app/vmctl/terminal: fix builds for GOOS=freebsd and GOOS=openbsd

This is a follow-up for 8da9502df6

.github/ISSUE_TEMPLATE/bug_report.md

@@ -1,46 +0,0 @@
----
-name: Bug report
-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 to [upgrade](https://docs.victoriametrics.com/#how-to-upgrade) 
-to [the latest available release](https://github.com/VictoriaMetrics/VictoriaMetrics/releases)
-and verify whether the bug is reproducible there.
-It's also recommended to read the [troubleshooting docs](https://docs.victoriametrics.com/Troubleshooting.html).
-
-**To Reproduce**
-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)
-* [monitoring for VictoriaMetrics cluster](https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html#monitoring)
-
-**Version**
-The line returned when passing `--version` command line flag to the binary. For example:
-```
-$ ./victoria-metrics-prod --version
-victoria-metrics-20190730-121249-heads-single-node-0-g671d9e55
-```
-
-**Used command-line flags**
-Please provide the command-line flags used for running VictoriaMetrics and its components. 

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -0,0 +1,86 @@
+name: Bug report
+description: Create a report to help us improve
+labels: [bug]
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Before filling a bug report it would be great to [upgrade](https://docs.victoriametrics.com/#how-to-upgrade) 
+        to [the latest available release](https://github.com/VictoriaMetrics/VictoriaMetrics/releases)
+        and verify whether the bug is reproducible there.
+        It's also recommended to read the [troubleshooting docs](https://docs.victoriametrics.com/Troubleshooting.html) first.
+  - type: textarea
+    id: describe-the-bug
+    attributes:
+      label: Describe the bug
+      description: |
+        A clear and concise description of what the bug is.
+      placeholder: |
+        When I do `A` VictoriaMetrics does `B`. I expect it to do `C`.
+    validations:
+      required: true
+  - type: textarea
+    id: to-reproduce
+    attributes:
+      label: To Reproduce
+      description: |
+        Steps to reproduce the behavior.
+        If reproducing an issue requires some specific configuration file, please paste it here.
+      placeholder: |
+        Steps to reproduce the behavior.
+    validations:
+      required: true
+  - type: textarea
+    id: version
+    attributes:
+      label: Version
+      description: |
+        The line returned when passing `--version` command line flag to the binary. For example:
+        ```
+        $ ./victoria-metrics-prod --version
+        victoria-metrics-20190730-121249-heads-single-node-0-g671d9e55
+        ```
+    validations:
+      required: true
+  - type: textarea
+    id: logs
+    attributes:
+      label: Logs
+      description: |
+        Check if any warnings or errors were logged by VictoriaMetrics components
+        or components in communication with VictoriaMetrics (e.g. Prometheus, Grafana).
+    validations:
+      required: false
+  - type: textarea
+    id: screenshots
+    attributes:
+      label: Screenshots
+      description: |
+        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/grafana/dashboards/10229-victoriametrics/)
+          * [Grafana dashboard for VictoriaMetrics cluster](https://grafana.com/grafana/dashboards/11176-victoriametrics-cluster/)
+        
+        See how to setup monitoring here:
+          * [monitoring for single-node VictoriaMetrics](https://docs.victoriametrics.com/#monitoring)
+          * [monitoring for VictoriaMetrics cluster](https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html#monitoring)
+    validations:
+      required: false
+  - type: textarea
+    id: flags
+    attributes:
+      label: Used command-line flags
+      description: |
+        Please provide the command-line flags used for running VictoriaMetrics and its components.
+    validations:
+      required: false
+  - type: textarea
+    id: additional-info
+    attributes:
+      label: Additional information
+      placeholder: |
+        Additional information that doesn't fit elsewhere
+    validations:
+      required: false

.github/ISSUE_TEMPLATE/configuration.yml

@@ -0,0 +1,5 @@
+blank_issues_enabled: true
+contact_links:
+  - name: Ask on Slack
+    url: https://slack.victoriametrics.com/
+    about: You can ask for help here!

.github/ISSUE_TEMPLATE/feature_request.md

@@ -1,20 +0,0 @@
----
-name: Feature request
-about: Suggest an idea for this project
-title: ''
-labels: ''
-assignees: ''
-
----
-
-**Is your feature request related to a problem? Please describe.**
-A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
-
-**Describe the solution you'd like**
-A clear and concise description of what you want to happen.
-
-**Describe alternatives you've considered**
-A clear and concise description of any alternative solutions or features you've considered.
-
-**Additional context**
-Add any other context or screenshots about the feature request here.

.github/ISSUE_TEMPLATE/feature_request.yml

@@ -0,0 +1,43 @@
+name: Feature request
+description: Suggest an idea for this project
+labels: [enhancement]
+body:
+  - type: textarea
+    id: describe-the-problem
+    attributes:
+      label: Is your feature request related to a problem? Please describe
+      description: |
+        A clear and concise description of what the problem is.
+      placeholder: |
+        Ex. I'm always frustrated when [...]
+    validations:
+      required: false
+  - type: textarea
+    id: describe-the-solution
+    attributes:
+      label: Describe the solution you'd like
+      description: |
+        A clear and concise description of what you want to happen.
+    validations:
+      required: true
+  - type: textarea
+    id: alternative-solutions
+    attributes:
+      label: Describe alternatives you've considered
+      description: |
+        A clear and concise description of any alternative solutions or features you've considered.
+      placeholder: |
+        I have tried to do `A`, but that doesn't solve a problem completely.
+        I have tried to do `A` and `B`, but implementing this would be better.
+    validations:
+      required: false
+  - type: textarea
+    id: feature-additional-info
+    attributes:
+      label: Additional information
+      description: |
+        Additional information which you consider helpful for implementing this feature.
+      placeholder: |
+        Add any other context or screenshots about the feature request here.
+    validations:
+      required: false

.github/ISSUE_TEMPLATE/question.yml

@@ -0,0 +1,32 @@
+name: Question
+description: Ask a question regarding VictoriaMetrics or its components
+labels: [question]
+body:
+  - type: textarea
+    id: describe-the-component
+    attributes:
+      label: Is your question request related to a specific component?
+      placeholder: |
+        VictoriaMetrics, vmagent, vmalert, vmui, etc...
+    validations:
+      required: false
+  - type: textarea
+    id: describe-the-question
+    attributes:
+      label: Describe the question in detail
+      description: |
+        A clear and concise description of the issue and the question.
+    validations:
+      required: true
+  - type: checkboxes
+    id: troubleshooting
+    attributes:
+      label: Troubleshooting docs
+      description: I am familiar with the following troubleshooting docs
+      options:
+        - label: General - https://docs.victoriametrics.com/Troubleshooting.html
+          required: false
+        - label: vmagent - https://docs.victoriametrics.com/vmagent.html#troubleshooting
+          required: false
+        - label: vmalert - https://docs.victoriametrics.com/vmalert.html#troubleshooting
+          required: false

.github/workflows/check-licenses.yml

@@ -17,7 +17,7 @@ jobs:
       - name: Setup Go
         uses: actions/setup-go@main
         with:
-          go-version: 1.19.4
+          go-version: 1.20.3
         id: go
       - name: Code checkout
         uses: actions/checkout@master

.github/workflows/codeql-analysis-js.yml

@@ -0,0 +1,46 @@
+name: "CodeQL - JS"
+
+on:
+  push:
+    branches: [master, cluster]
+    paths:
+      - "**.js"
+  pull_request:
+    # The branches below must be a subset of the branches above
+    branches: [master, cluster]
+    paths:
+      - "**.js"
+  schedule:
+    - cron: "30 18 * * 2"
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+  
+jobs:
+  analyze:
+    name: Analyze
+    runs-on: ubuntu-latest
+    permissions:
+      actions: read
+      contents: read
+      security-events: write
+
+    strategy:
+      fail-fast: false
+      matrix:
+        language: ["javascript"]
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v3
+
+      - name: Initialize CodeQL
+        uses: github/codeql-action/init@v2
+        with:
+          languages: ${{ matrix.language }}
+
+      - name: Perform CodeQL Analysis
+        uses: github/codeql-action/analyze@v2
+        with:
+          category: "javascript"

.github/workflows/codeql-analysis.yml

@@ -13,12 +13,26 @@ name: "CodeQL"
 
 on:
   push:
-    branches: [ master, cluster ]
+    branches: [master, cluster]
+    paths-ignore:
+      - "docs/**"
+      - "**.md"
+      - "**.txt"
+      - "**.js"
   pull_request:
     # The branches below must be a subset of the branches above
-    branches: [ master, cluster ]
+    branches: [master, cluster]
+    paths-ignore:
+      - "docs/**"
+      - "**.md"
+      - "**.txt"
+      - "**.js"
   schedule:
-    - cron: '30 18 * * 2'
+    - cron: "30 18 * * 2"
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
 
 jobs:
   analyze:
@@ -32,45 +46,47 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        language: [ 'go', 'javascript' ]
+        language: ["go"]
         # CodeQL supports [ 'cpp', 'csharp', 'go', 'java', 'javascript', 'python', 'ruby' ]
         # Learn more about CodeQL language support at https://git.io/codeql-language-support
 
     steps:
-    - name: Checkout repository
-      uses: actions/checkout@v3
+      - name: Checkout repository
+        uses: actions/checkout@v3
 
-    - name: Set up Go
-      uses: actions/setup-go@v2
-      with:
-        go-version: 1.19
-      if: ${{ matrix.language == 'go' }}
+      - name: Set up Go
+        uses: actions/setup-go@v4
+        with:
+          go-version: 1.20.3
+          check-latest: true
+          cache: true
+        if: ${{ matrix.language == 'go' }}
 
-    # Initializes the CodeQL tools for scanning.
-    - name: Initialize CodeQL
-      uses: github/codeql-action/init@v2
-      with:
-        languages: ${{ matrix.language }}
-        # If you wish to specify custom queries, you can do so here or in a config file.
-        # By default, queries listed here will override any specified in a config file.
-        # Prefix the list here with "+" to use these queries and those in the config file.
-        # queries: ./path/to/local/query, your-org/your-repo/queries@main
+      # Initializes the CodeQL tools for scanning.
+      - name: Initialize CodeQL
+        uses: github/codeql-action/init@v2
+        with:
+          languages: ${{ matrix.language }}
+          # If you wish to specify custom queries, you can do so here or in a config file.
+          # By default, queries listed here will override any specified in a config file.
+          # Prefix the list here with "+" to use these queries and those in the config file.
+          # queries: ./path/to/local/query, your-org/your-repo/queries@main
 
-    # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
-    # If this step fails, then you should remove it and run the build manually (see below)
-    - name: Autobuild
-      uses: github/codeql-action/autobuild@v2
+      # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
+      # If this step fails, then you should remove it and run the build manually (see below)
+      - name: Autobuild
+        uses: github/codeql-action/autobuild@v2
 
-    # ℹ️ Command-line programs to run using the OS shell.
-    # 📚 https://git.io/JvXDl
+      # ℹ️ Command-line programs to run using the OS shell.
+      # 📚 https://git.io/JvXDl
 
-    # ✏️ If the Autobuild fails above, remove it and uncomment the following three lines
-    #    and modify them (or add more) to build your code if your project
-    #    uses a compiled language
+      # ✏️ If the Autobuild fails above, remove it and uncomment the following three lines
+      #    and modify them (or add more) to build your code if your project
+      #    uses a compiled language
 
-    #- run: |
-    #   make bootstrap
-    #   make release
+      #- run: |
+      #   make bootstrap
+      #   make release
 
-    - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@v2
+      - name: Perform CodeQL Analysis
+        uses: github/codeql-action/analyze@v2

.github/workflows/main.yml

@@ -1,45 +1,96 @@
 name: main
 on:
   push:
+    branches:
+      - master
+      - cluster
     paths-ignore:
-      - 'docs/**'
-      - '**.md'
+      - "docs/**"
+      - "**.md"
   pull_request:
+    branches:
+      - master
+      - cluster
     paths-ignore:
-      - 'docs/**'
-      - '**.md'
+      - "docs/**"
+      - "**.md"
 permissions:
   contents: read
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
 jobs:
-  build:
-    name: Build
+  lint:
+    name: lint
     runs-on: ubuntu-latest
     steps:
-      - name: Setup Go
-        uses: actions/setup-go@main
-        with:
-          go-version: 1.19.4
-        id: go
       - name: Code checkout
-        uses: actions/checkout@master
+        uses: actions/checkout@v3
+
+      - name: Setup Go
+        uses: actions/setup-go@v4
+        with:
+          go-version: 1.20.3
+          check-latest: true
+          cache: true
+
       - name: Dependencies
         run: |
-          make install-golint
-          make install-errcheck
           make install-golangci-lint
-      - name: Build
-        run: |
-          export PATH=$PATH:$(go env GOPATH)/bin # temporary fix. See https://github.com/actions/setup-go/issues/14
           make check-all
           git diff --exit-code
-          make test-full
-          make test-pure
-          make test-full-386
-          make victoria-metrics-crossbuild
-          make vmuitils-crossbuild
+
+  test:
+    needs: lint
+    strategy:
+      matrix:
+        scenario: ["test-full", "test-pure", "test-full-386"]
+    name: test
+    runs-on: ubuntu-latest
+    steps:
+      - name: Code checkout
+        uses: actions/checkout@v3
+
+      - name: Setup Go
+        uses: actions/setup-go@v4
+        with:
+          go-version: 1.20.3
+          check-latest: true
+          cache: true
+
+      - name: run tests
+        run: |
+          make ${{ matrix.scenario}}
+
       - name: Publish coverage
         uses: codecov/codecov-action@v3
         with:
           file: ./coverage.txt
 
+  build:
+    needs: test
+    name: build
+    runs-on: ubuntu-latest
+    steps:
+      - name: Code checkout
+        uses: actions/checkout@v3
+
+      - name: Setup Go
+        id: go
+        uses: actions/setup-go@v4
+        with:
+          go-version: 1.20.3
+          check-latest: true
+          cache: true
+
+      - uses: actions/cache@v3
+        with:
+          path: gocache-for-docker
+          key:  gocache-docker-${{ runner.os }}-${{ steps.go.outputs.go-version }}-${{ hashFiles('go.mod') }}
+
+      - name: Build
+        run: |
+          make victoria-metrics-crossbuild
+          make vmuitils-crossbuild

.github/workflows/nightly-build.yml

@@ -0,0 +1,48 @@
+name: nightly-build
+on:
+  schedule:
+    # Daily at 2:48am
+    - cron: '48 2 * * *'
+
+permissions:
+  contents: read
+
+jobs:
+  build:
+    name: Build
+    runs-on: ubuntu-latest
+    steps:
+      - name: Login to Docker Hub
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+      - name: Setup Go
+        uses: actions/setup-go@main
+        with:
+          go-version: 1.20.3
+        id: go
+
+      - name: Setup docker scan
+        run: |
+          mkdir -p ~/.docker/cli-plugins && \
+          curl https://github.com/docker/scan-cli-plugin/releases/latest/download/docker-scan_linux_amd64 -L -s -S -o ~/.docker/cli-plugins/docker-scan &&\
+          chmod +x ~/.docker/cli-plugins/docker-scan
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v2
+      
+      - name: Code checkout
+        uses: actions/checkout@master
+
+      - uses: actions/cache@v3
+        with:
+          path: gocache-for-docker
+          key: gocache-docker-${{ runner.os }}-${{ steps.go.outputs.go-version }}-${{ hashFiles('go.mod') }}
+
+      - name: build & publish
+        run: |
+          docker scan --severity=medium --login --token "$SNYK_TOKEN" --accept-license
+          LATEST_TAG=nightly PKG_TAG=nightly make publish
+        env: 
+          SNYK_TOKEN: ${{ secrets.SNYK_AUTH_TOKEN }}

.golangci.yml

@@ -0,0 +1,19 @@
+run:
+  timeout: 2m
+
+linters:
+  enable:
+  - revive
+
+issues:
+  exclude-rules:
+  - linters:
+    - staticcheck
+    text: "SA(4003|1019|5011):"
+  include:
+  - EXC0012
+  - EXC0014
+
+linters-settings:
+  errcheck:
+    exclude: ./errcheck_excludes.txt

.wwhrd.yml

@@ -3,3 +3,4 @@ allowlist:
   - MIT
   - BSD-3-Clause
   - BSD-2-Clause
+  - ISC

LICENSE

@@ -175,7 +175,7 @@
 
    END OF TERMS AND CONDITIONS
 
-   Copyright 2019-2022 VictoriaMetrics, Inc.
+   Copyright 2019-2023 VictoriaMetrics, Inc.
 
    Licensed under the Apache License, Version 2.0 (the "License");
    you may not use this file except in compliance with the License.

Makefile

@@ -3,6 +3,7 @@ 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 -d' ' -f2 | cut -c 1-8)))
+LATEST_TAG ?= latest
 
 PKG_TAG ?= $(shell git tag -l --points-at HEAD)
 ifeq ($(PKG_TAG),)
@@ -140,9 +141,12 @@ vmutils-windows-amd64: \
 	vmagent-windows-amd64 \
 	vmalert-windows-amd64 \
 	vmauth-windows-amd64 \
+	vmbackup-windows-amd64 \
+	vmrestore-windows-amd64 \
 	vmctl-windows-amd64
 
 victoria-metrics-crossbuild: \
+	victoria-metrics-linux-386 \
 	victoria-metrics-linux-amd64 \
 	victoria-metrics-linux-arm64 \
 	victoria-metrics-linux-arm \
@@ -154,6 +158,7 @@ victoria-metrics-crossbuild: \
 	victoria-metrics-openbsd-amd64
 
 vmutils-crossbuild: \
+	vmutils-linux-386 \
 	vmutils-linux-amd64 \
 	vmutils-linux-arm64 \
 	vmutils-linux-arm \
@@ -166,23 +171,29 @@ vmutils-crossbuild: \
 	vmutils-windows-amd64
 
 publish-release:
-	git checkout $(TAG) && $(MAKE) release publish && \
-		git checkout $(TAG)-cluster && $(MAKE) release publish && \
-		git checkout $(TAG)-enterprise && $(MAKE) release publish && \
-		git checkout $(TAG)-enterprise-cluster && $(MAKE) release publish
+	git checkout $(TAG) && LATEST_TAG=stable $(MAKE) release publish && \
+		git checkout $(TAG)-cluster && LATEST_TAG=cluster-stable $(MAKE) release publish && \
+		git checkout $(TAG)-enterprise && LATEST_TAG=enterprise-stable $(MAKE) release publish && \
+		git checkout $(TAG)-enterprise-cluster && LATEST_TAG=enterprise-cluster-stable $(MAKE) release publish
 
 release: \
 	release-victoria-metrics \
 	release-vmutils
 
 release-victoria-metrics: \
+	release-victoria-metrics-linux-386 \
 	release-victoria-metrics-linux-amd64 \
 	release-victoria-metrics-linux-arm \
 	release-victoria-metrics-linux-arm64 \
 	release-victoria-metrics-darwin-amd64 \
 	release-victoria-metrics-darwin-arm64 \
 	release-victoria-metrics-freebsd-amd64 \
-	release-victoria-metrics-openbsd-amd64
+	release-victoria-metrics-openbsd-amd64 \
+	release-victoria-metrics-windows-amd64
+
+# adds i386 arch
+release-victoria-metrics-linux-386:
+	GOOS=linux GOARCH=386 $(MAKE) release-victoria-metrics-goos-goarch
 
 release-victoria-metrics-linux-amd64:
 	GOOS=linux GOARCH=amd64 $(MAKE) release-victoria-metrics-goos-goarch
@@ -205,6 +216,9 @@ release-victoria-metrics-freebsd-amd64:
 release-victoria-metrics-openbsd-amd64:
 	GOOS=openbsd GOARCH=amd64 $(MAKE) release-victoria-metrics-goos-goarch
 
+release-victoria-metrics-windows-amd64:
+	GOARCH=amd64 $(MAKE) release-victoria-metrics-windows-goarch
+
 release-victoria-metrics-goos-goarch: victoria-metrics-$(GOOS)-$(GOARCH)-prod
 	cd bin && \
 		tar --transform="flags=r;s|-$(GOOS)-$(GOARCH)||" -czf victoria-metrics-$(GOOS)-$(GOARCH)-$(PKG_TAG).tar.gz \
@@ -214,7 +228,18 @@ release-victoria-metrics-goos-goarch: victoria-metrics-$(GOOS)-$(GOARCH)-prod
 			| sed s/-$(GOOS)-$(GOARCH)-prod/-prod/ > victoria-metrics-$(GOOS)-$(GOARCH)-$(PKG_TAG)_checksums.txt
 	cd bin && rm -rf victoria-metrics-$(GOOS)-$(GOARCH)-prod
 
+release-victoria-metrics-windows-goarch: victoria-metrics-windows-$(GOARCH)-prod
+	cd bin && \
+		zip victoria-metrics-windows-$(GOARCH)-$(PKG_TAG).zip \
+			victoria-metrics-windows-$(GOARCH)-prod.exe \
+		&& sha256sum victoria-metrics-windows-$(GOARCH)-$(PKG_TAG).zip \
+			victoria-metrics-windows-$(GOARCH)-prod.exe \
+			> victoria-metrics-windows-$(GOARCH)-$(PKG_TAG)_checksums.txt
+	cd bin && rm -rf \
+		victoria-metrics-windows-$(GOARCH)-prod.exe
+
 release-vmutils: \
+	release-vmutils-linux-386 \
 	release-vmutils-linux-amd64 \
 	release-vmutils-linux-arm64 \
 	release-vmutils-linux-arm \
@@ -224,6 +249,9 @@ release-vmutils: \
 	release-vmutils-openbsd-amd64 \
 	release-vmutils-windows-amd64
 
+release-vmutils-linux-386:
+	GOOS=linux GOARCH=386 $(MAKE) release-vmutils-goos-goarch
+	
 release-vmutils-linux-amd64:
 	GOOS=linux GOARCH=amd64 $(MAKE) release-vmutils-goos-goarch
 
@@ -283,26 +311,33 @@ release-vmutils-windows-goarch: \
 	vmagent-windows-$(GOARCH)-prod \
 	vmalert-windows-$(GOARCH)-prod \
 	vmauth-windows-$(GOARCH)-prod \
+	vmbackup-windows-$(GOARCH)-prod \
+	vmrestore-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-$(GOARCH)-prod.exe \
+			vmbackup-windows-$(GOARCH)-prod.exe \
+			vmrestore-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-$(GOARCH)-prod.exe \
+			vmbackup-windows-$(GOARCH)-prod.exe \
+			vmrestore-windows-$(GOARCH)-prod.exe \
 			vmctl-windows-$(GOARCH)-prod.exe \
 			> vmutils-windows-$(GOARCH)-$(PKG_TAG)_checksums.txt
 	cd bin && rm -rf \
 		vmagent-windows-$(GOARCH)-prod.exe \
 		vmalert-windows-$(GOARCH)-prod.exe \
 		vmauth-windows-$(GOARCH)-prod.exe \
+		vmbackup-windows-$(GOARCH)-prod.exe \
+		vmrestore-windows-$(GOARCH)-prod.exe \
 		vmctl-windows-$(GOARCH)-prod.exe
 
-
 pprof-cpu:
 	go tool pprof -trim_path=github.com/VictoriaMetrics/VictoriaMetrics@ $(PPROF_FILE)
 
@@ -314,21 +349,7 @@ vet:
 	go vet ./lib/...
 	go vet ./app/...
 
-lint: install-golint
-	golint lib/...
-	golint app/...
-
-install-golint:
-	which golint || go install golang.org/x/lint/golint@latest
-
-errcheck: install-errcheck
-	errcheck -exclude=errcheck_excludes.txt ./lib/...
-	errcheck -exclude=errcheck_excludes.txt ./app/...
-
-install-errcheck:
-	which errcheck || go install github.com/kisielk/errcheck@latest
-
-check-all: fmt vet lint errcheck golangci-lint govulncheck
+check-all: fmt vet golangci-lint govulncheck
 
 test:
 	go test ./lib/... ./app/...
@@ -379,10 +400,10 @@ install-qtc:
 
 
 golangci-lint: install-golangci-lint
-	golangci-lint run --exclude '(SA4003|SA1019|SA5011):' -D errcheck -D structcheck --timeout 2m
+	golangci-lint run
 
 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 v1.48.0
+	which golangci-lint || curl -sSfL https://raw.githubusercontent.com/golangci/golangci-lint/master/install.sh | sh -s -- -b $(shell go env GOPATH)/bin v1.51.2
 
 govulncheck: install-govulncheck
 	govulncheck ./...

README.md

@@ -2,6 +2,7 @@
 
 [![Latest Release](https://img.shields.io/github/release/VictoriaMetrics/VictoriaMetrics.svg?style=flat-square)](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/latest)
 [![Docker Pulls](https://img.shields.io/docker/pulls/victoriametrics/victoria-metrics.svg?maxAge=604800)](https://hub.docker.com/r/victoriametrics/victoria-metrics)
+[![victoriametrics](https://snapcraft.io/victoriametrics/badge.svg)](https://snapcraft.io/victoriametrics)
 [![Slack](https://img.shields.io/badge/join%20slack-%23victoriametrics-brightgreen.svg)](https://slack.victoriametrics.com/)
 [![GitHub license](https://img.shields.io/github/license/VictoriaMetrics/VictoriaMetrics.svg)](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/LICENSE)
 [![Go Report](https://goreportcard.com/badge/github.com/VictoriaMetrics/VictoriaMetrics)](https://goreportcard.com/report/github.com/VictoriaMetrics/VictoriaMetrics)
@@ -39,20 +40,38 @@ VictoriaMetrics has the following prominent features:
 * It can be used as long-term storage for Prometheus. See [these docs](#prometheus-setup) for details.
 * It can be used as a drop-in replacement for Prometheus in Grafana, because it supports [Prometheus querying API](#prometheus-querying-api-usage).
 * It can be used as a drop-in replacement for Graphite in Grafana, because it supports [Graphite API](#graphite-api-usage).
-* It features easy setup and operation:
-  * VictoriaMetrics consists of a single [small executable](https://medium.com/@valyala/stripping-dependency-bloat-in-victoriametrics-docker-image-983fb5912b0d) without external dependencies.
+  VictoriaMetrics allows reducing infrastructure costs by more than 10x comparing to Graphite - see [this case study](https://docs.victoriametrics.com/CaseStudies.html#grammarly).
+* It is easy to setup and operate:
+  * VictoriaMetrics consists of a single [small executable](https://medium.com/@valyala/stripping-dependency-bloat-in-victoriametrics-docker-image-983fb5912b0d)
+    without external dependencies.
   * All the configuration is done via explicit command-line flags with reasonable defaults.
   * All the data is stored in a single directory pointed by `-storageDataPath` command-line flag.
-  * Easy and fast backups from [instant snapshots](https://medium.com/@valyala/how-victoriametrics-makes-instant-snapshots-for-multi-terabyte-time-series-data-e1f3fb0e0282) to S3 or GCS can be done with [vmbackup](https://docs.victoriametrics.com/vmbackup.html) / [vmrestore](https://docs.victoriametrics.com/vmrestore.html) tools. See [this article](https://medium.com/@valyala/speeding-up-backups-for-big-time-series-databases-533c1a927883) for more details.
-* It implements PromQL-based query language - [MetricsQL](https://docs.victoriametrics.com/MetricsQL.html), which provides improved functionality on top of PromQL.
+  * Easy and fast backups from [instant snapshots](https://medium.com/@valyala/how-victoriametrics-makes-instant-snapshots-for-multi-terabyte-time-series-data-e1f3fb0e0282)
+    can be done with [vmbackup](https://docs.victoriametrics.com/vmbackup.html) / [vmrestore](https://docs.victoriametrics.com/vmrestore.html) tools.
+    See [this article](https://medium.com/@valyala/speeding-up-backups-for-big-time-series-databases-533c1a927883) for more details.
+* It implements PromQL-like query language - [MetricsQL](https://docs.victoriametrics.com/MetricsQL.html), which provides improved functionality on top of PromQL.
 * It provides global query view. Multiple Prometheus instances or any other data sources may ingest data into VictoriaMetrics. Later this data may be queried via a single query.
-* It provides high performance and good vertical and horizontal scalability for both [data ingestion](https://medium.com/@valyala/high-cardinality-tsdb-benchmarks-victoriametrics-vs-timescaledb-vs-influxdb-13e6ee64dd6b) and [data querying](https://medium.com/@valyala/when-size-matters-benchmarking-victoriametrics-vs-timescale-and-influxdb-6035811952d4). It [outperforms InfluxDB and TimescaleDB by up to 20x](https://medium.com/@valyala/measuring-vertical-scalability-for-time-series-databases-in-google-cloud-92550d78d8ae).
-* It [uses 10x less RAM than InfluxDB](https://medium.com/@valyala/insert-benchmarks-with-inch-influxdb-vs-victoriametrics-e31a41ae2893) and [up to 7x less RAM than Prometheus, Thanos or Cortex](https://valyala.medium.com/prometheus-vs-victoriametrics-benchmark-on-node-exporter-metrics-4ca29c75590f) when dealing with millions of unique time series (aka [high cardinality](https://docs.victoriametrics.com/FAQ.html#what-is-high-cardinality)).
+* It provides high performance and good vertical and horizontal scalability for both
+  [data ingestion](https://medium.com/@valyala/high-cardinality-tsdb-benchmarks-victoriametrics-vs-timescaledb-vs-influxdb-13e6ee64dd6b)
+  and [data querying](https://medium.com/@valyala/when-size-matters-benchmarking-victoriametrics-vs-timescale-and-influxdb-6035811952d4).
+  It [outperforms InfluxDB and TimescaleDB by up to 20x](https://medium.com/@valyala/measuring-vertical-scalability-for-time-series-databases-in-google-cloud-92550d78d8ae).
+* It [uses 10x less RAM than InfluxDB](https://medium.com/@valyala/insert-benchmarks-with-inch-influxdb-vs-victoriametrics-e31a41ae2893)
+  and [up to 7x less RAM than Prometheus, Thanos or Cortex](https://valyala.medium.com/prometheus-vs-victoriametrics-benchmark-on-node-exporter-metrics-4ca29c75590f)
+  when dealing with millions of unique time series (aka [high cardinality](https://docs.victoriametrics.com/FAQ.html#what-is-high-cardinality)).
 * It is optimized for time series with [high churn rate](https://docs.victoriametrics.com/FAQ.html#what-is-high-churn-rate).
-* It provides high data compression, so [up to 70x more data points](https://medium.com/@valyala/when-size-matters-benchmarking-victoriametrics-vs-timescale-and-influxdb-6035811952d4) may be crammed into limited storage comparing to TimescaleDB and [up to 7x less storage space is required compared to Prometheus, Thanos or Cortex](https://valyala.medium.com/prometheus-vs-victoriametrics-benchmark-on-node-exporter-metrics-4ca29c75590f).
-* It is optimized for storage with high-latency IO and low IOPS (HDD and network storage in AWS, Google Cloud, Microsoft Azure, etc). See [disk IO graphs from these benchmarks](https://medium.com/@valyala/high-cardinality-tsdb-benchmarks-victoriametrics-vs-timescaledb-vs-influxdb-13e6ee64dd6b).
-* A single-node VictoriaMetrics may substitute moderately sized clusters built with competing solutions such as Thanos, M3DB, Cortex, InfluxDB or TimescaleDB. See [vertical scalability benchmarks](https://medium.com/@valyala/measuring-vertical-scalability-for-time-series-databases-in-google-cloud-92550d78d8ae), [comparing Thanos to VictoriaMetrics cluster](https://medium.com/@valyala/comparing-thanos-to-victoriametrics-cluster-b193bea1683) and [Remote Write Storage Wars](https://promcon.io/2019-munich/talks/remote-write-storage-wars/) talk from [PromCon 2019](https://promcon.io/2019-munich/talks/remote-write-storage-wars/).
-* It protects the storage from data corruption on unclean shutdown (i.e. OOM, hardware reset or `kill -9`) thanks to [the storage architecture](https://medium.com/@valyala/how-victoriametrics-makes-instant-snapshots-for-multi-terabyte-time-series-data-e1f3fb0e0282).
+* It provides high data compression, so up to 70x more data points may be stored into limited storage comparing to TimescaleDB
+  according to [these benchmarks](https://medium.com/@valyala/when-size-matters-benchmarking-victoriametrics-vs-timescale-and-influxdb-6035811952d4)
+  and up to 7x less storage space is required compared to Prometheus, Thanos or Cortex
+  according to [this benchmark](https://valyala.medium.com/prometheus-vs-victoriametrics-benchmark-on-node-exporter-metrics-4ca29c75590f).
+* It is optimized for storage with high-latency IO and low IOPS (HDD and network storage in AWS, Google Cloud, Microsoft Azure, etc).
+  See [disk IO graphs from these benchmarks](https://medium.com/@valyala/high-cardinality-tsdb-benchmarks-victoriametrics-vs-timescaledb-vs-influxdb-13e6ee64dd6b).
+* A single-node VictoriaMetrics may substitute moderately sized clusters built with competing solutions such as Thanos, M3DB, Cortex, InfluxDB or TimescaleDB.
+  See [vertical scalability benchmarks](https://medium.com/@valyala/measuring-vertical-scalability-for-time-series-databases-in-google-cloud-92550d78d8ae),
+  [comparing Thanos to VictoriaMetrics cluster](https://medium.com/@valyala/comparing-thanos-to-victoriametrics-cluster-b193bea1683)
+  and [Remote Write Storage Wars](https://promcon.io/2019-munich/talks/remote-write-storage-wars/) talk
+  from [PromCon 2019](https://promcon.io/2019-munich/talks/remote-write-storage-wars/).
+* It protects the storage from data corruption on unclean shutdown (i.e. OOM, hardware reset or `kill -9`) thanks to
+  [the storage architecture](https://medium.com/@valyala/how-victoriametrics-makes-instant-snapshots-for-multi-terabyte-time-series-data-e1f3fb0e0282).
 * It supports metrics' scraping, ingestion and [backfilling](#backfilling) via the following protocols:
   * [Metrics scraping from Prometheus exporters](#how-to-scrape-prometheus-exporters-such-as-node-exporter).
   * [Prometheus remote write API](#prometheus-setup).
@@ -65,11 +84,15 @@ VictoriaMetrics has the following prominent features:
   * [Arbitrary CSV data](#how-to-import-csv-data).
   * [Native binary format](#how-to-import-data-in-native-format).
   * [DataDog agent or DogStatsD](#how-to-send-data-from-datadog-agent).
+* It supports powerful [stream aggregation](https://docs.victoriametrics.com/stream-aggregation.html), which can be used as a [statsd](https://github.com/statsd/statsd) alternative.
 * It supports metrics [relabeling](#relabeling).
-* It can deal with [high cardinality issues](https://docs.victoriametrics.com/FAQ.html#what-is-high-cardinality) and [high churn rate](https://docs.victoriametrics.com/FAQ.html#what-is-high-churn-rate) issues via [series limiter](#cardinality-limiter).
-* It ideally works with big amounts of time series data from APM, Kubernetes, IoT sensors, connected cars, industrial telemetry, financial data and various [Enterprise workloads](https://docs.victoriametrics.com/enterprise.html).
+* It can deal with [high cardinality issues](https://docs.victoriametrics.com/FAQ.html#what-is-high-cardinality) and
+  [high churn rate](https://docs.victoriametrics.com/FAQ.html#what-is-high-churn-rate) issues via [series limiter](#cardinality-limiter).
+* It ideally works with big amounts of time series data from APM, Kubernetes, IoT sensors, connected cars, industrial telemetry, financial data
+  and various [Enterprise workloads](https://docs.victoriametrics.com/enterprise.html).
 * It has open source [cluster version](https://github.com/VictoriaMetrics/VictoriaMetrics/tree/cluster).
-* It can store data on [NFS-based storages](https://en.wikipedia.org/wiki/Network_File_System) such as [Amazon EFS](https://aws.amazon.com/efs/) and [Google Filestore](https://cloud.google.com/filestore).
+* It can store data on [NFS-based storages](https://en.wikipedia.org/wiki/Network_File_System) such as [Amazon EFS](https://aws.amazon.com/efs/)
+  and [Google Filestore](https://cloud.google.com/filestore).
 
 See also [various Articles about VictoriaMetrics](https://docs.victoriametrics.com/Articles.html).
 
@@ -84,7 +107,7 @@ Case studies:
 * [Brandwatch](https://docs.victoriametrics.com/CaseStudies.html#brandwatch)
 * [CERN](https://docs.victoriametrics.com/CaseStudies.html#cern)
 * [COLOPL](https://docs.victoriametrics.com/CaseStudies.html#colopl)
-* [Dreamteam](https://docs.victoriametrics.com/CaseStudies.html#dreamteam)
+* [Dig Security](https://docs.victoriametrics.com/CaseStudies.html#dig-security)
 * [Fly.io](https://docs.victoriametrics.com/CaseStudies.html#flyio)
 * [German Research Center for Artificial Intelligence](https://docs.victoriametrics.com/CaseStudies.html#german-research-center-for-artificial-intelligence)
 * [Grammarly](https://docs.victoriametrics.com/CaseStudies.html#grammarly)
@@ -105,11 +128,22 @@ See also [articles and slides about VictoriaMetrics from our users](https://docs
 
 ## Operation
 
-### How to start VictoriaMetrics
+### Install
 
-Just download [VictoriaMetrics executable](https://github.com/VictoriaMetrics/VictoriaMetrics/releases) or [Docker image](https://hub.docker.com/r/victoriametrics/victoria-metrics/) and start it with the desired command-line flags.
+To quickly try VictoriaMetrics, just download [VictoriaMetrics executable](https://github.com/VictoriaMetrics/VictoriaMetrics/releases) or [Docker image](https://hub.docker.com/r/victoriametrics/victoria-metrics/) and start it with the desired command-line flags.
 See also [QuickStart guide](https://docs.victoriametrics.com/Quick-Start.html) for additional information.
 
+VictoriaMetrics can also be installed via these installation methods:
+
+* [Helm charts for single-node and cluster versions of VictoriaMetrics](https://github.com/VictoriaMetrics/helm-charts).
+* [Kubernetes operator for VictoriaMetrics](https://github.com/VictoriaMetrics/operator).
+* [Ansible role for installing cluster VictoriaMetrics (by VictoriaMetrics)](https://github.com/VictoriaMetrics/ansible-playbooks).
+* [Ansible role for installing cluster VictoriaMetrics (by community)](https://github.com/Slapper/ansible-victoriametrics-cluster-role).
+* [Ansible role for installing single-node VictoriaMetrics (by community)](https://github.com/dreamteam-gg/ansible-victoriametrics-role).
+* [Snap package for VictoriaMetrics](https://snapcraft.io/victoriametrics).
+
+### How to start VictoriaMetrics
+
 The following command-line flags are used the most:
 
 * `-storageDataPath` - VictoriaMetrics stores all the data in this directory. Default path is `victoria-metrics-data` in the current working directory.
@@ -168,7 +202,7 @@ Changing scrape configuration is possible with text editor:
 vi $SNAP_DATA/var/snap/victoriametrics/current/etc/victoriametrics-scrape-config.yaml
 ```
 
-After changes were made, trigger config re-read with the command `curl 127.0.0.1:8248/-/reload`.
+After changes were made, trigger config re-read with the command `curl 127.0.0.1:8428/-/reload`.
 
 ## Prometheus setup
 
@@ -271,6 +305,8 @@ Prometheus doesn't drop data during VictoriaMetrics restart. See [this article](
 VictoriaMetrics provides UI for query troubleshooting and exploration. The UI is available at `http://victoriametrics:8428/vmui`.
 The UI allows exploring query results via graphs and tables.
 It also provides the following features:
+
+- [metrics explorer](#metrics-explorer)
 - [cardinality explorer](#cardinality-explorer)
 - [query tracer](#query-tracing)
 - [top queries explorer](#top-queries)
@@ -306,9 +342,21 @@ See the [example VMUI at VictoriaMetrics playground](https://play.victoriametric
 * queries with the biggest average execution duration;
 * queries that took the most summary time for execution.
 
+## Metrics explorer
+
+[VMUI](#vmui) provides an ability to explore metrics exported by a particular `job` / `instance` in the following way:
+
+1. Open the `vmui` at `http://victoriametrics:8428/vmui/`.
+2. Click the `Explore metrics` tab.
+3. Select the `job` you want to explore.
+4. Optionally select the `instance` for the selected job to explore.
+5. Select metrics you want to explore and compare.
+
+It is possible to change the selected time range for the graphs in the top right corner.
+
 ## Cardinality explorer
 
-VictoriaMetrics provides an ability to explore time series cardinality at `cardinality` tab in [vmui](#vmui) in the following ways:
+VictoriaMetrics provides an ability to explore time series cardinality at `Explore cardinality` tab in [vmui](#vmui) in the following ways:
 
 - To identify metric names with the highest number of series.
 - To identify labels with the highest number of series.
@@ -363,7 +411,7 @@ DataDog agent allows configuring destinations for metrics sending via ENV variab
 or via [configuration file](https://docs.datadoghq.com/agent/guide/agent-configuration-files/) in section `dd_url`.
 
 <p align="center">
-  <img src="Single-server-VictoriaMetrics-sending_DD_metrics_to_VM.png" width="800">
+  <img src="docs/Single-server-VictoriaMetrics-sending_DD_metrics_to_VM.png" width="800">
 </p>
 
 To configure DataDog agent via ENV variable add the following prefix:
@@ -397,7 +445,7 @@ DataDog allows configuring [Dual Shipping](https://docs.datadoghq.com/agent/guid
 sending via ENV variable `DD_ADDITIONAL_ENDPOINTS` or via configuration file `additional_endpoints`.
  
 <p align="center">
-  <img src="Single-server-VictoriaMetrics-sending_DD_metrics_to_VM_and_DD.png" width="800">
+  <img src="docs/Single-server-VictoriaMetrics-sending_DD_metrics_to_VM_and_DD.png" width="800">
 </p>
  
 Run DataDog using the following ENV variable with VictoriaMetrics as additional metrics receiver:
@@ -580,7 +628,6 @@ The `__graphite__` pseudo-label supports e.g. alternate regexp filters such as `
 
 VictoriaMetrics also supports Graphite query language - see [these docs](#graphite-render-api-usage).
 
-
 ## How to send data from OpenTSDB-compatible agents
 
 VictoriaMetrics supports [telnet put protocol](http://opentsdb.net/docs/build/html/api_telnet/put.html)
@@ -695,21 +742,45 @@ All the Prometheus querying API handlers can be prepended with `/prometheus` pre
 
 ### Prometheus querying API enhancements
 
-VictoriaMetrics accepts optional `extra_label=<label_name>=<label_value>` query arg, which can be used for enforcing additional label filters for queries. For example,
-`/api/v1/query_range?extra_label=user_id=123&extra_label=group_id=456&query=<query>` would automatically add `{user_id="123",group_id="456"}` label filters to the given `<query>`. This functionality can be used for limiting the scope of time series visible to the given tenant. It is expected that the `extra_label` query args are automatically set by auth proxy sitting in front of VictoriaMetrics. See [vmauth](https://docs.victoriametrics.com/vmauth.html) and [vmgateway](https://docs.victoriametrics.com/vmgateway.html) as examples of such proxies.
+VictoriaMetrics accepts optional `extra_label=<label_name>=<label_value>` query arg, which can be used
+for enforcing additional label filters for queries. For example, `/api/v1/query_range?extra_label=user_id=123&extra_label=group_id=456&query=<query>`
+would automatically add `{user_id="123",group_id="456"}` label filters to the given `<query>`.
+This functionality can be used for limiting the scope of time series visible to the given tenant.
+It is expected that the `extra_label` query args are automatically set by auth proxy sitting in front of VictoriaMetrics.
+See [vmauth](https://docs.victoriametrics.com/vmauth.html) and [vmgateway](https://docs.victoriametrics.com/vmgateway.html) as examples of such proxies.
 
-VictoriaMetrics accepts optional `extra_filters[]=series_selector` query arg, which can be used for enforcing arbitrary label filters for queries. For example,
-`/api/v1/query_range?extra_filters[]={env=~"prod|staging",user="xyz"}&query=<query>` would automatically add `{env=~"prod|staging",user="xyz"}` label filters to the given `<query>`. This functionality can be used for limiting the scope of time series visible to the given tenant. It is expected that the `extra_filters[]` query args are automatically set by auth proxy sitting in front of VictoriaMetrics. See [vmauth](https://docs.victoriametrics.com/vmauth.html) and [vmgateway](https://docs.victoriametrics.com/vmgateway.html) as examples of such proxies.
+VictoriaMetrics accepts optional `extra_filters[]=series_selector` query arg, which can be used for enforcing arbitrary label filters for queries.
+For example, `/api/v1/query_range?extra_filters[]={env=~"prod|staging",user="xyz"}&query=<query>` would automatically
+add `{env=~"prod|staging",user="xyz"}` label filters to the given `<query>`. This functionality can be used for limiting
+the scope of time series visible to the given tenant. It is expected that the `extra_filters[]` query args are automatically
+set by auth proxy sitting in front of VictoriaMetrics.
+See [vmauth](https://docs.victoriametrics.com/vmauth.html) and [vmgateway](https://docs.victoriametrics.com/vmgateway.html) as examples of such proxies.
 
-VictoriaMetrics accepts relative times in `time`, `start` and `end` query args additionally to unix timestamps and [RFC3339](https://www.ietf.org/rfc/rfc3339.txt).
-For example, the following query would return data for the last 30 minutes: `/api/v1/query_range?start=-30m&query=...`.
+VictoriaMetrics accepts multiple formats for `time`, `start` and `end` query args - see [these docs](#timestamp-formats).
 
-VictoriaMetrics accepts `round_digits` query arg for `/api/v1/query` and `/api/v1/query_range` handlers. It can be used for rounding response values to the given number of digits after the decimal point. For example, `/api/v1/query?query=avg_over_time(temperature[1h])&round_digits=2` would round response values to up to two digits after the decimal point.
+VictoriaMetrics accepts `round_digits` query arg for [/api/v1/query](https://docs.victoriametrics.com/keyConcepts.html#instant-query)
+and [/api/v1/query_range](https://docs.victoriametrics.com/keyConcepts.html#range-query) handlers. It can be used for rounding response values
+to the given number of digits after the decimal point.
+For example, `/api/v1/query?query=avg_over_time(temperature[1h])&round_digits=2` would round response values to up to two digits after the decimal point.
 
-VictoriaMetrics accepts `limit` query arg for `/api/v1/labels` and `/api/v1/label/<labelName>/values` handlers for limiting the number of returned entries. For example, the query to `/api/v1/labels?limit=5` returns a sample of up to 5 unique labels, while ignoring the rest of labels. If the provided `limit` value exceeds the corresponding `-search.maxTagKeys` / `-search.maxTagValues` command-line flag values, then limits specified in the command-line flags are used.
+VictoriaMetrics accepts `limit` query arg for [/api/v1/labels](https://docs.victoriametrics.com/url-examples.html#apiv1labels)
+and [`/api/v1/label/<labelName>/values`](https://docs.victoriametrics.com/url-examples.html#apiv1labelvalues) handlers for limiting the number of returned entries.
+For example, the query to `/api/v1/labels?limit=5` returns a sample of up to 5 unique labels, while ignoring the rest of labels.
+If the provided `limit` value exceeds the corresponding `-search.maxTagKeys` / `-search.maxTagValues` command-line flag values,
+then limits specified in the command-line flags are used.
 
-By default, VictoriaMetrics returns time series for the last 5 minutes from `/api/v1/series`, `/api/v1/labels` and `/api/v1/label/<labelName>/values` while the Prometheus API defaults to all time.  Explicitly set `start` and `end` to select the desired time range.
-VictoriaMetrics accepts `limit` query arg for `/api/v1/series` handlers for limiting the number of returned entries. For example, the query to `/api/v1/series?limit=5` returns a sample of up to 5 series, while ignoring the rest. If the provided `limit` value exceeds the corresponding `-search.maxSeries` command-line flag values, then limits specified in the command-line flags are used.
+By default, VictoriaMetrics returns time series for the last day starting at 00:00 UTC
+from [/api/v1/series](https://docs.victoriametrics.com/url-examples.html#apiv1series),
+[/api/v1/labels](https://docs.victoriametrics.com/url-examples.html#apiv1labels) and
+[`/api/v1/label/<labelName>/values`](https://docs.victoriametrics.com/url-examples.html#apiv1labelvalues),
+while the Prometheus API defaults to all time.  Explicitly set `start` and `end` to select the desired time range.
+VictoriaMetrics rounds the specified `start..end` time range to day granularity because of performance optimization concerns.
+If you need the exact set of label names and label values on the given time range, then send queries
+to [/api/v1/query](https://docs.victoriametrics.com/keyConcepts.html#instant-query) or to [/api/v1/query_range](https://docs.victoriametrics.com/keyConcepts.html#range-query).
+
+VictoriaMetrics accepts `limit` query arg at [/api/v1/series](https://docs.victoriametrics.com/url-examples.html#apiv1series)
+for limiting the number of returned entries. For example, the query to `/api/v1/series?limit=5` returns a sample of up to 5 series, while ignoring the rest of series.
+If the provided `limit` value exceeds the corresponding `-search.maxSeries` command-line flag values, then limits specified in the command-line flags are used.
 
 Additionally, VictoriaMetrics provides the following handlers:
 
@@ -727,6 +798,18 @@ Additionally, VictoriaMetrics provides the following handlers:
   For example, request to `/api/v1/status/top_queries?topN=5&maxLifetime=30s` would return up to 5 queries per list, which were executed during the last 30 seconds.
   VictoriaMetrics tracks the last `-search.queryStats.lastQueriesCount` queries with durations at least `-search.queryStats.minQueryDuration`.
 
+### Timestamp formats
+
+VictoriaMetrics accepts the following formats for `time`, `start` and `end` query args
+in [query APIs](https://docs.victoriametrics.com/#prometheus-querying-api-usage) and
+in [export APIs](https://docs.victoriametrics.com/#how-to-export-time-series).
+
+- Unix timestamps in seconds with optional milliseconds after the point. For example, `1562529662.678`.
+- [RFC3339](https://www.ietf.org/rfc/rfc3339.txt). For example, '2022-03-29T01:02:03Z`.
+- Partial RFC3339. Examples: `2022`, `2022-03`, `2022-03-29`, `2022-03-29T01`, `2022-03-29T01:02`.
+- Relative duration comparing to the current time. For example, `1h5m` means `one hour and five minutes ago`.
+
+
 ## Graphite API usage
 
 VictoriaMetrics supports data ingestion in Graphite protocol - see [these docs](#how-to-send-data-from-graphite-compatible-agents-such-as-statsd) for details.
@@ -746,10 +829,10 @@ VictoriaMetrics supports `__graphite__` pseudo-label for filtering time series w
 
 ### Graphite Render API usage
 
-[VictoriaMetrics Enterprise](https://docs.victoriametrics.com/enterprise.html) supports [Graphite Render API](https://graphite.readthedocs.io/en/stable/render_api.html) subset
+VictoriaMetrics supports [Graphite Render API](https://graphite.readthedocs.io/en/stable/render_api.html) subset
 at `/render` endpoint, which is used by [Graphite datasource in Grafana](https://grafana.com/docs/grafana/latest/datasources/graphite/).
-When configuring Graphite datasource in Grafana, the `Storage-Step` http request header must be set to a step between Graphite data points stored in VictoriaMetrics. For example, `Storage-Step: 10s` would mean 10 seconds distance between Graphite datapoints stored in VictoriaMetrics.
-Enterprise binaries can be downloaded and evaluated for free from [the releases page](https://github.com/VictoriaMetrics/VictoriaMetrics/releases).
+When configuring Graphite datasource in Grafana, the `Storage-Step` http request header must be set to a step between Graphite data points
+stored in VictoriaMetrics. For example, `Storage-Step: 10s` would mean 10 seconds distance between Graphite datapoints stored in VictoriaMetrics.
 
 ### Graphite Metrics API usage
 
@@ -946,12 +1029,13 @@ Each JSON line contains samples for a single time series. An example output:
 {"metric":{"__name__":"up","job":"prometheus","instance":"localhost:9090"},"values":[1,1,1],"timestamps":[1549891461511,1549891476511,1549891491511]}
 ```
 
-Optional `start` and `end` args may be added to the request in order to limit the time frame for the exported data. These args may contain either
-unix timestamp in seconds or [RFC3339](https://www.ietf.org/rfc/rfc3339.txt) values.
+Optional `start` and `end` args may be added to the request in order to limit the time frame for the exported data.
+See [allowed formats](#timestamp-formats) for these args.
+
 For example:
 ```console
 curl http://<victoriametrics-addr>:8428/api/v1/export -d 'match[]=<timeseries_selector_for_export>' -d 'start=1654543486' -d 'end=1654543486'
-curl http://<victoriametrics-addr>:8428/api/v1/export -d 'match[]=<timeseries_selector_for_export>' -d 'start=2022-06-06T19:25:48+00:00' -d 'end=2022-06-06T19:29:07+00:00'
+curl http://<victoriametrics-addr>:8428/api/v1/export -d 'match[]=<timeseries_selector_for_export>' -d 'start=2022-06-06T19:25:48' -d 'end=2022-06-06T19:29:07'
 ```
 
 Optional `max_rows_per_line` arg may be added to the request for limiting the maximum number of rows exported per each JSON line.
@@ -994,12 +1078,13 @@ where:
 * `<timeseries_selector_for_export>` may contain any [time series selector](https://prometheus.io/docs/prometheus/latest/querying/basics/#time-series-selectors)
 for metrics to export.
 
