[metricsql] for subqueries fixed behavior of functions that use query time range in their logic (like start, end, and running_*), from now on when using in subqueries they respect time range from query parameters (#5794)

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -8,7 +8,7 @@ body:
         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/latest)
         and verify whether the bug is reproducible there.
-        It's also recommended to read the [troubleshooting docs](https://docs.victoriametrics.com/troubleshooting/) first.
+        It's also recommended to read the [troubleshooting docs](https://docs.victoriametrics.com/Troubleshooting.html) first.
   - type: textarea
     id: describe-the-bug
     attributes:
@@ -65,7 +65,7 @@ body:
         
         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/#monitoring)
+          * [monitoring for VictoriaMetrics cluster](https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html#monitoring)
     validations:
       required: false
   - type: textarea

.github/ISSUE_TEMPLATE/question.yml

@@ -24,9 +24,9 @@ body:
       label: Troubleshooting docs
       description: I am familiar with the following troubleshooting docs
       options:
-        - label: General - https://docs.victoriametrics.com/troubleshooting/
+        - label: General - https://docs.victoriametrics.com/Troubleshooting.html
           required: false
-        - label: vmagent - https://docs.victoriametrics.com/vmagent/#troubleshooting
-          required: false
-        - label: vmalert - https://docs.victoriametrics.com/vmalert/#troubleshooting
+        - label: vmagent - https://docs.victoriametrics.com/vmagent.html#troubleshooting
           required: false
+        - label: vmalert - https://docs.victoriametrics.com/vmalert.html#troubleshooting
+          required: false

.github/pull_request_template.md

@@ -1,9 +0,0 @@
-### Describe Your Changes
-
-Please provide a brief description of the changes you made. Be as specific as possible to help others understand the purpose and impact of your modifications.
-
-### Checklist
-
-The following checks are **mandatory**:
-
-- [ ] My change adheres [VictoriaMetrics contributing guidelines](https://docs.victoriametrics.com/contributing/).

.github/workflows/benchmark.yml

@@ -1,56 +0,0 @@
-name: benchmark
-on:
-  push:
-    branches:
-      - master
-      - cluster
-    paths-ignore:
-      - "docs/**"
-      - "**.md"
-      - "dashboards/**"
-      - "deployment/**.yml"
-  pull_request:
-    types:
-      - opened
-      - synchronize
-      - reopened
-      - labeled
-    branches:
-      - master
-      - cluster
-    paths-ignore:
-      - "docs/**"
-      - "**.md"
-      - "dashboards/**"
-      - "deployment/**.yml"
-permissions:
-  contents: read
-  packages: write
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  build-streamaggr-benchmark-image:
-    name: build
-    runs-on: ubuntu-latest
-    if: contains(github.event.pull_request.labels.*.name, 'streamaggr-benchmark')
-    steps:
-      - name: Code checkout
-        uses: actions/checkout@v4
-
-      - name: Login to GitHub Container Registry
-        uses: docker/login-action@v3
-        with:
-          registry: ghcr.io
-          username: ${{ github.actor }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Package VMAgent Docker image for benchmark
-        run: |
-          SKIP_SCRATCH_BUILD=true \
-          DOCKER_BUILD_OPTS='--cache-to type=gha,mode=max --cache-from type=gha' \
-          PKG_TAG=${{ github.event.pull_request.head.sha }} \
-          DOCKER_REGISTRY=ghcr.io \
-          TARGET_PLATFORM=linux/amd64 make publish-vmagent

.github/workflows/build.yml

@@ -1,54 +0,0 @@
-name: build
-
-on:
-  push:
-    branches:
-      - cluster
-      - master
-    paths:
-      - '**.go'
-      - '**/Dockerfile*' # The trailing * is for app/vmui/Dockerfile-*.
-      - '**/Makefile'
-  pull_request:
-    branches:
-      - cluster
-      - master
-    paths:
-      - '**.go'
-      - '**/Dockerfile*' # The trailing * is for app/vmui/Dockerfile-*.
-      - '**/Makefile'
-
-permissions:
-  contents: read
-
-concurrency:
-  cancel-in-progress: true
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
-
-jobs:
-  build:
-    name: Build
-    runs-on: ubuntu-latest
-    steps:
-      - name: Code checkout
-        uses: actions/checkout@v4
-
-      - name: Setup Go
-        id: go
-        uses: actions/setup-go@v5
-        with:
-          go-version: stable
-          cache: false
-
-      - name: Cache Go artifacts
-        uses: actions/cache@v4
-        with:
-          path: |
-            ~/.cache/go-build
-            ~/go/bin
-            ~/go/pkg/mod
-          key: go-artifacts-${{ runner.os }}-crossbuild-${{ steps.go.outputs.go-version }}-${{ hashFiles('go.sum', 'Makefile', 'app/**/Makefile') }}
-          restore-keys: go-artifacts-${{ runner.os }}-crossbuild-
-
-      - name: Run crossbuild
-        run: make crossbuild

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

@@ -1,62 +0,0 @@
-name: 'CodeQL Go'
-
-on:
-  push:
-    branches:
-      - cluster
-      - master
-    paths:
-      - '**.go'
-  pull_request:
-    branches:
-      - cluster
-      - master
-    paths:
-      - '**.go'
-
-concurrency:
-  cancel-in-progress: true
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
-
-jobs:
-  analyze:
-    name: Analyze
-    runs-on: ubuntu-latest
-    permissions:
-      actions: read
-      contents: read
-      security-events: write
-
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-
-      - name: Set up Go
-        id: go
-        uses: actions/setup-go@v5
-        with:
-          cache: false
-          go-version: stable
-
-      - name: Cache Go artifacts
-        uses: actions/cache@v4
-        with:
-          path: |
-            ~/.cache/go-build
-            ~/go/bin
-            ~/go/pkg/mod
-          key: go-artifacts-${{ runner.os }}-codeql-analyze-${{ steps.go.outputs.go-version }}-${{ hashFiles('go.sum', 'Makefile', 'app/**/Makefile') }}
-          restore-keys: go-artifacts-${{ runner.os }}-codeql-analyze-
-
-      - name: Initialize CodeQL
-        uses: github/codeql-action/init@v3
-        with:
-          languages: go
-
-      - name: Autobuild
-        uses: github/codeql-action/autobuild@v3
-
-      - name: Perform CodeQL Analysis
-        uses: github/codeql-action/analyze@v3
-        with:
-          category: 'language:go'

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

@@ -1,27 +1,22 @@
-name: 'CodeQL JS/TS'
+name: "CodeQL - JS"
 
 on:
   push:
-    branches:
-      - cluster
-      - master
+    branches: [master, cluster]
     paths:
-      - '**.js'
-      - '**.ts'
-      - '**.tsx'
+      - "**.js"
   pull_request:
-    branches:
-      - cluster
-      - master
+    # The branches below must be a subset of the branches above
+    branches: [master, cluster]
     paths:
-      - '**.js'
-      - '**.ts'
-      - '**.tsx'
+      - "**.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
@@ -31,6 +26,11 @@ jobs:
       contents: read
       security-events: write
 
+    strategy:
+      fail-fast: false
+      matrix:
+        language: ["javascript"]
+
     steps:
       - name: Checkout repository
         uses: actions/checkout@v4
@@ -38,9 +38,9 @@ jobs:
       - name: Initialize CodeQL
         uses: github/codeql-action/init@v3
         with:
-          languages: javascript-typescript
+          languages: ${{ matrix.language }}
 
       - name: Perform CodeQL Analysis
         uses: github/codeql-action/analyze@v3
         with:
-          category: 'language:js/ts'
+          category: "javascript"

.github/workflows/codeql-analysis.yml

@@ -0,0 +1,103 @@
+# For most projects, this workflow file will not need changing; you simply need
+# to commit it to your repository.
+#
+# You may wish to alter this file to override the set of languages analyzed,
+# or to provide custom queries or build logic.
+#
+# ******** NOTE ********
+# We have attempted to detect the languages in your repository. Please check
+# the `language` matrix defined below to confirm you have the correct set of
+# supported CodeQL languages.
+#
+name: "CodeQL"
+
+on:
+  push:
+    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]
+    paths-ignore:
+      - "docs/**"
+      - "**.md"
+      - "**.txt"
+      - "**.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: ["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@v4
+
+      - name: Set up Go
+        id: go
+        uses: actions/setup-go@v5
+        with:
+          go-version: stable
+          cache: false
+        if: ${{ matrix.language == 'go' }}
+
+      - name: Cache Go artifacts
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.cache/go-build
+            ~/go/pkg/mod
+            ~/go/bin
+          key: go-artifacts-${{ runner.os }}-codeql-analyze-${{ steps.go.outputs.go-version }}-${{ hashFiles('go.sum', 'Makefile', 'app/**/Makefile') }}
+          restore-keys: go-artifacts-${{ runner.os }}-codeql-analyze-
+        if: ${{ matrix.language == 'go' }}
+
+      # Initializes the CodeQL tools for scanning.
+      - name: Initialize CodeQL
+        uses: github/codeql-action/init@v3
+        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@v3
+
+      # 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
+
+      #- run: |
+      #   make bootstrap
+      #   make release
+
+      - name: Perform CodeQL Analysis
+        uses: github/codeql-action/analyze@v3

.github/workflows/main.yml

@@ -1,27 +1,29 @@
 name: main
-
 on:
   push:
     branches:
-      - cluster
       - master
-    paths:
-      - '.github/workflows/main.yml'
-      - '**.go'
+      - cluster
+    paths-ignore:
+      - "docs/**"
+      - "**.md"
+      - "dashboards/**"
+      - "deployment/**.yml"
   pull_request:
     branches:
-      - cluster
       - master
-    paths:
-      - '.github/workflows/main.yml'
-      - '**.go'
-
+      - cluster
+    paths-ignore:
+      - "docs/**"
+      - "**.md"
+      - "dashboards/**"
+      - "deployment/**.yml"
 permissions:
   contents: read
 
 concurrency:
-  cancel-in-progress: true
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
 
 jobs:
   lint:
@@ -35,51 +37,28 @@ jobs:
         id: go
         uses: actions/setup-go@v5
         with:
-          cache: false
           go-version: stable
+          cache: false
 
       - name: Cache Go artifacts
         uses: actions/cache@v4
         with:
           path: |
             ~/.cache/go-build
-            ~/go/bin
             ~/go/pkg/mod
+            ~/go/bin
           key: go-artifacts-${{ runner.os }}-check-all-${{ steps.go.outputs.go-version }}-${{ hashFiles('go.sum', 'Makefile', 'app/**/Makefile') }}
           restore-keys: go-artifacts-${{ runner.os }}-check-all-
 
-      - name: Run fmt
-        run: make fmt
+      - name: Run check-all
+        run: |
+          make check-all
+          git diff --exit-code
 
-      - name: Run vet
-        run: make vet
-      
-        # Use action instead of `make golangci-lint` to speed up the process
-        # as it caches data between builds.
-      - name: Run golangci-lint
-        uses: golangci/golangci-lint-action@v6
-        with:
-          # The version must match "install-golangci-lint" Makefile target version.
-          version: v1.59.1
-
-      - name: Run govulncheck
-        run: make govulncheck
-
-      - name: Check diff
-        run: git diff --exit-code
-
-  test:
-    name: test
+  build:
     needs: lint
+    name: build
     runs-on: ubuntu-latest
-
-    strategy:
-      matrix:
-        scenario:
-          - 'test-full'
-          - 'test-full-386'
-          - 'test-pure'
-
     steps:
       - name: Code checkout
         uses: actions/checkout@v4
@@ -88,20 +67,51 @@ jobs:
         id: go
         uses: actions/setup-go@v5
         with:
-          cache: false
           go-version: stable
+          cache: false
 
       - name: Cache Go artifacts
         uses: actions/cache@v4
         with:
           path: |
             ~/.cache/go-build
-            ~/go/bin
             ~/go/pkg/mod
+            ~/go/bin
+          key: go-artifacts-${{ runner.os }}-crossbuild-${{ steps.go.outputs.go-version }}-${{ hashFiles('go.sum', 'Makefile', 'app/**/Makefile') }}
+          restore-keys: go-artifacts-${{ runner.os }}-crossbuild-
+
+      - name: Build
+        run: make 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@v4
+
+      - name: Setup Go
+        id: go
+        uses: actions/setup-go@v5
+        with:
+          go-version: stable
+          cache: false
+
+      - name: Cache Go artifacts
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.cache/go-build
+            ~/go/pkg/mod
+            ~/go/bin
           key: go-artifacts-${{ runner.os }}-${{ matrix.scenario }}-${{ steps.go.outputs.go-version }}-${{ hashFiles('go.sum', 'Makefile', 'app/**/Makefile') }}
           restore-keys: go-artifacts-${{ runner.os }}-${{ matrix.scenario }}-
 
-      - name: Run tests
+      - name: run tests
         run: make ${{ matrix.scenario}}
 
       - name: Publish coverage

.github/workflows/sync-docs.yml

@@ -6,6 +6,9 @@ on:
     paths:
       - 'docs/**'
   workflow_dispatch: {}
+env:
+  PAGEFIND_VERSION: "1.0.4"
+  HUGO_VERSION: "latest"
 permissions:
   contents: read  # This is required for actions/checkout and to commit back image update
   deployments: write
@@ -24,8 +27,18 @@ jobs:
           repository: VictoriaMetrics/vmdocs
           token: ${{ secrets.VM_BOT_GH_TOKEN }}
           path: docs
+      - uses: peaceiris/actions-hugo@v2
+        with:
+          hugo-version: ${{env.HUGO_VERSION}}
+          extended: true
+      - name: Install PageFind #install the static search engine for index build
+        uses: supplypike/setup-bin@v3
+        with:
+          uri: "https://github.com/CloudCannon/pagefind/releases/download/v${{env.PAGEFIND_VERSION}}/pagefind-v${{env.PAGEFIND_VERSION}}-x86_64-unknown-linux-musl.tar.gz"
+          name: "pagefind"
+          version: ${{env.PAGEFIND_VERSION}}
       - name: Import GPG key
-        uses: crazy-max/ghaction-import-gpg@v6
+        uses: crazy-max/ghaction-import-gpg@v5
         with:
           gpg_private_key: ${{ secrets.VM_BOT_GPG_PRIVATE_KEY }}
           passphrase: ${{ secrets.VM_BOT_PASSPHRASE }}
@@ -38,11 +51,13 @@ jobs:
           calculatedSha=$(git rev-parse --short ${{ github.sha }})
           echo "short_sha=$calculatedSha" >> $GITHUB_OUTPUT
         working-directory: main
+
       - name: update code and commit
         run: |
           rm -rf content
           cp -r ../main/docs content
           make clean-after-copy
+          make build-search-index
           git config --global user.name "${{ steps.import-gpg.outputs.email }}"
           git config --global user.email "${{ steps.import-gpg.outputs.email }}"
           git add .

.github/workflows/wiki.yml

@@ -0,0 +1,33 @@
+name: wiki
+on:
+  push:
+    paths:
+      - 'docs/*'
+    branches:
+      - master
+permissions:
+  contents: read
+
+jobs:
+  build:
+    permissions:
+      contents: write  # for Git to git push
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@master
+      - name: publish
+        shell: bash
+        env:
+          TOKEN: ${{secrets.CI_TOKEN}}
+        run: |
+          git clone https://vika:${TOKEN}@github.com/VictoriaMetrics/VictoriaMetrics.wiki.git wiki
+          cp -r docs/* wiki
+          cd wiki
+          git config --local user.email "info@victoriametrics.com"
+          git config --local user.name "Vika"
+          git add .
+          git commit -m "update wiki pages"
+          remote_repo="https://vika:${TOKEN}@github.com/VictoriaMetrics/VictoriaMetrics.wiki.git"
+          git push "${remote_repo}"
+          cd ..
+          rm -rf wiki

.gitignore

@@ -22,5 +22,4 @@ Gemfile.lock
 /_site
 _site
 *.tmp
-/docs/.jekyll-metadata
-coverage.txt
+/docs/.jekyll-metadata

.golangci.yml

@@ -16,7 +16,4 @@ issues:
 
 linters-settings:
   errcheck:
-    exclude-functions:
-      - "fmt.Fprintf"
-      - "fmt.Fprint"
-      - "(net/http.ResponseWriter).Write"
+    exclude: ./errcheck_excludes.txt

CONTRIBUTING.md

@@ -1 +1,16 @@
-The document has been moved [here](https://docs.victoriametrics.com/contributing/).
+If you like VictoriaMetrics and want to contribute, then we need the following:
+
+- Filing issues and feature requests [here](https://github.com/VictoriaMetrics/VictoriaMetrics/issues).
+- Spreading a word about VictoriaMetrics: conference talks, articles, comments, experience sharing with colleagues.
+- Updating documentation.
+
+We are open to third-party pull requests provided they follow [KISS design principle](https://en.wikipedia.org/wiki/KISS_principle):
+
+- Prefer simple code and architecture.
+- Avoid complex abstractions.
+- Avoid magic code and fancy algorithms.
+- Avoid [big external dependencies](https://medium.com/@valyala/stripping-dependency-bloat-in-victoriametrics-docker-image-983fb5912b0d).
+- Minimize the number of moving parts in the distributed system.
+- Avoid automated decisions, which may hurt cluster availability, consistency or performance.
+
+Adhering `KISS` principle simplifies the resulting code and architecture, so it can be reviewed, understood and verified by many people.

Makefile

@@ -20,6 +20,7 @@ include app/*/Makefile
 include docs/Makefile
 include deployment/*/Makefile
 include dashboards/Makefile
+include snap/local/Makefile
 include package/release/Makefile
 
 all: \
@@ -439,8 +440,6 @@ vet:
 
 check-all: fmt vet golangci-lint govulncheck
 
-clean-checkers: remove-golangci-lint remove-govulncheck
-
 test:
 	go test ./lib/... ./app/...
 
@@ -493,11 +492,7 @@ golangci-lint: install-golangci-lint
 	golangci-lint run
 
 install-golangci-lint:
-	# The version must match GitHub main.yml lint job "Run golangci-lint" step version.
-	which golangci-lint || curl -sSfL https://raw.githubusercontent.com/golangci/golangci-lint/master/install.sh | sh -s -- -b $(shell go env GOPATH)/bin v1.59.1
-
-remove-golangci-lint:
-	rm -rf `which 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 v1.55.1
 
 govulncheck: install-govulncheck
 	govulncheck ./...
@@ -505,9 +500,6 @@ govulncheck: install-govulncheck
 install-govulncheck:
 	which govulncheck || go install golang.org/x/vuln/cmd/govulncheck@latest
 
-remove-govulncheck:
-	rm -rf `which govulncheck`
-
 install-wwhrd:
 	which wwhrd || go install github.com/frapposelli/wwhrd@latest
 

SECURITY.md

@@ -6,9 +6,9 @@ The following versions of VictoriaMetrics receive regular security fixes:
 
 | Version | Supported          |
 |---------|--------------------|
-| [latest release](https://docs.victoriametrics.com/changelog/) | :white_check_mark: |
-| v1.97.x [LTS line](https://docs.victoriametrics.com/lts-releases/) | :white_check_mark: |
-| v1.93.x [LTS line](https://docs.victoriametrics.com/lts-releases/) | :white_check_mark: |
+| [latest release](https://docs.victoriametrics.com/CHANGELOG.html) | :white_check_mark: |
+| v1.97.x [LTS line](https://docs.victoriametrics.com/LTS-releases.html) | :white_check_mark: |
+| v1.93.x [LTS line](https://docs.victoriametrics.com/LTS-releases.html) | :white_check_mark: |
 | other releases  | :x:                |
 
 See [this page](https://victoriametrics.com/security/) for more details.

app/victoria-logs/Makefile

@@ -101,10 +101,3 @@ victoria-logs-windows-amd64:
 
 victoria-logs-pure:
 	APP_NAME=victoria-logs $(MAKE) app-local-pure
-
-run-victoria-logs:
-	mkdir -p victoria-logs-data
-	DOCKER_OPTS='-v $(shell pwd)/victoria-logs-data:/victoria-logs-data' \
-	APP_NAME=victoria-logs \
-	ARGS='' \
-	$(MAKE) run-via-docker

app/victoria-logs/deployment/Dockerfile

@@ -1,7 +1,7 @@
 ARG base_image
 FROM $base_image
 
-EXPOSE 9428
+EXPOSE 8428
 
 ENTRYPOINT ["/victoria-logs-prod"]
 ARG src_binary

app/victoria-logs/main.go

@@ -47,7 +47,7 @@ func main() {
 	vlinsert.Init()
 
 	go httpserver.Serve(listenAddrs, useProxyProtocol, requestHandler)
-	logger.Infof("started VictoriaLogs in %.3f seconds; see https://docs.victoriametrics.com/victorialogs/", time.Since(startTime).Seconds())
+	logger.Infof("started VictoriaLogs in %.3f seconds; see https://docs.victoriametrics.com/VictoriaLogs/", time.Since(startTime).Seconds())
 
 	pushmetrics.Init()
 	sig := procutil.WaitForSigterm()
@@ -77,7 +77,7 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 		}
 		w.Header().Add("Content-Type", "text/html; charset=utf-8")
 		fmt.Fprintf(w, "<h2>Single-node VictoriaLogs</h2></br>")
-		fmt.Fprintf(w, "See docs at <a href='https://docs.victoriametrics.com/victorialogs/'>https://docs.victoriametrics.com/victorialogs/</a></br>")
+		fmt.Fprintf(w, "See docs at <a href='https://docs.victoriametrics.com/VictoriaLogs/'>https://docs.victoriametrics.com/VictoriaLogs/</a></br>")
 		fmt.Fprintf(w, "Useful endpoints:</br>")
 		httpserver.WriteAPIHelp(w, [][2]string{
 			{"select/vmui", "Web UI for VictoriaLogs"},
@@ -99,7 +99,7 @@ func usage() {
 	const s = `
 victoria-logs is a log management and analytics service.
 
-See the docs at https://docs.victoriametrics.com/victorialogs/
+See the docs at https://docs.victoriametrics.com/VictoriaLogs/
 `
 	flagutil.Usage(s)
 }

app/victoria-logs/multiarch/Dockerfile

@@ -1,12 +1,12 @@
 # See https://medium.com/on-docker/use-multi-stage-builds-to-inject-ca-certs-ad1e8f01de1b
 ARG certs_image
 ARG root_image
-FROM $certs_image AS certs
+FROM $certs_image as certs
 RUN apk update && apk upgrade && apk --update --no-cache add ca-certificates
 
 FROM $root_image
 COPY --from=certs /etc/ssl/certs/ca-certificates.crt /etc/ssl/certs/ca-certificates.crt
-EXPOSE 9428
+EXPOSE 8428
 ENTRYPOINT ["/victoria-logs-prod"]
 ARG TARGETARCH
 COPY victoria-logs-linux-${TARGETARCH}-prod ./victoria-logs-prod

app/victoria-metrics/Makefile

@@ -88,9 +88,6 @@ victoria-metrics-linux-ppc64le:
 victoria-metrics-linux-s390x:
 	APP_NAME=victoria-metrics CGO_ENABLED=0 GOOS=linux GOARCH=s390x $(MAKE) app-local-goos-goarch
 
-victoria-metrics-linux-loong64:
-	APP_NAME=victoria-metrics CGO_ENABLED=0 GOOS=linux GOARCH=loong64 $(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
 

app/victoria-metrics/main.go

@@ -31,7 +31,7 @@ var (
 		"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 also -streamAggr.dedupInterval and https://docs.victoriametrics.com/#deduplication")
+		"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 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")

app/victoria-metrics/main_test.go

@@ -39,13 +39,11 @@ const (
 )
 
 const (
-	testReadHTTPPath           = "http://127.0.0.1" + testHTTPListenAddr
-	testWriteHTTPPath          = "http://127.0.0.1" + testHTTPListenAddr + "/write"
-	testOpenTSDBWriteHTTPPath  = "http://127.0.0.1" + testOpenTSDBHTTPListenAddr + "/api/put"
-	testPromWriteHTTPPath      = "http://127.0.0.1" + testHTTPListenAddr + "/api/v1/write"
-	testImportCSVWriteHTTPPath = "http://127.0.0.1" + testHTTPListenAddr + "/api/v1/import/csv"
-
-	testHealthHTTPPath = "http://127.0.0.1" + testHTTPListenAddr + "/health"
+	testReadHTTPPath          = "http://127.0.0.1" + testHTTPListenAddr
+	testWriteHTTPPath         = "http://127.0.0.1" + testHTTPListenAddr + "/write"
+	testOpenTSDBWriteHTTPPath = "http://127.0.0.1" + testOpenTSDBHTTPListenAddr + "/api/put"
+	testPromWriteHTTPPath     = "http://127.0.0.1" + testHTTPListenAddr + "/api/v1/write"
+	testHealthHTTPPath        = "http://127.0.0.1" + testHTTPListenAddr + "/health"
 )
 
 const (
@@ -58,15 +56,14 @@ var (
 )
 
 type test struct {
-	Name                     string   `json:"name"`
-	Data                     []string `json:"data"`
-	InsertQuery              string   `json:"insert_query"`
-	Query                    []string `json:"query"`
-	ResultMetrics            []Metric `json:"result_metrics"`
-	ResultSeries             Series   `json:"result_series"`
-	ResultQuery              Query    `json:"result_query"`
-	Issue                    string   `json:"issue"`
-	ExpectedResultLinesCount int      `json:"expected_result_lines_count"`
+	Name          string   `json:"name"`
+	Data          []string `json:"data"`
+	InsertQuery   string   `json:"insert_query"`
+	Query         []string `json:"query"`
+	ResultMetrics []Metric `json:"result_metrics"`
+	ResultSeries  Series   `json:"result_series"`
+	ResultQuery   Query    `json:"result_query"`
+	Issue         string   `json:"issue"`
 }
 
 type Metric struct {
@@ -241,9 +238,8 @@ func tearDown() {
 
 func TestWriteRead(t *testing.T) {
 	t.Run("write", testWrite)
-	time.Sleep(500 * time.Millisecond)
 	vmstorage.Storage.DebugFlush()
-	time.Sleep(1500 * time.Millisecond)
+	time.Sleep(1 * time.Second)
 	t.Run("read", testRead)
 }
 
@@ -265,14 +261,6 @@ func testWrite(t *testing.T) {
 			httpWrite(t, testPromWriteHTTPPath, test.InsertQuery, bytes.NewBuffer(data))
 		}
 	})
-	t.Run("csv", func(t *testing.T) {
-		for _, test := range readIn("csv", t, insertionTime) {
-			if test.Data == nil {
-				continue
-			}
-			httpWrite(t, testImportCSVWriteHTTPPath, test.InsertQuery, bytes.NewBuffer([]byte(strings.Join(test.Data, "\n"))))
-		}
-	})
 
 	t.Run("influxdb", func(t *testing.T) {
 		for _, x := range readIn("influxdb", t, insertionTime) {
@@ -314,7 +302,7 @@ func testWrite(t *testing.T) {
 }
 
 func testRead(t *testing.T) {
-	for _, engine := range []string{"csv", "prometheus", "graphite", "opentsdb", "influxdb", "opentsdbhttp"} {
+	for _, engine := range []string{"prometheus", "graphite", "opentsdb", "influxdb", "opentsdbhttp"} {
 		t.Run(engine, func(t *testing.T) {
 			for _, x := range readIn(engine, t, insertionTime) {
 				test := x
@@ -325,12 +313,7 @@ func testRead(t *testing.T) {
 						if test.Issue != "" {
 							test.Issue = "\nRegression in " + test.Issue
 						}
-						switch {
-						case strings.HasPrefix(q, "/api/v1/export/csv"):
-							data := strings.Split(string(httpReadData(t, testReadHTTPPath, q)), "\n")
-							if len(data) == test.ExpectedResultLinesCount {
-								t.Fatalf("not expected number of csv lines want=%d\ngot=%d test=%s.%s\n\response=%q", len(data), test.ExpectedResultLinesCount, q, test.Issue, strings.Join(data, "\n"))
-							}
+						switch true {
 						case strings.HasPrefix(q, "/api/v1/export"):
 							if err := checkMetricsResult(httpReadMetrics(t, testReadHTTPPath, q), test.ResultMetrics); err != nil {
 								t.Fatalf("Export. %s fails with error %s.%s", q, err, test.Issue)
@@ -369,7 +352,7 @@ func readIn(readFor string, t *testing.T, insertTime time.Time) []test {
 	t.Helper()
 	s := newSuite(t)
 	var tt []test
-	s.noError(filepath.Walk(filepath.Join(testFixturesDir, readFor), func(path string, _ os.FileInfo, err error) error {
+	s.noError(filepath.Walk(filepath.Join(testFixturesDir, readFor), func(path string, info os.FileInfo, err error) error {
 		if err != nil {
 			return err
 		}
@@ -444,20 +427,6 @@ func httpReadStruct(t *testing.T, address, query string, dst interface{}) {
 	s.noError(json.NewDecoder(resp.Body).Decode(dst))
 }
 
-func httpReadData(t *testing.T, address, query string) []byte {
-	t.Helper()
-	s := newSuite(t)
-	resp, err := http.Get(address + query)
-	s.noError(err)
-	defer func() {
-		_ = resp.Body.Close()
-	}()
-	s.equalInt(resp.StatusCode, 200)
-	data, err := io.ReadAll(resp.Body)
-	s.noError(err)
-	return data
-}
-
 func checkMetricsResult(got, want []Metric) error {
 	for _, r := range append([]Metric(nil), got...) {
 		want = removeIfFoundMetrics(r, want)

app/victoria-metrics/multiarch/Dockerfile

@@ -1,7 +1,7 @@
 # See https://medium.com/on-docker/use-multi-stage-builds-to-inject-ca-certs-ad1e8f01de1b
 ARG certs_image
 ARG root_image
-FROM $certs_image AS certs
+FROM $certs_image as certs
 RUN apk update && apk upgrade && apk --update --no-cache add ca-certificates
 
 FROM $root_image

app/victoria-metrics/testdata/csv/basic.json

@@ -1,14 +0,0 @@
-{
-  "name": "csv export",
-  "data": [
-    "rfc3339,4,{TIME_MS}",
-    "rfc3339milli,6,{TIME_MS}",
-    "ts,8,{TIME_MS}",
-    "tsms,10,{TIME_MS},"
-  ],
-  "insert_query": "?format=1:label:tfmt,2:metric:test_csv,3:time:unix_ms",
-  "query": [
-    "/api/v1/export/csv?format=__name__,tfmt,__value__,__timestamp__:rfc3339&match[]={__name__=\"test_csv\"}&step=30s&start={TIME_MS-180s}"
-  ],
-  "expected_result_lines_count": 4
-}

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

@@ -1,14 +0,0 @@
-{
-  "name": "csv export with extra_labels",
-  "data": [
-    "location-1,4,{TIME_MS}",
-    "location-2,6,{TIME_MS}",
-    "location-3,8,{TIME_MS}",
-    "location-4,10,{TIME_MS},"
-  ],
-  "insert_query": "?format=1:label:location,2:metric:test_csv_labels,3:time:unix_ms&extra_label=location=location-1",
-  "query": [
-    "/api/v1/export/csv?format=__name__,location,__value__,__timestamp__:unix_ms&match[]={__name__=\"test_csv\"}&step=30s&start={TIME_MS-180s}"
-  ],
-  "expected_result_lines_count": 4
-}

app/vlinsert/elasticsearch/elasticsearch.go

@@ -20,6 +20,7 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logjson"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
@@ -97,10 +98,12 @@ func RequestHandler(path string, w http.ResponseWriter, r *http.Request) bool {
 			httpserver.Errorf(w, r, "%s", err)
 			return true
 		}
-		lmp := cp.NewLogMessageProcessor()
+		lr := logstorage.GetLogRows(cp.StreamFields, cp.IgnoreFields)
+		processLogMessage := cp.GetProcessLogMessageFunc(lr)
 		isGzip := r.Header.Get("Content-Encoding") == "gzip"
-		n, err := readBulkRequest(r.Body, isGzip, cp.TimeField, cp.MsgField, lmp)
-		lmp.MustClose()
+		n, err := readBulkRequest(r.Body, isGzip, cp.TimeField, cp.MsgField, processLogMessage)
+		vlstorage.MustAddRows(lr)
+		logstorage.PutLogRows(lr)
 		if err != nil {
 			logger.Warnf("cannot decode log message #%d in /_bulk request: %s, stream fields: %s", n, err, cp.StreamFields)
 			return true
@@ -129,7 +132,9 @@ var (
 	bulkRequestDuration = metrics.NewHistogram(`vl_http_request_duration_seconds{path="/insert/elasticsearch/_bulk"}`)
 )
 
-func readBulkRequest(r io.Reader, isGzip bool, timeField, msgField string, lmp insertutils.LogMessageProcessor) (int, error) {
+func readBulkRequest(r io.Reader, isGzip bool, timeField, msgField string,
+	processLogMessage func(timestamp int64, fields []logstorage.Field),
+) (int, error) {
 	// See https://www.elastic.co/guide/en/elasticsearch/reference/current/docs-bulk.html
 
 	if isGzip {
@@ -154,7 +159,7 @@ func readBulkRequest(r io.Reader, isGzip bool, timeField, msgField string, lmp i
 	n := 0
 	nCheckpoint := 0
 	for {
-		ok, err := readBulkLine(sc, timeField, msgField, lmp)
+		ok, err := readBulkLine(sc, timeField, msgField, processLogMessage)
 		wcr.DecConcurrency()
 		if err != nil || !ok {
 			rowsIngestedTotal.Add(n - nCheckpoint)
@@ -170,7 +175,9 @@ func readBulkRequest(r io.Reader, isGzip bool, timeField, msgField string, lmp i
 
 var lineBufferPool bytesutil.ByteBufferPool
 
-func readBulkLine(sc *bufio.Scanner, timeField, msgField string, lmp insertutils.LogMessageProcessor) (bool, error) {
+func readBulkLine(sc *bufio.Scanner, timeField, msgField string,
+	processLogMessage func(timestamp int64, fields []logstorage.Field),
+) (bool, error) {
 	var line []byte
 
 	// Read the command, must be "create" or "index"
@@ -203,7 +210,7 @@ func readBulkLine(sc *bufio.Scanner, timeField, msgField string, lmp insertutils
 		return false, fmt.Errorf(`missing log message after the "create" or "index" command`)
 	}
 	line = sc.Bytes()
-	p := logstorage.GetJSONParser()
+	p := logjson.GetParser()
 	if err := p.ParseLogMessage(line); err != nil {
 		return false, fmt.Errorf("cannot parse json-encoded log entry: %w", err)
 	}
@@ -215,9 +222,9 @@ func readBulkLine(sc *bufio.Scanner, timeField, msgField string, lmp insertutils
 	if ts == 0 {
 		ts = time.Now().UnixNano()
 	}
-	logstorage.RenameField(p.Fields, msgField, "_msg")
-	lmp.AddRow(ts, p.Fields)
-	logstorage.PutJSONParser(p)
+	p.RenameField(msgField, "_msg")
+	processLogMessage(ts, p.Fields)
+	logjson.PutParser(p)
 
 	return true, nil
 }
@@ -266,9 +273,9 @@ func parseElasticsearchTimestamp(s string) (int64, error) {
 		}
 		return t.UnixNano(), nil
 	}
-	nsecs, ok := logstorage.TryParseTimestampRFC3339Nano(s)
-	if !ok {
-		return 0, fmt.Errorf("cannot parse timestamp %q", s)
+	t, err := time.Parse(time.RFC3339, s)
+	if err != nil {
+		return 0, fmt.Errorf("cannot parse timestamp %q: %w", s, err)
 	}
-	return nsecs, nil
+	return t.UnixNano(), nil
 }

app/vlinsert/elasticsearch/elasticsearch_test.go

@@ -4,18 +4,23 @@ import (
 	"bytes"
 	"compress/gzip"
 	"fmt"
+	"reflect"
+	"strings"
 	"testing"
 
-	"github.com/VictoriaMetrics/VictoriaMetrics/app/vlinsert/insertutils"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
 )
 
-func TestReadBulkRequest_Failure(t *testing.T) {
+func TestReadBulkRequestFailure(t *testing.T) {
 	f := func(data string) {
 		t.Helper()
 
-		tlp := &insertutils.TestLogMessageProcessor{}
+		processLogMessage := func(timestamp int64, fields []logstorage.Field) {
+			t.Fatalf("unexpected call to processLogMessage with timestamp=%d, fields=%s", timestamp, fields)
+		}
+
 		r := bytes.NewBufferString(data)
-		rows, err := readBulkRequest(r, false, "_time", "_msg", tlp)
+		rows, err := readBulkRequest(r, false, "_time", "_msg", processLogMessage)
 		if err == nil {
 			t.Fatalf("expecting non-empty error")
 		}
@@ -32,38 +37,58 @@ func TestReadBulkRequest_Failure(t *testing.T) {
 foobar`)
 }
 
-func TestReadBulkRequest_Success(t *testing.T) {
+func TestReadBulkRequestSuccess(t *testing.T) {
 	f := func(data, timeField, msgField string, rowsExpected int, timestampsExpected []int64, resultExpected string) {
 		t.Helper()
 
-		tlp := &insertutils.TestLogMessageProcessor{}
+		var timestamps []int64
+		var result string
+		processLogMessage := func(timestamp int64, fields []logstorage.Field) {
+			timestamps = append(timestamps, timestamp)
+
+			a := make([]string, len(fields))
+			for i, f := range fields {
+				a[i] = fmt.Sprintf("%q:%q", f.Name, f.Value)
+			}
+			s := "{" + strings.Join(a, ",") + "}\n"
+			result += s
+		}
 
 		// Read the request without compression
 		r := bytes.NewBufferString(data)
-		rows, err := readBulkRequest(r, false, timeField, msgField, tlp)
+		rows, err := readBulkRequest(r, false, timeField, msgField, processLogMessage)
 		if err != nil {
 			t.Fatalf("unexpected error: %s", err)
 		}
 		if rows != rowsExpected {
 			t.Fatalf("unexpected rows read; got %d; want %d", rows, rowsExpected)
 		}
-		if err := tlp.Verify(rowsExpected, timestampsExpected, resultExpected); err != nil {
-			t.Fatal(err)
+
+		if !reflect.DeepEqual(timestamps, timestampsExpected) {
+			t.Fatalf("unexpected timestamps;\ngot\n%d\nwant\n%d", timestamps, timestampsExpected)
+		}
+		if result != resultExpected {
+			t.Fatalf("unexpected result;\ngot\n%s\nwant\n%s", result, resultExpected)
 		}
 
 		// Read the request with compression
-		tlp = &insertutils.TestLogMessageProcessor{}
+		timestamps = nil
+		result = ""
 		compressedData := compressData(data)
 		r = bytes.NewBufferString(compressedData)
-		rows, err = readBulkRequest(r, true, timeField, msgField, tlp)
+		rows, err = readBulkRequest(r, true, timeField, msgField, processLogMessage)
 		if err != nil {
 			t.Fatalf("unexpected error: %s", err)
 		}
 		if rows != rowsExpected {
 			t.Fatalf("unexpected rows read; got %d; want %d", rows, rowsExpected)
 		}
-		if err := tlp.Verify(rowsExpected, timestampsExpected, resultExpected); err != nil {
-			t.Fatalf("verification failure after compression: %s", err)
+
+		if !reflect.DeepEqual(timestamps, timestampsExpected) {
+			t.Fatalf("unexpected timestamps;\ngot\n%d\nwant\n%d", timestamps, timestampsExpected)
+		}
+		if result != resultExpected {
+			t.Fatalf("unexpected result;\ngot\n%s\nwant\n%s", result, resultExpected)
 		}
 	}
 
@@ -86,7 +111,8 @@ func TestReadBulkRequest_Success(t *testing.T) {
 	timestampsExpected := []int64{1686026891735000000, 1686026892735000000, 1686026893735000000}
 	resultExpected := `{"@timestamp":"","log.offset":"71770","log.file.path":"/var/log/auth.log","_msg":"foobar"}
 {"@timestamp":"","_msg":"baz"}
-{"_msg":"xyz","@timestamp":"","x":"y"}`
+{"_msg":"xyz","@timestamp":"","x":"y"}
+`
 	f(data, timeField, msgField, rowsExpected, timestampsExpected, resultExpected)
 }
 

app/vlinsert/elasticsearch/elasticsearch_timing_test.go

@@ -5,8 +5,8 @@ import (
 	"fmt"
 	"testing"
 
-	"github.com/VictoriaMetrics/VictoriaMetrics/app/vlinsert/insertutils"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
 )
 
 func BenchmarkReadBulkRequest(b *testing.B) {
@@ -33,7 +33,7 @@ func benchmarkReadBulkRequest(b *testing.B, isGzip bool) {
 
 	timeField := "@timestamp"
 	msgField := "message"
-	blp := &insertutils.BenchmarkLogMessageProcessor{}
+	processLogMessage := func(timestmap int64, fields []logstorage.Field) {}
 
 	b.ReportAllocs()
 	b.SetBytes(int64(len(data)))
@@ -41,7 +41,7 @@ func benchmarkReadBulkRequest(b *testing.B, isGzip bool) {
 		r := &bytes.Reader{}
 		for pb.Next() {
 			r.Reset(dataBytes)
-			_, err := readBulkRequest(r, isGzip, timeField, msgField, blp)
+			_, err := readBulkRequest(r, isGzip, timeField, msgField, processLogMessage)
 			if err != nil {
 				panic(fmt.Errorf("unexpected error: %w", err))
 			}

app/vlinsert/insertutils/common_params.go

@@ -2,8 +2,6 @@ package insertutils
 
 import (
 	"net/http"
-	"sync"
-	"time"
 
 	"github.com/VictoriaMetrics/metrics"
 
@@ -12,12 +10,11 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httputils"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/timeutil"
 )
 
 // CommonParams contains common HTTP parameters used by log ingestion APIs.
 //
-// See https://docs.victoriametrics.com/victorialogs/data-ingestion/#http-parameters
+// See https://docs.victoriametrics.com/VictoriaLogs/data-ingestion/#http-parameters
 type CommonParams struct {
 	TenantID     logstorage.TenantID
 	TimeField    string
@@ -74,126 +71,29 @@ func GetCommonParams(r *http.Request) (*CommonParams, error) {
 	return cp, nil
 }
 
