+		if strings.HasPrefix(r.URL.Path, "/api/v1/") {
+			data, err := json.Marshal(alert)
+			if err != nil {
+				httpserver.Errorf(w, r, "failed to marshal alert: %s", err)
+				return true
+			}
+			w.Header().Set("Content-Type", "application/json; charset=utf-8")
+			w.Write(data)
+			return true
+		}
+
+		// <groupID>/<alertID>/status
+		WriteAlert(w, alert)
 		return true
 	}
 }
@@ -80,20 +119,25 @@ type listGroupsResponse struct {
 	Status string `json:"status"`
 }
 
-func (rh *requestHandler) listGroups() ([]byte, error) {
+func (rh *requestHandler) groups() []APIGroup {
 	rh.m.groupsMu.RLock()
 	defer rh.m.groupsMu.RUnlock()
 
-	lr := listGroupsResponse{Status: "success"}
+	var groups []APIGroup
 	for _, g := range rh.m.groups {
-		lr.Data.Groups = append(lr.Data.Groups, g.toAPI())
+		groups = append(groups, g.toAPI())
 	}
 
 	// sort list of alerts for deterministic output
-	sort.Slice(lr.Data.Groups, func(i, j int) bool {
-		return lr.Data.Groups[i].Name < lr.Data.Groups[j].Name
+	sort.Slice(groups, func(i, j int) bool {
+		return groups[i].Name < groups[j].Name
 	})
 
+	return groups
+}
+func (rh *requestHandler) listGroups() ([]byte, error) {
+	lr := listGroupsResponse{Status: "success"}
+	lr.Data.Groups = rh.groups()
 	b, err := json.Marshal(lr)
 	if err != nil {
 		return nil, &httpserver.ErrorWithStatusCode{
@@ -111,6 +155,30 @@ type listAlertsResponse struct {
 	Status string `json:"status"`
 }
 
+func (rh *requestHandler) groupAlerts() []GroupAlerts {
+	rh.m.groupsMu.RLock()
+	defer rh.m.groupsMu.RUnlock()
+
+	var groupAlerts []GroupAlerts
+	for _, g := range rh.m.groups {
+		var alerts []*APIAlert
+		for _, r := range g.Rules {
+			a, ok := r.(*AlertingRule)
+			if !ok {
+				continue
+			}
+			alerts = append(alerts, a.AlertsAPI()...)
+		}
+		if len(alerts) > 0 {
+			groupAlerts = append(groupAlerts, GroupAlerts{
+				Group:  g.toAPI(),
+				Alerts: alerts,
+			})
+		}
+	}
+	return groupAlerts
+}
+
 func (rh *requestHandler) listAlerts() ([]byte, error) {
 	rh.m.groupsMu.RLock()
 	defer rh.m.groupsMu.RUnlock()
@@ -141,18 +209,17 @@ func (rh *requestHandler) listAlerts() ([]byte, error) {
 	return b, nil
 }
 
-func (rh *requestHandler) alert(path string) ([]byte, error) {
+func (rh *requestHandler) alertByPath(path string) (*APIAlert, error) {
 	rh.m.groupsMu.RLock()
 	defer rh.m.groupsMu.RUnlock()
 
-	parts := strings.SplitN(strings.TrimPrefix(path, "/api/v1/"), "/", 3)
+	parts := strings.SplitN(strings.TrimLeft(path, "/"), "/", 3)
 	if len(parts) != 3 {
 		return nil, &httpserver.ErrorWithStatusCode{
-			Err:        fmt.Errorf(`path %q cointains /status suffix but doesn't match pattern "/group/alert/status"`, path),
+			Err:        fmt.Errorf(`path %q cointains /status suffix but doesn't match pattern "/groupID/alertID/status"`, path),
 			StatusCode: http.StatusBadRequest,
 		}
 	}
-
 	groupID, err := uint64FromPath(parts[0])
 	if err != nil {
 		return nil, badRequest(fmt.Errorf(`cannot parse groupID: %w`, err))
@@ -165,7 +232,7 @@ func (rh *requestHandler) alert(path string) ([]byte, error) {
 	if err != nil {
 		return nil, errResponse(err, http.StatusNotFound)
 	}
-	return json.Marshal(resp)
+	return resp, nil
 }
 
 func uint64FromPath(path string) (uint64, error) {

app/vmalert/web.qtpl

@@ -0,0 +1,276 @@
+{% package main %}
+
+{% import (
+    "time"
+    "sort"
+
+    "github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/tpl"
+) %}
+
+
+{% func Welcome() %}
+    {%= tpl.Header("vmalert", navItems) %}
+    <p>
+        API:<br>
+        {% for _, p := range apiLinks  %}
+            {%code
+                p, doc := p[0], p[1]
+            %}
+        	<a href="{%s p %}">{%s p %}</a> - {%s doc %}<br/>
+        {% endfor %}
+    </p>
+    {%= tpl.Footer() %}
+{% endfunc %}
+
+{% func ListGroups(groups []APIGroup) %}
+    {%= tpl.Header("Groups", navItems) %}
+    {%  if len(groups) > 0 %}
+        {%code
+            rOk := make(map[string]int)
+            rNotOk := make(map[string]int)
+            for _, g := range groups {
+                for _, r := range g.AlertingRules{
+                    if r.LastError != "" {
+                        rNotOk[g.Name]++
+                    } else {
+                        rOk[g.Name]++
+                    }
+                }
+                 for _, r := range g.RecordingRules{
+                    if r.LastError != "" {
+                        rNotOk[g.Name]++
+                    } else {
+                        rOk[g.Name]++
+                    }
+                }
+            }
+        %}
+         <a class="btn btn-primary" role="button" onclick="collapseAll()">Collapse All</a>
+         <a class="btn btn-primary" role="button" onclick="expandAll()">Expand All</a>
+        {% for _, g := range groups  %}
+              <div class="group-heading{% if rNotOk[g.Name] > 0 %} alert-danger{% endif %}"  data-bs-target="rules-{%s g.ID %}">
+                <span class="anchor" id="group-{%s g.ID %}"></span>
+                <a href="#group-{%s g.ID %}">{%s g.Name %}{% if g.Type != "prometheus" %} ({%s g.Type %}){% endif %} (every {%s g.Interval %})</a>
+                 {% if rNotOk[g.Name] > 0 %}<span class="badge bg-danger" title="Number of rules withs status Error">{%d rNotOk[g.Name] %}</span> {% endif %}
+                <span class="badge bg-success" title="Number of rules withs status Ok">{%d rOk[g.Name] %}</span>
+                <p class="fs-6 fw-lighter">{%s g.File %}</p>
+                {% if len(g.ExtraFilterLabels) > 0 %}
+                    <div class="fs-6 fw-lighter">Extra filter labels
+                    {% for k, v := range g.ExtraFilterLabels %}
+                            <span class="float-left badge bg-primary">{%s k %}={%s v %}</span>
+                    {% endfor %}
+                    </div>
+                {% endif %}
+            </div>
+            <div class="collapse" id="rules-{%s g.ID %}">
+                <table class="table table-striped table-hover table-sm">
+                    <thead>
+                        <tr>
+                            <th scope="col">Rule</th>
+                            <th scope="col" title="Shows if rule's execution ended with error">Error</th>
+                            <th scope="col" title="How many samples were produced by the rule">Samples</th>
+                            <th scope="col" title="How many seconds ago rule was executed">Updated</th>
+                        </tr>
+                    </thead>
+                    <tbody>
+                    {% for _, ar := range g.AlertingRules %}
+                        <tr{% if ar.LastError != "" %} class="alert-danger"{% endif %}>
+                            <td>
+                                <b>alert:</b> {%s ar.Name %} (for: {%v ar.For %})<br>
+                                <code><pre>{%s ar.Expression %}</pre></code><br>
+                                {% if len(ar.Labels) > 0 %} <b>Labels:</b>{% endif %}
+                                {% for k, v := range ar.Labels %}
+                                        <span class="ms-1 badge bg-primary">{%s k %}={%s v %}</span>
+                                {% endfor %}
+                            </td>
+                            <td><div class="error-cell">{%s ar.LastError %}</div></td>
+                            <td>{%d ar.LastSamples %}</td>
+                            <td>{%f.3 time.Since(ar.LastExec).Seconds() %}s ago</td>
+                        </tr>
+                    {% endfor %}
+                    {% for _, rr := range g.RecordingRules  %}
+                        <tr>
+                            <td>
+                                <b>record:</b> {%s rr.Name %}<br>
+                                <code><pre>{%s rr.Expression %}</pre></code>
+                                {% if len(rr.Labels) > 0 %} <b>Labels:</b>{% endif %}
+                                {% for k, v := range rr.Labels %}
+                                        <span class="ms-1 badge bg-primary">{%s k %}={%s v %}</span>
+                                {% endfor %}
+                            </td>
+                            <td><div class="error-cell">{%s rr.LastError %}</div></td>
+                            <td>{%d rr.LastSamples %}</td>
+                            <td>{%f.3 time.Since(rr.LastExec).Seconds() %}s ago</td>
+                        </tr>
+                    {% endfor %}
+                 </tbody>
+                </table>
+            </div>
+        {% endfor %}
+
+    {% else %}
+        <div>
+            <p>No items...</p>
+        </div>
+    {% endif %}
+
+    {%= tpl.Footer() %}
+
+{% endfunc %}
+
+
+{% func ListAlerts(groupAlerts []GroupAlerts) %}
+    {%= tpl.Header("Alerts", navItems) %}
+    {% if len(groupAlerts) > 0 %}
+         <a class="btn btn-primary" role="button" onclick="collapseAll()">Collapse All</a>
+         <a class="btn btn-primary" role="button" onclick="expandAll()">Expand All</a>
+         {% for _, ga := range groupAlerts %}
+            {%code g := ga.Group %}
+            <div class="group-heading alert-danger" data-bs-target="rules-{%s g.ID %}">
+                <span class="anchor" id="group-{%s g.ID %}"></span>
+                <a href="#group-{%s g.ID %}">{%s g.Name %}{% if g.Type != "prometheus" %} ({%s g.Type %}){% endif %}</a>
+                <span class="badge bg-danger" title="Number of active alerts">{%d len(ga.Alerts) %}</span>
+                <br>
+                <p class="fs-6 fw-lighter">{%s g.File %}</p>
+            </div>
+            {%code
+                var keys []string
+                alertsByRule := make(map[string][]*APIAlert)
+                for _, alert := range ga.Alerts {
+                    if len(alertsByRule[alert.RuleID]) < 1 {
+                        keys = append(keys, alert.RuleID)
+                    }
+                    alertsByRule[alert.RuleID] = append(alertsByRule[alert.RuleID], alert)
+                }
+                sort.Strings(keys)
+            %}
+            <div class="collapse" id="rules-{%s g.ID %}">
+                {% for _, ruleID := range keys %}
+                    {%code
+                        defaultAR := alertsByRule[ruleID][0]
+                        var labelKeys []string
+                        for k := range defaultAR.Labels {
+                            labelKeys = append(labelKeys, k)
+                        }
+                        sort.Strings(labelKeys)
+                    %}
+                    <br>
+                    <b>alert:</b> {%s defaultAR.Name %} ({%d len(alertsByRule[ruleID]) %})<br>
+                    <b>expr:</b><code><pre>{%s defaultAR.Expression %}</pre></code>
+                    <table class="table table-striped table-hover table-sm">
+                        <thead>
+                            <tr>
+                                <th scope="col">Labels</th>
+                                <th scope="col">State</th>
+                                <th scope="col">Active at</th>
+                                <th scope="col">Value</th>
+                                <th scope="col">Link</th>
+                            </tr>
+                        </thead>
+                        <tbody>
+                        {% for _, ar := range alertsByRule[ruleID] %}
+                            <tr>
+                                <td>
+                                    {% for _, k := range labelKeys %}
+                                        <span class="ms-1 badge bg-primary">{%s k %}={%s ar.Labels[k] %}</span>
+                                    {% endfor %}
+                                </td>
+                                <td><span class="badge {% if ar.State=="firing" %}bg-danger{% else %} bg-warning text-dark{% endif %}">{%s ar.State %}</span></td>
+                                <td>{%s ar.ActiveAt.Format("2006-01-02T15:04:05Z07:00") %}</td>
+                                <td>{%s ar.Value %}</td>
+                                <td>
+                                    <a href="/{%s g.ID %}/{%s ar.ID %}/status">Details</a>
+                                </td>
+                            </tr>
+                        {% endfor %}
+                     </tbody>
+                    </table>
+                {% endfor %}
+            </div>
+            <br>
+        {% endfor %}
+
+    {% else %}
+        <div>
+            <p>No items...</p>
+        </div>
+    {% endif %}
+
+    {%= tpl.Footer() %}
+
+{% endfunc %}
+
+{% func Alert(alert *APIAlert) %}
+    {%= tpl.Header("", navItems) %}
+    {%code
+        var labelKeys []string
+        for k := range alert.Labels {
+            labelKeys = append(labelKeys, k)
+        }
+        sort.Strings(labelKeys)
+
+        var annotationKeys []string
+        for k := range alert.Annotations {
+            annotationKeys = append(annotationKeys, k)
+        }
+        sort.Strings(annotationKeys)
+    %}
+    <div class="display-6 pb-3 mb-3">{%s alert.Name %}<span class="ms-2 badge {% if alert.State=="firing" %}bg-danger{% else %} bg-warning text-dark{% endif %}">{%s alert.State %}</span></div>
+    <div class="container border-bottom p-2">
+      <div class="row">
+        <div class="col-2">
+          Active at
+        </div>
+        <div class="col">
+          {%s alert.ActiveAt.Format("2006-01-02T15:04:05Z07:00") %}
+        </div>
+      </div>
+      </div>
+    <div class="container border-bottom p-2">
+      <div class="row">
+        <div class="col-2">
+          Expr
+        </div>
+        <div class="col">
+          <code><pre>{%s alert.Expression %}</pre></code>
+        </div>
+      </div>
+    </div>
+    <div class="container border-bottom p-2">
+      <div class="row">
+        <div class="col-2">
+          Labels
+        </div>
+        <div class="col">
+           {% for _, k := range labelKeys %}
+                <span class="m-1 badge bg-primary">{%s k %}={%s alert.Labels[k] %}</span>
+          {% endfor %}
+        </div>
+      </div>
+    </div>
+    <div class="container border-bottom p-2">
+      <div class="row">
+        <div class="col-2">
+          Annotations
+        </div>
+        <div class="col">
+           {% for _, k := range annotationKeys %}
+                <b>{%s k %}:</b><br>
+                <p>{%s alert.Annotations[k] %}</p>
+          {% endfor %}
+        </div>
+      </div>
+    </div>
+    <div class="container border-bottom p-2">
+      <div class="row">
+        <div class="col-2">
+          Group
+        </div>
+        <div class="col">
+           <a target="_blank" href="/groups#group-{%s alert.GroupID %}">{%s alert.GroupID %}</a>
+        </div>
+      </div>
+    </div>
+    {%= tpl.Footer() %}
+
+{% endfunc %}