-Optional `start` and `end` args may be added to the request in order to limit the time frame for the exported data. These args may contain either
-unix timestamp in seconds or [RFC3339](https://www.ietf.org/rfc/rfc3339.txt) values.
+Optional `start` and `end` args may be added to the request in order to limit the time frame for the exported data.
+See [allowed formats](#timestamp-formats) for these args.
+
 For example:
 ```console
 curl http://<victoriametrics-addr>:8428/api/v1/export/csv -d 'format=<format>' -d 'match[]=<timeseries_selector_for_export>' -d 'start=1654543486' -d 'end=1654543486'
-curl http://<victoriametrics-addr>:8428/api/v1/export/csv -d 'format=<format>' -d 'match[]=<timeseries_selector_for_export>' -d 'start=2022-06-06T19:25:48+00:00' -d 'end=2022-06-06T19:29:07+00:00'
+curl http://<victoriametrics-addr>:8428/api/v1/export/csv -d 'format=<format>' -d 'match[]=<timeseries_selector_for_export>' -d 'start=2022-06-06T19:25:48' -d 'end=2022-06-06T19:29:07'
 ```
 
 The exported CSV data can be imported to VictoriaMetrics via [/api/v1/import/csv](#how-to-import-csv-data).
@@ -1021,12 +1106,13 @@ wget -O- -q 'http://your_victoriametrics_instance:8428/api/v1/series/count' | jq
 # relaunch victoriametrics with search.maxExportSeries more than value from previous command
 ```
 
-Optional `start` and `end` args may be added to the request in order to limit the time frame for the exported data. These args may contain either
-unix timestamp in seconds or [RFC3339](https://www.ietf.org/rfc/rfc3339.txt) values.
+Optional `start` and `end` args may be added to the request in order to limit the time frame for the exported data.
+See [allowed formats](#timestamp-formats) for these args.
+
 For example:
 ```console
 curl http://<victoriametrics-addr>:8428/api/v1/export/native -d 'match[]=<timeseries_selector_for_export>' -d 'start=1654543486' -d 'end=1654543486'
-curl http://<victoriametrics-addr>:8428/api/v1/export/native -d 'match[]=<timeseries_selector_for_export>' -d 'start=2022-06-06T19:25:48+00:00' -d 'end=2022-06-06T19:29:07+00:00'
+curl http://<victoriametrics-addr>:8428/api/v1/export/native -d 'match[]=<timeseries_selector_for_export>' -d 'start=2022-06-06T19:25:48' -d 'end=2022-06-06T19:29:07'
 ```
 
 The exported data can be imported to VictoriaMetrics via [/api/v1/import/native](#how-to-import-data-in-native-format).
@@ -1037,7 +1123,9 @@ The [deduplication](#deduplication) isn't applied for the data exported in nativ
 
 ## How to import time series data
 
-Time series data can be imported into VictoriaMetrics via any supported data ingestion protocol:
+VictoriaMetrics can discover and scrape metrics from Prometheus-compatible targets (aka "pull" protocol) -
+see [these docs](#how-to-scrape-prometheus-exporters-such-as-node-exporter).
+Additionally, VictoriaMetrics can accept metrics via the following popular data ingestion protocols (aka "push" protocols):
 
 * [Prometheus remote_write API](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#remote_write). See [these docs](#prometheus-setup) for details.
 * DataDog `submit metrics` API. See [these docs](#how-to-send-data-from-datadog-agent) for details.
@@ -1258,11 +1346,12 @@ VictoriaMetrics exports [Prometheus-compatible federation data](https://promethe
 at `http://<victoriametrics-addr>:8428/federate?match[]=<timeseries_selector_for_federation>`.
 
 Optional `start` and `end` args may be added to the request in order to scrape the last point for each selected time series on the `[start ... end]` interval.
-`start` and `end` may contain either unix timestamp in seconds or [RFC3339](https://www.ietf.org/rfc/rfc3339.txt) values.
+See [allowed formats](#timestamp-formats) for these args.
+
 For example:
 ```console
 curl http://<victoriametrics-addr>:8428/federate -d 'match[]=<timeseries_selector_for_export>' -d 'start=1654543486' -d 'end=1654543486'
-curl http://<victoriametrics-addr>:8428/federate -d 'match[]=<timeseries_selector_for_export>' -d 'start=2022-06-06T19:25:48+00:00' -d 'end=2022-06-06T19:29:07+00:00'
+curl http://<victoriametrics-addr>:8428/federate -d 'match[]=<timeseries_selector_for_export>' -d 'start=2022-06-06T19:25:48' -d 'end=2022-06-06T19:29:07'
 ```
 By default, the last point on the interval `[now - max_lookback ... now]` is scraped for each time series. The default value for `max_lookback` is `5m` (5 minutes), but it can be overridden with `max_lookback` query arg.
 For instance, `/federate?match[]=up&max_lookback=1h` would return last points on the `[now - 1h ... now]` interval. This may be useful for time series federation
@@ -1305,6 +1394,7 @@ By default VictoriaMetrics is tuned for an optimal resource usage under typical
 - `-search.maxSamplesPerQuery` limits the number of raw samples a single query can process. This allows limiting CPU usage for heavy queries.
 - `-search.maxPointsPerTimeseries` limits the number of calculated points, which can be returned per each matching time series from [range query](https://docs.victoriametrics.com/keyConcepts.html#range-query).
 - `-search.maxPointsSubqueryPerTimeseries` limits the number of calculated points, which can be generated per each matching time series during [subquery](https://docs.victoriametrics.com/MetricsQL.html#subqueries) evaluation.
+- `-search.maxSeriesPerAggrFunc` limits the number of time series, which can be generated by [MetricsQL aggregate functions](https://docs.victoriametrics.com/MetricsQL.html#aggregate-functions) in a single query.
 - `-search.maxSeries` limits the number of time series, which may be returned from [/api/v1/series](https://prometheus.io/docs/prometheus/latest/querying/api/#finding-series-by-label-matchers). This endpoint is used mostly by Grafana for auto-completion of metric names, label names and label values. Queries to this endpoint may take big amounts of CPU time and memory when the database contains big number of unique time series because of [high churn rate](https://docs.victoriametrics.com/FAQ.html#what-is-high-churn-rate). In this case it might be useful to set the `-search.maxSeries` to quite low value in order limit CPU and memory usage.
 - `-search.maxTagKeys` limits the number of items, which may be returned from [/api/v1/labels](https://prometheus.io/docs/prometheus/latest/querying/api/#getting-label-names). This endpoint is used mostly by Grafana for auto-completion of label names. Queries to this endpoint may take big amounts of CPU time and memory when the database contains big number of unique time series because of [high churn rate](https://docs.victoriametrics.com/FAQ.html#what-is-high-churn-rate). In this case it might be useful to set the `-search.maxTagKeys` to quite low value in order to limit CPU and memory usage.
 - `-search.maxTagValues` limits the number of items, which may be returned from [/api/v1/label/.../values](https://prometheus.io/docs/prometheus/latest/querying/api/#querying-label-values). This endpoint is used mostly by Grafana for auto-completion of label values. Queries to this endpoint may take big amounts of CPU time and memory when the database contains big number of unique time series because of [high churn rate](https://docs.victoriametrics.com/FAQ.html#what-is-high-churn-rate). In this case it might be useful to set the `-search.maxTagValues` to quite low value in order to limit CPU and memory usage.
@@ -1382,12 +1472,14 @@ can be configured with the `-inmemoryDataFlushInterval` command-line flag (note
 In-memory parts are persisted to disk into `part` directories under the `<-storageDataPath>/data/small/YYYY_MM/` folder,
 where `YYYY_MM` is the month partition for the stored data. For example, `2022_11` is the partition for `parts`
 with [raw samples](https://docs.victoriametrics.com/keyConcepts.html#raw-samples) from `November 2022`.
+Each partition directory contains `parts.json` file with the actual list of parts in the partition.
 
-The `part` directory has the following name pattern: `rowsCount_blocksCount_minTimestamp_maxTimestamp`, where:
+Every `part` directory contains `metadata.json` file with the following fields:
 
-- `rowsCount` - the number of [raw samples](https://docs.victoriametrics.com/keyConcepts.html#raw-samples) stored in the part
-- `blocksCount` - the number of blocks stored in the part (see details about blocks below)
-- `minTimestamp` and `maxTimestamp` - minimum and maximum timestamps across raw samples stored in the part
+- `RowsCount` - the number of [raw samples](https://docs.victoriametrics.com/keyConcepts.html#raw-samples) stored in the part
+- `BlocksCount` - the number of blocks stored in the part (see details about blocks below)
+- `MinTimestamp` and `MaxTimestamp` - minimum and maximum timestamps across raw samples stored in the part
+- `MinDedupInterval` - the [deduplication interval](#deduplication) applied to the given part.
 
 Each `part` consists of `blocks` sorted by internal time series id (aka `TSID`).
 Each `block` contains up to 8K [raw samples](https://docs.victoriametrics.com/keyConcepts.html#raw-samples),
@@ -1409,9 +1501,8 @@ for fast block lookups, which belong to the given `TSID` and cover the given tim
   and [freeing up disk space for the deleted time series](#how-to-delete-time-series) are performed during the merge
 
 Newly added `parts` either successfully appear in the storage or fail to appear.
-The newly added `parts` are being created in a temporary directory under `<-storageDataPath>/data/{small,big}/YYYY_MM/tmp` folder.
-When the newly added `part` is fully written and [fsynced](https://man7.org/linux/man-pages/man2/fsync.2.html)
-to a temporary directory, then it is atomically moved to the storage directory.
+The newly added `part` is atomically registered in the `parts.json` file under the corresponding partition
+after it is fully written and [fsynced](https://man7.org/linux/man-pages/man2/fsync.2.html) to the storage.
 Thanks to this alogrithm, storage never contains partially created parts, even if hardware power off
 occurrs in the middle of writing the `part` to disk - such incompletely written `parts`
 are automatically deleted on the next VictoriaMetrics start.
@@ -1426,8 +1517,8 @@ This increases overhead during data querying, since VictoriaMetrics needs to rea
 bigger number of parts per each request. That's why it is recommended to have at least 20%
 of free disk space under directory pointed by `-storageDataPath` command-line flag.
 
-Information about merging process is available in [the dashboard for single-node VictoriaMetrics](https://grafana.com/dashboards/10229)
-and [the dashboard for VictoriaMetrics cluster](https://grafana.com/grafana/dashboards/11176).
+Information about merging process is available in [the dashboard for single-node VictoriaMetrics](https://grafana.com/grafana/dashboards/10229-victoriametrics/)
+and [the dashboard for VictoriaMetrics cluster](https://grafana.com/grafana/dashboards/11176-victoriametrics-cluster/).
 See more details in [monitoring docs](#monitoring).
 
 See [this article](https://valyala.medium.com/how-victoriametrics-makes-instant-snapshots-for-multi-terabyte-time-series-data-e1f3fb0e0282) for more details.
@@ -1440,8 +1531,7 @@ Retention is configured with the `-retentionPeriod` command-line flag, which tak
 
 Data is split in per-month partitions inside `<-storageDataPath>/data/{small,big}` folders.
 Data partitions outside the configured retention are deleted on the first day of the new month.
-Each partition consists of one or more data parts with the following name pattern `rowsCount_blocksCount_minTimestamp_maxTimestamp`.
-Data parts outside of the configured retention are eventually deleted during
+Each partition consists of one or more data parts. Data parts outside of the configured retention are eventually deleted during
 [background merge](https://medium.com/@valyala/how-victoriametrics-makes-instant-snapshots-for-multi-terabyte-time-series-data-e1f3fb0e0282).
 
 The maximum disk space usage for a given `-retentionPeriod` is going to be (`-retentionPeriod` + 1) months.
@@ -1565,7 +1655,9 @@ VictoriaMetrics provides the following security-related command-line flags:
 Explicitly set internal network interface for TCP and UDP ports for data ingestion with Graphite and OpenTSDB formats.
 For example, substitute `-graphiteListenAddr=:2003` with `-graphiteListenAddr=<internal_iface_ip>:2003`. This protects from unexpected requests from untrusted network interfaces.
 
-VictoriaMetrics has achieved security certifications for Database Software Development and Software-Based Monitoring Services. We apply strict security measures in everything we do. See our [Security page](https://victoriametrics.com/security/) for more details.
+See also [security recommendation for VictoriaMetrics cluster](https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html#security)
+and [the general security page at VictoriaMetrics website](https://victoriametrics.com/security/).
+
 
 ## Tuning
 
@@ -1594,8 +1686,8 @@ Alternatively, single-node VictoriaMetrics can self-scrape the metrics when `-se
 set to duration greater than 0. For example, `-selfScrapeInterval=10s` would enable self-scraping of `/metrics` page 
 with 10 seconds interval.
 
-Official Grafana dashboards available for [single-node](https://grafana.com/dashboards/10229) 
-and [clustered](https://grafana.com/grafana/dashboards/11176) VictoriaMetrics. 
+Official Grafana dashboards available for [single-node](https://grafana.com/grafana/dashboards/10229-victoriametrics/) 
+and [clustered](https://grafana.com/grafana/dashboards/11176-victoriametrics-cluster/) VictoriaMetrics. 
 See an [alternative dashboard for clustered VictoriaMetrics](https://grafana.com/grafana/dashboards/11831) 
 created by community.
 
@@ -1832,7 +1924,14 @@ are added to all the metrics before sending them to the remote storage:
 
 ## Cache removal
 
-VictoriaMetrics uses various internal caches. These caches are stored to `<-storageDataPath>/cache` directory during graceful shutdown (e.g. when VictoriaMetrics is stopped by sending `SIGINT` signal). The caches are read on the next VictoriaMetrics startup. Sometimes it is needed to remove such caches on the next startup. This can be performed by placing `reset_cache_on_startup` file inside the `<-storageDataPath>/cache` directory before the restart of VictoriaMetrics. See [this issue](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1447) for details.
+VictoriaMetrics uses various internal caches. These caches are stored to `<-storageDataPath>/cache` directory during graceful shutdown
+(e.g. when VictoriaMetrics is stopped by sending `SIGINT` signal). The caches are read on the next VictoriaMetrics startup.
+Sometimes it is needed to remove such caches on the next startup. This can be done in the following ways:
+
+- By manually removing the `<-storageDataPath>/cache` directory when VictoriaMetrics is stopped.
+- By placing `reset_cache_on_startup` file inside the `<-storageDataPath>/cache` directory before the restart of VictoriaMetrics.
+  In this case VictoriaMetrics will automatically remove all the caches on the next start.
+  See [this issue](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1447) for details.
 
 ## Cache tuning
 
@@ -1844,8 +1943,8 @@ The following metrics for each type of cache are exported at [`/metrics` page](#
 * `vm_cache_misses_total` - the number of cache misses
 * `vm_cache_entries` - the number of entries in the cache
 
-Both Grafana dashboards for [single-node VictoriaMetrics](https://grafana.com/dashboards/10229)
-and [clustered VictoriaMetrics](https://grafana.com/grafana/dashboards/11176)
+Both Grafana dashboards for [single-node VictoriaMetrics](https://grafana.com/grafana/dashboards/10229-victoriametrics/)
+and [clustered VictoriaMetrics](https://grafana.com/grafana/dashboards/11176-victoriametrics-cluster/)
 contain `Caches` section with cache metrics visualized. The panels show the current
 memory usage by each type of cache, and also a cache hit rate. If hit rate is close to 100%
 then cache efficiency is already very high and does not need any tuning.
@@ -1984,17 +2083,10 @@ It is safe sharing the collected profiles from security point of view, since the
 
 ## Integrations
 
-* [Helm charts for single-node and cluster versions of VictoriaMetrics](https://github.com/VictoriaMetrics/helm-charts).
-* [Kubernetes operator for VictoriaMetrics](https://github.com/VictoriaMetrics/operator).
-* [netdata](https://github.com/netdata/netdata) can push data into VictoriaMetrics via `Prometheus remote_write API`.
-  See [these docs](https://github.com/netdata/netdata#integrations).
 * [go-graphite/carbonapi](https://github.com/go-graphite/carbonapi) can use VictoriaMetrics as time series backend.
   See [this example](https://github.com/go-graphite/carbonapi/blob/main/cmd/carbonapi/carbonapi.example.victoriametrics.yaml).
-* [Ansible role for installing cluster VictoriaMetrics (by VictoriaMetrics)](https://github.com/VictoriaMetrics/ansible-playbooks).
-* [Ansible role for installing cluster VictoriaMetrics (by community)](https://github.com/Slapper/ansible-victoriametrics-cluster-role).
-* [Ansible role for installing single-node VictoriaMetrics (by community)](https://github.com/dreamteam-gg/ansible-victoriametrics-role).
-
-* [Snap package for VictoriaMetrics](https://snapcraft.io/victoriametrics).
+* [netdata](https://github.com/netdata/netdata) can push data into VictoriaMetrics via `Prometheus remote_write API`.
+  See [these docs](https://github.com/netdata/netdata#integrations).
 * [vmalert-cli](https://github.com/aorfanos/vmalert-cli) - a CLI application for managing [vmalert](https://docs.victoriametrics.com/vmalert.html).
 
 ## Third-party contributions
@@ -2086,7 +2178,7 @@ Pass `-help` to VictoriaMetrics in order to see the list of supported command-li
      Trim timestamps when importing csv data to this duration. Minimum practical duration is 1ms. Higher duration (i.e. 1s) may be used for reducing disk space usage for timestamp data (default 1ms)
   -datadog.maxInsertRequestSize size
      The maximum size in bytes of a single DataDog POST request to /api/v1/series
-     Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 67108864)
+     Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB (default 67108864)
   -datadog.sanitizeMetricName
      Sanitize metric names for the ingested DataDog data to comply with DataDog behaviour described at https://docs.datadoghq.com/metrics/custom_metrics/#naming-custom-metrics (default true)
   -dedup.minScrapeInterval duration
@@ -2101,7 +2193,7 @@ Pass `-help` to VictoriaMetrics in order to see the list of supported command-li
      Comma-separated downsampling periods in the format 'offset:period'. For example, '30d:10m' instructs to leave a single sample per 10 minutes for samples older than 30 days. See https://docs.victoriametrics.com/#downsampling for details. This flag is available only in VictoriaMetrics enterprise. See https://docs.victoriametrics.com/enterprise.html
      Supports an array of values separated by comma or specified via multiple flags.
   -dryRun
-     Whether to check only -promscrape.config and then exit. Unknown config entries aren't allowed in -promscrape.config by default. This can be changed with -promscrape.config.strictParse=false command-line flag
+     Whether to check config files without running VictoriaMetrics. The following config files are checked: -promscrape.config, -relabelConfig and -streamAggr.config. Unknown config entries aren't allowed in -promscrape.config by default. This can be changed with -promscrape.config.strictParse=false command-line flag
   -enableTCP6
      Whether to enable IPv6 for listening and dialing. By default only IPv4 TCP and UDP is used
   -envflag.enable
@@ -2121,7 +2213,9 @@ Pass `-help` to VictoriaMetrics in order to see the list of supported command-li
   -fs.disableMmap
      Whether to use pread() instead of mmap() for reading data files. By default mmap() is used for 64-bit arches and pread() is used for 32-bit arches, since they cannot read data files bigger than 2^32 bytes in memory. mmap() is usually faster for reading small data chunks than pread()
   -graphiteListenAddr string
-     TCP and UDP address to listen for Graphite plaintext data. Usually :2003 must be set. Doesn't work if empty
+     TCP and UDP address to listen for Graphite plaintext data. Usually :2003 must be set. Doesn't work if empty. See also -graphiteListenAddr.useProxyProtocol
+  -graphiteListenAddr.useProxyProtocol
+     Whether to use proxy protocol for connections accepted at -graphiteListenAddr . See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt
   -graphiteTrimTimestamp duration
      Trim timestamps for Graphite data to this duration. Minimum practical duration is 1s. Higher duration (i.e. 1m) may be used for reducing disk space usage for timestamp data (default 1s)
   -http.connTimeout duration
@@ -2141,20 +2235,24 @@ Pass `-help` to VictoriaMetrics in order to see the list of supported command-li
   -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 ":8428")
+     TCP address to listen for http connections. See also -httpListenAddr.useProxyProtocol (default ":8428")
+  -httpListenAddr.useProxyProtocol
+     Whether to use proxy protocol for connections accepted at -httpListenAddr . See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt
   -import.maxLineLen size
      The maximum length in bytes of a single line accepted by /api/v1/import; the line length can be limited with 'max_rows_per_line' query arg passed to /api/v1/export
-     Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 104857600)
+     Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB (default 104857600)
   -influx.databaseNames array
      Comma-separated list of database names to return from /query and /influx/query API. This can be needed for accepting data from Telegraf plugins such as https://github.com/fangli/fluent-plugin-influxdb
      Supports an array of values separated by comma or specified via multiple flags.
   -influx.maxLineSize size
      The maximum size in bytes for a single InfluxDB line during parsing
-     Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 262144)
+     Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB (default 262144)
   -influxDBLabel string
      Default label for the DB name sent over '?db={db_name}' query parameter (default "db")
   -influxListenAddr string
-     TCP and UDP address to listen for InfluxDB line protocol data. Usually :8089 must be set. Doesn't work if empty. This flag isn't needed when ingesting data over HTTP - just send it to http://<victoriametrics>:8428/write
+     TCP and UDP address to listen for InfluxDB line protocol data. Usually :8089 must be set. Doesn't work if empty. This flag isn't needed when ingesting data over HTTP - just send it to http://<victoriametrics>:8428/write . See also -influxListenAddr.useProxyProtocol
+  -influxListenAddr.useProxyProtocol
+     Whether to use proxy protocol for connections accepted at -influxListenAddr . See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt
   -influxMeasurementFieldSeparator string
      Separator for '{measurement}{separator}{field_name}' metric name when inserted via InfluxDB line protocol (default "_")
   -influxSkipMeasurement
@@ -2166,7 +2264,13 @@ Pass `-help` to VictoriaMetrics in order to see the list of supported command-li
   -inmemoryDataFlushInterval duration
      The interval for guaranteed saving of in-memory data to disk. The saved data survives unclean shutdown such as OOM crash, hardware reset, SIGKILL, etc. Bigger intervals may help increasing lifetime of flash storage with limited write cycles (e.g. Raspberry PI). Smaller intervals increase disk IO load. Minimum supported value is 1s (default 5s)
   -insert.maxQueueDuration duration
-     The maximum duration for waiting in the queue for insert requests due to -maxConcurrentInserts (default 1m0s)
+     The maximum duration to wait in the queue when -maxConcurrentInserts concurrent insert requests are executed (default 1m0s)
+  -internStringCacheExpireDuration duration
+     The expire duration for caches for interned strings. See https://en.wikipedia.org/wiki/String_interning . See also -internStringMaxLen and -internStringDisableCache (default 6m0s)
+  -internStringDisableCache
+     Whether to disable caches for interned strings. This may reduce memory usage at the cost of higher CPU usage. See https://en.wikipedia.org/wiki/String_interning . See also -internStringCacheExpireDuration and -internStringMaxLen
+  -internStringMaxLen int
+     The maximum length for strings to intern. Lower limit may save memory at the cost of higher CPU usage. See https://en.wikipedia.org/wiki/String_interning . See also -internStringDisableCache and -internStringCacheExpireDuration (default 500)
   -logNewSeries
      Whether to log new series. This option is for debug purposes only. It can lead to performance issues when big number of new series are ingested into VictoriaMetrics
   -loggerDisableTimestamps
@@ -2175,6 +2279,8 @@ Pass `-help` to VictoriaMetrics in order to see the list of supported command-li
      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")
+  -loggerJSONFields string
+     Allows renaming fields in JSON formatted logs. Example: "ts:timestamp,msg:message" renames "ts" to "timestamp" and "msg" to "message". Supported fields: ts, level, caller, msg
   -loggerLevel string
      Minimum level of errors to log. Possible values: INFO, WARN, ERROR, FATAL, PANIC (default "INFO")
   -loggerOutput string
@@ -2184,30 +2290,34 @@ Pass `-help` to VictoriaMetrics in order to see the list of supported command-li
   -loggerWarnsPerSecondLimit int
      Per-second limit on the number of WARN messages. If more than the given number of warns are emitted per second, then the remaining warns are suppressed. Zero values disable the rate limit
   -maxConcurrentInserts int
-     The maximum number of concurrent inserts. Default value should work for most cases, since it minimizes the overhead for concurrent inserts. This option is tigthly coupled with -insert.maxQueueDuration (default 16)
+     The maximum number of concurrent insert requests. Default value should work for most cases, since it minimizes the memory usage. The default value can be increased when clients send data over slow networks. See also -insert.maxQueueDuration (default 8)
   -maxInsertRequestSize size
      The maximum size in bytes of a single Prometheus remote_write API request
-     Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 33554432)
+     Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB (default 33554432)
   -maxLabelValueLen int
      The maximum length of label values in the accepted time series. Longer label values are truncated. In this case the vm_too_long_label_values_total metric at /metrics page is incremented (default 16384)
   -maxLabelsPerTimeseries int
      The maximum number of labels accepted per time series. Superfluous labels are dropped. In this case the vm_metrics_with_dropped_labels_total metric at /metrics page is incremented (default 30)
   -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)
+     Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB (default 0)
   -memory.allowedPercent float
      Allowed percent of system memory VictoriaMetrics caches may occupy. See also -memory.allowedBytes. Too low a value may increase cache miss rate usually resulting in higher CPU and disk IO usage. Too high a value may evict too much data from OS page cache which will result in higher disk IO usage (default 60)
   -metricsAuthKey string
      Auth key for /metrics endpoint. It must be passed via authKey query arg. It overrides httpAuth.* settings
   -opentsdbHTTPListenAddr string
-     TCP address to listen for OpentTSDB HTTP put requests. Usually :4242 must be set. Doesn't work if empty
+     TCP address to listen for OpenTSDB HTTP put requests. Usually :4242 must be set. Doesn't work if empty. See also -opentsdbHTTPListenAddr.useProxyProtocol
+  -opentsdbHTTPListenAddr.useProxyProtocol
+     Whether to use proxy protocol for connections accepted at -opentsdbHTTPListenAddr . See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt
   -opentsdbListenAddr string
-     TCP and UDP address to listen for OpentTSDB metrics. Telnet put messages and HTTP /api/put messages are simultaneously served on TCP port. Usually :4242 must be set. Doesn't work if empty
+     TCP and UDP address to listen for OpenTSDB metrics. Telnet put messages and HTTP /api/put messages are simultaneously served on TCP port. Usually :4242 must be set. Doesn't work if empty. See also -opentsdbListenAddr.useProxyProtocol
+  -opentsdbListenAddr.useProxyProtocol
+     Whether to use proxy protocol for connections accepted at -opentsdbListenAddr . See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt
   -opentsdbTrimTimestamp duration
      Trim timestamps for OpenTSDB 'telnet put' data to this duration. Minimum practical duration is 1s. Higher duration (i.e. 1m) may be used for reducing disk space usage for timestamp data (default 1s)
   -opentsdbhttp.maxInsertRequestSize size
      The maximum size of OpenTSDB HTTP put request
-     Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 33554432)
+     Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB (default 33554432)
   -opentsdbhttpTrimTimestamp duration
      Trim timestamps for OpenTSDB HTTP data to this duration. Minimum practical duration is 1ms. Higher duration (i.e. 1s) may be used for reducing disk space usage for timestamp data (default 1ms)
   -pprofAuthKey string
@@ -2270,25 +2380,31 @@ Pass `-help` to VictoriaMetrics in order to see the list of supported command-li
      How frequently to reload the full state from Kubernetes API server (default 30m0s)
   -promscrape.kubernetesSDCheckInterval duration
      Interval for checking for changes in Kubernetes API server. This works only if kubernetes_sd_configs is configured in '-promscrape.config' file. See https://docs.victoriametrics.com/sd_configs.html#kubernetes_sd_configs for details (default 30s)
+  -promscrape.kumaSDCheckInterval duration
+     Interval for checking for changes in kuma service discovery. This works only if kuma_sd_configs is configured in '-promscrape.config' file. See https://docs.victoriametrics.com/sd_configs.html#kuma_sd_configs for details (default 30s)
   -promscrape.maxDroppedTargets int
      The maximum number of droppedTargets to show at /api/v1/targets page. Increase this value if your setup drops more scrape targets during relabeling and you need investigating labels for all the dropped targets. Note that the increased number of tracked dropped targets may result in increased memory usage (default 1000)
   -promscrape.maxResponseHeadersSize size
      The maximum size of http response headers from Prometheus scrape targets
-     Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 4096)
+     Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB (default 4096)
   -promscrape.maxScrapeSize size
      The maximum size of scrape response in bytes to process from Prometheus targets. Bigger responses are rejected
-     Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 16777216)
+     Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB (default 16777216)
   -promscrape.minResponseSizeForStreamParse size
      The minimum target response size for automatic switching to stream parsing mode, which can reduce memory usage. See https://docs.victoriametrics.com/vmagent.html#stream-parsing-mode
-     Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 1000000)
+     Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB (default 1000000)
   -promscrape.noStaleMarkers
      Whether to disable sending Prometheus stale markers for metrics when scrape target disappears. This option may reduce memory usage if stale markers aren't needed for your setup. This option also disables populating the scrape_series_added metric. See https://prometheus.io/docs/concepts/jobs_instances/#automatically-generated-labels-and-time-series
+  -promscrape.nomad.waitTime duration
+     Wait time used by Nomad service discovery. Default value is used if not set
+  -promscrape.nomadSDCheckInterval duration
+     Interval for checking for changes in Nomad. This works only if nomad_sd_configs is configured in '-promscrape.config' file. See https://docs.victoriametrics.com/sd_configs.html#nomad_sd_configs for details (default 30s)
   -promscrape.openstackSDCheckInterval duration
      Interval for checking for changes in openstack API server. This works only if openstack_sd_configs is configured in '-promscrape.config' file. See https://docs.victoriametrics.com/sd_configs.html#openstack_sd_configs for details (default 30s)
   -promscrape.seriesLimitPerTarget int
      Optional limit on the number of unique time series a single scrape target can expose. See https://docs.victoriametrics.com/vmagent.html#cardinality-limiter for more info
   -promscrape.streamParse
-     Whether to enable stream parsing for metrics obtained from scrape targets. This may be useful for reducing memory usage when millions of metrics are exposed per each scrape target. It is posible to set 'stream_parse: true' individually per each 'scrape_config' section in '-promscrape.config' for fine grained control
+     Whether to enable stream parsing for metrics obtained from scrape targets. This may be useful for reducing memory usage when millions of metrics are exposed per each scrape target. It is possible to set 'stream_parse: true' individually per each 'scrape_config' section in '-promscrape.config' for fine grained control
   -promscrape.suppressDuplicateScrapeTargetErrors
      Whether to suppress 'duplicate scrape target' errors; see https://docs.victoriametrics.com/vmagent.html#troubleshooting for details
   -promscrape.suppressScrapeErrors
@@ -2322,13 +2438,16 @@ Pass `-help` to VictoriaMetrics in order to see the list of supported command-li
   -search.disableCache
      Whether to disable response caching. This may be useful during data backfilling
   -search.graphiteMaxPointsPerSeries int
-     The maximum number of points per series Graphite render API can return. This flag is available only in VictoriaMetrics enterprise. See https://docs.victoriametrics.com/enterprise.html (default 1000000)
+     The maximum number of points per series Graphite render API can return (default 1000000)
   -search.graphiteStorageStep duration
-     The interval between datapoints stored in the database. It is used at Graphite Render API handler for normalizing the interval between datapoints in case it isn't normalized. It can be overridden by sending 'storage_step' query arg to /render API or by sending the desired interval via 'Storage-Step' http header during querying /render API. This flag is available only in VictoriaMetrics enterprise. See https://docs.victoriametrics.com/enterprise.html (default 10s)
+     The interval between datapoints stored in the database. It is used at Graphite Render API handler for normalizing the interval between datapoints in case it isn't normalized. It can be overridden by sending 'storage_step' query arg to /render API or by sending the desired interval via 'Storage-Step' http header during querying /render API (default 10s)
   -search.latencyOffset duration
-     The time when data points become visible in query results after the collection. Too small value can result in incomplete last points for query results (default 30s)
+     The time when data points become visible in query results after the collection. It can be overridden on per-query basis via latency_offset arg. Too small value can result in incomplete last points for query results (default 30s)
+  -search.logQueryMemoryUsage size
+     Log queries, which require more memory than specified by this flag. This may help detecting and optimizing heavy queries. Query logging is disabled by default. See also -search.logSlowQueryDuration and -search.maxMemoryPerQuery
+     Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB (default 0)
   -search.logSlowQueryDuration duration
-     Log queries with execution time exceeding this value. Zero disables slow query logging (default 5s)
+     Log queries with execution time exceeding this value. Zero disables slow query logging. See also -search.logQueryMemoryUsage (default 5s)
   -search.maxConcurrentRequests int
      The maximum number of concurrent search requests. It shouldn't be high, since a single request can saturate all the CPU cores, while many concurrently executed requests may require high amounts of memory. See also -search.maxQueueDuration and -search.maxMemoryPerQuery (default 8)
   -search.maxExportDuration duration
@@ -2338,12 +2457,12 @@ Pass `-help` to VictoriaMetrics in order to see the list of supported command-li
   -search.maxFederateSeries int
      The maximum number of time series, which can be returned from /federate. This option allows limiting memory usage (default 1000000)
   -search.maxGraphiteSeries int
-     The maximum number of time series, which can be scanned during queries to Graphite Render API. See https://docs.victoriametrics.com/#graphite-render-api-usage . This flag is available only in VictoriaMetrics enterprise. See https://docs.victoriametrics.com/enterprise.html (default 300000)
+     The maximum number of time series, which can be scanned during queries to Graphite Render API. See https://docs.victoriametrics.com/#graphite-render-api-usage (default 300000)
   -search.maxLookback duration
      Synonym to -search.lookback-delta from Prometheus. The value is dynamically detected from interval between time series datapoints if not set. It can be overridden on per-query basis via max_lookback arg. See also '-search.maxStalenessInterval' flag, which has the same meaining due to historical reasons
   -search.maxMemoryPerQuery size
-     The maximum amounts of memory a single query may consume. Queries requiring more memory are rejected. The total memory limit for concurrently executed queries can be estimated as -search.maxMemoryPerQuery multiplied by -search.maxConcurrentRequests
-     Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 0)
+     The maximum amounts of memory a single query may consume. Queries requiring more memory are rejected. The total memory limit for concurrently executed queries can be estimated as -search.maxMemoryPerQuery multiplied by -search.maxConcurrentRequests . See also -search.logQueryMemoryUsage
+     Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB (default 0)
   -search.maxPointsPerTimeseries int
      The maximum points per a single timeseries returned from /api/v1/query_range. This option doesn't limit the number of scanned raw samples in the database. The main purpose of this option is to limit the number of per-series points returned to graphing UI such as VMUI or Grafana. There is no sense in setting this limit to values bigger than the horizontal resolution of the graph (default 30000)
   -search.maxPointsSubqueryPerTimeseries int
@@ -2352,7 +2471,7 @@ Pass `-help` to VictoriaMetrics in order to see the list of supported command-li
      The maximum duration for query execution (default 30s)
   -search.maxQueryLen size
      The maximum search query length in bytes
-     Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 16384)
+     Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB (default 16384)
   -search.maxQueueDuration duration
      The maximum time the request waits for execution when -search.maxConcurrentRequests limit is reached; see also -search.maxQueryDuration (default 10s)
   -search.maxSamplesPerQuery int
@@ -2361,6 +2480,8 @@ Pass `-help` to VictoriaMetrics in order to see the list of supported command-li
      The maximum number of raw samples a single query can scan per each time series. This option allows limiting memory usage (default 30000000)
   -search.maxSeries int
      The maximum number of time series, which can be returned from /api/v1/series. This option allows limiting memory usage (default 30000)
+  -search.maxSeriesPerAggrFunc int
+     The maximum number of time series an aggregate MetricsQL function can generate (default 1000000)
   -search.maxStalenessInterval duration
      The maximum interval for staleness calculations. By default it is automatically calculated from the median interval between samples. This flag could be useful for tuning Prometheus data model closer to Influx-style data model. See https://prometheus.io/docs/prometheus/latest/querying/basics/#staleness for details. See also '-search.setLookbackToStep' flag
   -search.maxStatusRequestDuration duration
@@ -2401,6 +2522,8 @@ Pass `-help` to VictoriaMetrics in order to see the list of supported command-li
      The maximum number of CPU cores to use for small merges. Default value is used if set to 0
   -snapshotAuthKey string
      authKey, which must be passed in query string to /snapshot* pages
+  -snapshotCreateTimeout duration
+     The timeout for creating new snapshot. If set, make sure that timeout is lower than backup period
   -snapshotsMaxAge value
      Automatically delete snapshots older than -snapshotsMaxAge if it is set to non-zero duration. Make sure that backup process has enough time to finish the backup before the corresponding snapshot is automatically deleted
      The following optional suffixes are supported: h (hour), d (day), w (week), y (year). If suffix isn't set, then the duration is counted in months (default 0)
@@ -2408,25 +2531,31 @@ Pass `-help` to VictoriaMetrics in order to see the list of supported command-li
      Whether to sort labels for incoming samples before writing them to storage. This may be needed for reducing memory usage at 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
   -storage.cacheSizeIndexDBDataBlocks size
      Overrides max size for indexdb/dataBlocks cache. See https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html#cache-tuning
-     Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 0)
+     Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB (default 0)
   -storage.cacheSizeIndexDBIndexBlocks size
      Overrides max size for indexdb/indexBlocks cache. See https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html#cache-tuning
-     Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 0)
+     Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB (default 0)
   -storage.cacheSizeIndexDBTagFilters size
      Overrides max size for indexdb/tagFiltersToMetricIDs cache. See https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html#cache-tuning
-     Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 0)
+     Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB (default 0)
   -storage.cacheSizeStorageTSID size
      Overrides max size for storage/tsid cache. See https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html#cache-tuning
-     Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 0)
+     Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB (default 0)
   -storage.maxDailySeries int
      The maximum number of unique series can be added to the storage 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/#cardinality-limiter . See also -storage.maxHourlySeries
   -storage.maxHourlySeries int
      The maximum number of unique series can be added to the storage during the last hour. Excess series are logged and dropped. This can be useful for limiting series cardinality. See https://docs.victoriametrics.com/#cardinality-limiter . See also -storage.maxDailySeries
   -storage.minFreeDiskSpaceBytes size
      The minimum free disk space at -storageDataPath after which the storage stops accepting new data
-     Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 10000000)
+     Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB (default 10000000)
   -storageDataPath string
      Path to storage data (default "victoria-metrics-data")
+  -streamAggr.config string
+     Optional path to file with stream aggregation config. See https://docs.victoriametrics.com/stream-aggregation.html . See also -remoteWrite.streamAggr.keepInput and -streamAggr.dedupInterval
+  -streamAggr.dedupInterval duration
+     Input samples are de-duplicated with this interval before being aggregated. Only the last sample per each time series per each interval is aggregated if the interval is greater than zero
+  -streamAggr.keepInput
+     Whether to keep input samples after the aggregation with -streamAggr.config. By default the input is dropped after the aggregation, so only the aggregate data is stored. See https://docs.victoriametrics.com/stream-aggregation.html
   -tls
      Whether to enable TLS for incoming HTTP requests at -httpListenAddr (aka https). -tlsCertFile and -tlsKeyFile must be set if -tls is set
   -tlsCertFile string
@@ -2444,4 +2573,6 @@ Pass `-help` to VictoriaMetrics in order to see the list of supported command-li
      Show VictoriaMetrics version
   -vmalert.proxyURL string
      Optional URL for proxying requests to vmalert. For example, if -vmalert.proxyURL=http://vmalert:8880 , then alerting API requests such as /api/v1/rules from Grafana will be proxied to http://vmalert:8880/api/v1/rules
+  -vmui.customDashboardsPath string
+     Optional path to vmui dashboards. See https://github.com/VictoriaMetrics/VictoriaMetrics/tree/master/app/vmui/packages/vmui/public/dashboards
 ```

SECURITY.md

@@ -4,10 +4,10 @@
 
 | Version | Supported          |
 |---------|--------------------|
-| 1.81.x  | :white_check_mark: |
-| 1.80.x  | :x:                |
-| 1.79.x  | :white_check_mark: |
-| < 1.78  | :x:                |
+| [latest release](https://docs.victoriametrics.com/CHANGELOG.html) | :white_check_mark: |
+| v1.87.x LTS release | :white_check_mark: |
+| v1.79.x LTS release | :white_check_mark: |
+| other releases  | :x:                |
 
 ## Reporting a Vulnerability
 

app/victoria-metrics/Makefile

@@ -39,6 +39,9 @@ victoria-metrics-freebsd-amd64-prod:
 victoria-metrics-openbsd-amd64-prod:
 	APP_NAME=victoria-metrics $(MAKE) app-via-docker-openbsd-amd64
 