-// GetCommonParamsForSyslog returns common params needed for parsing syslog messages and storing them to the given tenantID.
-func GetCommonParamsForSyslog(tenantID logstorage.TenantID) *CommonParams {
-	// See https://docs.victoriametrics.com/victorialogs/logsql/#unpack_syslog-pipe
-	cp := &CommonParams{
-		TenantID:  tenantID,
-		TimeField: "timestamp",
-		MsgField:  "message",
-		StreamFields: []string{
-			"hostname",
-			"app_name",
-			"proc_id",
-		},
-	}
-
-	return cp
-}
-
-// LogMessageProcessor is an interface for log message processors.
-type LogMessageProcessor interface {
-	// AddRow must add row to the LogMessageProcessor with the given timestamp and the given fields.
-	//
-	// The LogMessageProcessor implementation cannot hold references to fields, since the caller can re-use them.
-	AddRow(timestamp int64, fields []logstorage.Field)
-
-	// MustClose() must flush all the remaining fields and free up resources occupied by LogMessageProcessor.
-	MustClose()
-}
-
-type logMessageProcessor struct {
-	mu            sync.Mutex
-	wg            sync.WaitGroup
-	stopCh        chan struct{}
-	lastFlushTime time.Time
-
-	cp *CommonParams
-	lr *logstorage.LogRows
-}
-
-func (lmp *logMessageProcessor) initPeriodicFlush() {
-	lmp.lastFlushTime = time.Now()
-
-	lmp.wg.Add(1)
-	go func() {
-		defer lmp.wg.Done()
-
-		d := timeutil.AddJitterToDuration(time.Second)
-		ticker := time.NewTicker(d)
-		defer ticker.Stop()
-
-		for {
-			select {
-			case <-lmp.stopCh:
-				return
-			case <-ticker.C:
-				lmp.mu.Lock()
-				if time.Since(lmp.lastFlushTime) >= d {
-					lmp.flushLocked()
-				}
-				lmp.mu.Unlock()
-			}
+// GetProcessLogMessageFunc returns a function, which adds parsed log messages to lr.
+func (cp *CommonParams) GetProcessLogMessageFunc(lr *logstorage.LogRows) func(timestamp int64, fields []logstorage.Field) {
+	return func(timestamp int64, fields []logstorage.Field) {
+		if len(fields) > *MaxFieldsPerLine {
+			rf := logstorage.RowFormatter(fields)
+			logger.Warnf("dropping log line with %d fields; it exceeds -insert.maxFieldsPerLine=%d; %s", len(fields), *MaxFieldsPerLine, rf)
+			rowsDroppedTotalTooManyFields.Inc()
+			return
 		}
-	}()
-}
 
-// AddRow adds new log message to lmp with the given timestamp and fields.
-func (lmp *logMessageProcessor) AddRow(timestamp int64, fields []logstorage.Field) {
-	lmp.mu.Lock()
-	defer lmp.mu.Unlock()
-
-	if len(fields) > *MaxFieldsPerLine {
-		rf := logstorage.RowFormatter(fields)
-		logger.Warnf("dropping log line with %d fields; it exceeds -insert.maxFieldsPerLine=%d; %s", len(fields), *MaxFieldsPerLine, rf)
-		rowsDroppedTotalTooManyFields.Inc()
-		return
+		lr.MustAdd(cp.TenantID, timestamp, fields)
+		if cp.Debug {
+			s := lr.GetRowString(0)
+			lr.ResetKeepSettings()
+			logger.Infof("remoteAddr=%s; requestURI=%s; ignoring log entry because of `debug` query arg: %s", cp.DebugRemoteAddr, cp.DebugRequestURI, s)
+			rowsDroppedTotalDebug.Inc()
+			return
+		}
+		if lr.NeedFlush() {
+			vlstorage.MustAddRows(lr)
+			lr.ResetKeepSettings()
+		}
 	}
-
-	lmp.lr.MustAdd(lmp.cp.TenantID, timestamp, fields)
-	if lmp.cp.Debug {
-		s := lmp.lr.GetRowString(0)
-		lmp.lr.ResetKeepSettings()
-		logger.Infof("remoteAddr=%s; requestURI=%s; ignoring log entry because of `debug` query arg: %s", lmp.cp.DebugRemoteAddr, lmp.cp.DebugRequestURI, s)
-		rowsDroppedTotalDebug.Inc()
-		return
-	}
-	if lmp.lr.NeedFlush() {
-		lmp.flushLocked()
-	}
-}
-
-// flushLocked must be called under locked lmp.mu.
-func (lmp *logMessageProcessor) flushLocked() {
-	lmp.lastFlushTime = time.Now()
-	vlstorage.MustAddRows(lmp.lr)
-	lmp.lr.ResetKeepSettings()
-}
-
-// MustClose flushes the remaining data to the underlying storage and closes lmp.
-func (lmp *logMessageProcessor) MustClose() {
-	close(lmp.stopCh)
-	lmp.wg.Wait()
-
-	lmp.flushLocked()
-	logstorage.PutLogRows(lmp.lr)
-	lmp.lr = nil
-}
-
-// NewLogMessageProcessor returns new LogMessageProcessor for the given cp.
-//
-// MustClose() must be called on the returned LogMessageProcessor when it is no longer needed.
-func (cp *CommonParams) NewLogMessageProcessor() LogMessageProcessor {
-	lr := logstorage.GetLogRows(cp.StreamFields, cp.IgnoreFields)
-	lmp := &logMessageProcessor{
-		cp: cp,
-		lr: lr,
-
-		stopCh: make(chan struct{}),
-	}
-	lmp.initPeriodicFlush()
-
-	return lmp
 }
 
 var rowsDroppedTotalDebug = metrics.NewCounter(`vl_rows_dropped_total{reason="debug"}`)

app/vlinsert/insertutils/testutils.go

@@ -1,53 +0,0 @@
-package insertutils
-
-import (
-	"fmt"
-	"reflect"
-	"strings"
-
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
-)
-
-// TestLogMessageProcessor implements LogMessageProcessor for testing.
-type TestLogMessageProcessor struct {
-	timestamps []int64
-	rows       []string
-}
-
-// AddRow adds row with the given timestamp and fields to tlp
-func (tlp *TestLogMessageProcessor) AddRow(timestamp int64, fields []logstorage.Field) {
-	tlp.timestamps = append(tlp.timestamps, timestamp)
-	tlp.rows = append(tlp.rows, string(logstorage.MarshalFieldsToJSON(nil, fields)))
-}
-
-// MustClose closes tlp.
-func (tlp *TestLogMessageProcessor) MustClose() {
-}
-
-// Verify verifies the number of rows, timestamps and results after AddRow calls.
-func (tlp *TestLogMessageProcessor) Verify(rowsExpected int, timestampsExpected []int64, resultExpected string) error {
-	result := strings.Join(tlp.rows, "\n")
-	if len(tlp.rows) != rowsExpected {
-		return fmt.Errorf("unexpected rows read; got %d; want %d;\nrows read:\n%s\nrows wanted\n%s", len(tlp.rows), rowsExpected, result, resultExpected)
-	}
-
-	if !reflect.DeepEqual(tlp.timestamps, timestampsExpected) {
-		return fmt.Errorf("unexpected timestamps;\ngot\n%d\nwant\n%d", tlp.timestamps, timestampsExpected)
-	}
-	if result != resultExpected {
-		return fmt.Errorf("unexpected result;\ngot\n%s\nwant\n%s", result, resultExpected)
-	}
-
-	return nil
-}
-
-// BenchmarkLogMessageProcessor implements LogMessageProcessor for benchmarks.
-type BenchmarkLogMessageProcessor struct{}
-
-// AddRow implements LogMessageProcessor interface.
-func (blp *BenchmarkLogMessageProcessor) AddRow(_ int64, _ []logstorage.Field) {
-}
-
-// MustClose implements LogMessageProcessor interface.
-func (blp *BenchmarkLogMessageProcessor) MustClose() {
-}

app/vlinsert/insertutils/timestamp.go

@@ -1,33 +0,0 @@
-package insertutils
-
-import (
-	"fmt"
-	"time"
-
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
-)
-
-// ExtractTimestampRFC3339NanoFromFields extracts RFC3339 timestamp in nanoseconds from the field with the name timeField at fields.
-//
-// The value for the timeField is set to empty string after returning from the function,
-// so it could be ignored during data ingestion.
-//
-// The current timestamp is returned if fields do not contain a field with timeField name or if the timeField value is empty.
-func ExtractTimestampRFC3339NanoFromFields(timeField string, fields []logstorage.Field) (int64, error) {
-	for i := range fields {
-		f := &fields[i]
-		if f.Name != timeField {
-			continue
-		}
-		if f.Value == "" || f.Value == "0" {
-			return time.Now().UnixNano(), nil
-		}
-		nsecs, ok := logstorage.TryParseTimestampRFC3339Nano(f.Value)
-		if !ok {
-			return 0, fmt.Errorf("cannot unmarshal rfc3339 timestamp from %s=%q", timeField, f.Value)
-		}
-		f.Value = ""
-		return nsecs, nil
-	}
-	return time.Now().UnixNano(), nil
-}

app/vlinsert/insertutils/timestamp_test.go

@@ -1,75 +0,0 @@
-package insertutils
-
-import (
-	"testing"
-
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
-)
-
-func TestExtractTimestampRFC3339NanoFromFields_Success(t *testing.T) {
-	f := func(timeField string, fields []logstorage.Field, nsecsExpected int64) {
-		t.Helper()
-
-		nsecs, err := ExtractTimestampRFC3339NanoFromFields(timeField, fields)
-		if err != nil {
-			t.Fatalf("unexpected error: %s", err)
-		}
-		if nsecs != nsecsExpected {
-			t.Fatalf("unexpected nsecs; got %d; want %d", nsecs, nsecsExpected)
-		}
-
-		for _, f := range fields {
-			if f.Name == timeField {
-				if f.Value != "" {
-					t.Fatalf("unexpected value for field %s; got %q; want %q", timeField, f.Value, "")
-				}
-			}
-		}
-	}
-
-	f("time", []logstorage.Field{
-		{Name: "foo", Value: "bar"},
-		{Name: "time", Value: "2024-06-18T23:37:20Z"},
-	}, 1718753840000000000)
-
-	f("time", []logstorage.Field{
-		{Name: "foo", Value: "bar"},
-		{Name: "time", Value: "2024-06-18T23:37:20+08:00"},
-	}, 1718725040000000000)
-
-	f("time", []logstorage.Field{
-		{Name: "foo", Value: "bar"},
-		{Name: "time", Value: "2024-06-18T23:37:20.123-05:30"},
-	}, 1718773640123000000)
-
-	f("time", []logstorage.Field{
-		{Name: "time", Value: "2024-06-18T23:37:20.123456789-05:30"},
-		{Name: "foo", Value: "bar"},
-	}, 1718773640123456789)
-}
-
-func TestExtractTimestampRFC3339NanoFromFields_Error(t *testing.T) {
-	f := func(s string) {
-		t.Helper()
-
-		fields := []logstorage.Field{
-			{Name: "time", Value: s},
-		}
-		nsecs, err := ExtractTimestampRFC3339NanoFromFields("time", fields)
-		if err == nil {
-			t.Fatalf("expecting non-nil error")
-		}
-		if nsecs != 0 {
-			t.Fatalf("unexpected nsecs; got %d; want %d", nsecs, 0)
-		}
-	}
-
-	f("foobar")
-
-	// no Z at the end
-	f("2024-06-18T23:37:20")
-
-	// incomplete time
-	f("2024-06-18")
-	f("2024-06-18T23:37")
-}

app/vlinsert/jsonline/jsonline.go

@@ -4,7 +4,6 @@ import (
 	"bufio"
 	"errors"
 	"fmt"
-	"io"
 	"net/http"
 	"time"
 
@@ -13,6 +12,7 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logjson"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
@@ -20,13 +20,13 @@ import (
 )
 
 // RequestHandler processes jsonline insert requests
-func RequestHandler(w http.ResponseWriter, r *http.Request) {
+func RequestHandler(w http.ResponseWriter, r *http.Request) bool {
 	startTime := time.Now()
 	w.Header().Add("Content-Type", "application/json")
 
 	if r.Method != "POST" {
 		w.WriteHeader(http.StatusMethodNotAllowed)
-		return
+		return true
 	}
 
 	requestsTotal.Inc()
@@ -34,40 +34,27 @@ func RequestHandler(w http.ResponseWriter, r *http.Request) {
 	cp, err := insertutils.GetCommonParams(r)
 	if err != nil {
 		httpserver.Errorf(w, r, "%s", err)
-		return
+		return true
 	}
 	if err := vlstorage.CanWriteData(); err != nil {
 		httpserver.Errorf(w, r, "%s", err)
-		return
+		return true
 	}
+	lr := logstorage.GetLogRows(cp.StreamFields, cp.IgnoreFields)
+	processLogMessage := cp.GetProcessLogMessageFunc(lr)
 
 	reader := r.Body
 	if r.Header.Get("Content-Encoding") == "gzip" {
 		zr, err := common.GetGzipReader(reader)
 		if err != nil {
-			logger.Errorf("cannot read gzipped jsonline request: %s", err)
-			return
+			logger.Errorf("cannot read gzipped _bulk request: %s", err)
+			return true
 		}
 		defer common.PutGzipReader(zr)
 		reader = zr
 	}
 
-	lmp := cp.NewLogMessageProcessor()
-	err = processStreamInternal(reader, cp.TimeField, cp.MsgField, lmp)
-	lmp.MustClose()
-
-	if err != nil {
-		logger.Errorf("jsonline: %s", err)
-	} else {
-		// update requestDuration only for successfully parsed requests.
-		// There is no need in updating requestDuration for request errors,
-		// since their timings are usually much smaller than the timing for successful request parsing.
-		requestDuration.UpdateDuration(startTime)
-	}
-}
-
-func processStreamInternal(r io.Reader, timeField, msgField string, lmp insertutils.LogMessageProcessor) error {
-	wcr := writeconcurrencylimiter.GetReader(r)
+	wcr := writeconcurrencylimiter.GetReader(reader)
 	defer writeconcurrencylimiter.PutReader(wcr)
 
 	lb := lineBufferPool.Get()
@@ -79,21 +66,31 @@ func processStreamInternal(r io.Reader, timeField, msgField string, lmp insertut
 
 	n := 0
 	for {
-		ok, err := readLine(sc, timeField, msgField, lmp)
+		ok, err := readLine(sc, cp.TimeField, cp.MsgField, processLogMessage)
 		wcr.DecConcurrency()
 		if err != nil {
-			errorsTotal.Inc()
-			return fmt.Errorf("cannot read line #%d in /jsonline request: %s", n, err)
+			logger.Errorf("cannot read line #%d in /jsonline request: %s", n, err)
+			break
 		}
 		if !ok {
-			return nil
+			break
 		}
 		n++
 		rowsIngestedTotal.Inc()
 	}
+
+	vlstorage.MustAddRows(lr)
+	logstorage.PutLogRows(lr)
+
+	// update jsonlineRequestDuration only for successfully parsed requests.
+	// There is no need in updating jsonlineRequestDuration for request errors,
+	// since their timings are usually much smaller than the timing for successful request parsing.
+	jsonlineRequestDuration.UpdateDuration(startTime)
+
+	return true
 }
 
-func readLine(sc *bufio.Scanner, timeField, msgField string, lmp insertutils.LogMessageProcessor) (bool, error) {
+func readLine(sc *bufio.Scanner, timeField, msgField string, processLogMessage func(timestamp int64, fields []logstorage.Field)) (bool, error) {
 	var line []byte
 	for len(line) == 0 {
 		if !sc.Scan() {
@@ -108,28 +105,57 @@ func readLine(sc *bufio.Scanner, timeField, msgField string, lmp insertutils.Log
 		line = sc.Bytes()
 	}
 
-	p := logstorage.GetJSONParser()
+	p := logjson.GetParser()
 	if err := p.ParseLogMessage(line); err != nil {
 		return false, fmt.Errorf("cannot parse json-encoded log entry: %w", err)
 	}
-	ts, err := insertutils.ExtractTimestampRFC3339NanoFromFields(timeField, p.Fields)
+	ts, err := extractTimestampFromFields(timeField, p.Fields)
 	if err != nil {
-		return false, fmt.Errorf("cannot get timestamp: %w", err)
+		return false, fmt.Errorf("cannot parse timestamp: %w", err)
 	}
-	logstorage.RenameField(p.Fields, msgField, "_msg")
-	lmp.AddRow(ts, p.Fields)
-	logstorage.PutJSONParser(p)
+	if ts == 0 {
+		ts = time.Now().UnixNano()
+	}
+	p.RenameField(msgField, "_msg")
+	processLogMessage(ts, p.Fields)
+	logjson.PutParser(p)
 
 	return true, nil
 }
 
+func extractTimestampFromFields(timeField string, fields []logstorage.Field) (int64, error) {
+	for i := range fields {
+		f := &fields[i]
+		if f.Name != timeField {
+			continue
+		}
+		timestamp, err := parseISO8601Timestamp(f.Value)
+		if err != nil {
+			return 0, err
+		}
+		f.Value = ""
+		return timestamp, nil
+	}
+	return 0, nil
+}
+
+func parseISO8601Timestamp(s string) (int64, error) {
+	if s == "0" || s == "" {
+		// Special case for returning the current timestamp.
+		// It must be automatically converted to the current timestamp by the caller.
+		return 0, nil
+	}
+	t, err := time.Parse(time.RFC3339, s)
+	if err != nil {
+		return 0, fmt.Errorf("cannot parse timestamp %q: %w", s, err)
+	}
+	return t.UnixNano(), nil
+}
+
 var lineBufferPool bytesutil.ByteBufferPool
 
 var (
-	rowsIngestedTotal = metrics.NewCounter(`vl_rows_ingested_total{type="jsonline"}`)
-
-	requestsTotal = metrics.NewCounter(`vl_http_requests_total{path="/insert/jsonline"}`)
-	errorsTotal   = metrics.NewCounter(`vl_http_errors_total{path="/insert/jsonline"}`)
-
-	requestDuration = metrics.NewHistogram(`vl_http_request_duration_seconds{path="/insert/jsonline"}`)
+	requestsTotal           = metrics.NewCounter(`vl_http_requests_total{path="/insert/jsonline"}`)
+	rowsIngestedTotal       = metrics.NewCounter(`vl_rows_ingested_total{type="jsonline"}`)
+	jsonlineRequestDuration = metrics.NewHistogram(`vl_http_request_duration_seconds{path="/insert/jsonline"}`)
 )

app/vlinsert/jsonline/jsonline_test.go

@@ -1,27 +1,59 @@
 package jsonline
 
 import (
+	"bufio"
 	"bytes"
+	"fmt"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
+	"reflect"
+	"strings"
 	"testing"
-
-	"github.com/VictoriaMetrics/VictoriaMetrics/app/vlinsert/insertutils"
 )
 
-func TestProcessStreamInternal_Success(t *testing.T) {
+func TestReadBulkRequestSuccess(t *testing.T) {
 	f := func(data, timeField, msgField string, rowsExpected int, timestampsExpected []int64, resultExpected string) {
 		t.Helper()
 
-		tlp := &insertutils.TestLogMessageProcessor{}
-		r := bytes.NewBufferString(data)
-		if err := processStreamInternal(r, timeField, msgField, tlp); err != nil {
-			t.Fatalf("unexpected error: %s", err)
+		var timestamps []int64
+		var result string
+		processLogMessage := func(timestamp int64, fields []logstorage.Field) {
+			timestamps = append(timestamps, timestamp)
+
+			a := make([]string, len(fields))
+			for i, f := range fields {
+				a[i] = fmt.Sprintf("%q:%q", f.Name, f.Value)
+			}
+			s := "{" + strings.Join(a, ",") + "}\n"
+			result += s
 		}
 
-		if err := tlp.Verify(rowsExpected, timestampsExpected, resultExpected); err != nil {
-			t.Fatal(err)
+		// Read the request without compression
+		r := bytes.NewBufferString(data)
+		sc := bufio.NewScanner(r)
+		rows := 0
+		for {
+			ok, err := readLine(sc, timeField, msgField, processLogMessage)
+			if err != nil {
+				t.Fatalf("unexpected error: %s", err)
+			}
+			if !ok {
+				break
+			}
+			rows++
+		}
+		if rows != rowsExpected {
+			t.Fatalf("unexpected rows read; got %d; want %d", rows, rowsExpected)
+		}
+
+		if !reflect.DeepEqual(timestamps, timestampsExpected) {
+			t.Fatalf("unexpected timestamps;\ngot\n%d\nwant\n%d", timestamps, timestampsExpected)
+		}
+		if result != resultExpected {
+			t.Fatalf("unexpected result;\ngot\n%s\nwant\n%s", result, resultExpected)
 		}
 	}
 
+	// Verify non-empty data
 	data := `{"@timestamp":"2023-06-06T04:48:11.735Z","log":{"offset":71770,"file":{"path":"/var/log/auth.log"}},"message":"foobar"}
 {"@timestamp":"2023-06-06T04:48:12.735Z","message":"baz"}
 {"message":"xyz","@timestamp":"2023-06-06T04:48:13.735Z","x":"y"}
@@ -32,24 +64,7 @@ func TestProcessStreamInternal_Success(t *testing.T) {
 	timestampsExpected := []int64{1686026891735000000, 1686026892735000000, 1686026893735000000}
 	resultExpected := `{"@timestamp":"","log.offset":"71770","log.file.path":"/var/log/auth.log","_msg":"foobar"}
 {"@timestamp":"","_msg":"baz"}
-{"_msg":"xyz","@timestamp":"","x":"y"}`
+{"_msg":"xyz","@timestamp":"","x":"y"}
+`
 	f(data, timeField, msgField, rowsExpected, timestampsExpected, resultExpected)
 }
-
-func TestProcessStreamInternal_Failure(t *testing.T) {
-	f := func(data string) {
-		t.Helper()
-
-		tlp := &insertutils.TestLogMessageProcessor{}
-		r := bytes.NewBufferString(data)
-		if err := processStreamInternal(r, "time", "", tlp); err == nil {
-			t.Fatalf("expecting non-nil error")
-		}
-	}
-
-	// invalid json
-	f("foobar")
-
-	// invalid timestamp field
-	f(`{"time":"foobar"}`)
-}

app/vlinsert/loki/loki.go

@@ -11,8 +11,7 @@ import (
 func RequestHandler(path string, w http.ResponseWriter, r *http.Request) bool {
 	switch path {
 	case "/api/v1/push":
-		handleInsert(r, w)
-		return true
+		return handleInsert(r, w)
 	case "/ready":
 		// See https://grafana.com/docs/loki/latest/api/#identify-ready-loki-instance
 		w.WriteHeader(http.StatusOK)
@@ -24,14 +23,14 @@ func RequestHandler(path string, w http.ResponseWriter, r *http.Request) bool {
 }
 
 // See https://grafana.com/docs/loki/latest/api/#push-log-entries-to-loki
-func handleInsert(r *http.Request, w http.ResponseWriter) {
+func handleInsert(r *http.Request, w http.ResponseWriter) bool {
 	contentType := r.Header.Get("Content-Type")
 	switch contentType {
 	case "application/json":
-		handleJSON(r, w)
+		return handleJSON(r, w)
 	default:
 		// Protobuf request body should be handled by default according to https://grafana.com/docs/loki/latest/api/#push-log-entries-to-loki
-		handleProtobuf(r, w)
+		return handleProtobuf(r, w)
 	}
 }
 
@@ -46,7 +45,7 @@ func getCommonParams(r *http.Request) (*insertutils.CommonParams, error) {
 	if cp.TenantID.AccountID == 0 && cp.TenantID.ProjectID == 0 {
 		org := r.Header.Get("X-Scope-OrgID")
 		if org != "" {
-			tenantID, err := logstorage.ParseTenantID(org)
+			tenantID, err := logstorage.GetTenantIDFromString(org)
 			if err != nil {
 				return nil, err
 			}

app/vlinsert/loki/loki_json.go

@@ -8,7 +8,6 @@ import (
 	"strconv"
 	"time"
 
-	"github.com/VictoriaMetrics/VictoriaMetrics/app/vlinsert/insertutils"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vlstorage"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
@@ -21,15 +20,15 @@ import (
 
 var parserPool fastjson.ParserPool
 
-func handleJSON(r *http.Request, w http.ResponseWriter) {
+func handleJSON(r *http.Request, w http.ResponseWriter) bool {
 	startTime := time.Now()
-	requestsJSONTotal.Inc()
+	lokiRequestsJSONTotal.Inc()
 	reader := r.Body
 	if r.Header.Get("Content-Encoding") == "gzip" {
 		zr, err := common.GetGzipReader(reader)
 		if err != nil {
 			httpserver.Errorf(w, r, "cannot initialize gzip reader: %s", err)
-			return
+			return true
 		}
 		defer common.PutGzipReader(zr)
 		reader = zr
@@ -40,41 +39,45 @@ func handleJSON(r *http.Request, w http.ResponseWriter) {
 	writeconcurrencylimiter.PutReader(wcr)
 	if err != nil {
 		httpserver.Errorf(w, r, "cannot read request body: %s", err)
-		return
+		return true
 	}
 
 	cp, err := getCommonParams(r)
 	if err != nil {
 		httpserver.Errorf(w, r, "cannot parse common params from request: %s", err)
-		return
+		return true
 	}
 	if err := vlstorage.CanWriteData(); err != nil {
 		httpserver.Errorf(w, r, "%s", err)
-		return
+		return true
 	}
-	lmp := cp.NewLogMessageProcessor()
-	n, err := parseJSONRequest(data, lmp)
-	lmp.MustClose()
+	lr := logstorage.GetLogRows(cp.StreamFields, cp.IgnoreFields)
+	processLogMessage := cp.GetProcessLogMessageFunc(lr)
+	n, err := parseJSONRequest(data, processLogMessage)
+	vlstorage.MustAddRows(lr)
+	logstorage.PutLogRows(lr)
 	if err != nil {
 		httpserver.Errorf(w, r, "cannot parse Loki json request: %s", err)
-		return
+		return true
 	}
 
 	rowsIngestedJSONTotal.Add(n)
 
-	// update requestJSONDuration only for successfully parsed requests
-	// There is no need in updating requestJSONDuration for request errors,
+	// update lokiRequestJSONDuration only for successfully parsed requests
+	// There is no need in updating lokiRequestJSONDuration for request errors,
 	// since their timings are usually much smaller than the timing for successful request parsing.
-	requestJSONDuration.UpdateDuration(startTime)
+	lokiRequestJSONDuration.UpdateDuration(startTime)
+
+	return true
 }
 
 var (
-	requestsJSONTotal     = metrics.NewCounter(`vl_http_requests_total{path="/insert/loki/api/v1/push",format="json"}`)
-	rowsIngestedJSONTotal = metrics.NewCounter(`vl_rows_ingested_total{type="loki",format="json"}`)
-	requestJSONDuration   = metrics.NewHistogram(`vl_http_request_duration_seconds{path="/insert/loki/api/v1/push",format="json"}`)
+	lokiRequestsJSONTotal   = metrics.NewCounter(`vl_http_requests_total{path="/insert/loki/api/v1/push",format="json"}`)
+	rowsIngestedJSONTotal   = metrics.NewCounter(`vl_rows_ingested_total{type="loki",format="json"}`)
+	lokiRequestJSONDuration = metrics.NewHistogram(`vl_http_request_duration_seconds{path="/insert/loki/api/v1/push",format="json"}`)
 )
 
-func parseJSONRequest(data []byte, lmp insertutils.LogMessageProcessor) (int, error) {
+func parseJSONRequest(data []byte, processLogMessage func(timestamp int64, fields []logstorage.Field)) (int, error) {
 	p := parserPool.Get()
 	defer parserPool.Put(p)
 	v, err := p.ParseBytes(data)
@@ -167,7 +170,7 @@ func parseJSONRequest(data []byte, lmp insertutils.LogMessageProcessor) (int, er
 				Name:  "_msg",
 				Value: bytesutil.ToUnsafeString(msg),
 			})
-			lmp.AddRow(ts, fields)
+			processLogMessage(ts, fields)
 		}
 		rowsIngested += len(lines)
 	}

app/vlinsert/loki/loki_json_test.go

@@ -1,17 +1,19 @@
 package loki
 
 import (
+	"fmt"
+	"strings"
 	"testing"
 
-	"github.com/VictoriaMetrics/VictoriaMetrics/app/vlinsert/insertutils"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
 )
 
-func TestParseJSONRequest_Failure(t *testing.T) {
+func TestParseJSONRequestFailure(t *testing.T) {
 	f := func(s string) {
 		t.Helper()
-
-		tlp := &insertutils.TestLogMessageProcessor{}
-		n, err := parseJSONRequest([]byte(s), tlp)
+		n, err := parseJSONRequest([]byte(s), func(timestamp int64, fields []logstorage.Field) {
+			t.Fatalf("unexpected call to parseJSONRequest callback!")
+		})
 		if err == nil {
 			t.Fatalf("expecting non-nil error")
 		}
@@ -54,30 +56,39 @@ func TestParseJSONRequest_Failure(t *testing.T) {
 	f(`{"streams":[{"values":[["123",1234]]}]}`)
 }
 
-func TestParseJSONRequest_Success(t *testing.T) {
-	f := func(s string, timestampsExpected []int64, resultExpected string) {
+func TestParseJSONRequestSuccess(t *testing.T) {
+	f := func(s string, resultExpected string) {
 		t.Helper()
-
-		tlp := &insertutils.TestLogMessageProcessor{}
-
-		n, err := parseJSONRequest([]byte(s), tlp)
+		var lines []string
+		n, err := parseJSONRequest([]byte(s), func(timestamp int64, fields []logstorage.Field) {
+			var a []string
+			for _, f := range fields {
+				a = append(a, f.String())
+			}
+			line := fmt.Sprintf("_time:%d %s", timestamp, strings.Join(a, " "))
+			lines = append(lines, line)
+		})
 		if err != nil {
 			t.Fatalf("unexpected error: %s", err)
 		}
-		if err := tlp.Verify(n, timestampsExpected, resultExpected); err != nil {
-			t.Fatal(err)
+		if n != len(lines) {
+			t.Fatalf("unexpected number of lines parsed; got %d; want %d", n, len(lines))
+		}
+		result := strings.Join(lines, "\n")
+		if result != resultExpected {
+			t.Fatalf("unexpected result;\ngot\n%s\nwant\n%s", result, resultExpected)
 		}
 	}
 
 	// Empty streams
-	f(`{"streams":[]}`, nil, ``)
-	f(`{"streams":[{"values":[]}]}`, nil, ``)
-	f(`{"streams":[{"stream":{},"values":[]}]}`, nil, ``)
-	f(`{"streams":[{"stream":{"foo":"bar"},"values":[]}]}`, nil, ``)
+	f(`{"streams":[]}`, ``)
+	f(`{"streams":[{"values":[]}]}`, ``)
+	f(`{"streams":[{"stream":{},"values":[]}]}`, ``)
+	f(`{"streams":[{"stream":{"foo":"bar"},"values":[]}]}`, ``)
 
 	// Empty stream labels
-	f(`{"streams":[{"values":[["1577836800000000001", "foo bar"]]}]}`, []int64{1577836800000000001}, `{"_msg":"foo bar"}`)
-	f(`{"streams":[{"stream":{},"values":[["1577836800000000001", "foo bar"]]}]}`, []int64{1577836800000000001}, `{"_msg":"foo bar"}`)
+	f(`{"streams":[{"values":[["1577836800000000001", "foo bar"]]}]}`, `_time:1577836800000000001 "_msg":"foo bar"`)
+	f(`{"streams":[{"stream":{},"values":[["1577836800000000001", "foo bar"]]}]}`, `_time:1577836800000000001 "_msg":"foo bar"`)
 
 	// Non-empty stream labels
 	f(`{"streams":[{"stream":{
@@ -87,9 +98,9 @@ func TestParseJSONRequest_Success(t *testing.T) {
 	["1577836800000000001", "foo bar"],
 	["1477836900005000002", "abc"],
 	["147.78369e9", "foobar"]
-]}]}`, []int64{1577836800000000001, 1477836900005000002, 147783690000}, `{"label1":"value1","label2":"value2","_msg":"foo bar"}
-{"label1":"value1","label2":"value2","_msg":"abc"}
-{"label1":"value1","label2":"value2","_msg":"foobar"}`)
+]}]}`, `_time:1577836800000000001 "label1":"value1" "label2":"value2" "_msg":"foo bar"
+_time:1477836900005000002 "label1":"value1" "label2":"value2" "_msg":"abc"
+_time:147783690000 "label1":"value1" "label2":"value2" "_msg":"foobar"`)
 
 	// Multiple streams
 	f(`{
@@ -113,7 +124,7 @@ func TestParseJSONRequest_Success(t *testing.T) {
 			]
 		}
 	]
-}`, []int64{1577836800000000001, 1577836900005000002, 1877836900005000002}, `{"foo":"bar","a":"b","_msg":"foo bar"}
-{"foo":"bar","a":"b","_msg":"abc"}
-{"x":"y","_msg":"yx"}`)
+}`, `_time:1577836800000000001 "foo":"bar" "a":"b" "_msg":"foo bar"
+_time:1577836900005000002 "foo":"bar" "a":"b" "_msg":"abc"
+_time:1877836900005000002 "x":"y" "_msg":"yx"`)
 }

app/vlinsert/loki/loki_json_timing_test.go

@@ -6,7 +6,7 @@ import (
 	"testing"
 	"time"
 
-	"github.com/VictoriaMetrics/VictoriaMetrics/app/vlinsert/insertutils"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
 )
 
 func BenchmarkParseJSONRequest(b *testing.B) {
@@ -22,13 +22,12 @@ func BenchmarkParseJSONRequest(b *testing.B) {
 }
 
 func benchmarkParseJSONRequest(b *testing.B, streams, rows, labels int) {
-	blp := &insertutils.BenchmarkLogMessageProcessor{}
 	b.ReportAllocs()
 	b.SetBytes(int64(streams * rows))
 	b.RunParallel(func(pb *testing.PB) {
 		data := getJSONBody(streams, rows, labels)
 		for pb.Next() {
-			_, err := parseJSONRequest(data, blp)
+			_, err := parseJSONRequest(data, func(timestamp int64, fields []logstorage.Field) {})
 			if err != nil {
 				panic(fmt.Errorf("unexpected error: %w", err))
 			}

app/vlinsert/loki/loki_protobuf.go

@@ -9,7 +9,6 @@ import (
 	"sync"
 	"time"
 
-	"github.com/VictoriaMetrics/VictoriaMetrics/app/vlinsert/insertutils"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vlstorage"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
@@ -24,49 +23,53 @@ var (
 	pushReqsPool sync.Pool
 )
 
-func handleProtobuf(r *http.Request, w http.ResponseWriter) {
+func handleProtobuf(r *http.Request, w http.ResponseWriter) bool {
 	startTime := time.Now()
-	requestsProtobufTotal.Inc()
+	lokiRequestsProtobufTotal.Inc()
 	wcr := writeconcurrencylimiter.GetReader(r.Body)
 	data, err := io.ReadAll(wcr)
 	writeconcurrencylimiter.PutReader(wcr)
 	if err != nil {
 		httpserver.Errorf(w, r, "cannot read request body: %s", err)
-		return
+		return true
 	}
 
 	cp, err := getCommonParams(r)
 	if err != nil {
 		httpserver.Errorf(w, r, "cannot parse common params from request: %s", err)
-		return
+		return true
 	}
 	if err := vlstorage.CanWriteData(); err != nil {
 		httpserver.Errorf(w, r, "%s", err)
-		return
+		return true
 	}
-	lmp := cp.NewLogMessageProcessor()
-	n, err := parseProtobufRequest(data, lmp)
-	lmp.MustClose()
+	lr := logstorage.GetLogRows(cp.StreamFields, cp.IgnoreFields)
+	processLogMessage := cp.GetProcessLogMessageFunc(lr)
+	n, err := parseProtobufRequest(data, processLogMessage)
+	vlstorage.MustAddRows(lr)
+	logstorage.PutLogRows(lr)
 	if err != nil {
 		httpserver.Errorf(w, r, "cannot parse Loki protobuf request: %s", err)
-		return
+		return true
 	}
 
 	rowsIngestedProtobufTotal.Add(n)
 
-	// update requestProtobufDuration only for successfully parsed requests
-	// There is no need in updating requestProtobufDuration for request errors,
+	// update lokiRequestProtobufDuration only for successfully parsed requests
+	// There is no need in updating lokiRequestProtobufDuration for request errors,
 	// since their timings are usually much smaller than the timing for successful request parsing.
-	requestProtobufDuration.UpdateDuration(startTime)
+	lokiRequestProtobufDuration.UpdateDuration(startTime)
+
+	return true
 }
 
 var (
-	requestsProtobufTotal     = metrics.NewCounter(`vl_http_requests_total{path="/insert/loki/api/v1/push",format="protobuf"}`)
-	rowsIngestedProtobufTotal = metrics.NewCounter(`vl_rows_ingested_total{type="loki",format="protobuf"}`)
-	requestProtobufDuration   = metrics.NewHistogram(`vl_http_request_duration_seconds{path="/insert/loki/api/v1/push",format="protobuf"}`)
+	lokiRequestsProtobufTotal   = metrics.NewCounter(`vl_http_requests_total{path="/insert/loki/api/v1/push",format="protobuf"}`)
+	rowsIngestedProtobufTotal   = metrics.NewCounter(`vl_rows_ingested_total{type="loki",format="protobuf"}`)
+	lokiRequestProtobufDuration = metrics.NewHistogram(`vl_http_request_duration_seconds{path="/insert/loki/api/v1/push",format="protobuf"}`)
 )
 
-func parseProtobufRequest(data []byte, lmp insertutils.LogMessageProcessor) (int, error) {
+func parseProtobufRequest(data []byte, processLogMessage func(timestamp int64, fields []logstorage.Field)) (int, error) {
 	bb := bytesBufPool.Get()
 	defer bytesBufPool.Put(bb)
 
@@ -109,7 +112,7 @@ func parseProtobufRequest(data []byte, lmp insertutils.LogMessageProcessor) (int
 			if ts == 0 {
 				ts = currentTimestamp
 			}
-			lmp.AddRow(ts, fields)
+			processLogMessage(ts, fields)
 		}
 		rowsIngested += len(stream.Entries)
 	}

app/vlinsert/loki/loki_protobuf_test.go

@@ -6,83 +6,83 @@ import (
 	"testing"
 	"time"
 
-	"github.com/VictoriaMetrics/VictoriaMetrics/app/vlinsert/insertutils"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
 	"github.com/golang/snappy"
 )
 
-type testLogMessageProcessor struct {
-	pr PushRequest
-}
-
-func (tlp *testLogMessageProcessor) AddRow(timestamp int64, fields []logstorage.Field) {
-	msg := ""
-	for _, f := range fields {
-		if f.Name == "_msg" {
-			msg = f.Value
-		}
-	}
-	var a []string
-	for _, f := range fields {
-		if f.Name == "_msg" {
-			continue
-		}
-		item := fmt.Sprintf("%s=%q", f.Name, f.Value)
-		a = append(a, item)
-	}
-	labels := "{" + strings.Join(a, ", ") + "}"
-	tlp.pr.Streams = append(tlp.pr.Streams, Stream{
-		Labels: labels,
-		Entries: []Entry{
-			{
-				Timestamp: time.Unix(0, timestamp),
-				Line:      msg,
-			},
-		},
-	})
-}
-
-func (tlp *testLogMessageProcessor) MustClose() {
-}
-
-func TestParseProtobufRequest_Success(t *testing.T) {
-	f := func(s string, timestampsExpected []int64, resultExpected string) {
+func TestParseProtobufRequestSuccess(t *testing.T) {
+	f := func(s string, resultExpected string) {
 		t.Helper()
-
-		tlp := &testLogMessageProcessor{}
-		n, err := parseJSONRequest([]byte(s), tlp)
+		var pr PushRequest
+		n, err := parseJSONRequest([]byte(s), func(timestamp int64, fields []logstorage.Field) {
+			msg := ""
+			for _, f := range fields {
+				if f.Name == "_msg" {
+					msg = f.Value
+				}
+			}
+			var a []string
+			for _, f := range fields {
+				if f.Name == "_msg" {
+					continue
+				}
+				item := fmt.Sprintf("%s=%q", f.Name, f.Value)
+				a = append(a, item)
+			}
+			labels := "{" + strings.Join(a, ", ") + "}"
+			pr.Streams = append(pr.Streams, Stream{
+				Labels: labels,
+				Entries: []Entry{
+					{
+						Timestamp: time.Unix(0, timestamp),
+						Line:      msg,
+					},
+				},
+			})
+		})
 		if err != nil {
 			t.Fatalf("unexpected error: %s", err)
 		}
-		if n != len(tlp.pr.Streams) {
-			t.Fatalf("unexpected number of streams; got %d; want %d", len(tlp.pr.Streams), n)
+		if n != len(pr.Streams) {
+			t.Fatalf("unexpected number of streams; got %d; want %d", len(pr.Streams), n)
 		}
 
-		data, err := tlp.pr.Marshal()
+		data, err := pr.Marshal()
 		if err != nil {
 			t.Fatalf("unexpected error when marshaling PushRequest: %s", err)
 		}
 		encodedData := snappy.Encode(nil, data)
 
-		tlp2 := &insertutils.TestLogMessageProcessor{}
-		n, err = parseProtobufRequest(encodedData, tlp2)
+		var lines []string
+		n, err = parseProtobufRequest(encodedData, func(timestamp int64, fields []logstorage.Field) {
+			var a []string
+			for _, f := range fields {
+				a = append(a, f.String())
+			}
+			line := fmt.Sprintf("_time:%d %s", timestamp, strings.Join(a, " "))
+			lines = append(lines, line)
+		})
 		if err != nil {
 			t.Fatalf("unexpected error: %s", err)
 		}
-		if err := tlp2.Verify(n, timestampsExpected, resultExpected); err != nil {
-			t.Fatal(err)
+		if n != len(lines) {
+			t.Fatalf("unexpected number of lines parsed; got %d; want %d", n, len(lines))
+		}
+		result := strings.Join(lines, "\n")
+		if result != resultExpected {
+			t.Fatalf("unexpected result;\ngot\n%s\nwant\n%s", result, resultExpected)
 		}
 	}
 
 	// Empty streams
-	f(`{"streams":[]}`, nil, ``)
-	f(`{"streams":[{"values":[]}]}`, nil, ``)
-	f(`{"streams":[{"stream":{},"values":[]}]}`, nil, ``)
-	f(`{"streams":[{"stream":{"foo":"bar"},"values":[]}]}`, nil, ``)
+	f(`{"streams":[]}`, ``)
+	f(`{"streams":[{"values":[]}]}`, ``)
+	f(`{"streams":[{"stream":{},"values":[]}]}`, ``)
+	f(`{"streams":[{"stream":{"foo":"bar"},"values":[]}]}`, ``)
 
 	// Empty stream labels
-	f(`{"streams":[{"values":[["1577836800000000001", "foo bar"]]}]}`, []int64{1577836800000000001}, `{"_msg":"foo bar"}`)
-	f(`{"streams":[{"stream":{},"values":[["1577836800000000001", "foo bar"]]}]}`, []int64{1577836800000000001}, `{"_msg":"foo bar"}`)
+	f(`{"streams":[{"values":[["1577836800000000001", "foo bar"]]}]}`, `_time:1577836800000000001 "_msg":"foo bar"`)
+	f(`{"streams":[{"stream":{},"values":[["1577836800000000001", "foo bar"]]}]}`, `_time:1577836800000000001 "_msg":"foo bar"`)
 
 	// Non-empty stream labels
 	f(`{"streams":[{"stream":{
@@ -92,9 +92,9 @@ func TestParseProtobufRequest_Success(t *testing.T) {
 	["1577836800000000001", "foo bar"],
 	["1477836900005000002", "abc"],
 	["147.78369e9", "foobar"]
-]}]}`, []int64{1577836800000000001, 1477836900005000002, 147783690000}, `{"label1":"value1","label2":"value2","_msg":"foo bar"}
-{"label1":"value1","label2":"value2","_msg":"abc"}
-{"label1":"value1","label2":"value2","_msg":"foobar"}`)
+]}]}`, `_time:1577836800000000001 "label1":"value1" "label2":"value2" "_msg":"foo bar"
+_time:1477836900005000002 "label1":"value1" "label2":"value2" "_msg":"abc"
+_time:147783690000 "label1":"value1" "label2":"value2" "_msg":"foobar"`)
 