app/vmalert/web.qtpl.go

@@ -0,0 +1,912 @@
+// Code generated by qtc from "web.qtpl". DO NOT EDIT.
+// See https://github.com/valyala/quicktemplate for details.
+
+//line app/vmalert/web.qtpl:1
+package main
+
+//line app/vmalert/web.qtpl:3
+import (
+	"sort"
+	"time"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/tpl"
+)
+
+//line app/vmalert/web.qtpl:11
+import (
+	qtio422016 "io"
+
+	qt422016 "github.com/valyala/quicktemplate"
+)
+
+//line app/vmalert/web.qtpl:11
+var (
+	_ = qtio422016.Copy
+	_ = qt422016.AcquireByteBuffer
+)
+
+//line app/vmalert/web.qtpl:11
+func StreamWelcome(qw422016 *qt422016.Writer) {
+//line app/vmalert/web.qtpl:11
+	qw422016.N().S(`
+    `)
+//line app/vmalert/web.qtpl:12
+	tpl.StreamHeader(qw422016, "vmalert", navItems)
+//line app/vmalert/web.qtpl:12
+	qw422016.N().S(`
+    <p>
+        API:<br>
+        `)
+//line app/vmalert/web.qtpl:15
+	for _, p := range apiLinks {
+//line app/vmalert/web.qtpl:15
+		qw422016.N().S(`
+            `)
+//line app/vmalert/web.qtpl:17
+		p, doc := p[0], p[1]
+
+//line app/vmalert/web.qtpl:18
+		qw422016.N().S(`
+        	<a href="`)
+//line app/vmalert/web.qtpl:19
+		qw422016.E().S(p)
+//line app/vmalert/web.qtpl:19
+		qw422016.N().S(`">`)
+//line app/vmalert/web.qtpl:19
+		qw422016.E().S(p)
+//line app/vmalert/web.qtpl:19
+		qw422016.N().S(`</a> - `)
+//line app/vmalert/web.qtpl:19
+		qw422016.E().S(doc)
+//line app/vmalert/web.qtpl:19
+		qw422016.N().S(`<br/>
+        `)
+//line app/vmalert/web.qtpl:20
+	}
+//line app/vmalert/web.qtpl:20
+	qw422016.N().S(`
+    </p>
+    `)
+//line app/vmalert/web.qtpl:22
+	tpl.StreamFooter(qw422016)
+//line app/vmalert/web.qtpl:22
+	qw422016.N().S(`
+`)
+//line app/vmalert/web.qtpl:23
+}
+
+//line app/vmalert/web.qtpl:23
+func WriteWelcome(qq422016 qtio422016.Writer) {
+//line app/vmalert/web.qtpl:23
+	qw422016 := qt422016.AcquireWriter(qq422016)
+//line app/vmalert/web.qtpl:23
+	StreamWelcome(qw422016)
+//line app/vmalert/web.qtpl:23
+	qt422016.ReleaseWriter(qw422016)
+//line app/vmalert/web.qtpl:23
+}
+
+//line app/vmalert/web.qtpl:23
+func Welcome() string {
+//line app/vmalert/web.qtpl:23
+	qb422016 := qt422016.AcquireByteBuffer()
+//line app/vmalert/web.qtpl:23
+	WriteWelcome(qb422016)
+//line app/vmalert/web.qtpl:23
+	qs422016 := string(qb422016.B)
+//line app/vmalert/web.qtpl:23
+	qt422016.ReleaseByteBuffer(qb422016)
+//line app/vmalert/web.qtpl:23
+	return qs422016
+//line app/vmalert/web.qtpl:23
+}
+
+//line app/vmalert/web.qtpl:25
+func StreamListGroups(qw422016 *qt422016.Writer, groups []APIGroup) {
+//line app/vmalert/web.qtpl:25
+	qw422016.N().S(`
+    `)
+//line app/vmalert/web.qtpl:26
+	tpl.StreamHeader(qw422016, "Groups", navItems)
+//line app/vmalert/web.qtpl:26
+	qw422016.N().S(`
+    `)
+//line app/vmalert/web.qtpl:27
+	if len(groups) > 0 {
+//line app/vmalert/web.qtpl:27
+		qw422016.N().S(`
+        `)
+//line app/vmalert/web.qtpl:29
+		rOk := make(map[string]int)
+		rNotOk := make(map[string]int)
+		for _, g := range groups {
+			for _, r := range g.AlertingRules {
+				if r.LastError != "" {
+					rNotOk[g.Name]++
+				} else {
+					rOk[g.Name]++
+				}
+			}
+			for _, r := range g.RecordingRules {
+				if r.LastError != "" {
+					rNotOk[g.Name]++
+				} else {
+					rOk[g.Name]++
+				}
+			}
+		}
+
+//line app/vmalert/web.qtpl:47
+		qw422016.N().S(`
+         <a class="btn btn-primary" role="button" onclick="collapseAll()">Collapse All</a>
+         <a class="btn btn-primary" role="button" onclick="expandAll()">Expand All</a>
+        `)
+//line app/vmalert/web.qtpl:50
+		for _, g := range groups {
+//line app/vmalert/web.qtpl:50
+			qw422016.N().S(`
+              <div class="group-heading`)
+//line app/vmalert/web.qtpl:51
+			if rNotOk[g.Name] > 0 {
+//line app/vmalert/web.qtpl:51
+				qw422016.N().S(` alert-danger`)
+//line app/vmalert/web.qtpl:51
+			}
+//line app/vmalert/web.qtpl:51
+			qw422016.N().S(`"  data-bs-target="rules-`)
+//line app/vmalert/web.qtpl:51
+			qw422016.E().S(g.ID)
+//line app/vmalert/web.qtpl:51
+			qw422016.N().S(`">
+                <span class="anchor" id="group-`)
+//line app/vmalert/web.qtpl:52
+			qw422016.E().S(g.ID)
+//line app/vmalert/web.qtpl:52
+			qw422016.N().S(`"></span>
+                <a href="#group-`)
+//line app/vmalert/web.qtpl:53
+			qw422016.E().S(g.ID)
+//line app/vmalert/web.qtpl:53
+			qw422016.N().S(`">`)
+//line app/vmalert/web.qtpl:53
+			qw422016.E().S(g.Name)
+//line app/vmalert/web.qtpl:53
+			if g.Type != "prometheus" {
+//line app/vmalert/web.qtpl:53
+				qw422016.N().S(` (`)
+//line app/vmalert/web.qtpl:53
+				qw422016.E().S(g.Type)
+//line app/vmalert/web.qtpl:53
+				qw422016.N().S(`)`)
+//line app/vmalert/web.qtpl:53
+			}
+//line app/vmalert/web.qtpl:53
+			qw422016.N().S(` (every `)
+//line app/vmalert/web.qtpl:53
+			qw422016.E().S(g.Interval)
+//line app/vmalert/web.qtpl:53
+			qw422016.N().S(`)</a>
+                 `)
+//line app/vmalert/web.qtpl:54
+			if rNotOk[g.Name] > 0 {
+//line app/vmalert/web.qtpl:54
+				qw422016.N().S(`<span class="badge bg-danger" title="Number of rules withs status Error">`)
+//line app/vmalert/web.qtpl:54
+				qw422016.N().D(rNotOk[g.Name])
+//line app/vmalert/web.qtpl:54
+				qw422016.N().S(`</span> `)
+//line app/vmalert/web.qtpl:54
+			}
+//line app/vmalert/web.qtpl:54
+			qw422016.N().S(`
+                <span class="badge bg-success" title="Number of rules withs status Ok">`)
+//line app/vmalert/web.qtpl:55
+			qw422016.N().D(rOk[g.Name])
+//line app/vmalert/web.qtpl:55
+			qw422016.N().S(`</span>
+                <p class="fs-6 fw-lighter">`)
+//line app/vmalert/web.qtpl:56
+			qw422016.E().S(g.File)
+//line app/vmalert/web.qtpl:56
+			qw422016.N().S(`</p>
+                `)
+//line app/vmalert/web.qtpl:57
+			if len(g.ExtraFilterLabels) > 0 {
+//line app/vmalert/web.qtpl:57
+				qw422016.N().S(`
+                    <div class="fs-6 fw-lighter">Extra filter labels
+                    `)
+//line app/vmalert/web.qtpl:59
+				for k, v := range g.ExtraFilterLabels {
+//line app/vmalert/web.qtpl:59
+					qw422016.N().S(`
+                            <span class="float-left badge bg-primary">`)
+//line app/vmalert/web.qtpl:60
+					qw422016.E().S(k)
+//line app/vmalert/web.qtpl:60
+					qw422016.N().S(`=`)
+//line app/vmalert/web.qtpl:60
+					qw422016.E().S(v)
+//line app/vmalert/web.qtpl:60
+					qw422016.N().S(`</span>
+                    `)
+//line app/vmalert/web.qtpl:61
+				}
+//line app/vmalert/web.qtpl:61
+				qw422016.N().S(`
+                    </div>
+                `)
+//line app/vmalert/web.qtpl:63
+			}
+//line app/vmalert/web.qtpl:63
+			qw422016.N().S(`
+            </div>
+            <div class="collapse" id="rules-`)
+//line app/vmalert/web.qtpl:65
+			qw422016.E().S(g.ID)
+//line app/vmalert/web.qtpl:65
+			qw422016.N().S(`">
+                <table class="table table-striped table-hover table-sm">
+                    <thead>
+                        <tr>
+                            <th scope="col">Rule</th>
+                            <th scope="col" title="Shows if rule's execution ended with error">Error</th>
+                            <th scope="col" title="How many samples were produced by the rule">Samples</th>
+                            <th scope="col" title="How many seconds ago rule was executed">Updated</th>
+                        </tr>
+                    </thead>
+                    <tbody>
+                    `)
+//line app/vmalert/web.qtpl:76
+			for _, ar := range g.AlertingRules {
+//line app/vmalert/web.qtpl:76
+				qw422016.N().S(`
+                        <tr`)
+//line app/vmalert/web.qtpl:77
+				if ar.LastError != "" {
+//line app/vmalert/web.qtpl:77
+					qw422016.N().S(` class="alert-danger"`)
+//line app/vmalert/web.qtpl:77
+				}
+//line app/vmalert/web.qtpl:77
+				qw422016.N().S(`>
+                            <td>
+                                <b>alert:</b> `)
+//line app/vmalert/web.qtpl:79
+				qw422016.E().S(ar.Name)
+//line app/vmalert/web.qtpl:79
+				qw422016.N().S(` (for: `)
+//line app/vmalert/web.qtpl:79
+				qw422016.E().V(ar.For)
+//line app/vmalert/web.qtpl:79
+				qw422016.N().S(`)<br>
+                                <code><pre>`)
+//line app/vmalert/web.qtpl:80
+				qw422016.E().S(ar.Expression)
+//line app/vmalert/web.qtpl:80
+				qw422016.N().S(`</pre></code><br>
+                                `)
+//line app/vmalert/web.qtpl:81
+				if len(ar.Labels) > 0 {
+//line app/vmalert/web.qtpl:81
+					qw422016.N().S(` <b>Labels:</b>`)
+//line app/vmalert/web.qtpl:81
+				}
+//line app/vmalert/web.qtpl:81
+				qw422016.N().S(`
+                                `)
+//line app/vmalert/web.qtpl:82
+				for k, v := range ar.Labels {
+//line app/vmalert/web.qtpl:82
+					qw422016.N().S(`
+                                        <span class="ms-1 badge bg-primary">`)
+//line app/vmalert/web.qtpl:83
+					qw422016.E().S(k)