+victoria-metrics-windows-amd64-prod:
+	APP_NAME=victoria-metrics $(MAKE) app-via-docker-windows-amd64
+
 package-victoria-metrics:
 	APP_NAME=victoria-metrics $(MAKE) package-via-docker
 
@@ -82,6 +85,9 @@ victoria-metrics-linux-arm64:
 victoria-metrics-linux-ppc64le:
 	APP_NAME=victoria-metrics CGO_ENABLED=0 GOOS=linux GOARCH=ppc64le $(MAKE) app-local-goos-goarch
 
+victoria-metrics-linux-s390x:
+	APP_NAME=victoria-metrics CGO_ENABLED=0 GOOS=linux GOARCH=s390x $(MAKE) app-local-goos-goarch
+
 victoria-metrics-linux-386:
 	APP_NAME=victoria-metrics CGO_ENABLED=0 GOOS=linux GOARCH=386 $(MAKE) app-local-goos-goarch
 
@@ -97,6 +103,9 @@ victoria-metrics-freebsd-amd64:
 victoria-metrics-openbsd-amd64:
 	APP_NAME=victoria-metrics CGO_ENABLED=0 GOOS=openbsd GOARCH=amd64 $(MAKE) app-local-goos-goarch
 
+victoria-metrics-windows-amd64:
+	GOARCH=amd64 APP_NAME=victoria-metrics $(MAKE) app-local-windows-goarch
+
 victoria-metrics-pure:
 	APP_NAME=victoria-metrics $(MAKE) app-local-pure
 

app/victoria-metrics/main.go

@@ -8,6 +8,8 @@ import (
 	"time"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vminsert"
+	vminsertcommon "github.com/VictoriaMetrics/VictoriaMetrics/app/vminsert/common"
+	vminsertrelabel "github.com/VictoriaMetrics/VictoriaMetrics/app/vminsert/relabel"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmselect"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmselect/promql"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmstorage"
@@ -24,11 +26,15 @@ import (
 )
 
 var (
-	httpListenAddr    = flag.String("httpListenAddr", ":8428", "TCP address to listen for http connections")
+	httpListenAddr   = flag.String("httpListenAddr", ":8428", "TCP address to listen for http connections. See also -httpListenAddr.useProxyProtocol")
+	useProxyProtocol = flag.Bool("httpListenAddr.useProxyProtocol", false, "Whether to use proxy protocol for connections accepted at -httpListenAddr . "+
+		"See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt . "+
+		"With enabled proxy protocol http server cannot serve regular /metrics endpoint. Use -pushmetrics.url for metrics pushing")
 	minScrapeInterval = flag.Duration("dedup.minScrapeInterval", 0, "Leave only the last sample in every time series per each discrete interval "+
 		"equal to -dedup.minScrapeInterval > 0. See https://docs.victoriametrics.com/#deduplication and https://docs.victoriametrics.com/#downsampling")
-	dryRun = flag.Bool("dryRun", false, "Whether to check only -promscrape.config and then exit. "+
-		"Unknown config entries aren't allowed in -promscrape.config by default. This can be changed with -promscrape.config.strictParse=false command-line flag")
+	dryRun = flag.Bool("dryRun", false, "Whether to check config files without running VictoriaMetrics. The following config files are checked: "+
+		"-promscrape.config, -relabelConfig and -streamAggr.config. Unknown config entries aren't allowed in -promscrape.config by default. "+
+		"This can be changed with -promscrape.config.strictParse=false command-line flag")
 	inmemoryDataFlushInterval = flag.Duration("inmemoryDataFlushInterval", 5*time.Second, "The interval for guaranteed saving of in-memory data to disk. "+
 		"The saved data survives unclean shutdown such as OOM crash, hardware reset, SIGKILL, etc. "+
 		"Bigger intervals may help increasing lifetime of flash storage with limited write cycles (e.g. Raspberry PI). "+
@@ -51,7 +57,13 @@ func main() {
 		if err := promscrape.CheckConfig(); err != nil {
 			logger.Fatalf("error when checking -promscrape.config: %s", err)
 		}
-		logger.Infof("-promscrape.config is ok; exitting with 0 status code")
+		if err := vminsertrelabel.CheckRelabelConfig(); err != nil {
+			logger.Fatalf("error when checking -relabelConfig: %s", err)
+		}
+		if err := vminsertcommon.CheckStreamAggrConfig(); err != nil {
+			logger.Fatalf("error when checking -streamAggr.config: %s", err)
+		}
+		logger.Infof("-promscrape.config is ok; exiting with 0 status code")
 		return
 	}
 
@@ -64,7 +76,7 @@ func main() {
 	vminsert.Init()
 	startSelfScraper()
 
-	go httpserver.Serve(*httpListenAddr, requestHandler)
+	go httpserver.Serve(*httpListenAddr, *useProxyProtocol, requestHandler)
 	logger.Infof("started VictoriaMetrics in %.3f seconds", time.Since(startTime).Seconds())
 
 	sig := procutil.WaitForSigterm()
@@ -90,7 +102,7 @@ func main() {
 
 func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 	if r.URL.Path == "/" {
-		if r.Method != "GET" {
+		if r.Method != http.MethodGet {
 			return false
 		}
 		w.Header().Add("Content-Type", "text/html; charset=utf-8")
@@ -102,6 +114,7 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 			{"targets", "status for discovered active targets"},
 			{"service-discovery", "labels before and after relabeling for discovered targets"},
 			{"metric-relabel-debug", "debug metric relabeling"},
+			{"expand-with-exprs", "WITH expressions' tutorial"},
 			{"api/v1/targets", "advanced information about discovered targets in JSON format"},
 			{"config", "-promscrape.config contents"},
 			{"metrics", "available service metrics"},

app/victoria-metrics/main_test.go

@@ -129,10 +129,10 @@ func setUp() {
 	storagePath = filepath.Join(os.TempDir(), testStorageSuffix)
 	processFlags()
 	logger.Init()
-	vmstorage.InitWithoutMetrics(promql.ResetRollupResultCacheIfNeeded)
+	vmstorage.Init(promql.ResetRollupResultCacheIfNeeded)
 	vmselect.Init()
 	vminsert.Init()
-	go httpserver.Serve(*httpListenAddr, requestHandler)
+	go httpserver.Serve(*httpListenAddr, false, requestHandler)
 	readyStorageCheckFunc := func() bool {
 		resp, err := http.Get(testHealthHTTPPath)
 		if err != nil {
@@ -189,10 +189,8 @@ func tearDown() {
 
 func TestWriteRead(t *testing.T) {
 	t.Run("write", testWrite)
+	vmstorage.Storage.DebugFlush()
 	time.Sleep(1 * time.Second)
-	vmstorage.Stop()
-	// open storage after stop in write
-	vmstorage.InitWithoutMetrics(promql.ResetRollupResultCacheIfNeeded)
 	t.Run("read", testRead)
 }
 
@@ -261,7 +259,7 @@ func testRead(t *testing.T) {
 					for _, q := range test.Query {
 						q = testutil.PopulateTimeTplString(q, insertionTime)
 						if test.Issue != "" {
-							test.Issue = "Regression in " + test.Issue
+							test.Issue = "\nRegression in " + test.Issue
 						}
 						switch true {
 						case strings.HasPrefix(q, "/api/v1/export"):
@@ -284,7 +282,7 @@ func testRead(t *testing.T) {
 							queryResult := Query{}
 							httpReadStruct(t, testReadHTTPPath, q, &queryResult)
 							if err := checkQueryResult(queryResult, test.ResultQuery); err != nil {
-								t.Fatalf("Query. %s fails with error %s.%s", q, err, test.Issue)
+								t.Fatalf("Query. %s fails with error: %s.%s", q, err, test.Issue)
 							}
 						default:
 							t.Fatalf("unsupported read query %s", q)

app/victoria-metrics/multiarch/Dockerfile

@@ -2,7 +2,7 @@
 ARG certs_image
 ARG root_image
 FROM $certs_image as certs
-RUN apk --update --no-cache add ca-certificates
+RUN apk update && apk upgrade && 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

app/victoria-metrics/test/parser_test.go

@@ -12,7 +12,7 @@ func TestPopulateTimeTplString(t *testing.T) {
 	}
 	f := func(s, resultExpected string) {
 		t.Helper()
-		result := PopulateTimeTplString(s, now)
+		result := PopulateTimeTplString(s, now.UTC())
 		if result != resultExpected {
 			t.Fatalf("unexpected result; got %q; want %q", result, resultExpected)
 		}

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

@@ -6,7 +6,7 @@
     "forms_daily_count;item=x 2 {TIME_S-2m}",
     "forms_daily_count;item=y 3 {TIME_S-1m}",
     "forms_daily_count;item=y 4 {TIME_S-2m}"],
-  "query": ["/api/v1/query?query=min%20by%20(item)%20(min_over_time(forms_daily_count[10m:1m]))&time={TIME_S-1m}"],
+  "query": ["/api/v1/query?query=min%20by%20(item)%20(min_over_time(forms_daily_count[10m:1m]))&time={TIME_S-1m}&latency_offset=1ms"],
   "result_query": {
     "status":"success",
     "data":{"resultType":"vector","result":[{"metric":{"item":"x"},"value":["{TIME_S-1m}","2"]},{"metric":{"item":"y"},"value":["{TIME_S-1m}","4"]}]}

app/vmagent/Makefile

@@ -85,6 +85,9 @@ vmagent-linux-arm64:
 vmagent-linux-ppc64le:
 	APP_NAME=vmagent CGO_ENABLED=0 GOOS=linux GOARCH=ppc64le $(MAKE) app-local-goos-goarch
 
+vmagent-linux-s390x:
+	APP_NAME=vmagent CGO_ENABLED=0 GOOS=linux GOARCH=s390x $(MAKE) app-local-goos-goarch
+
 vmagent-linux-386:
 	APP_NAME=vmagent CGO_ENABLED=0 GOOS=linux GOARCH=386 $(MAKE) app-local-goos-goarch
 

app/vmagent/README.md

@@ -24,8 +24,10 @@ additionally to [discovering Prometheus-compatible targets and scraping metrics
   see [these docs](https://docs.victoriametrics.com/#how-to-scrape-prometheus-exporters-such-as-node-exporter).
 * Can add, remove and modify labels (aka tags) via Prometheus relabeling. Can filter data before sending it to remote storage. See [these docs](#relabeling) for details.
 * Can accept data via all the ingestion protocols supported by VictoriaMetrics - see [these docs](#how-to-push-data-to-vmagent).
-* Can replicate collected metrics simultaneously to multiple remote storage systems -
-  see [these docs](#replication-and-high-availability).
+* Can aggregate incoming samples by time and by labels before sending them to remote storage - see [these docs](https://docs.victoriametrics.com/stream-aggregation.html).
+* Can replicate collected metrics simultaneously to multiple Prometheus-compatible remote storage systems - see [these docs](#replication-and-high-availability).
+* Can save egress network bandwidth usage costs when [VictoriaMetrics remote write protocol](#victoriametrics-remote-write-protocol)
+  is used for sending the data to VictoriaMetrics.
 * Works smoothly in environments with unstable connections to remote storage. If the remote storage is unavailable, the collected metrics
   are buffered at `-remoteWrite.tmpDataPath`. The buffered metrics are sent to remote storage as soon as the connection
   to the remote storage is repaired. The maximum disk usage for the buffer can be limited with `-remoteWrite.maxDiskUsagePerURL`.
@@ -45,16 +47,26 @@ additionally to [discovering Prometheus-compatible targets and scraping metrics
 
 Please download `vmutils-*` archive from [releases page](https://github.com/VictoriaMetrics/VictoriaMetrics/releases) (
 `vmagent` is also available in [docker images](https://hub.docker.com/r/victoriametrics/vmagent/tags)),
-unpack it and pass the following flags to the `vmagent` binary in order to start scraping Prometheus-compatible targets:
+unpack it and pass the following flags to the `vmagent` binary in order to start scraping Prometheus-compatible targets
+and sending the data to the Prometheus-compatible remote storage:
 
-* `-promscrape.config` with the path to Prometheus config file (usually located at `/etc/prometheus/prometheus.yml`).
+* `-promscrape.config` with the path to [Prometheus config file](https://docs.victoriametrics.com/sd_configs.html) (usually located at `/etc/prometheus/prometheus.yml`).
   The path can point either to local file or to http url. `vmagent` doesn't support some sections of Prometheus config file,
   so you may need either to delete these sections or to run `vmagent` with `-promscrape.config.strictParse=false` command-line flag.
   In this case `vmagent` ignores unsupported sections. See [the list of unsupported sections](#unsupported-prometheus-config-sections).
-* `-remoteWrite.url` with the remote storage endpoint such as VictoriaMetrics, the `-remoteWrite.url` argument can be specified
-  multiple times to replicate data concurrently to an arbitrary number of remote storage systems. See [various use cases](#use-cases).
+* `-remoteWrite.url` with Prometheus-compatible remote storage endpoint such as VictoriaMetrics.
 
-Example command line:
+Example command for writing the data recieved via [supported push-based protocols](#how-to-push-data-to-vmagent)
+to [single-node VictoriaMetrics](https://docs.victoriametrics.com/) located at `victoria-metrics-host:8428`:
+
+```console
+/path/to/vmagent -remoteWrite.url=https://victoria-metrics-host:8428/api/v1/write
+```
+
+See [these docs](https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html#url-format) if you need writing
+the data to [VictoriaMetrics cluster](https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html).
+
+Example command for scraping Prometheus targets and writing the data to single-node VictoriaMetrics:
 
 ```console
 /path/to/vmagent -promscrape.config=/path/to/prometheus.yml -remoteWrite.url=https://victoria-metrics-host:8428/api/v1/write
@@ -65,16 +77,12 @@ See [how to scrape Prometheus-compatible targets](#how-to-collect-metrics-in-pro
 If you use single-node VictoriaMetrics, then you can discover and scrape Prometheus-compatible targets directly from VictoriaMetrics
 without the need to use `vmagent` - see [these docs](https://docs.victoriametrics.com/#how-to-scrape-prometheus-exporters-such-as-node-exporter).
 
-If you don't need to scrape Prometheus-compatible targets, then the `-promscrape.config` option isn't needed.
-For example, the following command is sufficient for accepting data via [supported push-based protocols](#how-to-push-data-to-vmagent)
-and sending it to the provided `-remoteWrite.url`:
-
-```console
-/path/to/vmagent -remoteWrite.url=https://victoria-metrics-host:8428/api/v1/write
-```
+`vmagent` can save network bandwidth usage costs under high load when [VictoriaMetrics remote write protocol is used](#victoriametrics-remote-write-protocol).
 
 See [troubleshooting docs](#troubleshooting) if you encounter common issues with `vmagent`.
 
+See [various use cases](#use-cases) for vmagent.
+
 Pass `-help` to `vmagent` in order to see [the full list of supported command-line flags with their descriptions](#advanced-usage).
 
 ## How to push data to vmagent
@@ -96,7 +104,7 @@ additionally to pull-based Prometheus-compatible targets' scraping:
 
 `vmagent` should be restarted in order to update config options set via command-line args.
 `vmagent` supports multiple approaches for reloading configs from updated config files such as
-`-promscrape.config`, `-remoteWrite.relabelConfig` and `-remoteWrite.urlRelabelConfig`:
+`-promscrape.config`, `-remoteWrite.relabelConfig`, `-remoteWrite.urlRelabelConfig` and `-remoteWrite.streamAggr.config`:
 
 * Sending `SIGHUP` signal to `vmagent` process:
 
@@ -118,7 +126,8 @@ data to the remote storage. It re-tries sending the data to remote storage until
 The maximum on-disk size for the buffered metrics can be limited with `-remoteWrite.maxDiskUsagePerURL`.
 
 `vmagent` works on various architectures from the IoT world - 32-bit arm, 64-bit arm, ppc64, 386, amd64.
-See [the corresponding Makefile rules](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/app/vmagent/Makefile) for details.
+
+The `vmagent` can save network bandwidth usage costs by using [VictoriaMetrics remote write protocol](#victoriametrics-remote-write-protocol).
 
 ### Drop-in replacement for Prometheus
 
@@ -126,6 +135,12 @@ If you use Prometheus only for scraping metrics from various targets and forward
 then `vmagent` can replace Prometheus. Typically, `vmagent` requires lower amounts of RAM, CPU and network bandwidth compared with Prometheus.
 See [these docs](#how-to-collect-metrics-in-prometheus-format) for details.
 
+### Statsd alternative
+
+`vmagent` can be used as an alternative to [statsd](https://github.com/statsd/statsd)
+when [stream aggregation](https://docs.victoriametrics.com/stream-aggregation.html) is enabled.
+See [these docs](https://docs.victoriametrics.com/stream-aggregation.html#statsd-alternative) for details.
+
 ### Flexible metrics relay
 
 `vmagent` can accept metrics in [various popular data ingestion protocols](#how-to-push-data-to-vmagent), apply [relabeling](#relabeling)
@@ -139,6 +154,11 @@ If a single remote storage instance temporarily is out of service, then the coll
 `vmagent` buffers the collected data in files at `-remoteWrite.tmpDataPath` until the remote storage becomes available again
 and then it sends the buffered data to the remote storage in order to prevent data gaps.
 
+[VictoriaMetrics cluster](https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html) already supports replication,
+so there is no need in specifying multiple `-remoteWrite.url` flags when writing data to the same cluster.
+See [these docs](https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html#replication-and-data-safety).
+
+
 ### Relabeling and filtering
 
 `vmagent` can add, remove or update labels on the collected data before sending it to the remote storage. Additionally,
@@ -167,6 +187,32 @@ the `-remoteWrite.url` command-line flag should be configured as `<schema>://<vm
 according to [these docs](https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html#url-format).
 There is also support for multitenant writes. See [these docs](#multitenancy).
 
+## VictoriaMetrics remote write protocol
+
+`vmagent` supports sending data to the configured `-remoteWrite.url` either via Prometheus remote write protocol
+or via VictoriaMetrics remote write protocol.
+
+VictoriaMetrics remote write protocol provides the following benefits comparing to Prometheus remote write protocol:
+
+- Reduced network bandwidth usage by 2x-5x. This allows saving network bandwidth usage costs when `vmagent` and
+  the configured remote storage systems are located in different datacenters, availability zones or regions.
+
+- Reduced disk read/write IO and disk space usage at `vmagent` when the remote storage is temporarily unavailable.
+  In this case `vmagent` buffers the incoming data to disk using the VictoriaMetrics remote write format.
+  This reduces disk read/write IO and disk space usage by 2x-5x comparing to Prometheus remote write format.
+
+`vmagent` automatically switches to VictoriaMetrics remote write protocol when it sends data to VictoriaMetrics components such as other `vmagent` instances,
+[single-node VictoriaMetrics](https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html)
+or `vminsert` at [cluster version](https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html).
+It is possible to force switch to VictoriaMetrics remote write protocol by specifying `-remoteWrite.forceVMProto`
+command-line flag for the corresponding `-remoteWrite.url`.
+It is possible to tune the compression level for VictoriaMetrics remote write protocol with `-remoteWrite.vmProtoCompressLevel` command-line flag.
+Bigger values reduce network usage at the cost of higher CPU usage. Negative values reduce CPU usage at the cost of higher network usage.
+
+`vmagent` automatically switches to Prometheus remote write protocol when it sends data to old versions of VictoriaMetrics components
+or to other Prometheus-compatible remote storage systems. It is possible to force switch to Prometheus remote write protocol
+by specifying `-remoteWrite.forcePromProto` command-line flag for the corresponding `-remoteWrite.url`.
+
 ## Multitenancy
 
 By default `vmagent` collects the data without tenant identifiers and routes it to the configured `-remoteWrite.url`.
@@ -316,7 +362,7 @@ Extra labels can be added to metrics collected by `vmagent` via the following me
 ## Automatically generated metrics
 
 `vmagent` automatically generates the following metrics per each scrape of every [Prometheus-compatible target](#how-to-collect-metrics-in-prometheus-format)
-and attaches target-specific `instance` and `job` labels to these metrics:
+and attaches `instance`, `job` and other target-specific labels to these metrics:
 
 * `up` - this metric exposes `1` value on successful scrape and `0` value on unsuccessful scrape. This allows monitoring
   failing scrapes with the following [MetricsQL query](https://docs.victoriametrics.com/MetricsQL.html):
@@ -568,7 +614,7 @@ Note that the `name` field must be substituted with explicit `__name__` option u
 If `__name__` option is missing under `labels` section, then the original Graphite-style metric name is left unchanged.
 
 For example, the following relabeling rule generates `requests_total{job="app42",instance="host124:8080"}` metric
-from "app42.host123.requests.total" Graphite-style metric:
+from `app42.host123.requests.total` Graphite-style metric:
 
 ```yaml
 - action: graphite
@@ -596,23 +642,22 @@ Additionally, the `action: graphite` relabeling rules usually work much faster t
 `vmagent` and [single-node VictoriaMetrics](https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html)
 provide the following tools for debugging target-level and metric-level relabeling:
 
-- Target-level relabeling (e.g. `relabel_configs` section at [scrape_configs](https://docs.victoriametrics.com/sd_configs.html#scrape_configs))
+- Target-level debugging (e.g. `relabel_configs` section at [scrape_configs](https://docs.victoriametrics.com/sd_configs.html#scrape_configs))
   can be performed by navigating to `http://vmagent:8429/targets` page (`http://victoriametrics:8428/targets` page for single-node VictoriaMetrics)
-  and clicking the `debug` link at the target, which must be debugged.
-  The opened page will show step-by-step results for the actual relabeling rules applied to the target labels.
+  and clicking the `debug target relabeling` link at the target, which must be debugged.
+  The opened page shows step-by-step results for the actual target relabeling rules applied to the discovered target labels.
+  The page shows also the target URL generated after applying all the relabeling rules.
 
   The `http://vmagent:8429/targets` page shows only active targets. If you need to understand why some target
   is dropped during the relabeling, then navigate to `http://vmagent:8428/service-discovery` page
   (`http://victoriametrics:8428/service-discovery` for single-node VictoriaMetrics), find the dropped target
-  and click the `debug` link there. The opened page will show step-by-step results for the actual relabeling rules,
+  and click the `debug` link there. The opened page shows step-by-step results for the actual relabeling rules,
   which result to target drop.
 
-- Metric-level relabeling (e.g. `metric_relabel_configs` section at [scrape_configs](https://docs.victoriametrics.com/sd_configs.html#scrape_configs)
-  and all the relabeling, which can be set up via `-relabelConfig`, `-remoteWrite.relabelConfig` and `-remoteWrite.urlRelabelConfig`
-  command-line flags) can be performed by navigating to `http://vmagent:8429/metric-relabel-debug` page
-  (`http://victoriametrics:8428/metric-relabel-debug` page for single-node VictoriaMetrics)
-  and submitting there relabeling rules together with the metric to be relabeled.
-  The page will show step-by-step results for the entered relabeling rules executed against the entered metric.
+- Metric-level debugging (e.g. `metric_relabel_configs` section at [scrape_configs](https://docs.victoriametrics.com/sd_configs.html#scrape_configs)
+  can be performed by navigating to `http://vmagent:8429/targets` page (`http://victoriametrics:8428/targets` page for single-node VictoriaMetrics)
+  and clicking the `debug metrics relabeling` link at the target, which must be debugged.
+  The opened page shows step-by-step results for the actual metric relabeling rules applied to the given target labels.
 
 ## Prometheus staleness markers
 
@@ -757,7 +802,8 @@ scrape_configs:
 
 ## Cardinality limiter
 
-By default `vmagent` doesn't limit the number of time series each scrape target can expose. The limit can be enforced in the following places:
+By default `vmagent` doesn't limit the number of time series each scrape target can expose. 
+The limit can be enforced in the following places:
 
 * Via `-promscrape.seriesLimitPerTarget` command-line option. This limit is applied individually
   to all the scrape targets defined in the file pointed by `-promscrape.config`.
@@ -768,10 +814,7 @@ By default `vmagent` doesn't limit the number of time series each scrape target
   via [Kubernetes annotations](https://kubernetes.io/docs/concepts/overview/working-with-objects/annotations/) for targets,
   which may expose too high number of time series.
 
-See also `sample_limit` option at [scrape_config section](https://docs.victoriametrics.com/sd_configs.html#scrape_configs).
-
-Scraped metrics are dropped for time series exceeding the given limit.
-
+Scraped metrics are dropped for time series exceeding the given limit on the time window of 24h.
 `vmagent` creates the following additional per-target metrics for targets with non-zero series limit:
 
 - `scrape_series_limit_samples_dropped` - the number of dropped samples during the scrape when the unique series limit is exceeded.
@@ -785,6 +828,7 @@ These metrics allow building the following alerting rules:
 - `scrape_series_current / scrape_series_limit > 0.9` - alerts when the number of series exposed by the target reaches 90% of the limit.
 - `sum_over_time(scrape_series_limit_samples_dropped[1h]) > 0` - alerts when some samples are dropped because the series limit on a particular target is reached.
 
+See also `sample_limit` option at [scrape_config section](https://docs.victoriametrics.com/sd_configs.html#scrape_configs).
 
 By default `vmagent` doesn't limit the number of time series written to remote storage systems specified at `-remoteWrite.url`.
 The limit can be enforced by setting the following command-line flags:
@@ -816,7 +860,7 @@ See also [cardinality explorer docs](https://docs.victoriametrics.com/#cardinali
 We recommend setting up regular scraping of this page either through `vmagent` itself or by Prometheus
 so that the exported metrics may be analyzed later.
 
-Use official [Grafana dashboard](https://grafana.com/grafana/dashboards/12683) for `vmagent` state overview.
+Use official [Grafana dashboard](https://grafana.com/grafana/dashboards/12683-victoriametrics-vmagent/) for `vmagent` state overview.
 Graphs on this dashboard contain useful hints - hover the `i` icon at the top left corner of each graph in order to read it.
 If you have suggestions for improvements or have found a bug - please open an issue on github or add a review to the dashboard.
 
@@ -875,7 +919,7 @@ If you have suggestions for improvements or have found a bug - please open an is
   The number of dropped blocks can be monitored via `vmagent_remotewrite_packets_dropped_total` metric exported at [/metrics page](#monitoring).
 
 * Use `-remoteWrite.queues=1` when `-remoteWrite.url` points to remote storage, which doesn't accept out-of-order samples (aka data backfilling).
-  Such storage systems include Prometheus, Cortex and Thanos, which typically emit `out of order sample` errors.
+  Such storage systems include Prometheus, Mimir, Cortex and Thanos, which typically emit `out of order sample` errors.
   The best solution is to use remote storage with [backfilling support](https://docs.victoriametrics.com/#backfilling) such as VictoriaMetrics.
 
 * `vmagent` buffers scraped data at the `-remoteWrite.tmpDataPath` directory until it is sent to `-remoteWrite.url`.
@@ -1136,13 +1180,13 @@ See the docs at https://docs.victoriametrics.com/vmagent.html .
      Trim timestamps when importing csv data to this duration. Minimum practical duration is 1ms. Higher duration (i.e. 1s) may be used for reducing disk space usage for timestamp data (default 1ms)
   -datadog.maxInsertRequestSize size
      The maximum size in bytes of a single DataDog POST request to /api/v1/series
-     Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 67108864)
+     Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB (default 67108864)
   -datadog.sanitizeMetricName
      Sanitize metric names for the ingested DataDog data to comply with DataDog behaviour described at https://docs.datadoghq.com/metrics/custom_metrics/#naming-custom-metrics (default true)
   -denyQueryTracing
      Whether to disable the ability to trace queries. See https://docs.victoriametrics.com/#query-tracing
   -dryRun
-     Whether to check only config files without running vmagent. The following files are checked: -promscrape.config, -remoteWrite.relabelConfig, -remoteWrite.urlRelabelConfig . Unknown config entries aren't allowed in -promscrape.config by default. This can be changed by passing -promscrape.config.strictParse=false command-line flag
+     Whether to check config files without running vmagent. The following files are checked: -promscrape.config, -remoteWrite.relabelConfig, -remoteWrite.urlRelabelConfig, -remoteWrite.streamAggr.config . Unknown config entries aren't allowed in -promscrape.config by default. This can be changed by passing -promscrape.config.strictParse=false command-line flag
   -enableTCP6
      Whether to enable IPv6 for listening and dialing. By default only IPv4 TCP and UDP is used
   -envflag.enable
@@ -1156,7 +1200,9 @@ See the docs at https://docs.victoriametrics.com/vmagent.html .
   -fs.disableMmap
      Whether to use pread() instead of mmap() for reading data files. By default mmap() is used for 64-bit arches and pread() is used for 32-bit arches, since they cannot read data files bigger than 2^32 bytes in memory. mmap() is usually faster for reading small data chunks than pread()
   -graphiteListenAddr string
-     TCP and UDP address to listen for Graphite plaintext data. Usually :2003 must be set. Doesn't work if empty
+     TCP and UDP address to listen for Graphite plaintext data. Usually :2003 must be set. Doesn't work if empty. See also -graphiteListenAddr.useProxyProtocol
+  -graphiteListenAddr.useProxyProtocol
+     Whether to use proxy protocol for connections accepted at -graphiteListenAddr . See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt
   -graphiteTrimTimestamp duration
      Trim timestamps for Graphite data to this duration. Minimum practical duration is 1s. Higher duration (i.e. 1m) may be used for reducing disk space usage for timestamp data (default 1s)
   -http.connTimeout duration
@@ -1176,20 +1222,24 @@ See the docs at https://docs.victoriametrics.com/vmagent.html .
   -httpAuth.username string
      Username for HTTP Basic Auth. The authentication is disabled if empty. See also -httpAuth.password
   -httpListenAddr string
-     TCP address to listen for http connections. Set this flag to empty value in order to disable listening on any port. This mode may be useful for running multiple vmagent instances on the same server. Note that /targets and /metrics pages aren't available if -httpListenAddr='' (default ":8429")
+     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=''. See also -httpListenAddr.useProxyProtocol (default ":8429")
+  -httpListenAddr.useProxyProtocol
+     Whether to use proxy protocol for connections accepted at -httpListenAddr . See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt
   -import.maxLineLen size
      The maximum length in bytes of a single line accepted by /api/v1/import; the line length can be limited with 'max_rows_per_line' query arg passed to /api/v1/export
-     Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 104857600)
+     Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB (default 104857600)
   -influx.databaseNames array
      Comma-separated list of database names to return from /query and /influx/query API. This can be needed for accepting data from Telegraf plugins such as https://github.com/fangli/fluent-plugin-influxdb
      Supports an array of values separated by comma or specified via multiple flags.
   -influx.maxLineSize size
      The maximum size in bytes for a single InfluxDB line during parsing
-     Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 262144)
+     Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB (default 262144)
   -influxDBLabel string
      Default label for the DB name sent over '?db={db_name}' query parameter (default "db")
   -influxListenAddr string
-     TCP and UDP address to listen for InfluxDB line protocol data. Usually :8089 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
+     TCP and UDP address to listen for InfluxDB line protocol data. Usually :8089 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 . See also -influxListenAddr.useProxyProtocol
+  -influxListenAddr.useProxyProtocol
+     Whether to use proxy protocol for connections accepted at -influxListenAddr . See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt
   -influxMeasurementFieldSeparator string
      Separator for '{measurement}{separator}{field_name}' metric name when inserted via InfluxDB line protocol (default "_")
   -influxSkipMeasurement
@@ -1199,7 +1249,13 @@ See the docs at https://docs.victoriametrics.com/vmagent.html .
   -influxTrimTimestamp duration
      Trim timestamps for InfluxDB line protocol data to this duration. Minimum practical duration is 1ms. Higher duration (i.e. 1s) may be used for reducing disk space usage for timestamp data (default 1ms)
   -insert.maxQueueDuration duration
-     The maximum duration for waiting in the queue for insert requests due to -maxConcurrentInserts (default 1m0s)
+     The maximum duration to wait in the queue when -maxConcurrentInserts concurrent insert requests are executed (default 1m0s)
+  -internStringCacheExpireDuration duration
+     The expire duration for caches for interned strings. See https://en.wikipedia.org/wiki/String_interning . See also -internStringMaxLen and -internStringDisableCache (default 6m0s)
+  -internStringDisableCache
+     Whether to disable caches for interned strings. This may reduce memory usage at the cost of higher CPU usage. See https://en.wikipedia.org/wiki/String_interning . See also -internStringCacheExpireDuration and -internStringMaxLen
+  -internStringMaxLen int
+     The maximum length for strings to intern. Lower limit may save memory at the cost of higher CPU usage. See https://en.wikipedia.org/wiki/String_interning . See also -internStringDisableCache and -internStringCacheExpireDuration (default 500)
   -kafka.consumer.topic array
      Kafka topic names for data consumption. This flag is available only in VictoriaMetrics enterprise. See https://docs.victoriametrics.com/enterprise.html
      Supports an array of values separated by comma or specified via multiple flags.
@@ -1232,6 +1288,8 @@ See the docs at https://docs.victoriametrics.com/vmagent.html .
      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")
+  -loggerJSONFields string
+     Allows renaming fields in JSON formatted logs. Example: "ts:timestamp,msg:message" renames "ts" to "timestamp" and "msg" to "message". Supported fields: ts, level, caller, msg
   -loggerLevel string
      Minimum level of errors to log. Possible values: INFO, WARN, ERROR, FATAL, PANIC (default "INFO")
   -loggerOutput string
@@ -1241,26 +1299,30 @@ See the docs at https://docs.victoriametrics.com/vmagent.html .
   -loggerWarnsPerSecondLimit int
      Per-second limit on the number of WARN messages. If more than the given number of warns are emitted per second, then the remaining warns are suppressed. Zero values disable the rate limit
   -maxConcurrentInserts int
-     The maximum number of concurrent inserts. Default value should work for most cases, since it minimizes the overhead for concurrent inserts. This option is tigthly coupled with -insert.maxQueueDuration (default 16)
+     The maximum number of concurrent insert requests. Default value should work for most cases, since it minimizes the memory usage. The default value can be increased when clients send data over slow networks. See also -insert.maxQueueDuration (default 8)
   -maxInsertRequestSize size
      The maximum size in bytes of a single Prometheus remote_write API request
-     Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 33554432)
+     Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB (default 33554432)
   -memory.allowedBytes size
      Allowed size of system memory VictoriaMetrics caches may occupy. This option overrides -memory.allowedPercent if set to a non-zero value. Too low a value may increase the cache miss rate usually resulting in higher CPU and disk IO usage. Too high a value may evict too much data from OS page cache resulting in higher disk IO usage
-     Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 0)
+     Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB (default 0)
   -memory.allowedPercent float
      Allowed percent of system memory VictoriaMetrics caches may occupy. See also -memory.allowedBytes. Too low a value may increase cache miss rate usually resulting in higher CPU and disk IO usage. Too high a value may evict too much data from OS page cache which will result in higher disk IO usage (default 60)
   -metricsAuthKey string
      Auth key for /metrics endpoint. It must be passed via authKey query arg. It overrides httpAuth.* settings
   -opentsdbHTTPListenAddr string
-     TCP address to listen for OpentTSDB HTTP put requests. Usually :4242 must be set. Doesn't work if empty
+     TCP address to listen for OpenTSDB HTTP put requests. Usually :4242 must be set. Doesn't work if empty. See also -opentsdbHTTPListenAddr.useProxyProtocol
+  -opentsdbHTTPListenAddr.useProxyProtocol
+     Whether to use proxy protocol for connections accepted at -opentsdbHTTPListenAddr . See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt
   -opentsdbListenAddr string
-     TCP and UDP address to listen for OpentTSDB metrics. Telnet put messages and HTTP /api/put messages are simultaneously served on TCP port. Usually :4242 must be set. Doesn't work if empty
+     TCP and UDP address to listen for OpenTSDB metrics. Telnet put messages and HTTP /api/put messages are simultaneously served on TCP port. Usually :4242 must be set. Doesn't work if empty. See also -opentsdbListenAddr.useProxyProtocol
+  -opentsdbListenAddr.useProxyProtocol
+     Whether to use proxy protocol for connections accepted at -opentsdbListenAddr . See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt
   -opentsdbTrimTimestamp duration
      Trim timestamps for OpenTSDB 'telnet put' data to this duration. Minimum practical duration is 1s. Higher duration (i.e. 1m) may be used for reducing disk space usage for timestamp data (default 1s)
   -opentsdbhttp.maxInsertRequestSize size
      The maximum size of OpenTSDB HTTP put request
-     Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 33554432)
+     Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB (default 33554432)
   -opentsdbhttpTrimTimestamp duration
      Trim timestamps for OpenTSDB HTTP data to this duration. Minimum practical duration is 1ms. Higher duration (i.e. 1s) may be used for reducing disk space usage for timestamp data (default 1ms)
   -pprofAuthKey string
@@ -1321,25 +1383,31 @@ See the docs at https://docs.victoriametrics.com/vmagent.html .
      How frequently to reload the full state from Kubernetes API server (default 30m0s)
   -promscrape.kubernetesSDCheckInterval duration
      Interval for checking for changes in Kubernetes API server. This works only if kubernetes_sd_configs is configured in '-promscrape.config' file. See https://docs.victoriametrics.com/sd_configs.html#kubernetes_sd_configs for details (default 30s)
+  -promscrape.kumaSDCheckInterval duration
+     Interval for checking for changes in kuma service discovery. This works only if kuma_sd_configs is configured in '-promscrape.config' file. See https://docs.victoriametrics.com/sd_configs.html#kuma_sd_configs for details (default 30s)
   -promscrape.maxDroppedTargets int
      The maximum number of droppedTargets to show at /api/v1/targets page. Increase this value if your setup drops more scrape targets during relabeling and you need investigating labels for all the dropped targets. Note that the increased number of tracked dropped targets may result in increased memory usage (default 1000)
   -promscrape.maxResponseHeadersSize size
      The maximum size of http response headers from Prometheus scrape targets
-     Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 4096)
+     Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB (default 4096)
   -promscrape.maxScrapeSize size
      The maximum size of scrape response in bytes to process from Prometheus targets. Bigger responses are rejected
-     Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 16777216)
+     Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB (default 16777216)
   -promscrape.minResponseSizeForStreamParse size
      The minimum target response size for automatic switching to stream parsing mode, which can reduce memory usage. See https://docs.victoriametrics.com/vmagent.html#stream-parsing-mode
-     Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 1000000)
+     Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB (default 1000000)
   -promscrape.noStaleMarkers
      Whether to disable sending Prometheus stale markers for metrics when scrape target disappears. This option may reduce memory usage if stale markers aren't needed for your setup. This option also disables populating the scrape_series_added metric. See https://prometheus.io/docs/concepts/jobs_instances/#automatically-generated-labels-and-time-series
+  -promscrape.nomad.waitTime duration
+     Wait time used by Nomad service discovery. Default value is used if not set
+  -promscrape.nomadSDCheckInterval duration
+     Interval for checking for changes in Nomad. This works only if nomad_sd_configs is configured in '-promscrape.config' file. See https://docs.victoriametrics.com/sd_configs.html#nomad_sd_configs for details (default 30s)
   -promscrape.openstackSDCheckInterval duration
      Interval for checking for changes in openstack API server. This works only if openstack_sd_configs is configured in '-promscrape.config' file. See https://docs.victoriametrics.com/sd_configs.html#openstack_sd_configs for details (default 30s)
   -promscrape.seriesLimitPerTarget int
      Optional limit on the number of unique time series a single scrape target can expose. See https://docs.victoriametrics.com/vmagent.html#cardinality-limiter for more info
   -promscrape.streamParse
-     Whether to enable stream parsing for metrics obtained from scrape targets. This may be useful for reducing memory usage when millions of metrics are exposed per each scrape target. It is posible to set 'stream_parse: true' individually per each 'scrape_config' section in '-promscrape.config' for fine grained control
+     Whether to enable stream parsing for metrics obtained from scrape targets. This may be useful for reducing memory usage when millions of metrics are exposed per each scrape target. It is possible to set 'stream_parse: true' individually per each 'scrape_config' section in '-promscrape.config' for fine grained control
   -promscrape.suppressDuplicateScrapeTargetErrors
      Whether to suppress 'duplicate scrape target' errors; see https://docs.victoriametrics.com/vmagent.html#troubleshooting for details
   -promscrape.suppressScrapeErrors
@@ -1397,6 +1465,12 @@ See the docs at https://docs.victoriametrics.com/vmagent.html .
      Supports an array of values separated by comma or specified via multiple flags.
   -remoteWrite.flushInterval duration
      Interval for flushing the data to remote storage. This option takes effect only when less than 10K data points per second are pushed to -remoteWrite.url (default 1s)
+  -remoteWrite.forcePromProto array
+     Whether to force Prometheus remote write protocol for sending data to the corresponding -remoteWrite.url . See https://docs.victoriametrics.com/vmagent.html#victoriametrics-remote-write-protocol
+     Supports array of values separated by comma or specified via multiple flags.
+  -remoteWrite.forceVMProto array
+     Whether to force VictoriaMetrics remote write protocol for sending data to the corresponding -remoteWrite.url . See https://docs.victoriametrics.com/vmagent.html#victoriametrics-remote-write-protocol
+     Supports array of values separated by comma or specified via multiple flags.
   -remoteWrite.headers array
      Optional HTTP headers to send with each request to the corresponding -remoteWrite.url. For example, -remoteWrite.headers='My-Auth:foobar' would send 'My-Auth: foobar' HTTP header with every request to the corresponding -remoteWrite.url. Multiple headers must be delimited by '^^': -remoteWrite.headers='header1:value1^^header2:value2'
      Supports an array of values separated by comma or specified via multiple flags.
@@ -1405,12 +1479,12 @@ See the docs at https://docs.victoriametrics.com/vmagent.html .
      Supports an array of values separated by comma or specified via multiple flags.
   -remoteWrite.maxBlockSize size
      The maximum block size to send to remote storage. Bigger blocks may improve performance at the cost of the increased memory usage. See also -remoteWrite.maxRowsPerBlock
-     Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 8388608)
+     Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB (default 8388608)
   -remoteWrite.maxDailySeries int
      The maximum number of unique series vmagent can send to remote storage systems during the last 24 hours. Excess series are logged and dropped. This can be useful for limiting series churn rate. See https://docs.victoriametrics.com/vmagent.html#cardinality-limiter
   -remoteWrite.maxDiskUsagePerURL array
      The maximum file-based buffer size in bytes at -remoteWrite.tmpDataPath for each -remoteWrite.url. When buffer size reaches the configured maximum, then old data is dropped when adding new data to the buffer. Buffered data is stored in ~500MB chunks, so the minimum practical value for this flag is 500MB. Disk usage is unlimited if the value is set to 0
-     Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB.
+     Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB.
      Supports array of values separated by comma or specified via multiple flags.
   -remoteWrite.maxHourlySeries int
      The maximum number of unique series vmagent can send to remote storage systems during the last hour. Excess series are logged and dropped. This can be useful for limiting series cardinality. See https://docs.victoriametrics.com/vmagent.html#cardinality-limiter
@@ -1443,7 +1517,9 @@ See the docs at https://docs.victoriametrics.com/vmagent.html .
      Optional rate limit in bytes per second for data sent to the corresponding -remoteWrite.url. By default the rate limit is disabled. It can be useful for limiting load on remote storage when big amounts of buffered data is sent after temporary unavailability of the remote storage
      Supports array of values separated by comma or specified via multiple flags.
   -remoteWrite.relabelConfig string
-     Optional path to file with relabel_config entries. The path can point either to local file or to http url. These entries are applied to all the metrics before sending them to -remoteWrite.url. See https://docs.victoriametrics.com/vmagent.html#relabeling for details
+     Optional path to file with relabeling configs, which are applied to all the metrics before sending them to -remoteWrite.url. See also -remoteWrite.urlRelabelConfig. The path can point either to local file or to http url. See https://docs.victoriametrics.com/vmagent.html#relabeling
+  -remoteWrite.keepDanglingQueues
+     Keep persistent queues contents at -remoteWrite.tmpDataPath in case there are no matching -remoteWrite.url. Useful when -remoteWrite.url is changed temporarily and persistent queue files will be needed later on.
   -remoteWrite.roundDigits array
      Round metric values to this number of decimal digits after the point before writing them to remote storage. Examples: -remoteWrite.roundDigits=2 would round 1.236 to 1.24, while -remoteWrite.roundDigits=-1 would round 126.78 to 130. By default digits rounding is disabled. Set it to 100 for disabling it for a particular remote storage. This option may be used for improving data compression for the stored metrics
      Supports array of values separated by comma or specified via multiple flags.
@@ -1455,6 +1531,15 @@ See the docs at https://docs.victoriametrics.com/vmagent.html .
   -remoteWrite.significantFigures array
      The number of significant figures to leave in metric values before writing them to remote storage. See https://en.wikipedia.org/wiki/Significant_figures . Zero value saves all the significant figures. This option may be used for improving data compression for the stored metrics. See also -remoteWrite.roundDigits
      Supports array of values separated by comma or specified via multiple flags.
+  -remoteWrite.streamAggr.config array
+     Optional path to file with stream aggregation config. See https://docs.victoriametrics.com/stream-aggregation.html . See also -remoteWrite.streamAggr.keepInput and -remoteWrite.streamAggr.dedupInterval
+     Supports an array of values separated by comma or specified via multiple flags.
+  -remoteWrite.streamAggr.dedupInterval array
+     Input samples are de-duplicated with this interval before being aggregated. Only the last sample per each time series per each interval is aggregated if the interval is greater than zero
+     Supports array of values separated by comma or specified via multiple flags.
+  -remoteWrite.streamAggr.keepInput array
+     Whether to keep input samples after the aggregation with -remoteWrite.streamAggr.config. By default the input is dropped after the aggregation, so only the aggregate data is sent to the -remoteWrite.url. See https://docs.victoriametrics.com/stream-aggregation.html
+     Supports array of values separated by comma or specified via multiple flags.
   -remoteWrite.tlsCAFile array
      Optional path to TLS CA file to use for verifying connections to the corresponding -remoteWrite.url. By default system CA is used
      Supports an array of values separated by comma or specified via multiple flags.
@@ -1473,11 +1558,13 @@ See the docs at https://docs.victoriametrics.com/vmagent.html .
   -remoteWrite.tmpDataPath string
      Path to directory where temporary data for remote write component is stored. See also -remoteWrite.maxDiskUsagePerURL (default "vmagent-remotewrite-data")
   -remoteWrite.url array
-     Remote storage URL to write data to. It must support Prometheus remote_write API. It is recommended using VictoriaMetrics as remote storage. Example url: http://<victoriametrics-host>:8428/api/v1/write . Pass multiple -remoteWrite.url flags in order to replicate data to multiple remote storage systems. See also -remoteWrite.multitenantURL
+     Remote storage URL to write data to. It must support either VictoriaMetrics remote write protocol or Prometheus remote_write protocol. Example url: http://<victoriametrics-host>:8428/api/v1/write . Pass multiple -remoteWrite.url options in order to replicate the collected data to multiple remote storage systems. See also -remoteWrite.multitenantURL
      Supports an array of values separated by comma or specified via multiple flags.
   -remoteWrite.urlRelabelConfig array
-     Optional path to relabel config for the corresponding -remoteWrite.url. The path can point either to local file or to http url
+     Optional path to relabel configs for the corresponding -remoteWrite.url. See also -remoteWrite.relabelConfig. The path can point either to local file or to http url. See https://docs.victoriametrics.com/vmagent.html#relabeling
      Supports an array of values separated by comma or specified via multiple flags.
+  -remoteWrite.vmProtoCompressLevel int
+     The compression level for VictoriaMetrics remote write protocol. Higher values reduce network traffic at the cost of higher CPU usage. Negative values reduce CPU usage at the cost of increased network traffic. See https://docs.victoriametrics.com/vmagent.html#victoriametrics-remote-write-protocol
   -sortLabels
      Whether to sort labels for incoming samples before writing them to all the configured remote storage systems. This may be needed for reducing memory usage at remote storage when the order of labels in incoming samples is random. For example, if m{k1="v1",k2="v2"} may be sent as m{k2="v2",k1="v1"}Enabled sorting for labels can slow down ingestion performance a bit
   -tls

app/vmagent/csvimport/request_handler.go

@@ -9,8 +9,8 @@ import (
 	"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/protoparser/csvimport/stream"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
 	"github.com/VictoriaMetrics/metrics"
 )
 