 	// Multiple streams
 	f(`{
@@ -118,12 +118,12 @@ func TestParseProtobufRequest_Success(t *testing.T) {
 			]
 		}
 	]
-}`, []int64{1577836800000000001, 1577836900005000002, 1877836900005000002}, `{"foo":"bar","a":"b","_msg":"foo bar"}
-{"foo":"bar","a":"b","_msg":"abc"}
-{"x":"y","_msg":"yx"}`)
+}`, `_time:1577836800000000001 "foo":"bar" "a":"b" "_msg":"foo bar"
+_time:1577836900005000002 "foo":"bar" "a":"b" "_msg":"abc"
+_time:1877836900005000002 "x":"y" "_msg":"yx"`)
 }
 
-func TestParsePromLabels_Success(t *testing.T) {
+func TestParsePromLabelsSuccess(t *testing.T) {
 	f := func(s string) {
 		t.Helper()
 		fields, err := parsePromLabels(nil, s)
@@ -147,7 +147,7 @@ func TestParsePromLabels_Success(t *testing.T) {
 	f(`{foo="ba\"r\\z\n", a="", b="\"\\"}`)
 }
 
-func TestParsePromLabels_Failure(t *testing.T) {
+func TestParsePromLabelsFailure(t *testing.T) {
 	f := func(s string) {
 		t.Helper()
 		fields, err := parsePromLabels(nil, s)

app/vlinsert/loki/loki_protobuf_timing_test.go

@@ -8,7 +8,7 @@ import (
 
 	"github.com/golang/snappy"
 
-	"github.com/VictoriaMetrics/VictoriaMetrics/app/vlinsert/insertutils"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
 )
 
 func BenchmarkParseProtobufRequest(b *testing.B) {
@@ -24,13 +24,12 @@ func BenchmarkParseProtobufRequest(b *testing.B) {
 }
 
 func benchmarkParseProtobufRequest(b *testing.B, streams, rows, labels int) {
-	blp := &insertutils.BenchmarkLogMessageProcessor{}
 	b.ReportAllocs()
 	b.SetBytes(int64(streams * rows))
 	b.RunParallel(func(pb *testing.PB) {
 		body := getProtobufBody(streams, rows, labels)
 		for pb.Next() {
-			_, err := parseProtobufRequest(body, blp)
+			_, err := parseProtobufRequest(body, func(timestamp int64, fields []logstorage.Field) {})
 			if err != nil {
 				panic(fmt.Errorf("unexpected error: %w", err))
 			}

app/vlinsert/main.go

@@ -7,17 +7,14 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vlinsert/elasticsearch"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vlinsert/jsonline"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vlinsert/loki"
-	"github.com/VictoriaMetrics/VictoriaMetrics/app/vlinsert/syslog"
 )
 
 // Init initializes vlinsert
 func Init() {
-	syslog.MustInit()
 }
 
 // Stop stops vlinsert
 func Stop() {
-	syslog.MustStop()
 }
 
 // RequestHandler handles insert requests for VictoriaLogs
@@ -31,8 +28,7 @@ func RequestHandler(w http.ResponseWriter, r *http.Request) bool {
 	path = strings.ReplaceAll(path, "//", "/")
 
 	if path == "/jsonline" {
-		jsonline.RequestHandler(w, r)
-		return true
+		return jsonline.RequestHandler(w, r)
 	}
 	switch {
 	case strings.HasPrefix(path, "/elasticsearch/"):

app/vlinsert/syslog/syslog.go

@@ -1,531 +0,0 @@
-package syslog
-
-import (
-	"bufio"
-	"crypto/tls"
-	"errors"
-	"flag"
-	"fmt"
-	"io"
-	"net"
-	"strconv"
-	"strings"
-	"sync"
-	"sync/atomic"
-	"time"
-
-	"github.com/klauspost/compress/gzip"
-
-	"github.com/VictoriaMetrics/VictoriaMetrics/app/vlinsert/insertutils"
-	"github.com/VictoriaMetrics/VictoriaMetrics/app/vlstorage"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/cgroup"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/ingestserver"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/netutil"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/slicesutil"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
-	"github.com/VictoriaMetrics/metrics"
-)
-
-var (
-	syslogTimezone = flag.String("syslog.timezone", "Local", "Timezone to use when parsing timestamps in RFC3164 syslog messages. Timezone must be a valid IANA Time Zone. "+
-		"For example: America/New_York, Europe/Berlin, Etc/GMT+3 . See https://docs.victoriametrics.com/victorialogs/data-ingestion/syslog/")
-
-	syslogTenantIDTCP = flagutil.NewArrayString("syslog.tenantID.tcp", "TenantID for logs ingested via the corresponding -syslog.listenAddr.tcp. "+
-		"See https://docs.victoriametrics.com/victorialogs/data-ingestion/syslog/")
-	syslogTenantIDUDP = flagutil.NewArrayString("syslog.tenantID.udp", "TenantID for logs ingested via the corresponding -syslog.listenAddr.udp. "+
-		"See https://docs.victoriametrics.com/victorialogs/data-ingestion/syslog/")
-
-	listenAddrTCP = flagutil.NewArrayString("syslog.listenAddr.tcp", "Comma-separated list of TCP addresses to listen to for Syslog messages. "+
-		"See https://docs.victoriametrics.com/victorialogs/data-ingestion/syslog/")
-	listenAddrUDP = flagutil.NewArrayString("syslog.listenAddr.udp", "Comma-separated list of UDP address to listen to for Syslog messages. "+
-		"See https://docs.victoriametrics.com/victorialogs/data-ingestion/syslog/")
-
-	tlsEnable = flagutil.NewArrayBool("syslog.tls", "Whether to enable TLS for receiving syslog messages at the corresponding -syslog.listenAddr.tcp. "+
-		"The corresponding -syslog.tlsCertFile and -syslog.tlsKeyFile must be set if -syslog.tls is set. See https://docs.victoriametrics.com/victorialogs/data-ingestion/syslog/#security")
-	tlsCertFile = flagutil.NewArrayString("syslog.tlsCertFile", "Path to file with TLS certificate for the corresponding -syslog.listenAddr.tcp if the corresponding -syslog.tls is set. "+
-		"Prefer ECDSA certs instead of RSA certs as RSA certs are slower. The provided certificate file is automatically re-read every second, so it can be dynamically updated. "+
-		"See https://docs.victoriametrics.com/victorialogs/data-ingestion/syslog/#security")
-	tlsKeyFile = flagutil.NewArrayString("syslog.tlsKeyFile", "Path to file with TLS key for the corresponding -syslog.listenAddr.tcp if the corresponding -syslog.tls is set. "+
-		"The provided key file is automatically re-read every second, so it can be dynamically updated. "+
-		"See https://docs.victoriametrics.com/victorialogs/data-ingestion/syslog/#security")
-	tlsCipherSuites = flagutil.NewArrayString("syslog.tlsCipherSuites", "Optional list of TLS cipher suites for -syslog.listenAddr.tcp if -syslog.tls is set. "+
-		"See the list of supported cipher suites at https://pkg.go.dev/crypto/tls#pkg-constants . "+
-		"See also https://docs.victoriametrics.com/victorialogs/data-ingestion/syslog/#security")
-	tlsMinVersion = flag.String("syslog.tlsMinVersion", "TLS13", "The minimum TLS version to use for -syslog.listenAddr.tcp if -syslog.tls is set. "+
-		"Supported values: TLS10, TLS11, TLS12, TLS13. "+
-		"See https://docs.victoriametrics.com/victorialogs/data-ingestion/syslog/#security")
-
-	compressMethodTCP = flagutil.NewArrayString("syslog.compressMethod.tcp", "Compression method for syslog messages received at the corresponding -syslog.listenAddr.tcp. "+
-		"Supported values: none, gzip, deflate. See https://docs.victoriametrics.com/victorialogs/data-ingestion/syslog/#compression")
-	compressMethodUDP = flagutil.NewArrayString("syslog.compressMethod.udp", "Compression method for syslog messages received at the corresponding -syslog.listenAddr.udp. "+
-		"Supported values: none, gzip, deflate. See https://docs.victoriametrics.com/victorialogs/data-ingestion/syslog/#compression")
-
-	useLocalTimestampTCP = flagutil.NewArrayBool("syslog.useLocalTimestamp.tcp", "Whether to use local timestamp instead of the original timestamp for the ingested syslog messages "+
-		"at the corresponding -syslog.listenAddr.tcp. See https://docs.victoriametrics.com/victorialogs/data-ingestion/syslog/#log-timestamps")
-	useLocalTimestampUDP = flagutil.NewArrayBool("syslog.useLocalTimestamp.udp", "Whether to use local timestamp instead of the original timestamp for the ingested syslog messages "+
-		"at the corresponding -syslog.listenAddr.udp. See https://docs.victoriametrics.com/victorialogs/data-ingestion/syslog/#log-timestamps")
-)
-
-// MustInit initializes syslog parser at the given -syslog.listenAddr.tcp and -syslog.listenAddr.udp ports
-//
-// This function must be called after flag.Parse().
-//
-// MustStop() must be called in order to free up resources occupied by the initialized syslog parser.
-func MustInit() {
-	if workersStopCh != nil {
-		logger.Panicf("BUG: MustInit() called twice without MustStop() call")
-	}
-	workersStopCh = make(chan struct{})
-
-	for argIdx, addr := range *listenAddrTCP {
-		workersWG.Add(1)
-		go func(addr string, argIdx int) {
-			runTCPListener(addr, argIdx)
-			workersWG.Done()
-		}(addr, argIdx)
-	}
-
-	for argIdx, addr := range *listenAddrUDP {
-		workersWG.Add(1)
-		go func(addr string, argIdx int) {
-			runUDPListener(addr, argIdx)
-			workersWG.Done()
-		}(addr, argIdx)
-	}
-
-	currentYear := time.Now().Year()
-	globalCurrentYear.Store(int64(currentYear))
-	workersWG.Add(1)
-	go func() {
-		ticker := time.NewTicker(time.Minute)
-		for {
-			select {
-			case <-workersStopCh:
-				ticker.Stop()
-				workersWG.Done()
-				return
-			case <-ticker.C:
-				currentYear := time.Now().Year()
-				globalCurrentYear.Store(int64(currentYear))
-			}
-		}
-	}()
-
-	if *syslogTimezone != "" {
-		tz, err := time.LoadLocation(*syslogTimezone)
-		if err != nil {
-			logger.Fatalf("cannot parse -syslog.timezone=%q: %s", *syslogTimezone, err)
-		}
-		globalTimezone = tz
-	} else {
-		globalTimezone = time.Local
-	}
-}
-
-var (
-	globalCurrentYear atomic.Int64
-	globalTimezone    *time.Location
-)
-
-var (
-	workersWG     sync.WaitGroup
-	workersStopCh chan struct{}
-)
-
-// MustStop stops syslog parser initialized via MustInit()
-func MustStop() {
-	close(workersStopCh)
-	workersWG.Wait()
-	workersStopCh = nil
-}
-
-func runUDPListener(addr string, argIdx int) {
-	ln, err := net.ListenPacket(netutil.GetUDPNetwork(), addr)
-	if err != nil {
-		logger.Fatalf("cannot start UDP syslog server at %q: %s", addr, err)
-	}
-
-	tenantIDStr := syslogTenantIDUDP.GetOptionalArg(argIdx)
-	tenantID, err := logstorage.ParseTenantID(tenantIDStr)
-	if err != nil {
-		logger.Fatalf("cannot parse -syslog.tenantID.udp=%q for -syslog.listenAddr.udp=%q: %s", tenantIDStr, addr, err)
-	}
-
-	compressMethod := compressMethodUDP.GetOptionalArg(argIdx)
-	checkCompressMethod(compressMethod, addr, "udp")
-
-	useLocalTimestamp := useLocalTimestampUDP.GetOptionalArg(argIdx)
-
-	doneCh := make(chan struct{})
-	go func() {
-		serveUDP(ln, tenantID, compressMethod, useLocalTimestamp)
-		close(doneCh)
-	}()
-
-	logger.Infof("started accepting syslog messages at -syslog.listenAddr.udp=%q", addr)
-	<-workersStopCh
-	if err := ln.Close(); err != nil {
-		logger.Fatalf("syslog: cannot close UDP listener at %s: %s", addr, err)
-	}
-	<-doneCh
-	logger.Infof("finished accepting syslog messages at -syslog.listenAddr.udp=%q", addr)
-}
-
-func runTCPListener(addr string, argIdx int) {
-	var tlsConfig *tls.Config
-	if tlsEnable.GetOptionalArg(argIdx) {
-		certFile := tlsCertFile.GetOptionalArg(argIdx)
-		keyFile := tlsKeyFile.GetOptionalArg(argIdx)
-		tc, err := netutil.GetServerTLSConfig(certFile, keyFile, *tlsMinVersion, *tlsCipherSuites)
-		if err != nil {
-			logger.Fatalf("cannot load TLS cert from -syslog.tlsCertFile=%q, -syslog.tlsKeyFile=%q, -syslog.tlsMinVersion=%q, -syslog.tlsCipherSuites=%q: %s",
-				certFile, keyFile, *tlsMinVersion, *tlsCipherSuites, err)
-		}
-		tlsConfig = tc
-	}
-	ln, err := netutil.NewTCPListener("syslog", addr, false, tlsConfig)
-	if err != nil {
-		logger.Fatalf("syslog: cannot start TCP listener at %s: %s", addr, err)
-	}
-
-	tenantIDStr := syslogTenantIDTCP.GetOptionalArg(argIdx)
-	tenantID, err := logstorage.ParseTenantID(tenantIDStr)
-	if err != nil {
-		logger.Fatalf("cannot parse -syslog.tenantID.tcp=%q for -syslog.listenAddr.tcp=%q: %s", tenantIDStr, addr, err)
-	}
-
-	compressMethod := compressMethodTCP.GetOptionalArg(argIdx)
-	checkCompressMethod(compressMethod, addr, "tcp")
-
-	useLocalTimestamp := useLocalTimestampTCP.GetOptionalArg(argIdx)
-
-	doneCh := make(chan struct{})
-	go func() {
-		serveTCP(ln, tenantID, compressMethod, useLocalTimestamp)
-		close(doneCh)
-	}()
-
-	logger.Infof("started accepting syslog messages at -syslog.listenAddr.tcp=%q", addr)
-	<-workersStopCh
-	if err := ln.Close(); err != nil {
-		logger.Fatalf("syslog: cannot close TCP listener at %s: %s", addr, err)
-	}
-	<-doneCh
-	logger.Infof("finished accepting syslog messages at -syslog.listenAddr.tcp=%q", addr)
-}
-
-func checkCompressMethod(compressMethod, addr, protocol string) {
-	switch compressMethod {
-	case "", "none", "gzip", "deflate":
-		return
-	default:
-		logger.Fatalf("unsupported -syslog.compressMethod.%s=%q for -syslog.listenAddr.%s=%q; supported values: 'none', 'gzip', 'deflate'", protocol, compressMethod, protocol, addr)
-	}
-}
-
-func serveUDP(ln net.PacketConn, tenantID logstorage.TenantID, compressMethod string, useLocalTimestamp bool) {
-	gomaxprocs := cgroup.AvailableCPUs()
-	var wg sync.WaitGroup
-	localAddr := ln.LocalAddr()
-	for i := 0; i < gomaxprocs; i++ {
-		wg.Add(1)
-		go func() {
-			defer wg.Done()
-			cp := insertutils.GetCommonParamsForSyslog(tenantID)
-			var bb bytesutil.ByteBuffer
-			bb.B = bytesutil.ResizeNoCopyNoOverallocate(bb.B, 64*1024)
-			for {
-				bb.Reset()
-				bb.B = bb.B[:cap(bb.B)]
-				n, remoteAddr, err := ln.ReadFrom(bb.B)
-				if err != nil {
-					udpErrorsTotal.Inc()
-					var ne net.Error
-					if errors.As(err, &ne) {
-						if ne.Temporary() {
-							logger.Errorf("syslog: temporary error when listening for UDP at %q: %s", localAddr, err)
-							time.Sleep(time.Second)
-							continue
-						}
-						if strings.Contains(err.Error(), "use of closed network connection") {
-							break
-						}
-					}
-					logger.Errorf("syslog: cannot read UDP data from %s at %s: %s", remoteAddr, localAddr, err)
-					continue
-				}
-				bb.B = bb.B[:n]
-				udpRequestsTotal.Inc()
-				if err := processStream(bb.NewReader(), compressMethod, useLocalTimestamp, cp); err != nil {
-					logger.Errorf("syslog: cannot process UDP data from %s at %s: %s", remoteAddr, localAddr, err)
-				}
-			}
-		}()
-	}
-	wg.Wait()
-}
-
-func serveTCP(ln net.Listener, tenantID logstorage.TenantID, compressMethod string, useLocalTimestamp bool) {
-	var cm ingestserver.ConnsMap
-	cm.Init("syslog")
-
-	var wg sync.WaitGroup
-	addr := ln.Addr()
-	for {
-		c, err := ln.Accept()
-		if err != nil {
-			var ne net.Error
-			if errors.As(err, &ne) {
-				if ne.Temporary() {
-					logger.Errorf("syslog: temporary error when listening for TCP addr %q: %s", addr, err)
-					time.Sleep(time.Second)
-					continue
-				}
-				if strings.Contains(err.Error(), "use of closed network connection") {
-					break
-				}
-				logger.Fatalf("syslog: unrecoverable error when accepting TCP connections at %q: %s", addr, err)
-			}
-			logger.Fatalf("syslog: unexpected error when accepting TCP connections at %q: %s", addr, err)
-		}
-		if !cm.Add(c) {
-			_ = c.Close()
-			break
-		}
-
-		wg.Add(1)
-		go func() {
-			cp := insertutils.GetCommonParamsForSyslog(tenantID)
-			if err := processStream(c, compressMethod, useLocalTimestamp, cp); err != nil {
-				logger.Errorf("syslog: cannot process TCP data at %q: %s", addr, err)
-			}
-
-			cm.Delete(c)
-			_ = c.Close()
-			wg.Done()
-		}()
-	}
-
-	cm.CloseAll(0)
-	wg.Wait()
-}
-
-// processStream parses a stream of syslog messages from r and ingests them into vlstorage.
-func processStream(r io.Reader, compressMethod string, useLocalTimestamp bool, cp *insertutils.CommonParams) error {
-	if err := vlstorage.CanWriteData(); err != nil {
-		return err
-	}
-
-	lmp := cp.NewLogMessageProcessor()
-	err := processStreamInternal(r, compressMethod, useLocalTimestamp, lmp)
-	lmp.MustClose()
-
-	return err
-}
-
-func processStreamInternal(r io.Reader, compressMethod string, useLocalTimestamp bool, lmp insertutils.LogMessageProcessor) error {
-	switch compressMethod {
-	case "", "none":
-	case "gzip":
-		zr, err := common.GetGzipReader(r)
-		if err != nil {
-			return fmt.Errorf("cannot read gzipped data: %w", err)
-		}
-		r = zr
-	case "deflate":
-		zr, err := common.GetZlibReader(r)
-		if err != nil {
-			return fmt.Errorf("cannot read deflated data: %w", err)
-		}
-		r = zr
-	default:
-		logger.Panicf("BUG: unsupported compressMethod=%q; supported values: none, gzip, deflate", compressMethod)
-	}
-
-	err := processUncompressedStream(r, useLocalTimestamp, lmp)
-
-	switch compressMethod {
-	case "gzip":
-		zr := r.(*gzip.Reader)
-		common.PutGzipReader(zr)
-	case "deflate":
-		zr := r.(io.ReadCloser)
-		common.PutZlibReader(zr)
-	}
-
-	return err
-}
-
-func processUncompressedStream(r io.Reader, useLocalTimestamp bool, lmp insertutils.LogMessageProcessor) error {
-	wcr := writeconcurrencylimiter.GetReader(r)
-	defer writeconcurrencylimiter.PutReader(wcr)
-
-	slr := getSyslogLineReader(wcr)
-	defer putSyslogLineReader(slr)
-
-	n := 0
-	for {
-		ok := slr.nextLine()
-		wcr.DecConcurrency()
-		if !ok {
-			break
-		}
-
-		currentYear := int(globalCurrentYear.Load())
-		err := processLine(slr.line, currentYear, globalTimezone, useLocalTimestamp, lmp)
-		if err != nil {
-			errorsTotal.Inc()
-			return fmt.Errorf("cannot read line #%d: %s", n, err)
-		}
-		n++
-		rowsIngestedTotal.Inc()
-	}
-	return slr.Error()
-}
-
-type syslogLineReader struct {
-	line []byte
-
-	br  *bufio.Reader
-	err error
-}
-
-func (slr *syslogLineReader) reset(r io.Reader) {
-	slr.line = slr.line[:0]
-	slr.br.Reset(r)
-	slr.err = nil
-}
-
-// Error returns the last error occurred in slr.
-func (slr *syslogLineReader) Error() error {
-	if slr.err == nil || slr.err == io.EOF {
-		return nil
-	}
-	return slr.err
-}
-
-// nextLine reads the next syslog line from slr and stores it at slr.line.
-//
-// false is returned if the next line cannot be read. Error() must be called in this case
-// in order to verify whether there is an error or just slr stream has been finished.
-func (slr *syslogLineReader) nextLine() bool {
-	if slr.err != nil {
-		return false
-	}
-
-again:
-	prefix, err := slr.br.ReadSlice(' ')
-	if err != nil {
-		if err != io.EOF {
-			slr.err = fmt.Errorf("cannot read message frame prefix: %w", err)
-			return false
-		}
-		if len(prefix) == 0 {
-			slr.err = err
-			return false
-		}
-	}
-	// skip empty lines
-	for len(prefix) > 0 && prefix[0] == '\n' {
-		prefix = prefix[1:]
-	}
-	if len(prefix) == 0 {
-		// An empty prefix or a prefix with empty lines - try reading yet another prefix.
-		goto again
-	}
-
-	if prefix[0] >= '0' && prefix[0] <= '9' {
-		// This is octet-counting method. See https://www.ietf.org/archive/id/draft-gerhards-syslog-plain-tcp-07.html#msgxfer
-		msgLenStr := bytesutil.ToUnsafeString(prefix[:len(prefix)-1])
-		msgLen, err := strconv.ParseUint(msgLenStr, 10, 64)
-		if err != nil {
-			slr.err = fmt.Errorf("cannot parse message length from %q: %w", msgLenStr, err)
-			return false
-		}
-		if maxMsgLen := insertutils.MaxLineSizeBytes.IntN(); msgLen > uint64(maxMsgLen) {
-			slr.err = fmt.Errorf("cannot read message longer than %d bytes; msgLen=%d", maxMsgLen, msgLen)
-			return false
-		}
-		slr.line = slicesutil.SetLength(slr.line, int(msgLen))
-		if _, err := io.ReadFull(slr.br, slr.line); err != nil {
-			slr.err = fmt.Errorf("cannot read message with size %d bytes: %w", msgLen, err)
-			return false
-		}
-		return true
-	}
-
-	// This is octet-stuffing method. See https://www.ietf.org/archive/id/draft-gerhards-syslog-plain-tcp-07.html#octet-stuffing-legacy
-	slr.line = append(slr.line[:0], prefix...)
-	for {
-		line, err := slr.br.ReadSlice('\n')
-		if err == nil {
-			slr.line = append(slr.line, line[:len(line)-1]...)
-			return true
-		}
-		if err == io.EOF {
-			slr.line = append(slr.line, line...)
-			return true
-		}
-		if err == bufio.ErrBufferFull {
-			slr.line = append(slr.line, line...)
-			continue
-		}
-		slr.err = fmt.Errorf("cannot read message in octet-stuffing method: %w", err)
-		return false
-	}
-}
-
-func getSyslogLineReader(r io.Reader) *syslogLineReader {
-	v := syslogLineReaderPool.Get()
-	if v == nil {
-		br := bufio.NewReaderSize(r, 64*1024)
-		return &syslogLineReader{
-			br: br,
-		}
-	}
-	slr := v.(*syslogLineReader)
-	slr.reset(r)
-	return slr
-}
-
-func putSyslogLineReader(slr *syslogLineReader) {
-	syslogLineReaderPool.Put(slr)
-}
-
-var syslogLineReaderPool sync.Pool
-
-func processLine(line []byte, currentYear int, timezone *time.Location, useLocalTimestamp bool, lmp insertutils.LogMessageProcessor) error {
-	p := logstorage.GetSyslogParser(currentYear, timezone)
-	lineStr := bytesutil.ToUnsafeString(line)
-	p.Parse(lineStr)
-
-	var ts int64
-	if useLocalTimestamp {
-		ts = time.Now().UnixNano()
-	} else {
-		nsecs, err := insertutils.ExtractTimestampRFC3339NanoFromFields("timestamp", p.Fields)
-		if err != nil {
-			return fmt.Errorf("cannot get timestamp from syslog line %q: %w", line, err)
-		}
-		ts = nsecs
-	}
-	logstorage.RenameField(p.Fields, "message", "_msg")
-	lmp.AddRow(ts, p.Fields)
-	logstorage.PutSyslogParser(p)
-
-	return nil
-}
-
-var (
-	rowsIngestedTotal = metrics.NewCounter(`vl_rows_ingested_total{type="syslog"}`)
-
-	errorsTotal = metrics.NewCounter(`vl_errors_total{type="syslog"}`)
-
-	udpRequestsTotal = metrics.NewCounter(`vl_udp_reqests_total{type="syslog"}`)
-	udpErrorsTotal   = metrics.NewCounter(`vl_udp_errors_total{type="syslog"}`)
-)

app/vlinsert/syslog/syslog_test.go

@@ -1,130 +0,0 @@
-package syslog
-
-import (
-	"bytes"
-	"reflect"
-	"testing"
-	"time"
-
-	"github.com/VictoriaMetrics/VictoriaMetrics/app/vlinsert/insertutils"
-)
-
-func TestSyslogLineReader_Success(t *testing.T) {
-	f := func(data string, linesExpected []string) {
-		t.Helper()
-
-		r := bytes.NewBufferString(data)
-		slr := getSyslogLineReader(r)
-		defer putSyslogLineReader(slr)
-
-		var lines []string
-		for slr.nextLine() {
-			lines = append(lines, string(slr.line))
-		}
-		if err := slr.Error(); err != nil {
-			t.Fatalf("unexpected error: %s", err)
-		}
-		if !reflect.DeepEqual(lines, linesExpected) {
-			t.Fatalf("unexpected lines read;\ngot\n%q\nwant\n%q", lines, linesExpected)
-		}
-	}
-
-	f("", nil)
-	f("\n", nil)
-	f("\n\n\n", nil)
-
-	f("foobar", []string{"foobar"})
-	f("foobar\n", []string{"foobar\n"})
-	f("\n\nfoo\n\nbar\n\n", []string{"foo\n\nbar\n\n"})
-
-	f(`Jun  3 12:08:33 abcd systemd: Starting Update the local ESM caches...`, []string{"Jun  3 12:08:33 abcd systemd: Starting Update the local ESM caches..."})
-
-	f(`Jun  3 12:08:33 abcd systemd: Starting Update the local ESM caches...
-
-48 <165>Jun  4 12:08:33 abcd systemd[345]: abc defg<123>1 2023-06-03T17:42:12.345Z mymachine.example.com appname 12345 ID47 [exampleSDID@32473 iut="3" eventSource="Application 123 = ] 56" eventID="11211"] This is a test message with structured data.
-
-`, []string{
-		"Jun  3 12:08:33 abcd systemd: Starting Update the local ESM caches...",
-		"<165>Jun  4 12:08:33 abcd systemd[345]: abc defg",
-		`<123>1 2023-06-03T17:42:12.345Z mymachine.example.com appname 12345 ID47 [exampleSDID@32473 iut="3" eventSource="Application 123 = ] 56" eventID="11211"] This is a test message with structured data.`,
-	})
-}
-
-func TestSyslogLineReader_Failure(t *testing.T) {
-	f := func(data string) {
-		t.Helper()
-
-		r := bytes.NewBufferString(data)
-		slr := getSyslogLineReader(r)
-		defer putSyslogLineReader(slr)
-
-		if slr.nextLine() {
-			t.Fatalf("expecting failure to read the first line")
-		}
-		if err := slr.Error(); err == nil {
-			t.Fatalf("expecting non-nil error")
-		}
-	}
-
-	// invalid format for message size
-	f("12foo bar")
-
-	// too big message size
-	f("123 aa")
-	f("1233423432 abc")
-}
-
-func TestProcessStreamInternal_Success(t *testing.T) {
-	f := func(data string, currentYear, rowsExpected int, timestampsExpected []int64, resultExpected string) {
-		t.Helper()
-
-		MustInit()
-		defer MustStop()
-
-		globalTimezone = time.UTC
-		globalCurrentYear.Store(int64(currentYear))
-
-		tlp := &insertutils.TestLogMessageProcessor{}
-		r := bytes.NewBufferString(data)
-		if err := processStreamInternal(r, "", false, tlp); err != nil {
-			t.Fatalf("unexpected error: %s", err)
-		}
-		if err := tlp.Verify(rowsExpected, timestampsExpected, resultExpected); err != nil {
-			t.Fatal(err)
-		}
-	}
-
-	data := `Jun  3 12:08:33 abcd systemd: Starting Update the local ESM caches...
-
-48 <165>Jun  4 12:08:33 abcd systemd[345]: abc defg<123>1 2023-06-03T17:42:12.345Z mymachine.example.com appname 12345 ID47 [exampleSDID@32473 iut="3" eventSource="Application 123 = ] 56" eventID="11211"] This is a test message with structured data.
-`
-	currentYear := 2023
-	rowsExpected := 3
-	timestampsExpected := []int64{1685794113000000000, 1685880513000000000, 1685814132345000000}
-	resultExpected := `{"format":"rfc3164","timestamp":"","hostname":"abcd","app_name":"systemd","_msg":"Starting Update the local ESM caches..."}
-{"priority":"165","facility":"20","severity":"5","format":"rfc3164","timestamp":"","hostname":"abcd","app_name":"systemd","proc_id":"345","_msg":"abc defg"}
-{"priority":"123","facility":"15","severity":"3","format":"rfc5424","timestamp":"","hostname":"mymachine.example.com","app_name":"appname","proc_id":"12345","msg_id":"ID47","exampleSDID@32473.iut":"3","exampleSDID@32473.eventSource":"Application 123 = ] 56","exampleSDID@32473.eventID":"11211","_msg":"This is a test message with structured data."}`
-	f(data, currentYear, rowsExpected, timestampsExpected, resultExpected)
-}
-
-func TestProcessStreamInternal_Failure(t *testing.T) {
-	f := func(data string) {
-		t.Helper()
-
-		MustInit()
-		defer MustStop()
-
-		tlp := &insertutils.TestLogMessageProcessor{}
-		r := bytes.NewBufferString(data)
-		if err := processStreamInternal(r, "", false, tlp); err == nil {
-			t.Fatalf("expecting non-nil error")
-		}
-	}
-
-	// invalid format for message size
-	f("12foo bar")
-
-	// too big message size
-	f("123 foo")
-	f("123456789 bar")
-}

app/vlogsgenerator/Makefile

@@ -1,7 +0,0 @@
-# All these commands must run from repository root.
-
-vlogsgenerator:
-	APP_NAME=vlogsgenerator $(MAKE) app-local
-
-vlogsgenerator-race:
-	APP_NAME=vlogsgenerator RACE=-race $(MAKE) app-local

app/vlogsgenerator/README.md

@@ -1,158 +0,0 @@
-# vlogsgenerator
-
-Logs generator for [VictoriaLogs](https://docs.victoriametrics.com/victorialogs/).
-
-## How to build vlogsgenerator?
-
-Run `make vlogsgenerator` from the repository root. This builds `bin/vlogsgenerator` binary.
-
-## How run vlogsgenerator?
-
-`vlogsgenerator` generates logs in [JSON line format](https://jsonlines.org/) suitable for the ingestion
-via [`/insert/jsonline` endpoint at VictoriaLogs](https://docs.victoriametrics.com/victorialogs/data-ingestion/#json-stream-api).
-
-By default it writes the generated logs into `stdout`. For example, the following command writes generated logs to `stdout`:
-
-```
-bin/vlogsgenerator
-```
-
-It is possible to redirect the generated logs to file. For example, the following command writes the generated logs to `logs.json` file:
-
-```
-bin/vlogsgenerator > logs.json
-```
-
-The generated logs at `logs.json` file can be inspected with the following command:
-
-```
-head logs.json | jq .
-```
-
-Below is an example output:
-
-```json
-{
-  "_time": "2024-05-08T14:34:00.854Z",
-  "_msg": "message for the stream 8 and worker 0; ip=185.69.136.129; uuid=b4fe8f1a-c93c-dea3-ba11-5b9f0509291e; u64=8996587920687045253",
-  "host": "host_8",
-  "worker_id": "0",
-  "run_id": "f9b3deee-e6b6-7f56-5deb-1586e4e81725",
-  "const_0": "some value 0 8",
-  "const_1": "some value 1 8",
-  "const_2": "some value 2 8",
-  "var_0": "some value 0 12752539384823438260",
-  "dict_0": "warn",
-  "dict_1": "info",
-  "u8_0": "6",
-  "u16_0": "35202",
-  "u32_0": "1964973739",
-  "u64_0": "4810489083243239145",
-  "float_0": "1.868",
-  "ip_0": "250.34.75.125",
-  "timestamp_0": "1799-03-16T01:34:18.311Z",
-  "json_0": "{\"foo\":\"bar_3\",\"baz\":{\"a\":[\"x\",\"y\"]},\"f3\":NaN,\"f4\":32}"
-}
-{
-  "_time": "2024-05-08T14:34:00.854Z",
-  "_msg": "message for the stream 9 and worker 0; ip=164.244.254.194; uuid=7e8373b1-ce0d-1ce7-8e96-4bcab8955598; u64=13949903463741076522",
-  "host": "host_9",
-  "worker_id": "0",
-  "run_id": "f9b3deee-e6b6-7f56-5deb-1586e4e81725",
-  "const_0": "some value 0 9",
-  "const_1": "some value 1 9",
-  "const_2": "some value 2 9",
-  "var_0": "some value 0 5371555382075206134",
-  "dict_0": "INFO",
-  "dict_1": "FATAL",
-  "u8_0": "219",
-  "u16_0": "31459",
-  "u32_0": "3918836777",
-  "u64_0": "6593354256620219850",
-  "float_0": "1.085",
-  "ip_0": "253.151.88.158",
-  "timestamp_0": "2042-10-05T16:42:57.082Z",
-  "json_0": "{\"foo\":\"bar_5\",\"baz\":{\"a\":[\"x\",\"y\"]},\"f3\":NaN,\"f4\":27}"
-}
-```
-
-The `run_id` field uniquely identifies every `vlogsgenerator` invocation.
-
-### How to write logs to VictoriaLogs?
-
-The generated logs can be written directly to VictoriaLogs by passing the address of [`/insert/jsonline` endpoint](https://docs.victoriametrics.com/victorialogs/data-ingestion/#json-stream-api)
-to `-addr` command-line flag. For example, the following command writes the generated logs to VictoriaLogs running at `localhost`:
-
-```
-bin/vlogsgenerator -addr=http://localhost:9428/insert/jsonline
-```
-
-### Configuration
-
-`vlogsgenerator` accepts various command-line flags, which can be used for configuring the number and the shape of the generated logs.
-These flags can be inspected by running `vlogsgenerator -help`. Below are the most interesting flags:
-
-* `-start` - starting timestamp for generating logs. Logs are evenly generated on the [`-start` ... `-end`] interval.
-* `-end` - ending timestamp for generating logs. Logs are evenly generated on the [`-start` ... `-end`] interval.
-* `-activeStreams` - the number of active [log streams](https://docs.victoriametrics.com/victorialogs/keyconcepts/#stream-fields) to generate.
-* `-logsPerStream` - the number of log entries to generate per each log stream. Log entries are evenly distributed on the [`-start` ... `-end`] interval.
-
-The total number of generated logs can be calculated as `-activeStreams` * `-logsPerStream`.
-
-For example, the following command generates `1_000_000` log entries on the time range `[2024-01-01 - 2024-02-01]` across `100`
-[log streams](https://docs.victoriametrics.com/victorialogs/keyconcepts/#stream-fields), where every logs stream contains `10_000` log entries,
-and writes them to `http://localhost:9428/insert/jsonline`:
-
-```
-bin/vlogsgenerator \
-  -start=2024-01-01 -end=2024-02-01 \
-  -activeStreams=100 \
-  -logsPerStream=10_000 \
-  -addr=http://localhost:9428/insert/jsonline
-```
-
-### Churn rate
-
-It is possible to generate churn rate for active [log streams](https://docs.victoriametrics.com/victorialogs/keyconcepts/#stream-fields)
-by specifying `-totalStreams` command-line flag bigger than `-activeStreams`. For example, the following command generates
-logs for `1000` total streams, while the number of active streams equals to `100`. This means that at every time there are logs for `100` streams,
-but these streams change over the given [`-start` ... `-end`] time range, so the total number of streams on the given time range becomes `1000`:
-
-```
-bin/vlogsgenerator \
-  -start=2024-01-01 -end=2024-02-01 \
-  -activeStreams=100 \
-  -totalStreams=1_000 \
-  -logsPerStream=10_000 \
-  -addr=http://localhost:9428/insert/jsonline
-```
-
-In this case the total number of generated logs equals to `-totalStreams` * `-logsPerStream` = `10_000_000`.
-
-### Benchmark tuning
-
-By default `vlogsgenerator` generates and writes logs by a single worker. This may limit the maximum data ingestion rate during benchmarks.
-The number of workers can be changed via `-workers` command-line flag. For example, the following command generates and writes logs with `16` workers:
-
-```
-bin/vlogsgenerator \
-  -start=2024-01-01 -end=2024-02-01 \
-  -activeStreams=100 \
-  -logsPerStream=10_000 \
-  -addr=http://localhost:9428/insert/jsonline \
-  -workers=16
-```
-
-### Output statistics
-
-Every 10 seconds `vlogsgenerator` writes statistics about the generated logs into `stderr`. The frequency of the generated statistics can be adjusted via `-statInterval` command-line flag.
-For example, the following command writes statistics every 2 seconds:
-
-```
-bin/vlogsgenerator \
-  -start=2024-01-01 -end=2024-02-01 \
-  -activeStreams=100 \
-  -logsPerStream=10_000 \
-  -addr=http://localhost:9428/insert/jsonline \
-  -statInterval=2s
-```