+//line app/vmalert/web.qtpl:83
+					qw422016.N().S(`=`)
+//line app/vmalert/web.qtpl:83
+					qw422016.E().S(v)
+//line app/vmalert/web.qtpl:83
+					qw422016.N().S(`</span>
+                                `)
+//line app/vmalert/web.qtpl:84
+				}
+//line app/vmalert/web.qtpl:84
+				qw422016.N().S(`
+                            </td>
+                            <td><div class="error-cell">`)
+//line app/vmalert/web.qtpl:86
+				qw422016.E().S(ar.LastError)
+//line app/vmalert/web.qtpl:86
+				qw422016.N().S(`</div></td>
+                            <td>`)
+//line app/vmalert/web.qtpl:87
+				qw422016.N().D(ar.LastSamples)
+//line app/vmalert/web.qtpl:87
+				qw422016.N().S(`</td>
+                            <td>`)
+//line app/vmalert/web.qtpl:88
+				qw422016.N().FPrec(time.Since(ar.LastExec).Seconds(), 3)
+//line app/vmalert/web.qtpl:88
+				qw422016.N().S(`s ago</td>
+                        </tr>
+                    `)
+//line app/vmalert/web.qtpl:90
+			}
+//line app/vmalert/web.qtpl:90
+			qw422016.N().S(`
+                    `)
+//line app/vmalert/web.qtpl:91
+			for _, rr := range g.RecordingRules {
+//line app/vmalert/web.qtpl:91
+				qw422016.N().S(`
+                        <tr>
+                            <td>
+                                <b>record:</b> `)
+//line app/vmalert/web.qtpl:94
+				qw422016.E().S(rr.Name)
+//line app/vmalert/web.qtpl:94
+				qw422016.N().S(`<br>
+                                <code><pre>`)
+//line app/vmalert/web.qtpl:95
+				qw422016.E().S(rr.Expression)
+//line app/vmalert/web.qtpl:95
+				qw422016.N().S(`</pre></code>
+                                `)
+//line app/vmalert/web.qtpl:96
+				if len(rr.Labels) > 0 {
+//line app/vmalert/web.qtpl:96
+					qw422016.N().S(` <b>Labels:</b>`)
+//line app/vmalert/web.qtpl:96
+				}
+//line app/vmalert/web.qtpl:96
+				qw422016.N().S(`
+                                `)
+//line app/vmalert/web.qtpl:97
+				for k, v := range rr.Labels {
+//line app/vmalert/web.qtpl:97
+					qw422016.N().S(`
+                                        <span class="ms-1 badge bg-primary">`)
+//line app/vmalert/web.qtpl:98
+					qw422016.E().S(k)
+//line app/vmalert/web.qtpl:98
+					qw422016.N().S(`=`)
+//line app/vmalert/web.qtpl:98
+					qw422016.E().S(v)
+//line app/vmalert/web.qtpl:98
+					qw422016.N().S(`</span>
+                                `)
+//line app/vmalert/web.qtpl:99
+				}
+//line app/vmalert/web.qtpl:99
+				qw422016.N().S(`
+                            </td>
+                            <td><div class="error-cell">`)
+//line app/vmalert/web.qtpl:101
+				qw422016.E().S(rr.LastError)
+//line app/vmalert/web.qtpl:101
+				qw422016.N().S(`</div></td>
+                            <td>`)
+//line app/vmalert/web.qtpl:102
+				qw422016.N().D(rr.LastSamples)
+//line app/vmalert/web.qtpl:102
+				qw422016.N().S(`</td>
+                            <td>`)
+//line app/vmalert/web.qtpl:103
+				qw422016.N().FPrec(time.Since(rr.LastExec).Seconds(), 3)
+//line app/vmalert/web.qtpl:103
+				qw422016.N().S(`s ago</td>
+                        </tr>
+                    `)
+//line app/vmalert/web.qtpl:105
+			}
+//line app/vmalert/web.qtpl:105
+			qw422016.N().S(`
+                 </tbody>
+                </table>
+            </div>
+        `)
+//line app/vmalert/web.qtpl:109
+		}
+//line app/vmalert/web.qtpl:109
+		qw422016.N().S(`
+
+    `)
+//line app/vmalert/web.qtpl:111
+	} else {
+//line app/vmalert/web.qtpl:111
+		qw422016.N().S(`
+        <div>
+            <p>No items...</p>
+        </div>
+    `)
+//line app/vmalert/web.qtpl:115
+	}
+//line app/vmalert/web.qtpl:115
+	qw422016.N().S(`
+
+    `)
+//line app/vmalert/web.qtpl:117
+	tpl.StreamFooter(qw422016)
+//line app/vmalert/web.qtpl:117
+	qw422016.N().S(`
+
+`)
+//line app/vmalert/web.qtpl:119
+}
+
+//line app/vmalert/web.qtpl:119
+func WriteListGroups(qq422016 qtio422016.Writer, groups []APIGroup) {
+//line app/vmalert/web.qtpl:119
+	qw422016 := qt422016.AcquireWriter(qq422016)
+//line app/vmalert/web.qtpl:119
+	StreamListGroups(qw422016, groups)
+//line app/vmalert/web.qtpl:119
+	qt422016.ReleaseWriter(qw422016)
+//line app/vmalert/web.qtpl:119
+}
+
+//line app/vmalert/web.qtpl:119
+func ListGroups(groups []APIGroup) string {
+//line app/vmalert/web.qtpl:119
+	qb422016 := qt422016.AcquireByteBuffer()
+//line app/vmalert/web.qtpl:119
+	WriteListGroups(qb422016, groups)
+//line app/vmalert/web.qtpl:119
+	qs422016 := string(qb422016.B)
+//line app/vmalert/web.qtpl:119
+	qt422016.ReleaseByteBuffer(qb422016)
+//line app/vmalert/web.qtpl:119
+	return qs422016
+//line app/vmalert/web.qtpl:119
+}
+
+//line app/vmalert/web.qtpl:122
+func StreamListAlerts(qw422016 *qt422016.Writer, groupAlerts []GroupAlerts) {
+//line app/vmalert/web.qtpl:122
+	qw422016.N().S(`
+    `)
+//line app/vmalert/web.qtpl:123
+	tpl.StreamHeader(qw422016, "Alerts", navItems)
+//line app/vmalert/web.qtpl:123
+	qw422016.N().S(`
+    `)
+//line app/vmalert/web.qtpl:124
+	if len(groupAlerts) > 0 {
+//line app/vmalert/web.qtpl:124
+		qw422016.N().S(`
+         <a class="btn btn-primary" role="button" onclick="collapseAll()">Collapse All</a>
+         <a class="btn btn-primary" role="button" onclick="expandAll()">Expand All</a>
+         `)
+//line app/vmalert/web.qtpl:127
+		for _, ga := range groupAlerts {
+//line app/vmalert/web.qtpl:127
+			qw422016.N().S(`
+            `)
+//line app/vmalert/web.qtpl:128
+			g := ga.Group
+
+//line app/vmalert/web.qtpl:128
+			qw422016.N().S(`
+            <div class="group-heading alert-danger" data-bs-target="rules-`)
+//line app/vmalert/web.qtpl:129
+			qw422016.E().S(g.ID)
+//line app/vmalert/web.qtpl:129
+			qw422016.N().S(`">
+                <span class="anchor" id="group-`)
+//line app/vmalert/web.qtpl:130
+			qw422016.E().S(g.ID)
+//line app/vmalert/web.qtpl:130
+			qw422016.N().S(`"></span>
+                <a href="#group-`)
+//line app/vmalert/web.qtpl:131
+			qw422016.E().S(g.ID)
+//line app/vmalert/web.qtpl:131
+			qw422016.N().S(`">`)
+//line app/vmalert/web.qtpl:131
+			qw422016.E().S(g.Name)
+//line app/vmalert/web.qtpl:131
+			if g.Type != "prometheus" {
+//line app/vmalert/web.qtpl:131
+				qw422016.N().S(` (`)
+//line app/vmalert/web.qtpl:131
+				qw422016.E().S(g.Type)
+//line app/vmalert/web.qtpl:131
+				qw422016.N().S(`)`)
+//line app/vmalert/web.qtpl:131
+			}
+//line app/vmalert/web.qtpl:131
+			qw422016.N().S(`</a>
+                <span class="badge bg-danger" title="Number of active alerts">`)
+//line app/vmalert/web.qtpl:132
+			qw422016.N().D(len(ga.Alerts))
+//line app/vmalert/web.qtpl:132
+			qw422016.N().S(`</span>
+                <br>
+                <p class="fs-6 fw-lighter">`)
+//line app/vmalert/web.qtpl:134
+			qw422016.E().S(g.File)
+//line app/vmalert/web.qtpl:134
+			qw422016.N().S(`</p>
+            </div>
+            `)
+//line app/vmalert/web.qtpl:137
+			var keys []string
+			alertsByRule := make(map[string][]*APIAlert)
+			for _, alert := range ga.Alerts {
+				if len(alertsByRule[alert.RuleID]) < 1 {
+					keys = append(keys, alert.RuleID)
+				}
+				alertsByRule[alert.RuleID] = append(alertsByRule[alert.RuleID], alert)
+			}
+			sort.Strings(keys)
+
+//line app/vmalert/web.qtpl:146
+			qw422016.N().S(`
+            <div class="collapse" id="rules-`)
+//line app/vmalert/web.qtpl:147
+			qw422016.E().S(g.ID)
+//line app/vmalert/web.qtpl:147
+			qw422016.N().S(`">
+                `)
+//line app/vmalert/web.qtpl:148
+			for _, ruleID := range keys {
+//line app/vmalert/web.qtpl:148
+				qw422016.N().S(`
+                    `)
+//line app/vmalert/web.qtpl:150
+				defaultAR := alertsByRule[ruleID][0]
+				var labelKeys []string
+				for k := range defaultAR.Labels {
+					labelKeys = append(labelKeys, k)
+				}
+				sort.Strings(labelKeys)
+
+//line app/vmalert/web.qtpl:156
+				qw422016.N().S(`
+                    <br>
+                    <b>alert:</b> `)
+//line app/vmalert/web.qtpl:158
+				qw422016.E().S(defaultAR.Name)
+//line app/vmalert/web.qtpl:158
+				qw422016.N().S(` (`)
+//line app/vmalert/web.qtpl:158
+				qw422016.N().D(len(alertsByRule[ruleID]))
+//line app/vmalert/web.qtpl:158
+				qw422016.N().S(`)<br>
+                    <b>expr:</b><code><pre>`)
+//line app/vmalert/web.qtpl:159
+				qw422016.E().S(defaultAR.Expression)
+//line app/vmalert/web.qtpl:159
+				qw422016.N().S(`</pre></code>
+                    <table class="table table-striped table-hover table-sm">
+                        <thead>
+                            <tr>
+                                <th scope="col">Labels</th>
+                                <th scope="col">State</th>
+                                <th scope="col">Active at</th>
+                                <th scope="col">Value</th>
+                                <th scope="col">Link</th>
+                            </tr>
+                        </thead>
+                        <tbody>