@@ -26,10 +26,8 @@ func InsertHandler(at *auth.Token, req *http.Request) error {
 	if err != nil {
 		return err
 	}
-	return writeconcurrencylimiter.Do(func() error {
-		return parser.ParseStream(req, func(rows []parser.Row) error {
-			return insertRows(at, rows, extraLabels)
-		})
+	return stream.Parse(req, func(rows []parser.Row) error {
+		return insertRows(at, rows, extraLabels)
 	})
 }
 

app/vmagent/datadog/request_handler.go

@@ -9,8 +9,8 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
 	parserCommon "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
 	parser "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadog"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadog/stream"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
 	"github.com/VictoriaMetrics/metrics"
 )
 
@@ -28,11 +28,9 @@ func InsertHandlerForHTTP(at *auth.Token, req *http.Request) error {
 	if err != nil {
 		return err
 	}
-	return writeconcurrencylimiter.Do(func() error {
-		ce := req.Header.Get("Content-Encoding")
-		return parser.ParseStream(req.Body, ce, func(series []parser.Series) error {
-			return insertRows(at, series, extraLabels)
-		})
+	ce := req.Header.Get("Content-Encoding")
+	return stream.Parse(req.Body, ce, func(series []parser.Series) error {
+		return insertRows(at, series, extraLabels)
 	})
 }
 

app/vmagent/graphite/request_handler.go

@@ -7,7 +7,7 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
 	parser "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/graphite"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/graphite/stream"
 	"github.com/VictoriaMetrics/metrics"
 )
 
@@ -20,9 +20,7 @@ var (
 //
 // See https://graphite.readthedocs.io/en/latest/feeding-carbon.html#the-plaintext-protocol
 func InsertHandler(r io.Reader) error {
-	return writeconcurrencylimiter.Do(func() error {
-		return parser.ParseStream(r, insertRows)
-	})
+	return stream.Parse(r, insertRows)
 }
 
 func insertRows(rows []parser.Row) error {

app/vmagent/influx/request_handler.go

@@ -15,8 +15,8 @@ import (
 	"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/protoparser/influx/stream"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
 	"github.com/VictoriaMetrics/metrics"
 )
 
@@ -37,10 +37,8 @@ var (
 //
 // See https://github.com/influxdata/telegraf/tree/master/plugins/inputs/socket_listener/
 func InsertHandlerForReader(r io.Reader, isGzipped bool) error {
-	return writeconcurrencylimiter.Do(func() error {
-		return parser.ParseStream(r, isGzipped, "", "", func(db string, rows []parser.Row) error {
-			return insertRows(nil, db, rows, nil)
-		})
+	return stream.Parse(r, isGzipped, "", "", func(db string, rows []parser.Row) error {
+		return insertRows(nil, db, rows, nil)
 	})
 }
 
@@ -52,15 +50,13 @@ func InsertHandlerForHTTP(at *auth.Token, req *http.Request) error {
 	if err != nil {
 		return err
 	}
-	return writeconcurrencylimiter.Do(func() error {
-		isGzipped := req.Header.Get("Content-Encoding") == "gzip"
-		q := req.URL.Query()
-		precision := q.Get("precision")
-		// Read db tag from https://docs.influxdata.com/influxdb/v1.7/tools/api/#write-http-endpoint
-		db := q.Get("db")
-		return parser.ParseStream(req.Body, isGzipped, precision, db, func(db string, rows []parser.Row) error {
-			return insertRows(at, db, rows, extraLabels)
-		})
+	isGzipped := req.Header.Get("Content-Encoding") == "gzip"
+	q := req.URL.Query()
+	precision := q.Get("precision")
+	// Read db tag from https://docs.influxdata.com/influxdb/v1.7/tools/api/#write-http-endpoint
+	db := q.Get("db")
+	return stream.Parse(req.Body, isGzipped, precision, db, func(db string, rows []parser.Row) error {
+		return insertRows(at, db, rows, extraLabels)
 	})
 }
 

app/vmagent/main.go

@@ -38,24 +38,37 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promscrape"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/pushmetrics"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
 	"github.com/VictoriaMetrics/metrics"
 )
 
 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=''")
+		"Note that /targets and /metrics pages aren't available if -httpListenAddr=''. See also -httpListenAddr.useProxyProtocol")
+	useProxyProtocol = flag.Bool("httpListenAddr.useProxyProtocol", false, "Whether to use proxy protocol for connections accepted at -httpListenAddr . "+
+		"See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt . "+
+		"With enabled proxy protocol http server cannot serve regular /metrics endpoint. Use -pushmetrics.url for metrics pushing")
 	influxListenAddr = flag.String("influxListenAddr", "", "TCP and UDP address to listen for InfluxDB line protocol data. Usually :8089 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. "+
+		"This flag isn't needed when ingesting data over HTTP - just send it to http://<vmagent>:8429/write . "+
+		"See also -influxListenAddr.useProxyProtocol")
+	influxUseProxyProtocol = flag.Bool("influxListenAddr.useProxyProtocol", false, "Whether to use proxy protocol for connections accepted at -influxListenAddr . "+
+		"See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt")
+	graphiteListenAddr = flag.String("graphiteListenAddr", "", "TCP and UDP address to listen for Graphite plaintext data. Usually :2003 must be set. Doesn't work if empty. "+
+		"See also -graphiteListenAddr.useProxyProtocol")
+	graphiteUseProxyProtocol = flag.Bool("graphiteListenAddr.useProxyProtocol", false, "Whether to use proxy protocol for connections accepted at -graphiteListenAddr . "+
+		"See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt")
+	opentsdbListenAddr = flag.String("opentsdbListenAddr", "", "TCP and UDP address to listen for OpenTSDB metrics. "+
 		"Telnet put messages and HTTP /api/put messages are simultaneously served on TCP port. "+
-		"Usually :4242 must be set. Doesn't work if empty")
-	opentsdbHTTPListenAddr = flag.String("opentsdbHTTPListenAddr", "", "TCP address to listen for OpentTSDB HTTP put requests. Usually :4242 must be set. Doesn't work if empty")
-	configAuthKey          = flag.String("configAuthKey", "", "Authorization key for accessing /config page. It must be passed via authKey query arg")
-	dryRun                 = flag.Bool("dryRun", false, "Whether to check only config files without running vmagent. The following files are checked: "+
-		"-promscrape.config, -remoteWrite.relabelConfig, -remoteWrite.urlRelabelConfig . "+
+		"Usually :4242 must be set. Doesn't work if empty. See also -opentsdbListenAddr.useProxyProtocol")
+	opentsdbUseProxyProtocol = flag.Bool("opentsdbListenAddr.useProxyProtocol", false, "Whether to use proxy protocol for connections accepted at -opentsdbListenAddr . "+
+		"See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt")
+	opentsdbHTTPListenAddr = flag.String("opentsdbHTTPListenAddr", "", "TCP address to listen for OpenTSDB HTTP put requests. Usually :4242 must be set. Doesn't work if empty. "+
+		"See also -opentsdbHTTPListenAddr.useProxyProtocol")
+	opentsdbHTTPUseProxyProtocol = flag.Bool("opentsdbHTTPListenAddr.useProxyProtocol", false, "Whether to use proxy protocol for connections accepted "+
+		"at -opentsdbHTTPListenAddr . See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt")
+	configAuthKey = flag.String("configAuthKey", "", "Authorization key for accessing /config page. It must be passed via authKey query arg")
+	dryRun        = flag.Bool("dryRun", false, "Whether to check config files without running vmagent. The following files are checked: "+
+		"-promscrape.config, -remoteWrite.relabelConfig, -remoteWrite.urlRelabelConfig, -remoteWrite.streamAggr.config . "+
 		"Unknown config entries aren't allowed in -promscrape.config by default. This can be changed by passing -promscrape.config.strictParse=false command-line flag")
 )
 
@@ -86,17 +99,20 @@ func main() {
 		if err := promscrape.CheckConfig(); err != nil {
 			logger.Fatalf("error when checking -promscrape.config: %s", err)
 		}
-		logger.Infof("-promscrape.config is ok; exitting with 0 status code")
+		logger.Infof("-promscrape.config is ok; exiting with 0 status code")
 		return
 	}
 	if *dryRun {
-		if err := remotewrite.CheckRelabelConfigs(); err != nil {
-			logger.Fatalf("error when checking relabel configs: %s", err)
-		}
 		if err := promscrape.CheckConfig(); err != nil {
 			logger.Fatalf("error when checking -promscrape.config: %s", err)
 		}
-		logger.Infof("all the configs are ok; exitting with 0 status code")
+		if err := remotewrite.CheckRelabelConfigs(); err != nil {
+			logger.Fatalf("error when checking relabel configs: %s", err)
+		}
+		if err := remotewrite.CheckStreamAggrConfigs(); err != nil {
+			logger.Fatalf("error when checking -remoteWrite.streamAggr.config: %s", err)
+		}
+		logger.Infof("all the configs are ok; exiting with 0 status code")
 		return
 	}
 
@@ -104,28 +120,27 @@ func main() {
 	startTime := time.Now()
 	remotewrite.Init()
 	common.StartUnmarshalWorkers()
-	writeconcurrencylimiter.Init()
 	if len(*influxListenAddr) > 0 {
-		influxServer = influxserver.MustStart(*influxListenAddr, func(r io.Reader) error {
+		influxServer = influxserver.MustStart(*influxListenAddr, *influxUseProxyProtocol, func(r io.Reader) error {
 			return influx.InsertHandlerForReader(r, false)
 		})
 	}
 	if len(*graphiteListenAddr) > 0 {
-		graphiteServer = graphiteserver.MustStart(*graphiteListenAddr, graphite.InsertHandler)
+		graphiteServer = graphiteserver.MustStart(*graphiteListenAddr, *graphiteUseProxyProtocol, graphite.InsertHandler)
 	}
 	if len(*opentsdbListenAddr) > 0 {
 		httpInsertHandler := getOpenTSDBHTTPInsertHandler()
-		opentsdbServer = opentsdbserver.MustStart(*opentsdbListenAddr, opentsdb.InsertHandler, httpInsertHandler)
+		opentsdbServer = opentsdbserver.MustStart(*opentsdbListenAddr, *opentsdbUseProxyProtocol, opentsdb.InsertHandler, httpInsertHandler)
 	}
 	if len(*opentsdbHTTPListenAddr) > 0 {
 		httpInsertHandler := getOpenTSDBHTTPInsertHandler()
-		opentsdbhttpServer = opentsdbhttpserver.MustStart(*opentsdbHTTPListenAddr, httpInsertHandler)
+		opentsdbhttpServer = opentsdbhttpserver.MustStart(*opentsdbHTTPListenAddr, *opentsdbHTTPUseProxyProtocol, httpInsertHandler)
 	}
 
 	promscrape.Init(remotewrite.Push)
 
 	if len(*httpListenAddr) > 0 {
-		go httpserver.Serve(*httpListenAddr, requestHandler)
+		go httpserver.Serve(*httpListenAddr, *useProxyProtocol, requestHandler)
 	}
 	logger.Infof("started vmagent in %.3f seconds", time.Since(startTime).Seconds())
 
@@ -197,7 +212,7 @@ func getAuthTokenFromPath(path string) (*auth.Token, error) {
 
 func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 	if r.URL.Path == "/" {
-		if r.Method != "GET" {
+		if r.Method != http.MethodGet {
 			return false
 		}
 		w.Header().Add("Content-Type", "text/html; charset=utf-8")
@@ -225,7 +240,14 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 			httpserver.Errorf(w, r, "%s", err)
 			return true
 		}
-		w.WriteHeader(http.StatusNoContent)
+		statusCode := http.StatusNoContent
+		if strings.HasPrefix(path, "/prometheus/api/v1/import/prometheus/metrics/job/") ||
+			strings.HasPrefix(path, "/api/v1/import/prometheus/metrics/job/") {
+			// Return 200 status code for pushgateway requests.
+			// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3636
+			statusCode = http.StatusOK
+		}
+		w.WriteHeader(statusCode)
 		return true
 	}
 	if strings.HasPrefix(path, "datadog/") {
@@ -235,6 +257,9 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 	}
 	switch path {
 	case "/prometheus/api/v1/write", "/api/v1/write":
+		if common.HandleVMProtoServerHandshake(w, r) {
+			return true
+		}
 		prometheusWriteRequests.Inc()
 		if err := promremotewrite.InsertHandler(nil, r); err != nil {
 			prometheusWriteErrors.Inc()
@@ -349,12 +374,7 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 		}
 		return true
 	case "/prometheus/config", "/config":
-		if *configAuthKey != "" && r.FormValue("authKey") != *configAuthKey {
-			err := &httpserver.ErrorWithStatusCode{
-				Err:        fmt.Errorf("The provided authKey doesn't match -configAuthKey"),
-				StatusCode: http.StatusUnauthorized,
-			}
-			httpserver.Errorf(w, r, "%s", err)
+		if !httpserver.CheckAuthFlag(w, r, *configAuthKey, "configAuthKey") {
 			return true
 		}
 		promscrapeConfigRequests.Inc()
@@ -363,12 +383,7 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 		return true
 	case "/prometheus/api/v1/status/config", "/api/v1/status/config":
 		// See https://prometheus.io/docs/prometheus/latest/querying/api/#config
-		if *configAuthKey != "" && r.FormValue("authKey") != *configAuthKey {
-			err := &httpserver.ErrorWithStatusCode{
-				Err:        fmt.Errorf("The provided authKey doesn't match -configAuthKey"),
-				StatusCode: http.StatusUnauthorized,
-			}
-			httpserver.Errorf(w, r, "%s", err)
+		if !httpserver.CheckAuthFlag(w, r, *configAuthKey, "configAuthKey") {
 			return true
 		}
 		promscrapeStatusConfigRequests.Inc()

app/vmagent/multiarch/Dockerfile

@@ -2,7 +2,7 @@
 ARG certs_image
 ARG root_image
 FROM $certs_image as certs
-RUN apk --update --no-cache add ca-certificates
+RUN apk update && apk upgrade && 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

app/vmagent/native/request_handler.go

@@ -10,9 +10,8 @@ import (
 	"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/protoparser/native/stream"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
 	"github.com/VictoriaMetrics/metrics"
 )
 
@@ -31,14 +30,12 @@ func InsertHandler(at *auth.Token, req *http.Request) error {
 		return err
 	}
 	isGzip := req.Header.Get("Content-Encoding") == "gzip"
-	return writeconcurrencylimiter.Do(func() error {
-		return parser.ParseStream(req.Body, isGzip, func(block *parser.Block) error {
-			return insertRows(at, block, extraLabels)
-		})
+	return stream.Parse(req.Body, isGzip, func(block *stream.Block) error {
+		return insertRows(at, block, extraLabels)
 	})
 }
 
-func insertRows(at *auth.Token, block *parser.Block, extraLabels []prompbmarshal.Label) error {
+func insertRows(at *auth.Token, block *stream.Block, extraLabels []prompbmarshal.Label) error {
 	ctx := common.GetPushCtx()
 	defer common.PutPushCtx(ctx)
 

app/vmagent/opentsdb/request_handler.go

@@ -7,7 +7,7 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
 	parser "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/opentsdb"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/opentsdb/stream"
 	"github.com/VictoriaMetrics/metrics"
 )
 
@@ -20,9 +20,7 @@ var (
 //
 // See http://opentsdb.net/docs/build/html/api_telnet/put.html
 func InsertHandler(r io.Reader) error {
-	return writeconcurrencylimiter.Do(func() error {
-		return parser.ParseStream(r, insertRows)
-	})
+	return stream.Parse(r, insertRows)
 }
 
 func insertRows(rows []parser.Row) error {

app/vmagent/opentsdbhttp/request_handler.go

@@ -9,7 +9,7 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
 	parserCommon "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
 	parser "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/opentsdbhttp"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/opentsdbhttp/stream"
 	"github.com/VictoriaMetrics/metrics"
 )
 
@@ -25,10 +25,8 @@ func InsertHandler(at *auth.Token, req *http.Request) error {
 	if err != nil {
 		return err
 	}
-	return writeconcurrencylimiter.Do(func() error {
-		return parser.ParseStream(req, func(rows []parser.Row) error {
-			return insertRows(at, rows, extraLabels)
-		})
+	return stream.Parse(req, func(rows []parser.Row) error {
+		return insertRows(at, rows, extraLabels)
 	})
 }
 

app/vmagent/prometheusimport/request_handler.go

@@ -1,17 +1,17 @@
 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/httpserver"
 	"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/protoparser/prometheus/stream"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
 	"github.com/VictoriaMetrics/metrics"
 )
 
@@ -31,20 +31,11 @@ func InsertHandler(at *auth.Token, req *http.Request) error {
 	if err != nil {
 		return err
 	}
-	return writeconcurrencylimiter.Do(func() error {
-		isGzipped := req.Header.Get("Content-Encoding") == "gzip"
-		return parser.ParseStream(req.Body, defaultTimestamp, isGzipped, func(rows []parser.Row) error {
-			return insertRows(at, rows, extraLabels)
-		}, nil)
-	})
-}
-
-// InsertHandlerForReader processes metrics from given reader with optional gzip format
-func InsertHandlerForReader(r io.Reader, isGzipped bool) error {
-	return writeconcurrencylimiter.Do(func() error {
-		return parser.ParseStream(r, 0, isGzipped, func(rows []parser.Row) error {
-			return insertRows(nil, rows, nil)
-		}, nil)
+	isGzipped := req.Header.Get("Content-Encoding") == "gzip"
+	return stream.Parse(req.Body, defaultTimestamp, isGzipped, func(rows []parser.Row) error {
+		return insertRows(at, rows, extraLabels)
+	}, func(s string) {
+		httpserver.LogError(req, s)
 	})
 }
 

app/vmagent/prometheusimport/request_handler_test.go

@@ -0,0 +1,60 @@
+package prometheusimport
+
+import (
+	"bytes"
+	"flag"
+	"log"
+	"net/http"
+	"net/http/httptest"
+	"strings"
+	"testing"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/fs"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
+)
+
+var (
+	srv        *httptest.Server
+	testOutput *bytes.Buffer
+)
+
+func TestInsertHandler(t *testing.T) {
+	setUp()
+	defer tearDown()
+	req := httptest.NewRequest(http.MethodPost, "/insert/0/api/v1/import/prometheus", bytes.NewBufferString(`{"foo":"bar"}
+go_memstats_alloc_bytes_total 1`))
+	if err := InsertHandler(nil, req); err != nil {
+		t.Errorf("unxepected error %s", err)
+	}
+	expectedMsg := "cannot unmarshal Prometheus line"
+	if !strings.Contains(testOutput.String(), expectedMsg) {
+		t.Errorf("output %q should contain %q", testOutput.String(), expectedMsg)
+	}
+}
+
+func setUp() {
+	srv = httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
+		w.WriteHeader(204)
+	}))
+	flag.Parse()
+	remoteWriteFlag := "remoteWrite.url"
+	if err := flag.Lookup(remoteWriteFlag).Value.Set(srv.URL); err != nil {
+		log.Fatalf("unable to set %q with value %q, err: %v", remoteWriteFlag, srv.URL, err)
+	}
+	logger.Init()
+	common.StartUnmarshalWorkers()
+	remotewrite.Init()
+	testOutput = &bytes.Buffer{}
+	logger.SetOutputForTests(testOutput)
+}
+
+func tearDown() {
+	common.StopUnmarshalWorkers()
+	srv.Close()
+	logger.ResetOutputForTest()
+	tmpDataDir := flag.Lookup("remoteWrite.tmpDataPath").Value.String()
+	fs.MustRemoveAll(tmpDataDir)
+
+}

app/vmagent/promremotewrite/request_handler.go

@@ -1,7 +1,6 @@
 package promremotewrite
 
 import (
-	"io"
 	"net/http"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/common"
@@ -11,9 +10,8 @@ import (
 	"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/protoparser/promremotewrite/stream"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
 	"github.com/VictoriaMetrics/metrics"
 )
 
@@ -29,19 +27,9 @@ func InsertHandler(at *auth.Token, req *http.Request) error {
 	if err != nil {
 		return err
 	}
-	return writeconcurrencylimiter.Do(func() error {
-		return parser.ParseStream(req.Body, func(tss []prompb.TimeSeries) error {
-			return insertRows(at, tss, extraLabels)
-		})
-	})
-}
-
-// InsertHandlerForReader processes metrics from given reader
-func InsertHandlerForReader(at *auth.Token, r io.Reader) error {
-	return writeconcurrencylimiter.Do(func() error {
-		return parser.ParseStream(r, func(tss []prompb.TimeSeries) error {
-			return insertRows(at, tss, nil)
-		})
+	isVMRemoteWrite := req.Header.Get("Content-Encoding") == "zstd"
+	return stream.Parse(req.Body, isVMRemoteWrite, func(tss []prompb.TimeSeries) error {
+		return insertRows(at, tss, extraLabels)
 	})
 }
 

app/vmagent/remotewrite/client.go

@@ -15,11 +15,17 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/persistentqueue"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promauth"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/timerpool"
 	"github.com/VictoriaMetrics/metrics"
 )
 
 var (
+	forcePromProto = flagutil.NewArrayBool("remoteWrite.forcePromProto", "Whether to force Prometheus remote write protocol for sending data "+
+		"to the corresponding -remoteWrite.url . See https://docs.victoriametrics.com/vmagent.html#victoriametrics-remote-write-protocol")
+	forceVMProto = flagutil.NewArrayBool("remoteWrite.forceVMProto", "Whether to force VictoriaMetrics remote write protocol for sending data "+
+		"to the corresponding -remoteWrite.url . See https://docs.victoriametrics.com/vmagent.html#victoriametrics-remote-write-protocol")
+
 	rateLimit = flagutil.NewArrayInt("remoteWrite.rateLimit", "Optional rate limit in bytes per second for data sent to the corresponding -remoteWrite.url. "+
 		"By default the rate limit is disabled. It can be useful for limiting load on remote storage when big amounts of buffered data "+
 		"is sent after temporary unavailability of the remote storage")
@@ -69,8 +75,12 @@ var (
 type client struct {
 	sanitizedURL   string
 	remoteWriteURL string
-	fq             *persistentqueue.FastQueue
-	hc             *http.Client
+
+	// Whether to use VictoriaMetrics remote write protocol for sending the data to remoteWriteURL
+	useVMProto bool
+
+	fq *persistentqueue.FastQueue
+	hc *http.Client
 
 	sendBlock func(block []byte) bool
 	authCfg   *promauth.Config
@@ -122,19 +132,39 @@ func newHTTPClient(argIdx int, remoteWriteURL, sanitizedURL string, fq *persiste
 		}
 		tr.Proxy = http.ProxyURL(pu)
 	}
+	hc := &http.Client{
+		Transport: tr,
+		Timeout:   sendTimeout.GetOptionalArgOrDefault(argIdx, time.Minute),
+	}
 	c := &client{
 		sanitizedURL:   sanitizedURL,
 		remoteWriteURL: remoteWriteURL,
 		authCfg:        authCfg,
 		awsCfg:         awsCfg,
 		fq:             fq,
-		hc: &http.Client{
-			Transport: tr,
-			Timeout:   sendTimeout.GetOptionalArgOrDefault(argIdx, time.Minute),
-		},
-		stopCh: make(chan struct{}),
+		hc:             hc,
+		stopCh:         make(chan struct{}),
 	}
 	c.sendBlock = c.sendBlockHTTP
+
+	useVMProto := forceVMProto.GetOptionalArg(argIdx)
+	usePromProto := forcePromProto.GetOptionalArg(argIdx)
+	if useVMProto && usePromProto {
+		logger.Fatalf("-remoteWrite.useVMProto and -remoteWrite.usePromProto cannot be set simultaneously for -remoteWrite.url=%s", sanitizedURL)
+	}
+	if !useVMProto && !usePromProto {
+		// Auto-detect whether the remote storage supports VictoriaMetrics remote write protocol.
+		doRequest := func(url string) (*http.Response, error) {
+			return c.doRequest(url, nil)
+		}
+		useVMProto = common.HandleVMProtoClientHandshake(c.remoteWriteURL, doRequest)
+		if !useVMProto {
+			logger.Infof("the remote storage at %q doesn't support VictoriaMetrics remote write protocol. Switching to Prometheus remote write protocol. "+
+				"See https://docs.victoriametrics.com/vmagent.html#victoriametrics-remote-write-protocol", sanitizedURL)
+		}
+	}
+	c.useVMProto = useVMProto
+
 	return c
 }
 
@@ -291,38 +321,45 @@ func (c *client) runWorker() {
 	}
 }
 
-// sendBlockHTTP returns false only if c.stopCh is closed.
-// Otherwise it tries sending the block to remote storage indefinitely.
-func (c *client) sendBlockHTTP(block []byte) bool {
-	c.rl.register(len(block), c.stopCh)
-	retryDuration := time.Second
-	retriesCount := 0
-	c.bytesSent.Add(len(block))
-	c.blocksSent.Inc()
-	sigv4Hash := ""
-	if c.awsCfg != nil {
-		sigv4Hash = awsapi.HashHex(block)
-	}
-
-again:
-	req, err := http.NewRequest("POST", c.remoteWriteURL, bytes.NewBuffer(block))
+func (c *client) doRequest(url string, body []byte) (*http.Response, error) {
+	reqBody := bytes.NewBuffer(body)
+	req, err := http.NewRequest(http.MethodPost, url, reqBody)
 	if err != nil {
-		logger.Panicf("BUG: unexpected error from http.NewRequest(%q): %s", c.sanitizedURL, err)
+		logger.Panicf("BUG: unexpected error from http.NewRequest(%q): %s", url, err)
 	}
 	c.authCfg.SetHeaders(req, true)
 	h := req.Header
 	h.Set("User-Agent", "vmagent")
 	h.Set("Content-Type", "application/x-protobuf")
-	h.Set("Content-Encoding", "snappy")
-	h.Set("X-Prometheus-Remote-Write-Version", "0.1.0")
+	if c.useVMProto {
+		h.Set("Content-Encoding", "zstd")
+		h.Set("X-VictoriaMetrics-Remote-Write-Version", "1")
+	} else {
+		h.Set("Content-Encoding", "snappy")
+		h.Set("X-Prometheus-Remote-Write-Version", "0.1.0")
+	}
 	if c.awsCfg != nil {
+		sigv4Hash := awsapi.HashHex(body)
 		if err := c.awsCfg.SignRequest(req, sigv4Hash); err != nil {
 			// there is no need in retry, request will be rejected by client.Do and retried by code below
 			logger.Warnf("cannot sign remoteWrite request with AWS sigv4: %s", err)
 		}
 	}
+	return c.hc.Do(req)
+}
+
+// sendBlockHTTP sends the given block to c.remoteWriteURL.
+//
+// The function returns false only if c.stopCh is closed.
+// Otherwise it tries sending the block to remote storage indefinitely.
+func (c *client) sendBlockHTTP(block []byte) bool {
+	c.rl.register(len(block), c.stopCh)
+	retryDuration := time.Second
+	retriesCount := 0
+
+again:
 	startTime := time.Now()
-	resp, err := c.hc.Do(req)
+	resp, err := c.doRequest(c.remoteWriteURL, block)
 	c.requestDuration.UpdateDuration(startTime)
 	if err != nil {
 		c.errorsCount.Inc()
@@ -347,6 +384,8 @@ again:
 	if statusCode/100 == 2 {
 		_ = resp.Body.Close()
 		c.requestsOKCount.Inc()
+		c.bytesSent.Add(len(block))
+		c.blocksSent.Inc()
 		return true
 	}
 	metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_requests_total{url=%q, status_code="%d"}`, c.sanitizedURL, statusCode)).Inc()

app/vmagent/remotewrite/pendingseries.go

@@ -8,6 +8,7 @@ import (
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/decimal"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/encoding/zstd"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/fasttime"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
@@ -23,6 +24,9 @@ var (
 		"This option takes effect only when less than 10K data points per second are pushed to -remoteWrite.url")
 	maxUnpackedBlockSize = flagutil.NewBytes("remoteWrite.maxBlockSize", 8*1024*1024, "The maximum block size to send to remote storage. Bigger blocks may improve performance at the cost of the increased memory usage. See also -remoteWrite.maxRowsPerBlock")
 	maxRowsPerBlock      = flag.Int("remoteWrite.maxRowsPerBlock", 10000, "The maximum number of samples to send in each block to remote storage. Higher number may improve performance at the cost of the increased memory usage. See also -remoteWrite.maxBlockSize")
+	vmProtoCompressLevel = flag.Int("remoteWrite.vmProtoCompressLevel", 0, "The compression level for VictoriaMetrics remote write protocol. "+
+		"Higher values reduce network traffic at the cost of higher CPU usage. Negative values reduce CPU usage at the cost of increased network traffic. "+
+		"See https://docs.victoriametrics.com/vmagent.html#victoriametrics-remote-write-protocol")
 )
 
 type pendingSeries struct {
@@ -33,9 +37,10 @@ type pendingSeries struct {
 	periodicFlusherWG sync.WaitGroup
 }
 
-func newPendingSeries(pushBlock func(block []byte), significantFigures, roundDigits int) *pendingSeries {
+func newPendingSeries(pushBlock func(block []byte), isVMRemoteWrite bool, significantFigures, roundDigits int) *pendingSeries {
 	var ps pendingSeries
 	ps.wr.pushBlock = pushBlock
+	ps.wr.isVMRemoteWrite = isVMRemoteWrite
 	ps.wr.significantFigures = significantFigures
 	ps.wr.roundDigits = roundDigits
 	ps.stopCh = make(chan struct{})
@@ -88,6 +93,9 @@ type writeRequest struct {
 	// pushBlock is called when whe write request is ready to be sent.
 	pushBlock func(block []byte)
 
+	// Whether to encode the write request with VictoriaMetrics remote write protocol.
+	isVMRemoteWrite bool
+
 	// How many significant figures must be left before sending the writeRequest to pushBlock.
 	significantFigures int
 
@@ -104,7 +112,7 @@ type writeRequest struct {
 }
 
 func (wr *writeRequest) reset() {
-	// Do not reset pushBlock, significantFigures and roundDigits, since they are re-used.
+	// Do not reset lastFlushTime, pushBlock, isVMRemoteWrite, significantFigures and roundDigits, since they are re-used.
 
 	wr.wr.Timeseries = nil
 
@@ -126,7 +134,7 @@ func (wr *writeRequest) flush() {
 	wr.wr.Timeseries = wr.tss
 	wr.adjustSampleValues()
 	atomic.StoreUint64(&wr.lastFlushTime, fasttime.UnixTimestamp())
-	pushWriteRequest(&wr.wr, wr.pushBlock)
+	pushWriteRequest(&wr.wr, wr.pushBlock, wr.isVMRemoteWrite)
 	wr.reset()
 }
 
@@ -188,16 +196,20 @@ func (wr *writeRequest) copyTimeSeries(dst, src *prompbmarshal.TimeSeries) {
 	wr.buf = buf
 }
 
-func pushWriteRequest(wr *prompbmarshal.WriteRequest, pushBlock func(block []byte)) {
+func pushWriteRequest(wr *prompbmarshal.WriteRequest, pushBlock func(block []byte), isVMRemoteWrite bool) {
 	if len(wr.Timeseries) == 0 {
 		// Nothing to push
 		return
 	}
 	bb := writeRequestBufPool.Get()
 	bb.B = prompbmarshal.MarshalWriteRequest(bb.B[:0], wr)
-	if len(bb.B) <= maxUnpackedBlockSize.N {
+	if len(bb.B) <= maxUnpackedBlockSize.IntN() {
 		zb := snappyBufPool.Get()
-		zb.B = snappy.Encode(zb.B[:cap(zb.B)], bb.B)
+		if isVMRemoteWrite {
+			zb.B = zstd.CompressLevel(zb.B[:0], bb.B, *vmProtoCompressLevel)
+		} else {
+			zb.B = snappy.Encode(zb.B[:cap(zb.B)], bb.B)
+		}
 		writeRequestBufPool.Put(bb)
 		if len(zb.B) <= persistentqueue.MaxBlockSize {
 			pushBlock(zb.B)
@@ -221,18 +233,18 @@ func pushWriteRequest(wr *prompbmarshal.WriteRequest, pushBlock func(block []byt
 		}
 		n := len(samples) / 2
 		wr.Timeseries[0].Samples = samples[:n]
-		pushWriteRequest(wr, pushBlock)
+		pushWriteRequest(wr, pushBlock, isVMRemoteWrite)
 		wr.Timeseries[0].Samples = samples[n:]
-		pushWriteRequest(wr, pushBlock)
+		pushWriteRequest(wr, pushBlock, isVMRemoteWrite)
 		wr.Timeseries[0].Samples = samples
 		return
 	}
 	timeseries := wr.Timeseries
 	n := len(timeseries) / 2
 	wr.Timeseries = timeseries[:n]
-	pushWriteRequest(wr, pushBlock)
+	pushWriteRequest(wr, pushBlock, isVMRemoteWrite)
 	wr.Timeseries = timeseries[n:]
-	pushWriteRequest(wr, pushBlock)
+	pushWriteRequest(wr, pushBlock, isVMRemoteWrite)
 	wr.Timeseries = timeseries
 }
 

app/vmagent/remotewrite/pendingseries_test.go

@@ -2,40 +2,48 @@ package remotewrite
 
 import (
 	"fmt"
+	"math"
 	"testing"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
-	"github.com/golang/snappy"
 )
 
 func TestPushWriteRequest(t *testing.T) {
-	for _, rowsCount := range []int{1, 10, 100, 1e3, 1e4} {
+	rowsCounts := []int{1, 10, 100, 1e3, 1e4}
+	expectedBlockLensProm := []int{216, 1848, 16424, 169882, 1757876}
+	expectedBlockLensVM := []int{138, 492, 3927, 34995, 288476}
+	for i, rowsCount := range rowsCounts {
+		expectedBlockLenProm := expectedBlockLensProm[i]
+		expectedBlockLenVM := expectedBlockLensVM[i]
 		t.Run(fmt.Sprintf("%d", rowsCount), func(t *testing.T) {
-			testPushWriteRequest(t, rowsCount)
+			testPushWriteRequest(t, rowsCount, expectedBlockLenProm, expectedBlockLenVM)
 		})
 	}
 }
 
-func testPushWriteRequest(t *testing.T, rowsCount int) {
-	wr := newTestWriteRequest(rowsCount, 10)
-	pushBlockLen := 0
-	pushBlock := func(block []byte) {
-		if pushBlockLen > 0 {
-			panic(fmt.Errorf("BUG: pushBlock called multiple times; pushBlockLen=%d at first call, len(block)=%d at second call", pushBlockLen, len(block)))
+func testPushWriteRequest(t *testing.T, rowsCount, expectedBlockLenProm, expectedBlockLenVM int) {
+	f := func(isVMRemoteWrite bool, expectedBlockLen int, tolerancePrc float64) {
+		t.Helper()
+		wr := newTestWriteRequest(rowsCount, 20)
+		pushBlockLen := 0
+		pushBlock := func(block []byte) {
+			if pushBlockLen > 0 {
+				panic(fmt.Errorf("BUG: pushBlock called multiple times; pushBlockLen=%d at first call, len(block)=%d at second call", pushBlockLen, len(block)))
+			}
+			pushBlockLen = len(block)
+		}
+		pushWriteRequest(wr, pushBlock, isVMRemoteWrite)
+		if math.Abs(float64(pushBlockLen-expectedBlockLen)/float64(expectedBlockLen)*100) > tolerancePrc {
+			t.Fatalf("unexpected block len for rowsCount=%d, isVMRemoteWrite=%v; got %d bytes; expecting %d bytes +- %.0f%%",
+				rowsCount, isVMRemoteWrite, pushBlockLen, expectedBlockLen, tolerancePrc)
 		}
-		pushBlockLen = len(block)
-	}
-	pushWriteRequest(wr, pushBlock)
-	b := prompbmarshal.MarshalWriteRequest(nil, wr)
-	zb := snappy.Encode(nil, b)
-	maxPushBlockLen := len(zb)
-	minPushBlockLen := maxPushBlockLen / 2
-	if pushBlockLen < minPushBlockLen {
-		t.Fatalf("unexpected block len after pushWriteRequest; got %d bytes; must be at least %d bytes", pushBlockLen, minPushBlockLen)
-	}
-	if pushBlockLen > maxPushBlockLen {
-		t.Fatalf("unexpected block len after pushWriteRequest; got %d bytes; must be smaller or equal to %d bytes", pushBlockLen, maxPushBlockLen)
 	}
+
+	// Check Prometheus remote write
+	f(false, expectedBlockLenProm, 0)
+
+	// Check VictoriaMetrics remote write
+	f(true, expectedBlockLenVM, 15)
 }
 
 func newTestWriteRequest(seriesCount, labelsCount int) *prompbmarshal.WriteRequest {

app/vmagent/remotewrite/relabel.go

@@ -15,11 +15,13 @@ import (
 var (
 	unparsedLabelsGlobal = flagutil.NewArrayString("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 labels to metrics before sending them to remote storage")
-	relabelConfigPathGlobal = flag.String("remoteWrite.relabelConfig", "", "Optional path to file with relabel_config entries. "+
-		"The path can point either to local file or to http url. These entries are applied to all the metrics "+
-		"before sending them to -remoteWrite.url. See https://docs.victoriametrics.com/vmagent.html#relabeling for details")
-	relabelConfigPaths = flagutil.NewArrayString("remoteWrite.urlRelabelConfig", "Optional path to relabel config for the corresponding -remoteWrite.url. "+
-		"The path can point either to local file or to http url")
+	relabelConfigPathGlobal = flag.String("remoteWrite.relabelConfig", "", "Optional path to file with relabeling configs, which are applied "+
+		"to all the metrics before sending them to -remoteWrite.url. See also -remoteWrite.urlRelabelConfig. "+
+		"The path can point either to local file or to http url. "+
+		"See https://docs.victoriametrics.com/vmagent.html#relabeling")
+	relabelConfigPaths = flagutil.NewArrayString("remoteWrite.urlRelabelConfig", "Optional path to relabel configs for the corresponding -remoteWrite.url. "+
+		"See also -remoteWrite.relabelConfig. The path can point either to local file or to http url. "+
+		"See https://docs.victoriametrics.com/vmagent.html#relabeling")
 
 	usePromCompatibleNaming = flag.Bool("usePromCompatibleNaming", false, "Whether to replace characters unsupported by Prometheus with underscores "+
 		"in the ingested metric names and label names. For example, foo.bar{a.b='c'} is transformed into foo_bar{a_b='c'} during data ingestion if this flag is set. "+
@@ -86,7 +88,7 @@ func initLabelsGlobal() {
 }
 
 func (rctx *relabelCtx) applyRelabeling(tss []prompbmarshal.TimeSeries, extraLabels []prompbmarshal.Label, pcs *promrelabel.ParsedConfigs) []prompbmarshal.TimeSeries {
-	if len(extraLabels) == 0 && pcs.Len() == 0 {
+	if len(extraLabels) == 0 && pcs.Len() == 0 && !*usePromCompatibleNaming {
 		// Nothing to change.
 		return tss
 	}

app/vmagent/remotewrite/relabel_test.go

@@ -0,0 +1,49 @@
+package remotewrite
+
+import (
+	"reflect"
+	"testing"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promutils"
+)
+
+func TestApplyRelabeling(t *testing.T) {
+	f := func(extraLabels []prompbmarshal.Label, pcs *promrelabel.ParsedConfigs, sTss, sExpTss string) {
+		rctx := &relabelCtx{}
+		tss, expTss := parseSeries(sTss), parseSeries(sExpTss)
+		gotTss := rctx.applyRelabeling(tss, extraLabels, pcs)
+		if !reflect.DeepEqual(gotTss, expTss) {
+			t.Fatalf("expected to have: \n%v;\ngot: \n%v", expTss, gotTss)
+		}
+	}
+
+	f(nil, nil, "up", "up")
+	f([]prompbmarshal.Label{{Name: "foo", Value: "bar"}}, nil, "up", `up{foo="bar"}`)
+	f([]prompbmarshal.Label{{Name: "foo", Value: "bar"}}, nil, `up{foo="baz"}`, `up{foo="bar"}`)
+
+	pcs, err := promrelabel.ParseRelabelConfigsData([]byte(`
+- target_label: "foo"
+  replacement: "aaa"
+- action: labeldrop
+  regex: "env.*"
+`))
+	if err != nil {
+		t.Fatalf("unexpected error: %s", err)
+	}
+	f(nil, pcs, `up{foo="baz", env="prod"}`, `up{foo="aaa"}`)
+
+	oldVal := *usePromCompatibleNaming
+	*usePromCompatibleNaming = true
+	f(nil, nil, `foo.bar`, `foo_bar`)
+	*usePromCompatibleNaming = oldVal
+}
+
+func parseSeries(data string) []prompbmarshal.TimeSeries {
+	var tss []prompbmarshal.TimeSeries
+	tss = append(tss, prompbmarshal.TimeSeries{
+		Labels: promutils.MustNewLabelsFromString(data).GetLabels(),
+	})
+	return tss
+}

app/vmagent/remotewrite/remotewrite.go

@@ -4,37 +4,44 @@ import (
 	"flag"
 	"fmt"
 	"net/url"
+	"os"
+	"path/filepath"
 	"strconv"
 	"sync"
 	"sync/atomic"
 	"time"
 
+	"github.com/cespare/xxhash/v2"
+
 	"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/fasttime"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/fs"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/memory"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/persistentqueue"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/procutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/streamaggr"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
 	"github.com/VictoriaMetrics/metrics"
-	"github.com/cespare/xxhash/v2"
 )
 
 var (
-	remoteWriteURLs = flagutil.NewArrayString("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 replicate data to multiple remote storage systems. See also -remoteWrite.multitenantURL")
+	remoteWriteURLs = flagutil.NewArrayString("remoteWrite.url", "Remote storage URL to write data to. It must support either VictoriaMetrics remote write protocol "+
+		"or Prometheus remote_write protocol. Example url: http://<victoriametrics-host>:8428/api/v1/write . "+
+		"Pass multiple -remoteWrite.url options in order to replicate the collected data to multiple remote storage systems. See also -remoteWrite.multitenantURL")
 	remoteWriteMultitenantURLs = flagutil.NewArrayString("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")
+	keepDanglingQueues = flag.Bool("remoteWrite.keepDanglingQueues", false, "Keep persistent queues contents at -remoteWrite.tmpDataPath in case there are no matching -remoteWrite.url. "+
+		"Useful when -remoteWrite.url is changed temporarily and persistent queue files will be needed later on.")
 	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. "+
@@ -58,6 +65,15 @@ var (
 		"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")
+
+	streamAggrConfig = flagutil.NewArrayString("remoteWrite.streamAggr.config", "Optional path to file with stream aggregation config. "+
+		"See https://docs.victoriametrics.com/stream-aggregation.html . "+
+		"See also -remoteWrite.streamAggr.keepInput and -remoteWrite.streamAggr.dedupInterval")
+	streamAggrKeepInput = flagutil.NewArrayBool("remoteWrite.streamAggr.keepInput", "Whether to keep input samples after the aggregation with -remoteWrite.streamAggr.config. "+
+		"By default the input is dropped after the aggregation, so only the aggregate data is sent to the -remoteWrite.url. "+
+		"See https://docs.victoriametrics.com/stream-aggregation.html")
+	streamAggrDedupInterval = flagutil.NewArrayDuration("remoteWrite.streamAggr.dedupInterval", "Input samples are de-duplicated with this interval before being aggregated. "+
+		"Only the last sample per each time series per each interval is aggregated if the interval is greater than zero")
 )
 
 var (
@@ -84,6 +100,8 @@ var allRelabelConfigs atomic.Value
 // since it may lead to high memory usage due to big number of buffers.
 var maxQueues = cgroup.AvailableCPUs() * 16
 
+const persistentQueueDirname = "persistent-queue"
+
 // InitSecretFlags must be called after flag.Parse and before any logging.
 func InitSecretFlags() {
 	if !*showRemoteWriteURL {
@@ -140,8 +158,8 @@ func Init() {
 		logger.Fatalf("cannot load relabel configs: %s", err)
 	}
 	allRelabelConfigs.Store(rcs)
-	configSuccess.Set(1)
-	configTimestamp.Set(fasttime.UnixTimestamp())
+	relabelConfigSuccess.Set(1)
+	relabelConfigTimestamp.Set(fasttime.UnixTimestamp())
 
 	if len(*remoteWriteURLs) > 0 {
 		rwctxsDefault = newRemoteWriteCtxs(nil, *remoteWriteURLs)
@@ -154,34 +172,56 @@ func Init() {
 		for {
 			select {
 			case <-sighupCh:
-			case <-stopCh:
+			case <-configReloaderStopCh:
 				return
 			}
-			configReloads.Inc()
-			logger.Infof("SIGHUP received; reloading relabel configs pointed by -remoteWrite.relabelConfig and -remoteWrite.urlRelabelConfig")
-			rcs, err := loadRelabelConfigs()
-			if err != nil {
-				configReloadErrors.Inc()
-				configSuccess.Set(0)
-				logger.Errorf("cannot reload relabel configs; preserving the previous configs; error: %s", err)
-				continue
-			}
-
-			allRelabelConfigs.Store(rcs)
-			configSuccess.Set(1)
-			configTimestamp.Set(fasttime.UnixTimestamp())
-			logger.Infof("Successfully reloaded relabel configs")
+			reloadRelabelConfigs()
+			reloadStreamAggrConfigs()
 		}
 	}()
 }
 