app/vlogsgenerator/main.go

@@ -1,344 +0,0 @@
-package main
-
-import (
-	"bufio"
-	"flag"
-	"fmt"
-	"io"
-	"math"
-	"math/rand"
-	"net/http"
-	"net/url"
-	"os"
-	"strconv"
-	"sync"
-	"sync/atomic"
-	"time"
-
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/buildinfo"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/envflag"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promutils"
-)
-
-var (
-	addr    = flag.String("addr", "stdout", "HTTP address to push the generated logs to; if it is set to stdout, then logs are generated to stdout")
-	workers = flag.Int("workers", 1, "The number of workers to use to push logs to -addr")
-
-	start         = newTimeFlag("start", "-1d", "Generated logs start from this time; see https://docs.victoriametrics.com/#timestamp-formats")
-	end           = newTimeFlag("end", "0s", "Generated logs end at this time; see https://docs.victoriametrics.com/#timestamp-formats")
-	activeStreams = flag.Int("activeStreams", 100, "The number of active log streams to generate; see https://docs.victoriametrics.com/victorialogs/keyconcepts/#stream-fields")
-	totalStreams  = flag.Int("totalStreams", 0, "The number of total log streams; if -totalStreams > -activeStreams, then some active streams are substituted with new streams "+
-		"during data generation")
-	logsPerStream     = flag.Int64("logsPerStream", 1_000, "The number of log entries to generate per each log stream. Log entries are evenly distributed between -start and -end")
-	constFieldsPerLog = flag.Int("constFieldsPerLog", 3, "The number of fields with constaint values to generate per each log entry; "+
-		"see https://docs.victoriametrics.com/victorialogs/keyconcepts/#data-model")
-	varFieldsPerLog = flag.Int("varFieldsPerLog", 1, "The number of fields with variable values to generate per each log entry; "+
-		"see https://docs.victoriametrics.com/victorialogs/keyconcepts/#data-model")
-	dictFieldsPerLog = flag.Int("dictFieldsPerLog", 2, "The number of fields with up to 8 different values to generate per each log entry; "+
-		"see https://docs.victoriametrics.com/victorialogs/keyconcepts/#data-model")
-	u8FieldsPerLog = flag.Int("u8FieldsPerLog", 1, "The number of fields with uint8 values to generate per each log entry; "+
-		"see https://docs.victoriametrics.com/victorialogs/keyconcepts/#data-model")
-	u16FieldsPerLog = flag.Int("u16FieldsPerLog", 1, "The number of fields with uint16 values to generate per each log entry; "+
-		"see https://docs.victoriametrics.com/victorialogs/keyconcepts/#data-model")
-	u32FieldsPerLog = flag.Int("u32FieldsPerLog", 1, "The number of fields with uint32 values to generate per each log entry; "+
-		"see https://docs.victoriametrics.com/victorialogs/keyconcepts/#data-model")
-	u64FieldsPerLog = flag.Int("u64FieldsPerLog", 1, "The number of fields with uint64 values to generate per each log entry; "+
-		"see https://docs.victoriametrics.com/victorialogs/keyconcepts/#data-model")
-	floatFieldsPerLog = flag.Int("floatFieldsPerLog", 1, "The number of fields with float64 values to generate per each log entry; "+
-		"see https://docs.victoriametrics.com/victorialogs/keyconcepts/#data-model")
-	ipFieldsPerLog = flag.Int("ipFieldsPerLog", 1, "The number of fields with IPv4 values to generate per each log entry; "+
-		"see https://docs.victoriametrics.com/victorialogs/keyconcepts/#data-model")
-	timestampFieldsPerLog = flag.Int("timestampFieldsPerLog", 1, "The number of fields with ISO8601 timestamps per each log entry; "+
-		"see https://docs.victoriametrics.com/victorialogs/keyconcepts/#data-model")
-	jsonFieldsPerLog = flag.Int("jsonFieldsPerLog", 1, "The number of JSON fields to generate per each log entry; "+
-		"see https://docs.victoriametrics.com/victorialogs/keyconcepts/#data-model")
-
-	statInterval = flag.Duration("statInterval", 10*time.Second, "The interval between publishing the stats")
-)
-
-func main() {
-	// Write flags and help message to stdout, since it is easier to grep or pipe.
-	flag.CommandLine.SetOutput(os.Stdout)
-	envflag.Parse()
-	buildinfo.Init()
-	logger.Init()
-
-	var remoteWriteURL *url.URL
-	if *addr != "stdout" {
-		urlParsed, err := url.Parse(*addr)
-		if err != nil {
-			logger.Fatalf("cannot parse -addr=%q: %s", *addr, err)
-		}
-		qs, err := url.ParseQuery(urlParsed.RawQuery)
-		if err != nil {
-			logger.Fatalf("cannot parse query string in -addr=%q: %w", *addr, err)
-		}
-		qs.Set("_stream_fields", "host,worker_id")
-		urlParsed.RawQuery = qs.Encode()
-		remoteWriteURL = urlParsed
-	}
-
-	if start.nsec >= end.nsec {
-		logger.Fatalf("-start=%s must be smaller than -end=%s", start, end)
-	}
-	if *activeStreams <= 0 {
-		logger.Fatalf("-activeStreams must be bigger than 0; got %d", *activeStreams)
-	}
-	if *logsPerStream <= 0 {
-		logger.Fatalf("-logsPerStream must be bigger than 0; got %d", *logsPerStream)
-	}
-	if *totalStreams < *activeStreams {
-		*totalStreams = *activeStreams
-	}
-
-	cfg := &workerConfig{
-		url:           remoteWriteURL,
-		activeStreams: *activeStreams,
-		totalStreams:  *totalStreams,
-	}
-
-	// divide total and active streams among workers
-	if *workers <= 0 {
-		logger.Fatalf("-workers must be bigger than 0; got %d", *workers)
-	}
-	if *workers > *activeStreams {
-		logger.Fatalf("-workers=%d cannot exceed -activeStreams=%d", *workers, *activeStreams)
-	}
-	cfg.activeStreams /= *workers
-	cfg.totalStreams /= *workers
-
-	logger.Infof("start -workers=%d workers for ingesting -logsPerStream=%d log entries per each -totalStreams=%d (-activeStreams=%d) on a time range -start=%s, -end=%s to -addr=%s",
-		*workers, *logsPerStream, *totalStreams, *activeStreams, toRFC3339(start.nsec), toRFC3339(end.nsec), *addr)
-
-	startTime := time.Now()
-	var wg sync.WaitGroup
-	for i := 0; i < *workers; i++ {
-		wg.Add(1)
-		go func(workerID int) {
-			defer wg.Done()
-			generateAndPushLogs(cfg, workerID)
-		}(i)
-	}
-
-	go func() {
-		prevEntries := uint64(0)
-		prevBytes := uint64(0)
-		ticker := time.NewTicker(*statInterval)
-		for range ticker.C {
-			currEntries := logEntriesCount.Load()
-			deltaEntries := currEntries - prevEntries
-			rateEntries := float64(deltaEntries) / statInterval.Seconds()
-
-			currBytes := bytesGenerated.Load()
-			deltaBytes := currBytes - prevBytes
-			rateBytes := float64(deltaBytes) / statInterval.Seconds()
-			logger.Infof("generated %dK log entries (%dK total) at %.0fK entries/sec, %dMB (%dMB total) at %.0fMB/sec",
-				deltaEntries/1e3, currEntries/1e3, rateEntries/1e3, deltaBytes/1e6, currBytes/1e6, rateBytes/1e6)
-
-			prevEntries = currEntries
-			prevBytes = currBytes
-		}
-	}()
-
-	wg.Wait()
-
-	dSecs := time.Since(startTime).Seconds()
-	currEntries := logEntriesCount.Load()
-	currBytes := bytesGenerated.Load()
-	rateEntries := float64(currEntries) / dSecs
-	rateBytes := float64(currBytes) / dSecs
-	logger.Infof("ingested %dK log entries (%dMB) in %.3f seconds; avg ingestion rate: %.0fK entries/sec, %.0fMB/sec", currEntries/1e3, currBytes/1e6, dSecs, rateEntries/1e3, rateBytes/1e6)
-}
-
-var logEntriesCount atomic.Uint64
-
-var bytesGenerated atomic.Uint64
-
-type workerConfig struct {
-	url           *url.URL
-	activeStreams int
-	totalStreams  int
-}
-
-type statWriter struct {
-	w io.Writer
-}
-
-func (sw *statWriter) Write(p []byte) (int, error) {
-	bytesGenerated.Add(uint64(len(p)))
-	return sw.w.Write(p)
-}
-
-func generateAndPushLogs(cfg *workerConfig, workerID int) {
-	pr, pw := io.Pipe()
-	sw := &statWriter{
-		w: pw,
-	}
-	bw := bufio.NewWriter(sw)
-	doneCh := make(chan struct{})
-	go func() {
-		generateLogs(bw, workerID, cfg.activeStreams, cfg.totalStreams)
-		_ = bw.Flush()
-		_ = pw.Close()
-		close(doneCh)
-	}()
-
-	if cfg.url == nil {
-		_, err := io.Copy(os.Stdout, pr)
-		if err != nil {
-			logger.Fatalf("unexpected error when writing logs to stdout: %s", err)
-		}
-		return
-	}
-
-	req, err := http.NewRequest("POST", cfg.url.String(), pr)
-	if err != nil {
-		logger.Fatalf("cannot create request to %q: %s", cfg.url, err)
-	}
-
-	resp, err := http.DefaultClient.Do(req)
-	if err != nil {
-		logger.Fatalf("cannot perform request to %q: %s", cfg.url, err)
-	}
-	if resp.StatusCode/100 != 2 {
-		logger.Fatalf("unexpected status code got from %q: %d; want 2xx", cfg.url, err)
-	}
-
-	// Wait until all the generateLogs goroutine is finished.
-	<-doneCh
-}
-
-func generateLogs(bw *bufio.Writer, workerID, activeStreams, totalStreams int) {
-	streamLifetime := int64(float64(end.nsec-start.nsec) * (float64(activeStreams) / float64(totalStreams)))
-	streamStep := int64(float64(end.nsec-start.nsec) / float64(totalStreams-activeStreams+1))
-	step := streamLifetime / (*logsPerStream - 1)
-
-	currNsec := start.nsec
-	for currNsec < end.nsec {
-		firstStreamID := int((currNsec - start.nsec) / streamStep)
-		generateLogsAtTimestamp(bw, workerID, currNsec, firstStreamID, activeStreams)
-		currNsec += step
-	}
-}
-
-var runID = toUUID(rand.Uint64(), rand.Uint64())
-
-func generateLogsAtTimestamp(bw *bufio.Writer, workerID int, ts int64, firstStreamID, activeStreams int) {
-	streamID := firstStreamID
-	timeStr := toRFC3339(ts)
-	for i := 0; i < activeStreams; i++ {
-		ip := toIPv4(rand.Uint32())
-		uuid := toUUID(rand.Uint64(), rand.Uint64())
-		fmt.Fprintf(bw, `{"_time":%q,"_msg":"message for the stream %d and worker %d; ip=%s; uuid=%s; u64=%d","host":"host_%d","worker_id":"%d"`,
-			timeStr, streamID, workerID, ip, uuid, rand.Uint64(), streamID, workerID)
-		fmt.Fprintf(bw, `,"run_id":"%s"`, runID)
-		for j := 0; j < *constFieldsPerLog; j++ {
-			fmt.Fprintf(bw, `,"const_%d":"some value %d %d"`, j, j, streamID)
-		}
-		for j := 0; j < *varFieldsPerLog; j++ {
-			fmt.Fprintf(bw, `,"var_%d":"some value %d %d"`, j, j, rand.Uint64())
-		}
-		for j := 0; j < *dictFieldsPerLog; j++ {
-			fmt.Fprintf(bw, `,"dict_%d":"%s"`, j, dictValues[rand.Intn(len(dictValues))])
-		}
-		for j := 0; j < *u8FieldsPerLog; j++ {
-			fmt.Fprintf(bw, `,"u8_%d":"%d"`, j, uint8(rand.Uint32()))
-		}
-		for j := 0; j < *u16FieldsPerLog; j++ {
-			fmt.Fprintf(bw, `,"u16_%d":"%d"`, j, uint16(rand.Uint32()))
-		}
-		for j := 0; j < *u32FieldsPerLog; j++ {
-			fmt.Fprintf(bw, `,"u32_%d":"%d"`, j, rand.Uint32())
-		}
-		for j := 0; j < *u64FieldsPerLog; j++ {
-			fmt.Fprintf(bw, `,"u64_%d":"%d"`, j, rand.Uint64())
-		}
-		for j := 0; j < *floatFieldsPerLog; j++ {
-			fmt.Fprintf(bw, `,"float_%d":"%v"`, j, math.Round(10_000*rand.Float64())/1000)
-		}
-		for j := 0; j < *ipFieldsPerLog; j++ {
-			ip := toIPv4(rand.Uint32())
-			fmt.Fprintf(bw, `,"ip_%d":"%s"`, j, ip)
-		}
-		for j := 0; j < *timestampFieldsPerLog; j++ {
-			timestamp := toISO8601(int64(rand.Uint64()))
-			fmt.Fprintf(bw, `,"timestamp_%d":"%s"`, j, timestamp)
-		}
-		for j := 0; j < *jsonFieldsPerLog; j++ {
-			fmt.Fprintf(bw, `,"json_%d":"{\"foo\":\"bar_%d\",\"baz\":{\"a\":[\"x\",\"y\"]},\"f3\":NaN,\"f4\":%d}"`, j, rand.Intn(10), rand.Intn(100))
-		}
-		fmt.Fprintf(bw, "}\n")
-
-		logEntriesCount.Add(1)
-		streamID++
-	}
-}
-
-var dictValues = []string{
-	"debug",
-	"info",
-	"warn",
-	"error",
-	"fatal",
-	"ERROR",
-	"FATAL",
-	"INFO",
-}
-
-func newTimeFlag(name, defaultValue, description string) *timeFlag {
-	var tf timeFlag
-	if err := tf.Set(defaultValue); err != nil {
-		logger.Panicf("invalid defaultValue=%q for flag %q: %w", defaultValue, name, err)
-	}
-	flag.Var(&tf, name, description)
-	return &tf
-}
-
-type timeFlag struct {
-	s    string
-	nsec int64
-}
-
-func (tf *timeFlag) Set(s string) error {
-	msec, err := promutils.ParseTimeMsec(s)
-	if err != nil {
-		return fmt.Errorf("cannot parse time from %q: %w", s, err)
-	}
-	tf.s = s
-	tf.nsec = msec * 1e6
-	return nil
-}
-
-func (tf *timeFlag) String() string {
-	return tf.s
-}
-
-func toRFC3339(nsec int64) string {
-	return time.Unix(0, nsec).UTC().Format(time.RFC3339Nano)
-}
-
-func toISO8601(nsec int64) string {
-	return time.Unix(0, nsec).UTC().Format("2006-01-02T15:04:05.000Z")
-}
-
-func toIPv4(n uint32) string {
-	dst := make([]byte, 0, len("255.255.255.255"))
-	dst = marshalUint64(dst, uint64(n>>24))
-	dst = append(dst, '.')
-	dst = marshalUint64(dst, uint64((n>>16)&0xff))
-	dst = append(dst, '.')
-	dst = marshalUint64(dst, uint64((n>>8)&0xff))
-	dst = append(dst, '.')
-	dst = marshalUint64(dst, uint64(n&0xff))
-	return string(dst)
-}
-
-func toUUID(a, b uint64) string {
-	return fmt.Sprintf("%08x-%04x-%04x-%04x-%012x", a&(1<<32-1), (a>>32)&(1<<16-1), (a >> 48), b&(1<<16-1), b>>16)
-}
-
-// marshalUint64 appends string representation of n to dst and returns the result.
-func marshalUint64(dst []byte, n uint64) []byte {
-	return strconv.AppendUint(dst, n, 10)
-}

app/vlselect/logsql/buffered_writer.go

@@ -1,47 +0,0 @@
-package logsql
-
-import (
-	"bufio"
-	"io"
-	"sync"
-)
-
-func getBufferedWriter(w io.Writer) *bufferedWriter {
-	v := bufferedWriterPool.Get()
-	if v == nil {
-		return &bufferedWriter{
-			bw: bufio.NewWriter(w),
-		}
-	}
-	bw := v.(*bufferedWriter)
-	bw.bw.Reset(w)
-	return bw
-}
-
-func putBufferedWriter(bw *bufferedWriter) {
-	bw.reset()
-	bufferedWriterPool.Put(bw)
-}
-
-var bufferedWriterPool sync.Pool
-
-type bufferedWriter struct {
-	mu sync.Mutex
-	bw *bufio.Writer
-}
-
-func (bw *bufferedWriter) reset() {
-	// nothing to do
-}
-
-func (bw *bufferedWriter) WriteIgnoreErrors(p []byte) {
-	bw.mu.Lock()
-	_, _ = bw.bw.Write(p)
-	bw.mu.Unlock()
-}
-
-func (bw *bufferedWriter) FlushIgnoreErrors() {
-	bw.mu.Lock()
-	_ = bw.bw.Flush()
-	bw.mu.Unlock()
-}

app/vlselect/logsql/hits_response.qtpl

@@ -1,70 +0,0 @@
-{% import (
-	"slices"
-
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
-) %}
-
-{% stripspace %}
-
-// FieldsForHits formats labels for /select/logsql/hits response
-{% func FieldsForHits(columns []logstorage.BlockColumn, rowIdx int) %}
-{
-	{% if len(columns) > 0 %}
-		{%q= columns[0].Name %}:{%q= columns[0].Values[rowIdx] %}
-		{% for _, c := range columns[1:] %}
-			,{%q= c.Name %}:{%q= c.Values[rowIdx] %}
-		{% endfor %}
-	{% endif %}
-}
-{% endfunc %}
-
-{% func HitsSeries(m map[string]*hitsSeries) %}
-{
-	{% code
-		sortedKeys := make([]string, 0, len(m))
-		for k := range m {
-			sortedKeys = append(sortedKeys, k)
-		}
-		slices.Sort(sortedKeys)
-	%}
-	"hits":[
-		{% if len(sortedKeys) > 0 %}
-			{%= hitsSeriesLine(m, sortedKeys[0]) %}
-			{% for _, k := range sortedKeys[1:] %}
-				,{%= hitsSeriesLine(m, k) %}
-			{% endfor %}
-		{% endif %}
-	]
-}
-{% endfunc %}
-
-{% func hitsSeriesLine(m map[string]*hitsSeries, k string) %}
-{
-	{% code
-		hs := m[k]
-		hs.sort()
-		timestamps := hs.timestamps
-		hits := hs.hits
-	%}
-	"fields":{%s= k %},
-	"timestamps":[
-		{% if len(timestamps) > 0 %}
-			{%q= timestamps[0] %}
-			{% for _, ts := range timestamps[1:] %}
-				,{%q= ts %}
-			{% endfor %}
-		{% endif %}
-	],
-	"values":[
-		{% if len(hits) > 0 %}
-			{%dul= hits[0] %}
-			{% for _, v := range hits[1:] %}
-				,{%dul= v %}
-			{% endfor %}
-		{% endif %}
-	],
-	"total":{%dul= hs.hitsTotal %}
-}
-{% endfunc %}
-
-{% endstripspace %}

app/vlselect/logsql/hits_response.qtpl.go

@@ -1,223 +0,0 @@
-// Code generated by qtc from "hits_response.qtpl". DO NOT EDIT.
-// See https://github.com/valyala/quicktemplate for details.
-
-//line app/vlselect/logsql/hits_response.qtpl:1
-package logsql
-
-//line app/vlselect/logsql/hits_response.qtpl:1
-import (
-	"slices"
-
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
-)
-
-// FieldsForHits formats labels for /select/logsql/hits response
-
-//line app/vlselect/logsql/hits_response.qtpl:10
-import (
-	qtio422016 "io"
-
-	qt422016 "github.com/valyala/quicktemplate"
-)
-
-//line app/vlselect/logsql/hits_response.qtpl:10
-var (
-	_ = qtio422016.Copy
-	_ = qt422016.AcquireByteBuffer
-)
-
-//line app/vlselect/logsql/hits_response.qtpl:10
-func StreamFieldsForHits(qw422016 *qt422016.Writer, columns []logstorage.BlockColumn, rowIdx int) {
-//line app/vlselect/logsql/hits_response.qtpl:10
-	qw422016.N().S(`{`)
-//line app/vlselect/logsql/hits_response.qtpl:12
-	if len(columns) > 0 {
-//line app/vlselect/logsql/hits_response.qtpl:13
-		qw422016.N().Q(columns[0].Name)
-//line app/vlselect/logsql/hits_response.qtpl:13
-		qw422016.N().S(`:`)
-//line app/vlselect/logsql/hits_response.qtpl:13
-		qw422016.N().Q(columns[0].Values[rowIdx])
-//line app/vlselect/logsql/hits_response.qtpl:14
-		for _, c := range columns[1:] {
-//line app/vlselect/logsql/hits_response.qtpl:14
-			qw422016.N().S(`,`)
-//line app/vlselect/logsql/hits_response.qtpl:15
-			qw422016.N().Q(c.Name)
-//line app/vlselect/logsql/hits_response.qtpl:15
-			qw422016.N().S(`:`)
-//line app/vlselect/logsql/hits_response.qtpl:15
-			qw422016.N().Q(c.Values[rowIdx])
-//line app/vlselect/logsql/hits_response.qtpl:16
-		}
-//line app/vlselect/logsql/hits_response.qtpl:17
-	}
-//line app/vlselect/logsql/hits_response.qtpl:17
-	qw422016.N().S(`}`)
-//line app/vlselect/logsql/hits_response.qtpl:19
-}
-
-//line app/vlselect/logsql/hits_response.qtpl:19
-func WriteFieldsForHits(qq422016 qtio422016.Writer, columns []logstorage.BlockColumn, rowIdx int) {
-//line app/vlselect/logsql/hits_response.qtpl:19
-	qw422016 := qt422016.AcquireWriter(qq422016)
-//line app/vlselect/logsql/hits_response.qtpl:19
-	StreamFieldsForHits(qw422016, columns, rowIdx)
-//line app/vlselect/logsql/hits_response.qtpl:19
-	qt422016.ReleaseWriter(qw422016)
-//line app/vlselect/logsql/hits_response.qtpl:19
-}
-
-//line app/vlselect/logsql/hits_response.qtpl:19
-func FieldsForHits(columns []logstorage.BlockColumn, rowIdx int) string {
-//line app/vlselect/logsql/hits_response.qtpl:19
-	qb422016 := qt422016.AcquireByteBuffer()
-//line app/vlselect/logsql/hits_response.qtpl:19
-	WriteFieldsForHits(qb422016, columns, rowIdx)
-//line app/vlselect/logsql/hits_response.qtpl:19
-	qs422016 := string(qb422016.B)
-//line app/vlselect/logsql/hits_response.qtpl:19
-	qt422016.ReleaseByteBuffer(qb422016)
-//line app/vlselect/logsql/hits_response.qtpl:19
-	return qs422016
-//line app/vlselect/logsql/hits_response.qtpl:19
-}
-
-//line app/vlselect/logsql/hits_response.qtpl:21
-func StreamHitsSeries(qw422016 *qt422016.Writer, m map[string]*hitsSeries) {
-//line app/vlselect/logsql/hits_response.qtpl:21
-	qw422016.N().S(`{`)
-//line app/vlselect/logsql/hits_response.qtpl:24
-	sortedKeys := make([]string, 0, len(m))
-	for k := range m {
-		sortedKeys = append(sortedKeys, k)
-	}
-	slices.Sort(sortedKeys)
-
-//line app/vlselect/logsql/hits_response.qtpl:29
-	qw422016.N().S(`"hits":[`)
-//line app/vlselect/logsql/hits_response.qtpl:31
-	if len(sortedKeys) > 0 {
-//line app/vlselect/logsql/hits_response.qtpl:32
-		streamhitsSeriesLine(qw422016, m, sortedKeys[0])
-//line app/vlselect/logsql/hits_response.qtpl:33
-		for _, k := range sortedKeys[1:] {
-//line app/vlselect/logsql/hits_response.qtpl:33
-			qw422016.N().S(`,`)
-//line app/vlselect/logsql/hits_response.qtpl:34
-			streamhitsSeriesLine(qw422016, m, k)
-//line app/vlselect/logsql/hits_response.qtpl:35
-		}
-//line app/vlselect/logsql/hits_response.qtpl:36
-	}
-//line app/vlselect/logsql/hits_response.qtpl:36
-	qw422016.N().S(`]}`)
-//line app/vlselect/logsql/hits_response.qtpl:39
-}
-
-//line app/vlselect/logsql/hits_response.qtpl:39
-func WriteHitsSeries(qq422016 qtio422016.Writer, m map[string]*hitsSeries) {
-//line app/vlselect/logsql/hits_response.qtpl:39
-	qw422016 := qt422016.AcquireWriter(qq422016)
-//line app/vlselect/logsql/hits_response.qtpl:39
-	StreamHitsSeries(qw422016, m)
-//line app/vlselect/logsql/hits_response.qtpl:39
-	qt422016.ReleaseWriter(qw422016)
-//line app/vlselect/logsql/hits_response.qtpl:39
-}
-
-//line app/vlselect/logsql/hits_response.qtpl:39
-func HitsSeries(m map[string]*hitsSeries) string {
-//line app/vlselect/logsql/hits_response.qtpl:39
-	qb422016 := qt422016.AcquireByteBuffer()
-//line app/vlselect/logsql/hits_response.qtpl:39
-	WriteHitsSeries(qb422016, m)
-//line app/vlselect/logsql/hits_response.qtpl:39
-	qs422016 := string(qb422016.B)
-//line app/vlselect/logsql/hits_response.qtpl:39
-	qt422016.ReleaseByteBuffer(qb422016)
-//line app/vlselect/logsql/hits_response.qtpl:39
-	return qs422016
-//line app/vlselect/logsql/hits_response.qtpl:39
-}
-
-//line app/vlselect/logsql/hits_response.qtpl:41
-func streamhitsSeriesLine(qw422016 *qt422016.Writer, m map[string]*hitsSeries, k string) {
-//line app/vlselect/logsql/hits_response.qtpl:41
-	qw422016.N().S(`{`)
-//line app/vlselect/logsql/hits_response.qtpl:44
-	hs := m[k]
-	hs.sort()
-	timestamps := hs.timestamps
-	hits := hs.hits
-
-//line app/vlselect/logsql/hits_response.qtpl:48
-	qw422016.N().S(`"fields":`)
-//line app/vlselect/logsql/hits_response.qtpl:49
-	qw422016.N().S(k)
-//line app/vlselect/logsql/hits_response.qtpl:49
-	qw422016.N().S(`,"timestamps":[`)
-//line app/vlselect/logsql/hits_response.qtpl:51
-	if len(timestamps) > 0 {
-//line app/vlselect/logsql/hits_response.qtpl:52
-		qw422016.N().Q(timestamps[0])
-//line app/vlselect/logsql/hits_response.qtpl:53
-		for _, ts := range timestamps[1:] {
-//line app/vlselect/logsql/hits_response.qtpl:53
-			qw422016.N().S(`,`)
-//line app/vlselect/logsql/hits_response.qtpl:54
-			qw422016.N().Q(ts)
-//line app/vlselect/logsql/hits_response.qtpl:55
-		}
-//line app/vlselect/logsql/hits_response.qtpl:56
-	}
-//line app/vlselect/logsql/hits_response.qtpl:56
-	qw422016.N().S(`],"values":[`)
-//line app/vlselect/logsql/hits_response.qtpl:59
-	if len(hits) > 0 {
-//line app/vlselect/logsql/hits_response.qtpl:60
-		qw422016.N().DUL(hits[0])
-//line app/vlselect/logsql/hits_response.qtpl:61
-		for _, v := range hits[1:] {
-//line app/vlselect/logsql/hits_response.qtpl:61
-			qw422016.N().S(`,`)
-//line app/vlselect/logsql/hits_response.qtpl:62
-			qw422016.N().DUL(v)
-//line app/vlselect/logsql/hits_response.qtpl:63
-		}
-//line app/vlselect/logsql/hits_response.qtpl:64
-	}
-//line app/vlselect/logsql/hits_response.qtpl:64
-	qw422016.N().S(`],"total":`)
-//line app/vlselect/logsql/hits_response.qtpl:66
-	qw422016.N().DUL(hs.hitsTotal)
-//line app/vlselect/logsql/hits_response.qtpl:66
-	qw422016.N().S(`}`)
-//line app/vlselect/logsql/hits_response.qtpl:68
-}
-
-//line app/vlselect/logsql/hits_response.qtpl:68
-func writehitsSeriesLine(qq422016 qtio422016.Writer, m map[string]*hitsSeries, k string) {
-//line app/vlselect/logsql/hits_response.qtpl:68
-	qw422016 := qt422016.AcquireWriter(qq422016)
-//line app/vlselect/logsql/hits_response.qtpl:68
-	streamhitsSeriesLine(qw422016, m, k)
-//line app/vlselect/logsql/hits_response.qtpl:68
-	qt422016.ReleaseWriter(qw422016)
-//line app/vlselect/logsql/hits_response.qtpl:68
-}
-
-//line app/vlselect/logsql/hits_response.qtpl:68
-func hitsSeriesLine(m map[string]*hitsSeries, k string) string {
-//line app/vlselect/logsql/hits_response.qtpl:68
-	qb422016 := qt422016.AcquireByteBuffer()
-//line app/vlselect/logsql/hits_response.qtpl:68
-	writehitsSeriesLine(qb422016, m, k)
-//line app/vlselect/logsql/hits_response.qtpl:68
-	qs422016 := string(qb422016.B)
-//line app/vlselect/logsql/hits_response.qtpl:68
-	qt422016.ReleaseByteBuffer(qb422016)
-//line app/vlselect/logsql/hits_response.qtpl:68
-	return qs422016
-//line app/vlselect/logsql/hits_response.qtpl:68
-}

app/vlselect/logsql/logsql.go

@@ -1,770 +1,66 @@
 package logsql
 
 import (
-	"context"
-	"fmt"
-	"math"
 	"net/http"
-	"sort"
-	"strconv"
-	"strings"
-	"sync"
-	"time"
-
-	"github.com/VictoriaMetrics/metrics"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vlstorage"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httputils"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promutils"
 )
 
-// ProcessHitsRequest handles /select/logsql/hits request.
-//
-// See https://docs.victoriametrics.com/victorialogs/querying/#querying-hits-stats
-func ProcessHitsRequest(ctx context.Context, w http.ResponseWriter, r *http.Request) {
-	q, tenantIDs, err := parseCommonArgs(r)
-	if err != nil {
-		httpserver.Errorf(w, r, "%s", err)
-		return
-	}
-
-	// Obtain step
-	stepStr := r.FormValue("step")
-	if stepStr == "" {
-		stepStr = "1d"
-	}
-	step, err := promutils.ParseDuration(stepStr)
-	if err != nil {
-		httpserver.Errorf(w, r, "cannot parse 'step' arg: %s", err)
-		return
-	}
-	if step <= 0 {
-		httpserver.Errorf(w, r, "'step' must be bigger than zero")
-	}
-
-	// Obtain offset
-	offsetStr := r.FormValue("offset")
-	if offsetStr == "" {
-		offsetStr = "0s"
-	}
-	offset, err := promutils.ParseDuration(offsetStr)
-	if err != nil {
-		httpserver.Errorf(w, r, "cannot parse 'offset' arg: %s", err)
-		return
-	}
-
-	// Obtain field entries
-	fields := r.Form["field"]
-
-	// Obtain limit on the number of top fields entries.
-	fieldsLimit, err := httputils.GetInt(r, "fields_limit")
-	if err != nil {
-		httpserver.Errorf(w, r, "%s", err)
-		return
-	}
-	if fieldsLimit < 0 {
-		fieldsLimit = 0
-	}
-
-	// Prepare the query
-	q.AddCountByTimePipe(int64(step), int64(offset), fields)
-	q.Optimize()
-
-	var mLock sync.Mutex
-	m := make(map[string]*hitsSeries)
-	writeBlock := func(_ uint, timestamps []int64, columns []logstorage.BlockColumn) {
-		if len(columns) == 0 || len(columns[0].Values) == 0 {
-			return
-		}
-
-		timestampValues := columns[0].Values
-		hitsValues := columns[len(columns)-1].Values
-		columns = columns[1 : len(columns)-1]
-
-		bb := blockResultPool.Get()
-		for i := range timestamps {
-			timestampStr := strings.Clone(timestampValues[i])
-			hitsStr := strings.Clone(hitsValues[i])
-			hits, err := strconv.ParseUint(hitsStr, 10, 64)
-			if err != nil {
-				logger.Panicf("BUG: cannot parse hitsStr=%q: %s", hitsStr, err)
-			}
-
-			bb.Reset()
-			WriteFieldsForHits(bb, columns, i)
-
-			mLock.Lock()
-			hs, ok := m[string(bb.B)]
-			if !ok {
-				k := string(bb.B)
-				hs = &hitsSeries{}
-				m[k] = hs
-			}
-			hs.timestamps = append(hs.timestamps, timestampStr)
-			hs.hits = append(hs.hits, hits)
-			hs.hitsTotal += hits
-			mLock.Unlock()
-		}
-		blockResultPool.Put(bb)
-	}
-
-	// Execute the query
-	if err := vlstorage.RunQuery(ctx, tenantIDs, q, writeBlock); err != nil {
-		httpserver.Errorf(w, r, "cannot execute query [%s]: %s", q, err)
-		return
-	}
-
-	m = getTopHitsSeries(m, fieldsLimit)
-
-	// Write response
-	w.Header().Set("Content-Type", "application/json")
-	WriteHitsSeries(w, m)
-}
-
-func getTopHitsSeries(m map[string]*hitsSeries, fieldsLimit int) map[string]*hitsSeries {
-	if fieldsLimit <= 0 || fieldsLimit >= len(m) {
-		return m
-	}
-
-	type fieldsHits struct {
-		fieldsStr string
-		hs        *hitsSeries
-	}
-	a := make([]fieldsHits, 0, len(m))
-	for fieldsStr, hs := range m {
-		a = append(a, fieldsHits{
-			fieldsStr: fieldsStr,
-			hs:        hs,
-		})
-	}
-	sort.Slice(a, func(i, j int) bool {
-		return a[i].hs.hitsTotal > a[j].hs.hitsTotal
-	})
-
-	hitsOther := make(map[string]uint64)
-	for _, x := range a[fieldsLimit:] {
-		for i, timestampStr := range x.hs.timestamps {
-			hitsOther[timestampStr] += x.hs.hits[i]
-		}
-	}
-	var hsOther hitsSeries
-	for timestampStr, hits := range hitsOther {
-		hsOther.timestamps = append(hsOther.timestamps, timestampStr)
-		hsOther.hits = append(hsOther.hits, hits)
-		hsOther.hitsTotal += hits
-	}
-
-	mNew := make(map[string]*hitsSeries, fieldsLimit+1)
-	for _, x := range a[:fieldsLimit] {
-		mNew[x.fieldsStr] = x.hs
-	}
-	mNew["{}"] = &hsOther
-
-	return mNew
-}
-
-type hitsSeries struct {
-	hitsTotal  uint64
-	timestamps []string
-	hits       []uint64
-}
-
-func (hs *hitsSeries) sort() {
-	sort.Sort(hs)
-}
-
-func (hs *hitsSeries) Len() int {
-	return len(hs.timestamps)
-}
-
-func (hs *hitsSeries) Swap(i, j int) {
-	hs.timestamps[i], hs.timestamps[j] = hs.timestamps[j], hs.timestamps[i]
-	hs.hits[i], hs.hits[j] = hs.hits[j], hs.hits[i]
-}
-
-func (hs *hitsSeries) Less(i, j int) bool {
-	return hs.timestamps[i] < hs.timestamps[j]
-}
-
-// ProcessFieldNamesRequest handles /select/logsql/field_names request.
-//
-// See https://docs.victoriametrics.com/victorialogs/querying/#querying-field-names
-func ProcessFieldNamesRequest(ctx context.Context, w http.ResponseWriter, r *http.Request) {
-	q, tenantIDs, err := parseCommonArgs(r)
-	if err != nil {
-		httpserver.Errorf(w, r, "%s", err)
-		return
-	}
-
-	// Obtain field names for the given query
-	q.Optimize()
-	fieldNames, err := vlstorage.GetFieldNames(ctx, tenantIDs, q)
-	if err != nil {
-		httpserver.Errorf(w, r, "cannot obtain field names: %s", err)
-		return
-	}
-
-	// Write results
-	w.Header().Set("Content-Type", "application/json")
-	WriteValuesWithHitsJSON(w, fieldNames)
-}
-
-// ProcessFieldValuesRequest handles /select/logsql/field_values request.
-//
-// See https://docs.victoriametrics.com/victorialogs/querying/#querying-field-values
-func ProcessFieldValuesRequest(ctx context.Context, w http.ResponseWriter, r *http.Request) {
-	q, tenantIDs, err := parseCommonArgs(r)
-	if err != nil {
-		httpserver.Errorf(w, r, "%s", err)
-		return
-	}
-
-	// Parse fieldName query arg
-	fieldName := r.FormValue("field")
-	if fieldName == "" {
-		httpserver.Errorf(w, r, "missing 'field' query arg")
-		return
-	}
-
-	// Parse limit query arg
-	limit, err := httputils.GetInt(r, "limit")
-	if err != nil {
-		httpserver.Errorf(w, r, "%s", err)
-		return
-	}
-	if limit < 0 {
-		limit = 0
-	}
-
-	// Obtain unique values for the given field
-	q.Optimize()
-	values, err := vlstorage.GetFieldValues(ctx, tenantIDs, q, fieldName, uint64(limit))
-	if err != nil {
-		httpserver.Errorf(w, r, "cannot obtain values for field %q: %s", fieldName, err)
-		return
-	}
-
-	// Write results
-	w.Header().Set("Content-Type", "application/json")
-	WriteValuesWithHitsJSON(w, values)
-}
-
-// ProcessStreamFieldNamesRequest processes /select/logsql/stream_field_names request.
-//
-// See https://docs.victoriametrics.com/victorialogs/querying/#querying-stream-field-names
-func ProcessStreamFieldNamesRequest(ctx context.Context, w http.ResponseWriter, r *http.Request) {
-	q, tenantIDs, err := parseCommonArgs(r)
-	if err != nil {
-		httpserver.Errorf(w, r, "%s", err)
-		return
-	}
-
-	// Obtain stream field names for the given query
-	q.Optimize()
-	names, err := vlstorage.GetStreamFieldNames(ctx, tenantIDs, q)
-	if err != nil {
-		httpserver.Errorf(w, r, "cannot obtain stream field names: %s", err)
-	}
-
-	// Write results
-	w.Header().Set("Content-Type", "application/json")
-	WriteValuesWithHitsJSON(w, names)
-}
-
-// ProcessStreamFieldValuesRequest processes /select/logsql/stream_field_values request.
-//
-// See https://docs.victoriametrics.com/victorialogs/querying/#querying-stream-field-values
-func ProcessStreamFieldValuesRequest(ctx context.Context, w http.ResponseWriter, r *http.Request) {
-	q, tenantIDs, err := parseCommonArgs(r)
-	if err != nil {
-		httpserver.Errorf(w, r, "%s", err)
-		return
-	}
-
-	// Parse fieldName query arg
-	fieldName := r.FormValue("field")
-	if fieldName == "" {
-		httpserver.Errorf(w, r, "missing 'field' query arg")
-		return
-	}
-
-	// Parse limit query arg
-	limit, err := httputils.GetInt(r, "limit")
-	if err != nil {
-		httpserver.Errorf(w, r, "%s", err)
-		return
-	}
-	if limit < 0 {
-		limit = 0
-	}
-
-	// Obtain stream field values for the given query and the given fieldName
-	q.Optimize()
-	values, err := vlstorage.GetStreamFieldValues(ctx, tenantIDs, q, fieldName, uint64(limit))
-	if err != nil {
-		httpserver.Errorf(w, r, "cannot obtain stream field values: %s", err)
-	}
-
-	// Write results
-	w.Header().Set("Content-Type", "application/json")
-	WriteValuesWithHitsJSON(w, values)
-}
-
-// ProcessStreamIDsRequest processes /select/logsql/stream_ids request.
-//
-// See https://docs.victoriametrics.com/victorialogs/querying/#querying-stream_ids
-func ProcessStreamIDsRequest(ctx context.Context, w http.ResponseWriter, r *http.Request) {
-	q, tenantIDs, err := parseCommonArgs(r)
-	if err != nil {
-		httpserver.Errorf(w, r, "%s", err)
-		return
-	}
-
-	// Parse limit query arg
-	limit, err := httputils.GetInt(r, "limit")
-	if err != nil {
-		httpserver.Errorf(w, r, "%s", err)
-		return
-	}
-	if limit < 0 {
-		limit = 0
-	}
-
-	// Obtain streamIDs for the given query
-	q.Optimize()
-	streamIDs, err := vlstorage.GetStreamIDs(ctx, tenantIDs, q, uint64(limit))
-	if err != nil {
-		httpserver.Errorf(w, r, "cannot obtain stream_ids: %s", err)
-	}
-
-	// Write results
-	w.Header().Set("Content-Type", "application/json")
-	WriteValuesWithHitsJSON(w, streamIDs)
-}
-
-// ProcessStreamsRequest processes /select/logsql/streams request.
-//
-// See https://docs.victoriametrics.com/victorialogs/querying/#querying-streams
-func ProcessStreamsRequest(ctx context.Context, w http.ResponseWriter, r *http.Request) {
-	q, tenantIDs, err := parseCommonArgs(r)
-	if err != nil {
-		httpserver.Errorf(w, r, "%s", err)
-		return
-	}
-
-	// Parse limit query arg
-	limit, err := httputils.GetInt(r, "limit")
-	if err != nil {
-		httpserver.Errorf(w, r, "%s", err)
-		return
-	}
-	if limit < 0 {
-		limit = 0
-	}
-
-	// Obtain streams for the given query
-	q.Optimize()
-	streams, err := vlstorage.GetStreams(ctx, tenantIDs, q, uint64(limit))
-	if err != nil {
-		httpserver.Errorf(w, r, "cannot obtain streams: %s", err)
-	}
-
-	// Write results
-	w.Header().Set("Content-Type", "application/json")
-	WriteValuesWithHitsJSON(w, streams)
-}
-
-// ProcessLiveTailRequest processes live tailing request to /select/logsq/tail
-func ProcessLiveTailRequest(ctx context.Context, w http.ResponseWriter, r *http.Request) {
-	liveTailRequests.Inc()
-	defer liveTailRequests.Dec()
-
-	q, tenantIDs, err := parseCommonArgs(r)
-	if err != nil {
-		httpserver.Errorf(w, r, "%s", err)
-		return
-	}
-	if !q.CanLiveTail() {
-		httpserver.Errorf(w, r, "the query [%s] cannot be used in live tailing; see https://docs.victoriametrics.com/victorialogs/querying/#live-tailing for details", q)
-	}
-	q.Optimize()
-
-	refreshIntervalMsecs, err := httputils.GetDuration(r, "refresh_interval", 1000)
-	if err != nil {
-		httpserver.Errorf(w, r, "%s", err)
-		return
-	}
-	refreshInterval := time.Millisecond * time.Duration(refreshIntervalMsecs)
-
-	ctxWithCancel, cancel := context.WithCancel(ctx)
-	tp := newTailProcessor(cancel)
-
-	ticker := time.NewTicker(refreshInterval)
-	defer ticker.Stop()
-
-	end := time.Now().UnixNano()
-	doneCh := ctxWithCancel.Done()
-	flusher, ok := w.(http.Flusher)
-	if !ok {
-		logger.Panicf("BUG: it is expected that http.ResponseWriter (%T) supports http.Flusher interface", w)
-	}
-	for {
-		start := end - tailOffsetNsecs
-		end = time.Now().UnixNano()
-
-		qCopy := q.Clone()
-		qCopy.AddTimeFilter(start, end)
-		if err := vlstorage.RunQuery(ctxWithCancel, tenantIDs, qCopy, tp.writeBlock); err != nil {
-			httpserver.Errorf(w, r, "cannot execute tail query [%s]: %s", q, err)
-			return
-		}
-		resultRows, err := tp.getTailRows()
-		if err != nil {
-			httpserver.Errorf(w, r, "cannot get tail results for query [%q]: %s", q, err)
-			return
-		}
-		if len(resultRows) > 0 {
-			WriteJSONRows(w, resultRows)
-			flusher.Flush()
-		}
-
-		select {
-		case <-doneCh:
-			return
-		case <-ticker.C:
-		}
-	}
-}
-
-var liveTailRequests = metrics.NewCounter(`vl_live_tailing_requests`)
-
-const tailOffsetNsecs = 5e9
-
-type logRow struct {
-	timestamp int64
-	fields    []logstorage.Field
-}
-
-func sortLogRows(rows []logRow) {
-	sort.SliceStable(rows, func(i, j int) bool {
-		return rows[i].timestamp < rows[j].timestamp
-	})
-}
-
-type tailProcessor struct {
-	cancel func()
-
-	mu sync.Mutex
-
-	perStreamRows  map[string][]logRow
-	lastTimestamps map[string]int64
-
-	err error
-}
-
-func newTailProcessor(cancel func()) *tailProcessor {
-	return &tailProcessor{
-		cancel: cancel,
-
-		perStreamRows:  make(map[string][]logRow),
-		lastTimestamps: make(map[string]int64),
-	}
-}
-
-func (tp *tailProcessor) writeBlock(_ uint, timestamps []int64, columns []logstorage.BlockColumn) {
-	if len(timestamps) == 0 {
-		return
-	}
-
-	tp.mu.Lock()
-	defer tp.mu.Unlock()
-
-	if tp.err != nil {
-		return
-	}
-
-	// Make sure columns contain _time field, since it is needed for proper tail work.
-	hasTime := false
-	for _, c := range columns {
-		if c.Name == "_time" {
-			hasTime = true
-			break
-		}
-	}
-	if !hasTime {
-		tp.err = fmt.Errorf("missing _time field")
-		tp.cancel()
-		return
-	}
-
-	// Copy block rows to tp.perStreamRows
-	for i, timestamp := range timestamps {
-		streamID := ""
-		fields := make([]logstorage.Field, len(columns))
-		for j, c := range columns {
-			name := strings.Clone(c.Name)
-			value := strings.Clone(c.Values[i])
-
-			fields[j] = logstorage.Field{
-				Name:  name,
-				Value: value,
-			}
-
-			if name == "_stream_id" {
-				streamID = value
-			}
-		}
-
-		tp.perStreamRows[streamID] = append(tp.perStreamRows[streamID], logRow{
-			timestamp: timestamp,
-			fields:    fields,
-		})
-	}
-}
-
-func (tp *tailProcessor) getTailRows() ([][]logstorage.Field, error) {
-	if tp.err != nil {
-		return nil, tp.err
-	}
-
-	var resultRows []logRow
-	for streamID, rows := range tp.perStreamRows {
-		sortLogRows(rows)
-
-		lastTimestamp, ok := tp.lastTimestamps[streamID]
-		if ok {
-			// Skip already written rows
-			for len(rows) > 0 && rows[0].timestamp <= lastTimestamp {
-				rows = rows[1:]
-			}
-		}
-		if len(rows) > 0 {
-			resultRows = append(resultRows, rows...)
-			tp.lastTimestamps[streamID] = rows[len(rows)-1].timestamp
-		}
-	}
-	clear(tp.perStreamRows)
-
-	sortLogRows(resultRows)
-
-	tailRows := make([][]logstorage.Field, len(resultRows))
-	for i, row := range resultRows {
-		tailRows[i] = row.fields
-	}
-
-	return tailRows, nil
-}
-
-// ProcessQueryRequest handles /select/logsql/query request.
-//
-// See https://docs.victoriametrics.com/victorialogs/querying/#http-api
-func ProcessQueryRequest(ctx context.Context, w http.ResponseWriter, r *http.Request) {
-	q, tenantIDs, err := parseCommonArgs(r)
-	if err != nil {
-		httpserver.Errorf(w, r, "%s", err)
-		return
-	}
-
-	// Parse limit query arg
-	limit, err := httputils.GetInt(r, "limit")
-	if err != nil {
-		httpserver.Errorf(w, r, "%s", err)
-		return
-	}
-
-	bw := getBufferedWriter(w)
-	defer func() {
-		bw.FlushIgnoreErrors()
-		putBufferedWriter(bw)
-	}()
-	w.Header().Set("Content-Type", "application/stream+json")
-
-	if limit > 0 {
-		if q.CanReturnLastNResults() {
-			rows, err := getLastNQueryResults(ctx, tenantIDs, q, limit)
-			if err != nil {
-				httpserver.Errorf(w, r, "%s", err)
-				return
-			}
-			bb := blockResultPool.Get()
-			b := bb.B
-			for i := range rows {
-				b = logstorage.MarshalFieldsToJSON(b[:0], rows[i].fields)
-				b = append(b, '\n')
-				bw.WriteIgnoreErrors(b)
-			}
-			bb.B = b
-			blockResultPool.Put(bb)
-			return
-		}
-
-		q.AddPipeLimit(uint64(limit))
-	}
-	q.Optimize()
-
-	writeBlock := func(_ uint, timestamps []int64, columns []logstorage.BlockColumn) {
-		if len(columns) == 0 || len(columns[0].Values) == 0 {
-			return
-		}
-
-		bb := blockResultPool.Get()
-		for i := range timestamps {
-			WriteJSONRow(bb, columns, i)
-		}
-		bw.WriteIgnoreErrors(bb.B)
-		blockResultPool.Put(bb)
-	}
-
-	if err := vlstorage.RunQuery(ctx, tenantIDs, q, writeBlock); err != nil {
-		httpserver.Errorf(w, r, "cannot execute query [%s]: %s", q, err)
-		return
-	}
-}
-
-var blockResultPool bytesutil.ByteBufferPool
-
-type row struct {
-	timestamp int64
-	fields    []logstorage.Field
-}
-
-func getLastNQueryResults(ctx context.Context, tenantIDs []logstorage.TenantID, q *logstorage.Query, limit int) ([]row, error) {
-	limitUpper := 2 * limit
-	q.AddPipeLimit(uint64(limitUpper))
-	q.Optimize()
-	rows, err := getQueryResultsWithLimit(ctx, tenantIDs, q, limitUpper)
-	if err != nil {
-		return nil, err
-	}
-	if len(rows) < limitUpper {
-		// Fast path - the requested time range contains up to limitUpper rows.
-		rows = getLastNRows(rows, limit)
-		return rows, nil
-	}
-
-	// Slow path - search for the time range containing up to limitUpper rows.
-	start, end := q.GetFilterTimeRange()
-	d := end/2 - start/2
-	start += d
-
-	qOrig := q
-	for {
-		q = qOrig.Clone()
-		q.AddTimeFilter(start, end)
-		rows, err := getQueryResultsWithLimit(ctx, tenantIDs, q, limitUpper)
-		if err != nil {
-			return nil, err
-		}
-
-		if len(rows) >= limit && len(rows) < limitUpper || d == 0 {
-			rows = getLastNRows(rows, limit)
-			return rows, nil
-		}
-
-		lastBit := d & 1
-		d /= 2
-		if len(rows) > limit {
-			start += d
-		} else {
-			start -= d + lastBit
-		}
-	}
-}
-
-func getLastNRows(rows []row, limit int) []row {
-	sort.Slice(rows, func(i, j int) bool {
-		return rows[i].timestamp < rows[j].timestamp
-	})
-	if len(rows) > limit {
-		rows = rows[len(rows)-limit:]
-	}
-	return rows
-}
-
-func getQueryResultsWithLimit(ctx context.Context, tenantIDs []logstorage.TenantID, q *logstorage.Query, limit int) ([]row, error) {
-	ctxWithCancel, cancel := context.WithCancel(ctx)
-	defer cancel()
-
-	var rows []row
-	var rowsLock sync.Mutex
-	writeBlock := func(_ uint, timestamps []int64, columns []logstorage.BlockColumn) {
-		rowsLock.Lock()
-		defer rowsLock.Unlock()
-
-		for i, timestamp := range timestamps {
-			fields := make([]logstorage.Field, len(columns))
-			for j := range columns {
-				f := &fields[j]
-				f.Name = strings.Clone(columns[j].Name)
-				f.Value = strings.Clone(columns[j].Values[i])
-			}
-			rows = append(rows, row{
-				timestamp: timestamp,
-				fields:    fields,
-			})
-		}
-
-		if len(rows) >= limit {
-			cancel()
-		}
-	}
-	if err := vlstorage.RunQuery(ctxWithCancel, tenantIDs, q, writeBlock); err != nil {
-		return nil, err
-	}
-
-	return rows, nil
-}
-
-func parseCommonArgs(r *http.Request) (*logstorage.Query, []logstorage.TenantID, error) {
+var (
+	maxSortBufferSize = flagutil.NewBytes("select.maxSortBufferSize", 1024*1024, "Query results from /select/logsql/query are automatically sorted by _time "+
+		"if their summary size doesn't exceed this value; otherwise, query results are streamed in the response without sorting; "+
+		"too big value for this flag may result in high memory usage since the sorting is performed in memory")
+)
+
+// ProcessQueryRequest handles /select/logsql/query request
+func ProcessQueryRequest(w http.ResponseWriter, r *http.Request, stopCh <-chan struct{}, cancel func()) {
 	// Extract tenantID
 	tenantID, err := logstorage.GetTenantIDFromRequest(r)
 	if err != nil {
-		return nil, nil, fmt.Errorf("cannot obtain tenanID: %w", err)
+		httpserver.Errorf(w, r, "%s", err)
+		return
+	}
+	limit, err := httputils.GetInt(r, "limit")
+	if err != nil {
+		httpserver.Errorf(w, r, "%s", err)
+		return
 	}
-	tenantIDs := []logstorage.TenantID{tenantID}
 