+                        `)
+//line app/vmalert/web.qtpl:171
+				for _, ar := range alertsByRule[ruleID] {
+//line app/vmalert/web.qtpl:171
+					qw422016.N().S(`
+                            <tr>
+                                <td>
+                                    `)
+//line app/vmalert/web.qtpl:174
+					for _, k := range labelKeys {
+//line app/vmalert/web.qtpl:174
+						qw422016.N().S(`
+                                        <span class="ms-1 badge bg-primary">`)
+//line app/vmalert/web.qtpl:175
+						qw422016.E().S(k)
+//line app/vmalert/web.qtpl:175
+						qw422016.N().S(`=`)
+//line app/vmalert/web.qtpl:175
+						qw422016.E().S(ar.Labels[k])
+//line app/vmalert/web.qtpl:175
+						qw422016.N().S(`</span>
+                                    `)
+//line app/vmalert/web.qtpl:176
+					}
+//line app/vmalert/web.qtpl:176
+					qw422016.N().S(`
+                                </td>
+                                <td><span class="badge `)
+//line app/vmalert/web.qtpl:178
+					if ar.State == "firing" {
+//line app/vmalert/web.qtpl:178
+						qw422016.N().S(`bg-danger`)
+//line app/vmalert/web.qtpl:178
+					} else {
+//line app/vmalert/web.qtpl:178
+						qw422016.N().S(` bg-warning text-dark`)
+//line app/vmalert/web.qtpl:178
+					}
+//line app/vmalert/web.qtpl:178
+					qw422016.N().S(`">`)
+//line app/vmalert/web.qtpl:178
+					qw422016.E().S(ar.State)
+//line app/vmalert/web.qtpl:178
+					qw422016.N().S(`</span></td>
+                                <td>`)
+//line app/vmalert/web.qtpl:179
+					qw422016.E().S(ar.ActiveAt.Format("2006-01-02T15:04:05Z07:00"))
+//line app/vmalert/web.qtpl:179
+					qw422016.N().S(`</td>
+                                <td>`)
+//line app/vmalert/web.qtpl:180
+					qw422016.E().S(ar.Value)
+//line app/vmalert/web.qtpl:180
+					qw422016.N().S(`</td>
+                                <td>
+                                    <a href="/`)
+//line app/vmalert/web.qtpl:182
+					qw422016.E().S(g.ID)
+//line app/vmalert/web.qtpl:182
+					qw422016.N().S(`/`)
+//line app/vmalert/web.qtpl:182
+					qw422016.E().S(ar.ID)
+//line app/vmalert/web.qtpl:182
+					qw422016.N().S(`/status">Details</a>
+                                </td>
+                            </tr>
+                        `)
+//line app/vmalert/web.qtpl:185
+				}
+//line app/vmalert/web.qtpl:185
+				qw422016.N().S(`
+                     </tbody>
+                    </table>
+                `)
+//line app/vmalert/web.qtpl:188
+			}
+//line app/vmalert/web.qtpl:188
+			qw422016.N().S(`
+            </div>
+            <br>
+        `)
+//line app/vmalert/web.qtpl:191
+		}
+//line app/vmalert/web.qtpl:191
+		qw422016.N().S(`
+
+    `)
+//line app/vmalert/web.qtpl:193
+	} else {
+//line app/vmalert/web.qtpl:193
+		qw422016.N().S(`
+        <div>
+            <p>No items...</p>
+        </div>
+    `)
+//line app/vmalert/web.qtpl:197
+	}
+//line app/vmalert/web.qtpl:197
+	qw422016.N().S(`
+
+    `)
+//line app/vmalert/web.qtpl:199
+	tpl.StreamFooter(qw422016)
+//line app/vmalert/web.qtpl:199
+	qw422016.N().S(`
+
+`)
+//line app/vmalert/web.qtpl:201
+}
+
+//line app/vmalert/web.qtpl:201
+func WriteListAlerts(qq422016 qtio422016.Writer, groupAlerts []GroupAlerts) {
+//line app/vmalert/web.qtpl:201
+	qw422016 := qt422016.AcquireWriter(qq422016)
+//line app/vmalert/web.qtpl:201
+	StreamListAlerts(qw422016, groupAlerts)
+//line app/vmalert/web.qtpl:201
+	qt422016.ReleaseWriter(qw422016)
+//line app/vmalert/web.qtpl:201
+}
+
+//line app/vmalert/web.qtpl:201
+func ListAlerts(groupAlerts []GroupAlerts) string {
+//line app/vmalert/web.qtpl:201
+	qb422016 := qt422016.AcquireByteBuffer()
+//line app/vmalert/web.qtpl:201
+	WriteListAlerts(qb422016, groupAlerts)
+//line app/vmalert/web.qtpl:201
+	qs422016 := string(qb422016.B)
+//line app/vmalert/web.qtpl:201
+	qt422016.ReleaseByteBuffer(qb422016)
+//line app/vmalert/web.qtpl:201
+	return qs422016
+//line app/vmalert/web.qtpl:201
+}
+
+//line app/vmalert/web.qtpl:203
+func StreamAlert(qw422016 *qt422016.Writer, alert *APIAlert) {
+//line app/vmalert/web.qtpl:203
+	qw422016.N().S(`
+    `)
+//line app/vmalert/web.qtpl:204
+	tpl.StreamHeader(qw422016, "", navItems)
+//line app/vmalert/web.qtpl:204
+	qw422016.N().S(`
+    `)
+//line app/vmalert/web.qtpl:206
+	var labelKeys []string
+	for k := range alert.Labels {
+		labelKeys = append(labelKeys, k)
+	}
+	sort.Strings(labelKeys)
+
+	var annotationKeys []string
+	for k := range alert.Annotations {
+		annotationKeys = append(annotationKeys, k)
+	}
+	sort.Strings(annotationKeys)
+
+//line app/vmalert/web.qtpl:217
+	qw422016.N().S(`
+    <div class="display-6 pb-3 mb-3">`)
+//line app/vmalert/web.qtpl:218
+	qw422016.E().S(alert.Name)
+//line app/vmalert/web.qtpl:218
+	qw422016.N().S(`<span class="ms-2 badge `)
+//line app/vmalert/web.qtpl:218
+	if alert.State == "firing" {
+//line app/vmalert/web.qtpl:218
+		qw422016.N().S(`bg-danger`)
+//line app/vmalert/web.qtpl:218
+	} else {
+//line app/vmalert/web.qtpl:218
+		qw422016.N().S(` bg-warning text-dark`)
+//line app/vmalert/web.qtpl:218
+	}
+//line app/vmalert/web.qtpl:218
+	qw422016.N().S(`">`)
+//line app/vmalert/web.qtpl:218
+	qw422016.E().S(alert.State)
+//line app/vmalert/web.qtpl:218
+	qw422016.N().S(`</span></div>
+    <div class="container border-bottom p-2">
+      <div class="row">
+        <div class="col-2">
+          Active at
+        </div>
+        <div class="col">
+          `)
+//line app/vmalert/web.qtpl:225
+	qw422016.E().S(alert.ActiveAt.Format("2006-01-02T15:04:05Z07:00"))
+//line app/vmalert/web.qtpl:225
+	qw422016.N().S(`
+        </div>
+      </div>
+      </div>
+    <div class="container border-bottom p-2">
+      <div class="row">
+        <div class="col-2">
+          Expr
+        </div>
+        <div class="col">
+          <code><pre>`)
+//line app/vmalert/web.qtpl:235
+	qw422016.E().S(alert.Expression)
+//line app/vmalert/web.qtpl:235
+	qw422016.N().S(`</pre></code>
+        </div>
+      </div>
+    </div>
+    <div class="container border-bottom p-2">
+      <div class="row">
+        <div class="col-2">
+          Labels
+        </div>
+        <div class="col">
+           `)
+//line app/vmalert/web.qtpl:245
+	for _, k := range labelKeys {
+//line app/vmalert/web.qtpl:245
+		qw422016.N().S(`
+                <span class="m-1 badge bg-primary">`)
+//line app/vmalert/web.qtpl:246
+		qw422016.E().S(k)
+//line app/vmalert/web.qtpl:246
+		qw422016.N().S(`=`)
+//line app/vmalert/web.qtpl:246
+		qw422016.E().S(alert.Labels[k])
+//line app/vmalert/web.qtpl:246
+		qw422016.N().S(`</span>
+          `)
+//line app/vmalert/web.qtpl:247
+	}
+//line app/vmalert/web.qtpl:247
+	qw422016.N().S(`
+        </div>
+      </div>
+    </div>
+    <div class="container border-bottom p-2">
+      <div class="row">
+        <div class="col-2">
+          Annotations
+        </div>
+        <div class="col">
+           `)
+//line app/vmalert/web.qtpl:257
+	for _, k := range annotationKeys {
+//line app/vmalert/web.qtpl:257
+		qw422016.N().S(`
+                <b>`)
+//line app/vmalert/web.qtpl:258
+		qw422016.E().S(k)
+//line app/vmalert/web.qtpl:258
+		qw422016.N().S(`:</b><br>
+                <p>`)
+//line app/vmalert/web.qtpl:259
+		qw422016.E().S(alert.Annotations[k])
+//line app/vmalert/web.qtpl:259
+		qw422016.N().S(`</p>
+          `)
+//line app/vmalert/web.qtpl:260
+	}
+//line app/vmalert/web.qtpl:260
+	qw422016.N().S(`
+        </div>
+      </div>
+    </div>
+    <div class="container border-bottom p-2">
+      <div class="row">
+        <div class="col-2">
+          Group
+        </div>
+        <div class="col">
+           <a target="_blank" href="/groups#group-`)
+//line app/vmalert/web.qtpl:270
+	qw422016.E().S(alert.GroupID)
+//line app/vmalert/web.qtpl:270
+	qw422016.N().S(`">`)
+//line app/vmalert/web.qtpl:270
+	qw422016.E().S(alert.GroupID)
+//line app/vmalert/web.qtpl:270
+	qw422016.N().S(`</a>
+        </div>
+      </div>
+    </div>
+    `)
+//line app/vmalert/web.qtpl:274
+	tpl.StreamFooter(qw422016)
+//line app/vmalert/web.qtpl:274
+	qw422016.N().S(`
+
+`)
+//line app/vmalert/web.qtpl:276
+}
+
+//line app/vmalert/web.qtpl:276
+func WriteAlert(qq422016 qtio422016.Writer, alert *APIAlert) {
+//line app/vmalert/web.qtpl:276
+	qw422016 := qt422016.AcquireWriter(qq422016)
+//line app/vmalert/web.qtpl:276
+	StreamAlert(qw422016, alert)
+//line app/vmalert/web.qtpl:276
+	qt422016.ReleaseWriter(qw422016)
+//line app/vmalert/web.qtpl:276
+}
+
+//line app/vmalert/web.qtpl:276
+func Alert(alert *APIAlert) string {
+//line app/vmalert/web.qtpl:276
+	qb422016 := qt422016.AcquireByteBuffer()
+//line app/vmalert/web.qtpl:276
+	WriteAlert(qb422016, alert)
+//line app/vmalert/web.qtpl:276
+	qs422016 := string(qb422016.B)
+//line app/vmalert/web.qtpl:276
+	qt422016.ReleaseByteBuffer(qb422016)
+//line app/vmalert/web.qtpl:276
+	return qs422016
+//line app/vmalert/web.qtpl:276
+}