+func reloadRelabelConfigs() {
+	relabelConfigReloads.Inc()
+	logger.Infof("reloading relabel configs pointed by -remoteWrite.relabelConfig and -remoteWrite.urlRelabelConfig")
+	rcs, err := loadRelabelConfigs()
+	if err != nil {
+		relabelConfigReloadErrors.Inc()
+		relabelConfigSuccess.Set(0)
+		logger.Errorf("cannot reload relabel configs; preserving the previous configs; error: %s", err)
+		return
+	}
+	allRelabelConfigs.Store(rcs)
+	relabelConfigSuccess.Set(1)
+	relabelConfigTimestamp.Set(fasttime.UnixTimestamp())
+	logger.Infof("successfully reloaded relabel configs")
+}
+
 var (
-	configReloads      = metrics.NewCounter(`vmagent_relabel_config_reloads_total`)
-	configReloadErrors = metrics.NewCounter(`vmagent_relabel_config_reloads_errors_total`)
-	configSuccess      = metrics.NewCounter(`vmagent_relabel_config_last_reload_successful`)
-	configTimestamp    = metrics.NewCounter(`vmagent_relabel_config_last_reload_success_timestamp_seconds`)
+	relabelConfigReloads      = metrics.NewCounter(`vmagent_relabel_config_reloads_total`)
+	relabelConfigReloadErrors = metrics.NewCounter(`vmagent_relabel_config_reloads_errors_total`)
+	relabelConfigSuccess      = metrics.NewCounter(`vmagent_relabel_config_last_reload_successful`)
+	relabelConfigTimestamp    = metrics.NewCounter(`vmagent_relabel_config_last_reload_success_timestamp_seconds`)
 )
 
+func reloadStreamAggrConfigs() {
+	if len(*remoteWriteMultitenantURLs) > 0 {
+		rwctxsMapLock.Lock()
+		for _, rwctxs := range rwctxsMap {
+			reinitStreamAggr(rwctxs)
+		}
+		rwctxsMapLock.Unlock()
+	} else {
+		reinitStreamAggr(rwctxsDefault)
+	}
+}
+
+func reinitStreamAggr(rwctxs []*remoteWriteCtx) {
+	for _, rwctx := range rwctxs {
+		rwctx.reinitStreamAggr()
+	}
+}
+
 func newRemoteWriteCtxs(at *auth.Token, urls []string) []*remoteWriteCtx {
 	if len(urls) == 0 {
 		logger.Panicf("BUG: urls must be non-empty")
@@ -214,17 +254,47 @@ func newRemoteWriteCtxs(at *auth.Token, urls []string) []*remoteWriteCtx {
 		}
 		rwctxs[i] = newRemoteWriteCtx(i, at, remoteWriteURL, maxInmemoryBlocks, sanitizedURL)
 	}
+
+	if !*keepDanglingQueues {
+		// Remove dangling queues, if any.
+		// This is required for the case when the number of queues has been changed or URL have been changed.
+		// See: https://github.com/VictoriaMetrics/VictoriaMetrics/issues/4014
+		existingQueues := make(map[string]struct{}, len(rwctxs))
+		for _, rwctx := range rwctxs {
+			existingQueues[rwctx.fq.Dirname()] = struct{}{}
+		}
+
+		queuesDir := filepath.Join(*tmpDataPath, persistentQueueDirname)
+		files, err := os.ReadDir(queuesDir)
+		if err != nil {
+			logger.Fatalf("cannot read queues dir %q: %s", queuesDir, err)
+		}
+		removed := 0
+		for _, f := range files {
+			dirname := f.Name()
+			if _, ok := existingQueues[dirname]; !ok {
+				logger.Infof("removing dangling queue %q", dirname)
+				fullPath := filepath.Join(queuesDir, dirname)
+				fs.MustRemoveAll(fullPath)
+				removed++
+			}
+		}
+		if removed > 0 {
+			logger.Infof("removed %d dangling queues from %q, active queues: %d", removed, *tmpDataPath, len(rwctxs))
+		}
+	}
+
 	return rwctxs
 }
 
-var stopCh = make(chan struct{})
+var configReloaderStopCh = make(chan struct{})
 var configReloaderWG sync.WaitGroup
 
 // Stop stops remotewrite.
 //
 // It is expected that nobody calls Push during and after the call to this func.
 func Stop() {
-	close(stopCh)
+	close(configReloaderStopCh)
 	configReloaderWG.Wait()
 
 	for _, rwctx := range rwctxsDefault {
@@ -435,9 +505,13 @@ var (
 )
 
 type remoteWriteCtx struct {
-	idx        int
-	fq         *persistentqueue.FastQueue
-	c          *client
+	idx int
+	fq  *persistentqueue.FastQueue
+	c   *client
+
+	sas                 atomic.Pointer[streamaggr.Aggregators]
+	streamAggrKeepInput bool
+
 	pss        []*pendingSeries
 	pssNextIdx uint64
 
@@ -451,7 +525,7 @@ func newRemoteWriteCtx(argIdx int, at *auth.Token, remoteWriteURL *url.URL, maxI
 	pqURL.RawQuery = ""
 	pqURL.Fragment = ""
 	h := xxhash.Sum64([]byte(pqURL.String()))
-	queuePath := fmt.Sprintf("%s/persistent-queue/%d_%016X", *tmpDataPath, argIdx+1, h)
+	queuePath := filepath.Join(*tmpDataPath, persistentQueueDirname, fmt.Sprintf("%d_%016X", argIdx+1, h))
 	maxPendingBytes := maxPendingBytesPerURL.GetOptionalArgOrDefault(argIdx, 0)
 	fq := persistentqueue.MustOpenFastQueue(queuePath, sanitizedURL, maxInmemoryBlocks, maxPendingBytes)
 	_ = metrics.GetOrCreateGauge(fmt.Sprintf(`vmagent_remotewrite_pending_data_bytes{path=%q, url=%q}`, queuePath, sanitizedURL), func() float64 {
@@ -460,6 +534,7 @@ func newRemoteWriteCtx(argIdx int, at *auth.Token, remoteWriteURL *url.URL, maxI
 	_ = metrics.GetOrCreateGauge(fmt.Sprintf(`vmagent_remotewrite_pending_inmemory_blocks{path=%q, url=%q}`, queuePath, sanitizedURL), func() float64 {
 		return float64(fq.GetInmemoryQueueLen())
 	})
+
 	var c *client
 	switch remoteWriteURL.Scheme {
 	case "http", "https":
@@ -469,6 +544,7 @@ func newRemoteWriteCtx(argIdx int, at *auth.Token, remoteWriteURL *url.URL, maxI
 	}
 	c.init(argIdx, *queues, sanitizedURL)
 
+	// Initialize pss
 	sf := significantFigures.GetOptionalArgOrDefault(argIdx, 0)
 	rd := roundDigits.GetOptionalArgOrDefault(argIdx, 100)
 	pssLen := *queues
@@ -479,9 +555,10 @@ func newRemoteWriteCtx(argIdx int, at *auth.Token, remoteWriteURL *url.URL, maxI
 	}
 	pss := make([]*pendingSeries, pssLen)
 	for i := range pss {
-		pss[i] = newPendingSeries(fq.MustWriteBlock, sf, rd)
+		pss[i] = newPendingSeries(fq.MustWriteBlock, c.useVMProto, sf, rd)
 	}
-	return &remoteWriteCtx{
+
+	rwctx := &remoteWriteCtx{
 		idx: argIdx,
 		fq:  fq,
 		c:   c,
@@ -490,6 +567,22 @@ func newRemoteWriteCtx(argIdx int, at *auth.Token, remoteWriteURL *url.URL, maxI
 		rowsPushedAfterRelabel: metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_rows_pushed_after_relabel_total{path=%q, url=%q}`, queuePath, sanitizedURL)),
 		rowsDroppedByRelabel:   metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_relabel_metrics_dropped_total{path=%q, url=%q}`, queuePath, sanitizedURL)),
 	}
+
+	// Initialize sas
+	sasFile := streamAggrConfig.GetOptionalArg(argIdx)
+	if sasFile != "" {
+		dedupInterval := streamAggrDedupInterval.GetOptionalArgOrDefault(argIdx, 0)
+		sas, err := streamaggr.LoadFromFile(sasFile, rwctx.pushInternal, dedupInterval)
+		if err != nil {
+			logger.Fatalf("cannot initialize stream aggregators from -remoteWrite.streamAggr.config=%q: %s", sasFile, err)
+		}
+		rwctx.sas.Store(sas)
+		rwctx.streamAggrKeepInput = streamAggrKeepInput.GetOptionalArg(argIdx)
+		metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reload_successful{path=%q}`, sasFile)).Set(1)
+		metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reload_success_timestamp_seconds{path=%q}`, sasFile)).Set(fasttime.UnixTimestamp())
+	}
+
+	return rwctx
 }
 
 func (rwctx *remoteWriteCtx) MustStop() {
@@ -501,6 +594,10 @@ func (rwctx *remoteWriteCtx) MustStop() {
 	rwctx.fq.UnblockAllReaders()
 	rwctx.c.MustStop()
 	rwctx.c = nil
+
+	sas := rwctx.sas.Swap(nil)
+	sas.MustStop()
+
 	rwctx.fq.MustClose()
 	rwctx.fq = nil
 
@@ -509,6 +606,7 @@ func (rwctx *remoteWriteCtx) MustStop() {
 }
 
 func (rwctx *remoteWriteCtx) Push(tss []prompbmarshal.TimeSeries) {
+	// Apply relabeling
 	var rctx *relabelCtx
 	var v *[]prompbmarshal.TimeSeries
 	rcs := allRelabelConfigs.Load().(*relabelConfigs)
@@ -526,11 +624,18 @@ func (rwctx *remoteWriteCtx) Push(tss []prompbmarshal.TimeSeries) {
 		rowsCountAfterRelabel := getRowsCount(tss)
 		rwctx.rowsDroppedByRelabel.Add(rowsCountBeforeRelabel - rowsCountAfterRelabel)
 	}
-	pss := rwctx.pss
-	idx := atomic.AddUint64(&rwctx.pssNextIdx, 1) % uint64(len(pss))
 	rowsCount := getRowsCount(tss)
 	rwctx.rowsPushedAfterRelabel.Add(rowsCount)
-	pss[idx].Push(tss)
+
+	// Apply stream aggregation if any
+	sas := rwctx.sas.Load()
+	sas.Push(tss)
+	if sas == nil || rwctx.streamAggrKeepInput {
+		// Push samples to the remote storage
+		rwctx.pushInternal(tss)
+	}
+
+	// Return back relabeling contexts to the pool
 	if rctx != nil {
 		*v = prompbmarshal.ResetTimeSeries(tss)
 		tssRelabelPool.Put(v)
@@ -538,6 +643,42 @@ func (rwctx *remoteWriteCtx) Push(tss []prompbmarshal.TimeSeries) {
 	}
 }
 
+func (rwctx *remoteWriteCtx) pushInternal(tss []prompbmarshal.TimeSeries) {
+	pss := rwctx.pss
+	idx := atomic.AddUint64(&rwctx.pssNextIdx, 1) % uint64(len(pss))
+	pss[idx].Push(tss)
+}
+
+func (rwctx *remoteWriteCtx) reinitStreamAggr() {
+	sas := rwctx.sas.Load()
+	if sas == nil {
+		// There is no stream aggregation for rwctx
+		return
+	}
+
+	sasFile := streamAggrConfig.GetOptionalArg(rwctx.idx)
+	logger.Infof("reloading stream aggregation configs pointed by -remoteWrite.streamAggr.config=%q", sasFile)
+	metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reloads_total{path=%q}`, sasFile)).Inc()
+	dedupInterval := streamAggrDedupInterval.GetOptionalArgOrDefault(rwctx.idx, 0)
+	sasNew, err := streamaggr.LoadFromFile(sasFile, rwctx.pushInternal, dedupInterval)
+	if err != nil {
+		metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reloads_errors_total{path=%q}`, sasFile)).Inc()
+		metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reload_successful{path=%q}`, sasFile)).Set(0)
+		logger.Errorf("cannot reload stream aggregation config from -remoteWrite.streamAggr.config=%q; continue using the previously loaded config; error: %s", sasFile, err)
+		return
+	}
+	if !sasNew.Equal(sas) {
+		sasOld := rwctx.sas.Swap(sasNew)
+		sasOld.MustStop()
+		logger.Infof("successfully reloaded stream aggregation configs at -remoteWrite.streamAggr.config=%q", sasFile)
+	} else {
+		sasNew.MustStop()
+		logger.Infof("the config at -remoteWrite.streamAggr.config=%q wasn't changed", sasFile)
+	}
+	metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reload_successful{path=%q}`, sasFile)).Set(1)
+	metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reload_success_timestamp_seconds{path=%q}`, sasFile)).Set(fasttime.UnixTimestamp())
+}
+
 var tssRelabelPool = &sync.Pool{
 	New: func() interface{} {
 		a := []prompbmarshal.TimeSeries{}
@@ -552,3 +693,20 @@ func getRowsCount(tss []prompbmarshal.TimeSeries) int {
 	}
 	return rowsCount
 }
+
+// CheckStreamAggrConfigs checks configs pointed by -remoteWrite.streamAggr.config
+func CheckStreamAggrConfigs() error {
+	pushNoop := func(tss []prompbmarshal.TimeSeries) {}
+	for idx, sasFile := range *streamAggrConfig {
+		if sasFile == "" {
+			continue
+		}
+		dedupInterval := streamAggrDedupInterval.GetOptionalArgOrDefault(idx, 0)
+		sas, err := streamaggr.LoadFromFile(sasFile, pushNoop, dedupInterval)
+		if err != nil {
+			return fmt.Errorf("cannot load -remoteWrite.streamAggr.config=%q: %w", sasFile, err)
+		}
+		sas.MustStop()
+	}
+	return nil
+}

app/vmagent/vmimport/request_handler.go

@@ -1,7 +1,6 @@
 package vmimport
 
 import (
-	"io"
 	"net/http"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/common"
@@ -12,8 +11,8 @@ import (
 	"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/protoparser/vmimport/stream"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
 	"github.com/VictoriaMetrics/metrics"
 )
 
@@ -31,20 +30,9 @@ func InsertHandler(at *auth.Token, req *http.Request) error {
 	if err != nil {
 		return err
 	}
-	return writeconcurrencylimiter.Do(func() error {
-		isGzipped := req.Header.Get("Content-Encoding") == "gzip"
-		return parser.ParseStream(req.Body, isGzipped, func(rows []parser.Row) error {
-			return insertRows(at, rows, extraLabels)
-		})
-	})
-}
-
-// 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)
-		})
+	isGzipped := req.Header.Get("Content-Encoding") == "gzip"
+	return stream.Parse(req.Body, isGzipped, func(rows []parser.Row) error {
+		return insertRows(at, rows, extraLabels)
 	})
 }
 

app/vmalert/Makefile

@@ -114,6 +114,9 @@ vmalert-linux-arm64:
 vmalert-linux-ppc64le:
 	APP_NAME=vmalert CGO_ENABLED=0 GOOS=linux GOARCH=ppc64le $(MAKE) app-local-goos-goarch
 
+vmalert-linux-s390x:
+	APP_NAME=vmalert CGO_ENABLED=0 GOOS=linux GOARCH=s390x $(MAKE) app-local-goos-goarch
+
 vmalert-linux-386:
 	APP_NAME=vmalert CGO_ENABLED=0 GOOS=linux GOARCH=386 $(MAKE) app-local-goos-goarch
 

app/vmalert/README.md

@@ -9,6 +9,13 @@ protocol and require `-remoteWrite.url` to be configured.
 Vmalert is heavily inspired by [Prometheus](https://prometheus.io/docs/alerting/latest/overview/)
 implementation and aims to be compatible with its syntax.
 
+A [single-node](https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html#vmalert)
+or [cluster version](https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html#vmalert)
+of VictoriaMetrics are capable of proxying requests to vmalert via `-vmalert.proxyURL` command-line flag. 
+Use this feature for the following cases:
+* for proxying requests from [Grafana Alerting UI](https://grafana.com/docs/grafana/latest/alerting/);
+* for accessing vmalert's UI through VictoriaMetrics Web interface.
+
 ## Features
 
 * Integration with [VictoriaMetrics](https://github.com/VictoriaMetrics/VictoriaMetrics) TSDB;
@@ -21,7 +28,8 @@ implementation and aims to be compatible with its syntax.
 * 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 and without extra dependencies.
-* Supports [reusable templates](#reusable-templates) for annotations.
+* Supports [reusable templates](#reusable-templates) for annotations;
+* Load of recording and alerting rules from local filesystem, GCS and S3.
 
 ## Limitations
 
@@ -69,16 +77,17 @@ Then configure `vmalert` accordingly:
     -external.label=replica=a                # Multiple external labels may be set
 ```
 
-Note there's a separate `remoteWrite.url` to allow writing results of
+Note there's a separate `-remoteWrite.url` command-line flag to allow writing results of
 alerting/recording rules into a different storage than the initial data that's
 queried. This allows using `vmalert` to aggregate data from a short-term,
 high-frequency, high-cardinality storage into a long-term storage with
 decreased cardinality and a bigger interval between samples.
+See also [stream aggregation](https://docs.victoriametrics.com/stream-aggregation.html).
 
 See the full list of configuration flags in [configuration](#configuration) section.
 
 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.
+to specify different `-external.label` command-line 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
@@ -191,6 +200,11 @@ expr: <string>
 # Is applicable to alerting rules only.
 [ debug: <bool> | default = false ]
 
+# Defines the number of rule's updates entries stored in memory
+# and available for view on rule's Details page.
+# Overrides `rule.updateEntriesLimit` value for this specific rule.
+[ update_entries_limit: <integer> | default 0 ]
+
 # Labels to add or overwrite for each alert.
 labels:
   [ <labelname>: <tmpl_string> ]
@@ -213,7 +227,8 @@ The following variables are available in templating:
 | $labels or .Labels                 | The list of labels of the current alert. Use as ".Labels.<label_name>".                                   | {% raw %}Too high number of connections for {{ .Labels.instance }}{% endraw %}                                                                                         |
 | $alertID or .AlertID               | The current alert's ID generated by vmalert.                                                              | {% raw %}Link: vmalert/alert?group_id={{.GroupID}}&alert_id={{.AlertID}}{% endraw %}                                                                                   |
 | $groupID or .GroupID               | The current alert's group ID generated by vmalert.                                                        | {% raw %}Link: vmalert/alert?group_id={{.GroupID}}&alert_id={{.AlertID}}{% endraw %}                                                                                   |
-| $expr or .Expr                     | Alert's expression. Can be used for generating links to Grafana or other systems.                         | {% raw %}/api/v1/query?query={{ $expr&#124;queryEscape }}{% endraw %}                                                                                |
+| $expr or .Expr                     | Alert's expression. Can be used for generating links to Grafana or other systems.                         | {% raw %}/api/v1/query?query={{ $expr&#124;queryEscape }}{% endraw %}                                                                                                  |
+| $for or .For                       | Alert's configured for param.                                                                             | {% raw %}Number of connections is too high for more than {{ .For }}{% endraw %}                                                                                        |
 | $externalLabels or .ExternalLabels | List of labels configured via `-external.label` command-line flag.                                        | {% raw %}Issues with {{ $labels.instance }} (datacenter-{{ $externalLabels.dc }}){% endraw %}                                                                          |
 | $externalURL or .ExternalURL       | URL configured via `-external.url` command-line flag. Used for cases when vmalert is hidden behind proxy. | {% raw %}Visit {{ $externalURL }} for more details{% endraw %}                                                                                                         |
 
@@ -318,6 +333,12 @@ expr: <string>
 # Labels to add or overwrite before storing the result.
 labels:
   [ <labelname>: <labelvalue> ]
+
+
+# Defines the number of rule's updates entries stored in memory
+# and available for view on rule's Details page.
+# Overrides `rule.updateEntriesLimit` value for this specific rule.
+[ update_entries_limit: <integer> | default 0 ]
 ```
 
 For recording rules to work `-remoteWrite.url` must be specified.
@@ -384,6 +405,25 @@ The enterprise version of vmalert is available in `vmutils-*-enterprise.tar.gz`
 at [release page](https://github.com/VictoriaMetrics/VictoriaMetrics/releases) and in `*-enterprise`
 tags at [Docker Hub](https://hub.docker.com/r/victoriametrics/vmalert/tags).
 
+### Reading rules from object storage
+
+[Enterprise version](https://docs.victoriametrics.com/enterprise.html) of `vmalert` may read alerting and recording rules
+from object storage:
+
+- `./bin/vmalert -rule=s3://bucket/dir/alert.rules` would read rules from the given path at S3 bucket
+- `./bin/vmalert -rule=gs://bucket/bir/alert.rules` would read rules from the given path at GCS bucket
+
+S3 and GCS paths support only matching by prefix, e.g. `s3://bucket/dir/rule_` matches
+all files with prefix `rule_` in the folder `dir`.
+
+The following [command-line flags](#flags) can be used for fine-tuning access to S3 and GCS:
+
+- `-s3.credsFilePath` - path to file with GCS or S3 credentials. Credentials are loaded from default locations if not set.
+- `-s3.configFilePath` - path to file with S3 configs. Configs are loaded from default location if not set.
+- `-s3.configProfile` - profile name for S3 configs. If no set, the value of the environment variable will be loaded (`AWS_PROFILE` or `AWS_DEFAULT_PROFILE`).
+- `-s3.customEndpoint` - custom S3 endpoint for use with S3-compatible storages (e.g. MinIO). S3 is used if not set.
+- `-s3.forcePathStyle` - prefixing endpoint with bucket name when set false, true by default.
+
 ### Topology examples
 
 The following sections are showing how `vmalert` may be used and configured
@@ -468,7 +508,8 @@ Alertmanager will automatically deduplicate alerts with identical labels, so ens
 all `vmalert`s are having the same config.
 
 Don't forget to configure [cluster mode](https://prometheus.io/docs/alerting/latest/alertmanager/)
-for Alertmanagers for better reliability.
+for Alertmanagers for better reliability. List all Alertmanager URLs in vmalert's `-notifier.url` 
+to ensure [high availability](https://github.com/prometheus/alertmanager#high-availability).
 