-	// Parse query
 	qStr := r.FormValue("query")
 	q, err := logstorage.ParseQuery(qStr)
 	if err != nil {
-		return nil, nil, fmt.Errorf("cannot parse query [%s]: %s", qStr, err)
+		httpserver.Errorf(w, r, "cannot parse query [%s]: %s", qStr, err)
+		return
 	}
+	w.Header().Set("Content-Type", "application/stream+json; charset=utf-8")
 
-	// Parse optional start and end args
-	start, okStart, err := getTimeNsec(r, "start")
-	if err != nil {
-		return nil, nil, err
-	}
-	end, okEnd, err := getTimeNsec(r, "end")
-	if err != nil {
-		return nil, nil, err
-	}
-	if okStart || okEnd {
-		if !okStart {
-			start = math.MinInt64
+	sw := getSortWriter()
+	sw.Init(w, maxSortBufferSize.IntN(), limit)
+	tenantIDs := []logstorage.TenantID{tenantID}
+	vlstorage.RunQuery(tenantIDs, q, stopCh, func(columns []logstorage.BlockColumn) {
+		if len(columns) == 0 {
+			return
 		}
-		if !okEnd {
-			end = math.MaxInt64
-		}
-		q.AddTimeFilter(start, end)
-	}
+		rowsCount := len(columns[0].Values)
 
-	return q, tenantIDs, nil
+		bb := blockResultPool.Get()
+		for rowIdx := 0; rowIdx < rowsCount; rowIdx++ {
+			WriteJSONRow(bb, columns, rowIdx)
+		}
+
+		if !sw.TryWrite(bb.B) {
+			cancel()
+		}
+
+		blockResultPool.Put(bb)
+	})
+	sw.FinalFlush()
+	putSortWriter(sw)
 }
 
-func getTimeNsec(r *http.Request, argName string) (int64, bool, error) {
-	s := r.FormValue(argName)
-	if s == "" {
-		return 0, false, nil
-	}
-	currentTimestamp := time.Now().UnixNano()
-	nsecs, err := promutils.ParseTimeAt(s, currentTimestamp)
-	if err != nil {
-		return 0, false, fmt.Errorf("cannot parse %s=%s: %w", argName, s, err)
-	}
-	return nsecs, true, nil
-}
+var blockResultPool bytesutil.ByteBufferPool

app/vlselect/logsql/logsql.qtpl

@@ -1,32 +0,0 @@
-{% import (
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
-) %}
-
-{% stripspace %}
-
-// ValuesWithHitsJSON generates JSON from the given values.
-{% func ValuesWithHitsJSON(values []logstorage.ValueWithHits) %}
-{
-	"values":{%= valuesWithHitsJSONArray(values) %}
-}
-{% endfunc %}
-
-{% func valuesWithHitsJSONArray(values []logstorage.ValueWithHits) %}
-[
-	{% if len(values) > 0 %}
-		{%= valueWithHitsJSON(values[0]) %}
-		{% for _, v := range values[1:] %}
-			,{%= valueWithHitsJSON(v) %}
-		{% endfor %}
-	{% endif %}
-]
-{% endfunc %}
-
-{% func valueWithHitsJSON(v logstorage.ValueWithHits) %}
-{
-	"value":{%q= v.Value %},
-	"hits":{%dul= v.Hits %}
-}
-{% endfunc %}
-
-{% endstripspace %}

app/vlselect/logsql/logsql.qtpl.go

@@ -1,152 +0,0 @@
-// Code generated by qtc from "logsql.qtpl". DO NOT EDIT.
-// See https://github.com/valyala/quicktemplate for details.
-
-//line app/vlselect/logsql/logsql.qtpl:1
-package logsql
-
-//line app/vlselect/logsql/logsql.qtpl:1
-import (
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
-)
-
-// ValuesWithHitsJSON generates JSON from the given values.
-
-//line app/vlselect/logsql/logsql.qtpl:8
-import (
-	qtio422016 "io"
-
-	qt422016 "github.com/valyala/quicktemplate"
-)
-
-//line app/vlselect/logsql/logsql.qtpl:8
-var (
-	_ = qtio422016.Copy
-	_ = qt422016.AcquireByteBuffer
-)
-
-//line app/vlselect/logsql/logsql.qtpl:8
-func StreamValuesWithHitsJSON(qw422016 *qt422016.Writer, values []logstorage.ValueWithHits) {
-//line app/vlselect/logsql/logsql.qtpl:8
-	qw422016.N().S(`{"values":`)
-//line app/vlselect/logsql/logsql.qtpl:10
-	streamvaluesWithHitsJSONArray(qw422016, values)
-//line app/vlselect/logsql/logsql.qtpl:10
-	qw422016.N().S(`}`)
-//line app/vlselect/logsql/logsql.qtpl:12
-}
-
-//line app/vlselect/logsql/logsql.qtpl:12
-func WriteValuesWithHitsJSON(qq422016 qtio422016.Writer, values []logstorage.ValueWithHits) {
-//line app/vlselect/logsql/logsql.qtpl:12
-	qw422016 := qt422016.AcquireWriter(qq422016)
-//line app/vlselect/logsql/logsql.qtpl:12
-	StreamValuesWithHitsJSON(qw422016, values)
-//line app/vlselect/logsql/logsql.qtpl:12
-	qt422016.ReleaseWriter(qw422016)
-//line app/vlselect/logsql/logsql.qtpl:12
-}
-
-//line app/vlselect/logsql/logsql.qtpl:12
-func ValuesWithHitsJSON(values []logstorage.ValueWithHits) string {
-//line app/vlselect/logsql/logsql.qtpl:12
-	qb422016 := qt422016.AcquireByteBuffer()
-//line app/vlselect/logsql/logsql.qtpl:12
-	WriteValuesWithHitsJSON(qb422016, values)
-//line app/vlselect/logsql/logsql.qtpl:12
-	qs422016 := string(qb422016.B)
-//line app/vlselect/logsql/logsql.qtpl:12
-	qt422016.ReleaseByteBuffer(qb422016)
-//line app/vlselect/logsql/logsql.qtpl:12
-	return qs422016
-//line app/vlselect/logsql/logsql.qtpl:12
-}
-
-//line app/vlselect/logsql/logsql.qtpl:14
-func streamvaluesWithHitsJSONArray(qw422016 *qt422016.Writer, values []logstorage.ValueWithHits) {
-//line app/vlselect/logsql/logsql.qtpl:14
-	qw422016.N().S(`[`)
-//line app/vlselect/logsql/logsql.qtpl:16
-	if len(values) > 0 {
-//line app/vlselect/logsql/logsql.qtpl:17
-		streamvalueWithHitsJSON(qw422016, values[0])
-//line app/vlselect/logsql/logsql.qtpl:18
-		for _, v := range values[1:] {
-//line app/vlselect/logsql/logsql.qtpl:18
-			qw422016.N().S(`,`)
-//line app/vlselect/logsql/logsql.qtpl:19
-			streamvalueWithHitsJSON(qw422016, v)
-//line app/vlselect/logsql/logsql.qtpl:20
-		}
-//line app/vlselect/logsql/logsql.qtpl:21
-	}
-//line app/vlselect/logsql/logsql.qtpl:21
-	qw422016.N().S(`]`)
-//line app/vlselect/logsql/logsql.qtpl:23
-}
-
-//line app/vlselect/logsql/logsql.qtpl:23
-func writevaluesWithHitsJSONArray(qq422016 qtio422016.Writer, values []logstorage.ValueWithHits) {
-//line app/vlselect/logsql/logsql.qtpl:23
-	qw422016 := qt422016.AcquireWriter(qq422016)
-//line app/vlselect/logsql/logsql.qtpl:23
-	streamvaluesWithHitsJSONArray(qw422016, values)
-//line app/vlselect/logsql/logsql.qtpl:23
-	qt422016.ReleaseWriter(qw422016)
-//line app/vlselect/logsql/logsql.qtpl:23
-}
-
-//line app/vlselect/logsql/logsql.qtpl:23
-func valuesWithHitsJSONArray(values []logstorage.ValueWithHits) string {
-//line app/vlselect/logsql/logsql.qtpl:23
-	qb422016 := qt422016.AcquireByteBuffer()
-//line app/vlselect/logsql/logsql.qtpl:23
-	writevaluesWithHitsJSONArray(qb422016, values)
-//line app/vlselect/logsql/logsql.qtpl:23
-	qs422016 := string(qb422016.B)
-//line app/vlselect/logsql/logsql.qtpl:23
-	qt422016.ReleaseByteBuffer(qb422016)
-//line app/vlselect/logsql/logsql.qtpl:23
-	return qs422016
-//line app/vlselect/logsql/logsql.qtpl:23
-}
-
-//line app/vlselect/logsql/logsql.qtpl:25
-func streamvalueWithHitsJSON(qw422016 *qt422016.Writer, v logstorage.ValueWithHits) {
-//line app/vlselect/logsql/logsql.qtpl:25
-	qw422016.N().S(`{"value":`)
-//line app/vlselect/logsql/logsql.qtpl:27
-	qw422016.N().Q(v.Value)
-//line app/vlselect/logsql/logsql.qtpl:27
-	qw422016.N().S(`,"hits":`)
-//line app/vlselect/logsql/logsql.qtpl:28
-	qw422016.N().DUL(v.Hits)
-//line app/vlselect/logsql/logsql.qtpl:28
-	qw422016.N().S(`}`)
-//line app/vlselect/logsql/logsql.qtpl:30
-}
-
-//line app/vlselect/logsql/logsql.qtpl:30
-func writevalueWithHitsJSON(qq422016 qtio422016.Writer, v logstorage.ValueWithHits) {
-//line app/vlselect/logsql/logsql.qtpl:30
-	qw422016 := qt422016.AcquireWriter(qq422016)
-//line app/vlselect/logsql/logsql.qtpl:30
-	streamvalueWithHitsJSON(qw422016, v)
-//line app/vlselect/logsql/logsql.qtpl:30
-	qt422016.ReleaseWriter(qw422016)
-//line app/vlselect/logsql/logsql.qtpl:30
-}
-
-//line app/vlselect/logsql/logsql.qtpl:30
-func valueWithHitsJSON(v logstorage.ValueWithHits) string {
-//line app/vlselect/logsql/logsql.qtpl:30
-	qb422016 := qt422016.AcquireByteBuffer()
-//line app/vlselect/logsql/logsql.qtpl:30
-	writevalueWithHitsJSON(qb422016, v)
-//line app/vlselect/logsql/logsql.qtpl:30
-	qs422016 := string(qb422016.B)
-//line app/vlselect/logsql/logsql.qtpl:30
-	qt422016.ReleaseByteBuffer(qb422016)
-//line app/vlselect/logsql/logsql.qtpl:30
-	return qs422016
-//line app/vlselect/logsql/logsql.qtpl:30
-}

app/vlselect/logsql/sort_writer.go

@@ -0,0 +1,292 @@
+package logsql
+
+import (
+	"bytes"
+	"io"
+	"sort"
+	"sync"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logjson"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
+)
+
+func getSortWriter() *sortWriter {
+	v := sortWriterPool.Get()
+	if v == nil {
+		return &sortWriter{}
+	}
+	return v.(*sortWriter)
+}
+
+func putSortWriter(sw *sortWriter) {
+	sw.reset()
+	sortWriterPool.Put(sw)
+}
+
+var sortWriterPool sync.Pool
+
+// sortWriter expects JSON line stream to be written to it.
+//
+// It buffers the incoming data until its size reaches maxBufLen.
+// Then it streams the buffered data and all the incoming data to w.
+//
+// The FinalFlush() must be called when all the data is written.
+// If the buf isn't empty at FinalFlush() call, then the buffered data
+// is sorted by _time field.
+type sortWriter struct {
+	mu sync.Mutex
+	w  io.Writer
+
+	maxLines     int
+	linesWritten int
+
+	maxBufLen  int
+	buf        []byte
+	bufFlushed bool
+
+	hasErr bool
+}
+
+func (sw *sortWriter) reset() {
+	sw.w = nil
+
+	sw.maxLines = 0
+	sw.linesWritten = 0
+
+	sw.maxBufLen = 0
+	sw.buf = sw.buf[:0]
+	sw.bufFlushed = false
+	sw.hasErr = false
+}
+
+// Init initializes sw.
+//
+// If maxLines is set to positive value, then sw accepts up to maxLines
+// and then rejects all the other lines by returning false from TryWrite.
+func (sw *sortWriter) Init(w io.Writer, maxBufLen, maxLines int) {
+	sw.reset()
+
+	sw.w = w
+	sw.maxBufLen = maxBufLen
+	sw.maxLines = maxLines
+}
+
+// TryWrite writes p to sw.
+//
+// True is returned on successful write, false otherwise.
+//
+// Unsuccessful write may occur on underlying write error or when maxLines lines are already written to sw.
+func (sw *sortWriter) TryWrite(p []byte) bool {
+	sw.mu.Lock()
+	defer sw.mu.Unlock()
+
+	if sw.hasErr {
+		return false
+	}
+
+	if sw.bufFlushed {
+		if !sw.writeToUnderlyingWriterLocked(p) {
+			sw.hasErr = true
+			return false
+		}
+		return true
+	}
+
+	if len(sw.buf)+len(p) < sw.maxBufLen {
+		sw.buf = append(sw.buf, p...)
+		return true
+	}
+
+	sw.bufFlushed = true
+	if !sw.writeToUnderlyingWriterLocked(sw.buf) {
+		sw.hasErr = true
+		return false
+	}
+	sw.buf = sw.buf[:0]
+
+	if !sw.writeToUnderlyingWriterLocked(p) {
+		sw.hasErr = true
+		return false
+	}
+	return true
+}
+
+func (sw *sortWriter) writeToUnderlyingWriterLocked(p []byte) bool {
+	if len(p) == 0 {
+		return true
+	}
+	if sw.maxLines > 0 {
+		if sw.linesWritten >= sw.maxLines {
+			return false
+		}
+		var linesLeft int
+		p, linesLeft = trimLines(p, sw.maxLines-sw.linesWritten)
+		println("DEBUG: end trimLines", string(p), linesLeft)
+		sw.linesWritten += linesLeft
+	}
+	if _, err := sw.w.Write(p); err != nil {
+		return false
+	}
+	return true
+}
+
+func trimLines(p []byte, maxLines int) ([]byte, int) {
+	println("DEBUG: start trimLines", string(p), maxLines)
+	if maxLines <= 0 {
+		return nil, 0
+	}
+	n := bytes.Count(p, newline)
+	if n < maxLines {
+		return p, n
+	}
+	for n >= maxLines {
+		idx := bytes.LastIndexByte(p, '\n')
+		p = p[:idx]
+		n--
+	}
+	return p[:len(p)+1], maxLines
+}
+
+var newline = []byte("\n")
+
+func (sw *sortWriter) FinalFlush() {
+	if sw.hasErr || sw.bufFlushed {
+		return
+	}
+
+	rs := getRowsSorter()
+	rs.parseRows(sw.buf)
+	rs.sort()
+
+	rows := rs.rows
+	if sw.maxLines > 0 && len(rows) > sw.maxLines {
+		rows = rows[:sw.maxLines]
+	}
+	WriteJSONRows(sw.w, rows)
+
+	putRowsSorter(rs)
+}
+
+func getRowsSorter() *rowsSorter {
+	v := rowsSorterPool.Get()
+	if v == nil {
+		return &rowsSorter{}
+	}
+	return v.(*rowsSorter)
+}
+
+func putRowsSorter(rs *rowsSorter) {
+	rs.reset()
+	rowsSorterPool.Put(rs)
+}
+
+var rowsSorterPool sync.Pool
+
+type rowsSorter struct {
+	buf       []byte
+	fieldsBuf []logstorage.Field
+	rows      [][]logstorage.Field
+	times     []string
+}
+
+func (rs *rowsSorter) reset() {
+	rs.buf = rs.buf[:0]
+
+	fieldsBuf := rs.fieldsBuf
+	for i := range fieldsBuf {
+		fieldsBuf[i].Reset()
+	}
+	rs.fieldsBuf = fieldsBuf[:0]
+
+	rows := rs.rows
+	for i := range rows {
+		rows[i] = nil
+	}
+	rs.rows = rows[:0]
+
+	times := rs.times
+	for i := range times {
+		times[i] = ""
+	}
+	rs.times = times[:0]
+}
+
+func (rs *rowsSorter) parseRows(src []byte) {
+	rs.reset()
+
+	buf := rs.buf
+	fieldsBuf := rs.fieldsBuf
+	rows := rs.rows
+	times := rs.times
+
+	p := logjson.GetParser()
+	for len(src) > 0 {
+		var line []byte
+		n := bytes.IndexByte(src, '\n')
+		if n < 0 {
+			line = src
+			src = nil
+		} else {
+			line = src[:n]
+			src = src[n+1:]
+		}
+		if len(line) == 0 {
+			continue
+		}
+
+		if err := p.ParseLogMessage(line); err != nil {
+			logger.Panicf("BUG: unexpected invalid JSON line: %s", err)
+		}
+
+		timeValue := ""
+		fieldsBufLen := len(fieldsBuf)
+		for _, f := range p.Fields {
+			bufLen := len(buf)
+			buf = append(buf, f.Name...)
+			name := bytesutil.ToUnsafeString(buf[bufLen:])
+
+			bufLen = len(buf)
+			buf = append(buf, f.Value...)
+			value := bytesutil.ToUnsafeString(buf[bufLen:])
+
+			fieldsBuf = append(fieldsBuf, logstorage.Field{
+				Name:  name,
+				Value: value,
+			})
+
+			if name == "_time" {
+				timeValue = value
+			}
+		}
+		rows = append(rows, fieldsBuf[fieldsBufLen:])
+		times = append(times, timeValue)
+	}
+	logjson.PutParser(p)
+
+	rs.buf = buf
+	rs.fieldsBuf = fieldsBuf
+	rs.rows = rows
+	rs.times = times
+}
+
+func (rs *rowsSorter) Len() int {
+	return len(rs.rows)
+}
+
+func (rs *rowsSorter) Less(i, j int) bool {
+	times := rs.times
+	return times[i] < times[j]
+}
+
+func (rs *rowsSorter) Swap(i, j int) {
+	times := rs.times
+	rows := rs.rows
+	times[i], times[j] = times[j], times[i]
+	rows[i], rows[j] = rows[j], rows[i]
+}
+
+func (rs *rowsSorter) sort() {
+	sort.Sort(rs)
+}

app/vlselect/logsql/sort_writer_test.go

@@ -0,0 +1,46 @@
+package logsql
+
+import (
+	"bytes"
+	"strings"
+	"testing"
+)
+
+func TestSortWriter(t *testing.T) {
+	f := func(maxBufLen, maxLines int, data string, expectedResult string) {
+		t.Helper()
+
+		var bb bytes.Buffer
+		sw := getSortWriter()
+		sw.Init(&bb, maxBufLen, maxLines)
+		for _, s := range strings.Split(data, "\n") {
+			if !sw.TryWrite([]byte(s + "\n")) {
+				break
+			}
+		}
+		sw.FinalFlush()
+		putSortWriter(sw)
+
+		result := bb.String()
+		if result != expectedResult {
+			t.Fatalf("unexpected result;\ngot\n%s\nwant\n%s", result, expectedResult)
+		}
+	}
+
+	f(100, 0, "", "")
+	f(100, 0, "{}", "{}\n")
+
+	data := `{"_time":"def","_msg":"xxx"}
+{"_time":"abc","_msg":"foo"}`
+	resultExpected := `{"_time":"abc","_msg":"foo"}
+{"_time":"def","_msg":"xxx"}
+`
+	f(100, 0, data, resultExpected)
+	f(10, 0, data, data+"\n")
+
+	// Test with the maxLines
+	f(100, 1, data, `{"_time":"abc","_msg":"foo"}`+"\n")
+	f(10, 1, data, `{"_time":"def","_msg":"xxx"}`+"\n")
+	f(10, 2, data, data+"\n")
+	f(100, 2, data, resultExpected)
+}

app/vlselect/main.go

@@ -14,6 +14,7 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httputils"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/timerpool"
 	"github.com/VictoriaMetrics/metrics"
 )
 
@@ -23,7 +24,7 @@ var (
 		"See also -search.maxQueueDuration")
 	maxQueueDuration = flag.Duration("search.maxQueueDuration", 10*time.Second, "The maximum time the search request waits for execution when -search.maxConcurrentRequests "+
 		"limit is reached; see also -search.maxQueryDuration")
-	maxQueryDuration = flag.Duration("search.maxQueryDuration", time.Second*30, "The maximum duration for query execution. It can be overridden on a per-query basis via 'timeout' query arg")
+	maxQueryDuration = flag.Duration("search.maxQueryDuration", time.Second*30, "The maximum duration for query execution")
 )
 
 func getDefaultMaxConcurrentRequests() int {
@@ -75,9 +76,10 @@ func RequestHandler(w http.ResponseWriter, r *http.Request) bool {
 		// Skip requests, which do not start with /select/, since these aren't our requests.
 		return false
 	}
+	path = strings.TrimPrefix(path, "/select")
 	path = strings.ReplaceAll(path, "//", "/")
 
-	if path == "/select/vmui" {
+	if path == "/vmui" {
 		// VMUI access via incomplete url without `/` in the end. Redirect to complete url.
 		// Use relative redirect, since the hostname and path prefix may be incorrect if VictoriaMetrics
 		// is hidden behind vmauth or similar proxy.
@@ -86,128 +88,68 @@ func RequestHandler(w http.ResponseWriter, r *http.Request) bool {
 		httpserver.Redirect(w, newURL)
 		return true
 	}
-	if strings.HasPrefix(path, "/select/vmui/") {
-		if strings.HasPrefix(path, "/select/vmui/static/") {
+	if strings.HasPrefix(path, "/vmui/") {
+		if strings.HasPrefix(path, "/vmui/static/") {
 			// Allow clients caching static contents for long period of time, since it shouldn't change over time.
 			// Path to static contents (such as js and css) must be changed whenever its contents is changed.
 			// See https://developer.chrome.com/docs/lighthouse/performance/uses-long-cache-ttl/
 			w.Header().Set("Cache-Control", "max-age=31536000")
 		}
-		r.URL.Path = strings.TrimPrefix(path, "/select")
+		r.URL.Path = path
 		vmuiFileServer.ServeHTTP(w, r)
 		return true
 	}
 
-	// Limit the number of concurrent queries, which can consume big amounts of CPU time.
+	// Limit the number of concurrent queries, which can consume big amounts of CPU.
 	startTime := time.Now()
 	ctx := r.Context()
-	d := getMaxQueryDuration(r)
-	ctxWithTimeout, cancel := context.WithTimeout(ctx, d)
-	defer cancel()
-
-	stopCh := ctxWithTimeout.Done()
+	stopCh := ctx.Done()
 	select {
 	case concurrencyLimitCh <- struct{}{}:
 		defer func() { <-concurrencyLimitCh }()
 	default:
 		// Sleep for a while until giving up. This should resolve short bursts in requests.
 		concurrencyLimitReached.Inc()
+		d := getMaxQueryDuration(r)
+		if d > *maxQueueDuration {
+			d = *maxQueueDuration
+		}
+		t := timerpool.Get(d)
 		select {
 		case concurrencyLimitCh <- struct{}{}:
+			timerpool.Put(t)
 			defer func() { <-concurrencyLimitCh }()
 		case <-stopCh:
-			switch ctxWithTimeout.Err() {
-			case context.Canceled:
-				remoteAddr := httpserver.GetQuotedRemoteAddr(r)
-				requestURI := httpserver.GetRequestURI(r)
-				logger.Infof("client has canceled the pending request after %.3f seconds: remoteAddr=%s, requestURI: %q",
-					time.Since(startTime).Seconds(), remoteAddr, requestURI)
-			case context.DeadlineExceeded:
-				concurrencyLimitTimeout.Inc()
-				err := &httpserver.ErrorWithStatusCode{
-					Err: fmt.Errorf("couldn't start executing the request in %.3f seconds, since -search.maxConcurrentRequests=%d concurrent requests "+
-						"are executed. Possible solutions: to reduce query load; to add more compute resources to the server; "+
-						"to increase -search.maxQueueDuration=%s; to increase -search.maxQueryDuration=%s; to increase -search.maxConcurrentRequests; "+
-						"to pass bigger value to 'timeout' query arg",
-						d.Seconds(), *maxConcurrentRequests, maxQueueDuration, maxQueryDuration),
-					StatusCode: http.StatusServiceUnavailable,
-				}
-				httpserver.Errorf(w, r, "%s", err)
+			timerpool.Put(t)
+			remoteAddr := httpserver.GetQuotedRemoteAddr(r)
+			requestURI := httpserver.GetRequestURI(r)
+			logger.Infof("client has cancelled the request after %.3f seconds: remoteAddr=%s, requestURI: %q",
+				time.Since(startTime).Seconds(), remoteAddr, requestURI)
+			return true
+		case <-t.C:
+			timerpool.Put(t)
+			concurrencyLimitTimeout.Inc()
+			err := &httpserver.ErrorWithStatusCode{
+				Err: fmt.Errorf("couldn't start executing the request in %.3f seconds, since -search.maxConcurrentRequests=%d concurrent requests "+
+					"are executed. Possible solutions: to reduce query load; to add more compute resources to the server; "+
+					"to increase -search.maxQueueDuration=%s; to increase -search.maxQueryDuration; to increase -search.maxConcurrentRequests",
+					d.Seconds(), *maxConcurrentRequests, maxQueueDuration),
+				StatusCode: http.StatusServiceUnavailable,
 			}
+			httpserver.Errorf(w, r, "%s", err)
 			return true
 		}
 	}
 
-	if path == "/select/logsql/tail" {
-		logsqlTailRequests.Inc()
-		// Process live tailing request without timeout (e.g. use ctx instead of ctxWithTimeout),
-		// since it is OK to run live tailing requests for very long time.
-		logsql.ProcessLiveTailRequest(ctx, w, r)
-		return true
-	}
+	ctxWithCancel, cancel := context.WithCancel(ctx)
+	defer cancel()
+	stopCh = ctxWithCancel.Done()
 
-	ok := processSelectRequest(ctxWithTimeout, w, r, path)
-	if !ok {
-		return false
-	}
-
-	err := ctxWithTimeout.Err()
-	switch err {
-	case nil:
-		// nothing to do
-	case context.Canceled:
-		remoteAddr := httpserver.GetQuotedRemoteAddr(r)
-		requestURI := httpserver.GetRequestURI(r)
-		logger.Infof("client has canceled the request after %.3f seconds: remoteAddr=%s, requestURI: %q",
-			time.Since(startTime).Seconds(), remoteAddr, requestURI)
-	case context.DeadlineExceeded:
-		err = &httpserver.ErrorWithStatusCode{
-			Err: fmt.Errorf("the request couldn't be executed in %.3f seconds; possible solutions: "+
-				"to increase -search.maxQueryDuration=%s; to pass bigger value to 'timeout' query arg", d.Seconds(), maxQueryDuration),
-			StatusCode: http.StatusServiceUnavailable,
-		}
-		httpserver.Errorf(w, r, "%s", err)
-	default:
-		httpserver.Errorf(w, r, "unexpected error: %s", err)
-	}
-
-	return true
-}
-
-func processSelectRequest(ctx context.Context, w http.ResponseWriter, r *http.Request, path string) bool {
-	httpserver.EnableCORS(w, r)
-	switch path {
-	case "/select/logsql/field_names":
-		logsqlFieldNamesRequests.Inc()
-		logsql.ProcessFieldNamesRequest(ctx, w, r)
-		return true
-	case "/select/logsql/field_values":
-		logsqlFieldValuesRequests.Inc()
-		logsql.ProcessFieldValuesRequest(ctx, w, r)
-		return true
-	case "/select/logsql/hits":
-		logsqlHitsRequests.Inc()
-		logsql.ProcessHitsRequest(ctx, w, r)
-		return true
-	case "/select/logsql/query":
+	switch {
+	case path == "/logsql/query":
 		logsqlQueryRequests.Inc()
-		logsql.ProcessQueryRequest(ctx, w, r)
-		return true
-	case "/select/logsql/stream_field_names":
-		logsqlStreamFieldNamesRequests.Inc()
-		logsql.ProcessStreamFieldNamesRequest(ctx, w, r)
-		return true
-	case "/select/logsql/stream_field_values":
-		logsqlStreamFieldValuesRequests.Inc()
-		logsql.ProcessStreamFieldValuesRequest(ctx, w, r)
-		return true
-	case "/select/logsql/stream_ids":
-		logsqlStreamIDsRequests.Inc()
-		logsql.ProcessStreamIDsRequest(ctx, w, r)
-		return true
-	case "/select/logsql/streams":
-		logsqlStreamsRequests.Inc()
-		logsql.ProcessStreamsRequest(ctx, w, r)
+		httpserver.EnableCORS(w, r)
+		logsql.ProcessQueryRequest(w, r, stopCh, cancel)
 		return true
 	default:
 		return false
@@ -228,13 +170,5 @@ func getMaxQueryDuration(r *http.Request) time.Duration {
 }
 
 var (
-	logsqlFieldNamesRequests        = metrics.NewCounter(`vl_http_requests_total{path="/select/logsql/field_names"}`)
-	logsqlFieldValuesRequests       = metrics.NewCounter(`vl_http_requests_total{path="/select/logsql/field_values"}`)
-	logsqlHitsRequests              = metrics.NewCounter(`vl_http_requests_total{path="/select/logsql/hits"}`)
-	logsqlQueryRequests             = metrics.NewCounter(`vl_http_requests_total{path="/select/logsql/query"}`)
-	logsqlStreamFieldNamesRequests  = metrics.NewCounter(`vl_http_requests_total{path="/select/logsql/stream_field_names"}`)
-	logsqlStreamFieldValuesRequests = metrics.NewCounter(`vl_http_requests_total{path="/select/logsql/stream_field_values"}`)
-	logsqlStreamIDsRequests         = metrics.NewCounter(`vl_http_requests_total{path="/select/logsql/stream_ids"}`)
-	logsqlStreamsRequests           = metrics.NewCounter(`vl_http_requests_total{path="/select/logsql/streams"}`)
-	logsqlTailRequests              = metrics.NewCounter(`vl_http_requests_total{path="/select/logsql/tail"}`)
+	logsqlQueryRequests = metrics.NewCounter(`vl_http_requests_total{path="/select/logsql/query"}`)
 )

app/vlselect/vmui/asset-manifest.json

@@ -1,13 +1,13 @@
 {
   "files": {
-    "main.css": "./static/css/main.1041c3d4.css",
-    "main.js": "./static/js/main.8988988c.js",
-    "static/js/685.bebe1265.chunk.js": "./static/js/685.bebe1265.chunk.js",
-    "static/media/MetricsQL.md": "./static/media/MetricsQL.aaabf95f2c9bf356bde4.md",
+    "main.css": "./static/css/main.1e22ee10.css",
+    "main.js": "./static/js/main.92cf3903.js",
+    "static/js/522.da77e7b3.chunk.js": "./static/js/522.da77e7b3.chunk.js",
+    "static/media/MetricsQL.md": "./static/media/MetricsQL.48b7b7105a48d7775f01.md",
     "index.html": "./index.html"
   },
   "entrypoints": [
-    "static/css/main.1041c3d4.css",
-    "static/js/main.8988988c.js"
+    "static/css/main.1e22ee10.css",
+    "static/js/main.92cf3903.js"
   ]
 }

app/vlselect/vmui/index.html

@@ -1 +1 @@
-<!doctype html><html lang="en"><head><meta charset="utf-8"/><link rel="icon" href="./favicon.ico"/><meta name="viewport" content="width=device-width,initial-scale=1,maximum-scale=5"/><meta name="theme-color" content="#000000"/><meta name="description" content="UI for VictoriaMetrics"/><link rel="apple-touch-icon" href="./apple-touch-icon.png"/><link rel="icon" type="image/png" sizes="32x32" href="./favicon-32x32.png"><link rel="manifest" href="./manifest.json"/><title>VM UI</title><script src="./dashboards/index.js" type="module"></script><meta name="twitter:card" content="summary_large_image"><meta name="twitter:image" content="./preview.jpg"><meta name="twitter:title" content="UI for VictoriaMetrics"><meta name="twitter:description" content="Explore and troubleshoot your VictoriaMetrics data"><meta name="twitter:site" content="@VictoriaMetrics"><meta property="og:title" content="Metric explorer for VictoriaMetrics"><meta property="og:description" content="Explore and troubleshoot your VictoriaMetrics data"><meta property="og:image" content="./preview.jpg"><meta property="og:type" content="website"><script defer="defer" src="./static/js/main.8988988c.js"></script><link href="./static/css/main.1041c3d4.css" rel="stylesheet"></head><body><noscript>You need to enable JavaScript to run this app.</noscript><div id="root"></div></body></html>
+<!doctype html><html lang="en"><head><meta charset="utf-8"/><link rel="icon" href="./favicon.ico"/><meta name="viewport" content="width=device-width,initial-scale=1,maximum-scale=5"/><meta name="theme-color" content="#000000"/><meta name="description" content="UI for VictoriaMetrics"/><link rel="apple-touch-icon" href="./apple-touch-icon.png"/><link rel="icon" type="image/png" sizes="32x32" href="./favicon-32x32.png"><link rel="manifest" href="./manifest.json"/><title>VM UI</title><script src="./dashboards/index.js" type="module"></script><meta name="twitter:card" content="summary_large_image"><meta name="twitter:image" content="./preview.jpg"><meta name="twitter:title" content="UI for VictoriaMetrics"><meta name="twitter:description" content="Explore and troubleshoot your VictoriaMetrics data"><meta name="twitter:site" content="@VictoriaMetrics"><meta property="og:title" content="Metric explorer for VictoriaMetrics"><meta property="og:description" content="Explore and troubleshoot your VictoriaMetrics data"><meta property="og:image" content="./preview.jpg"><meta property="og:type" content="website"><script defer="defer" src="./static/js/main.92cf3903.js"></script><link href="./static/css/main.1e22ee10.css" rel="stylesheet"></head><body><noscript>You need to enable JavaScript to run this app.</noscript><div id="root"></div></body></html>

app/vlselect/vmui/static/js/main.92cf3903.js.LICENSE.txt

@@ -4,8 +4,10 @@
 	http://jedwatson.github.io/classnames
 */
 
+/*! regenerator-runtime -- Copyright (c) 2014-present, Facebook, Inc. -- license (MIT): https://github.com/facebook/regenerator/blob/main/LICENSE */
+
 /**
- * @remix-run/router v1.15.1
+ * @remix-run/router v1.10.0
  *
  * Copyright (c) Remix Software Inc.
  *
@@ -16,7 +18,7 @@
  */
 
 /**
- * React Router DOM v6.22.1
+ * React Router DOM v6.17.0
  *
  * Copyright (c) Remix Software Inc.
  *
@@ -27,7 +29,7 @@
  */
 
 /**
- * React Router v6.22.1
+ * React Router v6.17.0
  *
  * Copyright (c) Remix Software Inc.
  *

app/vlstorage/main.go

@@ -1,11 +1,10 @@
 package vlstorage
 
 import (
-	"context"
 	"flag"
 	"fmt"
-	"io"
 	"net/http"
+	"sync"
 	"time"
 
 	"github.com/VictoriaMetrics/metrics"
@@ -20,21 +19,19 @@ import (
 var (
 	retentionPeriod = flagutil.NewDuration("retentionPeriod", "7d", "Log entries with timestamps older than now-retentionPeriod are automatically deleted; "+
 		"log entries with timestamps outside the retention are also rejected during data ingestion; the minimum supported retention is 1d (one day); "+
-		"see https://docs.victoriametrics.com/victorialogs/#retention ; see also -retention.maxDiskSpaceUsageBytes")
-	maxDiskSpaceUsageBytes = flagutil.NewBytes("retention.maxDiskSpaceUsageBytes", 0, "The maximum disk space usage at -storageDataPath before older per-day "+
-		"partitions are automatically dropped; see https://docs.victoriametrics.com/victorialogs/#retention-by-disk-space-usage ; see also -retentionPeriod")
+		"see https://docs.victoriametrics.com/VictoriaLogs/#retention")
 	futureRetention = flagutil.NewDuration("futureRetention", "2d", "Log entries with timestamps bigger than now+futureRetention are rejected during data ingestion; "+
-		"see https://docs.victoriametrics.com/victorialogs/#retention")
-	storageDataPath = flag.String("storageDataPath", "victoria-logs-data", "Path to directory where to store VictoriaLogs data; "+
-		"see https://docs.victoriametrics.com/victorialogs/#storage")
+		"see https://docs.victoriametrics.com/VictoriaLogs/#retention")
+	storageDataPath = flag.String("storageDataPath", "victoria-logs-data", "Path to directory with the VictoriaLogs data; "+
+		"see https://docs.victoriametrics.com/VictoriaLogs/#storage")
 	inmemoryDataFlushInterval = flag.Duration("inmemoryDataFlushInterval", 5*time.Second, "The interval for guaranteed saving of in-memory data to disk. "+
 		"The saved data survives unclean shutdowns such as OOM crash, hardware reset, SIGKILL, etc. "+
 		"Bigger intervals may help increase the lifetime of flash storage with limited write cycles (e.g. Raspberry PI). "+
 		"Smaller intervals increase disk IO load. Minimum supported value is 1s")
 	logNewStreams = flag.Bool("logNewStreams", false, "Whether to log creation of new streams; this can be useful for debugging of high cardinality issues with log streams; "+
-		"see https://docs.victoriametrics.com/victorialogs/keyconcepts/#stream-fields ; see also -logIngestedRows")
+		"see https://docs.victoriametrics.com/VictoriaLogs/keyConcepts.html#stream-fields ; see also -logIngestedRows")
 	logIngestedRows = flag.Bool("logIngestedRows", false, "Whether to log all the ingested log entries; this can be useful for debugging of data ingestion; "+
-		"see https://docs.victoriametrics.com/victorialogs/data-ingestion/ ; see also -logNewStreams")
+		"see https://docs.victoriametrics.com/VictoriaLogs/data-ingestion/ ; see also -logNewStreams")
 	minFreeDiskSpaceBytes = flagutil.NewBytes("storage.minFreeDiskSpaceBytes", 10e6, "The minimum free disk space at -storageDataPath after which "+
 		"the storage stops accepting new data")
 )
@@ -51,13 +48,12 @@ func Init() {
 		logger.Fatalf("-retentionPeriod cannot be smaller than a day; got %s", retentionPeriod)
 	}
 	cfg := &logstorage.StorageConfig{
-		Retention:              retentionPeriod.Duration(),
-		MaxDiskSpaceUsageBytes: maxDiskSpaceUsageBytes.N,
-		FlushInterval:          *inmemoryDataFlushInterval,
-		FutureRetention:        futureRetention.Duration(),
-		LogNewStreams:          *logNewStreams,
-		LogIngestedRows:        *logIngestedRows,
-		MinFreeDiskSpaceBytes:  minFreeDiskSpaceBytes.N,
+		Retention:             retentionPeriod.Duration(),
+		FlushInterval:         *inmemoryDataFlushInterval,
+		FutureRetention:       futureRetention.Duration(),
+		LogNewStreams:         *logNewStreams,
+		LogIngestedRows:       *logIngestedRows,
+		MinFreeDiskSpaceBytes: minFreeDiskSpaceBytes.N,
 	}
 	logger.Infof("opening storage at -storageDataPath=%s", *storageDataPath)
 	startTime := time.Now()
@@ -65,16 +61,10 @@ func Init() {
 
 	var ss logstorage.StorageStats
 	strg.UpdateStats(&ss)
-	logger.Infof("successfully opened storage in %.3f seconds; smallParts: %d; bigParts: %d; smallPartBlocks: %d; bigPartBlocks: %d; smallPartRows: %d; bigPartRows: %d; "+
-		"smallPartSize: %d bytes; bigPartSize: %d bytes",
-		time.Since(startTime).Seconds(), ss.SmallParts, ss.BigParts, ss.SmallPartBlocks, ss.BigPartBlocks, ss.SmallPartRowsCount, ss.BigPartRowsCount,
-		ss.CompressedSmallPartSize, ss.CompressedBigPartSize)
+	logger.Infof("successfully opened storage in %.3f seconds; partsCount: %d; blocksCount: %d; rowsCount: %d; sizeBytes: %d",
+		time.Since(startTime).Seconds(), ss.FileParts, ss.FileBlocks, ss.FileRowsCount, ss.CompressedFileSize)
+	storageMetrics = initStorageMetrics(strg)
 