app/vmalert/web_types.go

@@ -9,6 +9,7 @@ import (
 type APIAlert struct {
 	ID          string            `json:"id"`
 	Name        string            `json:"name"`
+	RuleID      string            `json:"rule_id"`
 	GroupID     string            `json:"group_id"`
 	Expression  string            `json:"expression"`
 	State       string            `json:"state"`
@@ -20,14 +21,16 @@ type APIAlert struct {
 
 // APIGroup represents Group for WEB view
 type APIGroup struct {
-	Name           string             `json:"name"`
-	Type           string             `json:"type"`
-	ID             string             `json:"id"`
-	File           string             `json:"file"`
-	Interval       string             `json:"interval"`
-	Concurrency    int                `json:"concurrency"`
-	AlertingRules  []APIAlertingRule  `json:"alerting_rules"`
-	RecordingRules []APIRecordingRule `json:"recording_rules"`
+	Name              string             `json:"name"`
+	Type              string             `json:"type"`
+	ID                string             `json:"id"`
+	File              string             `json:"file"`
+	Interval          string             `json:"interval"`
+	Concurrency       int                `json:"concurrency"`
+	ExtraFilterLabels map[string]string  `json:"extra_filter_labels"`
+	Labels            map[string]string  `json:"labels,omitempty"`
+	AlertingRules     []APIAlertingRule  `json:"alerting_rules"`
+	RecordingRules    []APIRecordingRule `json:"recording_rules"`
 }
 
 // APIAlertingRule represents AlertingRule for WEB view
@@ -39,6 +42,7 @@ type APIAlertingRule struct {
 	Expression  string            `json:"expression"`
 	For         string            `json:"for"`
 	LastError   string            `json:"last_error"`
+	LastSamples int               `json:"last_samples"`
 	LastExec    time.Time         `json:"last_exec"`
 	Labels      map[string]string `json:"labels"`
 	Annotations map[string]string `json:"annotations"`
@@ -46,12 +50,19 @@ type APIAlertingRule struct {
 
 // APIRecordingRule represents RecordingRule for WEB view
 type APIRecordingRule struct {
-	ID         string            `json:"id"`
-	Name       string            `json:"name"`
-	Type       string            `json:"type"`
-	GroupID    string            `json:"group_id"`
-	Expression string            `json:"expression"`
-	LastError  string            `json:"last_error"`
-	LastExec   time.Time         `json:"last_exec"`
-	Labels     map[string]string `json:"labels"`
+	ID          string            `json:"id"`
+	Name        string            `json:"name"`
+	Type        string            `json:"type"`
+	GroupID     string            `json:"group_id"`
+	Expression  string            `json:"expression"`
+	LastError   string            `json:"last_error"`
+	LastSamples int               `json:"last_samples"`
+	LastExec    time.Time         `json:"last_exec"`
+	Labels      map[string]string `json:"labels"`
+}
+
+// GroupAlerts represents a group of alerts for WEB view
+type GroupAlerts struct {
+	Group  APIGroup
+	Alerts []*APIAlert
 }

app/vmauth/Makefile

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

app/vmauth/README.md

@@ -1,8 +1,8 @@
-## vmauth
+# vmauth
 
-`vmauth` is a simple auth proxy and router for [VictoriaMetrics](https://github.com/VictoriaMetrics/VictoriaMetrics).
-It reads username and password from [Basic Auth headers](https://en.wikipedia.org/wiki/Basic_access_authentication),
-matches them against configs pointed by `-auth.config` command-line flag and proxies incoming HTTP requests to the configured per-user `url_prefix` on successful match.
+`vmauth` is a simple auth proxy, router and [load balancer](#load-balancing) for [VictoriaMetrics](https://github.com/VictoriaMetrics/VictoriaMetrics).
+It reads auth credentials from `Authorization` http header ([Basic Auth](https://en.wikipedia.org/wiki/Basic_access_authentication) and `Bearer token` is supported),
+matches them against configs pointed by [-auth.config](#auth-config) command-line flag and proxies incoming HTTP requests to the configured per-user `url_prefix` on successful match.
 
 
 ## Quick start
@@ -17,18 +17,24 @@ and pass the following flag to `vmauth` binary in order to start authorizing and
 After that `vmauth` starts accepting HTTP requests on port `8427` and routing them according to the provided [-auth.config](#auth-config).
 The port can be modified via `-httpListenAddr` command-line flag.
 
-The auth config can be reloaded by passing `SIGHUP` signal to `vmauth`.
+The auth config can be reloaded either by passing `SIGHUP` signal to `vmauth` or by querying `/-/reload` http endpoint.
 
 Docker images for `vmauth` are available [here](https://hub.docker.com/r/victoriametrics/vmauth/tags).
 
 Pass `-help` to `vmauth` in order to see all the supported command-line flags with their descriptions.
 
-Feel free [contacting us](mailto:info@victoriametrics.com) if you need customized auth proxy for VictoriaMetrics with the support of LDAP, SSO, RBAC, SAML, accounting, limits, etc.
+Feel free [contacting us](mailto:info@victoriametrics.com) if you need customized auth proxy for VictoriaMetrics with the support of LDAP, SSO, RBAC, SAML,
+accounting and rate limiting such as [vmgateway](https://docs.victoriametrics.com/vmgateway.html).
+
+
+## Load balancing
+
+Each `url_prefix` in the [-auth.config](#auth-config) may contain either a single url or a list of urls. In the latter case `vmauth` balances load among the configured urls in a round-robin manner. This feature is useful for balancing the load among multiple `vmselect` and/or `vminsert` nodes in [VictoriaMetrics cluster](https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html).
 
 
 ## Auth config
 
-Auth config is represented in the following simple `yml` format:
+`-auth.config` is represented in the following simple `yml` format:
 
 ```yml
 
@@ -36,32 +42,73 @@ Auth config is represented in the following simple `yml` format:
 # Usernames must be unique.
 
 users:
+  # Requests with the 'Authorization: Bearer XXXX' header are proxied to http://localhost:8428 .
+  # For example, http://vmauth:8427/api/v1/query is proxied to http://localhost:8428/api/v1/query
+- bearer_token: "XXXX"
+  url_prefix: "http://localhost:8428"
 
   # The user for querying local single-node VictoriaMetrics.
   # All the requests to http://vmauth:8427 with the given Basic Auth (username:password)
-  # will be routed to http://localhost:8428 .
-  # For example, http://vmauth:8427/api/v1/query is routed to http://localhost:8428/api/v1/query
+  # will be proxied to http://localhost:8428 .
+  # For example, http://vmauth:8427/api/v1/query is proxied to http://localhost:8428/api/v1/query
 - username: "local-single-node"
   password: "***"
   url_prefix: "http://localhost:8428"
 
-  # The user for querying account 123 in VictoriaMetrics cluster
-  # See https://victoriametrics.github.io/Cluster-VictoriaMetrics.html#url-format
+  # The user for querying local single-node VictoriaMetrics with extra_label team=dev.
   # All the requests to http://vmauth:8427 with the given Basic Auth (username:password)
-  # will be routed to http://vmselect:8481/select/123/prometheus .
-  # For example, http://vmauth:8427/api/v1/query is routed to http://vmselect:8481/select/123/prometheus/api/v1/select
+  # will be routed to http://localhost:8428 with extra_label=team=dev query arg.
+  # For example, http://vmauth:8427/api/v1/query is routed to http://localhost:8428/api/v1/query?extra_label=team=dev
+- username: "local-single-node"
+  password: "***"
+  url_prefix: "http://localhost:8428?extra_label=team=dev"
+
+  # The user for querying account 123 in VictoriaMetrics cluster
+  # See https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html#url-format
+  # All the requests to http://vmauth:8427 with the given Basic Auth (username:password)
+  # will be load-balanced among http://vmselect1:8481/select/123/prometheus and http://vmselect2:8481/select/123/prometheus
+  # For example, http://vmauth:8427/api/v1/query is proxied to the following urls in a round-robin manner:
+  #   - http://vmselect1:8481/select/123/prometheus/api/v1/select
+  #   - http://vmselect2:8481/select/123/prometheus/api/v1/select
 - username: "cluster-select-account-123"
   password: "***"
-  url_prefix: "http://vmselect:8481/select/123/prometheus"
+  url_prefix:
+  - "http://vmselect1:8481/select/123/prometheus"
+  - "http://vmselect2:8481/select/123/prometheus"
 
   # The user for inserting Prometheus data into VictoriaMetrics cluster under account 42
-  # See https://victoriametrics.github.io/Cluster-VictoriaMetrics.html#url-format
-  # All the reuqests to http://vmauth:8427 with the given Basic Auth (username:password)
-  # will be routed to http://vminsert:8480/insert/42/prometheus .
-  # For example, http://vmauth:8427/api/v1/write is routed to http://vminsert:8480/insert/42/prometheus/api/v1/write
+  # See https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html#url-format
+  # All the requests to http://vmauth:8427 with the given Basic Auth (username:password)
+  # will be load-balanced between http://vminsert1:8480/insert/42/prometheus and http://vminsert2:8480/insert/42/prometheus
+  # For example, http://vmauth:8427/api/v1/write is proxied to the following urls in a round-robin manner:
+  #   - http://vminsert1:8480/insert/42/prometheus/api/v1/write
+  #   - http://vminsert2:8480/insert/42/prometheus/api/v1/write
 - username: "cluster-insert-account-42"
   password: "***"
-  url_prefix: "http://vminsert:8480/insert/42/prometheus"
+  url_prefix:
+  - "http://vminsert1:8480/insert/42/prometheus"
+  - "http://vminsert2:8480/insert/42/prometheus"
+
+
+  # A single user for querying and inserting data:
+  # - Requests to http://vmauth:8427/api/v1/query, http://vmauth:8427/api/v1/query_range
+  #   and http://vmauth:8427/api/v1/label/<label_name>/values are proxied to the following urls in a round-robin manner:
+  #     - http://vmselect1:8481/select/42/prometheus
+  #     - http://vmselect2:8481/select/42/prometheus
+  #   For example, http://vmauth:8427/api/v1/query is proxied to http://vmselect1:8480/select/42/prometheus/api/v1/query
+  #   or to http://vmselect2:8480/select/42/prometheus/api/v1/query .
+  # - Requests to http://vmauth:8427/api/v1/write are proxied to http://vminsert:8480/insert/42/prometheus/api/v1/write
+- username: "foobar"
+  url_map:
+  - src_paths:
+    - "/api/v1/query"
+    - "/api/v1/query_range"
+    - "/api/v1/label/[^/]+/values"
+    url_prefix:
+    - "http://vmselect1:8481/select/42/prometheus"
+    - "http://vmselect2:8481/select/42/prometheus"
+  - src_paths: ["/api/v1/write"]
+    url_prefix: "http://vminsert:8480/insert/42/prometheus"
 ```
 
 The config may contain `%{ENV_VAR}` placeholders, which are substituted by the corresponding `ENV_VAR` environment variable values.
@@ -83,11 +130,13 @@ Do not transfer Basic Auth headers in plaintext over untrusted networks. Enable
 
 Alternatively, [https termination proxy](https://en.wikipedia.org/wiki/TLS_termination_proxy) may be put in front of `vmauth`.
 