 This example uses single-node VM server for the sake of simplicity.
 Check how to replace it with [cluster VictoriaMetrics](#cluster-victoriametrics) if needed.
@@ -501,8 +542,8 @@ groups:
       expr: avg_over_time(http_requests[5m])
 ```
 
-Ability of `vmalert` to be configured with different `datasource.url` and `remoteWrite.url` allows
-reading data from one data source and backfilling results to another. This helps to build a system
+Ability of `vmalert` to be configured with different `-datasource.url` and `-remoteWrite.url` command-line flags
+allows reading data from one data source and backfilling results to another. This helps to build a system
 for aggregating and downsampling the data.
 
 The following example shows how to build a topology where `vmalert` will process data from one cluster
@@ -526,7 +567,7 @@ Please note, [replay](#rules-backfilling) feature may be used for transforming h
 
 Flags `-remoteRead.url` and `-notifier.url` are omitted since we assume only recording rules are used.
 
-See also [downsampling docs](https://docs.victoriametrics.com/#downsampling).
+See also [stream aggregation](https://docs.victoriametrics.com/stream-aggregation.html) and [downsampling](https://docs.victoriametrics.com/#downsampling).
 
 #### Multiple remote writes
 
@@ -580,6 +621,12 @@ can read the same rules configuration as normal, evaluate them on the given time
 results via remote write to the configured storage. vmalert supports any PromQL/MetricsQL compatible
 data source for backfilling.
 
+Please note, that response caching may lead to unexpected results during and after backfilling process.
+In order to avoid this you need to reset cache contents or disable caching when using backfilling
+as described in [backfilling docs](https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html#backfilling).
+
+See a blogpost about [Rules backfilling via vmalert](https://victoriametrics.com/blog/rules-replay/).
+
 ### How it works
 
 In `replay` mode vmalert works as a cli-tool and exits immediately after work is done.
@@ -677,38 +724,49 @@ The default list of alerting rules for these metric can be found [here](https://
 We recommend setting up regular scraping of this page either through `vmagent` or by Prometheus so that the exported
 metrics may be analyzed later.
 
-Use the official [Grafana dashboard](https://grafana.com/grafana/dashboards/14950) for `vmalert` overview. 
+Use the official [Grafana dashboard](https://grafana.com/grafana/dashboards/14950-victoriametrics-vmalert/) for `vmalert` overview. 
 Graphs on this dashboard contain useful hints - hover the `i` icon in the top left corner of each graph in order to read it.
 If you have suggestions for improvements or have found a bug - please open an issue on github or add
 a review to the dashboard.
 
 ## Troubleshooting
 
-vmalert executes configured rules within certain intervals. It is expected that at the moment when rule is executed,
-the data is already present in configured `-datasource.url`:
+### Data delay
+
+Data delay is one of the most common issues with rules execution.
+vmalert executes configured rules within certain intervals at specifics timestamps. 
+It expects that the data is already present in configured `-datasource.url` at the moment of time when rule is executed:
 
 <img alt="vmalert expected evaluation" src="vmalert_ts_normal.gif">
 
 Usually, troubles start to appear when data in `-datasource.url` is delayed or absent. In such cases, evaluations
-may get empty response from datasource and produce empty recording rules or reset alerts state:
+may get empty response from the datasource and produce empty recording rules or reset alerts state:
 
 <img alt="vmalert evaluation when data is delayed" src="vmalert_ts_data_delay.gif">
 
-_By default recently written samples to VictoriaMetrics aren't visible for queries for up to 30s.
-This behavior is controlled by `-search.latencyOffset` command-line flag on vmselect. Usually, this results into
-a 30s shift for recording rules results.
-Note that too small value passed to `-search.latencyOffset` may lead to incomplete query results._
+Try the following recommendations to reduce the chance of hitting the data delay issue:
 
-Try the following recommendations in such cases:
-
-* Always configure group's `evaluationInterval` to be bigger or equal to `scrape_interval` at which metrics
-are delivered to the datasource;
+* Always configure group's `evaluationInterval` to be bigger or at least equal to 
+[time series resolution](https://docs.victoriametrics.com/keyConcepts.html#time-series-resolution);
+* Ensure that `[duration]` value is at least twice bigger than 
+[time series resolution](https://docs.victoriametrics.com/keyConcepts.html#time-series-resolution). For example,
+if expression is `rate(my_metric[2m]) > 0` then ensure that `my_metric` resolution is at least `1m` or better `30s`. 
+If you use VictoriaMetrics as datasource, `[duration]` can be omitted and VictoriaMetrics will adjust it automatically.
 * If you know in advance, that data in datasource is delayed - try changing vmalert's `-datasource.lookback`
-command-line flag to add a time shift for evaluations;
-* If time intervals between datapoints in datasource are irregular or `>=5min` - try changing vmalert's
-`-datasource.queryStep` command-line flag to specify how far search query can lookback for the recent datapoint. 
-The recommendation is to have the step at least two times bigger than `scrape_interval`, since
-there are no guarantees that scrape will not fail.
+command-line flag to add a time shift for evaluations. Or extend `[duration]` to tolerate the delay.
+For example, `max_over_time(errors_total[10m]) > 0` will be active even if there is no data in datasource for last `9m`.
+* If [time series resolution](https://docs.victoriametrics.com/keyConcepts.html#time-series-resolution)
+in datasource is inconsistent or `>=5min` - try changing vmalert's `-datasource.queryStep` command-line flag to specify 
+how far search query can lookback for the recent datapoint. The recommendation is to have the step 
+at least two times bigger than the resolution.
+
+> Please note, data delay is inevitable in distributed systems. And it is better to account for it instead of ignoring.
+
+By default, recently written samples to VictoriaMetrics aren't visible for queries for up to 30s
+(see `-search.latencyOffset` command-line flag at vmselect). Such delay is needed to eliminate risk of incomplete
+data on the moment of querying, since metrics collectors won't be able to deliver the data in time.
+
+### Alerts state
 
 Sometimes, it is not clear why some specific alert fired or didn't fire. It is very important to remember, that
 alerts with `for: 0` fire immediately when their expression becomes true. And alerts with `for > 0` will fire only
@@ -720,8 +778,9 @@ If `-remoteWrite.url` command-line flag is configured, vmalert will persist aler
 [vmui](https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html#vmui) or Grafana to track how alerts state
 changed in time.
 
-vmalert also stores last N state updates for each rule. To check updates, click on `Details` link next to rule's name
-on `/vmalert/groups` page and check the `Last updates` section:
+vmalert stores last `-rule.updateEntriesLimit` (or `update_entries_limit` [per-rule config](https://docs.victoriametrics.com/vmalert.html#alerting-rules)) 
+state updates for each rule. To check updates, click on `Details` link next to rule's name on `/vmalert/groups` page 
+and check the `Last updates` section:
 
 <img alt="vmalert state" src="vmalert_state.png">
 
@@ -730,7 +789,9 @@ HTTP request sent by vmalert to the `-datasource.url` during evaluation. If spec
 no samples returned and curl command returns data - then it is very likely there was no data in datasource on the
 moment when rule was evaluated.
 
-vmalert also alows configuring more detailed logging for specific rule. Just set `debug: true` in rule's configuration
+### Debug mode
+
+vmalert allows configuring more detailed logging for specific alerting rule. Just set `debug: true` in rule's configuration
 and vmalert will start printing additional log messages:
 ```terminal
 2022-09-15T13:35:41.155Z  DEBUG rule "TestGroup":"Conns" (2601299393013563564) at 2022-09-15T15:35:41+02:00: query returned 0 samples (elapsed: 5.896041ms)
@@ -855,7 +916,7 @@ The shortlist of configuration flags is the following:
   -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. Supports templating - see https://docs.victoriametrics.com/vmalert.html#templating . For example, link to Grafana: -external.alert.source='explore?orgId=1&left=["now-1h","now","VictoriaMetrics",{"expr":{{$expr|jsonEscape|queryEscape}} },{"mode":"Metrics"},{"ui":[true,true,true,"none"]}]' . If empty 'vmalert/alert?group_id={{.GroupID}}&alert_id={{.AlertID}}' is used.
+     External Alert Source allows to override the Source link for alerts sent to AlertManager for cases where you want to build a custom link to Grafana, Prometheus or any other service. Supports templating - see https://docs.victoriametrics.com/vmalert.html#templating . For example, link to Grafana: -external.alert.source='explore?orgId=1&left={"datasource":"VictoriaMetrics","queries":[{"expr":{{$expr|jsonEscape|queryEscape}},"refId":"A"}],"range":{"from":"now-1h","to":"now"}}'. Link to VMUI: -external.alert.source='vmui/#/?g0.expr={{.Expr|queryEscape}}'. If empty 'vmalert/alert?group_id={{.GroupID}}&alert_id={{.AlertID}}' is used.
   -external.label array
      Optional label in the form 'Name=value' to add to all generated recording rules and alerts. Pass multiple -label flags in order to add multiple label sets.
      Supports an array of values separated by comma or specified via multiple flags.
@@ -882,13 +943,21 @@ The shortlist of configuration flags is the following:
   -httpAuth.username string
      Username for HTTP Basic Auth. The authentication is disabled if empty. See also -httpAuth.password
   -httpListenAddr string
-     Address to listen for http connections (default ":8880")
+     Address to listen for http connections. See also -httpListenAddr.useProxyProtocol (default ":8880")
+  -httpListenAddr.useProxyProtocol
+     Whether to use proxy protocol for connections accepted at -httpListenAddr . See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt
+  -insert.maxQueueDuration duration
+     The maximum duration to wait in the queue when -maxConcurrentInserts concurrent insert requests are executed (default 1m0s)
+  -internStringMaxLen int
+     The maximum length for strings to intern. Lower limit may save memory at the cost of higher CPU usage. See https://en.wikipedia.org/wiki/String_interning (default 500)
   -loggerDisableTimestamps
      Whether to disable writing timestamps in logs
   -loggerErrorsPerSecondLimit int
      Per-second limit on the number of ERROR messages. If more than the given number of errors are emitted per second, the remaining errors are suppressed. Zero values disable the rate limit
   -loggerFormat string
      Format for logs. Possible values: default, json (default "default")
+  -loggerJSONFields string
+     Allows renaming fields in JSON formatted logs. Example: "ts:timestamp,msg:message" renames "ts" to "timestamp" and "msg" to "message". Supported fields: ts, level, caller, msg
   -loggerLevel string
      Minimum level of errors to log. Possible values: INFO, WARN, ERROR, FATAL, PANIC (default "INFO")
   -loggerOutput string
@@ -897,9 +966,11 @@ The shortlist of configuration flags is the following:
      Timezone to use for timestamps in logs. Timezone must be a valid IANA Time Zone. For example: America/New_York, Europe/Berlin, Etc/GMT+3 or Local (default "UTC")
   -loggerWarnsPerSecondLimit int
      Per-second limit on the number of WARN messages. If more than the given number of warns are emitted per second, then the remaining warns are suppressed. Zero values disable the rate limit
+  -maxConcurrentInserts int
+     The maximum number of concurrent insert requests. Default value should work for most cases, since it minimizes the memory usage. The default value can be increased when clients send data over slow networks. See also -insert.maxQueueDuration (default 8)
   -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)
+     Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB (default 0)
   -memory.allowedPercent float
      Allowed percent of system memory VictoriaMetrics caches may occupy. See also -memory.allowedBytes. Too low a value may increase cache miss rate usually resulting in higher CPU and disk IO usage. Too high a value may evict too much data from OS page cache which will result in higher disk IO usage (default 60)
   -metricsAuthKey string
@@ -954,7 +1025,7 @@ The shortlist of configuration flags is the following:
      Optional TLS server name to use for connections to -notifier.url. By default the server name from -notifier.url is used
      Supports an array of values separated by comma or specified via multiple flags.
   -notifier.url array
-     Prometheus alertmanager URL, e.g. http://127.0.0.1:9093
+     Prometheus Alertmanager URL, e.g. http://127.0.0.1:9093. List all Alertmanager URLs if it runs in the cluster mode to ensure high availability.
      Supports an array of values separated by comma or specified via multiple flags.
   -pprofAuthKey string
      Auth key for /debug/pprof/* endpoints. It must be passed via authKey query arg. It overrides httpAuth.* settings
@@ -991,7 +1062,7 @@ The shortlist of configuration flags is the following:
   -remoteRead.headers string
      Optional HTTP headers to send with each request to the corresponding -remoteRead.url. For example, -remoteRead.headers='My-Auth:foobar' would send 'My-Auth: foobar' HTTP header with every request to the corresponding -remoteRead.url. Multiple headers must be delimited by '^^': -remoteRead.headers='header1:value1^^header2:value2'
   -remoteRead.ignoreRestoreErrors
-     Whether to ignore errors from remote storage when restoring alerts state on startup. (default true)
+     Whether to ignore errors from remote storage when restoring alerts state on startup. DEPRECATED - this flag has no effect and will be removed in the next releases. (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.oauth2.clientID string
@@ -1068,8 +1139,8 @@ The shortlist of configuration flags is the following:
      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, '-remoteWrite.showURL'.
   -replay.disableProgressBar
      Whether to disable rendering progress bars during the replay. Progress bar rendering might be verbose or break the logs parsing, so it is recommended to be disabled when not used in interactive mode.
-  -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.maxDatapointsPerQuery /query_range
+     Max number of data points expected in one request. It affects the max time range for every /query_range request during the replay. 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
@@ -1079,18 +1150,24 @@ The shortlist of configuration flags is the following:
   -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 files with alerting and/or recording rules.
+     Supports hierarchical patterns and regexpes.
      Examples:
       -rule="/path/to/file". Path to a single file with alerting rules
-      -rule="dir/*.yaml" -rule="/*.yaml". Relative path to all .yaml files in "dir" folder,
-     absolute path to all .yaml files in root.
+      -rule="dir/*.yaml" -rule="/*.yaml" -rule="gcs://vmalert-rules/tenant_%{TENANT_ID}/prod". 
      Rule files may contain %{ENV_VAR} placeholders, which are substituted by the corresponding env vars.
+     
+     Enterprise version of vmalert supports S3 and GCS paths to rules.
+     For example: gs://bucket/path/to/rules, s3://bucket/path/to/rules
+     S3 and GCS paths support only matching by prefix, e.g. s3://bucket/dir/rule_ matches
+     all files with prefix rule_ in folder dir.
+     See https://docs.victoriametrics.com/vmalert.html#reading-rules-from-object-storage
+     
      Supports an array of values separated by comma or specified via multiple flags.
   -rule.configCheckInterval duration
      Interval for checking for changes in '-rule' files. By default the checking is disabled. Send SIGHUP signal in order to force config check for changes. DEPRECATED - see '-configCheckInterval' instead
   -rule.maxResolveDuration duration
-     Limits the maximum duration for automatic alert expiration, which is by default equal to 3 evaluation intervals of the parent group.
+     Limits the maximum duration for automatic alert expiration, which by default is 4 times evaluationInterval of the parent group.
   -rule.resendDelay duration
      Minimum amount of time to wait before resending an alert to notifier
   -rule.templates array
@@ -1101,10 +1178,24 @@ The shortlist of configuration flags is the following:
       -rule.templates="dir/*.tpl" -rule.templates="/*.tpl". Relative path to all .tpl files in "dir" folder,
      absolute path to all .tpl files in root.
      Supports an array of values separated by comma or specified via multiple flags.
+  -rule.updateEntriesLimit int
+     Defines the max number of rule's state updates stored in-memory. Rule's updates are available on rule's Details page and are used for debugging purposes. The number of stored updates can be overriden per rule via update_entries_limit param. (default 20)
   -rule.validateExpressions
      Whether to validate rules expressions via MetricsQL engine (default true)
   -rule.validateTemplates
      Whether to validate annotation and label templates (default true)
+  -s3.configFilePath string
+     Path to file with S3 configs. Configs are loaded from default location if not set.
+     See https://docs.aws.amazon.com/general/latest/gr/aws-security-credentials.html . This flag is available only in VictoriaMetrics enterprise. See https://docs.victoriametrics.com/enterprise.html
+  -s3.configProfile string
+     Profile name for S3 configs. If no set, the value of the environment variable will be loaded (AWS_PROFILE or AWS_DEFAULT_PROFILE), or if both not set, DefaultSharedConfigProfile is used. This flag is available only in VictoriaMetrics enterprise. See https://docs.victoriametrics.com/enterprise.html
+  -s3.credsFilePath string
+     Path to file with GCS or S3 credentials. Credentials are loaded from default locations if not set.
+     See https://cloud.google.com/iam/docs/creating-managing-service-account-keys and https://docs.aws.amazon.com/general/latest/gr/aws-security-credentials.html . This flag is available only in VictoriaMetrics enterprise. See https://docs.victoriametrics.com/enterprise.html
+  -s3.customEndpoint string
+     Custom S3 endpoint for use with S3-compatible storages (e.g. MinIO). S3 is used if not set. This flag is available only in VictoriaMetrics enterprise. See https://docs.victoriametrics.com/enterprise.html
+  -s3.forcePathStyle
+     Prefixing endpoint with bucket name when set false, true by default. This flag is available only in VictoriaMetrics enterprise. See https://docs.victoriametrics.com/enterprise.html (default true)
   -tls
      Whether to enable TLS for incoming HTTP requests at -httpListenAddr (aka https). -tlsCertFile and -tlsKeyFile must be set if -tls is set
   -tlsCertFile string
@@ -1184,6 +1275,8 @@ dns_sd_configs:
 ```
 
 The list of configured or discovered Notifiers can be explored via [UI](#Web).
+If Alertmanager runs in cluster mode then all its URLs needs to be available during discovery
+to ensure [high availability](https://github.com/prometheus/alertmanager#high-availability).
 
 The configuration file [specification](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/app/vmalert/notifier/config.go)
 is the following:

app/vmalert/alerting.go

@@ -74,10 +74,15 @@ func newAlertingRule(qb datasource.QuerierBuilder, group *Group, cfg config.Rule
 			Debug:              cfg.Debug,
 		}),
 		alerts:  make(map[uint64]*notifier.Alert),
-		state:   newRuleState(),
 		metrics: &alertingRuleMetrics{},
 	}
 
+	if cfg.UpdateEntriesLimit != nil {
+		ar.state = newRuleState(*cfg.UpdateEntriesLimit)
+	} else {
+		ar.state = newRuleState(*ruleUpdateEntriesLimit)
+	}
+
 	labels := fmt.Sprintf(`alertname=%q, group=%q, id="%d"`, ar.Name, group.Name, ar.ID())
 	ar.metrics.pending = utils.GetOrCreateGauge(fmt.Sprintf(`vmalert_alerts_pending{%s}`, labels),
 		func() float64 {
@@ -416,7 +421,9 @@ func (ar *AlertingRule) UpdateWith(r Rule) error {
 	ar.Labels = nr.Labels
 	ar.Annotations = nr.Annotations
 	ar.EvalInterval = nr.EvalInterval
+	ar.Debug = nr.Debug
 	ar.q = nr.q
+	ar.state = nr.state
 	return nil
 }
 
@@ -456,6 +463,7 @@ func (ar *AlertingRule) newAlert(m datasource.Metric, ls *labelSet, start time.T
 		Value:    m.Values[0],
 		ActiveAt: start,
 		Expr:     ar.Expr,
+		For:      ar.For,
 	}
 	a.Annotations, err = a.ExecTemplate(qFn, ls.origin, ar.Annotations)
 	return a, err
@@ -490,7 +498,9 @@ func (ar *AlertingRule) ToAPI() APIRule {
 		State:          "inactive",
 		Alerts:         ar.AlertsToAPI(),
 		LastSamples:    lastState.samples,
+		MaxUpdates:     ar.state.size(),
 		Updates:        ar.state.getAll(),
+		Debug:          ar.Debug,
 
 		// encode as strings to avoid rounding in JSON
 		ID:      fmt.Sprintf("%d", ar.ID()),
@@ -597,54 +607,59 @@ func alertForToTimeSeries(a *notifier.Alert, timestamp int64) prompbmarshal.Time
 	return newTimeSeries([]float64{float64(a.ActiveAt.Unix())}, []int64{timestamp}, labels)
 }
 
-// Restore restores the state of active alerts basing on previously written time series.
-// Restore restores only ActiveAt field. Field State will be always Pending and supposed
-// to be updated on next Exec, as well as Value field.
-// Only rules with For > 0 will be restored.
-func (ar *AlertingRule) Restore(ctx context.Context, q datasource.Querier, lookback time.Duration, labels map[string]string) error {
-	if q == nil {
-		return fmt.Errorf("querier is nil")
+// Restore restores the value of ActiveAt field for active alerts,
+// based on previously written time series `alertForStateMetricName`.
+// Only rules with For > 0 can be restored.
+func (ar *AlertingRule) Restore(ctx context.Context, q datasource.Querier, ts time.Time, lookback time.Duration) error {
+	if ar.For < 1 {
+		return nil
 	}
 
-	ts := time.Now()
-	qFn := func(query string) ([]datasource.Metric, error) {
-		res, _, err := ar.q.Query(ctx, query, ts)
-		return res, err
+	ar.alertsMu.Lock()
+	defer ar.alertsMu.Unlock()
+
+	if len(ar.alerts) < 1 {
+		return nil
 	}
 
-	// account for external labels in filter
-	var labelsFilter string
-	for k, v := range labels {
-		labelsFilter += fmt.Sprintf(",%s=%q", k, v)
-	}
-
-	expr := fmt.Sprintf("last_over_time(%s{alertname=%q%s}[%ds])",
-		alertForStateMetricName, ar.Name, labelsFilter, int(lookback.Seconds()))
-	qMetrics, _, err := q.Query(ctx, expr, ts)
-	if err != nil {
-		return err
-	}
-
-	for _, m := range qMetrics {
-		ls := &labelSet{
-			origin:    make(map[string]string, len(m.Labels)),
-			processed: make(map[string]string, len(m.Labels)),
+	for _, a := range ar.alerts {
+		if a.Restored || a.State != notifier.StatePending {
+			continue
 		}
-		for _, l := range m.Labels {
-			if l.Name == "__name__" {
-				continue
-			}
-			ls.origin[l.Name] = l.Value
-			ls.processed[l.Name] = l.Value
+
+		var labelsFilter []string
+		for k, v := range a.Labels {
+			labelsFilter = append(labelsFilter, fmt.Sprintf("%s=%q", k, v))
 		}
-		a, err := ar.newAlert(m, ls, time.Unix(int64(m.Values[0]), 0), qFn)
+		sort.Strings(labelsFilter)
+		expr := fmt.Sprintf("last_over_time(%s{%s}[%ds])",
+			alertForStateMetricName, strings.Join(labelsFilter, ","), int(lookback.Seconds()))
+
+		ar.logDebugf(ts, nil, "restoring alert state via query %q", expr)
+
+		qMetrics, _, err := q.Query(ctx, expr, ts)
 		if err != nil {
-			return fmt.Errorf("failed to create alert: %w", err)
+			return err
 		}
-		a.ID = hash(ls.processed)
-		a.State = notifier.StatePending
+
+		if len(qMetrics) < 1 {
+			ar.logDebugf(ts, nil, "no response was received from restore query")
+			continue
+		}
+
+		// only one series expected in response
+		m := qMetrics[0]
+		// __name__ supposed to be alertForStateMetricName
+		m.DelLabel("__name__")
+
+		// we assume that restore query contains all label matchers,
+		// so all received labels will match anyway if their number is equal.
+		if len(m.Labels) != len(a.Labels) {
+			ar.logDebugf(ts, nil, "state restore query returned not expected label-set %v", m.Labels)
+			continue
+		}
+		a.ActiveAt = time.Unix(int64(m.Values[0]), 0)
 		a.Restored = true
-		ar.alerts[a.ID] = a
 		logger.Infof("alert %q (%d) restored to state at %v", a.Name, a.ID, a.ActiveAt)
 	}
 	return nil

app/vmalert/alerting_test.go

@@ -6,12 +6,15 @@ import (
 	"reflect"
 	"sort"
 	"strings"
+	"sync"
 	"testing"
 	"time"
 
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/config"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promutils"
 )
 
 func TestAlertingRule_ToTimeSeries(t *testing.T) {
@@ -502,118 +505,156 @@ func TestAlertingRule_ExecRange(t *testing.T) {
 	}
 }
 
-func TestAlertingRule_Restore(t *testing.T) {
-	testCases := []struct {
-		rule      *AlertingRule
-		metrics   []datasource.Metric
-		expAlerts map[uint64]*notifier.Alert
-	}{
-		{
-			newTestRuleWithLabels("no extra labels"),
-			[]datasource.Metric{
-				metricWithValueAndLabels(t, float64(time.Now().Truncate(time.Hour).Unix()),
-					"__name__", alertForStateMetricName,
-				),
-			},
-			map[uint64]*notifier.Alert{
-				hash(nil): {State: notifier.StatePending,
-					ActiveAt: time.Now().Truncate(time.Hour)},
-			},
-		},
-		{
-			newTestRuleWithLabels("metric labels"),
-			[]datasource.Metric{
-				metricWithValueAndLabels(t, float64(time.Now().Truncate(time.Hour).Unix()),
-					"__name__", alertForStateMetricName,
-					alertNameLabel, "metric labels",
-					alertGroupNameLabel, "groupID",
-					"foo", "bar",
-					"namespace", "baz",
-				),
-			},
-			map[uint64]*notifier.Alert{
-				hash(map[string]string{
-					alertNameLabel:      "metric labels",
-					alertGroupNameLabel: "groupID",
-					"foo":               "bar",
-					"namespace":         "baz",
-				}): {State: notifier.StatePending,
-					ActiveAt: time.Now().Truncate(time.Hour)},
-			},
-		},
-		{
-			newTestRuleWithLabels("rule labels", "source", "vm"),
-			[]datasource.Metric{
-				metricWithValueAndLabels(t, float64(time.Now().Truncate(time.Hour).Unix()),
-					"__name__", alertForStateMetricName,
-					"foo", "bar",
-					"namespace", "baz",
-					// extra labels set by rule
-					"source", "vm",
-				),
-			},
-			map[uint64]*notifier.Alert{
-				hash(map[string]string{
-					"foo":       "bar",
-					"namespace": "baz",
-					"source":    "vm",
-				}): {State: notifier.StatePending,
-					ActiveAt: time.Now().Truncate(time.Hour)},
-			},
-		},
-		{
-			newTestRuleWithLabels("multiple alerts"),
-			[]datasource.Metric{
-				metricWithValueAndLabels(t, float64(time.Now().Truncate(time.Hour).Unix()),
-					"__name__", alertForStateMetricName,
-					"host", "localhost-1",
-				),
-				metricWithValueAndLabels(t, float64(time.Now().Truncate(2*time.Hour).Unix()),
-					"__name__", alertForStateMetricName,
-					"host", "localhost-2",
-				),
-				metricWithValueAndLabels(t, float64(time.Now().Truncate(3*time.Hour).Unix()),
-					"__name__", alertForStateMetricName,
-					"host", "localhost-3",
-				),
-			},
-			map[uint64]*notifier.Alert{
-				hash(map[string]string{"host": "localhost-1"}): {State: notifier.StatePending,
-					ActiveAt: time.Now().Truncate(time.Hour)},
-				hash(map[string]string{"host": "localhost-2"}): {State: notifier.StatePending,
-					ActiveAt: time.Now().Truncate(2 * time.Hour)},
-				hash(map[string]string{"host": "localhost-3"}): {State: notifier.StatePending,
-					ActiveAt: time.Now().Truncate(3 * time.Hour)},
-			},
-		},
+func TestGroup_Restore(t *testing.T) {
+	defaultTS := time.Now()
+	fqr := &fakeQuerierWithRegistry{}
+	fn := func(rules []config.Rule, expAlerts map[uint64]*notifier.Alert) {
+		t.Helper()
+		defer fqr.reset()
+
+		for _, r := range rules {
+			fqr.set(r.Expr, metricWithValueAndLabels(t, 0, "__name__", r.Alert))
+		}
+
+		fg := newGroup(config.Group{Name: "TestRestore", Rules: rules}, fqr, time.Second, nil)
+		wg := sync.WaitGroup{}
+		wg.Add(1)
+		go func() {
+			nts := func() []notifier.Notifier { return []notifier.Notifier{&fakeNotifier{}} }
+			fg.start(context.Background(), nts, nil, fqr)
+			wg.Done()
+		}()
+		fg.close()
+		wg.Wait()
+
+		gotAlerts := make(map[uint64]*notifier.Alert)
+		for _, rs := range fg.Rules {
+			alerts := rs.(*AlertingRule).alerts
+			for k, v := range alerts {
+				if !v.Restored {
+					// set not restored alerts to predictable timestamp
+					v.ActiveAt = defaultTS
+				}
+				gotAlerts[k] = v
+			}
+		}
+
+		if len(gotAlerts) != len(expAlerts) {
+			t.Fatalf("expected %d alerts; got %d", len(expAlerts), len(gotAlerts))
+		}
+		for key, exp := range expAlerts {
+			got, ok := gotAlerts[key]
+			if !ok {
+				t.Fatalf("expected to have key %d", key)
+			}
+			if got.State != notifier.StatePending {
+				t.Fatalf("expected state %d; got %d", notifier.StatePending, got.State)
+			}
+			if got.ActiveAt != exp.ActiveAt {
+				t.Fatalf("expected ActiveAt %v; got %v", exp.ActiveAt, got.ActiveAt)
+			}
+		}
 	}
-	fakeGroup := Group{Name: "TestRule_Exec"}
-	for _, tc := range testCases {
-		t.Run(tc.rule.Name, func(t *testing.T) {
-			fq := &fakeQuerier{}
-			tc.rule.GroupID = fakeGroup.ID()
-			tc.rule.q = fq
-			fq.add(tc.metrics...)
-			if err := tc.rule.Restore(context.TODO(), fq, time.Hour, nil); err != nil {
-				t.Fatalf("unexpected err: %s", err)
-			}
-			if len(tc.rule.alerts) != len(tc.expAlerts) {
-				t.Fatalf("expected %d alerts; got %d", len(tc.expAlerts), len(tc.rule.alerts))
-			}
-			for key, exp := range tc.expAlerts {
-				got, ok := tc.rule.alerts[key]
-				if !ok {
-					t.Fatalf("expected to have key %d", key)
-				}
-				if got.State != exp.State {
-					t.Fatalf("expected state %d; got %d", exp.State, got.State)
-				}
-				if got.ActiveAt != exp.ActiveAt {
-					t.Fatalf("expected ActiveAt %v; got %v", exp.ActiveAt, got.ActiveAt)
-				}
-			}
+
+	stateMetric := func(name string, value time.Time, labels ...string) datasource.Metric {
+		labels = append(labels, "__name__", alertForStateMetricName)
+		labels = append(labels, alertNameLabel, name)
+		labels = append(labels, alertGroupNameLabel, "TestRestore")
+		return metricWithValueAndLabels(t, float64(value.Unix()), labels...)
+	}
+
+	// one active alert, no previous state
+	fn(
+		[]config.Rule{{Alert: "foo", Expr: "foo", For: promutils.NewDuration(time.Second)}},
+		map[uint64]*notifier.Alert{
+			hash(map[string]string{alertNameLabel: "foo", alertGroupNameLabel: "TestRestore"}): {
+				ActiveAt: defaultTS,
+			},
+		})
+	fqr.reset()
+
+	// one active alert with state restore
+	ts := time.Now().Truncate(time.Hour)
+	fqr.set(`last_over_time(ALERTS_FOR_STATE{alertgroup="TestRestore",alertname="foo"}[3600s])`,
+		stateMetric("foo", ts))
+	fn(
+		[]config.Rule{{Alert: "foo", Expr: "foo", For: promutils.NewDuration(time.Second)}},
+		map[uint64]*notifier.Alert{
+			hash(map[string]string{alertNameLabel: "foo", alertGroupNameLabel: "TestRestore"}): {
+				ActiveAt: ts},
+		})
+
+	// two rules, two active alerts, one with state restored
+	ts = time.Now().Truncate(time.Hour)
+	fqr.set(`last_over_time(ALERTS_FOR_STATE{alertgroup="TestRestore",alertname="bar"}[3600s])`,
+		stateMetric("foo", ts))
+	fn(
+		[]config.Rule{
+			{Alert: "foo", Expr: "foo", For: promutils.NewDuration(time.Second)},
+			{Alert: "bar", Expr: "bar", For: promutils.NewDuration(time.Second)},
+		},
+		map[uint64]*notifier.Alert{
+			hash(map[string]string{alertNameLabel: "foo", alertGroupNameLabel: "TestRestore"}): {
+				ActiveAt: defaultTS,
+			},
+			hash(map[string]string{alertNameLabel: "bar", alertGroupNameLabel: "TestRestore"}): {
+				ActiveAt: ts},
+		})
+
+	// two rules, two active alerts, two with state restored
+	ts = time.Now().Truncate(time.Hour)
+	fqr.set(`last_over_time(ALERTS_FOR_STATE{alertgroup="TestRestore",alertname="foo"}[3600s])`,
+		stateMetric("foo", ts))
+	fqr.set(`last_over_time(ALERTS_FOR_STATE{alertgroup="TestRestore",alertname="bar"}[3600s])`,
+		stateMetric("bar", ts))
+	fn(
+		[]config.Rule{
+			{Alert: "foo", Expr: "foo", For: promutils.NewDuration(time.Second)},
+			{Alert: "bar", Expr: "bar", For: promutils.NewDuration(time.Second)},
+		},
+		map[uint64]*notifier.Alert{
+			hash(map[string]string{alertNameLabel: "foo", alertGroupNameLabel: "TestRestore"}): {
+				ActiveAt: ts,
+			},
+			hash(map[string]string{alertNameLabel: "bar", alertGroupNameLabel: "TestRestore"}): {
+				ActiveAt: ts},
+		})
+
+	// one active alert but wrong state restore
+	ts = time.Now().Truncate(time.Hour)
+	fqr.set(`last_over_time(ALERTS_FOR_STATE{alertname="bar",alertgroup="TestRestore"}[3600s])`,
+		stateMetric("wrong alert", ts))
+	fn(
+		[]config.Rule{{Alert: "foo", Expr: "foo", For: promutils.NewDuration(time.Second)}},
+		map[uint64]*notifier.Alert{
+			hash(map[string]string{alertNameLabel: "foo", alertGroupNameLabel: "TestRestore"}): {
+				ActiveAt: defaultTS,
+			},
+		})
+
+	// one active alert with labels
+	ts = time.Now().Truncate(time.Hour)
+	fqr.set(`last_over_time(ALERTS_FOR_STATE{alertgroup="TestRestore",alertname="foo",env="dev"}[3600s])`,
+		stateMetric("foo", ts, "env", "dev"))
+	fn(
+		[]config.Rule{{Alert: "foo", Expr: "foo", Labels: map[string]string{"env": "dev"}, For: promutils.NewDuration(time.Second)}},
+		map[uint64]*notifier.Alert{
+			hash(map[string]string{alertNameLabel: "foo", alertGroupNameLabel: "TestRestore", "env": "dev"}): {
+				ActiveAt: ts,
+			},
+		})
+
+	// one active alert with restore labels missmatch
+	ts = time.Now().Truncate(time.Hour)
+	fqr.set(`last_over_time(ALERTS_FOR_STATE{alertgroup="TestRestore",alertname="foo",env="dev"}[3600s])`,
+		stateMetric("foo", ts, "env", "dev", "team", "foo"))
+	fn(
+		[]config.Rule{{Alert: "foo", Expr: "foo", Labels: map[string]string{"env": "dev"}, For: promutils.NewDuration(time.Second)}},
+		map[uint64]*notifier.Alert{
+			hash(map[string]string{alertNameLabel: "foo", alertGroupNameLabel: "TestRestore", "env": "dev"}): {
+				ActiveAt: defaultTS,
+			},
 		})
-	}
 }
 
 func TestAlertingRule_Exec_Negative(t *testing.T) {
@@ -709,7 +750,6 @@ func TestAlertingRule_Template(t *testing.T) {
 					"summary": `{{ $labels.alertname }}: Too high connection number for "{{ $labels.instance }}"`,
 				},
 				alerts: make(map[uint64]*notifier.Alert),
-				state:  newRuleState(),
 			},
 			[]datasource.Metric{
 				metricWithValueAndLabels(t, 1, "instance", "foo"),
@@ -749,7 +789,6 @@ func TestAlertingRule_Template(t *testing.T) {
 					"description": `{{ $labels.alertname}}: It is {{ $value }} connections for "{{ $labels.instance }}"`,
 				},
 				alerts: make(map[uint64]*notifier.Alert),
-				state:  newRuleState(),
 			},
 			[]datasource.Metric{
 				metricWithValueAndLabels(t, 2, "__name__", "first", "instance", "foo", alertNameLabel, "override"),
@@ -789,7 +828,6 @@ func TestAlertingRule_Template(t *testing.T) {
 					"summary": `Alert "{{ $labels.alertname }}({{ $labels.alertgroup }})" for instance {{ $labels.instance }}`,
 				},
 				alerts: make(map[uint64]*notifier.Alert),
-				state:  newRuleState(),
 			},
 			[]datasource.Metric{
 				metricWithValueAndLabels(t, 1,
@@ -820,6 +858,7 @@ func TestAlertingRule_Template(t *testing.T) {
 			fq := &fakeQuerier{}
 			tc.rule.GroupID = fakeGroup.ID()
 			tc.rule.q = fq
+			tc.rule.state = newRuleState(10)
 			fq.add(tc.metrics...)
 			if _, err := tc.rule.Exec(context.TODO(), time.Now(), 0); err != nil {
 				t.Fatalf("unexpected err: %s", err)
@@ -936,6 +975,6 @@ func newTestAlertingRule(name string, waitFor time.Duration) *AlertingRule {
 		For:          waitFor,
 		EvalInterval: waitFor,
 		alerts:       make(map[uint64]*notifier.Alert),
-		state:        newRuleState(),
+		state:        newRuleState(10),
 	}
 }

app/vmalert/config/config.go

@@ -5,16 +5,14 @@ import (
 	"fmt"
 	"hash/fnv"
 	"net/url"
-	"os"
-	"path/filepath"
 	"sort"
 	"strings"
 
 	"gopkg.in/yaml.v2"
 
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/config/log"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/utils"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/envtemplate"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promutils"
 )
 
@@ -114,6 +112,9 @@ type Rule struct {
 	Labels      map[string]string   `yaml:"labels,omitempty"`
 	Annotations map[string]string   `yaml:"annotations,omitempty"`
 	Debug       bool                `yaml:"debug,omitempty"`
+	// UpdateEntriesLimit defines max number of rule's state updates stored in memory.
+	// Overrides `-rule.updateEntriesLimit`.
+	UpdateEntriesLimit *int `yaml:"update_entries_limit,omitempty"`
 
 	// Catches all undefined fields and must be empty after parsing.
 	XXX map[string]interface{} `yaml:",inline"`
@@ -198,21 +199,45 @@ func (r *Rule) Validate() error {
 // ValidateTplFn must validate the given annotations
 type ValidateTplFn func(annotations map[string]string) error
 
+// cLogger is a logger with support of logs suppressing.
+// it is used when logs emitted by config package needs
+// to be suppressed.
+var cLogger = &log.Logger{}
+
+// ParseSilent parses rule configs from given file patterns without emitting logs
+func ParseSilent(pathPatterns []string, validateTplFn ValidateTplFn, validateExpressions bool) ([]Group, error) {
+	cLogger.Suppress(true)
+	defer cLogger.Suppress(false)
+
+	files, err := readFromFS(pathPatterns)
+	if err != nil {
+		return nil, fmt.Errorf("failed to read from the config: %s", err)
+	}
+	return parse(files, validateTplFn, validateExpressions)
+}
+
 // Parse parses rule configs from given file patterns
 func Parse(pathPatterns []string, validateTplFn ValidateTplFn, validateExpressions bool) ([]Group, error) {
-	var fp []string
-	for _, pattern := range pathPatterns {
-		matches, err := filepath.Glob(pattern)
-		if err != nil {
-			return nil, fmt.Errorf("error reading file pattern %s: %w", pattern, err)
-		}
-		fp = append(fp, matches...)
+	files, err := readFromFS(pathPatterns)
+	if err != nil {
+		return nil, fmt.Errorf("failed to read from the config: %s", err)
 	}
+	groups, err := parse(files, validateTplFn, validateExpressions)
+	if err != nil {
+		return nil, fmt.Errorf("failed to parse %s: %s", pathPatterns, err)
+	}
+	if len(groups) < 1 {
+		cLogger.Warnf("no groups found in %s", strings.Join(pathPatterns, ";"))
+	}
+	return groups, nil
+}
+
+func parse(files map[string][]byte, validateTplFn ValidateTplFn, validateExpressions bool) ([]Group, error) {
 	errGroup := new(utils.ErrGroup)
 	var groups []Group
-	for _, file := range fp {
+	for file, data := range files {
 		uniqueGroups := map[string]struct{}{}
-		gr, err := parseFile(file)
+		gr, err := parseConfig(data)
 		if err != nil {
 			errGroup.Add(fmt.Errorf("failed to parse file %q: %w", file, err))
 			continue
@@ -234,20 +259,19 @@ func Parse(pathPatterns []string, validateTplFn ValidateTplFn, validateExpressio
 	if err := errGroup.Err(); err != nil {
 		return nil, err
 	}
-	if len(groups) < 1 {
-		logger.Warnf("no groups found in %s", strings.Join(pathPatterns, ";"))
-	}
+	sort.SliceStable(groups, func(i, j int) bool {
+		if groups[i].File != groups[j].File {
+			return groups[i].File < groups[j].File
+		}
+		return groups[i].Name < groups[j].Name
+	})
 	return groups, nil
 }
 
-func parseFile(path string) ([]Group, error) {
-	data, err := os.ReadFile(path)
+func parseConfig(data []byte) ([]Group, error) {
+	data, err := envtemplate.ReplaceBytes(data)
 	if err != nil {
-		return nil, fmt.Errorf("error reading alert rule file %q: %w", path, err)
-	}
-	data, err = envtemplate.ReplaceBytes(data)
-	if err != nil {
-		return nil, fmt.Errorf("cannot expand environment vars in %q: %w", path, err)
+		return nil, fmt.Errorf("cannot expand environment vars: %w", err)
 	}
 	g := struct {
 		Groups []Group `yaml:"groups"`

app/vmalert/config/config_test.go

@@ -550,6 +550,20 @@ rules:
   - alert: foo
     expr: sum by(job) (up == 1)
     debug: true
+`)
+	})
+	t.Run("`update_entries_limit` change", func(t *testing.T) {
+		f(t, `
+name: TestGroup
+rules:
+  - alert: foo
+    expr: sum by(job) (up == 1)
+`, `
+name: TestGroup
+rules:
+  - alert: foo
+    expr: sum by(job) (up == 1)
+    update_entries_limit: 33
 `)
 	})
 }

app/vmalert/config/fs.go

@@ -0,0 +1,108 @@
+package config
+
+import (
+	"fmt"
+	"strings"
+	"sync"
+	"time"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/config/fslocal"
+)
+
+// FS represent a file system abstract for reading files.
+type FS interface {
+	// Init initializes FS.
+	Init() error
+
+	// String must return human-readable representation of FS.
+	String() string
+
+	// List returns the list of file names which will be read via Read fn
+	List() ([]string, error)
+
+	// Read returns a list of read files in form of a map
+	// where key is a file name and value is a content of read file.
+	// Read must be called only after the successful Init call.
+	Read(files []string) (map[string][]byte, error)
+}
+
+var (
+	fsRegistryMu sync.Mutex
+	fsRegistry   = make(map[string]FS)
+)
+
+// readFromFS parses the given path list and inits FS for each item.
+// Once inited, readFromFS will try to read and return files from each FS.
+// readFromFS returns an error if at least one FS failed to init.
+// The function can be called multiple times but each unique path
+// will be inited only once.
+//
+// It is allowed to mix different FS types in path list.
+func readFromFS(paths []string) (map[string][]byte, error) {
+	var err error
+	result := make(map[string][]byte)
+	for _, path := range paths {
+
+		fsRegistryMu.Lock()
+		fs, ok := fsRegistry[path]
+		if !ok {
+			fs, err = newFS(path)
+			if err != nil {
+				fsRegistryMu.Unlock()
+				return nil, fmt.Errorf("error while parsing path %q: %w", path, err)
+			}
+			if err := fs.Init(); err != nil {
+				fsRegistryMu.Unlock()
+				return nil, fmt.Errorf("error while initializing path %q: %w", path, err)
+			}
+			fsRegistry[path] = fs
+		}
+		fsRegistryMu.Unlock()
+
+		list, err := fs.List()
+		if err != nil {
+			return nil, fmt.Errorf("failed to list files from %q", fs)
+		}
+
+		cLogger.Infof("found %d files to read from %q", len(list), fs)
+
+		if len(list) < 1 {
+			continue
+		}
+
+		ts := time.Now()
+		files, err := fs.Read(list)
+		if err != nil {
+			return nil, fmt.Errorf("error while reading files from %q: %w", fs, err)
+		}
+		cLogger.Infof("finished reading %d files in %v from %q", len(list), time.Since(ts), fs)
+
+		for k, v := range files {
+			if _, ok := result[k]; ok {
+				return nil, fmt.Errorf("duplicate found for file name %q: file names must be unique", k)
+			}
+			result[k] = v
+		}
+	}
+	return result, nil
+}
+
+// newFS creates FS based on the give path.
+// Supported file systems are: fs
+func newFS(path string) (FS, error) {
+	scheme := "fs"
+	n := strings.Index(path, "://")
+	if n >= 0 {
+		scheme = path[:n]
+		path = path[n+len("://"):]
+	}
+	if len(path) == 0 {
+		return nil, fmt.Errorf("path cannot be empty")
+	}
+	switch scheme {
+	case "fs":
+		return &fslocal.FS{Pattern: path}, nil
+	default:
+		return nil, fmt.Errorf("unsupported scheme %q", scheme)
+	}
+}

app/vmalert/config/fs_test.go

@@ -0,0 +1,39 @@
+package config
+
+import (
+	"strings"
+	"testing"
+)
+
+func TestNewFS(t *testing.T) {
+	f := func(path, expStr string) {
+		t.Helper()
+		fs, err := newFS(path)
+		if err != nil {
+			t.Fatalf("unexpected err: %s", err)
+		}
+		if fs.String() != expStr {
+			t.Fatalf("expected FS %q; got %q", expStr, fs.String())
+		}
+	}
+
+	f("/foo/bar", "Local FS{MatchPattern: \"/foo/bar\"}")
+	f("fs:///foo/bar", "Local FS{MatchPattern: \"/foo/bar\"}")
+}
+
+func TestNewFSNegative(t *testing.T) {
+	f := func(path, expErr string) {
+		t.Helper()
+		_, err := newFS(path)
+		if err == nil {
+			t.Fatalf("expected to have err: %s", expErr)
+		}
+		if !strings.Contains(err.Error(), expErr) {
+			t.Fatalf("expected to have err %q; got %q instead", expErr, err)
+		}
+	}
+
+	f("", "path cannot be empty")
+	f("fs://", "path cannot be empty")
+	f("foobar://baz", `unsupported scheme "foobar"`)
+}

app/vmalert/config/fslocal/fslocal.go

@@ -0,0 +1,49 @@
+package fslocal
+
+import (
+	"fmt"
+	"os"
+	"path/filepath"
+)
+
+// FS represents a local file system
+type FS struct {
+	// Pattern is used for matching one or multiple files.
+	// The pattern may describe hierarchical names such as
+	// /usr/*/bin/ed (assuming the Separator is '/').
+	Pattern string
+}
+
+// Init verifies that configured Pattern is correct
+func (fs *FS) Init() error {
+	_, err := filepath.Glob(fs.Pattern)
+	return err
+}
+
+// String implements Stringer interface
+func (fs *FS) String() string {
+	return fmt.Sprintf("Local FS{MatchPattern: %q}", fs.Pattern)
+}
+
+// List returns the list of file names which will be read via Read fn
+func (fs *FS) List() ([]string, error) {
+	matches, err := filepath.Glob(fs.Pattern)
+	if err != nil {
+		return nil, fmt.Errorf("error while matching files via pattern %s: %w", fs.Pattern, err)
+	}
+	return matches, nil
+}
+
+// Read returns a map of read files where
+// key is the file name and value is file's content.
+func (fs *FS) Read(files []string) (map[string][]byte, error) {
+	result := make(map[string][]byte)
+	for _, path := range files {
+		data, err := os.ReadFile(path)
+		if err != nil {
+			return nil, fmt.Errorf("error while reading file %q: %w", path, err)
+		}
+		result[path] = data
+	}
+	return result, nil
+}

app/vmalert/config/log/logger.go

@@ -0,0 +1,59 @@
+package log
+
+import (
+	"sync"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
+)
+
+// Logger is using lib/logger for logging
+// but can be suppressed via Suppress method
+type Logger struct {
+	mu       sync.RWMutex
+	disabled bool
+}
+
+// Suppress whether to ignore message logging.
+// Once suppressed, logging continues to be ignored
+// until logger is un-suppressed.
+func (l *Logger) Suppress(v bool) {
+	l.mu.Lock()
+	l.disabled = v
+	l.mu.Unlock()
+}
+
+func (l *Logger) isDisabled() bool {
+	l.mu.RLock()
+	defer l.mu.RUnlock()
+	return l.disabled
+}
+
+// Errorf logs error message.
+func (l *Logger) Errorf(format string, args ...interface{}) {
+	if l.isDisabled() {
+		return
+	}
+	logger.Errorf(format, args...)
+}
+
+// Warnf logs warning message.
+func (l *Logger) Warnf(format string, args ...interface{}) {
+	if l.isDisabled() {
+		return
+	}
+	logger.Warnf(format, args...)
+}
+
+// Infof logs info message.
+func (l *Logger) Infof(format string, args ...interface{}) {
+	if l.isDisabled() {
+		return
+	}
+	logger.Infof(format, args...)
+}
+
+// Panicf logs panic message and panics.
+// Panicf can't be suppressed
+func (l *Logger) Panicf(format string, args ...interface{}) {
+	logger.Panicf(format, args...)
+}

app/vmalert/config/log/logger_test.go

@@ -0,0 +1,54 @@
+package log
+
+import (
+	"bytes"
+	"fmt"
+	"strings"
+	"testing"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
+)
+
+func TestOutput(t *testing.T) {
+	testOutput := &bytes.Buffer{}
+	logger.SetOutputForTests(testOutput)
+	defer logger.ResetOutputForTest()
+
+	log := &Logger{}
+
+	mustMatch := func(exp string) {
+		t.Helper()
+		if exp == "" {
+			if testOutput.String() != "" {
+				t.Errorf("expected output to be empty; got %q", testOutput.String())
+				return
+			}
+		}
+		if !strings.Contains(testOutput.String(), exp) {
+			t.Errorf("output %q should contain %q", testOutput.String(), exp)
+		}
+		fmt.Println(testOutput.String())
+		testOutput.Reset()
+	}
+
+	log.Warnf("foo")
+	mustMatch("foo")
+
+	log.Infof("info %d", 2)
+	mustMatch("info 2")
+
+	log.Errorf("error %s %d", "baz", 5)
+	mustMatch("error baz 5")
+
+	log.Suppress(true)
+
+	log.Warnf("foo")
+	mustMatch("")
+
+	log.Infof("info %d", 2)
+	mustMatch("")
+
+	log.Errorf("error %q %d", "baz", 5)
+	mustMatch("")
+
+}

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

@@ -12,6 +12,7 @@ groups:
         expr: vm_tcplistener_conns > 0
         for: 3m
         debug: true
+        update_entries_limit: 40
         annotations:
           labels: "Available labels: {{ $labels }}"
           summary: Too high connection number for {{ $labels.instance }}
@@ -20,6 +21,7 @@ groups:
             {{ end }}
           description: "It is {{ $value }} connections for {{$labels.instance}}"
       - alert: ExampleAlertAlwaysFiring
+        update_entries_limit: -1
         expr: sum by(job)
           (up == 1)
         labels:

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

@@ -7,6 +7,7 @@ groups:
       - alert: Conns
         expr: filterSeries(sumSeries(host.receiver.interface.cons),'last','>', 500)
         for: 3m
+
         annotations:
           summary: Too high connection number for {{$labels.instance}}
           description: "It is {{ $value }} connections for {{$labels.instance}}"

app/vmalert/datasource/datasource.go

@@ -72,6 +72,15 @@ func (m *Metric) AddLabel(key, value string) {