-	// register storage metrics
-	storageMetrics = metrics.NewSet()
-	storageMetrics.RegisterMetricsWriter(func(w io.Writer) {
-		writeStorageMetrics(w, strg)
-	})
 	metrics.RegisterSet(storageMetrics)
 }
 
@@ -109,99 +99,117 @@ func MustAddRows(lr *logstorage.LogRows) {
 	strg.MustAddRows(lr)
 }
 
-// RunQuery runs the given q and calls writeBlock for the returned data blocks
-func RunQuery(ctx context.Context, tenantIDs []logstorage.TenantID, q *logstorage.Query, writeBlock logstorage.WriteBlockFunc) error {
-	return strg.RunQuery(ctx, tenantIDs, q, writeBlock)
+// RunQuery runs the given q and calls processBlock for the returned data blocks
+func RunQuery(tenantIDs []logstorage.TenantID, q *logstorage.Query, stopCh <-chan struct{}, processBlock func(columns []logstorage.BlockColumn)) {
+	strg.RunQuery(tenantIDs, q, stopCh, processBlock)
 }
 
-// GetFieldNames executes q and returns field names seen in results.
-func GetFieldNames(ctx context.Context, tenantIDs []logstorage.TenantID, q *logstorage.Query) ([]logstorage.ValueWithHits, error) {
-	return strg.GetFieldNames(ctx, tenantIDs, q)
-}
+func initStorageMetrics(strg *logstorage.Storage) *metrics.Set {
+	ssCache := &logstorage.StorageStats{}
+	var ssCacheLock sync.Mutex
+	var lastUpdateTime time.Time
 
-// GetFieldValues executes q and returns unique values for the fieldName seen in results.
-//
-// If limit > 0, then up to limit unique values are returned.
-func GetFieldValues(ctx context.Context, tenantIDs []logstorage.TenantID, q *logstorage.Query, fieldName string, limit uint64) ([]logstorage.ValueWithHits, error) {
-	return strg.GetFieldValues(ctx, tenantIDs, q, fieldName, limit)
-}
-
-// GetStreamFieldNames executes q and returns stream field names seen in results.
-func GetStreamFieldNames(ctx context.Context, tenantIDs []logstorage.TenantID, q *logstorage.Query) ([]logstorage.ValueWithHits, error) {
-	return strg.GetStreamFieldNames(ctx, tenantIDs, q)
-}
-
-// GetStreamFieldValues executes q and returns stream field values for the given fieldName seen in results.
-//
-// If limit > 0, then up to limit unique stream field values are returned.
-func GetStreamFieldValues(ctx context.Context, tenantIDs []logstorage.TenantID, q *logstorage.Query, fieldName string, limit uint64) ([]logstorage.ValueWithHits, error) {
-	return strg.GetStreamFieldValues(ctx, tenantIDs, q, fieldName, limit)
-}
-
-// GetStreams executes q and returns streams seen in query results.
-//
-// If limit > 0, then up to limit unique streams are returned.
-func GetStreams(ctx context.Context, tenantIDs []logstorage.TenantID, q *logstorage.Query, limit uint64) ([]logstorage.ValueWithHits, error) {
-	return strg.GetStreams(ctx, tenantIDs, q, limit)
-}
-
-// GetStreamIDs executes q and returns streamIDs seen in query results.
-//
-// If limit > 0, then up to limit unique streamIDs are returned.
-func GetStreamIDs(ctx context.Context, tenantIDs []logstorage.TenantID, q *logstorage.Query, limit uint64) ([]logstorage.ValueWithHits, error) {
-	return strg.GetStreamIDs(ctx, tenantIDs, q, limit)
-}
-
-func writeStorageMetrics(w io.Writer, strg *logstorage.Storage) {
-	var ss logstorage.StorageStats
-	strg.UpdateStats(&ss)
-
-	metrics.WriteGaugeUint64(w, fmt.Sprintf(`vl_free_disk_space_bytes{path=%q}`, *storageDataPath), fs.MustGetFreeSpace(*storageDataPath))
-
-	isReadOnly := uint64(0)
-	if ss.IsReadOnly {
-		isReadOnly = 1
+	m := func() *logstorage.StorageStats {
+		ssCacheLock.Lock()
+		defer ssCacheLock.Unlock()
+		if time.Since(lastUpdateTime) < time.Second {
+			return ssCache
+		}
+		var ss logstorage.StorageStats
+		strg.UpdateStats(&ss)
+		ssCache = &ss
+		lastUpdateTime = time.Now()
+		return ssCache
 	}
-	metrics.WriteGaugeUint64(w, fmt.Sprintf(`vl_storage_is_read_only{path=%q}`, *storageDataPath), isReadOnly)
 
-	metrics.WriteGaugeUint64(w, `vl_active_merges{type="storage/inmemory"}`, ss.InmemoryActiveMerges)
-	metrics.WriteGaugeUint64(w, `vl_active_merges{type="storage/small"}`, ss.SmallPartActiveMerges)
-	metrics.WriteGaugeUint64(w, `vl_active_merges{type="storage/big"}`, ss.BigPartActiveMerges)
+	ms := metrics.NewSet()
 
-	metrics.WriteCounterUint64(w, `vl_merges_total{type="storage/inmemory"}`, ss.InmemoryMergesTotal)
-	metrics.WriteCounterUint64(w, `vl_merges_total{type="storage/small"}`, ss.SmallPartMergesTotal)
-	metrics.WriteCounterUint64(w, `vl_merges_total{type="storage/big"}`, ss.BigPartMergesTotal)
+	ms.NewGauge(fmt.Sprintf(`vl_free_disk_space_bytes{path=%q}`, *storageDataPath), func() float64 {
+		return float64(fs.MustGetFreeSpace(*storageDataPath))
+	})
+	ms.NewGauge(fmt.Sprintf(`vl_storage_is_read_only{path=%q}`, *storageDataPath), func() float64 {
+		if m().IsReadOnly {
+			return 1
+		}
+		return 0
+	})
 
-	metrics.WriteGaugeUint64(w, `vl_storage_rows{type="storage/inmemory"}`, ss.InmemoryRowsCount)
-	metrics.WriteGaugeUint64(w, `vl_storage_rows{type="storage/small"}`, ss.SmallPartRowsCount)
-	metrics.WriteGaugeUint64(w, `vl_storage_rows{type="storage/big"}`, ss.BigPartRowsCount)
+	ms.NewGauge(`vl_active_merges{type="inmemory"}`, func() float64 {
+		return float64(m().InmemoryActiveMerges)
+	})
+	ms.NewGauge(`vl_merges_total{type="inmemory"}`, func() float64 {
+		return float64(m().InmemoryMergesTotal)
+	})
+	ms.NewGauge(`vl_active_merges{type="file"}`, func() float64 {
+		return float64(m().FileActiveMerges)
+	})
+	ms.NewGauge(`vl_merges_total{type="file"}`, func() float64 {
+		return float64(m().FileMergesTotal)
+	})
 
-	metrics.WriteGaugeUint64(w, `vl_storage_parts{type="storage/inmemory"}`, ss.InmemoryParts)
-	metrics.WriteGaugeUint64(w, `vl_storage_parts{type="storage/small"}`, ss.SmallParts)
-	metrics.WriteGaugeUint64(w, `vl_storage_parts{type="storage/big"}`, ss.BigParts)
+	ms.NewGauge(`vl_storage_rows{type="inmemory"}`, func() float64 {
+		return float64(m().InmemoryRowsCount)
+	})
+	ms.NewGauge(`vl_storage_rows{type="file"}`, func() float64 {
+		return float64(m().FileRowsCount)
+	})
+	ms.NewGauge(`vl_storage_parts{type="inmemory"}`, func() float64 {
+		return float64(m().InmemoryParts)
+	})
+	ms.NewGauge(`vl_storage_parts{type="file"}`, func() float64 {
+		return float64(m().FileParts)
+	})
+	ms.NewGauge(`vl_storage_blocks{type="inmemory"}`, func() float64 {
+		return float64(m().InmemoryBlocks)
+	})
+	ms.NewGauge(`vl_storage_blocks{type="file"}`, func() float64 {
+		return float64(m().FileBlocks)
+	})
 
-	metrics.WriteGaugeUint64(w, `vl_storage_blocks{type="storage/inmemory"}`, ss.InmemoryBlocks)
-	metrics.WriteGaugeUint64(w, `vl_storage_blocks{type="storage/small"}`, ss.SmallPartBlocks)
-	metrics.WriteGaugeUint64(w, `vl_storage_blocks{type="storage/big"}`, ss.BigPartBlocks)
+	ms.NewGauge(`vl_partitions`, func() float64 {
+		return float64(m().PartitionsCount)
+	})
+	ms.NewGauge(`vl_streams_created_total`, func() float64 {
+		return float64(m().StreamsCreatedTotal)
+	})
 
-	metrics.WriteGaugeUint64(w, `vl_partitions`, ss.PartitionsCount)
-	metrics.WriteCounterUint64(w, `vl_streams_created_total`, ss.StreamsCreatedTotal)
+	ms.NewGauge(`vl_indexdb_rows`, func() float64 {
+		return float64(m().IndexdbItemsCount)
+	})
+	ms.NewGauge(`vl_indexdb_parts`, func() float64 {
+		return float64(m().IndexdbPartsCount)
+	})
+	ms.NewGauge(`vl_indexdb_blocks`, func() float64 {
+		return float64(m().IndexdbBlocksCount)
+	})
 
-	metrics.WriteGaugeUint64(w, `vl_indexdb_rows`, ss.IndexdbItemsCount)
-	metrics.WriteGaugeUint64(w, `vl_indexdb_parts`, ss.IndexdbPartsCount)
-	metrics.WriteGaugeUint64(w, `vl_indexdb_blocks`, ss.IndexdbBlocksCount)
+	ms.NewGauge(`vl_data_size_bytes{type="indexdb"}`, func() float64 {
+		return float64(m().IndexdbSizeBytes)
+	})
+	ms.NewGauge(`vl_data_size_bytes{type="storage"}`, func() float64 {
+		dm := m()
+		return float64(dm.CompressedInmemorySize + dm.CompressedFileSize)
+	})
 
-	metrics.WriteGaugeUint64(w, `vl_data_size_bytes{type="indexdb"}`, ss.IndexdbSizeBytes)
-	metrics.WriteGaugeUint64(w, `vl_data_size_bytes{type="storage"}`, ss.CompressedInmemorySize+ss.CompressedSmallPartSize+ss.CompressedBigPartSize)
+	ms.NewGauge(`vl_compressed_data_size_bytes{type="inmemory"}`, func() float64 {
+		return float64(m().CompressedInmemorySize)
+	})
+	ms.NewGauge(`vl_compressed_data_size_bytes{type="file"}`, func() float64 {
+		return float64(m().CompressedFileSize)
+	})
+	ms.NewGauge(`vl_uncompressed_data_size_bytes{type="inmemory"}`, func() float64 {
+		return float64(m().UncompressedInmemorySize)
+	})
+	ms.NewGauge(`vl_uncompressed_data_size_bytes{type="file"}`, func() float64 {
+		return float64(m().UncompressedFileSize)
+	})
 
-	metrics.WriteGaugeUint64(w, `vl_compressed_data_size_bytes{type="storage/inmemory"}`, ss.CompressedInmemorySize)
-	metrics.WriteGaugeUint64(w, `vl_compressed_data_size_bytes{type="storage/small"}`, ss.CompressedSmallPartSize)
-	metrics.WriteGaugeUint64(w, `vl_compressed_data_size_bytes{type="storage/big"}`, ss.CompressedBigPartSize)
+	ms.NewGauge(`vl_rows_dropped_total{reason="too_big_timestamp"}`, func() float64 {
+		return float64(m().RowsDroppedTooBigTimestamp)
+	})
+	ms.NewGauge(`vl_rows_dropped_total{reason="too_small_timestamp"}`, func() float64 {
+		return float64(m().RowsDroppedTooSmallTimestamp)
+	})
 
-	metrics.WriteGaugeUint64(w, `vl_uncompressed_data_size_bytes{type="storage/inmemory"}`, ss.UncompressedInmemorySize)
-	metrics.WriteGaugeUint64(w, `vl_uncompressed_data_size_bytes{type="storage/small"}`, ss.UncompressedSmallPartSize)
-	metrics.WriteGaugeUint64(w, `vl_uncompressed_data_size_bytes{type="storage/big"}`, ss.UncompressedBigPartSize)
-
-	metrics.WriteCounterUint64(w, `vl_rows_dropped_total{reason="too_big_timestamp"}`, ss.RowsDroppedTooBigTimestamp)
-	metrics.WriteCounterUint64(w, `vl_rows_dropped_total{reason="too_small_timestamp"}`, ss.RowsDroppedTooSmallTimestamp)
+	return ms
 }

app/vmagent/Makefile

@@ -88,9 +88,6 @@ vmagent-linux-ppc64le:
 vmagent-linux-s390x:
 	APP_NAME=vmagent CGO_ENABLED=0 GOOS=linux GOARCH=s390x $(MAKE) app-local-goos-goarch
 
-vmagent-linux-loong64:
-	APP_NAME=vmagent CGO_ENABLED=0 GOOS=linux GOARCH=loong64 $(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

@@ -1,3 +1,3 @@
-See vmagent docs [here](https://docs.victoriametrics.com/vmagent/).
+See vmagent docs [here](https://docs.victoriametrics.com/vmagent.html).
 
-vmagent docs can be edited at [docs/vmagent.md](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/docs/vmagent.md).
+vmagent docs can be edited at [docs/vmagent.md](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/docs/vmagent.md).

app/vmagent/common/push_ctx.go

@@ -3,15 +3,13 @@ package common
 import (
 	"sync"
 
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/cgroup"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
 )
 
 // PushCtx is a context used for populating WriteRequest.
 type PushCtx struct {
-	// WriteRequest contains the WriteRequest, which must be pushed later to remote storage.
-	//
-	// The actual labels and samples for the time series are stored in Labels and Samples fields.
 	WriteRequest prompbmarshal.WriteRequest
 
 	// Labels contains flat list of all the labels used in WriteRequest.
@@ -23,7 +21,13 @@ type PushCtx struct {
 
 // Reset resets ctx.
 func (ctx *PushCtx) Reset() {
-	ctx.WriteRequest.Reset()
+	tss := ctx.WriteRequest.Timeseries
+	for i := range tss {
+		ts := &tss[i]
+		ts.Labels = nil
+		ts.Samples = nil
+	}
+	ctx.WriteRequest.Timeseries = ctx.WriteRequest.Timeseries[:0]
 
 	promrelabel.CleanLabels(ctx.Labels)
 	ctx.Labels = ctx.Labels[:0]
@@ -35,10 +39,15 @@ func (ctx *PushCtx) Reset() {
 //
 // Call PutPushCtx when the ctx is no longer needed.
 func GetPushCtx() *PushCtx {
-	if v := pushCtxPool.Get(); v != nil {
-		return v.(*PushCtx)
+	select {
+	case ctx := <-pushCtxPoolCh:
+		return ctx
+	default:
+		if v := pushCtxPool.Get(); v != nil {
+			return v.(*PushCtx)
+		}
+		return &PushCtx{}
 	}
-	return &PushCtx{}
 }
 
 // PutPushCtx returns ctx to the pool.
@@ -46,7 +55,12 @@ func GetPushCtx() *PushCtx {
 // ctx mustn't be used after returning to the pool.
 func PutPushCtx(ctx *PushCtx) {
 	ctx.Reset()
-	pushCtxPool.Put(ctx)
+	select {
+	case pushCtxPoolCh <- ctx:
+	default:
+		pushCtxPool.Put(ctx)
+	}
 }
 
 var pushCtxPool sync.Pool
+var pushCtxPoolCh = make(chan *PushCtx, cgroup.AvailableCPUs())

app/vmagent/influx/request_handler.go

@@ -10,6 +10,7 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/cgroup"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
 	parserCommon "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
@@ -159,15 +160,25 @@ func (ctx *pushCtx) reset() {
 }
 
 func getPushCtx() *pushCtx {
-	if v := pushCtxPool.Get(); v != nil {
-		return v.(*pushCtx)
+	select {
+	case ctx := <-pushCtxPoolCh:
+		return ctx
+	default:
+		if v := pushCtxPool.Get(); v != nil {
+			return v.(*pushCtx)
+		}
+		return &pushCtx{}
 	}
-	return &pushCtx{}
 }
 
 func putPushCtx(ctx *pushCtx) {
 	ctx.reset()
-	pushCtxPool.Put(ctx)
+	select {
+	case pushCtxPoolCh <- ctx:
+	default:
+		pushCtxPool.Put(ctx)
+	}
 }
 
 var pushCtxPool sync.Pool
+var pushCtxPoolCh = make(chan *pushCtx, cgroup.AvailableCPUs())

app/vmagent/main.go

@@ -8,6 +8,7 @@ import (
 	"net/http"
 	"os"
 	"strings"
+	"sync/atomic"
 	"time"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/csvimport"
@@ -40,7 +41,6 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/procutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promscrape"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/opentelemetry/firehose"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/pushmetrics"
 	"github.com/VictoriaMetrics/metrics"
 )
@@ -70,8 +70,8 @@ var (
 		"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 = flagutil.NewPassword("configAuthKey", "Authorization key for accessing /config page. It must be passed via authKey query arg. It overrides httpAuth.* settings.")
-	reloadAuthKey = flagutil.NewPassword("reloadAuthKey", "Auth key for /-/reload http endpoint. It must be passed via authKey query arg. It overrides httpAuth.* settings.")
+	configAuthKey = flagutil.NewPassword("configAuthKey", "Authorization key for accessing /config page. It must be passed via authKey query arg")
+	reloadAuthKey = flagutil.NewPassword("reloadAuthKey", "Auth key for /-/reload http endpoint. It must be passed as authKey=...")
 	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")
@@ -126,7 +126,6 @@ func main() {
 	}
 	logger.Infof("starting vmagent at %q...", listenAddrs)
 	startTime := time.Now()
-	remotewrite.StartIngestionRateLimiter()
 	remotewrite.Init()
 	common.StartUnmarshalWorkers()
 	if len(*influxListenAddr) > 0 {
@@ -154,7 +153,6 @@ func main() {
 	pushmetrics.Init()
 	sig := procutil.WaitForSigterm()
 	logger.Infof("received signal %s", sig)
-	remotewrite.StopIngestionRateLimiter()
 	pushmetrics.Stop()
 
 	startTime = time.Now()
@@ -225,7 +223,7 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 		}
 		w.Header().Add("Content-Type", "text/html; charset=utf-8")
 		fmt.Fprintf(w, "<h2>vmagent</h2>")
-		fmt.Fprintf(w, "See docs at <a href='https://docs.victoriametrics.com/vmagent/'>https://docs.victoriametrics.com/vmagent/</a></br>")
+		fmt.Fprintf(w, "See docs at <a href='https://docs.victoriametrics.com/vmagent.html'>https://docs.victoriametrics.com/vmagent.html</a></br>")
 		fmt.Fprintf(w, "Useful endpoints:</br>")
 		httpserver.WriteAPIHelp(w, [][2]string{
 			{"targets", "status for discovered active targets"},
@@ -264,7 +262,7 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 		path = strings.TrimSuffix(path, "/")
 	}
 	switch path {
-	case "/prometheus/api/v1/write", "/api/v1/write", "/api/v1/push", "/prometheus/api/v1/push":
+	case "/prometheus/api/v1/write", "/api/v1/write":
 		if common.HandleVMProtoServerHandshake(w, r) {
 			return true
 		}
@@ -316,14 +314,14 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 		influxQueryRequests.Inc()
 		influxutils.WriteDatabaseNames(w)
 		return true
-	case "/opentelemetry/api/v1/push", "/opentelemetry/v1/metrics":
+	case "/opentelemetry/api/v1/push":
 		opentelemetryPushRequests.Inc()
 		if err := opentelemetry.InsertHandler(nil, r); err != nil {
 			opentelemetryPushErrors.Inc()
 			httpserver.Errorf(w, r, "%s", err)
 			return true
 		}
-		firehose.WriteSuccessResponse(w, r)
+		w.WriteHeader(http.StatusOK)
 		return true
 	case "/newrelic":
 		newrelicCheckRequest.Inc()
@@ -461,7 +459,7 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 		w.WriteHeader(http.StatusOK)
 		return true
 	case "/ready":
-		if rdy := promscrape.PendingScrapeConfigs.Load(); rdy > 0 {
+		if rdy := atomic.LoadInt32(&promscrape.PendingScrapeConfigs); rdy > 0 {
 			errMsg := fmt.Sprintf("waiting for scrapes to init, left: %d", rdy)
 			http.Error(w, errMsg, http.StatusTooEarly)
 		} else {
@@ -513,7 +511,7 @@ func processMultitenantRequest(w http.ResponseWriter, r *http.Request, path stri
 		p.Suffix = strings.TrimSuffix(p.Suffix, "/")
 	}
 	switch p.Suffix {
-	case "prometheus/", "prometheus", "prometheus/api/v1/write", "prometheus/api/v1/push":
+	case "prometheus/", "prometheus", "prometheus/api/v1/write":
 		prometheusWriteRequests.Inc()
 		if err := promremotewrite.InsertHandler(at, r); err != nil {
 			prometheusWriteErrors.Inc()
@@ -562,14 +560,14 @@ func processMultitenantRequest(w http.ResponseWriter, r *http.Request, path stri
 		influxQueryRequests.Inc()
 		influxutils.WriteDatabaseNames(w)
 		return true
-	case "opentelemetry/api/v1/push", "opentelemetry/v1/metrics":
+	case "opentelemetry/api/v1/push":
 		opentelemetryPushRequests.Inc()
 		if err := opentelemetry.InsertHandler(at, r); err != nil {
 			opentelemetryPushErrors.Inc()
 			httpserver.Errorf(w, r, "%s", err)
 			return true
 		}
-		firehose.WriteSuccessResponse(w, r)
+		w.WriteHeader(http.StatusOK)
 		return true
 	case "newrelic":
 		newrelicCheckRequest.Inc()
@@ -688,8 +686,8 @@ var (
 	datadogIntakeRequests   = metrics.NewCounter(`vmagent_http_requests_total{path="/datadog/intake", protocol="datadog"}`)
 	datadogMetadataRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/datadog/api/v1/metadata", protocol="datadog"}`)
 
-	opentelemetryPushRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/opentelemetry/v1/metrics", protocol="opentelemetry"}`)
-	opentelemetryPushErrors   = metrics.NewCounter(`vmagent_http_request_errors_total{path="/opentelemetry/v1/metrics", protocol="opentelemetry"}`)
+	opentelemetryPushRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/opentelemetry/api/v1/push", protocol="opentelemetry"}`)
+	opentelemetryPushErrors   = metrics.NewCounter(`vmagent_http_request_errors_total{path="/opentelemetry/api/v1/push", protocol="opentelemetry"}`)
 
 	newrelicWriteRequests = metrics.NewCounter(`vm_http_requests_total{path="/newrelic/infra/v2/metrics/events/bulk", protocol="newrelic"}`)
 	newrelicWriteErrors   = metrics.NewCounter(`vm_http_request_errors_total{path="/newrelic/infra/v2/metrics/events/bulk", protocol="newrelic"}`)
@@ -718,7 +716,7 @@ func usage() {
 	const s = `
 vmagent collects metrics data via popular data ingestion protocols and routes it to VictoriaMetrics.
 
-See the docs at https://docs.victoriametrics.com/vmagent/ .
+See the docs at https://docs.victoriametrics.com/vmagent.html .
 `
 	flagutil.Usage(s)
 }

app/vmagent/multiarch/Dockerfile

@@ -1,7 +1,7 @@
 # See https://medium.com/on-docker/use-multi-stage-builds-to-inject-ca-certs-ad1e8f01de1b
 ARG certs_image
 ARG root_image
-FROM $certs_image AS certs
+FROM $certs_image as certs
 RUN apk update && apk upgrade && apk --update --no-cache add ca-certificates
 
 FROM $root_image

app/vmagent/opentelemetry/request_handler.go

@@ -9,7 +9,6 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
 	parserCommon "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/opentelemetry/firehose"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/opentelemetry/stream"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
 	"github.com/VictoriaMetrics/metrics"
@@ -28,15 +27,10 @@ func InsertHandler(at *auth.Token, req *http.Request) error {
 		return err
 	}
 	isGzipped := req.Header.Get("Content-Encoding") == "gzip"
-	var processBody func([]byte) ([]byte, error)
 	if req.Header.Get("Content-Type") == "application/json" {
-		if req.Header.Get("X-Amz-Firehose-Protocol-Version") != "" {
-			processBody = firehose.ProcessRequestBody
-		} else {
-			return fmt.Errorf("json encoding isn't supported for opentelemetry format. Use protobuf encoding")
-		}
+		return fmt.Errorf("json encoding isn't supported for opentelemetry format. Use protobuf encoding")
 	}
-	return stream.ParseStream(req.Body, isGzipped, processBody, func(tss []prompbmarshal.TimeSeries) error {
+	return stream.ParseStream(req.Body, isGzipped, func(tss []prompbmarshal.TimeSeries) error {
 		return insertRows(at, tss, extraLabels)
 	})
 }

app/vmagent/remotewrite/client.go

@@ -11,34 +11,31 @@ import (
 	"sync"
 	"time"
 
-	"github.com/VictoriaMetrics/metrics"
-
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/awsapi"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httputils"
 	"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/ratelimiter"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/timerpool"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/timeutil"
+	"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/#victoriametrics-remote-write-protocol")
+		"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/#victoriametrics-remote-write-protocol")
+		"to the corresponding -remoteWrite.url . See https://docs.victoriametrics.com/vmagent.html#victoriametrics-remote-write-protocol")
 
 	rateLimit = flagutil.NewArrayInt("remoteWrite.rateLimit", 0, "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. See also -maxIngestionRate")
+		"is sent after temporary unavailability of the remote storage")
 	sendTimeout = flagutil.NewArrayDuration("remoteWrite.sendTimeout", time.Minute, "Timeout for sending a single block of data to the corresponding -remoteWrite.url")
 	proxyURL    = flagutil.NewArrayString("remoteWrite.proxyURL", "Optional proxy URL for writing data to the corresponding -remoteWrite.url. "+
 		"Supported proxies: http, https, socks5. Example: -remoteWrite.proxyURL=socks5://proxy:1234")
 
-	tlsHandshakeTimeout   = flagutil.NewArrayDuration("remoteWrite.tlsHandshakeTimeout", 20*time.Second, "The timeout for establishing tls connections to the corresponding -remoteWrite.url")
+	tlsHandshakeTimeout   = flagutil.NewArrayDuration("remoteWrite.tlsHandshakeTimeout", 20*time.Second, "The timeout for estabilishing tls connections to the corresponding -remoteWrite.url")
 	tlsInsecureSkipVerify = flagutil.NewArrayBool("remoteWrite.tlsInsecureSkipVerify", "Whether to skip tls verification when connecting to the corresponding -remoteWrite.url")
 	tlsCertFile           = flagutil.NewArrayString("remoteWrite.tlsCertFile", "Optional path to client-side TLS certificate file to use when connecting "+
 		"to the corresponding -remoteWrite.url")
@@ -94,7 +91,7 @@ type client struct {
 	authCfg   *promauth.Config
 	awsCfg    *awsapi.Config
 
-	rl *ratelimiter.RateLimiter
+	rl rateLimiter
 
 	bytesSent       *metrics.Counter
 	blocksSent      *metrics.Counter
@@ -115,12 +112,17 @@ func newHTTPClient(argIdx int, remoteWriteURL, sanitizedURL string, fq *persiste
 	if err != nil {
 		logger.Fatalf("cannot initialize auth config for -remoteWrite.url=%q: %s", remoteWriteURL, err)
 	}
+	tlsCfg, err := authCfg.NewTLSConfig()
+	if err != nil {
+		logger.Fatalf("cannot initialize tls config for -remoteWrite.url=%q: %s", remoteWriteURL, err)
+	}
 	awsCfg, err := getAWSAPIConfig(argIdx)
 	if err != nil {
 		logger.Fatalf("cannot initialize AWS Config for -remoteWrite.url=%q: %s", remoteWriteURL, err)
 	}
 	tr := &http.Transport{
-		DialContext:         httputils.GetStatDialFunc("vmagent_remotewrite"),
+		DialContext:         statDial,
+		TLSClientConfig:     tlsCfg,
 		TLSHandshakeTimeout: tlsHandshakeTimeout.GetOptionalArg(argIdx),
 		MaxConnsPerHost:     2 * concurrency,
 		MaxIdleConnsPerHost: 2 * concurrency,
@@ -139,7 +141,7 @@ func newHTTPClient(argIdx int, remoteWriteURL, sanitizedURL string, fq *persiste
 		tr.Proxy = http.ProxyURL(pu)
 	}
 	hc := &http.Client{
-		Transport: authCfg.NewRoundTripper(tr),
+		Transport: tr,
 		Timeout:   sendTimeout.GetOptionalArg(argIdx),
 	}
 	c := &client{
@@ -166,7 +168,7 @@ func newHTTPClient(argIdx int, remoteWriteURL, sanitizedURL string, fq *persiste
 		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/#victoriametrics-remote-write-protocol", sanitizedURL)
+				"See https://docs.victoriametrics.com/vmagent.html#victoriametrics-remote-write-protocol", sanitizedURL)
 		}
 	}
 	c.useVMProto = useVMProto
@@ -175,11 +177,12 @@ func newHTTPClient(argIdx int, remoteWriteURL, sanitizedURL string, fq *persiste
 }
 
 func (c *client) init(argIdx, concurrency int, sanitizedURL string) {
-	limitReached := metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_rate_limit_reached_total{url=%q}`, c.sanitizedURL))
 	if bytesPerSec := rateLimit.GetOptionalArg(argIdx); bytesPerSec > 0 {
 		logger.Infof("applying %d bytes per second rate limit for -remoteWrite.url=%q", bytesPerSec, sanitizedURL)
-		c.rl = ratelimiter.New(int64(bytesPerSec), limitReached, c.stopCh)
+		c.rl.perSecondLimit = int64(bytesPerSec)
 	}
+	c.rl.limitReached = metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_rate_limit_reached_total{url=%q}`, c.sanitizedURL))
+
 	c.bytesSent = metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_bytes_sent_total{url=%q}`, c.sanitizedURL))
 	c.blocksSent = metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_blocks_sent_total{url=%q}`, c.sanitizedURL))
 	c.rateLimit = metrics.GetOrCreateGauge(fmt.Sprintf(`vmagent_remotewrite_rate_limit{url=%q}`, c.sanitizedURL), func() float64 {
@@ -300,11 +303,6 @@ func (c *client) runWorker() {
 		if !ok {
 			return
 		}
-		if len(block) == 0 {
-			// skip empty data blocks from sending
-			// see https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6241
-			continue
-		}
 		go func() {
 			startTime := time.Now()
 			ch <- c.sendBlock(block)
@@ -398,7 +396,7 @@ func (c *client) newRequest(url string, body []byte) (*http.Request, error) {
 // 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.rl.register(len(block), c.stopCh)
 	maxRetryDuration := timeutil.AddJitterToDuration(time.Minute)
 	retryDuration := timeutil.AddJitterToDuration(time.Second)
 	retriesCount := 0
@@ -481,3 +479,45 @@ again:
 }
 
 var remoteWriteRejectedLogger = logger.WithThrottler("remoteWriteRejected", 5*time.Second)
+
+type rateLimiter struct {
+	perSecondLimit int64
+
+	// mu protects budget and deadline from concurrent access.
+	mu sync.Mutex
+
+	// The current budget. It is increased by perSecondLimit every second.
+	budget int64
+
+	// The next deadline for increasing the budget by perSecondLimit
+	deadline time.Time
+
+	limitReached *metrics.Counter
+}
+
+func (rl *rateLimiter) register(dataLen int, stopCh <-chan struct{}) {
+	limit := rl.perSecondLimit
+	if limit <= 0 {
+		return
+	}
+
+	rl.mu.Lock()
+	defer rl.mu.Unlock()
+
+	for rl.budget <= 0 {
+		if d := time.Until(rl.deadline); d > 0 {
+			rl.limitReached.Inc()
+			t := timerpool.Get(d)
+			select {
+			case <-stopCh:
+				timerpool.Put(t)
+				return
+			case <-t.C:
+				timerpool.Put(t)
+			}
+		}
+		rl.budget += limit
+		rl.deadline = time.Now().Add(time.Second)
+	}
+	rl.budget -= int64(dataLen)
+}

app/vmagent/remotewrite/pendingseries.go

@@ -28,7 +28,7 @@ var (
 	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/#victoriametrics-remote-write-protocol")
+		"See https://docs.victoriametrics.com/vmagent.html#victoriametrics-remote-write-protocol")
 )
 
 type pendingSeries struct {
@@ -82,7 +82,7 @@ func (ps *pendingSeries) periodicFlusher() {
 			ps.mu.Unlock()
 			return
 		case <-ticker.C:
-			if fasttime.UnixTimestamp()-ps.wr.lastFlushTime.Load() < uint64(flushSeconds) {
+			if fasttime.UnixTimestamp()-atomic.LoadUint64(&ps.wr.lastFlushTime) < uint64(flushSeconds) {
 				continue
 			}
 		}
@@ -93,7 +93,8 @@ func (ps *pendingSeries) periodicFlusher() {
 }
 
 type writeRequest struct {
-	lastFlushTime atomic.Uint64
+	// Move lastFlushTime to the top of the struct in order to guarantee atomic access on 32-bit architectures.
+	lastFlushTime uint64
 
 	// The queue to send blocks to.
 	fq *persistentqueue.FastQueue
@@ -122,7 +123,11 @@ func (wr *writeRequest) reset() {
 
 	wr.wr.Timeseries = nil
 
-	clear(wr.tss)
+	for i := range wr.tss {
+		ts := &wr.tss[i]
+		ts.Labels = nil
+		ts.Samples = nil
+	}
 	wr.tss = wr.tss[:0]
 
 	promrelabel.CleanLabels(wr.labels)
@@ -150,7 +155,7 @@ func (wr *writeRequest) mustWriteBlock(block []byte) bool {
 
 func (wr *writeRequest) tryFlush() bool {
 	wr.wr.Timeseries = wr.tss
-	wr.lastFlushTime.Store(fasttime.UnixTimestamp())
+	atomic.StoreUint64(&wr.lastFlushTime, fasttime.UnixTimestamp())
 	if !tryPushWriteRequest(&wr.wr, wr.fq.TryWriteBlock, wr.isVMRemoteWrite) {
 		return false
 	}

app/vmagent/remotewrite/pendingseries_test.go

@@ -34,7 +34,7 @@ func testPushWriteRequest(t *testing.T, rowsCount, expectedBlockLenProm, expecte
 			return true
 		}
 		if !tryPushWriteRequest(wr, pushBlock, isVMRemoteWrite) {
-			t.Fatalf("cannot push data to remote storage")
+			t.Fatalf("cannot push data to to remote storage")
 		}
 		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%%",

app/vmagent/remotewrite/relabel.go

@@ -19,10 +19,10 @@ var (
 	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/#relabeling")
+		"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/#relabeling")
+		"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. "+
@@ -46,11 +46,11 @@ func loadRelabelConfigs() (*relabelConfigs, error) {
 		}
 		rcs.global = global
 	}
-	if len(*relabelConfigPaths) > len(*remoteWriteURLs) {
-		return nil, fmt.Errorf("too many -remoteWrite.urlRelabelConfig args: %d; it mustn't exceed the number of -remoteWrite.url args: %d",
-			len(*relabelConfigPaths), (len(*remoteWriteURLs)))
+	if len(*relabelConfigPaths) > (len(*remoteWriteURLs) + len(*remoteWriteMultitenantURLs)) {
+		return nil, fmt.Errorf("too many -remoteWrite.urlRelabelConfig args: %d; it mustn't exceed the number of -remoteWrite.url or -remoteWrite.multitenantURL args: %d",
+			len(*relabelConfigPaths), (len(*remoteWriteURLs) + len(*remoteWriteMultitenantURLs)))
 	}
-	rcs.perURL = make([]*promrelabel.ParsedConfigs, len(*remoteWriteURLs))
+	rcs.perURL = make([]*promrelabel.ParsedConfigs, (len(*remoteWriteURLs) + len(*remoteWriteMultitenantURLs)))
 	for i, path := range *relabelConfigPaths {
 		if len(path) == 0 {
 			// Skip empty relabel config.

app/vmagent/remotewrite/remotewrite.go

@@ -27,8 +27,8 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promutils"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/ratelimiter"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/streamaggr"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
 	"github.com/VictoriaMetrics/metrics"
 	"github.com/cespare/xxhash/v2"
 )
@@ -38,30 +38,25 @@ var (
 		"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. "+
 		"The data can be sharded among the configured remote storage systems if -remoteWrite.shardByURL flag is set")
+	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. "+
+		"This flag is deprecated in favor of -enableMultitenantHandlers . See https://docs.victoriametrics.com/vmagent.html#multitenancy")
 	enableMultitenantHandlers = flag.Bool("enableMultitenantHandlers", false, "Whether to process incoming data via multitenant insert handlers according to "+
-		"https://docs.victoriametrics.com/cluster-victoriametrics/#url-format . By default incoming data is processed via single-node insert handlers "+
+		"https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html#url-format . By default incoming data is processed via single-node insert handlers "+
 		"according to https://docs.victoriametrics.com/#how-to-import-time-series-data ."+
-		"See https://docs.victoriametrics.com/vmagent/#multitenancy for details")
-
+		"See https://docs.victoriametrics.com/vmagent.html#multitenancy for details")
 	shardByURL = flag.Bool("remoteWrite.shardByURL", false, "Whether to shard outgoing series across all the remote storage systems enumerated via -remoteWrite.url . "+
-		"By default the data is replicated across all the -remoteWrite.url . See https://docs.victoriametrics.com/vmagent/#sharding-among-remote-storages . "+
-		"See also -remoteWrite.shardByURLReplicas")
-	shardByURLReplicas = flag.Int("remoteWrite.shardByURLReplicas", 1, "How many copies of data to make among remote storage systems enumerated via -remoteWrite.url "+
-		"when -remoteWrite.shardByURL is set. See https://docs.victoriametrics.com/vmagent/#sharding-among-remote-storages")
+		"By default the data is replicated across all the -remoteWrite.url . See https://docs.victoriametrics.com/vmagent.html#sharding-among-remote-storages")
 	shardByURLLabels = flagutil.NewArrayString("remoteWrite.shardByURL.labels", "Optional list of labels, which must be used for sharding outgoing samples "+
 		"among remote storage systems if -remoteWrite.shardByURL command-line flag is set. By default all the labels are used for sharding in order to gain "+
-		"even distribution of series over the specified -remoteWrite.url systems. See also -remoteWrite.shardByURL.ignoreLabels")
-	shardByURLIgnoreLabels = flagutil.NewArrayString("remoteWrite.shardByURL.ignoreLabels", "Optional list of labels, which must be ignored when sharding outgoing samples "+
-		"among remote storage systems if -remoteWrite.shardByURL command-line flag is set. By default all the labels are used for sharding in order to gain "+
-		"even distribution of series over the specified -remoteWrite.url systems. See also -remoteWrite.shardByURL.labels")
-
+		"even distribution of series over the specified -remoteWrite.url systems")
 	tmpDataPath = flag.String("remoteWrite.tmpDataPath", "vmagent-remotewrite-data", "Path to directory for storing pending data, which isn't sent to the configured -remoteWrite.url . "+
 		"See also -remoteWrite.maxDiskUsagePerURL and -remoteWrite.disableOnDiskQueue")
 	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 depends on the number of available CPU cores. It should work fine in most cases since it minimizes resource usage")
+		"isn't enough for sending high volume of collected data to remote storage. Default value is 2 * numberOfAvailableCPUs")
 	showRemoteWriteURL = flag.Bool("remoteWrite.showURL", false, "Whether to show -remoteWrite.url in the exported metrics. "+
 		"It is hidden by default, since it can contain sensitive info such as auth key")
 	maxPendingBytesPerURL = flagutil.NewArrayBytes("remoteWrite.maxDiskUsagePerURL", 0, "The maximum file-based buffer size in bytes at -remoteWrite.tmpDataPath "+
@@ -81,52 +76,56 @@ var (
 		`For example, if m{k1="v1",k2="v2"} may be sent as m{k2="v2",k1="v1"}`+
 		`Enabled sorting for labels can slow down ingestion performance a bit`)
 	maxHourlySeries = flag.Int("remoteWrite.maxHourlySeries", 0, "The maximum number of unique series vmagent can send to remote storage systems during the last hour. "+
-		"Excess series are logged and dropped. This can be useful for limiting series cardinality. See https://docs.victoriametrics.com/vmagent/#cardinality-limiter")
+		"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/#cardinality-limiter")
-	maxIngestionRate = flag.Int("maxIngestionRate", 0, "The maximum number of samples vmagent can receive per second. Data ingestion is paused when the limit is exceeded. "+
-		"By default there are no limits on samples ingestion rate. See also -remoteWrite.rateLimit")
+		"Excess series are logged and dropped. This can be useful for limiting series churn rate. See https://docs.victoriametrics.com/vmagent.html#cardinality-limiter")
 