+It is recommended protecting `/-/reload` endpoint with `-reloadAuthKey` command-line flag, so external users couldn't trigger config reload.
+
 
 ## Monitoring
 
 `vmauth` exports various metrics in Prometheus exposition format at `http://vmauth-host:8427/metrics` page. It is recommended setting up regular scraping of this page
-either via [vmagent](https://victoriametrics.github.io/vmagent.html) or via Prometheus, so the exported metrics could be analyzed later.
+either via [vmagent](https://docs.victoriametrics.com/vmagent.html) or via Prometheus, so the exported metrics could be analyzed later.
 
 
 ## How to build from sources
@@ -97,14 +146,14 @@ It is recommended using [binary releases](https://github.com/VictoriaMetrics/Vic
 
 ### Development build
 
-1. [Install Go](https://golang.org/doc/install). The minimum supported version is Go 1.13.
-2. Run `make vmauth` from the root folder of the repository.
+1. [Install Go](https://golang.org/doc/install). The minimum supported version is Go 1.16.
+2. Run `make vmauth` from the root folder of [the repository](https://github.com/VictoriaMetrics/VictoriaMetrics).
    It builds `vmauth` binary and puts it into the `bin` folder.
 
 ### Production build
 
 1. [Install docker](https://docs.docker.com/install/).
-2. Run `make vmauth-prod` from the root folder of the repository.
+2. Run `make vmauth-prod` from the root folder of [the repository](https://github.com/VictoriaMetrics/VictoriaMetrics).
    It builds `vmauth-prod` binary and puts it into the `bin` folder.
 
 ### Building docker images
@@ -151,55 +200,69 @@ Pass `-help` command-line arg to `vmauth` in order to see all the configuration
 
 vmauth authenticates and authorizes incoming requests and proxies them to VictoriaMetrics.
 
-See the docs at https://victoriametrics.github.io/vmauth.html .
+See the docs at https://docs.victoriametrics.com/vmauth.html .
 
   -auth.config string
-    	Path to auth config. See https://victoriametrics.github.io/vmauth.html for details on the format of this auth config
+    	Path to auth config. See https://docs.victoriametrics.com/vmauth.html for details on the format of this auth config
   -enableTCP6
-    	Whether to enable IPv6 for listening and dialing. By default only IPv4 TCP is used
+    	Whether to enable IPv6 for listening and dialing. By default only IPv4 TCP and UDP is used
   -envflag.enable
-    	Whether to enable reading flags from environment variables additionally to command line. Command line flag values have priority over values from environment vars. Flags are read only from command line if this flag isn't set
+    	Whether to enable reading flags from environment variables additionally to command line. Command line flag values have priority over values from environment vars. Flags are read only from command line if this flag isn't set. See https://docs.victoriametrics.com/#environment-variables for more details
   -envflag.prefix string
     	Prefix for environment variables if -envflag.enable is set
+  -fs.disableMmap
+    	Whether to use pread() instead of mmap() for reading data files. By default mmap() is used for 64-bit arches and pread() is used for 32-bit arches, since they cannot read data files bigger than 2^32 bytes in memory. mmap() is usually faster for reading small data chunks than pread()
   -http.connTimeout duration
-    	Incoming http connections are closed after the configured timeout. This may help spreading incoming load among a cluster of services behind load balancer. Note that the real timeout may be bigger by up to 10% as a protection from Thundering herd problem (default 2m0s)
+    	Incoming http connections are closed after the configured timeout. This may help to spread the incoming load among a cluster of services behind a load balancer. Please note that the real timeout may be bigger by up to 10% as a protection against the thundering herd problem (default 2m0s)
   -http.disableResponseCompression
-    	Disable compression of HTTP responses for saving CPU resources. By default compression is enabled to save network bandwidth
+    	Disable compression of HTTP responses to save CPU resources. By default compression is enabled to save network bandwidth
   -http.idleConnTimeout duration
     	Timeout for incoming idle http connections (default 1m0s)
   -http.maxGracefulShutdownDuration duration
-    	The maximum duration for graceful shutdown of HTTP server. Highly loaded server may require increased value for graceful shutdown (default 7s)
+    	The maximum duration for a graceful shutdown of the HTTP server. A highly loaded server may require increased value for a graceful shutdown (default 7s)
   -http.pathPrefix string
     	An optional prefix to add to all the paths handled by http server. For example, if '-http.pathPrefix=/foo/bar' is set, then all the http requests will be handled on '/foo/bar/*' paths. This may be useful for proxied requests. See https://www.robustperception.io/using-external-urls-and-proxies-with-prometheus
   -http.shutdownDelay duration
-    	Optional delay before http server shutdown. During this dealy the servier returns non-OK responses from /health page, so load balancers can route new requests to other servers
+    	Optional delay before http server shutdown. During this delay, the server returns non-OK responses from /health page, so load balancers can route new requests to other servers
   -httpAuth.password string
     	Password for HTTP Basic Auth. The authentication is disabled if -httpAuth.username is empty
   -httpAuth.username string
     	Username for HTTP Basic Auth. The authentication is disabled if empty. See also -httpAuth.password
   -httpListenAddr string
     	TCP address to listen for http connections (default ":8427")
+  -logInvalidAuthTokens
+    	Whether to log requests with invalid auth tokens. Such requests are always counted at vmagent_http_request_errors_total{reason="invalid_auth_token"} metric, which is exposed at /metrics page
+  -loggerDisableTimestamps
+    	Whether to disable writing timestamps in logs
   -loggerErrorsPerSecondLimit int
-    	Per-second limit on the number of ERROR messages. If more than the given number of errors are emitted per second, then the remaining errors are suppressed. Zero value disables the rate limit (default 10)
+    	Per-second limit on the number of ERROR messages. If more than the given number of errors are emitted per second, the remaining errors are suppressed. Zero values disable the rate limit
   -loggerFormat string
     	Format for logs. Possible values: default, json (default "default")
   -loggerLevel string
     	Minimum level of errors to log. Possible values: INFO, WARN, ERROR, FATAL, PANIC (default "INFO")
   -loggerOutput string
     	Output for the logs. Supported values: stderr, stdout (default "stderr")
-  -memory.allowedBytes value
-    	Allowed size of system memory VictoriaMetrics caches may occupy. This option overrides -memory.allowedPercent if set to non-zero value. Too low value may increase cache miss rate, which usually results in higher CPU and disk IO usage. Too high value may evict too much data from OS page cache, which will result in higher disk IO usage
-    	Supports the following optional suffixes for values: KB, MB, GB, KiB, MiB, GiB (default 0)
+  -loggerTimezone string
+    	Timezone to use for timestamps in logs. Timezone must be a valid IANA Time Zone. For example: America/New_York, Europe/Berlin, Etc/GMT+3 or Local (default "UTC")
+  -loggerWarnsPerSecondLimit int
+    	Per-second limit on the number of WARN messages. If more than the given number of warns are emitted per second, then the remaining warns are suppressed. Zero values disable the rate limit
+  -maxIdleConnsPerBackend int
+    	The maximum number of idle connections vmauth can open per each backend host (default 100)
+  -memory.allowedBytes size
+    	Allowed size of system memory VictoriaMetrics caches may occupy. This option overrides -memory.allowedPercent if set to a non-zero value. Too low a value may increase the cache miss rate usually resulting in higher CPU and disk IO usage. Too high a value may evict too much data from OS page cache resulting in higher disk IO usage
+    	Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 0)
   -memory.allowedPercent float
-    	Allowed percent of system memory VictoriaMetrics caches may occupy. See also -memory.allowedBytes. Too low value may increase cache miss rate, which usually results in higher CPU and disk IO usage. Too high value may evict too much data from OS page cache, which will result in higher disk IO usage (default 60)
+    	Allowed percent of system memory VictoriaMetrics caches may occupy. See also -memory.allowedBytes. Too low a value may increase cache miss rate usually resulting in higher CPU and disk IO usage. Too high a value may evict too much data from OS page cache which will result in higher disk IO usage (default 60)
   -metricsAuthKey string
     	Auth key for /metrics. It overrides httpAuth settings
   -pprofAuthKey string
     	Auth key for /debug/pprof. It overrides httpAuth settings
+  -reloadAuthKey string
+    	Auth key for /-/reload http endpoint. It must be passed as authKey=...
   -tls
     	Whether to enable TLS (aka HTTPS) for incoming requests. -tlsCertFile and -tlsKeyFile must be set if -tls is set
   -tlsCertFile string
-    	Path to file with TLS certificate. Used only if -tls is set. Prefer ECDSA certs instead of RSA certs, since RSA certs are slow
+    	Path to file with TLS certificate. Used only if -tls is set. Prefer ECDSA certs instead of RSA certs as RSA certs are slower
   -tlsKeyFile string
     	Path to file with TLS key. Used only if -tls is set
   -version

app/vmauth/auth_config.go

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

app/vmauth/auth_config_test.go

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

app/vmauth/example_config.yml

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

app/vmauth/main.go

@@ -2,6 +2,7 @@ package main
 
 import (
 	"flag"
+	"fmt"
 	"net/http"
 	"net/http/httputil"
 	"net/url"
@@ -14,10 +15,15 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/procutil"
+	"github.com/VictoriaMetrics/metrics"
 )
 
 var (
-	httpListenAddr = flag.String("httpListenAddr", ":8427", "TCP address to listen for http connections")
+	httpListenAddr         = flag.String("httpListenAddr", ":8427", "TCP address to listen for http connections")
+	maxIdleConnsPerBackend = flag.Int("maxIdleConnsPerBackend", 100, "The maximum number of idle connections vmauth can open per each backend host")
+	reloadAuthKey          = flag.String("reloadAuthKey", "", "Auth key for /-/reload http endpoint. It must be passed as authKey=...")
+	logInvalidAuthTokens   = flag.Bool("logInvalidAuthTokens", false, "Whether to log requests with invalid auth tokens. "+
+		`Such requests are always counted at vmagent_http_request_errors_total{reason="invalid_auth_token"} metric, which is exposed at /metrics page`)
 )
 
 func main() {
@@ -47,30 +53,67 @@ func main() {
 }
 
 func requestHandler(w http.ResponseWriter, r *http.Request) bool {
-	username, password, ok := r.BasicAuth()
-	if !ok {
+	switch r.URL.Path {
+	case "/-/reload":
+		authKey := r.FormValue("authKey")
+		if authKey != *reloadAuthKey {
+			httpserver.Errorf(w, r, "invalid authKey %q. It must match the value from -reloadAuthKey command line flag", authKey)
+			return true
+		}
+		configReloadRequests.Inc()
+		procutil.SelfSIGHUP()
+		w.WriteHeader(http.StatusOK)
+		return true
+	}
+	authToken := r.Header.Get("Authorization")
+	if authToken == "" {
 		w.Header().Set("WWW-Authenticate", `Basic realm="Restricted"`)
-		http.Error(w, "missing `Authorization: Basic *` header", http.StatusUnauthorized)
+		http.Error(w, "missing `Authorization` request header", http.StatusUnauthorized)
 		return true
 	}
 	ac := authConfig.Load().(map[string]*UserInfo)
-	info := ac[username]
-	if info == nil || info.Password != password {
-		httpserver.Errorf(w, r, "cannot find the provided username %q or password in config", username)
+	ui := ac[authToken]
+	if ui == nil {
+		invalidAuthTokenRequests.Inc()
+		if *logInvalidAuthTokens {
+			httpserver.Errorf(w, r, "cannot find the provided auth token %q in config", authToken)
+		} else {
+			errStr := fmt.Sprintf("cannot find the provided auth token %q in config", authToken)
+			http.Error(w, errStr, http.StatusBadRequest)
+		}
 		return true
 	}
-	info.requests.Inc()
-
-	targetURL := createTargetURL(info.URLPrefix, r.URL)
-	if _, err := url.Parse(targetURL); err != nil {
-		httpserver.Errorf(w, r, "invalid targetURL=%q: %s", targetURL, err)
+	ui.requests.Inc()
+	targetURL, err := createTargetURL(ui, r.URL)
+	if err != nil {
+		httpserver.Errorf(w, r, "cannot determine targetURL: %s", err)
 		return true
 	}
-	r.Header.Set("vm-target-url", targetURL)
-	reverseProxy.ServeHTTP(w, r)
+	r.Header.Set("vm-target-url", targetURL.String())
+	proxyRequest(w, r)
 	return true
 }
 