 	m.Labels = append(m.Labels, Label{Name: key, Value: value})
 }
 
+// DelLabel deletes the given label from the label set
+func (m *Metric) DelLabel(key string) {
+	for i, l := range m.Labels {
+		if l.Name == key {
+			m.Labels = append(m.Labels[:i], m.Labels[i+1:]...)
+		}
+	}
+}
+
 // Label returns the given label value.
 // If label is missing empty string will be returned
 func (m *Metric) Label(key string) string {

app/vmalert/datasource/vm.go

@@ -174,7 +174,7 @@ func (s *VMStorage) do(ctx context.Context, req *http.Request) (*http.Response,
 }
 
 func (s *VMStorage) newRequestPOST() (*http.Request, error) {
-	req, err := http.NewRequest("POST", s.datasourceURL, nil)
+	req, err := http.NewRequest(http.MethodPost, s.datasourceURL, nil)
 	if err != nil {
 		return nil, err
 	}

app/vmalert/group.go

@@ -2,6 +2,7 @@ package main
 
 import (
 	"context"
+	"errors"
 	"fmt"
 	"hash/fnv"
 	"net/url"
@@ -44,6 +45,9 @@ type Group struct {
 	// channel accepts new Group obj
 	// which supposed to update current group
 	updateCh chan *Group
+	// evalCancel stores the cancel fn for interrupting
+	// rules evaluation. Used on groups update() and close().
+	evalCancel context.CancelFunc
 
 	metrics *groupMetrics
 }
@@ -158,23 +162,23 @@ func (g *Group) ID() uint64 {
 }
 
 // Restore restores alerts state for group rules
-func (g *Group) Restore(ctx context.Context, qb datasource.QuerierBuilder, lookback time.Duration, labels map[string]string) error {
-	labels = mergeLabels(g.Name, "", labels, g.Labels)
+func (g *Group) Restore(ctx context.Context, qb datasource.QuerierBuilder, ts time.Time, lookback time.Duration) error {
 	for _, rule := range g.Rules {
-		rr, ok := rule.(*AlertingRule)
+		ar, ok := rule.(*AlertingRule)
 		if !ok {
 			continue
 		}
-		if rr.For < 1 {
+		if ar.For < 1 {
 			continue
 		}
-		// ignore QueryParams on purpose, because they could contain
-		// query filters. This may affect the restore procedure.
 		q := qb.BuildWithParams(datasource.QuerierParams{
-			DataSourceType: g.Type.String(),
-			Headers:        g.Headers,
+			DataSourceType:     g.Type.String(),
+			EvaluationInterval: g.Interval,
+			QueryParams:        g.Params,
+			Headers:            g.Headers,
+			Debug:              ar.Debug,
 		})
-		if err := rr.Restore(ctx, q, lookback, labels); err != nil {
+		if err := ar.Restore(ctx, q, ts, lookback); err != nil {
 			return fmt.Errorf("error while restoring rule %q: %w", rule, err)
 		}
 	}
@@ -233,11 +237,24 @@ func (g *Group) updateWith(newGroup *Group) error {
 	return nil
 }
 
+// interruptEval interrupts in-flight rules evaluations
+// within the group. It is expected that g.evalCancel
+// will be repopulated after the call.
+func (g *Group) interruptEval() {
+	g.mu.RLock()
+	defer g.mu.RUnlock()
+
+	if g.evalCancel != nil {
+		g.evalCancel()
+	}
+}
+
 func (g *Group) close() {
 	if g.doneCh == nil {
 		return
 	}
 	close(g.doneCh)
+	g.interruptEval()
 	<-g.finishedCh
 
 	g.metrics.iterationDuration.Unregister()
@@ -251,14 +268,9 @@ func (g *Group) close() {
 
 var skipRandSleepOnGroupStart bool
 
-func (g *Group) start(ctx context.Context, nts func() []notifier.Notifier, rw *remotewrite.Client) {
+func (g *Group) start(ctx context.Context, nts func() []notifier.Notifier, rw *remotewrite.Client, rr datasource.QuerierBuilder) {
 	defer func() { close(g.finishedCh) }()
 
-	e := &executor{
-		rw:                       rw,
-		notifiers:                nts,
-		previouslySentSeriesToRW: make(map[uint64]map[string][]prompbmarshal.Label)}
-
 	// Spread group rules evaluation over time in order to reduce load on VictoriaMetrics.
 	if !skipRandSleepOnGroupStart {
 		randSleep := uint64(float64(g.Interval) * (float64(g.ID()) / (1 << 64)))
@@ -279,11 +291,16 @@ func (g *Group) start(ctx context.Context, nts func() []notifier.Notifier, rw *r
 		}
 	}
 
+	e := &executor{
+		rw:                       rw,
+		notifiers:                nts,
+		previouslySentSeriesToRW: make(map[uint64]map[string][]prompbmarshal.Label)}
+
 	evalTS := time.Now()
 
 	logger.Infof("group %q started; interval=%v; concurrency=%d", g.Name, g.Interval, g.Concurrency)
 
-	eval := func(ts time.Time) {
+	eval := func(ctx context.Context, ts time.Time) {
 		g.metrics.iterationTotal.Inc()
 
 		start := time.Now()
@@ -305,10 +322,26 @@ func (g *Group) start(ctx context.Context, nts func() []notifier.Notifier, rw *r
 		g.LastEvaluation = start
 	}
 
-	eval(evalTS)
+	evalCtx, cancel := context.WithCancel(ctx)
+	g.mu.Lock()
+	g.evalCancel = cancel
+	g.mu.Unlock()
+	defer g.evalCancel()
+
+	eval(evalCtx, evalTS)
 
 	t := time.NewTicker(g.Interval)
 	defer t.Stop()
+
+	// restore the rules state after the first evaluation
+	// so only active alerts can be restored.
+	if rr != nil {
+		err := g.Restore(ctx, rr, evalTS, *remoteReadLookBack)
+		if err != nil {
+			logger.Errorf("error while restoring ruleState for group %q: %s", g.Name, err)
+		}
+	}
+
 	for {
 		select {
 		case <-ctx.Done():
@@ -319,6 +352,14 @@ func (g *Group) start(ctx context.Context, nts func() []notifier.Notifier, rw *r
 			return
 		case ng := <-g.updateCh:
 			g.mu.Lock()
+
+			// it is expected that g.evalCancel will be evoked
+			// somewhere else to unblock group from the rules evaluation.
+			// we recreate the evalCtx and g.evalCancel, so it can
+			// be called again.
+			evalCtx, cancel = context.WithCancel(ctx)
+			g.evalCancel = cancel
+
 			err := g.updateWith(ng)
 			if err != nil {
 				logger.Errorf("group %q: failed to update: %s", g.Name, err)
@@ -343,7 +384,7 @@ func (g *Group) start(ctx context.Context, nts func() []notifier.Notifier, rw *r
 			}
 			evalTS = evalTS.Add((missed + 1) * g.Interval)
 
-			eval(evalTS)
+			eval(evalCtx, evalTS)
 		}
 	}
 }
@@ -417,6 +458,11 @@ func (e *executor) exec(ctx context.Context, rule Rule, ts time.Time, resolveDur
 
 	tss, err := rule.Exec(ctx, ts, limit)
 	if err != nil {
+		if errors.Is(err, context.Canceled) {
+			// the context can be cancelled on graceful shutdown
+			// or on group update. So no need to handle the error as usual.
+			return nil
+		}
 		execErrors.Inc()
 		return fmt.Errorf("rule %q: failed to execute: %w", rule, err)
 	}

app/vmalert/group_test.go

@@ -209,7 +209,7 @@ func TestGroupStart(t *testing.T) {
 	fs.add(m1)
 	fs.add(m2)
 	go func() {
-		g.start(context.Background(), func() []notifier.Notifier { return []notifier.Notifier{fn} }, nil)
+		g.start(context.Background(), func() []notifier.Notifier { return []notifier.Notifier{fn} }, nil, fs)
 		close(finished)
 	}()
 
@@ -460,7 +460,7 @@ func TestFaultyRW(t *testing.T) {
 
 	r := &RecordingRule{
 		Name:  "test",
-		state: newRuleState(),
+		state: newRuleState(10),
 		q:     fq,
 	}
 
@@ -474,3 +474,31 @@ func TestFaultyRW(t *testing.T) {
 		t.Fatalf("expected to get an error from faulty RW client, got nil instead")
 	}
 }
+
+func TestCloseWithEvalInterruption(t *testing.T) {
+	groups, err := config.Parse([]string{"config/testdata/rules/rules1-good.rules"}, notifier.ValidateTemplates, true)
+	if err != nil {
+		t.Fatalf("failed to parse rules: %s", err)
+	}
+
+	const delay = time.Second * 2
+	fq := &fakeQuerierWithDelay{delay: delay}
+
+	const evalInterval = time.Millisecond
+	g := newGroup(groups[0], fq, evalInterval, nil)
+
+	go g.start(context.Background(), nil, nil, nil)
+
+	time.Sleep(evalInterval * 20)
+
+	go func() {
+		g.close()
+	}()
+
+	deadline := time.Tick(delay / 2)
+	select {
+	case <-deadline:
+		t.Fatalf("deadline for close exceeded")
+	case <-g.finishedCh:
+	}
+}

app/vmalert/helpers_test.go

@@ -61,6 +61,67 @@ func (fq *fakeQuerier) Query(_ context.Context, _ string, _ time.Time) ([]dataso
 	return cp, req, nil
 }
 
+type fakeQuerierWithRegistry struct {
+	sync.Mutex
+	registry map[string][]datasource.Metric
+}
+
+func (fqr *fakeQuerierWithRegistry) set(key string, metrics ...datasource.Metric) {
+	fqr.Lock()
+	if fqr.registry == nil {
+		fqr.registry = make(map[string][]datasource.Metric)
+	}
+	fqr.registry[key] = metrics
+	fqr.Unlock()
+}
+
+func (fqr *fakeQuerierWithRegistry) reset() {
+	fqr.Lock()
+	fqr.registry = nil
+	fqr.Unlock()
+}
+
+func (fqr *fakeQuerierWithRegistry) BuildWithParams(_ datasource.QuerierParams) datasource.Querier {
+	return fqr
+}
+
+func (fqr *fakeQuerierWithRegistry) QueryRange(ctx context.Context, q string, _, _ time.Time) ([]datasource.Metric, error) {
+	req, _, err := fqr.Query(ctx, q, time.Now())
+	return req, err
+}
+
+func (fqr *fakeQuerierWithRegistry) Query(_ context.Context, expr string, _ time.Time) ([]datasource.Metric, *http.Request, error) {
+	fqr.Lock()
+	defer fqr.Unlock()
+
+	req, _ := http.NewRequest(http.MethodPost, "foo.com", nil)
+	metrics, ok := fqr.registry[expr]
+	if !ok {
+		return nil, req, nil
+	}
+	cp := make([]datasource.Metric, len(metrics))
+	copy(cp, metrics)
+	return cp, req, nil
+}
+
+type fakeQuerierWithDelay struct {
+	fakeQuerier
+	delay time.Duration
+}
+
+func (fqd *fakeQuerierWithDelay) Query(ctx context.Context, expr string, ts time.Time) ([]datasource.Metric, *http.Request, error) {
+	timer := time.NewTimer(fqd.delay)
+	select {
+	case <-ctx.Done():
+	case <-timer.C:
+	}
+	return fqd.fakeQuerier.Query(ctx, expr, ts)
+}
+
+func (fqd *fakeQuerierWithDelay) BuildWithParams(_ datasource.QuerierParams) datasource.Querier {
+	return fqd
+}
+
 type fakeNotifier struct {
 	sync.Mutex
 	alerts []notifier.Alert

app/vmalert/main.go

@@ -28,13 +28,19 @@ import (
 )
 
 var (
-	rulePath = flagutil.NewArrayString("rule", `Path to the file with alert rules.
-Supports patterns. Flag can be specified multiple times.
+	rulePath = flagutil.NewArrayString("rule", `Path to the files with alerting and/or recording rules.
+Supports hierarchical patterns and regexpes.
 Examples:
  -rule="/path/to/file". Path to a single file with alerting rules
- -rule="dir/*.yaml" -rule="/*.yaml". Relative path to all .yaml files in "dir" folder,
-absolute path to all .yaml files in root.
-Rule files may contain %{ENV_VAR} placeholders, which are substituted by the corresponding env vars.`)
+ -rule="dir/*.yaml" -rule="/*.yaml" -rule="gcs://vmalert-rules/tenant_%{TENANT_ID}/prod". 
+Rule files may contain %{ENV_VAR} placeholders, which are substituted by the corresponding env vars.
+
+Enterprise version of vmalert supports S3 and GCS paths to rules.
+For example: gs://bucket/path/to/rules, s3://bucket/path/to/rules
+S3 and GCS paths support only matching by prefix, e.g. s3://bucket/dir/rule_ matches
+all files with prefix rule_ in folder dir.
+See https://docs.victoriametrics.com/vmalert.html#reading-rules-from-object-storage
+`)
 
 	ruleTemplatesPath = flagutil.NewArrayString("rule.templates", `Path or glob pattern to location with go template definitions
 	for rules annotations templating. Flag can be specified multiple times.
@@ -49,27 +55,33 @@ absolute path to all .tpl files in root.`)
 	configCheckInterval = flag.Duration("configCheckInterval", 0, "Interval for checking for changes in '-rule' or '-notifier.config' files. "+
 		"By default the checking is disabled. Send SIGHUP signal in order to force config check for changes.")
 
-	httpListenAddr     = flag.String("httpListenAddr", ":8880", "Address to listen for http connections")
+	httpListenAddr   = flag.String("httpListenAddr", ":8880", "Address to listen for http connections. See also -httpListenAddr.useProxyProtocol")
+	useProxyProtocol = flag.Bool("httpListenAddr.useProxyProtocol", false, "Whether to use proxy protocol for connections accepted at -httpListenAddr . "+
+		"See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt . "+
+		"With enabled proxy protocol http server cannot serve regular /metrics endpoint. Use -pushmetrics.url for metrics pushing")
 	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.")
-	resendDelay = flag.Duration("rule.resendDelay", 0, "Minimum amount of time to wait before resending an alert to notifier")
+		"which by default is 4 times evaluationInterval of the parent group.")
+	resendDelay            = flag.Duration("rule.resendDelay", 0, "Minimum amount of time to wait before resending an alert to notifier")
+	ruleUpdateEntriesLimit = flag.Int("rule.updateEntriesLimit", 20, "Defines the max number of rule's state updates stored in-memory. "+
+		"Rule's updates are available on rule's Details page and are used for debugging purposes. The number of stored updates can be overriden per rule via update_entries_limit param.")
 
 	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. `+
 		`Supports templating - see https://docs.victoriametrics.com/vmalert.html#templating . `+
-		`For example, link to Grafana: -external.alert.source='explore?orgId=1&left=["now-1h","now","VictoriaMetrics",{"expr":{{$expr|jsonEscape|queryEscape}} },{"mode":"Metrics"},{"ui":[true,true,true,"none"]}]' . `+
+		`For example, link to Grafana: -external.alert.source='explore?orgId=1&left={"datasource":"VictoriaMetrics","queries":[{"expr":{{$expr|jsonEscape|queryEscape}},"refId":"A"}],"range":{"from":"now-1h","to":"now"}}'. `+
+		`Link to VMUI: -external.alert.source='vmui/#/?g0.expr={{.Expr|queryEscape}}'. `+
 		`If empty 'vmalert/alert?group_id={{.GroupID}}&alert_id={{.AlertID}}' is used.`)
 	externalLabels = flagutil.NewArrayString("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.")
+	remoteReadIgnoreRestoreErrors = flag.Bool("remoteRead.ignoreRestoreErrors", true, "Whether to ignore errors from remote storage when restoring alerts state on startup. DEPRECATED - this flag has no effect and will be removed in the next releases.")
 
 	disableAlertGroupLabel = flag.Bool("disableAlertgroupLabel", false, "Whether to disable adding group's Name as label to generated alerts and time series.")
 
@@ -90,6 +102,10 @@ func main() {
 	logger.Init()
 	pushmetrics.Init()
 
+	if !*remoteReadIgnoreRestoreErrors {
+		logger.Warnf("flag `remoteRead.ignoreRestoreErrors` is deprecated and will be removed in next releases.")
+	}
+
 	err := templates.Load(*ruleTemplatesPath, true)
 	if err != nil {
 		logger.Fatalf("failed to parse %q: %s", *ruleTemplatesPath, err)
@@ -168,7 +184,7 @@ func main() {
 	go configReload(ctx, manager, groupsCfg, sighupCh)
 
 	rh := &requestHandler{m: manager}
-	go httpserver.Serve(*httpListenAddr, rh.handler)
+	go httpserver.Serve(*httpListenAddr, *useProxyProtocol, rh.handler)
 
 	sig := procutil.WaitForSigterm()
 	logger.Infof("service received signal %s", sig)
@@ -304,6 +320,7 @@ func configReload(ctx context.Context, m *manager, groupsCfg []config.Group, sig
 	// init reload metrics with positive values to improve alerting conditions
 	configSuccess.Set(1)
 	configTimestamp.Set(fasttime.UnixTimestamp())
+	parseFn := config.Parse
 	for {
 		select {
 		case <-ctx.Done():
@@ -315,7 +332,11 @@ func configReload(ctx context.Context, m *manager, groupsCfg []config.Group, sig
 			}
 			logger.Infof("SIGHUP received. Going to reload rules %q %s...", *rulePath, tmplMsg)
 			configReloads.Inc()
+			// allow logs emitting during manual config reload
+			parseFn = config.Parse
 		case <-configCheckCh:
+			// disable logs emitting during per-interval config reload
+			parseFn = config.ParseSilent
 		}
 		if err := notifier.Reload(); err != nil {
 			configReloadErrors.Inc()
@@ -330,7 +351,7 @@ func configReload(ctx context.Context, m *manager, groupsCfg []config.Group, sig
 			logger.Errorf("failed to load new templates: %s", err)
 			continue
 		}
-		newGroupsCfg, err := config.Parse(*rulePath, validateTplFn, *validateExpressions)
+		newGroupsCfg, err := parseFn(*rulePath, validateTplFn, *validateExpressions)
 		if err != nil {
 			configReloadErrors.Inc()
 			configSuccess.Set(0)

app/vmalert/manager.go

@@ -82,24 +82,18 @@ func (m *manager) close() {
 	m.wg.Wait()
 }
 
-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 ruleState for group %q: %w", group.Name, err)
-			}
-			logger.Errorf("error while restoring ruleState for group %q: %s", group.Name, err)
-		}
-	}
-
+func (m *manager) startGroup(ctx context.Context, g *Group, restore bool) error {
 	m.wg.Add(1)
-	id := group.ID()
+	id := g.ID()
 	go func() {
-		group.start(ctx, m.notifiers, m.rw)
-		m.wg.Done()
+		defer m.wg.Done()
+		if restore {
+			g.start(ctx, m.notifiers, m.rw, m.rr)
+		} else {
+			g.start(ctx, m.notifiers, m.rw, nil)
+		}
 	}()
-	m.groups[id] = group
+	m.groups[id] = g
 	return nil
 }
 
@@ -153,6 +147,7 @@ func (m *manager) update(ctx context.Context, groupsCfg []config.Group, restore
 	}
 	for _, ng := range groupsRegistry {
 		if err := m.startGroup(ctx, ng, restore); err != nil {
+			m.groupsMu.Unlock()
 			return err
 		}
 	}
@@ -166,6 +161,7 @@ func (m *manager) update(ctx context.Context, groupsCfg []config.Group, restore
 				old.updateCh <- new
 				wg.Done()
 			}(item.old, item.new)
+			item.old.interruptEval()
 		}
 		wg.Wait()
 	}

app/vmalert/manager_test.go

@@ -64,17 +64,18 @@ func TestManagerUpdateConcurrent(t *testing.T) {
 	wg := sync.WaitGroup{}
 	wg.Add(workers)
 	for i := 0; i < workers; i++ {
-		go func() {
+		go func(n int) {
 			defer wg.Done()
+			r := rand.New(rand.NewSource(int64(n)))
 			for i := 0; i < iterations; i++ {
-				rnd := rand.Intn(len(paths))
+				rnd := r.Intn(len(paths))
 				cfg, err := config.Parse([]string{paths[rnd]}, notifier.ValidateTemplates, true)
 				if err != nil { // update can fail and this is expected
 					continue
 				}
 				_ = m.update(context.Background(), cfg, false)
 			}
-		}()
+		}(i)
 	}
 	wg.Wait()
 }

app/vmalert/multiarch/Dockerfile

@@ -2,7 +2,7 @@
 ARG certs_image
 ARG root_image
 FROM $certs_image as certs
-RUN apk --update --no-cache add ca-certificates
+RUN apk update && apk upgrade && 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

app/vmalert/notifier/alert.go

@@ -41,10 +41,12 @@ type Alert struct {
 	LastSent time.Time
 	// Value stores the value returned from evaluating expression from Expr field
 	Value float64
-	// ID is the unique identifer for the Alert
+	// ID is the unique identifier for the Alert
 	ID uint64
 	// Restored is true if Alert was restored after restart
 	Restored bool
+	// For defines for how long Alert needs to be active to become StateFiring
+	For time.Duration
 }
 
 // AlertState type indicates the Alert state
@@ -80,6 +82,7 @@ type AlertTplData struct {
 	AlertID  uint64
 	GroupID  uint64
 	ActiveAt time.Time
+	For      time.Duration
 }
 
 var tplHeaders = []string{
@@ -91,6 +94,7 @@ var tplHeaders = []string{
 	"{{ $alertID := .AlertID }}",
 	"{{ $groupID := .GroupID }}",
 	"{{ $activeAt := .ActiveAt }}",
+	"{{ $for := .For }}",
 }
 
 // ExecTemplate executes the Alert template for given
@@ -98,12 +102,16 @@ var tplHeaders = []string{
 // Every alert could have a different datasource, so function
 // requires a queryFunction as an argument.
 func (a *Alert) ExecTemplate(q templates.QueryFn, labels, annotations map[string]string) (map[string]string, error) {
-	tplData := AlertTplData{Value: a.Value, Labels: labels, Expr: a.Expr, AlertID: a.ID, GroupID: a.GroupID, ActiveAt: a.ActiveAt}
-	tmpl, err := templates.GetWithFuncs(templates.FuncsWithQuery(q))
-	if err != nil {
-		return nil, fmt.Errorf("error getting a template: %w", err)
+	tplData := AlertTplData{
+		Value:    a.Value,
+		Labels:   labels,
+		Expr:     a.Expr,
+		AlertID:  a.ID,
+		GroupID:  a.GroupID,
+		ActiveAt: a.ActiveAt,
+		For:      a.For,
 	}
-	return templateAnnotations(annotations, tplData, tmpl, true)
+	return ExecTemplate(q, annotations, tplData)
 }
 
 // ExecTemplate executes the given template for given annotations map.
@@ -162,6 +170,8 @@ func templateAnnotation(dst io.Writer, text string, data tplData, tmpl *textTpl.
 	if err != nil {
 		return fmt.Errorf("error cloning template before parse annotation: %w", err)
 	}
+	// Clone() doesn't copy tpl Options, so we set them manually
+	tpl = tpl.Option("missingkey=zero")
 	tpl, err = tpl.Parse(text)
 	if err != nil {
 		return fmt.Errorf("error parsing annotation template: %w", err)

app/vmalert/notifier/alert_test.go

@@ -54,14 +54,15 @@ func TestAlert_ExecTemplate(t *testing.T) {
 					"job":      "staging",
 					"instance": "localhost",
 				},
+				For: 5 * time.Minute,
 			},
 			annotations: map[string]string{
 				"summary":     "Too high connection number for {{$labels.instance}} for job {{$labels.job}}",
-				"description": "It is {{ $value }} connections for {{$labels.instance}}",
+				"description": "It is {{ $value }} connections for {{$labels.instance}} for more than {{ .For }}",
 			},
 			expTpl: map[string]string{
 				"summary":     "Too high connection number for localhost for job staging",
-				"description": "It is 10000 connections for localhost",
+				"description": "It is 10000 connections for localhost for more than 5m0s",
 			},
 		},
 		{
@@ -152,7 +153,7 @@ func TestAlert_ExecTemplate(t *testing.T) {
 			},
 		},
 		{
-			name: "ActiveAt custome format",
+			name: "ActiveAt custom format",
 			alert: &Alert{
 				ActiveAt: time.Date(2022, 8, 19, 20, 34, 58, 651387237, time.UTC),
 			},
@@ -199,6 +200,9 @@ func TestAlert_ExecTemplate(t *testing.T) {
 	}
 	for _, tc := range testCases {
 		t.Run(tc.name, func(t *testing.T) {
+			if err := ValidateTemplates(tc.annotations); err != nil {
+				t.Fatal(err)
+			}
 			tpl, err := tc.alert.ExecTemplate(qFn, tc.alert.Labels, tc.annotations)
 			if err != nil {
 				t.Fatal(err)

app/vmalert/notifier/alertmanager.go

@@ -64,7 +64,7 @@ func (am *AlertManager) send(ctx context.Context, alerts []Alert) error {
 	b := &bytes.Buffer{}
 	writeamRequest(b, alerts, am.argFunc, am.relabelConfigs)
 
-	req, err := http.NewRequest("POST", am.addr, b)
+	req, err := http.NewRequest(http.MethodPost, am.addr, b)
 	if err != nil {
 		return err
 	}

app/vmalert/notifier/config.go

@@ -29,7 +29,7 @@ type Config struct {
 	// ConsulSDConfigs contains list of settings for service discovery via Consul
 	// see https://prometheus.io/docs/prometheus/latest/configuration/configuration/#consul_sd_config
 	ConsulSDConfigs []consul.SDConfig `yaml:"consul_sd_configs,omitempty"`
-	// DNSSDConfigs ontains list of settings for service discovery via DNS.
+	// DNSSDConfigs contains list of settings for service discovery via DNS.
 	// See https://prometheus.io/docs/prometheus/latest/configuration/configuration/#dns_sd_config
 	DNSSDConfigs []dns.SDConfig `yaml:"dns_sd_configs,omitempty"`
 

app/vmalert/notifier/config_watcher_test.go

@@ -162,14 +162,15 @@ consul_sd_configs:
 	wg := sync.WaitGroup{}
 	wg.Add(workers)
 	for i := 0; i < workers; i++ {
-		go func() {
+		go func(n int) {
 			defer wg.Done()
+			r := rand.New(rand.NewSource(int64(n)))
 			for i := 0; i < iterations; i++ {
-				rnd := rand.Intn(len(paths))
+				rnd := r.Intn(len(paths))
 				_ = cw.reload(paths[rnd]) // update can fail and this is expected
 				_ = cw.notifiers()
 			}
-		}()
+		}(i)
 	}
 	wg.Wait()
 }

app/vmalert/notifier/init.go

@@ -17,7 +17,8 @@ var (
 	configPath                    = flag.String("notifier.config", "", "Path to configuration file for notifiers")
 	suppressDuplicateTargetErrors = flag.Bool("notifier.suppressDuplicateTargetErrors", false, "Whether to suppress 'duplicate target' errors during discovery")
 
-	addrs = flagutil.NewArrayString("notifier.url", "Prometheus alertmanager URL, e.g. http://127.0.0.1:9093")
+	addrs = flagutil.NewArrayString("notifier.url", "Prometheus Alertmanager URL, e.g. http://127.0.0.1:9093. "+
+		"List all Alertmanager URLs if it runs in the cluster mode to ensure high availability.")
 
 	basicAuthUsername     = flagutil.NewArrayString("notifier.basicAuth.username", "Optional basic auth username for -notifier.url")
 	basicAuthPassword     = flagutil.NewArrayString("notifier.basicAuth.password", "Optional basic auth password for -notifier.url")
@@ -80,10 +81,6 @@ var (
 //
 // Init returns an error if both mods are used.
 func Init(gen AlertURLGenerator, extLabels map[string]string, extURL string) (func() []Notifier, error) {
-	if externalLabels != nil || externalURL != "" {
-		return nil, fmt.Errorf("BUG: notifier.Init was called multiple times")
-	}
-
 	externalURL = extURL
 	externalLabels = extLabels
 	eu, err := url.Parse(externalURL)

app/vmalert/notifier/init_test.go

@@ -0,0 +1,37 @@
+package notifier
+
+import (
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
+	"testing"
+)
+
+func TestInit(t *testing.T) {
+	oldAddrs := *addrs
+	defer func() { *addrs = oldAddrs }()
+
+	*addrs = flagutil.ArrayString{"127.0.0.1", "127.0.0.2"}
+
+	fn, err := Init(nil, nil, "")
+	if err != nil {
+		t.Fatalf("%s", err)
+	}
+
+	nfs := fn()
+	if len(nfs) != 2 {
+		t.Fatalf("expected to get 2 notifiers; got %d", len(nfs))
+	}
+
+	targets := GetTargets()
+	if targets == nil || targets[TargetStatic] == nil {
+		t.Fatalf("expected to get static targets in response")
+	}
+
+	nf1 := targets[TargetStatic][0]
+	if nf1.Addr() != "127.0.0.1/api/v2/alerts" {
+		t.Fatalf("expected to get \"127.0.0.1/api/v2/alerts\"; got %q instead", nf1.Addr())
+	}
+	nf2 := targets[TargetStatic][1]
+	if nf2.Addr() != "127.0.0.2/api/v2/alerts" {
+		t.Fatalf("expected to get \"127.0.0.2/api/v2/alerts\"; got %q instead", nf2.Addr())
+	}
+}

app/vmalert/recording.go

@@ -58,7 +58,6 @@ func newRecordingRule(qb datasource.QuerierBuilder, group *Group, cfg config.Rul
 		Labels:  cfg.Labels,
 		GroupID: group.ID(),
 		metrics: &recordingRuleMetrics{},
-		state:   newRuleState(),
 		q: qb.BuildWithParams(datasource.QuerierParams{
 			DataSourceType:     group.Type.String(),
 			EvaluationInterval: group.Interval,
@@ -67,6 +66,12 @@ func newRecordingRule(qb datasource.QuerierBuilder, group *Group, cfg config.Rul
 		}),
 	}
 
+	if cfg.UpdateEntriesLimit != nil {
+		rr.state = newRuleState(*cfg.UpdateEntriesLimit)
+	} else {
+		rr.state = newRuleState(*ruleUpdateEntriesLimit)
+	}
+
 	labels := fmt.Sprintf(`recording=%q, group=%q, id="%d"`, rr.Name, group.Name, rr.ID())
 	rr.metrics.errors = utils.GetOrCreateGauge(fmt.Sprintf(`vmalert_recording_rules_error{%s}`, labels),
 		func() float64 {
@@ -212,6 +217,7 @@ func (rr *RecordingRule) ToAPI() APIRule {
 		EvaluationTime: lastState.duration.Seconds(),
 		Health:         "ok",
 		LastSamples:    lastState.samples,
+		MaxUpdates:     rr.state.size(),
 		Updates:        rr.state.getAll(),
 
 		// encode as strings to avoid rounding

app/vmalert/recording_test.go

@@ -19,7 +19,7 @@ func TestRecordingRule_Exec(t *testing.T) {
 		expTS   []prompbmarshal.TimeSeries
 	}{
 		{
-			&RecordingRule{Name: "foo", state: newRuleState()},
+			&RecordingRule{Name: "foo"},
 			[]datasource.Metric{metricWithValueAndLabels(t, 10,
 				"__name__", "bar",
 			)},
@@ -30,7 +30,7 @@ func TestRecordingRule_Exec(t *testing.T) {
 			},
 		},
 		{
-			&RecordingRule{Name: "foobarbaz", state: newRuleState()},
+			&RecordingRule{Name: "foobarbaz"},
 			[]datasource.Metric{
 				metricWithValueAndLabels(t, 1, "__name__", "foo", "job", "foo"),
 				metricWithValueAndLabels(t, 2, "__name__", "bar", "job", "bar"),
@@ -53,8 +53,7 @@ func TestRecordingRule_Exec(t *testing.T) {
 		},
 		{
 			&RecordingRule{
-				Name:  "job:foo",
-				state: newRuleState(),
+				Name: "job:foo",
 				Labels: map[string]string{
 					"source": "test",
 				}},
@@ -80,6 +79,7 @@ func TestRecordingRule_Exec(t *testing.T) {
 			fq := &fakeQuerier{}
 			fq.add(tc.metrics...)
 			tc.rule.q = fq
+			tc.rule.state = newRuleState(10)
 			tss, err := tc.rule.Exec(context.TODO(), time.Now(), 0)
 			if err != nil {
 				t.Fatalf("unexpected Exec err: %s", err)
@@ -198,7 +198,7 @@ func TestRecordingRuleLimit(t *testing.T) {
 		metricWithValuesAndLabels(t, []float64{2, 3}, "__name__", "bar", "job", "bar"),
 		metricWithValuesAndLabels(t, []float64{4, 5, 6}, "__name__", "baz", "job", "baz"),
 	}
-	rule := &RecordingRule{Name: "job:foo", state: newRuleState(), Labels: map[string]string{
+	rule := &RecordingRule{Name: "job:foo", state: newRuleState(10), Labels: map[string]string{
 		"source": "test_limit",
 	}}
 	var err error
@@ -216,7 +216,7 @@ func TestRecordingRuleLimit(t *testing.T) {
 func TestRecordingRule_ExecNegative(t *testing.T) {
 	rr := &RecordingRule{
 		Name:  "job:foo",
-		state: newRuleState(),
+		state: newRuleState(10),
 		Labels: map[string]string{
 			"job": "test",
 		},

app/vmalert/remotewrite/init_test.go

@@ -0,0 +1,20 @@
+package remotewrite
+
+import (
+	"context"
+	"testing"
+)
+
+func TestInit(t *testing.T) {
+	oldAddr := *addr
+	defer func() { *addr = oldAddr }()
+
+	*addr = "http://localhost:8428"
+	cl, err := Init(context.Background())
+	if err != nil {
+		t.Fatal(err)
+	}
+	if err := cl.Close(); err != nil {
+		t.Fatal(err)
+	}
+}

app/vmalert/remotewrite/remotewrite.go

@@ -225,7 +225,7 @@ func (c *Client) flush(ctx context.Context, wr *prompbmarshal.WriteRequest) {
 
 func (c *Client) send(ctx context.Context, data []byte) error {
 	r := bytes.NewReader(data)
-	req, err := http.NewRequest("POST", c.addr, r)
+	req, err := http.NewRequest(http.MethodPost, c.addr, r)
 	if err != nil {
 		return fmt.Errorf("failed to create new HTTP request: %w", err)
 	}

app/vmalert/remotewrite/remotewrite_test.go

@@ -27,12 +27,13 @@ func TestClient_Push(t *testing.T) {
 	if err != nil {
 		t.Fatalf("failed to create client: %s", err)
 	}
+	r := rand.New(rand.NewSource(1))
 	const rowsN = 1e4
 	var sent int
 	for i := 0; i < rowsN; i++ {
 		s := prompbmarshal.TimeSeries{
 			Samples: []prompbmarshal.Sample{{
-				Value:     rand.Float64(),
+				Value:     r.Float64(),
 				Timestamp: time.Now().Unix(),
 			}},
 		}

app/vmalert/replay.go

@@ -26,7 +26,7 @@ var (
 			"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.")
+		"Max number of data points expected in one request. It affects the max time range for every `/query_range` request during the replay. 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.")
 	disableProgressBar = flag.Bool("replay.disableProgressBar", false, "Whether to disable rendering progress bars during the replay. "+

app/vmalert/rule.go

@@ -57,11 +57,12 @@ type ruleStateEntry struct {
 	curl string
 }
 
-const defaultStateEntriesLimit = 20
-
-func newRuleState() *ruleState {
+func newRuleState(size int) *ruleState {
+	if size < 1 {
+		size = 1
+	}
 	return &ruleState{
-		entries: make([]ruleStateEntry, defaultStateEntriesLimit),
+		entries: make([]ruleStateEntry, size),
 	}
 }
 
@@ -71,6 +72,12 @@ func (s *ruleState) getLast() ruleStateEntry {
 	return s.entries[s.cur]
 }
 
+func (s *ruleState) size() int {
+	s.RLock()
+	defer s.RUnlock()
+	return len(s.entries)
+}
+
 func (s *ruleState) getAll() []ruleStateEntry {
 	entries := make([]ruleStateEntry, 0)
 

app/vmalert/rule_test.go

@@ -6,8 +6,27 @@ import (
 	"time"
 )
 
+func TestRule_stateDisabled(t *testing.T) {
+	state := newRuleState(-1)
+	e := state.getLast()
+	if !e.at.IsZero() {
+		t.Fatalf("expected entry to be zero")
+	}
+
+	state.add(ruleStateEntry{at: time.Now()})
+	state.add(ruleStateEntry{at: time.Now()})
+	state.add(ruleStateEntry{at: time.Now()})
+
+	if len(state.getAll()) != 1 {
+		// state should store at least one update at any circumstances
+		t.Fatalf("expected for state to have %d entries; got %d",
+			1, len(state.getAll()),
+		)
+	}
+}
 func TestRule_state(t *testing.T) {
-	state := newRuleState()
+	stateEntriesN := 20
+	state := newRuleState(stateEntriesN)
 	e := state.getLast()
 	if !e.at.IsZero() {
 		t.Fatalf("expected entry to be zero")
@@ -39,7 +58,7 @@ func TestRule_state(t *testing.T) {
 	}
 
 	var last time.Time
-	for i := 0; i < defaultStateEntriesLimit*2; i++ {
+	for i := 0; i < stateEntriesN*2; i++ {
 		last = time.Now()
 		state.add(ruleStateEntry{at: last})
 	}
@@ -50,9 +69,9 @@ func TestRule_state(t *testing.T) {
 			e.at, last)
 	}
 
-	if len(state.getAll()) != defaultStateEntriesLimit {
+	if len(state.getAll()) != stateEntriesN {
 		t.Fatalf("expected for state to have %d entries only; got %d",
-			defaultStateEntriesLimit, len(state.getAll()),
+			stateEntriesN, len(state.getAll()),
 		)
 	}
 }
@@ -61,7 +80,7 @@ func TestRule_state(t *testing.T) {
 // execution of state updates.
 // Should be executed with -race flag
 func TestRule_stateConcurrent(t *testing.T) {
-	state := newRuleState()
+	state := newRuleState(20)
 
 	const workers = 50
 	const iterations = 100

app/vmalert/templates/template.go

@@ -27,11 +27,11 @@ import (
 	"strconv"
 	"strings"
 	"sync"
+	textTpl "text/template"
 	"time"
 
-	textTpl "text/template"
-
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/formatutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promutils"
 )
 
@@ -225,7 +225,7 @@ func templateFuncs() textTpl.FuncMap {
 		"toLower": strings.ToLower,
 
 		// crlfEscape replaces '\n' and '\r' chars with `\\n` and `\\r`.
-		// This funcion is deprectated.
+		// This function is deprecated.
 		//
 		// It is better to use quotesEscape, jsonEscape, queryEscape or pathEscape instead -
 		// these functions properly escape `\n` and `\r` chars according to their purpose.
@@ -350,18 +350,10 @@ func templateFuncs() textTpl.FuncMap {
 			if math.Abs(v) <= 1 || math.IsNaN(v) || math.IsInf(v, 0) {
 				return fmt.Sprintf("%.4g", v), nil
 			}
-			prefix := ""
-			for _, p := range []string{"ki", "Mi", "Gi", "Ti", "Pi", "Ei", "Zi", "Yi"} {
-				if math.Abs(v) < 1024 {
-					break
-				}
-				prefix = p
-				v /= 1024
-			}
-			return fmt.Sprintf("%.4g%s", v, prefix), nil
+			return formatutil.HumanizeBytes(v), nil
 		},
 
-		// humanizeDuration converts given seconds to a human readable duration
+		// humanizeDuration converts given seconds to a human-readable duration
 		"humanizeDuration": func(i interface{}) (string, error) {
 			v, err := toFloat64(i)
 			if err != nil {

app/vmalert/templates/template_test.go

@@ -1,6 +1,7 @@
 package templates
 
 import (
+	"math"
 	"strings"
 	"testing"
 	textTpl "text/template"
@@ -50,6 +51,45 @@ func TestTemplateFuncs(t *testing.T) {
 	if !ok {
 		t.Fatalf("unexpected mismatch")
 	}
+
+	formatting := func(funcName string, p interface{}, resultExpected string) {
+		t.Helper()
+		v := funcs[funcName]
+		fLocal := v.(func(s interface{}) (string, error))
+		result, err := fLocal(p)
+		if err != nil {
+			t.Fatalf("unexpected error for %s(%f): %s", funcName, p, err)
+		}
+		if result != resultExpected {
+			t.Fatalf("unexpected result for %s(%f); got\n%s\nwant\n%s", funcName, p, result, resultExpected)
+		}
+	}
+	formatting("humanize1024", float64(0), "0")
+	formatting("humanize1024", math.Inf(0), "+Inf")
+	formatting("humanize1024", math.NaN(), "NaN")
+	formatting("humanize1024", float64(127087), "124.1ki")
+	formatting("humanize1024", float64(130137088), "124.1Mi")
+	formatting("humanize1024", float64(133260378112), "124.1Gi")
+	formatting("humanize1024", float64(136458627186688), "124.1Ti")
+	formatting("humanize1024", float64(139733634239168512), "124.1Pi")
+	formatting("humanize1024", float64(143087241460908556288), "124.1Ei")
+	formatting("humanize1024", float64(146521335255970361638912), "124.1Zi")
+	formatting("humanize1024", float64(150037847302113650318245888), "124.1Yi")
+	formatting("humanize1024", float64(153638755637364377925883789312), "1.271e+05Yi")
+
+	formatting("humanize", float64(127087), "127.1k")
+	formatting("humanize", float64(136458627186688), "136.5T")
+
+	formatting("humanizeDuration", 1, "1s")
+	formatting("humanizeDuration", 0.2, "200ms")
+	formatting("humanizeDuration", 42000, "11h 40m 0s")
+	formatting("humanizeDuration", 16790555, "194d 8h 2m 35s")
+
+	formatting("humanizePercentage", 1, "100%")
+	formatting("humanizePercentage", 0.8, "80%")
+	formatting("humanizePercentage", 0.015, "1.5%")
+
+	formatting("humanizeTimestamp", 1679055557, "2023-03-17 12:19:17 +0000 UTC")
 }
 
 func mkTemplate(current, replacement interface{}) textTemplate {

app/vmalert/web.go

@@ -57,7 +57,7 @@ func (rh *requestHandler) handler(w http.ResponseWriter, r *http.Request) bool {
 
 	switch r.URL.Path {
 	case "/", "/vmalert", "/vmalert/":
-		if r.Method != "GET" {
+		if r.Method != http.MethodGet {
 			httpserver.Errorf(w, r, "path %q supports only GET method", r.URL.Path)
 			return false
 		}

app/vmalert/web.qtpl

@@ -40,9 +40,9 @@
             for _, g := range groups {
                 for _, r := range g.Rules {
                     if r.LastError != "" {
-                        rNotOk[g.Name]++
+                        rNotOk[g.ID]++
                     } else {
-                        rOk[g.Name]++
+                        rOk[g.ID]++
                     }
                 }
             }
@@ -50,11 +50,11 @@
          <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 %}">
+              <div class="group-heading{% if rNotOk[g.ID] > 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 {%f.0 g.Interval %}s)</a>
-                 {% if rNotOk[g.Name] > 0 %}<span class="badge bg-danger" title="Number of rules with 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>
+                <a href="#group-{%s g.ID %}">{%s g.Name %}{% if g.Type != "prometheus" %} ({%s g.Type %}){% endif %} (every {%f.0 g.Interval %}s) #</a>
+                 {% if rNotOk[g.ID] > 0 %}<span class="badge bg-danger" title="Number of rules with status Error">{%d rNotOk[g.ID] %}</span> {% endif %}
+                <span class="badge bg-success" title="Number of rules withs status Ok">{%d rOk[g.ID] %}</span>
                 <p class="fs-6 fw-lighter">{%s g.File %}</p>
                 {% if len(g.Params) > 0 %}
                     <div class="fs-6 fw-lighter">Extra params
@@ -427,6 +427,16 @@
         </div>
       </div>
     </div>
+    <div class="container border-bottom p-2">
+      <div class="row">
+        <div class="col-2">
+          Debug
+        </div>
+        <div class="col">
+           {%v rule.Debug %}
+        </div>
+      </div>
+    </div>
     {% endif %}
     <div class="container border-bottom p-2">
       <div class="row">
@@ -440,7 +450,7 @@
     </div>
 
     <br>
-    <div class="display-6 pb-3">Last {%d len(rule.Updates) %} updates</span>:</div>
+    <div class="display-6 pb-3">Last {%d len(rule.Updates) %}/{%d rule.MaxUpdates %} updates</span>:</div>
         <table class="table table-striped table-hover table-sm">
             <thead>
                 <tr>

app/vmalert/web.qtpl.go

@@ -171,9 +171,9 @@ func StreamListGroups(qw422016 *qt422016.Writer, r *http.Request, groups []APIGr
 		for _, g := range groups {
 			for _, r := range g.Rules {
 				if r.LastError != "" {
-					rNotOk[g.Name]++
+					rNotOk[g.ID]++
 				} else {
-					rOk[g.Name]++
+					rOk[g.ID]++
 				}
 			}
 		}
@@ -189,7 +189,7 @@ func StreamListGroups(qw422016 *qt422016.Writer, r *http.Request, groups []APIGr
 			qw422016.N().S(`
               <div class="group-heading`)
 //line app/vmalert/web.qtpl:53
-			if rNotOk[g.Name] > 0 {
+			if rNotOk[g.ID] > 0 {
 //line app/vmalert/web.qtpl:53
 				qw422016.N().S(` alert-danger`)
 //line app/vmalert/web.qtpl:53
@@ -227,14 +227,14 @@ func StreamListGroups(qw422016 *qt422016.Writer, r *http.Request, groups []APIGr
 //line app/vmalert/web.qtpl:55
 			qw422016.N().FPrec(g.Interval, 0)
 //line app/vmalert/web.qtpl:55
-			qw422016.N().S(`s)</a>
+			qw422016.N().S(`s) #</a>
                  `)
 //line app/vmalert/web.qtpl:56
-			if rNotOk[g.Name] > 0 {
+			if rNotOk[g.ID] > 0 {
 //line app/vmalert/web.qtpl:56
 				qw422016.N().S(`<span class="badge bg-danger" title="Number of rules with status Error">`)
 //line app/vmalert/web.qtpl:56
-				qw422016.N().D(rNotOk[g.Name])
+				qw422016.N().D(rNotOk[g.ID])
 //line app/vmalert/web.qtpl:56
 				qw422016.N().S(`</span> `)
 //line app/vmalert/web.qtpl:56
@@ -243,7 +243,7 @@ func StreamListGroups(qw422016 *qt422016.Writer, r *http.Request, groups []APIGr
 			qw422016.N().S(`
                 <span class="badge bg-success" title="Number of rules withs status Ok">`)
 //line app/vmalert/web.qtpl:57
-			qw422016.N().D(rOk[g.Name])
+			qw422016.N().D(rOk[g.ID])
 //line app/vmalert/web.qtpl:57
 			qw422016.N().S(`</span>
                 <p class="fs-6 fw-lighter">`)
@@ -1313,10 +1313,24 @@ func StreamRuleDetails(qw422016 *qt422016.Writer, r *http.Request, rule APIRule)
         </div>
       </div>
     </div>
+    <div class="container border-bottom p-2">
+      <div class="row">
+        <div class="col-2">
+          Debug
+        </div>
+        <div class="col">
+           `)
+//line app/vmalert/web.qtpl:436
+		qw422016.E().V(rule.Debug)
+//line app/vmalert/web.qtpl:436
+		qw422016.N().S(`
+        </div>
+      </div>
+    </div>
     `)
-//line app/vmalert/web.qtpl:430
+//line app/vmalert/web.qtpl:440
 	}
-//line app/vmalert/web.qtpl:430
+//line app/vmalert/web.qtpl:440
 	qw422016.N().S(`
     <div class="container border-bottom p-2">
       <div class="row">
@@ -1325,17 +1339,17 @@ func StreamRuleDetails(qw422016 *qt422016.Writer, r *http.Request, rule APIRule)
         </div>
         <div class="col">
            <a target="_blank" href="`)
-//line app/vmalert/web.qtpl:437
+//line app/vmalert/web.qtpl:447
 	qw422016.E().S(prefix)
-//line app/vmalert/web.qtpl:437
+//line app/vmalert/web.qtpl:447
 	qw422016.N().S(`groups#group-`)
-//line app/vmalert/web.qtpl:437
+//line app/vmalert/web.qtpl:447
 	qw422016.E().S(rule.GroupID)
-//line app/vmalert/web.qtpl:437
+//line app/vmalert/web.qtpl:447
 	qw422016.N().S(`">`)
-//line app/vmalert/web.qtpl:437
+//line app/vmalert/web.qtpl:447
 	qw422016.E().S(rule.GroupID)
-//line app/vmalert/web.qtpl:437
+//line app/vmalert/web.qtpl:447
 	qw422016.N().S(`</a>
         </div>
       </div>
@@ -1343,9 +1357,13 @@ func StreamRuleDetails(qw422016 *qt422016.Writer, r *http.Request, rule APIRule)
 
     <br>
     <div class="display-6 pb-3">Last `)
-//line app/vmalert/web.qtpl:443
+//line app/vmalert/web.qtpl:453
 	qw422016.N().D(len(rule.Updates))
-//line app/vmalert/web.qtpl:443
+//line app/vmalert/web.qtpl:453
+	qw422016.N().S(`/`)
+//line app/vmalert/web.qtpl:453
+	qw422016.N().D(rule.MaxUpdates)
+//line app/vmalert/web.qtpl:453
 	qw422016.N().S(` updates</span>:</div>
         <table class="table table-striped table-hover table-sm">
             <thead>
@@ -1360,201 +1378,201 @@ func StreamRuleDetails(qw422016 *qt422016.Writer, r *http.Request, rule APIRule)
             <tbody>
 
      `)
-//line app/vmalert/web.qtpl:456
+//line app/vmalert/web.qtpl:466
 	for _, u := range rule.Updates {
-//line app/vmalert/web.qtpl:456
+//line app/vmalert/web.qtpl:466
 		qw422016.N().S(`
              <tr`)
-//line app/vmalert/web.qtpl:457
+//line app/vmalert/web.qtpl:467
 		if u.err != nil {
-//line app/vmalert/web.qtpl:457
+//line app/vmalert/web.qtpl:467
 			qw422016.N().S(` class="alert-danger"`)
-//line app/vmalert/web.qtpl:457
+//line app/vmalert/web.qtpl:467
 		}
-//line app/vmalert/web.qtpl:457
+//line app/vmalert/web.qtpl:467
 		qw422016.N().S(`>
                  <td>
                     <span class="badge bg-primary rounded-pill me-3" title="Updated at">`)
-//line app/vmalert/web.qtpl:459
+//line app/vmalert/web.qtpl:469
 		qw422016.E().S(u.time.Format(time.RFC3339))
-//line app/vmalert/web.qtpl:459
+//line app/vmalert/web.qtpl:469
 		qw422016.N().S(`</span>
                  </td>
                  <td class="text-center" wi>`)
-//line app/vmalert/web.qtpl:461
+//line app/vmalert/web.qtpl:471
 		qw422016.N().D(u.samples)
-//line app/vmalert/web.qtpl:461
+//line app/vmalert/web.qtpl:471
 		qw422016.N().S(`</td>
                  <td class="text-center">`)
-//line app/vmalert/web.qtpl:462
+//line app/vmalert/web.qtpl:472
 		qw422016.N().FPrec(u.duration.Seconds(), 3)
-//line app/vmalert/web.qtpl:462
+//line app/vmalert/web.qtpl:472
 		qw422016.N().S(`s</td>
                  <td class="text-center">`)
-//line app/vmalert/web.qtpl:463
+//line app/vmalert/web.qtpl:473
 		qw422016.E().S(u.at.Format(time.RFC3339))
-//line app/vmalert/web.qtpl:463
+//line app/vmalert/web.qtpl:473
 		qw422016.N().S(`</td>
                  <td>
                     <textarea class="curl-area" rows="1" onclick="this.focus();this.select()">`)
-//line app/vmalert/web.qtpl:465
+//line app/vmalert/web.qtpl:475
 		qw422016.E().S(u.curl)
-//line app/vmalert/web.qtpl:465
+//line app/vmalert/web.qtpl:475
 		qw422016.N().S(`</textarea>
                 </td>
              </tr>
           </li>
           `)
-//line app/vmalert/web.qtpl:469
+//line app/vmalert/web.qtpl:479
 		if u.err != nil {
-//line app/vmalert/web.qtpl:469
+//line app/vmalert/web.qtpl:479
 			qw422016.N().S(`
              <tr`)
-//line app/vmalert/web.qtpl:470
+//line app/vmalert/web.qtpl:480
 			if u.err != nil {
-//line app/vmalert/web.qtpl:470
+//line app/vmalert/web.qtpl:480
 				qw422016.N().S(` class="alert-danger"`)
-//line app/vmalert/web.qtpl:470
+//line app/vmalert/web.qtpl:480
 			}
-//line app/vmalert/web.qtpl:470
+//line app/vmalert/web.qtpl:480
 			qw422016.N().S(`>
                <td colspan="5">
                    <span class="alert-danger">`)
-//line app/vmalert/web.qtpl:472
+//line app/vmalert/web.qtpl:482
 			qw422016.E().V(u.err)
-//line app/vmalert/web.qtpl:472
+//line app/vmalert/web.qtpl:482
 			qw422016.N().S(`</span>
                </td>
              </tr>
           `)
-//line app/vmalert/web.qtpl:475
+//line app/vmalert/web.qtpl:485
 		}
-//line app/vmalert/web.qtpl:475
+//line app/vmalert/web.qtpl:485
 		qw422016.N().S(`
      `)
-//line app/vmalert/web.qtpl:476
+//line app/vmalert/web.qtpl:486
 	}
-//line app/vmalert/web.qtpl:476
+//line app/vmalert/web.qtpl:486
 	qw422016.N().S(`
 
     `)
-//line app/vmalert/web.qtpl:478
+//line app/vmalert/web.qtpl:488
 	tpl.StreamFooter(qw422016, r)
-//line app/vmalert/web.qtpl:478
+//line app/vmalert/web.qtpl:488
 	qw422016.N().S(`
 `)
-//line app/vmalert/web.qtpl:479
+//line app/vmalert/web.qtpl:489
 }
 
-//line app/vmalert/web.qtpl:479
+//line app/vmalert/web.qtpl:489
 func WriteRuleDetails(qq422016 qtio422016.Writer, r *http.Request, rule APIRule) {
-//line app/vmalert/web.qtpl:479
+//line app/vmalert/web.qtpl:489
 	qw422016 := qt422016.AcquireWriter(qq422016)
-//line app/vmalert/web.qtpl:479
+//line app/vmalert/web.qtpl:489
 	StreamRuleDetails(qw422016, r, rule)
-//line app/vmalert/web.qtpl:479
+//line app/vmalert/web.qtpl:489
 	qt422016.ReleaseWriter(qw422016)
-//line app/vmalert/web.qtpl:479
+//line app/vmalert/web.qtpl:489
 }
 
-//line app/vmalert/web.qtpl:479
+//line app/vmalert/web.qtpl:489
 func RuleDetails(r *http.Request, rule APIRule) string {
-//line app/vmalert/web.qtpl:479
+//line app/vmalert/web.qtpl:489
 	qb422016 := qt422016.AcquireByteBuffer()
-//line app/vmalert/web.qtpl:479
+//line app/vmalert/web.qtpl:489
 	WriteRuleDetails(qb422016, r, rule)
-//line app/vmalert/web.qtpl:479
+//line app/vmalert/web.qtpl:489
 	qs422016 := string(qb422016.B)
-//line app/vmalert/web.qtpl:479
+//line app/vmalert/web.qtpl:489
 	qt422016.ReleaseByteBuffer(qb422016)
-//line app/vmalert/web.qtpl:479
+//line app/vmalert/web.qtpl:489
 	return qs422016
-//line app/vmalert/web.qtpl:479
+//line app/vmalert/web.qtpl:489
 }
 
-//line app/vmalert/web.qtpl:483
+//line app/vmalert/web.qtpl:493
 func streambadgeState(qw422016 *qt422016.Writer, state string) {
-//line app/vmalert/web.qtpl:483
+//line app/vmalert/web.qtpl:493
 	qw422016.N().S(`
 `)
-//line app/vmalert/web.qtpl:485
+//line app/vmalert/web.qtpl:495
 	badgeClass := "bg-warning text-dark"
 	if state == "firing" {
 		badgeClass = "bg-danger"
 	}
 
-//line app/vmalert/web.qtpl:489
+//line app/vmalert/web.qtpl:499
 	qw422016.N().S(`
 <span class="badge `)
-//line app/vmalert/web.qtpl:490
+//line app/vmalert/web.qtpl:500
 	qw422016.E().S(badgeClass)
-//line app/vmalert/web.qtpl:490
+//line app/vmalert/web.qtpl:500
 	qw422016.N().S(`">`)
-//line app/vmalert/web.qtpl:490
+//line app/vmalert/web.qtpl:500
 	qw422016.E().S(state)
-//line app/vmalert/web.qtpl:490
+//line app/vmalert/web.qtpl:500
 	qw422016.N().S(`</span>
 `)
-//line app/vmalert/web.qtpl:491
+//line app/vmalert/web.qtpl:501
 }
 
-//line app/vmalert/web.qtpl:491
+//line app/vmalert/web.qtpl:501
 func writebadgeState(qq422016 qtio422016.Writer, state string) {
-//line app/vmalert/web.qtpl:491
+//line app/vmalert/web.qtpl:501
 	qw422016 := qt422016.AcquireWriter(qq422016)
-//line app/vmalert/web.qtpl:491
+//line app/vmalert/web.qtpl:501
 	streambadgeState(qw422016, state)
-//line app/vmalert/web.qtpl:491
+//line app/vmalert/web.qtpl:501
 	qt422016.ReleaseWriter(qw422016)
-//line app/vmalert/web.qtpl:491
+//line app/vmalert/web.qtpl:501
 }
 
-//line app/vmalert/web.qtpl:491
+//line app/vmalert/web.qtpl:501
 func badgeState(state string) string {
-//line app/vmalert/web.qtpl:491
+//line app/vmalert/web.qtpl:501
 	qb422016 := qt422016.AcquireByteBuffer()
-//line app/vmalert/web.qtpl:491
+//line app/vmalert/web.qtpl:501
 	writebadgeState(qb422016, state)
-//line app/vmalert/web.qtpl:491
+//line app/vmalert/web.qtpl:501
 	qs422016 := string(qb422016.B)
-//line app/vmalert/web.qtpl:491
+//line app/vmalert/web.qtpl:501
 	qt422016.ReleaseByteBuffer(qb422016)
-//line app/vmalert/web.qtpl:491
+//line app/vmalert/web.qtpl:501
 	return qs422016
-//line app/vmalert/web.qtpl:491
+//line app/vmalert/web.qtpl:501
 }
 
-//line app/vmalert/web.qtpl:493
+//line app/vmalert/web.qtpl:503
 func streambadgeRestored(qw422016 *qt422016.Writer) {
-//line app/vmalert/web.qtpl:493
+//line app/vmalert/web.qtpl:503
 	qw422016.N().S(`
 <span class="badge bg-warning text-dark" title="Alert state was restored after the service restart from remote storage">restored</span>
 `)