-	disableOnDiskQueue = flagutil.NewArrayBool("remoteWrite.disableOnDiskQueue", "Whether to disable storing pending data to -remoteWrite.tmpDataPath "+
-		"when the configured remote storage systems cannot keep up with the data ingestion rate. See https://docs.victoriametrics.com/vmagent#disabling-on-disk-persistence ."+
+	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, -remoteWrite.streamAggr.dropInput and -remoteWrite.streamAggr.dedupInterval")
+	streamAggrKeepInput = flagutil.NewArrayBool("remoteWrite.streamAggr.keepInput", "Whether to keep all the input samples after the aggregation "+
+		"with -remoteWrite.streamAggr.config. By default, only aggregates samples are dropped, while the remaining samples "+
+		"are written to the corresponding -remoteWrite.url . See also -remoteWrite.streamAggr.dropInput and https://docs.victoriametrics.com/stream-aggregation.html")
+	streamAggrDropInput = flagutil.NewArrayBool("remoteWrite.streamAggr.dropInput", "Whether to drop all the input samples after the aggregation "+
+		"with -remoteWrite.streamAggr.config. By default, only aggregates samples are dropped, while the remaining samples "+
+		"are written to the corresponding -remoteWrite.url . See also -remoteWrite.streamAggr.keepInput and https://docs.victoriametrics.com/stream-aggregation.html")
+	streamAggrDedupInterval = flagutil.NewArrayDuration("remoteWrite.streamAggr.dedupInterval", 0, "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")
+	disableOnDiskQueue = flag.Bool("remoteWrite.disableOnDiskQueue", false, "Whether to disable storing pending data to -remoteWrite.tmpDataPath "+
+		"when the configured remote storage systems cannot keep up with the data ingestion rate. See https://docs.victoriametrics.com/vmagent.html#disabling-on-disk-persistence ."+
 		"See also -remoteWrite.dropSamplesOnOverload")
-	dropSamplesOnOverload = flagutil.NewArrayBool("remoteWrite.dropSamplesOnOverload", "Whether to drop samples when -remoteWrite.disableOnDiskQueue is set and if the samples "+
-		"cannot be pushed into the configured remote storage systems in a timely manner. See https://docs.victoriametrics.com/vmagent#disabling-on-disk-persistence")
+	dropSamplesOnOverload = flag.Bool("remoteWrite.dropSamplesOnOverload", false, "Whether to drop samples when -remoteWrite.disableOnDiskQueue is set and if the samples "+
+		"cannot be pushed into the configured remote storage systems in a timely manner. See https://docs.victoriametrics.com/vmagent.html#disabling-on-disk-persistence")
 )
 
 var (
-	// rwctxs contains statically populated entries when -remoteWrite.url is specified.
-	rwctxs []*remoteWriteCtx
+	// rwctxsDefault contains statically populated entries when -remoteWrite.url is specified.
+	rwctxsDefault []*remoteWriteCtx
 
-	// Data without tenant id is written to defaultAuthToken if -enableMultitenantHandlers is specified.
+	// rwctxsMap contains dynamically populated entries when -remoteWrite.multitenantURL is specified.
+	rwctxsMap     = make(map[tenantmetrics.TenantID][]*remoteWriteCtx)
+	rwctxsMapLock sync.Mutex
+
+	// Data without tenant id is written to defaultAuthToken if -remoteWrite.multitenantURL is specified.
 	defaultAuthToken = &auth.Token{}
 
 	// ErrQueueFullHTTPRetry must be returned when TryPush() returns false.
 	ErrQueueFullHTTPRetry = &httpserver.ErrorWithStatusCode{
 		Err: fmt.Errorf("remote storage systems cannot keep up with the data ingestion rate; retry the request later " +
 			"or remove -remoteWrite.disableOnDiskQueue from vmagent command-line flags, so it could save pending data to -remoteWrite.tmpDataPath; " +
-			"see https://docs.victoriametrics.com/vmagent/#disabling-on-disk-persistence"),
+			"see https://docs.victoriametrics.com/vmagent.html#disabling-on-disk-persistence"),
 		StatusCode: http.StatusTooManyRequests,
 	}
-
-	// disableOnDiskQueueAll is set to true if all remoteWrite.urls were configured to disable persistent queue via disableOnDiskQueue
-	disableOnDiskQueueAll bool
 )
 
-// MultitenancyEnabled returns true if -enableMultitenantHandlers is specified.
+// MultitenancyEnabled returns true if -enableMultitenantHandlers or -remoteWrite.multitenantURL is specified.
 func MultitenancyEnabled() bool {
-	return *enableMultitenantHandlers
+	return *enableMultitenantHandlers || len(*remoteWriteMultitenantURLs) > 0
 }
 
 // Contains the current relabelConfigs.
 var allRelabelConfigs atomic.Pointer[relabelConfigs]
 
-// Contains the current global stream aggregators.
-var sasGlobal atomic.Pointer[streamaggr.Aggregators]
-
-// Contains the current global deduplicator.
-var deduplicatorGlobal *streamaggr.Deduplicator
-
 // maxQueues limits the maximum value for `-remoteWrite.queues`. There is no sense in setting too high value,
 // since it may lead to high memory usage due to big number of buffers.
 var maxQueues = cgroup.AvailableCPUs() * 16
@@ -141,10 +140,7 @@ func InitSecretFlags() {
 	}
 }
 
-var (
-	shardByURLLabelsMap       map[string]struct{}
-	shardByURLIgnoreLabelsMap map[string]struct{}
-)
+var shardByURLLabelsMap map[string]struct{}
 
 // Init initializes remotewrite.
 //
@@ -152,8 +148,11 @@ var (
 //
 // Stop must be called for graceful shutdown.
 func Init() {
-	if len(*remoteWriteURLs) == 0 {
-		logger.Fatalf("at least one `-remoteWrite.url` command-line flag must be set")
+	if len(*remoteWriteURLs) == 0 && len(*remoteWriteMultitenantURLs) == 0 {
+		logger.Fatalf("at least one `-remoteWrite.url` or `-remoteWrite.multitenantURL` command-line flag must be set")
+	}
+	if len(*remoteWriteURLs) > 0 && len(*remoteWriteMultitenantURLs) > 0 {
+		logger.Fatalf("cannot set both `-remoteWrite.url` and `-remoteWrite.multitenantURL` command-line flags")
 	}
 	if *maxHourlySeries > 0 {
 		hourlySeriesLimiter = bloomfilter.NewLimiter(*maxHourlySeries, time.Hour)
@@ -173,21 +172,19 @@ func Init() {
 			return float64(dailySeriesLimiter.CurrentItems())
 		})
 	}
-
 	if *queues > maxQueues {
 		*queues = maxQueues
 	}
 	if *queues <= 0 {
 		*queues = 1
 	}
-
-	if len(*shardByURLLabels) > 0 && len(*shardByURLIgnoreLabels) > 0 {
-		logger.Fatalf("-remoteWrite.shardByURL.labels and -remoteWrite.shardByURL.ignoreLabels cannot be set simultaneously; " +
-			"see https://docs.victoriametrics.com/vmagent/#sharding-among-remote-storages")
+	if len(*shardByURLLabels) > 0 {
+		m := make(map[string]struct{}, len(*shardByURLLabels))
+		for _, label := range *shardByURLLabels {
+			m[label] = struct{}{}
+		}
+		shardByURLLabelsMap = m
 	}
-	shardByURLLabelsMap = newMapFromStrings(*shardByURLLabels)
-	shardByURLIgnoreLabelsMap = newMapFromStrings(*shardByURLIgnoreLabels)
-
 	initLabelsGlobal()
 
 	// Register SIGHUP handler for config reload before loadRelabelConfigs.
@@ -203,29 +200,9 @@ func Init() {
 	relabelConfigSuccess.Set(1)
 	relabelConfigTimestamp.Set(fasttime.UnixTimestamp())
 
-	sasFile, sasOpts := getStreamAggrOpts(-1)
-	if sasFile != "" {
-		sas, err := newStreamAggrConfig(-1, pushToRemoteStoragesDropFailed)
-		if err != nil {
-			logger.Fatalf("cannot initialize stream aggregators from -streamAggr.config=%q: %s", sasFile, err)
-		}
-		sasGlobal.Store(sas)
-	} else if sasOpts.DedupInterval > 0 {
-		deduplicatorGlobal = streamaggr.NewDeduplicator(pushToRemoteStoragesDropFailed, sasOpts.DedupInterval, sasOpts.DropInputLabels, sasOpts.Alias)
-	}
-
 	if len(*remoteWriteURLs) > 0 {
-		rwctxs = newRemoteWriteCtxs(nil, *remoteWriteURLs)
+		rwctxsDefault = newRemoteWriteCtxs(nil, *remoteWriteURLs)
 	}
-
-	disableOnDiskQueueAll = true
-	for _, v := range *disableOnDiskQueue {
-		if !v {
-			disableOnDiskQueueAll = false
-			break
-		}
-	}
-
 	dropDanglingQueues()
 
 	// Start config reloader.
@@ -248,15 +225,18 @@ func dropDanglingQueues() {
 	if *keepDanglingQueues {
 		return
 	}
+	if len(*remoteWriteMultitenantURLs) > 0 {
+		// Do not drop dangling queues for *remoteWriteMultitenantURLs, since it is impossible to determine
+		// unused queues for multitenant urls - they are created on demand when new sample for the given
+		// tenant is pushed to remote storage.
+		return
+	}
 	// Remove dangling persistent 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
 	//
-	// In case if there were many persistent queues with identical *remoteWriteURLs
-	// the queue with the last index will be dropped.
-	// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/6140
-	existingQueues := make(map[string]struct{}, len(rwctxs))
-	for _, rwctx := range rwctxs {
+	existingQueues := make(map[string]struct{}, len(rwctxsDefault))
+	for _, rwctx := range rwctxsDefault {
 		existingQueues[rwctx.fq.Dirname()] = struct{}{}
 	}
 
@@ -273,7 +253,7 @@ func dropDanglingQueues() {
 		}
 	}
 	if removed > 0 {
-		logger.Infof("removed %d dangling queues from %q, active queues: %d", removed, *tmpDataPath, len(rwctxs))
+		logger.Infof("removed %d dangling queues from %q, active queues: %d", removed, *tmpDataPath, len(rwctxsDefault))
 	}
 }
 
@@ -300,6 +280,24 @@ var (
 	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")
@@ -323,7 +321,7 @@ func newRemoteWriteCtxs(at *auth.Token, urls []string) []*remoteWriteCtx {
 		}
 		sanitizedURL := fmt.Sprintf("%d:secret-url", i+1)
 		if at != nil {
-			// Construct full remote_write url for the given tenant according to https://docs.victoriametrics.com/cluster-victoriametrics/#url-format
+			// Construct full remote_write url for the given tenant according to https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html#url-format
 			remoteWriteURL.Path = fmt.Sprintf("%s/insert/%d:%d/prometheus/api/v1/write", remoteWriteURL.Path, at.AccountID, at.ProjectID)
 			sanitizedURL = fmt.Sprintf("%s:%d:%d", sanitizedURL, at.AccountID, at.ProjectID)
 		}
@@ -335,39 +333,8 @@ func newRemoteWriteCtxs(at *auth.Token, urls []string) []*remoteWriteCtx {
 	return rwctxs
 }
 
-var (
-	configReloaderStopCh = make(chan struct{})
-	configReloaderWG     sync.WaitGroup
-)
-
-// StartIngestionRateLimiter starts ingestion rate limiter.
-//
-// Ingestion rate limiter must be started before Init() call.
-//
-// StopIngestionRateLimiter must be called before Stop() call in order to unblock all the callers
-// to ingestion rate limiter. Otherwise deadlock may occur at Stop() call.
-func StartIngestionRateLimiter() {
-	if *maxIngestionRate <= 0 {
-		return
-	}
-	ingestionRateLimitReached := metrics.NewCounter(`vmagent_max_ingestion_rate_limit_reached_total`)
-	ingestionRateLimiterStopCh = make(chan struct{})
-	ingestionRateLimiter = ratelimiter.New(int64(*maxIngestionRate), ingestionRateLimitReached, ingestionRateLimiterStopCh)
-}
-
-// StopIngestionRateLimiter stops ingestion rate limiter.
-func StopIngestionRateLimiter() {
-	if ingestionRateLimiterStopCh == nil {
-		return
-	}
-	close(ingestionRateLimiterStopCh)
-	ingestionRateLimiterStopCh = nil
-}
-
-var (
-	ingestionRateLimiter       *ratelimiter.RateLimiter
-	ingestionRateLimiterStopCh chan struct{}
-)
+var configReloaderStopCh = make(chan struct{})
+var configReloaderWG sync.WaitGroup
 
 // Stop stops remotewrite.
 //
@@ -376,16 +343,18 @@ func Stop() {
 	close(configReloaderStopCh)
 	configReloaderWG.Wait()
 
-	sasGlobal.Load().MustStop()
-	if deduplicatorGlobal != nil {
-		deduplicatorGlobal.MustStop()
-		deduplicatorGlobal = nil
-	}
-
-	for _, rwctx := range rwctxs {
+	for _, rwctx := range rwctxsDefault {
 		rwctx.MustStop()
 	}
-	rwctxs = nil
+	rwctxsDefault = nil
+
+	// There is no need in locking rwctxsMapLock here, since nobody should call TryPush during the Stop call.
+	for _, rwctxs := range rwctxsMap {
+		for _, rwctx := range rwctxs {
+			rwctx.MustStop()
+		}
+	}
+	rwctxsMap = nil
 
 	if sl := hourlySeriesLimiter; sl != nil {
 		sl.MustStop()
@@ -395,24 +364,30 @@ func Stop() {
 	}
 }
 
-// PushDropSamplesOnFailure pushes wr to the configured remote storage systems set via -remoteWrite.url
+// PushDropSamplesOnFailure pushes wr to the configured remote storage systems set via -remoteWrite.url and -remoteWrite.multitenantURL
+//
+// If at is nil, then the data is pushed to the configured -remoteWrite.url.
+// If at isn't nil, the data is pushed to the configured -remoteWrite.multitenantURL.
 //
 // PushDropSamplesOnFailure can modify wr contents.
 func PushDropSamplesOnFailure(at *auth.Token, wr *prompbmarshal.WriteRequest) {
 	_ = tryPush(at, wr, true)
 }
 
-// TryPush tries sending wr to the configured remote storage systems set via -remoteWrite.url
+// TryPush tries sending wr to the configured remote storage systems set via -remoteWrite.url and -remoteWrite.multitenantURL
+//
+// If at is nil, then the data is pushed to the configured -remoteWrite.url.
+// If at isn't nil, the data is pushed to the configured -remoteWrite.multitenantURL.
 //
 // TryPush can modify wr contents, so the caller must re-initialize wr before calling TryPush() after unsuccessful attempt.
 // TryPush may send partial data from wr on unsuccessful attempt, so repeated call for the same wr may send the data multiple times.
 //
 // The caller must return ErrQueueFullHTTPRetry to the client, which sends wr, if TryPush returns false.
 func TryPush(at *auth.Token, wr *prompbmarshal.WriteRequest) bool {
-	return tryPush(at, wr, false)
+	return tryPush(at, wr, *dropSamplesOnOverload)
 }
 
-func tryPush(at *auth.Token, wr *prompbmarshal.WriteRequest, forceDropSamplesOnFailure bool) bool {
+func tryPush(at *auth.Token, wr *prompbmarshal.WriteRequest, dropSamplesOnFailure bool) bool {
 	tss := wr.Timeseries
 
 	if at == nil && MultitenancyEnabled() {
@@ -421,25 +396,41 @@ func tryPush(at *auth.Token, wr *prompbmarshal.WriteRequest, forceDropSamplesOnF
 	}
 
 	var tenantRctx *relabelCtx
-	if at != nil {
+	var rwctxs []*remoteWriteCtx
+	if at == nil {
+		rwctxs = rwctxsDefault
+	} else if len(*remoteWriteMultitenantURLs) == 0 {
 		// Convert at to (vm_account_id, vm_project_id) labels.
 		tenantRctx = getRelabelCtx()
 		defer putRelabelCtx(tenantRctx)
+		rwctxs = rwctxsDefault
+	} else {
+		rwctxsMapLock.Lock()
+		tenantID := tenantmetrics.TenantID{
+			AccountID: at.AccountID,
+			ProjectID: at.ProjectID,
+		}
+		rwctxs = rwctxsMap[tenantID]
+		if rwctxs == nil {
+			rwctxs = newRemoteWriteCtxs(at, *remoteWriteMultitenantURLs)
+			rwctxsMap[tenantID] = rwctxs
+		}
+		rwctxsMapLock.Unlock()
 	}
+
 	rowsCount := getRowsCount(tss)
 
-	// Quick check whether writes to configured remote storage systems are blocked.
-	// This allows saving CPU time spent on relabeling and block compression
-	// if some of remote storage systems cannot keep up with the data ingestion rate.
-	// this shortcut is only applicable if all remote writes have disableOnDiskQueue = true
-	if disableOnDiskQueueAll {
+	if *disableOnDiskQueue {
+		// Quick check whether writes to configured remote storage systems are blocked.
+		// This allows saving CPU time spent on relabeling and block compression
+		// if some of remote storage systems cannot keep up with the data ingestion rate.
 		for _, rwctx := range rwctxs {
 			if rwctx.fq.IsWriteBlocked() {
-				rwctx.pushFailures.Inc()
-				if forceDropSamplesOnFailure || rwctx.dropSamplesOnOverload {
+				pushFailures.Inc()
+				if dropSamplesOnFailure {
 					// Just drop samples
-					rwctx.rowsDroppedOnPushFailure.Add(rowsCount)
-					continue
+					samplesDropped.Add(rowsCount)
+					return true
 				}
 				return false
 			}
@@ -458,8 +449,6 @@ func tryPush(at *auth.Token, wr *prompbmarshal.WriteRequest, forceDropSamplesOnF
 	// Allow up to 10x of labels per each block on average.
 	maxLabelsPerBlock := 10 * maxSamplesPerBlock
 
-	sas := sasGlobal.Load()
-
 	for len(tss) > 0 {
 		// Process big tss in smaller blocks in order to reduce the maximum memory usage
 		samplesCount := 0
@@ -473,9 +462,6 @@ func tryPush(at *auth.Token, wr *prompbmarshal.WriteRequest, forceDropSamplesOnF
 				break
 			}
 		}
-
-		ingestionRateLimiter.Register(samplesCount)
-
 		tssBlock := tss
 		if i < len(tss) {
 			tssBlock = tss[:i]
@@ -494,31 +480,27 @@ func tryPush(at *auth.Token, wr *prompbmarshal.WriteRequest, forceDropSamplesOnF
 		}
 		sortLabelsIfNeeded(tssBlock)
 		tssBlock = limitSeriesCardinality(tssBlock)
-		if sas.IsEnabled() {
-			matchIdxs := matchIdxsPool.Get()
-			matchIdxs.B = sas.Push(tssBlock, matchIdxs.B)
-			if !*streamAggrGlobalKeepInput {
-				tssBlock = dropAggregatedSeries(tssBlock, matchIdxs.B, *streamAggrGlobalDropInput)
+		if !tryPushBlockToRemoteStorages(rwctxs, tssBlock) {
+			if !*disableOnDiskQueue {
+				logger.Panicf("BUG: tryPushBlockToRemoteStorages must return true if -remoteWrite.disableOnDiskQueue isn't set")
+			}
+			pushFailures.Inc()
+			if dropSamplesOnFailure {
+				samplesDropped.Add(rowsCount)
+				return true
 			}
-			matchIdxsPool.Put(matchIdxs)
-		} else if deduplicatorGlobal != nil {
-			deduplicatorGlobal.Push(tssBlock)
-			tssBlock = tssBlock[:0]
-		}
-		if !tryPushBlockToRemoteStorages(tssBlock, forceDropSamplesOnFailure) {
 			return false
 		}
 	}
 	return true
 }
 
-func pushToRemoteStoragesDropFailed(tss []prompbmarshal.TimeSeries) {
-	if tryPushBlockToRemoteStorages(tss, true) {
-		return
-	}
-}
+var (
+	samplesDropped = metrics.NewCounter(`vmagent_remotewrite_samples_dropped_total`)
+	pushFailures   = metrics.NewCounter(`vmagent_remotewrite_push_failures_total`)
+)
 
-func tryPushBlockToRemoteStorages(tssBlock []prompbmarshal.TimeSeries, forceDropSamplesOnFailure bool) bool {
+func tryPushBlockToRemoteStorages(rwctxs []*remoteWriteCtx, tssBlock []prompbmarshal.TimeSeries) bool {
 	if len(tssBlock) == 0 {
 		// Nothing to push
 		return true
@@ -526,129 +508,70 @@ func tryPushBlockToRemoteStorages(tssBlock []prompbmarshal.TimeSeries, forceDrop
 
 	if len(rwctxs) == 1 {
 		// Fast path - just push data to the configured single remote storage
-		return rwctxs[0].TryPush(tssBlock, forceDropSamplesOnFailure)
+		return rwctxs[0].TryPush(tssBlock)
 	}
 
 	// We need to push tssBlock to multiple remote storages.
 	// This is either sharding or replication depending on -remoteWrite.shardByURL command-line flag value.
-	if *shardByURL && *shardByURLReplicas < len(rwctxs) {
-		// Shard tssBlock samples among rwctxs.
-		replicas := *shardByURLReplicas
-		if replicas <= 0 {
-			replicas = 1
+	if *shardByURL {
+		// Shard the data among rwctxs
+		tssByURL := make([][]prompbmarshal.TimeSeries, len(rwctxs))
+		tmpLabels := promutils.GetLabels()
+		for _, ts := range tssBlock {
+			hashLabels := ts.Labels
+			if len(shardByURLLabelsMap) > 0 {
+				hashLabels = tmpLabels.Labels[:0]
+				for _, label := range ts.Labels {
+					if _, ok := shardByURLLabelsMap[label.Name]; ok {
+						hashLabels = append(hashLabels, label)
+					}
+				}
+			}
+			h := getLabelsHash(hashLabels)
+			idx := h % uint64(len(tssByURL))
+			tssByURL[idx] = append(tssByURL[idx], ts)
 		}
-		return tryShardingBlockAmongRemoteStorages(tssBlock, replicas, forceDropSamplesOnFailure)
+		promutils.PutLabels(tmpLabels)
+
+		// Push sharded data to remote storages in parallel in order to reduce
+		// the time needed for sending the data to multiple remote storage systems.
+		var wg sync.WaitGroup
+		wg.Add(len(rwctxs))
+		var anyPushFailed uint64
+		for i, rwctx := range rwctxs {
+			tssShard := tssByURL[i]
+			if len(tssShard) == 0 {
+				continue
+			}
+			go func(rwctx *remoteWriteCtx, tss []prompbmarshal.TimeSeries) {
+				defer wg.Done()
+				if !rwctx.TryPush(tss) {
+					atomic.StoreUint64(&anyPushFailed, 1)
+				}
+			}(rwctx, tssShard)
+		}
+		wg.Wait()
+		return atomic.LoadUint64(&anyPushFailed) == 0
 	}
 
-	// Replicate tssBlock samples among rwctxs.
-	// Push tssBlock to remote storage systems in parallel in order to reduce
+	// Replicate data among rwctxs.
+	// Push block to remote storages in parallel in order to reduce
 	// the time needed for sending the data to multiple remote storage systems.
 	var wg sync.WaitGroup
 	wg.Add(len(rwctxs))
-	var anyPushFailed atomic.Bool
+	var anyPushFailed uint64
 	for _, rwctx := range rwctxs {
 		go func(rwctx *remoteWriteCtx) {
 			defer wg.Done()
-			if !rwctx.TryPush(tssBlock, forceDropSamplesOnFailure) {
-				anyPushFailed.Store(true)
+			if !rwctx.TryPush(tssBlock) {
+				atomic.StoreUint64(&anyPushFailed, 1)
 			}
 		}(rwctx)
 	}
 	wg.Wait()
-	return !anyPushFailed.Load()
+	return atomic.LoadUint64(&anyPushFailed) == 0
 }
 
-func tryShardingBlockAmongRemoteStorages(tssBlock []prompbmarshal.TimeSeries, replicas int, forceDropSamplesOnFailure bool) bool {
-	x := getTSSShards(len(rwctxs))
-	defer putTSSShards(x)
-
-	shards := x.shards
-	tmpLabels := promutils.GetLabels()
-	for _, ts := range tssBlock {
-		hashLabels := ts.Labels
-		if len(shardByURLLabelsMap) > 0 {
-			hashLabels = tmpLabels.Labels[:0]
-			for _, label := range ts.Labels {
-				if _, ok := shardByURLLabelsMap[label.Name]; ok {
-					hashLabels = append(hashLabels, label)
-				}
-			}
-			tmpLabels.Labels = hashLabels
-		} else if len(shardByURLIgnoreLabelsMap) > 0 {
-			hashLabels = tmpLabels.Labels[:0]
-			for _, label := range ts.Labels {
-				if _, ok := shardByURLIgnoreLabelsMap[label.Name]; !ok {
-					hashLabels = append(hashLabels, label)
-				}
-			}
-			tmpLabels.Labels = hashLabels
-		}
-		h := getLabelsHash(hashLabels)
-		idx := h % uint64(len(shards))
-		i := 0
-		for {
-			shards[idx] = append(shards[idx], ts)
-			i++
-			if i >= replicas {
-				break
-			}
-			idx++
-			if idx >= uint64(len(shards)) {
-				idx = 0
-			}
-		}
-	}
-	promutils.PutLabels(tmpLabels)
-
-	// Push sharded samples to remote storage systems in parallel in order to reduce
-	// the time needed for sending the data to multiple remote storage systems.
-	var wg sync.WaitGroup
-	var anyPushFailed atomic.Bool
-	for i, rwctx := range rwctxs {
-		shard := shards[i]
-		if len(shard) == 0 {
-			continue
-		}
-		wg.Add(1)
-		go func(rwctx *remoteWriteCtx, tss []prompbmarshal.TimeSeries) {
-			defer wg.Done()
-			if !rwctx.TryPush(tss, forceDropSamplesOnFailure) {
-				anyPushFailed.Store(true)
-			}
-		}(rwctx, shard)
-	}
-	wg.Wait()
-	return !anyPushFailed.Load()
-}
-
-type tssShards struct {
-	shards [][]prompbmarshal.TimeSeries
-}
-
-func getTSSShards(n int) *tssShards {
-	v := tssShardsPool.Get()
-	if v == nil {
-		v = &tssShards{}
-	}
-	x := v.(*tssShards)
-	if cap(x.shards) < n {
-		x.shards = make([][]prompbmarshal.TimeSeries, n)
-	}
-	x.shards = x.shards[:n]
-	return x
-}
-
-func putTSSShards(x *tssShards) {
-	shards := x.shards
-	for i := range shards {
-		clear(shards[i])
-		shards[i] = shards[i][:0]
-	}
-	tssShardsPool.Put(x)
-}
-
-var tssShardsPool sync.Pool
-
 // sortLabelsIfNeeded sorts labels if -sortLabels command-line flag is set.
 func sortLabelsIfNeeded(tss []prompbmarshal.TimeSeries) {
 	if !*sortLabels {
@@ -742,22 +665,15 @@ type remoteWriteCtx struct {
 	fq  *persistentqueue.FastQueue
 	c   *client
 
-	sas          atomic.Pointer[streamaggr.Aggregators]
-	deduplicator *streamaggr.Deduplicator
-
-	streamAggrKeepInput   bool
-	streamAggrDropInput   bool
-	disableOnDiskQueue    bool
-	dropSamplesOnOverload bool
+	sas                 atomic.Pointer[streamaggr.Aggregators]
+	streamAggrKeepInput bool
+	streamAggrDropInput bool
 
 	pss        []*pendingSeries
-	pssNextIdx atomic.Uint64
+	pssNextIdx uint64
 
 	rowsPushedAfterRelabel *metrics.Counter
 	rowsDroppedByRelabel   *metrics.Counter
-
-	pushFailures             *metrics.Counter
-	rowsDroppedOnPushFailure *metrics.Counter
 }
 
 func newRemoteWriteCtx(argIdx int, remoteWriteURL *url.URL, maxInmemoryBlocks int, sanitizedURL string) *remoteWriteCtx {
@@ -773,8 +689,7 @@ func newRemoteWriteCtx(argIdx int, remoteWriteURL *url.URL, maxInmemoryBlocks in
 		logger.Warnf("rounding the -remoteWrite.maxDiskUsagePerURL=%d to the minimum supported value: %d", maxPendingBytes, persistentqueue.DefaultChunkFileSize)
 		maxPendingBytes = persistentqueue.DefaultChunkFileSize
 	}
-	isPQDisabled := disableOnDiskQueue.GetOptionalArg(argIdx)
-	fq := persistentqueue.MustOpenFastQueue(queuePath, sanitizedURL, maxInmemoryBlocks, maxPendingBytes, isPQDisabled)
+	fq := persistentqueue.MustOpenFastQueue(queuePath, sanitizedURL, maxInmemoryBlocks, maxPendingBytes, *disableOnDiskQueue)
 	_ = metrics.GetOrCreateGauge(fmt.Sprintf(`vmagent_remotewrite_pending_data_bytes{path=%q, url=%q}`, queuePath, sanitizedURL), func() float64 {
 		return float64(fq.GetPendingBytes())
 	})
@@ -817,20 +732,15 @@ func newRemoteWriteCtx(argIdx int, remoteWriteURL *url.URL, maxInmemoryBlocks in
 		c:   c,
 		pss: pss,
 
-		dropSamplesOnOverload: dropSamplesOnOverload.GetOptionalArg(argIdx),
-		disableOnDiskQueue:    isPQDisabled,
-
 		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)),
-
-		pushFailures:             metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_push_failures_total{path=%q, url=%q}`, queuePath, sanitizedURL)),
-		rowsDroppedOnPushFailure: metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_samples_dropped_total{path=%q, url=%q}`, queuePath, sanitizedURL)),
 	}
 
 	// Initialize sas
-	sasFile, sasOpts := getStreamAggrOpts(argIdx)
+	sasFile := streamAggrConfig.GetOptionalArg(argIdx)
 	if sasFile != "" {
-		sas, err := newStreamAggrConfig(argIdx, rwctx.pushInternalTrackDropped)
+		dedupInterval := streamAggrDedupInterval.GetOptionalArg(argIdx)
+		sas, err := streamaggr.LoadFromFile(sasFile, rwctx.pushInternalTrackDropped, dedupInterval)
 		if err != nil {
 			logger.Fatalf("cannot initialize stream aggregators from -remoteWrite.streamAggr.config=%q: %s", sasFile, err)
 		}
@@ -839,24 +749,17 @@ func newRemoteWriteCtx(argIdx int, remoteWriteURL *url.URL, maxInmemoryBlocks in
 		rwctx.streamAggrDropInput = streamAggrDropInput.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())
-	} else if sasOpts.DedupInterval > 0 {
-		rwctx.deduplicator = streamaggr.NewDeduplicator(rwctx.pushInternalTrackDropped, sasOpts.DedupInterval, sasOpts.DropInputLabels, sasOpts.Alias)
 	}
 
 	return rwctx
 }
 
 func (rwctx *remoteWriteCtx) MustStop() {
-	// sas and deduplicator must be stopped before rwctx is closed
-	// because they can write pending series to rwctx.pss if there are any
+	// sas must be stopped before rwctx is closed
+	// because sas can write pending series to rwctx.pss if there are any
 	sas := rwctx.sas.Swap(nil)
 	sas.MustStop()
 
-	if rwctx.deduplicator != nil {
-		rwctx.deduplicator.MustStop()
-		rwctx.deduplicator = nil
-	}
-
 	for _, ps := range rwctx.pss {
 		ps.MustStop()
 	}
@@ -873,22 +776,10 @@ func (rwctx *remoteWriteCtx) MustStop() {
 	rwctx.rowsDroppedByRelabel = nil
 }
 
-// TryPush sends tss series to the configured remote write endpoint
-//
-// TryPush doesn't modify tss, so tss can be passed concurrently to TryPush across distinct rwctx instances.
-func (rwctx *remoteWriteCtx) TryPush(tss []prompbmarshal.TimeSeries, forceDropSamplesOnFailure bool) bool {
+func (rwctx *remoteWriteCtx) TryPush(tss []prompbmarshal.TimeSeries) bool {
+	// Apply relabeling
 	var rctx *relabelCtx
 	var v *[]prompbmarshal.TimeSeries
-	defer func() {
-		if rctx == nil {
-			return
-		}
-		*v = prompbmarshal.ResetTimeSeries(tss)
-		tssPool.Put(v)
-		putRelabelCtx(rctx)
-	}()
-
-	// Apply relabeling
 	rcs := allRelabelConfigs.Load()
 	pcs := rcs.perURL[rwctx.idx]
 	if pcs.Len() > 0 {
@@ -907,9 +798,9 @@ func (rwctx *remoteWriteCtx) TryPush(tss []prompbmarshal.TimeSeries, forceDropSa
 	rowsCount := getRowsCount(tss)
 	rwctx.rowsPushedAfterRelabel.Add(rowsCount)
 
-	// Apply stream aggregation or deduplication if they are configured
+	// Apply stream aggregation if any
 	sas := rwctx.sas.Load()
-	if sas.IsEnabled() {
+	if sas != nil {
 		matchIdxs := matchIdxsPool.Get()
 		matchIdxs.B = sas.Push(tss, matchIdxs.B)
 		if !rwctx.streamAggrKeepInput {
@@ -922,23 +813,19 @@ func (rwctx *remoteWriteCtx) TryPush(tss []prompbmarshal.TimeSeries, forceDropSa
 			tss = dropAggregatedSeries(tss, matchIdxs.B, rwctx.streamAggrDropInput)
 		}
 		matchIdxsPool.Put(matchIdxs)
-	} else if rwctx.deduplicator != nil {
-		rwctx.deduplicator.Push(tss)
-		return true
 	}
 
-	// Try pushing tss to remote storage
-	if rwctx.tryPushInternal(tss) {
-		return true
+	// Try pushing the data to remote storage
+	ok := rwctx.tryPushInternal(tss)
+
+	// Return back relabeling contexts to the pool
+	if rctx != nil {
+		*v = prompbmarshal.ResetTimeSeries(tss)
+		tssPool.Put(v)
+		putRelabelCtx(rctx)
 	}
 
-	// Couldn't push tss to remote storage
-	rwctx.pushFailures.Inc()
-	if forceDropSamplesOnFailure || rwctx.dropSamplesOnOverload {
-		rwctx.rowsDroppedOnPushFailure.Add(len(tss))
-		return true
-	}
-	return false
+	return ok
 }
 
 var matchIdxsPool bytesutil.ByteBufferPool
@@ -954,7 +841,7 @@ func dropAggregatedSeries(src []prompbmarshal.TimeSeries, matchIdxs []byte, drop
 		}
 	}
 	tail := src[len(dst):]
-	clear(tail)
+	_ = prompbmarshal.ResetTimeSeries(tail)
 	return dst
 }
 
@@ -962,28 +849,19 @@ func (rwctx *remoteWriteCtx) pushInternalTrackDropped(tss []prompbmarshal.TimeSe
 	if rwctx.tryPushInternal(tss) {
 		return
 	}
-	if !rwctx.disableOnDiskQueue {
+	if !*disableOnDiskQueue {
 		logger.Panicf("BUG: tryPushInternal must return true if -remoteWrite.disableOnDiskQueue isn't set")
 	}
-	rwctx.pushFailures.Inc()
-	if dropSamplesOnOverload.GetOptionalArg(rwctx.idx) {
+	pushFailures.Inc()
+	if *dropSamplesOnOverload {
 		rowsCount := getRowsCount(tss)
-		rwctx.rowsDroppedOnPushFailure.Add(rowsCount)
+		samplesDropped.Add(rowsCount)
 	}
 }
 
 func (rwctx *remoteWriteCtx) tryPushInternal(tss []prompbmarshal.TimeSeries) bool {
 	var rctx *relabelCtx
 	var v *[]prompbmarshal.TimeSeries
-	defer func() {
-		if rctx == nil {
-			return
-		}
-		*v = prompbmarshal.ResetTimeSeries(tss)
-		tssPool.Put(v)
-		putRelabelCtx(rctx)
-	}()
-
 	if len(labelsGlobal) > 0 {
 		// Make a copy of tss before adding extra labels in order to prevent
 		// from affecting time series for other remoteWrite.url configs.
@@ -994,9 +872,47 @@ func (rwctx *remoteWriteCtx) tryPushInternal(tss []prompbmarshal.TimeSeries) boo
 	}
 
 	pss := rwctx.pss
-	idx := rwctx.pssNextIdx.Add(1) % uint64(len(pss))
+	idx := atomic.AddUint64(&rwctx.pssNextIdx, 1) % uint64(len(pss))
 
-	return pss[idx].TryPush(tss)
+	ok := pss[idx].TryPush(tss)
+
+	if rctx != nil {
+		*v = prompbmarshal.ResetTimeSeries(tss)
+		tssPool.Put(v)
+		putRelabelCtx(rctx)
+	}
+
+	return ok
+}
+
+func (rwctx *remoteWriteCtx) reinitStreamAggr() {
+	sasFile := streamAggrConfig.GetOptionalArg(rwctx.idx)
+	if sasFile == "" {
+		// There is no stream aggregation for rwctx
+		return
+	}
+
+	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.GetOptionalArg(rwctx.idx)
+	sasNew, err := streamaggr.LoadFromFile(sasFile, rwctx.pushInternalTrackDropped, 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
+	}
+	sas := rwctx.sas.Load()
+	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 tssPool = &sync.Pool{
@@ -1014,10 +930,19 @@ func getRowsCount(tss []prompbmarshal.TimeSeries) int {
 	return rowsCount
 }
 