+func proxyRequest(w http.ResponseWriter, r *http.Request) {
+	defer func() {
+		err := recover()
+		if err == nil || err == http.ErrAbortHandler {
+			// Suppress http.ErrAbortHandler panic.
+			// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1353
+			return
+		}
+		// Forward other panics to the caller.
+		panic(err)
+	}()
+	reverseProxy.ServeHTTP(w, r)
+}
+
+var (
+	configReloadRequests     = metrics.NewCounter(`vmagent_http_requests_total{path="/-/reload"}`)
+	invalidAuthTokenRequests = metrics.NewCounter(`vmagent_http_request_errors_total{reason="invalid_auth_token"}`)
+	missingRouteRequests     = metrics.NewCounter(`vmagent_http_request_errors_total{reason="missing_route"}`)
+)
+
 var reverseProxy = &httputil.ReverseProxy{
 	Director: func(r *http.Request) {
 		targetURL := r.Header.Get("vm-target-url")
@@ -86,6 +129,7 @@ var reverseProxy = &httputil.ReverseProxy{
 		tr.DisableCompression = true
 		// Disable HTTP/2.0, since VictoriaMetrics components don't support HTTP/2.0 (because there is no sense in this).
 		tr.ForceAttemptHTTP2 = false
+		tr.MaxIdleConnsPerHost = *maxIdleConnsPerBackend
 		return tr
 	}(),
 	FlushInterval: time.Second,
@@ -96,7 +140,7 @@ func usage() {
 	const s = `
 vmauth authenticates and authorizes incoming requests and proxies them to VictoriaMetrics.
 
-See the docs at https://victoriametrics.github.io/vmauth.html .
+See the docs at https://docs.victoriametrics.com/vmauth.html .
 `
 	flagutil.Usage(s)
 }

app/vmauth/multiarch/Dockerfile

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

app/vmauth/target_url.go

@@ -1,16 +1,58 @@
 package main
 
 import (
+	"fmt"
 	"net/url"
 	"path"
 	"strings"
 )
 
-func createTargetURL(prefix string, u *url.URL) string {
+func (up *URLPrefix) mergeURLs(requestURI *url.URL) *url.URL {
+	pu := up.getNextURL()
+	return mergeURLs(pu, requestURI)
+}
+
+func mergeURLs(uiURL, requestURI *url.URL) *url.URL {
+	targetURL := *uiURL
+	targetURL.Path += requestURI.Path
+	requestParams := requestURI.Query()
+	// fast path
+	if len(requestParams) == 0 {
+		return &targetURL
+	}
+	// merge query parameters from requests.
+	uiParams := targetURL.Query()
+	for k, v := range requestParams {
+		// skip clashed query params from original request
+		if exist := uiParams.Get(k); len(exist) > 0 {
+			continue
+		}
+		for i := range v {
+			uiParams.Add(k, v[i])
+		}
+	}
+	targetURL.RawQuery = uiParams.Encode()
+	return &targetURL
+}
+
+func createTargetURL(ui *UserInfo, uOrig *url.URL) (*url.URL, error) {
+	u := *uOrig
 	// Prevent from attacks with using `..` in r.URL.Path
 	u.Path = path.Clean(u.Path)
 	if !strings.HasPrefix(u.Path, "/") {
 		u.Path = "/" + u.Path
 	}
-	return prefix + u.RequestURI()
+	u.Path = strings.TrimSuffix(u.Path, "/")
+	for _, e := range ui.URLMap {
+		for _, sp := range e.SrcPaths {
+			if sp.match(u.Path) {
+				return e.URLPrefix.mergeURLs(&u), nil
+			}
+		}
+	}
+	if ui.URLPrefix != nil {
+		return ui.URLPrefix.mergeURLs(&u), nil
+	}
+	missingRouteRequests.Inc()
+	return nil, fmt.Errorf("missing route for %q", u.String())
 }

app/vmauth/target_url_test.go

@@ -5,22 +5,112 @@ import (
 	"testing"
 )
 
-func TestCreateTargetURL(t *testing.T) {
-	f := func(prefix, requestURI, expectedTarget string) {
+func TestCreateTargetURLSuccess(t *testing.T) {
+	f := func(ui *UserInfo, requestURI, expectedTarget string) {
 		t.Helper()
 		u, err := url.Parse(requestURI)
 		if err != nil {
 			t.Fatalf("cannot parse %q: %s", requestURI, err)
 		}
-		target := createTargetURL(prefix, u)
-		if target != expectedTarget {
+		target, err := createTargetURL(ui, u)
+		if err != nil {
+			t.Fatalf("unexpected error: %s", err)
+		}
+		if target.String() != expectedTarget {
 			t.Fatalf("unexpected target; got %q; want %q", target, expectedTarget)
 		}
 	}
-	f("http://foo.bar", "", "http://foo.bar/.")
-	f("http://foo.bar", "/", "http://foo.bar/")
-	f("http://foo.bar", "a/b?c=d", "http://foo.bar/a/b?c=d")
-	f("https://sss:3894/x/y", "/z", "https://sss:3894/x/y/z")
-	f("https://sss:3894/x/y", "/../../aaa", "https://sss:3894/x/y/aaa")
-	f("https://sss:3894/x/y", "/./asd/../../aaa?a=d&s=s/../d", "https://sss:3894/x/y/aaa?a=d&s=s/../d")
+	// Simple routing with `url_prefix`
+	f(&UserInfo{
+		URLPrefix: mustParseURL("http://foo.bar"),
+	}, "", "http://foo.bar/.")
+	f(&UserInfo{
+		URLPrefix: mustParseURL("http://foo.bar"),
+	}, "/", "http://foo.bar")
+	f(&UserInfo{
+		URLPrefix: mustParseURL("http://foo.bar/federate"),
+	}, "/", "http://foo.bar/federate")
+	f(&UserInfo{
+		URLPrefix: mustParseURL("http://foo.bar"),
+	}, "a/b?c=d", "http://foo.bar/a/b?c=d")
+	f(&UserInfo{
+		URLPrefix: mustParseURL("https://sss:3894/x/y"),
+	}, "/z", "https://sss:3894/x/y/z")
+	f(&UserInfo{
+		URLPrefix: mustParseURL("https://sss:3894/x/y"),
+	}, "/../../aaa", "https://sss:3894/x/y/aaa")
+	f(&UserInfo{
+		URLPrefix: mustParseURL("https://sss:3894/x/y"),
+	}, "/./asd/../../aaa?a=d&s=s/../d", "https://sss:3894/x/y/aaa?a=d&s=s%2F..%2Fd")
+
+	// Complex routing with `url_map`
+	ui := &UserInfo{
+		URLMap: []URLMap{
+			{
+				SrcPaths:  getSrcPaths([]string{"/api/v1/query"}),
+				URLPrefix: mustParseURL("http://vmselect/0/prometheus"),
+			},
+			{
+				SrcPaths:  getSrcPaths([]string{"/api/v1/write"}),
+				URLPrefix: mustParseURL("http://vminsert/0/prometheus"),
+			},
+		},
+		URLPrefix: mustParseURL("http://default-server"),
+	}
+	f(ui, "/api/v1/query?query=up", "http://vmselect/0/prometheus/api/v1/query?query=up")
+	f(ui, "/api/v1/write", "http://vminsert/0/prometheus/api/v1/write")
+	f(ui, "/api/v1/query_range", "http://default-server/api/v1/query_range")
+
+	// Complex routing regexp paths in `url_map`
+	ui = &UserInfo{
+		URLMap: []URLMap{
+			{
+				SrcPaths:  getSrcPaths([]string{"/api/v1/query(_range)?", "/api/v1/label/[^/]+/values"}),
+				URLPrefix: mustParseURL("http://vmselect/0/prometheus"),
+			},
+			{
+				SrcPaths:  getSrcPaths([]string{"/api/v1/write"}),
+				URLPrefix: mustParseURL("http://vminsert/0/prometheus"),
+			},
+		},
+		URLPrefix: mustParseURL("http://default-server"),
+	}
+	f(ui, "/api/v1/query?query=up", "http://vmselect/0/prometheus/api/v1/query?query=up")
+	f(ui, "/api/v1/query_range?query=up", "http://vmselect/0/prometheus/api/v1/query_range?query=up")
+	f(ui, "/api/v1/label/foo/values", "http://vmselect/0/prometheus/api/v1/label/foo/values")
+	f(ui, "/api/v1/write", "http://vminsert/0/prometheus/api/v1/write")
+	f(ui, "/api/v1/foo/bar", "http://default-server/api/v1/foo/bar")
+	f(&UserInfo{
+		URLPrefix: mustParseURL("http://foo.bar?extra_label=team=dev"),
+	}, "/api/v1/query", "http://foo.bar/api/v1/query?extra_label=team=dev")
+	f(&UserInfo{
+		URLPrefix: mustParseURL("http://foo.bar?extra_label=team=mobile"),
+	}, "/api/v1/query?extra_label=team=dev", "http://foo.bar/api/v1/query?extra_label=team%3Dmobile")
+
+}
+
+func TestCreateTargetURLFailure(t *testing.T) {
+	f := func(ui *UserInfo, requestURI string) {
+		t.Helper()
+		u, err := url.Parse(requestURI)
+		if err != nil {
+			t.Fatalf("cannot parse %q: %s", requestURI, err)
+		}
+		target, err := createTargetURL(ui, u)
+		if err == nil {
+			t.Fatalf("expecting non-nil error")
+		}
+		if target != nil {
+			t.Fatalf("unexpected target=%q; want empty string", target)
+		}
+	}
+	f(&UserInfo{}, "/foo/bar")
+	f(&UserInfo{
+		URLMap: []URLMap{
+			{
+				SrcPaths:  getSrcPaths([]string{"/api/v1/query"}),
+				URLPrefix: mustParseURL("http://foobar/baz"),
+			},
+		},
+	}, "/api/v1/write")
 }

app/vmbackup/README.md

@@ -1,6 +1,6 @@
-## vmbackup
+# vmbackup
 
-`vmbackup` creates VictoriaMetrics data backups from [instant snapshots](https://victoriametrics.github.io/Single-server-VictoriaMetrics.html#how-to-work-with-snapshots).
+`vmbackup` creates VictoriaMetrics data backups from [instant snapshots](https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html#how-to-work-with-snapshots).
 
 Supported storage systems for backups:
 
@@ -15,11 +15,11 @@ data between the existing backup and new backup. It saves time and costs on data
 
 Backup process can be interrupted at any time. It is automatically resumed from the interruption point when restarting `vmbackup` with the same args.
 
-Backed up data can be restored with [vmrestore](https://victoriametrics.github.io/vmrestore.html).
+Backed up data can be restored with [vmrestore](https://docs.victoriametrics.com/vmrestore.html).
 
 See [this article](https://medium.com/@valyala/speeding-up-backups-for-big-time-series-databases-533c1a927883) for more details.
 
-See also [vmbackuper](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/466) tool built on top of `vmbackup`. This tool simplifies
+See also [vmbackupmanager](https://docs.victoriametrics.com/vmbackupmanager.html) tool built on top of `vmbackup`. This tool simplifies
 creation of hourly, daily, weekly and monthly backups.
 