-//line app/vmalert/web.qtpl:495
+//line app/vmalert/web.qtpl:505
 }
 
-//line app/vmalert/web.qtpl:495
+//line app/vmalert/web.qtpl:505
 func writebadgeRestored(qq422016 qtio422016.Writer) {
-//line app/vmalert/web.qtpl:495
+//line app/vmalert/web.qtpl:505
 	qw422016 := qt422016.AcquireWriter(qq422016)
-//line app/vmalert/web.qtpl:495
+//line app/vmalert/web.qtpl:505
 	streambadgeRestored(qw422016)
-//line app/vmalert/web.qtpl:495
+//line app/vmalert/web.qtpl:505
 	qt422016.ReleaseWriter(qw422016)
-//line app/vmalert/web.qtpl:495
+//line app/vmalert/web.qtpl:505
 }
 
-//line app/vmalert/web.qtpl:495
+//line app/vmalert/web.qtpl:505
 func badgeRestored() string {
-//line app/vmalert/web.qtpl:495
+//line app/vmalert/web.qtpl:505
 	qb422016 := qt422016.AcquireByteBuffer()
-//line app/vmalert/web.qtpl:495
+//line app/vmalert/web.qtpl:505
 	writebadgeRestored(qb422016)
-//line app/vmalert/web.qtpl:495
+//line app/vmalert/web.qtpl:505
 	qs422016 := string(qb422016.B)
-//line app/vmalert/web.qtpl:495
+//line app/vmalert/web.qtpl:505
 	qt422016.ReleaseByteBuffer(qb422016)
-//line app/vmalert/web.qtpl:495
+//line app/vmalert/web.qtpl:505
 	return qs422016
-//line app/vmalert/web.qtpl:495
+//line app/vmalert/web.qtpl:505
 }

app/vmalert/web_test.go

@@ -7,6 +7,7 @@ import (
 	"net/http/httptest"
 	"reflect"
 	"testing"
+	"time"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
 )
@@ -17,11 +18,20 @@ func TestHandler(t *testing.T) {
 		alerts: map[uint64]*notifier.Alert{
 			0: {State: notifier.StateFiring},
 		},
-		state: newRuleState(),
+		state: newRuleState(10),
+	}
+	ar.state.add(ruleStateEntry{
+		time:    time.Now(),
+		at:      time.Now(),
+		samples: 10,
+	})
+	rr := &RecordingRule{
+		Name:  "record",
+		state: newRuleState(10),
 	}
 	g := &Group{
 		Name:  "group",
-		Rules: []Rule{ar},
+		Rules: []Rule{ar, rr},
 	}
 	m := &manager{groups: make(map[uint64]*Group)}
 	m.groups[0] = g
@@ -62,6 +72,14 @@ func TestHandler(t *testing.T) {
 	t.Run("/vmalert/rule", func(t *testing.T) {
 		a := ar.ToAPI()
 		getResp(ts.URL+"/vmalert/"+a.WebLink(), nil, 200)
+		r := rr.ToAPI()
+		getResp(ts.URL+"/vmalert/"+r.WebLink(), nil, 200)
+	})
+	t.Run("/vmalert/alert", func(t *testing.T) {
+		alerts := ar.AlertsToAPI()
+		for _, a := range alerts {
+			getResp(ts.URL+"/vmalert/"+a.WebLink(), nil, 200)
+		}
 	})
 	t.Run("/vmalert/rule?badParam", func(t *testing.T) {
 		params := fmt.Sprintf("?%s=0&%s=1", paramGroupID, paramRuleID)

app/vmalert/web_types.go

@@ -113,16 +113,20 @@ type APIRule struct {
 
 	// Additional fields
 
-	// Type of the rule: recording or alerting
+	// DatasourceType of the rule: prometheus or graphite
 	DatasourceType string `json:"datasourceType"`
 	LastSamples    int    `json:"lastSamples"`
 	// ID is a unique Alert's ID within a group
 	ID string `json:"id"`
 	// GroupID is an unique Group's ID
 	GroupID string `json:"group_id"`
+	// Debug shows whether debug mode is enabled
+	Debug bool `json:"debug"`
 
+	// MaxUpdates is the max number of recorded ruleStateEntry objects
+	MaxUpdates int `json:"max_updates_entries"`
 	// Updates contains the ordered list of recorded ruleStateEntry objects
-	Updates []ruleStateEntry `json:"updates"`
+	Updates []ruleStateEntry `json:"-"`
 }
 
 // WebLink returns a link to the alert which can be used in UI.

app/vmauth/Makefile

@@ -84,6 +84,9 @@ vmauth-linux-arm64:
 vmauth-linux-ppc64le:
 	APP_NAME=vmauth CGO_ENABLED=0 GOOS=linux GOARCH=ppc64le $(MAKE) app-local-goos-goarch
 
+vmauth-linux-s390x:
+	APP_NAME=vmauth CGO_ENABLED=0 GOOS=linux GOARCH=s390x $(MAKE) app-local-goos-goarch
+
 vmauth-linux-386:
 	APP_NAME=vmauth CGO_ENABLED=0 GOOS=linux GOARCH=386 $(MAKE) app-local-goos-goarch
 

app/vmauth/README.md

@@ -17,7 +17,12 @@ 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 either by passing `SIGHUP` signal to `vmauth` or by querying `/-/reload` http endpoint.
+The auth config can be reloaded via the following ways:
+
+- By passing `SIGHUP` signal to `vmauth`.
+- By querying `/-/reload` http endpoint. This endpoint can be protected with `-reloadAuthKey` command-line flag. See [security docs](#security) for more details.
+- By specifying `-configCheckInterval` command-line flag to the interval between config re-reads. For example, `-configCheckInterval=5s` will re-read the config
+  and apply new changes every 5 seconds.
 
 Docker images for `vmauth` are available [here](https://hub.docker.com/r/victoriametrics/vmauth/tags).
 
@@ -28,7 +33,36 @@ accounting and rate limiting such as [vmgateway](https://docs.victoriametrics.co
 
 ## 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).
+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 least-loaded round-robin manner.
+`vmauth` retries failing `GET` requests across the configured list of urls.
+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).
+
+## Concurrency limiting
+
+`vmauth` limits the number of concurrent requests it can proxy according to the following command-line flags:
+
+- `-maxConcurrentRequests` limits the global number of concurrent requests `vmauth` can serve across all the configured users.
+- `-maxConcurrentPerUserRequests` limits the number of concurrent requests `vmauth` can serve per each configured user.
+
+It is also possible to set individual limits on the number of concurrent requests per each user
+with the `max_concurrent_requests` option - see [auth config example](#auth-config).
+
+`vmauth` responds with `429 Too Many Requests` HTTP error when the number of concurrent requests exceeds the configured limits.
+
+The following [metrics](#monitoring) related to concurrency limits are exposed by `vmauth`:
+
+- `vmauth_concurrent_requests_capacity` - the global limit on the number of concurrent requests `vmauth` can serve.
+  It is set via `-maxConcurrentRequests` command-line flag.
+- `vmauth_concurrent_requests_current` - the current number of concurrent requests `vmauth` processes.
+- `vmauth_concurrent_requests_limit_reached_total` - the number of requests rejected with `429 Too Many Requests` error
+  because of the global concurrency limit has been reached.
+- `vmauth_user_concurrent_requests_capacity{username="..."}` - the limit on the number of concurrent requests for the given `username`.
+- `vmauth_user_concurrent_requests_current{username="..."}` - the current number of concurrent requests for the given `username`.
+- `vmauth_user_concurrent_requests_limit_reached_total{username="foo"}` - the number of requests rejected with `429 Too Many Requests` error
+  because of the concurrency limit has been reached for the given `username`.
+
 
 ## Auth config
 
@@ -55,26 +89,27 @@ users:
   headers:
   - "X-Scope-OrgID: foobar"
 
-  # The user for querying local single-node VictoriaMetrics.
   # All the requests to http://vmauth:8427 with the given Basic Auth (username:password)
-  # will be proxied to http://localhost:8428 .
+  # are proxied to http://localhost:8428 .
   # For example, http://vmauth:8427/api/v1/query is proxied to http://localhost:8428/api/v1/query
+  #
+  # The given user can send maximum 10 concurrent requests according to the provided max_concurrent_requests.
+  # Excess concurrent requests are rejected with 429 HTTP status code.
+  # See also -maxConcurrentPerUserRequests and -maxConcurrentRequests command-line flags.
 - username: "local-single-node"
   password: "***"
   url_prefix: "http://localhost:8428"
+  max_concurrent_requests: 10
 
-  # 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://localhost:8428 with extra_label=team=dev query arg.
+  # are proxied 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"
+- username: "local-single-node2"
   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
+  # are 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
@@ -84,10 +119,8 @@ users:
   - "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://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
+  # are 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
@@ -232,6 +265,8 @@ See the docs at https://docs.victoriametrics.com/vmauth.html .
 
   -auth.config string
      Path to auth config. It can point either to local file or to http url. See https://docs.victoriametrics.com/vmauth.html for details on the format of this auth config
+  -configCheckInterval duration
+     Interval for config file re-read. Zero value disables config re-reading. By default, refreshing is disabled, send SIGHUP for config refresh.
   -enableTCP6
      Whether to enable IPv6 for listening and dialing. By default only IPv4 TCP and UDP is used
   -envflag.enable
@@ -261,7 +296,11 @@ See the docs at https://docs.victoriametrics.com/vmauth.html .
   -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")
+     TCP address to listen for http connections. See also -httpListenAddr.useProxyProtocol (default ":8427")
+  -httpListenAddr.useProxyProtocol
+     Whether to use proxy protocol for connections accepted at -httpListenAddr . See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt
+  -internStringMaxLen int
+     The maximum length for strings to intern. Lower limit may save memory at the cost of higher CPU usage. See https://en.wikipedia.org/wiki/String_interning (default 500)
   -logInvalidAuthTokens
      Whether to log requests with invalid auth tokens. Such requests are always counted at vmauth_http_request_errors_total{reason="invalid_auth_token"} metric, which is exposed at /metrics page
   -loggerDisableTimestamps
@@ -270,6 +309,8 @@ See the docs at https://docs.victoriametrics.com/vmauth.html .
      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")
+  -loggerJSONFields string
+     Allows renaming fields in JSON formatted logs. Example: "ts:timestamp,msg:message" renames "ts" to "timestamp" and "msg" to "message". Supported fields: ts, level, caller, msg
   -loggerLevel string
      Minimum level of errors to log. Possible values: INFO, WARN, ERROR, FATAL, PANIC (default "INFO")
   -loggerOutput string
@@ -278,11 +319,15 @@ See the docs at https://docs.victoriametrics.com/vmauth.html .
      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
+  -maxConcurrentPerUserRequests int
+     The maximum number of concurrent requests vmauth can process per each configured user. Other requests are rejected with '429 Too Many Requests' http status code. See also -maxConcurrentRequests command-line option and max_concurrent_requests option in per-user config (default 300)
+  -maxConcurrentRequests int
+     The maximum number of concurrent requests vmauth can process. Other requests are rejected with '429 Too Many Requests' http status code. See also -maxConcurrentPerUserRequests and -maxIdleConnsPerBackend command-line options (default 1000)
   -maxIdleConnsPerBackend int
-     The maximum number of idle connections vmauth can open per each backend host (default 100)
+     The maximum number of idle connections vmauth can open per each backend host. See also -maxConcurrentRequests (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)
+     Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB (default 0)
   -memory.allowedPercent float
      Allowed percent of system memory VictoriaMetrics caches may occupy. See also -memory.allowedBytes. Too low a value may increase cache miss rate usually resulting in higher CPU and disk IO usage. Too high a value may evict too much data from OS page cache which will result in higher disk IO usage (default 60)
   -metricsAuthKey string
@@ -299,6 +344,8 @@ See the docs at https://docs.victoriametrics.com/vmauth.html .
      Supports an array of values separated by comma or specified via multiple flags.
   -reloadAuthKey string
      Auth key for /-/reload http endpoint. It must be passed as authKey=...
+  -responseTimeout duration
+     The timeout for receiving a response from backend (default 5m0s)
   -tls
      Whether to enable TLS for incoming HTTP requests at -httpListenAddr (aka https). -tlsCertFile and -tlsKeyFile must be set if -tls is set
   -tlsCertFile string

app/vmauth/auth_config.go

@@ -11,8 +11,10 @@ import (
 	"strings"
 	"sync"
 	"sync/atomic"
+	"time"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/envtemplate"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/fasttime"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/fs"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/procutil"
@@ -23,6 +25,8 @@ import (
 var (
 	authConfigPath = flag.String("auth.config", "", "Path to auth config. It can point either to local file or to http url. "+
 		"See https://docs.victoriametrics.com/vmauth.html for details on the format of this auth config")
+	configCheckInterval = flag.Duration("configCheckInterval", 0, "interval for config file re-read. "+
+		"Zero value disables config re-reading. By default, refreshing is disabled, send SIGHUP for config refresh.")
 )
 
 // AuthConfig represents auth config.
@@ -32,17 +36,43 @@ type AuthConfig struct {
 
 // UserInfo is user information read from authConfigPath
 type UserInfo struct {
-	Name        string     `yaml:"name,omitempty"`
-	BearerToken string     `yaml:"bearer_token,omitempty"`
-	Username    string     `yaml:"username,omitempty"`
-	Password    string     `yaml:"password,omitempty"`
-	URLPrefix   *URLPrefix `yaml:"url_prefix,omitempty"`
-	URLMap      []URLMap   `yaml:"url_map,omitempty"`
-	Headers     []Header   `yaml:"headers,omitempty"`
+	Name                  string     `yaml:"name,omitempty"`
+	BearerToken           string     `yaml:"bearer_token,omitempty"`
+	Username              string     `yaml:"username,omitempty"`
+	Password              string     `yaml:"password,omitempty"`
+	URLPrefix             *URLPrefix `yaml:"url_prefix,omitempty"`
+	URLMaps               []URLMap   `yaml:"url_map,omitempty"`
+	Headers               []Header   `yaml:"headers,omitempty"`
+	MaxConcurrentRequests int        `yaml:"max_concurrent_requests,omitempty"`
+
+	concurrencyLimitCh      chan struct{}
+	concurrencyLimitReached *metrics.Counter
 
 	requests *metrics.Counter
 }
 
+func (ui *UserInfo) beginConcurrencyLimit() error {
+	select {
+	case ui.concurrencyLimitCh <- struct{}{}:
+		return nil
+	default:
+		ui.concurrencyLimitReached.Inc()
+		return fmt.Errorf("cannot handle more than %d concurrent requests from user %s", ui.getMaxConcurrentRequests(), ui.name())
+	}
+}
+
+func (ui *UserInfo) endConcurrencyLimit() {
+	<-ui.concurrencyLimitCh
+}
+
+func (ui *UserInfo) getMaxConcurrentRequests() int {
+	mcr := ui.MaxConcurrentRequests
+	if mcr <= 0 {
+		mcr = *maxConcurrentPerUserRequests
+	}
+	return mcr
+}
+
 // Header is `Name: Value` http header, which must be added to the proxied request.
 type Header struct {
 	Name  string
@@ -83,16 +113,77 @@ type SrcPath struct {
 	re        *regexp.Regexp
 }
 
-// URLPrefix represents pased `url_prefix`
+// URLPrefix represents passed `url_prefix`
 type URLPrefix struct {
-	n    uint32
-	urls []*url.URL
+	n   uint32
+	bus []*backendURL
 }
 
-func (up *URLPrefix) getNextURL() *url.URL {
+type backendURL struct {
+	brokenDeadline     uint64
+	concurrentRequests int32
+	url                *url.URL
+}
+
+func (bu *backendURL) isBroken() bool {
+	ct := fasttime.UnixTimestamp()
+	return ct < atomic.LoadUint64(&bu.brokenDeadline)
+}
+
+func (bu *backendURL) setBroken() {
+	deadline := fasttime.UnixTimestamp() + 3
+	atomic.StoreUint64(&bu.brokenDeadline, deadline)
+}
+
+func (bu *backendURL) put() {
+	atomic.AddInt32(&bu.concurrentRequests, -1)
+}
+
+func (up *URLPrefix) getBackendsCount() int {
+	return len(up.bus)
+}
+
+// getLeastLoadedBackendURL returns the backendURL with the minimum number of concurrent requests.
+//
+// backendURL.put() must be called on the returned backendURL after the request is complete.
+func (up *URLPrefix) getLeastLoadedBackendURL() *backendURL {
+	bus := up.bus
+	if len(bus) == 1 {
+		// Fast path - return the only backend url.
+		bu := bus[0]
+		atomic.AddInt32(&bu.concurrentRequests, 1)
+		return bu
+	}
+
+	// Slow path - select other backend urls.
 	n := atomic.AddUint32(&up.n, 1)
-	idx := n % uint32(len(up.urls))
-	return up.urls[idx]
+
+	for i := uint32(0); i < uint32(len(bus)); i++ {
+		idx := (n + i) % uint32(len(bus))
+		bu := bus[idx]
+		if bu.isBroken() {
+			continue
+		}
+		if atomic.CompareAndSwapInt32(&bu.concurrentRequests, 0, 1) {
+			// Fast path - return the backend with zero concurrently executed requests.
+			return bu
+		}
+	}
+
+	// Slow path - return the backend with the minimum number of concurrently executed requests.
+	buMin := bus[n%uint32(len(bus))]
+	minRequests := atomic.LoadInt32(&buMin.concurrentRequests)
+	for _, bu := range bus {
+		if bu.isBroken() {
+			continue
+		}
+		if n := atomic.LoadInt32(&bu.concurrentRequests); n < minRequests {
+			buMin = bu
+			minRequests = n
+		}
+	}
+	atomic.AddInt32(&buMin.concurrentRequests, 1)
+	return buMin
 }
 
 // UnmarshalYAML unmarshals up from yaml.
@@ -121,31 +212,33 @@ func (up *URLPrefix) UnmarshalYAML(f func(interface{}) error) error {
 	default:
 		return fmt.Errorf("unexpected type for `url_prefix`: %T; want string or []string", v)
 	}
-	pus := make([]*url.URL, len(urls))
+	bus := make([]*backendURL, 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
+		bus[i] = &backendURL{
+			url: pu,
+		}
 	}
-	up.urls = pus
+	up.bus = bus
 	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()
+	if len(up.bus) == 1 {
+		u := up.bus[0].url.String()
 		b = strconv.AppendQuote(b, u)
 		return string(b), nil
 	}
 	b = append(b, '[')
-	for i, pu := range up.urls {
-		u := pu.String()
+	for i, bu := range up.bus {
+		u := bu.url.String()
 		b = strconv.AppendQuote(b, u)
-		if i+1 < len(up.urls) {
+		if i+1 < len(up.bus) {
 			b = append(b, ',')
 		}
 	}
@@ -215,10 +308,20 @@ func stopAuthConfig() {
 }
 
 func authConfigReloader(sighupCh <-chan os.Signal) {
+	var refreshCh <-chan time.Time
+	// initialize auth refresh interval
+	if *configCheckInterval > 0 {
+		ticker := time.NewTicker(*configCheckInterval)
+		defer ticker.Stop()
+		refreshCh = ticker.C
+	}
+
 	for {
 		select {
 		case <-stopCh:
 			return
+		case <-refreshCh:
+			procutil.SelfSIGHUP()
 		case <-sighupCh:
 			logger.Infof("SIGHUP received; loading -auth.config=%q", *authConfigPath)
 			m, err := readAuthConfig(*authConfigPath)
@@ -284,7 +387,7 @@ func parseAuthConfig(data []byte) (map[string]*UserInfo, error) {
 				return nil, err
 			}
 		}
-		for _, e := range ui.URLMap {
+		for _, e := range ui.URLMaps {
 			if len(e.SrcPaths) == 0 {
 				return nil, fmt.Errorf("missing `src_paths` in `url_map`")
 			}
@@ -295,32 +398,47 @@ func parseAuthConfig(data []byte) (map[string]*UserInfo, error) {
 				return nil, err
 			}
 		}
-		if len(ui.URLMap) == 0 && ui.URLPrefix == nil {
+		if len(ui.URLMaps) == 0 && ui.URLPrefix == nil {
 			return nil, fmt.Errorf("missing `url_prefix`")
 		}
+		name := ui.name()
 		if ui.BearerToken != "" {
-			name := "bearer_token"
-			if ui.Name != "" {
-				name = ui.Name
-			}
 			if ui.Password != "" {
 				return nil, fmt.Errorf("password shouldn't be set for bearer_token %q", ui.BearerToken)
 			}
 			ui.requests = metrics.GetOrCreateCounter(fmt.Sprintf(`vmauth_user_requests_total{username=%q}`, name))
 		}
 		if ui.Username != "" {
-			name := ui.Username
-			if ui.Name != "" {
-				name = ui.Name
-			}
 			ui.requests = metrics.GetOrCreateCounter(fmt.Sprintf(`vmauth_user_requests_total{username=%q}`, name))
 		}
+		mcr := ui.getMaxConcurrentRequests()
+		ui.concurrencyLimitCh = make(chan struct{}, mcr)
+		ui.concurrencyLimitReached = metrics.GetOrCreateCounter(fmt.Sprintf(`vmauth_user_concurrent_requests_limit_reached_total{username=%q}`, name))
+		_ = metrics.GetOrCreateGauge(fmt.Sprintf(`vmauth_user_concurrent_requests_capacity{username=%q}`, name), func() float64 {
+			return float64(cap(ui.concurrencyLimitCh))
+		})
+		_ = metrics.GetOrCreateGauge(fmt.Sprintf(`vmauth_user_concurrent_requests_current{username=%q}`, name), func() float64 {
+			return float64(len(ui.concurrencyLimitCh))
+		})
 		byAuthToken[at1] = ui
 		byAuthToken[at2] = ui
 	}
 	return byAuthToken, nil
 }
 
+func (ui *UserInfo) name() string {
+	if ui.Name != "" {
+		return ui.Name
+	}
+	if ui.Username != "" {
+		return ui.Username
+	}
+	if ui.BearerToken != "" {
+		return "bearer_token"
+	}
+	return ""
+}
+
 func getAuthTokens(bearerToken, username, password string) (string, string) {
 	if bearerToken != "" {
 		// Accept the bearerToken as Basic Auth username with empty password
@@ -342,12 +460,12 @@ func getAuthToken(bearerToken, username, password string) string {
 }
 
 func (up *URLPrefix) sanitize() error {
-	for i, pu := range up.urls {
-		puNew, err := sanitizeURLPrefix(pu)
+	for _, bu := range up.bus {
+		puNew, err := sanitizeURLPrefix(bu.url)
 		if err != nil {
 			return err
 		}
-		up.urls[i] = puNew
+		bu.url = puNew
 	}
 	return nil
 }

app/vmauth/auth_config_test.go

@@ -218,11 +218,13 @@ users:
 - username: foo
   password: bar
   url_prefix: http://aaa:343/bbb
+  max_concurrent_requests: 5
 `, map[string]*UserInfo{
 		getAuthToken("", "foo", "bar"): {
-			Username:  "foo",
-			Password:  "bar",
-			URLPrefix: mustParseURL("http://aaa:343/bbb"),
+			Username:              "foo",
+			Password:              "bar",
+			URLPrefix:             mustParseURL("http://aaa:343/bbb"),
+			MaxConcurrentRequests: 5,
 		},
 	})
 
@@ -278,7 +280,7 @@ users:
 `, map[string]*UserInfo{
 		getAuthToken("foo", "", ""): {
 			BearerToken: "foo",
-			URLMap: []URLMap{
+			URLMaps: []URLMap{
 				{
 					SrcPaths:  getSrcPaths([]string{"/api/v1/query", "/api/v1/query_range", "/api/v1/label/[^./]+/.+"}),
 					URLPrefix: mustParseURL("http://vmselect/select/0/prometheus"),
@@ -304,7 +306,7 @@ users:
 		},
 		getAuthToken("", "foo", ""): {
 			BearerToken: "foo",
-			URLMap: []URLMap{
+			URLMaps: []URLMap{
 				{
 					SrcPaths:  getSrcPaths([]string{"/api/v1/query", "/api/v1/query_range", "/api/v1/label/[^./]+/.+"}),
 					URLPrefix: mustParseURL("http://vmselect/select/0/prometheus"),
@@ -390,15 +392,17 @@ func mustParseURL(u string) *URLPrefix {
 }
 
 func mustParseURLs(us []string) *URLPrefix {
-	pus := make([]*url.URL, len(us))
+	bus := make([]*backendURL, 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
+		bus[i] = &backendURL{
+			url: pu,
+		}
 	}
 	return &URLPrefix{
-		urls: pus,
+		bus: bus,
 	}
 }

app/vmauth/example_config.yml

@@ -18,26 +18,27 @@ users:
   headers:
   - "X-Scope-OrgID: foobar"
 
-  # The user for querying local single-node VictoriaMetrics.
   # All the requests to http://vmauth:8427 with the given Basic Auth (username:password)
-  # will be proxied to http://localhost:8428 .
+  # are proxied to http://localhost:8428 .
   # For example, http://vmauth:8427/api/v1/query is proxied to http://localhost:8428/api/v1/query
+  #
+  # The given user can send maximum 10 concurrent requests according to the provided max_concurrent_requests.
+  # Excess concurrent requests are rejected with 429 HTTP status code.
+  # See also -maxConcurrentPerUserRequests and -maxConcurrentRequests command-line flags.
 - username: "local-single-node"
   password: "***"
   url_prefix: "http://localhost:8428"
+  max_concurrent_requests: 10
 
-  # 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://localhost:8428 with extra_label=team=dev query arg.
+  # are proxied 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"
+- username: "local-single-node2"
   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
+  # are 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
@@ -47,10 +48,8 @@ users:
   - "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://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
+  # are 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

app/vmauth/main.go

@@ -3,8 +3,10 @@ package main
 import (
 	"flag"
 	"fmt"
+	"io"
+	"net"
 	"net/http"
-	"net/http/httputil"
+	"net/textproto"
 	"net/url"
 	"os"
 	"strings"
@@ -12,20 +14,32 @@ import (
 	"time"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/buildinfo"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/envflag"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/netutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/procutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/pushmetrics"
 	"github.com/VictoriaMetrics/metrics"
 )
 
 var (
-	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. "+
+	httpListenAddr   = flag.String("httpListenAddr", ":8427", "TCP address to listen for http connections. See also -httpListenAddr.useProxyProtocol")
+	useProxyProtocol = flag.Bool("httpListenAddr.useProxyProtocol", false, "Whether to use proxy protocol for connections accepted at -httpListenAddr . "+
+		"See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt . "+
+		"With enabled proxy protocol http server cannot serve regular /metrics endpoint. Use -pushmetrics.url for metrics pushing")
+	maxIdleConnsPerBackend = flag.Int("maxIdleConnsPerBackend", 100, "The maximum number of idle connections vmauth can open per each backend host. "+
+		"See also -maxConcurrentRequests")
+	responseTimeout       = flag.Duration("responseTimeout", 5*time.Minute, "The timeout for receiving a response from backend")
+	maxConcurrentRequests = flag.Int("maxConcurrentRequests", 1000, "The maximum number of concurrent requests vmauth can process. Other requests are rejected with "+
+		"'429 Too Many Requests' http status code. See also -maxConcurrentPerUserRequests and -maxIdleConnsPerBackend command-line options")
+	maxConcurrentPerUserRequests = flag.Int("maxConcurrentPerUserRequests", 300, "The maximum number of concurrent requests vmauth can process per each configured user. "+
+		"Other requests are rejected with '429 Too Many Requests' http status code. See also -maxConcurrentRequests command-line option and max_concurrent_requests option "+
+		"in per-user config")
+	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 vmauth_http_request_errors_total{reason="invalid_auth_token"} metric, which is exposed at /metrics page`)
 )
 
@@ -41,7 +55,7 @@ func main() {
 	logger.Infof("starting vmauth at %q...", *httpListenAddr)
 	startTime := time.Now()
 	initAuthConfig()
-	go httpserver.Serve(*httpListenAddr, requestHandler)
+	go httpserver.Serve(*httpListenAddr, *useProxyProtocol, requestHandler)
 	logger.Infof("started vmauth in %.3f seconds", time.Since(startTime).Seconds())
 
 	sig := procutil.WaitForSigterm()
@@ -60,9 +74,7 @@ func main() {
 func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 	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)
+		if !httpserver.CheckAuthFlag(w, r, *reloadAuthKey, "reloadAuthKey") {
 			return true
 		}
 		configReloadRequests.Inc()
@@ -81,44 +93,175 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 		// See https://docs.influxdata.com/influxdb/v2.0/api/
 		authToken = strings.Replace(authToken, "Token", "Bearer", 1)
 	}
+
 	ac := authConfig.Load().(map[string]*UserInfo)
 	ui := ac[authToken]
 	if ui == nil {
 		invalidAuthTokenRequests.Inc()
+		err := fmt.Errorf("cannot find the provided auth token %q in config", authToken)
 		if *logInvalidAuthTokens {
-			httpserver.Errorf(w, r, "cannot find the provided auth token %q in config", authToken)
+			err = &httpserver.ErrorWithStatusCode{
+				Err:        err,
+				StatusCode: http.StatusUnauthorized,
+			}
+			httpserver.Errorf(w, r, "%s", err)
 		} else {
-			errStr := fmt.Sprintf("cannot find the provided auth token %q in config", authToken)
-			http.Error(w, errStr, http.StatusBadRequest)
+			http.Error(w, err.Error(), http.StatusUnauthorized)
 		}
 		return true
 	}
 	ui.requests.Inc()
-	targetURL, headers, err := createTargetURL(ui, r.URL)
-	if err != nil {
-		httpserver.Errorf(w, r, "cannot determine targetURL: %s", err)
+
+	// Limit the concurrency of requests to backends
+	concurrencyLimitOnce.Do(concurrencyLimitInit)
+	select {
+	case concurrencyLimitCh <- struct{}{}:
+		if err := ui.beginConcurrencyLimit(); err != nil {
+			handleConcurrencyLimitError(w, r, err)
+			<-concurrencyLimitCh
+			return true
+		}
+	default:
+		concurrentRequestsLimitReached.Inc()
+		err := fmt.Errorf("cannot serve more than -maxConcurrentRequests=%d concurrent requests", cap(concurrencyLimitCh))
+		handleConcurrencyLimitError(w, r, err)
 		return true
 	}
-	r.Header.Set("vm-target-url", targetURL.String())
-	for _, h := range headers {
-		r.Header.Set(h.Name, h.Value)
-	}
-	proxyRequest(w, r)
+	processRequest(w, r, ui)
+	ui.endConcurrencyLimit()
+	<-concurrencyLimitCh
 	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
+func processRequest(w http.ResponseWriter, r *http.Request, ui *UserInfo) {
+	u := normalizeURL(r.URL)
+	up, headers, err := ui.getURLPrefixAndHeaders(u)
+	if err != nil {
+		httpserver.Errorf(w, r, "cannot determine targetURL: %s", err)
+		return
+	}
+	maxAttempts := up.getBackendsCount()
+	for i := 0; i < maxAttempts; i++ {
+		bu := up.getLeastLoadedBackendURL()
+		targetURL := mergeURLs(bu.url, u)
+		ok := tryProcessingRequest(w, r, targetURL, headers)
+		bu.put()
+		if ok {
 			return
 		}
-		// Forward other panics to the caller.
-		panic(err)
-	}()
-	getReverseProxy().ServeHTTP(w, r)
+		bu.setBroken()
+	}
+	err = &httpserver.ErrorWithStatusCode{
+		Err:        fmt.Errorf("all the backends for the user %q are unavailable", ui.name()),
+		StatusCode: http.StatusServiceUnavailable,
+	}
+	httpserver.Errorf(w, r, "%s", err)
+}
+
+func tryProcessingRequest(w http.ResponseWriter, r *http.Request, targetURL *url.URL, headers []Header) bool {
+	// This code has been copied from net/http/httputil/reverseproxy.go
+	req := sanitizeRequestHeaders(r)
+	req.URL = targetURL
+	for _, h := range headers {
+		req.Header.Set(h.Name, h.Value)
+	}
+	transportOnce.Do(transportInit)
+	res, err := transport.RoundTrip(req)
+	if err != nil {
+		remoteAddr := httpserver.GetQuotedRemoteAddr(r)
+		requestURI := httpserver.GetRequestURI(r)
+		if r.Method == http.MethodPost || r.Method == http.MethodPut {
+			// It is impossible to retry POST and PUT requests,
+			// since we already proxied the request body to the backend.
+			err = &httpserver.ErrorWithStatusCode{
+				Err:        fmt.Errorf("cannot proxy the request to %q: %w", targetURL, err),
+				StatusCode: http.StatusServiceUnavailable,
+			}
+			httpserver.Errorf(w, r, "%s", err)
+			return true
+		}
+		logger.Warnf("remoteAddr: %s; requestURI: %s; error when proxying the request to %q: %s", remoteAddr, requestURI, targetURL, err)
+		return false
+	}
+	removeHopHeaders(res.Header)
+	copyHeader(w.Header(), res.Header)
+	w.WriteHeader(res.StatusCode)
+
+	copyBuf := copyBufPool.Get()
+	copyBuf.B = bytesutil.ResizeNoCopyNoOverallocate(copyBuf.B, 16*1024)
+	_, err = io.CopyBuffer(w, res.Body, copyBuf.B)
+	copyBufPool.Put(copyBuf)
+	_ = res.Body.Close()
+	if err != nil && !netutil.IsTrivialNetworkError(err) {
+		remoteAddr := httpserver.GetQuotedRemoteAddr(r)
+		requestURI := httpserver.GetRequestURI(r)
+		logger.Warnf("remoteAddr: %s; requestURI: %s; error when proxying response body from %s: %s", remoteAddr, requestURI, targetURL, err)
+		return true
+	}
+	return true
+}
+
+var copyBufPool bytesutil.ByteBufferPool
+
+func copyHeader(dst, src http.Header) {
+	for k, vv := range src {
+		for _, v := range vv {
+			dst.Add(k, v)
+		}
+	}
+}
+
+func sanitizeRequestHeaders(r *http.Request) *http.Request {
+	// This code has been copied from net/http/httputil/reverseproxy.go
+	req := r.Clone(r.Context())
+	removeHopHeaders(req.Header)
+	if clientIP, _, err := net.SplitHostPort(req.RemoteAddr); err == nil {
+		// If we aren't the first proxy retain prior
+		// X-Forwarded-For information as a comma+space
+		// separated list and fold multiple headers into one.
+		prior := req.Header["X-Forwarded-For"]
+		if len(prior) > 0 {
+			clientIP = strings.Join(prior, ", ") + ", " + clientIP
+		}
+		req.Header.Set("X-Forwarded-For", clientIP)
+	}
+	return req
+}
+
+func removeHopHeaders(h http.Header) {
+	// remove hop-by-hop headers listed in the "Connection" header of h.
+	// See RFC 7230, section 6.1
+	for _, f := range h["Connection"] {
+		for _, sf := range strings.Split(f, ",") {
+			if sf = textproto.TrimString(sf); sf != "" {
+				h.Del(sf)
+			}
+		}
+	}
+
+	// Remove hop-by-hop headers to the backend. Especially
+	// important is "Connection" because we want a persistent
+	// connection, regardless of what the client sent to us.
+	for _, key := range hopHeaders {
+		h.Del(key)
+	}
+}
+
+// Hop-by-hop headers. These are removed when sent to the backend.
+// As of RFC 7230, hop-by-hop headers are required to appear in the
+// Connection header field. These are the headers defined by the
+// obsoleted RFC 2616 (section 13.5.1) and are used for backward
+// compatibility.
+var hopHeaders = []string{
+	"Connection",
+	"Proxy-Connection", // non-standard but still sent by libcurl and rejected by e.g. google
+	"Keep-Alive",
+	"Proxy-Authenticate",
+	"Proxy-Authorization",
+	"Te",      // canonicalized version of "TE"
+	"Trailer", // not Trailers per URL above; https://www.rfc-editor.org/errata_search.php?eid=4522
+	"Transfer-Encoding",
+	"Upgrade",
 }
 
 var (
@@ -128,43 +271,41 @@ var (
 )
 
 var (
-	reverseProxy     *httputil.ReverseProxy
-	reverseProxyOnce sync.Once
+	transport     *http.Transport
+	transportOnce sync.Once
 )
 
-func getReverseProxy() *httputil.ReverseProxy {
-	reverseProxyOnce.Do(initReverseProxy)
-	return reverseProxy
+func transportInit() {
+	tr := http.DefaultTransport.(*http.Transport).Clone()
+	tr.ResponseHeaderTimeout = *responseTimeout
+	// Automatic compression must be disabled in order to fix https://github.com/VictoriaMetrics/VictoriaMetrics/issues/535
+	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
+	if tr.MaxIdleConns != 0 && tr.MaxIdleConns < tr.MaxIdleConnsPerHost {
+		tr.MaxIdleConns = tr.MaxIdleConnsPerHost
+	}
+	transport = tr
 }
 
-// initReverseProxy must be called after flag.Parse(), since it uses command-line flags.
-func initReverseProxy() {
-	reverseProxy = &httputil.ReverseProxy{
-		Director: func(r *http.Request) {
-			targetURL := r.Header.Get("vm-target-url")
-			target, err := url.Parse(targetURL)
-			if err != nil {
-				logger.Panicf("BUG: unexpected error when parsing targetURL=%q: %s", targetURL, err)
-			}
-			r.URL = target
-		},
-		Transport: func() *http.Transport {
-			tr := http.DefaultTransport.(*http.Transport).Clone()
-			// Automatic compression must be disabled in order to fix https://github.com/VictoriaMetrics/VictoriaMetrics/issues/535
-			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
-			if tr.MaxIdleConns != 0 && tr.MaxIdleConns < tr.MaxIdleConnsPerHost {
-				tr.MaxIdleConns = tr.MaxIdleConnsPerHost
-			}
-			return tr
-		}(),
-		FlushInterval: time.Second,
-		ErrorLog:      logger.StdErrorLogger(),
-	}
+var (
+	concurrencyLimitCh   chan struct{}
+	concurrencyLimitOnce sync.Once
+)
+
+func concurrencyLimitInit() {
+	concurrencyLimitCh = make(chan struct{}, *maxConcurrentRequests)
+	_ = metrics.NewGauge("vmauth_concurrent_requests_capacity", func() float64 {
+		return float64(*maxConcurrentRequests)
+	})
+	_ = metrics.NewGauge("vmauth_concurrent_requests_current", func() float64 {
+		return float64(len(concurrencyLimitCh))
+	})
 }
 
+var concurrentRequestsLimitReached = metrics.NewCounter("vmauth_concurrent_requests_limit_reached_total")
+
 func usage() {
 	const s = `
 vmauth authenticates and authorizes incoming requests and proxies them to VictoriaMetrics.
@@ -173,3 +314,12 @@ See the docs at https://docs.victoriametrics.com/vmauth.html .
 `
 	flagutil.Usage(s)
 }
+
+func handleConcurrencyLimitError(w http.ResponseWriter, r *http.Request, err error) {
+	w.Header().Add("Retry-After", "10")
+	err = &httpserver.ErrorWithStatusCode{
+		Err:        err,
+		StatusCode: http.StatusTooManyRequests,
+	}
+	httpserver.Errorf(w, r, "%s", err)
+}

app/vmauth/multiarch/Dockerfile

@@ -2,7 +2,7 @@
 ARG certs_image
 ARG root_image
 FROM $certs_image as certs
-RUN apk --update --no-cache add ca-certificates
+RUN apk update && apk upgrade && 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

app/vmauth/target_url.go

@@ -7,11 +7,6 @@ import (
 	"strings"
 )
 
-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
@@ -35,12 +30,27 @@ func mergeURLs(uiURL, requestURI *url.URL) *url.URL {
 	return &targetURL
 }
 
-func createTargetURL(ui *UserInfo, uOrig *url.URL) (*url.URL, []Header, error) {
+func (ui *UserInfo) getURLPrefixAndHeaders(u *url.URL) (*URLPrefix, []Header, error) {
+	for _, e := range ui.URLMaps {
+		for _, sp := range e.SrcPaths {
+			if sp.match(u.Path) {
+				return e.URLPrefix, e.Headers, nil
+			}
+		}
+	}
+	if ui.URLPrefix != nil {
+		return ui.URLPrefix, ui.Headers, nil
+	}
+	missingRouteRequests.Inc()
+	return nil, nil, fmt.Errorf("missing route for %q", u.String())
+}
+
+func normalizeURL(uOrig *url.URL) *url.URL {
 	u := *uOrig
 	// Prevent from attacks with using `..` in r.URL.Path
 	u.Path = path.Clean(u.Path)
 	if !strings.HasSuffix(u.Path, "/") && strings.HasSuffix(uOrig.Path, "/") {
-		// The path.Clean() removes traling slash.
+		// The path.Clean() removes trailing slash.
 		// Return it back if needed.
 		// This should fix https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1752
 		u.Path += "/"
@@ -52,16 +62,5 @@ func createTargetURL(ui *UserInfo, uOrig *url.URL) (*url.URL, []Header, error) {
 		// See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/1554
 		u.Path = ""
 	}
-	for _, e := range ui.URLMap {
-		for _, sp := range e.SrcPaths {
-			if sp.match(u.Path) {
-				return e.URLPrefix.mergeURLs(&u), e.Headers, nil
-			}
-		}
-	}
-	if ui.URLPrefix != nil {
-		return ui.URLPrefix.mergeURLs(&u), ui.Headers, nil
-	}
-	missingRouteRequests.Inc()
-	return nil, nil, fmt.Errorf("missing route for %q", u.String())
+	return &u
 }

app/vmauth/target_url_test.go

@@ -13,10 +13,14 @@ func TestCreateTargetURLSuccess(t *testing.T) {
 		if err != nil {
 			t.Fatalf("cannot parse %q: %s", requestURI, err)
 		}
-		target, headers, err := createTargetURL(ui, u)
+		u = normalizeURL(u)
+		up, headers, err := ui.getURLPrefixAndHeaders(u)
 		if err != nil {
 			t.Fatalf("unexpected error: %s", err)
 		}
+		bu := up.getLeastLoadedBackendURL()
+		target := mergeURLs(bu.url, u)
+		bu.put()
 		if target.String() != expectedTarget {
 			t.Fatalf("unexpected target; got %q; want %q", target, expectedTarget)
 		}
@@ -54,7 +58,7 @@ func TestCreateTargetURLSuccess(t *testing.T) {
 
 	// Complex routing with `url_map`
 	ui := &UserInfo{
-		URLMap: []URLMap{
+		URLMaps: []URLMap{
 			{
 				SrcPaths:  getSrcPaths([]string{"/api/v1/query"}),
 				URLPrefix: mustParseURL("http://vmselect/0/prometheus"),
@@ -86,7 +90,7 @@ func TestCreateTargetURLSuccess(t *testing.T) {
 
 	// Complex routing regexp paths in `url_map`
 	ui = &UserInfo{
-		URLMap: []URLMap{
+		URLMaps: []URLMap{
 			{
 				SrcPaths:  getSrcPaths([]string{"/api/v1/query(_range)?", "/api/v1/label/[^/]+/values"}),
 				URLPrefix: mustParseURL("http://vmselect/0/prometheus"),
@@ -119,20 +123,21 @@ func TestCreateTargetURLFailure(t *testing.T) {
 		if err != nil {
 			t.Fatalf("cannot parse %q: %s", requestURI, err)
 		}
-		target, headers, err := createTargetURL(ui, u)
+		u = normalizeURL(u)
+		up, headers, err := ui.getURLPrefixAndHeaders(u)
 		if err == nil {
 			t.Fatalf("expecting non-nil error")
 		}
-		if target != nil {
-			t.Fatalf("unexpected target=%q; want empty string", target)
+		if up != nil {
+			t.Fatalf("unexpected non-empty up=%#v", up)
 		}
 		if headers != nil {
-			t.Fatalf("unexpected headers=%q; want empty string", headers)
+			t.Fatalf("unexpected non-empty headers=%q", headers)
 		}
 	}
 	f(&UserInfo{}, "/foo/bar")
 	f(&UserInfo{
-		URLMap: []URLMap{
+		URLMaps: []URLMap{
 			{
 				SrcPaths:  getSrcPaths([]string{"/api/v1/query"}),
 				URLPrefix: mustParseURL("http://foobar/baz"),

app/vmbackup/Makefile

@@ -39,6 +39,9 @@ vmbackup-freebsd-amd64-prod:
 vmbackup-openbsd-amd64-prod:
 	APP_NAME=vmbackup $(MAKE) app-via-docker-openbsd-amd64
 
+vmbackup-windows-amd64-prod:
+	APP_NAME=vmbackup $(MAKE) app-via-docker-windows-amd64
+
 package-vmbackup:
 	APP_NAME=vmbackup $(MAKE) package-via-docker
 
@@ -75,6 +78,9 @@ vmbackup-linux-arm64:
 vmbackup-linux-ppc64le:
 	APP_NAME=vmbackup CGO_ENABLED=0 GOOS=linux GOARCH=ppc64le $(MAKE) app-local-goos-goarch
 
+vmbackup-linux-s390x:
+	APP_NAME=vmbackup CGO_ENABLED=0 GOOS=linux GOARCH=s390x $(MAKE) app-local-goos-goarch
+
 vmbackup-linux-386:
 	APP_NAME=vmbackup CGO_ENABLED=0 GOOS=linux GOARCH=386 $(MAKE) app-local-goos-goarch
 
@@ -90,5 +96,8 @@ vmbackup-freebsd-amd64:
 vmbackup-openbsd-amd64:
 	APP_NAME=vmbackup CGO_ENABLED=0 GOOS=openbsd GOARCH=amd64 $(MAKE) app-local-goos-goarch
 
+vmbackup-windows-amd64:
+	GOARCH=amd64 APP_NAME=vmbackup $(MAKE) app-local-windows-goarch
+
 vmbackup-pure:
 	APP_NAME=vmbackup $(MAKE) app-local-pure

app/vmbackup/README.md

@@ -21,7 +21,7 @@ creation of hourly, daily, weekly and monthly backups.
 
 * [GCS](https://cloud.google.com/storage/). Example: `gs://<bucket>/<path/to/backup>`
 * [S3](https://aws.amazon.com/s3/). Example: `s3://<bucket>/<path/to/backup>`
-* [Azure Blob Storage](https://azure.microsoft.com/en-us/products/storage/blobs/). Example: `azblob://<bucket>/<path/to/backup>`
+* [Azure Blob Storage](https://azure.microsoft.com/en-us/products/storage/blobs/). Example: `azblob://<container>/<path/to/backup>`
 * Any S3-compatible storage such as [MinIO](https://github.com/minio/minio), [Ceph](https://docs.ceph.com/en/pacific/radosgw/s3/) or [Swift](https://platform.swiftstack.com/docs/admin/middleware/s3_middleware.html). See [these docs](#advanced-usage) for details.
 * Local filesystem. Example: `fs://</absolute/path/to/backup>`. Note that `vmbackup` prevents from storing the backup into the directory pointed by `-storageDataPath` command-line flag, since this directory should be managed solely by VictoriaMetrics or `vmstorage`.
 
@@ -187,7 +187,7 @@ See [this article](https://medium.com/@valyala/speeding-up-backups-for-big-time-
   -customS3Endpoint string
      Custom S3 endpoint for use with S3-compatible storages (e.g. MinIO). S3 is used if not set
   -dst string
-     Where to put the backup on the remote storage. Example: gs://bucket/path/to/backup, s3://bucket/path/to/backup, azblob://bucket/path/to/backup or fs:///path/to/local/backup/dir
+     Where to put the backup on the remote storage. Example: gs://bucket/path/to/backup, s3://bucket/path/to/backup, azblob://container/path/to/backup 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
   -enableTCP6
      Whether to enable IPv6 for listening and dialing. By default only IPv4 TCP and UDP is used
@@ -225,6 +225,8 @@ See [this article](https://medium.com/@valyala/speeding-up-backups-for-big-time-
      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")
+  -loggerJSONFields string
+     Allows renaming fields in JSON formatted logs. Example: "ts:timestamp,msg:message" renames "ts" to "timestamp" and "msg" to "message". Supported fields: ts, level, caller, msg
   -loggerLevel string
      Minimum level of errors to log. Possible values: INFO, WARN, ERROR, FATAL, PANIC (default "INFO")
   -loggerOutput string
@@ -235,10 +237,10 @@ See [this article](https://medium.com/@valyala/speeding-up-backups-for-big-time-
      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 size values: KB, MB, GB, KiB, MiB, GiB (default 0)
+     Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB (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)
+     Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB (default 0)
   -memory.allowedPercent float
      Allowed percent of system memory VictoriaMetrics caches may occupy. See also -memory.allowedBytes. Too low a value may increase cache miss rate usually resulting in higher CPU and disk IO usage. Too high a value may evict too much data from OS page cache which will result in higher disk IO usage (default 60)
   -metricsAuthKey string

app/vmbackup/main.go

@@ -3,6 +3,7 @@ package main
 import (
 	"flag"
 	"fmt"
+	"net/url"
 	"os"
 	"path/filepath"
 	"strings"
@@ -30,7 +31,7 @@ var (
 	snapshotDeleteURL = flag.String("snapshot.deleteURL", "", "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")
 	dst = flag.String("dst", "", "Where to put the backup on the remote storage. "+
-		"Example: gs://bucket/path/to/backup, s3://bucket/path/to/backup, azblob://bucket/path/to/backup or fs:///path/to/local/backup/dir\n"+
+		"Example: gs://bucket/path/to/backup, s3://bucket/path/to/backup, azblob://container/path/to/backup 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")
 	origin            = flag.String("origin", "", "Optional origin directory on the remote storage with old backup for server-side copying when performing full backup. This speeds up full backups")
 	concurrency       = flag.Int("concurrency", 10, "The number of concurrent workers. Higher concurrency may reduce backup duration")
@@ -41,25 +42,42 @@ func main() {
 	// Write flags and help message to stdout, since it is easier to grep or pipe.
 	flag.CommandLine.SetOutput(os.Stdout)
 	flag.Usage = usage
+	flagutil.RegisterSecretFlag("snapshot.createURL")
+	flagutil.RegisterSecretFlag("snapshot.deleteURL")
 	envflag.Parse()
 	buildinfo.Init()
 	logger.Init()
 	pushmetrics.Init()
 
+	// Storing snapshot delete function to be able to call it in case
+	// of error since logger.Fatal will exit the program without
+	// calling deferred functions.
+	// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/2055
+	deleteSnapshot := func() {}
+
 	if len(*snapshotCreateURL) > 0 {
+		// create net/url object
+		createURL, err := url.Parse(*snapshotCreateURL)
+		if err != nil {
+			logger.Fatalf("cannot parse snapshotCreateURL: %s", err)
+		}
 		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)
+		logger.Infof("Snapshot create url %s", createURL.Redacted())
 		if len(*snapshotDeleteURL) <= 0 {
 			err := flag.Set("snapshot.deleteURL", strings.Replace(*snapshotCreateURL, "/create", "/delete", 1))
 			if err != nil {
 				logger.Fatalf("Failed to set snapshot.deleteURL flag: %v", err)
 			}
 		}
-		logger.Infof("Snapshot delete url %s", *snapshotDeleteURL)
+		deleteURL, err := url.Parse(*snapshotDeleteURL)
+		if err != nil {
+			logger.Fatalf("cannot parse snapshotDeleteURL: %s", err)
+		}
+		logger.Infof("Snapshot delete url %s", deleteURL.Redacted())
 
-		name, err := snapshot.Create(*snapshotCreateURL)
+		name, err := snapshot.Create(createURL.String())
 		if err != nil {
 			logger.Fatalf("cannot create snapshot: %s", err)
 		}
@@ -68,45 +86,23 @@ func main() {
 			logger.Fatalf("cannot set snapshotName flag: %v", err)
 		}
 
-		defer func() {
-			err := snapshot.Delete(*snapshotDeleteURL, name)
+		deleteSnapshot = func() {
+			err := snapshot.Delete(deleteURL.String(), name)
 			if err != nil {
 				logger.Fatalf("cannot delete snapshot: %s", err)
 			}
-		}()
+		}
 	} else if len(*snapshotName) == 0 {
 		logger.Fatalf("`-snapshotName` or `-snapshot.createURL` must be provided")
 	}
-	if err := snapshot.Validate(*snapshotName); err != nil {
-		logger.Fatalf("invalid -snapshotName=%q: %s", *snapshotName, err)
-	}
 
-	go httpserver.Serve(*httpListenAddr, nil)
+	go httpserver.Serve(*httpListenAddr, false, nil)
 
-	srcFS, err := newSrcFS()
+	err := makeBackup()
+	deleteSnapshot()
 	if err != nil {
-		logger.Fatalf("%s", err)
-	}
-	dstFS, err := newDstFS()
-	if err != nil {
-		logger.Fatalf("%s", err)
-	}
-	originFS, err := newOriginFS()
-	if err != nil {
-		logger.Fatalf("%s", err)
-	}
-	a := &actions.Backup{
-		Concurrency: *concurrency,
-		Src:         srcFS,
-		Dst:         dstFS,
-		Origin:      originFS,
-	}
-	if err := a.Run(); err != nil {
 		logger.Fatalf("cannot create backup: %s", err)
 	}
-	srcFS.MustStop()
-	dstFS.MustStop()
-	originFS.MustStop()
 
 	startTime := time.Now()
 	logger.Infof("gracefully shutting down http server for metrics at %q", *httpListenAddr)
@@ -116,9 +112,41 @@ func main() {
 	logger.Infof("successfully shut down http server for metrics in %.3f seconds", time.Since(startTime).Seconds())
 }
 
+func makeBackup() error {
+	if err := snapshot.Validate(*snapshotName); err != nil {
+		return fmt.Errorf("invalid -snapshotName=%q: %s", *snapshotName, err)
+	}
+
+	srcFS, err := newSrcFS()
+	if err != nil {
+		return err
+	}
+	dstFS, err := newDstFS()
+	if err != nil {
+		return err
+	}
+	originFS, err := newOriginFS()
+	if err != nil {
+		return err
+	}
+	a := &actions.Backup{
+		Concurrency: *concurrency,
+		Src:         srcFS,
+		Dst:         dstFS,
+		Origin:      originFS,
+	}
+	if err := a.Run(); err != nil {
+		return err
+	}
+	srcFS.MustStop()
+	dstFS.MustStop()
+	originFS.MustStop()
+	return nil
+}
+
 func usage() {
 	const s = `
-vmbackup performs backups for VictoriaMetrics data from instant snapshots to gcs, s3
+vmbackup performs backups for VictoriaMetrics data from instant snapshots to gcs, s3, azblob
 or local filesystem. Backed up data can be restored with vmrestore.
 
 See the docs at https://docs.victoriametrics.com/vmbackup.html .
@@ -145,7 +173,7 @@ func newSrcFS() (*fslocal.FS, error) {
 
 	fs := &fslocal.FS{
 		Dir:               snapshotPath,
-		MaxBytesPerSecond: maxBytesPerSecond.N,
+		MaxBytesPerSecond: maxBytesPerSecond.IntN(),
 	}
 	if err := fs.Init(); err != nil {
 		return nil, fmt.Errorf("cannot initialize fs: %w", err)