 
@@ -34,8 +34,8 @@ vmbackup -storageDataPath=</path/to/victoria-metrics-data> -snapshotName=<local-
 ```
 
 * `</path/to/victoria-metrics-data>` - path to VictoriaMetrics data pointed by `-storageDataPath` command-line flag in single-node VictoriaMetrics or in cluster `vmstorage`.
-  There is no need to stop VictoriaMetrics for creating backups, since they are performed from immutable [instant snapshots](https://victoriametrics.github.io/Single-server-VictoriaMetrics.html#how-to-work-with-snapshots).
-* `<local-snapshot>` is the snapshot to back up. See [how to create instant snapshots](https://victoriametrics.github.io/Single-server-VictoriaMetrics.html#how-to-work-with-snapshots).
+  There is no need to stop VictoriaMetrics for creating backups, since they are performed from immutable [instant snapshots](https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html#how-to-work-with-snapshots).
+* `<local-snapshot>` is the snapshot to back up. See [how to create instant snapshots](https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html#how-to-work-with-snapshots). `vmbackup` can create the snapshot on itself if `-snapshot.createURL` command-line flag is set to an url for creating snapshots. In this case `-snapshotName` flag isn't needed.
 * `<bucket>` is an already existing name for [GCS bucket](https://cloud.google.com/storage/docs/creating-buckets).
 * `<path/to/new/backup>` is the destination path where new backup will be placed.
 
@@ -72,7 +72,7 @@ Smart backups mean storing full daily backups into `YYYYMMDD` folders and creati
 vmbackup -snapshotName=<latest-snapshot> -dst=gcs://<bucket>/latest
 ```
 
-Where `<latest-snapshot>` is the latest [snapshot](https://victoriametrics.github.io/Single-server-VictoriaMetrics.html#how-to-work-with-snapshots).
+Where `<latest-snapshot>` is the latest [snapshot](https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html#how-to-work-with-snapshots).
 The command will upload only changed data to `gcs://<bucket>/latest`.
 
 * Run the following command once a day:
@@ -89,7 +89,7 @@ or from any day (`YYYYMMDD` backups). Note that hourly backup shouldn't run when
 
 Do not forget removing old snapshots and backups when they are no longer needed for saving storage costs.
 
-See also [vmbackuper tool](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/466) for automating smart backups.
+See also [vmbackupmanager tool](https://docs.victoriametrics.com/vmbackupmanager.html) for automating smart backups.
 
 
 ## How does it work?
@@ -123,8 +123,8 @@ See [this article](https://medium.com/@valyala/speeding-up-backups-for-big-time-
 * If the backup is slow, then try setting higher value for `-concurrency` flag. This will increase the number of concurrent workers that upload data to backup storage.
 * If `vmbackup` eats all the network bandwidth, then set `-maxBytesPerSecond` to the desired value.
 * If `vmbackup` has been interrupted due to temporary error, then just restart it with the same args. It will resume the backup process.
-* Backups created from [single-node VictoriaMetrics](https://victoriametrics.github.io/Single-server-VictoriaMetrics.html) cannot be restored
-  at [cluster VictoriaMetrics](https://victoriametrics.github.io/Cluster-VictoriaMetrics.html) and vice versa.
+* Backups created from [single-node VictoriaMetrics](https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html) cannot be restored
+  at [cluster VictoriaMetrics](https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html) and vice versa.
 
 
 ## Advanced usage
@@ -186,35 +186,41 @@ See [this article](https://medium.com/@valyala/speeding-up-backups-for-big-time-
     	Where to put the backup on the remote storage. Example: gcs://bucket/path/to/backup/dir, s3://bucket/path/to/backup/dir or fs:///path/to/local/backup/dir
     	-dst can point to the previous backup. In this case incremental backup is performed, i.e. only changed data is uploaded
   -envflag.enable
-    	Whether to enable reading flags from environment variables additionally to command line. Command line flag values have priority over values from environment vars. Flags are read only from command line if this flag isn't set
+    	Whether to enable reading flags from environment variables additionally to command line. Command line flag values have priority over values from environment vars. Flags are read only from command line if this flag isn't set. See https://docs.victoriametrics.com/#environment-variables for more details
   -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()
+  -loggerDisableTimestamps
+    	Whether to disable writing timestamps in logs
   -loggerErrorsPerSecondLimit int
-    	Per-second limit on the number of ERROR messages. If more than the given number of errors are emitted per second, then the remaining errors are suppressed. Zero value disables the rate limit (default 10)
+    	Per-second limit on the number of ERROR messages. If more than the given number of errors are emitted per second, the remaining errors are suppressed. Zero values disable the rate limit
   -loggerFormat string
     	Format for logs. Possible values: default, json (default "default")
   -loggerLevel string
     	Minimum level of errors to log. Possible values: INFO, WARN, ERROR, FATAL, PANIC (default "INFO")
   -loggerOutput string
     	Output for the logs. Supported values: stderr, stdout (default "stderr")
-  -maxBytesPerSecond value
+  -loggerTimezone string
+    	Timezone to use for timestamps in logs. Timezone must be a valid IANA Time Zone. For example: America/New_York, Europe/Berlin, Etc/GMT+3 or Local (default "UTC")
+  -loggerWarnsPerSecondLimit int
+    	Per-second limit on the number of WARN messages. If more than the given number of warns are emitted per second, then the remaining warns are suppressed. Zero values disable the rate limit
+  -maxBytesPerSecond size
     	The maximum upload speed. There is no limit if it is set to 0
-    	Supports the following optional suffixes for values: KB, MB, GB, KiB, MiB, GiB (default 0)
-  -memory.allowedBytes value
-    	Allowed size of system memory VictoriaMetrics caches may occupy. This option overrides -memory.allowedPercent if set to non-zero value. Too low value may increase cache miss rate, which usually results in higher CPU and disk IO usage. Too high value may evict too much data from OS page cache, which will result in higher disk IO usage
-    	Supports the following optional suffixes for values: KB, MB, GB, KiB, MiB, GiB (default 0)
+    	Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 0)
+  -memory.allowedBytes size
+    	Allowed size of system memory VictoriaMetrics caches may occupy. This option overrides -memory.allowedPercent if set to a non-zero value. Too low a value may increase the cache miss rate usually resulting in higher CPU and disk IO usage. Too high a value may evict too much data from OS page cache resulting in higher disk IO usage
+    	Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 0)
   -memory.allowedPercent float
-    	Allowed percent of system memory VictoriaMetrics caches may occupy. See also -memory.allowedBytes. Too low value may increase cache miss rate, which usually results in higher CPU and disk IO usage. Too high value may evict too much data from OS page cache, which will result in higher disk IO usage (default 60)
+    	Allowed percent of system memory VictoriaMetrics caches may occupy. See also -memory.allowedBytes. Too low a value may increase cache miss rate usually resulting in higher CPU and disk IO usage. Too high a value may evict too much data from OS page cache which will result in higher disk IO usage (default 60)
   -origin string
     	Optional origin directory on the remote storage with old backup for server-side copying when performing full backup. This speeds up full backups
   -snapshot.createURL string
-    	VictoriaMetrics create snapshot url. When this is given a snapshot will automatically be created during backup. Example: http://victoriametrics:8428/snaphsot/create
+    	VictoriaMetrics create snapshot url. When this is given a snapshot will automatically be created during backup. Example: http://victoriametrics:8428/snapshot/create . There is no need in setting -snapshotName if -snapshot.createURL is set
   -snapshot.deleteURL string
-    	VictoriaMetrics delete snapshot url. Optional. Will be generated from -snapshot.createURL if not provided. All created snaphosts will be automatically deleted. Example: http://victoriametrics:8428/snaphsot/delete
+    	VictoriaMetrics delete snapshot url. Optional. Will be generated from -snapshot.createURL if not provided. All created snapshots will be automatically deleted. Example: http://victoriametrics:8428/snapshot/delete
   -snapshotName string
-    	Name for the snapshot to backup. See https://victoriametrics.github.io/Single-server-VictoriaMetrics.html#how-to-work-with-snapshots
+    	Name for the snapshot to backup. See https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html#how-to-work-with-snapshots. There is no need in setting -snapshotName if -snapshot.createURL is set
   -storageDataPath string
     	Path to VictoriaMetrics data. Must match -storageDataPath from VictoriaMetrics or vmstorage (default "victoria-metrics-data")
   -version
@@ -229,14 +235,14 @@ It is recommended using [binary releases](https://github.com/VictoriaMetrics/Vic
 
 ### Development build
 
-1. [Install Go](https://golang.org/doc/install). The minimum supported version is Go 1.13.
-2. Run `make vmbackup` from the root folder of the repository.
+1. [Install Go](https://golang.org/doc/install). The minimum supported version is Go 1.16.
+2. Run `make vmbackup` from the root folder of [the repository](https://github.com/VictoriaMetrics/VictoriaMetrics).
    It builds `vmbackup` binary and puts it into the `bin` folder.
 
 ### Production build
 
 1. [Install docker](https://docs.docker.com/install/).
-2. Run `make vmbackup-prod` from the root folder of the repository.
+2. Run `make vmbackup-prod` from the root folder of [the repository](https://github.com/VictoriaMetrics/VictoriaMetrics).
    It builds `vmbackup-prod` binary and puts it into the `bin` folder.
 
 ### Building docker images

app/vmbackup/main.go

@@ -19,11 +19,11 @@ import (
 
 var (
 	storageDataPath   = flag.String("storageDataPath", "victoria-metrics-data", "Path to VictoriaMetrics data. Must match -storageDataPath from VictoriaMetrics or vmstorage")
-	snapshotName      = flag.String("snapshotName", "", "Name for the snapshot to backup. See https://victoriametrics.github.io/Single-server-VictoriaMetrics.html#how-to-work-with-snapshots")
+	snapshotName      = flag.String("snapshotName", "", "Name for the snapshot to backup. See https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html#how-to-work-with-snapshots. There is no need in setting -snapshotName if -snapshot.createURL is set")
 	snapshotCreateURL = flag.String("snapshot.createURL", "", "VictoriaMetrics create snapshot url. When this is given a snapshot will automatically be created during backup. "+
-		"Example: http://victoriametrics:8428/snaphsot/create")
+		"Example: http://victoriametrics:8428/snapshot/create . There is no need in setting -snapshotName if -snapshot.createURL is set")
 	snapshotDeleteURL = flag.String("snapshot.deleteURL", "", "VictoriaMetrics delete snapshot url. Optional. Will be generated from -snapshot.createURL if not provided. "+
-		"All created snaphosts will be automatically deleted. Example: http://victoriametrics:8428/snaphsot/delete")
+		"All created snapshots will be automatically deleted. Example: http://victoriametrics:8428/snapshot/delete")
 	dst = flag.String("dst", "", "Where to put the backup on the remote storage. "+
 		"Example: gcs://bucket/path/to/backup/dir, s3://bucket/path/to/backup/dir or fs:///path/to/local/backup/dir\n"+
 		"-dst can point to the previous backup. In this case incremental backup is performed, i.e. only changed data is uploaded")
@@ -41,7 +41,9 @@ func main() {
 	logger.Init()
 
 	if len(*snapshotCreateURL) > 0 {
-		logger.Infof("Snapshots enabled")
+		if len(*snapshotName) > 0 {
+			logger.Fatalf("-snapshotName shouldn't be set if -snapshot.createURL is set, since snapshots are created automatically in this case")
+		}
 		logger.Infof("Snapshot create url %s", *snapshotCreateURL)
 		if len(*snapshotDeleteURL) <= 0 {
 			err := flag.Set("snapshot.deleteURL", strings.Replace(*snapshotCreateURL, "/create", "/delete", 1))
@@ -99,7 +101,7 @@ func usage() {
 vmbackup performs backups for VictoriaMetrics data from instant snapshots to gcs, s3
 or local filesystem. Backed up data can be restored with vmrestore.
 
-See the docs at https://victoriametrics.github.io/vbackup.html .
+See the docs at https://docs.victoriametrics.com/vmbackup.html .
 `
 	flagutil.Usage(s)
 }