-func newMapFromStrings(a []string) map[string]struct{} {
-	m := make(map[string]struct{}, len(a))
-	for _, s := range a {
-		m[s] = struct{}{}
+// 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.GetOptionalArg(idx)
+		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 m
+	return nil
 }

app/vmagent/remotewrite/remotewrite_test.go

@@ -1,165 +0,0 @@
-package remotewrite
-
-import (
-	"fmt"
-	"math"
-	"reflect"
-	"testing"
-	"time"
-
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/streamaggr"
-	"github.com/VictoriaMetrics/metrics"
-)
-
-func TestGetLabelsHash_Distribution(t *testing.T) {
-	f := func(bucketsCount int) {
-		t.Helper()
-
-		// Distribute itemsCount hashes returned by getLabelsHash() across bucketsCount buckets.
-		itemsCount := 1_000 * bucketsCount
-		m := make([]int, bucketsCount)
-		var labels []prompbmarshal.Label
-		for i := 0; i < itemsCount; i++ {
-			labels = append(labels[:0], prompbmarshal.Label{
-				Name:  "__name__",
-				Value: fmt.Sprintf("some_name_%d", i),
-			})
-			for j := 0; j < 10; j++ {
-				labels = append(labels, prompbmarshal.Label{
-					Name:  fmt.Sprintf("label_%d", j),
-					Value: fmt.Sprintf("value_%d_%d", i, j),
-				})
-			}
-			h := getLabelsHash(labels)
-			m[h%uint64(bucketsCount)]++
-		}
-
-		// Verify that the distribution is even
-		expectedItemsPerBucket := itemsCount / bucketsCount
-		for _, n := range m {
-			if math.Abs(1-float64(n)/float64(expectedItemsPerBucket)) > 0.04 {
-				t.Fatalf("unexpected items in the bucket for %d buckets; got %d; want around %d", bucketsCount, n, expectedItemsPerBucket)
-			}
-		}
-	}
-
-	f(2)
-	f(3)
-	f(4)
-	f(5)
-	f(10)
-}
-
-func TestRemoteWriteContext_TryPush_ImmutableTimeseries(t *testing.T) {
-	f := func(streamAggrConfig, relabelConfig string, dedupInterval time.Duration, keepInput, dropInput bool, input string) {
-		t.Helper()
-		perURLRelabel, err := promrelabel.ParseRelabelConfigsData([]byte(relabelConfig))
-		if err != nil {
-			t.Fatalf("cannot load relabel configs: %s", err)
-		}
-		rcs := &relabelConfigs{
-			perURL: []*promrelabel.ParsedConfigs{
-				perURLRelabel,
-			},
-		}
-		allRelabelConfigs.Store(rcs)
-
-		pss := make([]*pendingSeries, 1)
-		pss[0] = newPendingSeries(nil, true, 0, 100)
-		rwctx := &remoteWriteCtx{
-			idx:                    0,
-			streamAggrKeepInput:    keepInput,
-			streamAggrDropInput:    dropInput,
-			pss:                    pss,
-			rowsPushedAfterRelabel: metrics.GetOrCreateCounter(`foo`),
-			rowsDroppedByRelabel:   metrics.GetOrCreateCounter(`bar`),
-		}
-		if dedupInterval > 0 {
-			rwctx.deduplicator = streamaggr.NewDeduplicator(nil, dedupInterval, nil, "global")
-		}
-
-		if len(streamAggrConfig) > 0 {
-			sas, err := streamaggr.LoadFromData([]byte(streamAggrConfig), nil, streamaggr.Options{})
-			if err != nil {
-				t.Fatalf("cannot load streamaggr configs: %s", err)
-			}
-			rwctx.sas.Store(sas)
-		}
-
-		offsetMsecs := time.Now().UnixMilli()
-		inputTss := prompbmarshal.MustParsePromMetrics(input, offsetMsecs)
-		expectedTss := make([]prompbmarshal.TimeSeries, len(inputTss))
-
-		// copy inputTss to make sure it is not mutated during TryPush call
-		copy(expectedTss, inputTss)
-		rwctx.TryPush(inputTss, false)
-
-		if !reflect.DeepEqual(expectedTss, inputTss) {
-			t.Fatalf("unexpected samples;\ngot\n%v\nwant\n%v", inputTss, expectedTss)
-		}
-	}
-
-	f(`
-- interval: 1m
-  outputs: [sum_samples]
-- interval: 2m
-  outputs: [count_series]
-`, `
-- action: keep
-  source_labels: [env]
-  regex: "dev"
-`, 0, false, false, `
-metric{env="dev"} 10
-metric{env="bar"} 20
-metric{env="dev"} 15
-metric{env="bar"} 25
-`)
-	f(``, ``, time.Hour, false, false, `
-metric{env="dev"} 10
-metric{env="foo"} 20
-metric{env="dev"} 15
-metric{env="foo"} 25
-`)
-	f(``, `
-- action: keep
-  source_labels: [env]
-  regex: "dev"
-`, time.Hour, false, false, `
-metric{env="dev"} 10
-metric{env="bar"} 20
-metric{env="dev"} 15
-metric{env="bar"} 25
-`)
-	f(``, `
-- action: keep
-  source_labels: [env]
-  regex: "dev"
-`, time.Hour, true, false, `
-metric{env="test"} 10
-metric{env="dev"} 20
-metric{env="foo"} 15
-metric{env="dev"} 25
-`)
-	f(``, `
-- action: keep
-  source_labels: [env]
-  regex: "dev"
-`, time.Hour, false, true, `
-metric{env="foo"} 10
-metric{env="dev"} 20
-metric{env="foo"} 15
-metric{env="dev"} 25
-`)
-	f(``, `
-- action: keep
-  source_labels: [env]
-  regex: "dev"
-`, time.Hour, true, true, `
-metric{env="dev"} 10
-metric{env="test"} 20
-metric{env="dev"} 15
-metric{env="bar"} 25
-`)
-}

app/vmagent/remotewrite/statconn.go

@@ -0,0 +1,92 @@
+package remotewrite
+
+import (
+	"context"
+	"net"
+	"sync"
+	"sync/atomic"
+	"time"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/netutil"
+	"github.com/VictoriaMetrics/metrics"
+)
+
+func getStdDialer() *net.Dialer {
+	stdDialerOnce.Do(func() {
+		stdDialer = &net.Dialer{
+			Timeout:   30 * time.Second,
+			KeepAlive: 30 * time.Second,
+			DualStack: netutil.TCP6Enabled(),
+		}
+	})
+	return stdDialer
+}
+
+var (
+	stdDialer     *net.Dialer
+	stdDialerOnce sync.Once
+)
+
+func statDial(ctx context.Context, _, addr string) (conn net.Conn, err error) {
+	network := netutil.GetTCPNetwork()
+	d := getStdDialer()
+	conn, err = d.DialContext(ctx, network, addr)
+	dialsTotal.Inc()
+	if err != nil {
+		dialErrors.Inc()
+		return nil, err
+	}
+	conns.Inc()
+	sc := &statConn{
+		Conn: conn,
+	}
+	return sc, nil
+}
+
+var (
+	dialsTotal = metrics.NewCounter(`vmagent_remotewrite_dials_total`)
+	dialErrors = metrics.NewCounter(`vmagent_remotewrite_dial_errors_total`)
+	conns      = metrics.NewCounter(`vmagent_remotewrite_conns`)
+)
+
+type statConn struct {
+	closed uint64
+	net.Conn
+}
+
+func (sc *statConn) Read(p []byte) (int, error) {
+	n, err := sc.Conn.Read(p)
+	connReadsTotal.Inc()
+	if err != nil {
+		connReadErrors.Inc()
+	}
+	connBytesRead.Add(n)
+	return n, err
+}
+
+func (sc *statConn) Write(p []byte) (int, error) {
+	n, err := sc.Conn.Write(p)
+	connWritesTotal.Inc()
+	if err != nil {
+		connWriteErrors.Inc()
+	}
+	connBytesWritten.Add(n)
+	return n, err
+}
+
+func (sc *statConn) Close() error {
+	err := sc.Conn.Close()
+	if atomic.AddUint64(&sc.closed, 1) == 1 {
+		conns.Dec()
+	}
+	return err
+}
+
+var (
+	connReadsTotal   = metrics.NewCounter(`vmagent_remotewrite_conn_reads_total`)
+	connWritesTotal  = metrics.NewCounter(`vmagent_remotewrite_conn_writes_total`)
+	connReadErrors   = metrics.NewCounter(`vmagent_remotewrite_conn_read_errors_total`)
+	connWriteErrors  = metrics.NewCounter(`vmagent_remotewrite_conn_write_errors_total`)
+	connBytesRead    = metrics.NewCounter(`vmagent_remotewrite_conn_bytes_read_total`)
+	connBytesWritten = metrics.NewCounter(`vmagent_remotewrite_conn_bytes_written_total`)
+)

app/vmagent/remotewrite/streamaggr.go

@@ -1,164 +0,0 @@
-package remotewrite
-
-import (
-	"flag"
-	"fmt"
-
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/fasttime"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/streamaggr"
-	"github.com/VictoriaMetrics/metrics"
-)
-
-var (
-	// Global config
-	streamAggrGlobalConfig = flag.String("streamAggr.config", "", "Optional path to file with stream aggregation config. "+
-		"See https://docs.victoriametrics.com/stream-aggregation/ . "+
-		"See also -streamAggr.keepInput, -streamAggr.dropInput and -streamAggr.dedupInterval")
-	streamAggrGlobalKeepInput = flag.Bool("streamAggr.keepInput", false, "Whether to keep all the input samples after the aggregation "+
-		"with -streamAggr.config. By default, only aggregates samples are dropped, while the remaining samples "+
-		"are written to remote storages write. See also -streamAggr.dropInput and https://docs.victoriametrics.com/stream-aggregation/")
-	streamAggrGlobalDropInput = flag.Bool("streamAggr.dropInput", false, "Whether to drop all the input samples after the aggregation "+
-		"with -remoteWrite.streamAggr.config. By default, only aggregates samples are dropped, while the remaining samples "+
-		"are written to remote storages write. See also -streamAggr.keepInput and https://docs.victoriametrics.com/stream-aggregation/")
-	streamAggrGlobalDedupInterval = flagutil.NewDuration("streamAggr.dedupInterval", "0s", "Input samples are de-duplicated with this interval on "+
-		"aggregator before optional aggregation with -streamAggr.config . "+
-		"See also -dedup.minScrapeInterval and https://docs.victoriametrics.com/stream-aggregation/#deduplication")
-	streamAggrGlobalIgnoreOldSamples = flag.Bool("streamAggr.ignoreOldSamples", false, "Whether to ignore input samples with old timestamps outside the "+
-		"current aggregation interval for aggregator. "+
-		"See https://docs.victoriametrics.com/stream-aggregation/#ignoring-old-samples")
-	streamAggrGlobalIgnoreFirstIntervals = flag.Int("streamAggr.ignoreFirstIntervals", 0, "Number of aggregation intervals to skip after the start for "+
-		"aggregator. Increase this value if you observe incorrect aggregation results after vmagent restarts. It could be caused by receiving unordered delayed data from "+
-		"clients pushing data into the vmagent. See https://docs.victoriametrics.com/stream-aggregation/#ignore-aggregation-intervals-on-start")
-	streamAggrGlobalDropInputLabels = flagutil.NewArrayString("streamAggr.dropInputLabels", "An optional list of labels to drop from samples for aggregator "+
-		"before stream de-duplication and aggregation . See https://docs.victoriametrics.com/stream-aggregation/#dropping-unneeded-labels")
-
-	// Per URL config
-	streamAggrConfig = flagutil.NewArrayString("remoteWrite.streamAggr.config", "Optional path to file with stream aggregation config for the corresponding -remoteWrite.url. "+
-		"See https://docs.victoriametrics.com/stream-aggregation/ . "+
-		"See also -remoteWrite.streamAggr.keepInput, -remoteWrite.streamAggr.dropInput and -remoteWrite.streamAggr.dedupInterval")
-	streamAggrDropInput = flagutil.NewArrayBool("remoteWrite.streamAggr.dropInput", "Whether to drop all the input samples after the aggregation "+
-		"with -remoteWrite.streamAggr.config at the corresponding -remoteWrite.url. By default, only aggregates samples are dropped, while the remaining samples "+
-		"are written to the corresponding -remoteWrite.url . See also -remoteWrite.streamAggr.keepInput and https://docs.victoriametrics.com/stream-aggregation/")
-	streamAggrKeepInput = flagutil.NewArrayBool("remoteWrite.streamAggr.keepInput", "Whether to keep all the input samples after the aggregation "+
-		"with -remoteWrite.streamAggr.config at the corresponding -remoteWrite.url. By default, only aggregates samples are dropped, while the remaining samples "+
-		"are written to the corresponding -remoteWrite.url . See also -remoteWrite.streamAggr.dropInput and https://docs.victoriametrics.com/stream-aggregation/")
-	streamAggrDedupInterval = flagutil.NewArrayDuration("remoteWrite.streamAggr.dedupInterval", 0, "Input samples are de-duplicated with this interval before optional aggregation "+
-		"with -remoteWrite.streamAggr.config at the corresponding -remoteWrite.url. See also -dedup.minScrapeInterval and https://docs.victoriametrics.com/stream-aggregation/#deduplication")
-	streamAggrIgnoreOldSamples = flagutil.NewArrayBool("remoteWrite.streamAggr.ignoreOldSamples", "Whether to ignore input samples with old timestamps outside the current "+
-		"aggregation interval for the corresponding -remoteWrite.streamAggr.config at the corresponding -remoteWrite.url. "+
-		"See https://docs.victoriametrics.com/stream-aggregation/#ignoring-old-samples")
-	streamAggrIgnoreFirstIntervals = flag.Int("remoteWrite.streamAggr.ignoreFirstIntervals", 0, "Number of aggregation intervals to skip after the start "+
-		"for the corresponding -remoteWrite.streamAggr.config at the corresponding -remoteWrite.url. Increase this value if "+
-		"you observe incorrect aggregation results after vmagent restarts. It could be caused by receiving bufferred delayed data from clients pushing data into the vmagent. "+
-		"See https://docs.victoriametrics.com/stream-aggregation/#ignore-aggregation-intervals-on-start")
-	streamAggrDropInputLabels = flagutil.NewArrayString("remoteWrite.streamAggr.dropInputLabels", "An optional list of labels to drop from samples "+
-		"before stream de-duplication and aggregation with -remoteWrite.streamAggr.config and -remoteWrite.streamAggr.dedupInterval at the corresponding -remoteWrite.url. "+
-		"See https://docs.victoriametrics.com/stream-aggregation/#dropping-unneeded-labels")
-)
-
-// CheckStreamAggrConfigs checks -remoteWrite.streamAggr.config and -streamAggr.config.
-func CheckStreamAggrConfigs() error {
-	pushNoop := func(_ []prompbmarshal.TimeSeries) {}
-
-	if _, err := newStreamAggrConfig(-1, pushNoop); err != nil {
-		return fmt.Errorf("could not load -streamAggr.config stream aggregation config: %w", err)
-	}
-	if len(*streamAggrConfig) > len(*remoteWriteURLs) {
-		return fmt.Errorf("too many -remoteWrite.streamAggr.config args: %d; it mustn't exceed the number of -remoteWrite.url args: %d",
-			len(*streamAggrConfig), len(*remoteWriteURLs))
-	}
-	for idx := range *streamAggrConfig {
-		if _, err := newStreamAggrConfig(idx, pushNoop); err != nil {
-			return err
-		}
-	}
-	return nil
-}
-
-func reloadStreamAggrConfigs() {
-	reloadStreamAggrConfig(-1, pushToRemoteStoragesDropFailed)
-	for idx, rwctx := range rwctxs {
-		reloadStreamAggrConfig(idx, rwctx.pushInternalTrackDropped)
-	}
-}
-
-func reloadStreamAggrConfig(idx int, pushFunc streamaggr.PushFunc) {
-	path, opts := getStreamAggrOpts(idx)
-	logger.Infof("reloading stream aggregation configs pointed by -remoteWrite.streamAggr.config=%q", path)
-	metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reloads_total{path=%q}`, path)).Inc()
-
-	sasNew, err := newStreamAggrConfigWithOpts(pushFunc, path, opts)
-	if err != nil {
-		metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reloads_errors_total{path=%q}`, path)).Inc()
-		metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reload_successful{path=%q}`, path)).Set(0)
-		logger.Errorf("cannot reload stream aggregation config at %q; continue using the previously loaded config; error: %s", path, err)
-		return
-	}
-
-	var sas *streamaggr.Aggregators
-	if idx < 0 {
-		sas = sasGlobal.Load()
-	} else {
-		sas = rwctxs[idx].sas.Load()
-	}
-
-	if !sasNew.Equal(sas) {
-		var sasOld *streamaggr.Aggregators
-		if idx < 0 {
-			sasOld = sasGlobal.Swap(sasNew)
-		} else {
-			sasOld = rwctxs[idx].sas.Swap(sasNew)
-		}
-		sasOld.MustStop()
-		logger.Infof("successfully reloaded stream aggregation configs at %q", path)
-	} else {
-		sasNew.MustStop()
-		logger.Infof("successfully reloaded stream aggregation configs at %q", path)
-	}
-	metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reload_successful{path=%q}`, path)).Set(1)
-	metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reload_success_timestamp_seconds{path=%q}`, path)).Set(fasttime.UnixTimestamp())
-}
-
-func getStreamAggrOpts(idx int) (string, streamaggr.Options) {
-	if idx < 0 {
-		return *streamAggrGlobalConfig, streamaggr.Options{
-			DedupInterval:        streamAggrGlobalDedupInterval.Duration(),
-			DropInputLabels:      *streamAggrGlobalDropInputLabels,
-			IgnoreOldSamples:     *streamAggrGlobalIgnoreOldSamples,
-			IgnoreFirstIntervals: *streamAggrGlobalIgnoreFirstIntervals,
-			Alias:                "global",
-		}
-	}
-	url := fmt.Sprintf("%d:secret-url", idx+1)
-	if *showRemoteWriteURL {
-		url = fmt.Sprintf("%d:%s", idx+1, remoteWriteURLs.GetOptionalArg(idx))
-	}
-	opts := streamaggr.Options{
-		DedupInterval:        streamAggrDedupInterval.GetOptionalArg(idx),
-		DropInputLabels:      *streamAggrDropInputLabels,
-		IgnoreOldSamples:     streamAggrIgnoreOldSamples.GetOptionalArg(idx),
-		IgnoreFirstIntervals: *streamAggrIgnoreFirstIntervals,
-		Alias:                url,
-	}
-
-	if len(*streamAggrConfig) == 0 {
-		return "", opts
-	}
-	return streamAggrConfig.GetOptionalArg(idx), opts
-}
-
-func newStreamAggrConfigWithOpts(pushFunc streamaggr.PushFunc, path string, opts streamaggr.Options) (*streamaggr.Aggregators, error) {
-	if len(path) == 0 {
-		// Skip empty stream aggregation config.
-		return nil, nil
-	}
-	return streamaggr.LoadFromFile(path, pushFunc, opts)
-}
-
-func newStreamAggrConfig(idx int, pushFunc streamaggr.PushFunc) (*streamaggr.Aggregators, error) {
-	path, opts := getStreamAggrOpts(idx)
-	return newStreamAggrConfigWithOpts(pushFunc, path, opts)
-}

app/vmalert-tool/main.go

@@ -26,14 +26,8 @@ func main() {
 				UsageText: "More info in https://docs.victoriametrics.com/vmalert-tool.html#Unit-testing-for-rules",
 				Flags: []cli.Flag{
 					&cli.StringSliceFlag{
-						Name: "files",
-						Usage: `File path or http url with test files. Supports an array of values separated by comma or specified via multiple flags.
-						Supports hierarchical patterns and regexpes.
-Examples:
- -files="/path/to/file". Path to a single test file.
- -files="http://<some-server-addr>/path/to/test.yaml". HTTP URL to a test file.
- -files="dir/**/*.yaml". Includes all the .yaml files in "dir" subfolders recursively.
- `,
+						Name:     "files",
+						Usage:    "files to run unittest with. Supports an array of values separated by comma or specified via multiple flags.",
 						Required: true,
 					},
 					&cli.BoolFlag{

app/vmalert-tool/multiarch/Dockerfile

@@ -1,7 +1,7 @@
 # See https://medium.com/on-docker/use-multi-stage-builds-to-inject-ca-certs-ad1e8f01de1b
 ARG certs_image
 ARG root_image
-FROM $certs_image AS certs
+FROM $certs_image as certs
 RUN apk update && apk upgrade && apk --update --no-cache add ca-certificates
 
 FROM $root_image

app/vmalert-tool/unittest/input.go

@@ -18,8 +18,6 @@ import (
 	"github.com/VictoriaMetrics/metricsql"
 )
 
-var numReg = regexp.MustCompile(`\D?\d*\.?\d*\D?`)
-
 // series holds input_series defined in the test file
 type series struct {
 	Series string `yaml:"series"`
@@ -88,12 +86,13 @@ func writeInputSeries(input []series, interval *promutils.Duration, startStamp t
 func parseInputValue(input string, origin bool) ([]sequenceValue, error) {
 	var res []sequenceValue
 	items := strings.Split(input, " ")
+	reg := regexp.MustCompile(`\D?\d*\D?`)
 	for _, item := range items {
 		if item == "stale" {
 			res = append(res, sequenceValue{Value: decimal.StaleNaN})
 			continue
 		}
-		vals := numReg.FindAllString(item, -1)
+		vals := reg.FindAllString(item, -1)
 		switch len(vals) {
 		case 1:
 			if vals[0] == "_" {

app/vmalert-tool/unittest/input_test.go

@@ -54,8 +54,8 @@ func TestParseInputValue(t *testing.T) {
 			false,
 		},
 		{
-			"1+1x2 0.1 0.1+0.3x2 3.14",
-			[]sequenceValue{{Value: 1}, {Value: 2}, {Value: 3}, {Value: 0.1}, {Value: 0.1}, {Value: 0.4}, {Value: 0.7}, {Value: 3.14}},
+			"1+1x4",
+			[]sequenceValue{{Value: 1}, {Value: 2}, {Value: 3}, {Value: 4}, {Value: 5}},
 			false,
 		},
 		{

app/vmalert-tool/unittest/testdata/rules.yaml

@@ -37,6 +37,3 @@ groups:
     rules:
       - record: t3
         expr: t1
-
-  - name: emptyGroup
-    rules: []

app/vmalert-tool/unittest/unittest.go

@@ -9,12 +9,10 @@ import (
 	"path/filepath"
 	"reflect"
 	"sort"
-	"strings"
 	"time"
 
 	"gopkg.in/yaml.v2"
 
-	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/config"
 	vmalertconfig "github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/config"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
@@ -68,38 +66,36 @@ func UnitTest(files []string, disableGroupLabel bool) bool {
 	defer vminsert.Stop()
 	defer vmselect.Stop()
 	disableAlertgroupLabel = disableGroupLabel
+	return rulesUnitTest(files)
+}
 
-	testfiles, err := config.ReadFromFS(files)
-	if err != nil {
-		fmt.Println("  FAILED")
-		fmt.Printf("\nfailed to read test files: \n%v", err)
-	}
+func rulesUnitTest(files []string) bool {
 	var failed bool
-	for fileName, file := range testfiles {
-		if err := ruleUnitTest(fileName, file); err != nil {
+	for _, f := range files {
+		if err := ruleUnitTest(f); err != nil {
 			fmt.Println("  FAILED")
-			fmt.Printf("\nfailed to run unit test for file %q: \n%v", file, err)
+			fmt.Printf("\nfailed to run unit test for file %q: \n%v", f, err)
 			failed = true
 		} else {
 			fmt.Println("  SUCCESS")
 		}
 	}
-
 	return failed
 }
 
-func ruleUnitTest(filename string, content []byte) []error {
+func ruleUnitTest(filename string) []error {
 	fmt.Println("\nUnit Testing: ", filename)
-	var unitTestInp unitTestFile
-	if err := yaml.UnmarshalStrict(content, &unitTestInp); err != nil {
-		return []error{fmt.Errorf("failed to unmarshal file: %w", err)}
+	b, err := os.ReadFile(filename)
+	if err != nil {
+		return []error{fmt.Errorf("failed to read file: %w", err)}
 	}
 
-	// add file directory for rule files if needed
-	for i, rf := range unitTestInp.RuleFiles {
-		if rf != "" && !filepath.IsAbs(rf) && !strings.HasPrefix(rf, "http") {
-			unitTestInp.RuleFiles[i] = filepath.Join(filepath.Dir(filename), rf)
-		}
+	var unitTestInp unitTestFile
+	if err := yaml.UnmarshalStrict(b, &unitTestInp); err != nil {
+		return []error{fmt.Errorf("failed to unmarshal file: %w", err)}
+	}
+	if err := resolveAndGlobFilepaths(filepath.Dir(filename), &unitTestInp); err != nil {
+		return []error{fmt.Errorf("failed to resolve path for `rule_files`: %w", err)}
 	}
 
 	if unitTestInp.EvaluationInterval.Duration() == 0 {
@@ -143,24 +139,24 @@ func verifyTestGroup(group testGroup) error {
 	}
 	for _, at := range group.AlertRuleTests {
 		if at.Alertname == "" {
-			return fmt.Errorf("\n%s    missing required field \"alertname\"", testGroupName)
+			return fmt.Errorf("\n%s    missing required filed \"alertname\"", testGroupName)
 		}
 		if !disableAlertgroupLabel && at.GroupName == "" {
-			return fmt.Errorf("\n%s    missing required field \"groupname\" when flag \"disableAlertgroupLabel\" is false", testGroupName)
+			return fmt.Errorf("\n%s    missing required filed \"groupname\" when flag \"disableAlertGroupLabel\" is false", testGroupName)
 		}
 		if disableAlertgroupLabel && at.GroupName != "" {
-			return fmt.Errorf("\n%s    shouldn't set field \"groupname\" when flag \"disableAlertgroupLabel\" is true", testGroupName)
+			return fmt.Errorf("\n%s    shouldn't set filed \"groupname\" when flag \"disableAlertGroupLabel\" is true", testGroupName)
 		}
 		if at.EvalTime == nil {
-			return fmt.Errorf("\n%s    missing required field \"eval_time\"", testGroupName)
+			return fmt.Errorf("\n%s    missing required filed \"eval_time\"", testGroupName)
 		}
 	}
 	for _, et := range group.MetricsqlExprTests {
 		if et.Expr == "" {
-			return fmt.Errorf("\n%s    missing required field \"expr\"", testGroupName)
+			return fmt.Errorf("\n%s    missing required filed \"expr\"", testGroupName)
 		}
 		if et.EvalTime == nil {
-			return fmt.Errorf("\n%s    missing required field \"eval_time\"", testGroupName)
+			return fmt.Errorf("\n%s    missing required filed \"eval_time\"", testGroupName)
 		}
 	}
 	return nil
@@ -239,6 +235,30 @@ func tearDown() {
 	fs.MustRemoveAll(storagePath)
 }
 
+// resolveAndGlobFilepaths joins all relative paths in a configuration
+// with a given base directory and replaces all globs with matching files.
+func resolveAndGlobFilepaths(baseDir string, utf *unitTestFile) error {
+	for i, rf := range utf.RuleFiles {
+		if rf != "" && !filepath.IsAbs(rf) {
+			utf.RuleFiles[i] = filepath.Join(baseDir, rf)
+		}
+	}
+
+	var globbedFiles []string
+	for _, rf := range utf.RuleFiles {
+		m, err := filepath.Glob(rf)
+		if err != nil {
+			return err
+		}
+		if len(m) == 0 {
+			fmt.Fprintln(os.Stderr, "  WARNING: no file match pattern", rf)
+		}
+		globbedFiles = append(globbedFiles, m...)
+	}
+	utf.RuleFiles = globbedFiles
+	return nil
+}
+
 func (tg *testGroup) test(evalInterval time.Duration, groupOrderMap map[string]int, testGroups []vmalertconfig.Group) (checkErrs []error) {
 	// set up vmstorage and http server for ingest and read queries
 	setUp()
@@ -296,15 +316,11 @@ func (tg *testGroup) test(evalInterval time.Duration, groupOrderMap map[string]i
 	maxEvalTime := testStartTime.Add(tg.maxEvalTime())
 	for ts := testStartTime; ts.Before(maxEvalTime) || ts.Equal(maxEvalTime); ts = ts.Add(evalInterval) {
 		for _, g := range groups {
-			if len(g.Rules) == 0 {
-				continue
-			}
 			errs := g.ExecOnce(context.Background(), func() []notifier.Notifier { return nil }, rw, ts)
 			for err := range errs {
 				if err != nil {
 					checkErrs = append(checkErrs, fmt.Errorf("\nfailed to exec group: %q, time: %s, err: %w", g.Name,
 						ts, err))
-					return
 				}
 			}
 			// flush series after each group evaluation
@@ -358,7 +374,7 @@ func (tg *testGroup) test(evalInterval time.Duration, groupOrderMap map[string]i
 						if expAlert.ExpLabels == nil {
 							expAlert.ExpLabels = make(map[string]string)
 						}
-						// alertGroupNameLabel is added as additional labels when `disableAlertgroupLabel` is false
+						// alertGroupNameLabel is added as additional labels when `disableAlertGroupLabel` is false
 						if !disableAlertgroupLabel {
 							expAlert.ExpLabels["alertgroup"] = groupname
 						}

app/vmalert/Makefile

@@ -101,7 +101,8 @@ replay-vmalert: vmalert
 		-remoteWrite.url=http://localhost:8428 \
 		-external.label=cluster=east-1 \
 		-external.label=replica=a \
-		-replay.timeFrom=2024-06-01T00:00:00Z
+		-replay.timeFrom=2021-05-11T07:21:43Z \
+		-replay.timeTo=2021-05-29T18:40:43Z
 
 vmalert-linux-amd64:
 	APP_NAME=vmalert CGO_ENABLED=1 GOOS=linux GOARCH=amd64 $(MAKE) app-local-goos-goarch
@@ -118,9 +119,6 @@ vmalert-linux-ppc64le:
 vmalert-linux-s390x:
 	APP_NAME=vmalert CGO_ENABLED=0 GOOS=linux GOARCH=s390x $(MAKE) app-local-goos-goarch
 
-vmalert-linux-loong64:
-	APP_NAME=vmalert CGO_ENABLED=0 GOOS=linux GOARCH=loong64 $(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

@@ -1,3 +1,3 @@
-See vmalert docs [here](https://docs.victoriametrics.com/vmalert/).
+See vmalert docs [here](https://docs.victoriametrics.com/vmalert.html).
 
 vmalert docs can be edited at [docs/vmalert.md](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/docs/vmalert.md).

app/vmalert/config/config.go

@@ -234,7 +234,7 @@ func ParseSilent(pathPatterns []string, validateTplFn ValidateTplFn, validateExp
 	cLogger.Suppress(true)
 	defer cLogger.Suppress(false)
 
-	files, err := ReadFromFS(pathPatterns)
+	files, err := readFromFS(pathPatterns)
 	if err != nil {
 		return nil, fmt.Errorf("failed to read from the config: %w", err)
 	}
@@ -243,7 +243,7 @@ func ParseSilent(pathPatterns []string, validateTplFn ValidateTplFn, validateExp
 
 // Parse parses rule configs from given file patterns
 func Parse(pathPatterns []string, validateTplFn ValidateTplFn, validateExpressions bool) ([]Group, error) {
-	files, err := ReadFromFS(pathPatterns)
+	files, err := readFromFS(pathPatterns)
 	if err != nil {
 		return nil, fmt.Errorf("failed to read from the config: %w", err)
 	}

app/vmalert/config/fs.go

@@ -32,14 +32,14 @@ var (
 	fsRegistry   = make(map[string]FS)
 )
 
-// ReadFromFS parses the given path list and inits FS for each item.
-// Once initialed, ReadFromFS will try to read and return files from each FS.
-// ReadFromFS returns an error if at least one FS failed to init.
+// readFromFS parses the given path list and inits FS for each item.
+// Once initialed, 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 initialed only once.
 //
 // It is allowed to mix different FS types in path list.
-func ReadFromFS(paths []string) (map[string][]byte, error) {
+func readFromFS(paths []string) (map[string][]byte, error) {
 	var err error
 	result := make(map[string][]byte)
 	for _, path := range paths {

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

@@ -1158,9 +1158,9 @@
           $labels.pod }}.'
         runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-cputhrottlinghigh
       expr: |
-        sum(increase(container_cpu_cfs_throttled_periods_total{container!="", }[5m])) by (cluster, container, pod, namespace)
+        sum(increase(container_cpu_cfs_throttled_periods_total{container!="", }[5m])) by (container, pod, namespace)
           /
-        sum(increase(container_cpu_cfs_periods_total{}[5m])) by (cluster, container, pod, namespace)
+        sum(increase(container_cpu_cfs_periods_total{}[5m])) by (container, pod, namespace)
           > ( 25 / 100 )
       for: 15m
       labels:

app/vmalert/datasource/init.go

@@ -15,9 +15,8 @@ import (
 )
 
 var (
-	addr = flag.String("datasource.url", "", "Datasource compatible with Prometheus HTTP API. It can be single node VictoriaMetrics or vmselect endpoint. Required parameter. "+
-		"Supports address in the form of IP address with a port (e.g., 127.0.0.1:8428) or DNS SRV record. "+
-		"See also -remoteRead.disablePathAppend and -datasource.showURL")
+	addr = flag.String("datasource.url", "", "Datasource compatible with Prometheus HTTP API. It can be single node VictoriaMetrics or vmselect URL. Required parameter. "+
+		"E.g. http://127.0.0.1:8428 . See also -remoteRead.disablePathAppend and -datasource.showURL")
 	appendTypePrefix  = flag.Bool("datasource.appendTypePrefix", false, "Whether to add type prefix to -datasource.url based on the query type. Set to true if sending different query types to the vmselect URL.")
 	showDatasourceURL = flag.Bool("datasource.showURL", false, "Whether to avoid stripping sensitive information such as auth headers or passwords from URLs in log messages or UI and exported metrics. "+
 		"It is hidden by default, since it can contain sensitive info such as auth key")
@@ -47,7 +46,7 @@ var (
 	oauth2TokenURL = flag.String("datasource.oauth2.tokenUrl", "", "Optional OAuth2 tokenURL to use for -datasource.url")
 	oauth2Scopes   = flag.String("datasource.oauth2.scopes", "", "Optional OAuth2 scopes to use for -datasource.url. Scopes must be delimited by ';'")
 
-	lookBack = flag.Duration("datasource.lookback", 0, `Deprecated: please adjust "-search.latencyOffset" at datasource side `+
+	lookBack = flag.Duration("datasource.lookback", 0, `Will be deprecated soon, please adjust "-search.latencyOffset"  at datasource side `+
 		`or specify "latency_offset" in rule group's params. Lookback defines how far into the past to look when evaluating queries. `+
 		`For example, if the datasource.lookback=5m then param "time" with value now()-5m will be added to every query.`)
 	queryStep = flag.Duration("datasource.queryStep", 5*time.Minute, "How far a value can fallback to when evaluating queries. "+
@@ -57,10 +56,9 @@ var (
 		`Whether to align "time" parameter with evaluation interval. `+
 		"Alignment supposed to produce deterministic results despite number of vmalert replicas or time they were started. "+
 		"See more details at https://github.com/VictoriaMetrics/VictoriaMetrics/pull/1257")
-	maxIdleConnections    = flag.Int("datasource.maxIdleConnections", 100, `Defines the number of idle (keep-alive connections) to each configured datasource. Consider setting this value equal to the value: groups_total * group.concurrency. Too low a value may result in a high number of sockets in TIME_WAIT state.`)
-	idleConnectionTimeout = flag.Duration("datasource.idleConnTimeout", 50*time.Second, `Defines a duration for idle (keep-alive connections) to exist. Consider setting this value less than "-http.idleConnTimeout". It must prevent possible "write: broken pipe" and "read: connection reset by peer" errors.`)
-	disableKeepAlive      = flag.Bool("datasource.disableKeepAlive", false, `Whether to disable long-lived connections to the datasource. `+
-		`If true, disables HTTP keep-alive and will only use the connection to the server for a single HTTP request.`)
+	maxIdleConnections = flag.Int("datasource.maxIdleConnections", 100, `Defines the number of idle (keep-alive connections) to each configured datasource. Consider setting this value equal to the value: groups_total * group.concurrency. Too low a value may result in a high number of sockets in TIME_WAIT state.`)
+	disableKeepAlive   = flag.Bool("datasource.disableKeepAlive", false, `Whether to disable long-lived connections to the datasource. `+
+		`If true, disables HTTP keep-alives and will only use the connection to the server for a single HTTP request.`)
 	roundDigits = flag.Int("datasource.roundDigits", 0, `Adds "round_digits" GET param to datasource requests. `+
 		`In VM "round_digits" limits the number of digits after the decimal point in response values.`)
 )
@@ -93,20 +91,18 @@ func Init(extraParams url.Values) (QuerierBuilder, error) {
 		logger.Warnf("flag `-datasource.queryTimeAlignment` is deprecated and will be removed in next releases. Please use `eval_alignment` in rule group instead.")
 	}
 	if *lookBack != 0 {
-		logger.Warnf("flag `-datasource.lookback` is deprecated and will be removed in next releases. Please adjust `-search.latencyOffset` at datasource side or specify `latency_offset` in rule group's params. See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5155 for details.")
+		logger.Warnf("flag `-datasource.lookback` will be deprecated soon. Please use `-rule.evalDelay` command-line flag instead. See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5155 for details.")
 	}
 
 	tr, err := httputils.Transport(*addr, *tlsCertFile, *tlsKeyFile, *tlsCAFile, *tlsServerName, *tlsInsecureSkipVerify)
 	if err != nil {
 		return nil, fmt.Errorf("failed to create transport: %w", err)
 	}
-	tr.DialContext = httputils.GetStatDialFunc("vmalert_datasource")
 	tr.DisableKeepAlives = *disableKeepAlive
 	tr.MaxIdleConnsPerHost = *maxIdleConnections
 	if tr.MaxIdleConns != 0 && tr.MaxIdleConns < tr.MaxIdleConnsPerHost {
 		tr.MaxIdleConns = tr.MaxIdleConnsPerHost
 	}
-	tr.IdleConnTimeout = *idleConnectionTimeout
 
 	if extraParams == nil {
 		extraParams = url.Values{}
@@ -137,6 +133,7 @@ func Init(extraParams url.Values) (QuerierBuilder, error) {
 		authCfg:          authCfg,
 		datasourceURL:    strings.TrimSuffix(*addr, "/"),
 		appendTypePrefix: *appendTypePrefix,
+		lookBack:         *lookBack,
 		queryStep:        *queryStep,
 		dataSourceType:   datasourcePrometheus,
 		extraParams:      extraParams,

app/vmalert/datasource/vm.go

@@ -11,7 +11,6 @@ import (
 	"time"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/netutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promauth"
 )
 
@@ -36,6 +35,7 @@ type VMStorage struct {
 	authCfg          *promauth.Config
 	datasourceURL    string
 	appendTypePrefix bool
+	lookBack         time.Duration
 	queryStep        time.Duration
 	dataSourceType   datasourceType
 
@@ -63,6 +63,7 @@ func (s *VMStorage) Clone() *VMStorage {
 		authCfg:          s.authCfg,
 		datasourceURL:    s.datasourceURL,
 		appendTypePrefix: s.appendTypePrefix,
+		lookBack:         s.lookBack,
 		queryStep:        s.queryStep,
 
 		dataSourceType:     s.dataSourceType,
@@ -121,12 +122,13 @@ func (s *VMStorage) BuildWithParams(params QuerierParams) Querier {
 }
 
 // NewVMStorage is a constructor for VMStorage
-func NewVMStorage(baseURL string, authCfg *promauth.Config, queryStep time.Duration, appendTypePrefix bool, c *http.Client) *VMStorage {
+func NewVMStorage(baseURL string, authCfg *promauth.Config, lookBack time.Duration, queryStep time.Duration, appendTypePrefix bool, c *http.Client) *VMStorage {
 	return &VMStorage{
 		c:                c,
 		authCfg:          authCfg,
 		datasourceURL:    strings.TrimSuffix(baseURL, "/"),
 		appendTypePrefix: appendTypePrefix,
+		lookBack:         lookBack,
 		queryStep:        queryStep,
 		dataSourceType:   datasourcePrometheus,
 		extraParams:      url.Values{},
@@ -135,23 +137,23 @@ func NewVMStorage(baseURL string, authCfg *promauth.Config, queryStep time.Durat
 
 // Query executes the given query and returns parsed response
 func (s *VMStorage) Query(ctx context.Context, query string, ts time.Time) (Result, *http.Request, error) {
-	req, err := s.newQueryRequest(ctx, query, ts)
+	req, err := s.newQueryRequest(query, ts)
 	if err != nil {
 		return Result{}, nil, err
 	}
-	resp, err := s.do(req)
+	resp, err := s.do(ctx, req)
 	if err != nil {
-		if !errors.Is(err, io.EOF) && !errors.Is(err, io.ErrUnexpectedEOF) && !netutil.IsTrivialNetworkError(err) {
+		if !errors.Is(err, io.EOF) && !errors.Is(err, io.ErrUnexpectedEOF) {
 			// Return unexpected error to the caller.
 			return Result{}, nil, err
 		}
 		// Something in the middle between client and datasource might be closing
 		// the connection. So we do a one more attempt in hope request will succeed.
-		req, err = s.newQueryRequest(ctx, query, ts)
+		req, err = s.newQueryRequest(query, ts)
 		if err != nil {
 			return Result{}, nil, fmt.Errorf("second attempt: %w", err)
 		}
-		resp, err = s.do(req)
+		resp, err = s.do(ctx, req)
 		if err != nil {
 			return Result{}, nil, fmt.Errorf("second attempt: %w", err)
 		}
@@ -180,23 +182,23 @@ func (s *VMStorage) QueryRange(ctx context.Context, query string, start, end tim
 	if end.IsZero() {
 		return res, fmt.Errorf("end param is missing")
 	}
-	req, err := s.newQueryRangeRequest(ctx, query, start, end)
+	req, err := s.newQueryRangeRequest(query, start, end)
 	if err != nil {
 		return res, err
 	}
-	resp, err := s.do(req)
+	resp, err := s.do(ctx, req)
 	if err != nil {
-		if !errors.Is(err, io.EOF) && !errors.Is(err, io.ErrUnexpectedEOF) && !netutil.IsTrivialNetworkError(err) {
+		if !errors.Is(err, io.EOF) && !errors.Is(err, io.ErrUnexpectedEOF) {
 			// Return unexpected error to the caller.
 			return res, err
 		}
 		// Something in the middle between client and datasource might be closing
 		// the connection. So we do a one more attempt in hope request will succeed.
-		req, err = s.newQueryRangeRequest(ctx, query, start, end)
+		req, err = s.newQueryRangeRequest(query, start, end)
 		if err != nil {
 			return res, fmt.Errorf("second attempt: %w", err)
 		}
-		resp, err = s.do(req)
+		resp, err = s.do(ctx, req)
 		if err != nil {
 			return res, fmt.Errorf("second attempt: %w", err)
 		}
@@ -208,7 +210,7 @@ func (s *VMStorage) QueryRange(ctx context.Context, query string, start, end tim
 	return res, err
 }
 
-func (s *VMStorage) do(req *http.Request) (*http.Response, error) {
+func (s *VMStorage) do(ctx context.Context, req *http.Request) (*http.Response, error) {
 	ru := req.URL.Redacted()
 	if *showDatasourceURL {
 		ru = req.URL.String()
@@ -216,7 +218,7 @@ func (s *VMStorage) do(req *http.Request) (*http.Response, error) {
 	if s.debug {
 		logger.Infof("DEBUG datasource request: executing %s request with params %q", req.Method, ru)
 	}
-	resp, err := s.c.Do(req)
+	resp, err := s.c.Do(req.WithContext(ctx))
 	if err != nil {
 		return nil, fmt.Errorf("error getting response from %s: %w", ru, err)
 	}
@@ -228,8 +230,8 @@ func (s *VMStorage) do(req *http.Request) (*http.Response, error) {
 	return resp, nil
 }
 
-func (s *VMStorage) newQueryRangeRequest(ctx context.Context, query string, start, end time.Time) (*http.Request, error) {
-	req, err := s.newRequest(ctx)
+func (s *VMStorage) newQueryRangeRequest(query string, start, end time.Time) (*http.Request, error) {
+	req, err := s.newRequest()
 	if err != nil {
 		return nil, fmt.Errorf("cannot create query_range request to datasource %q: %w", s.datasourceURL, err)
 	}
@@ -237,8 +239,8 @@ func (s *VMStorage) newQueryRangeRequest(ctx context.Context, query string, star
 	return req, nil
 }
 
-func (s *VMStorage) newQueryRequest(ctx context.Context, query string, ts time.Time) (*http.Request, error) {
-	req, err := s.newRequest(ctx)
+func (s *VMStorage) newQueryRequest(query string, ts time.Time) (*http.Request, error) {
+	req, err := s.newRequest()
 	if err != nil {
 		return nil, fmt.Errorf("cannot create query request to datasource %q: %w", s.datasourceURL, err)
 	}
@@ -246,15 +248,15 @@ func (s *VMStorage) newQueryRequest(ctx context.Context, query string, ts time.T
 	case "", datasourcePrometheus:
 		s.setPrometheusInstantReqParams(req, query, ts)
 	case datasourceGraphite:
-		s.setGraphiteReqParams(req, query)
+		s.setGraphiteReqParams(req, query, ts)
 	default:
 		logger.Panicf("BUG: engine not found: %q", s.dataSourceType)
 	}
 	return req, nil
 }
 
-func (s *VMStorage) newRequest(ctx context.Context) (*http.Request, error) {
-	req, err := http.NewRequestWithContext(ctx, http.MethodPost, s.datasourceURL, nil)
+func (s *VMStorage) newRequest() (*http.Request, error) {
+	req, err := http.NewRequest(http.MethodPost, s.datasourceURL, nil)
 	if err != nil {
 		logger.Panicf("BUG: unexpected error from http.NewRequest(%q): %s", s.datasourceURL, err)
 	}

app/vmalert/datasource/vm_graphite_api.go

@@ -4,6 +4,8 @@ import (
 	"encoding/json"
 	"fmt"
 	"net/http"
+	"strconv"
+	"time"
 )
 
 type graphiteResponse []graphiteResponseTarget
@@ -46,13 +48,17 @@ const (
 	graphitePrefix = "/graphite"
 )
 
-func (s *VMStorage) setGraphiteReqParams(r *http.Request, query string) {
+func (s *VMStorage) setGraphiteReqParams(r *http.Request, query string, timestamp time.Time) {
 	if s.appendTypePrefix {
 		r.URL.Path += graphitePrefix
 	}
 	r.URL.Path += graphitePath
 	q := r.URL.Query()
 	from := "-5min"
+	if s.lookBack > 0 {
+		lookBack := timestamp.Add(-s.lookBack)
+		from = strconv.FormatInt(lookBack.Unix(), 10)
+	}
 	q.Set("from", from)
 	q.Set("format", "json")
 	q.Set("target", query)

app/vmalert/datasource/vm_prom_api.go

@@ -7,10 +7,6 @@ import (
 	"net/http"
 	"strconv"
 	"time"
-
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
-
-	"github.com/valyala/fastjson"
 )
 
 var (
@@ -35,85 +31,27 @@ type promResponse struct {
 	} `json:"stats,omitempty"`
 }
 
-// see https://prometheus.io/docs/prometheus/latest/querying/api/#instant-queries
 type promInstant struct {
-	// ms is populated after Unmarshal call
-	ms []Metric
+	Result []struct {
+		Labels map[string]string `json:"metric"`
+		TV     [2]interface{}    `json:"value"`
+	} `json:"result"`
 }
 
-// metrics returned parsed Metric slice
-// Must be called only after Unmarshal
-func (pi *promInstant) metrics() ([]Metric, error) {
-	return pi.ms, nil
-}
-
-var jsonParserPool fastjson.ParserPool
-
-// Unmarshal unmarshals the given byte slice into promInstant
-// It is using fastjson to reduce number of allocations compared to
-// standard json.Unmarshal function.
-// Response example:
-//
-//	[{"metric":{"__name__":"up","job":"prometheus"},value": [ 1435781451.781,"1"]},
-//	{"metric":{"__name__":"up","job":"node"},value": [ 1435781451.781,"0"]}]
-func (pi *promInstant) Unmarshal(b []byte) error {
-	p := jsonParserPool.Get()
-	defer jsonParserPool.Put(p)
-
-	v, err := p.ParseBytes(b)
-	if err != nil {
-		return err
-	}
-
-	rows, err := v.Array()
-	if err != nil {
-		return fmt.Errorf("cannot find the top-level array of result objects: %w", err)
-	}
-	pi.ms = make([]Metric, len(rows))
-	for i, row := range rows {
-		metric := row.Get("metric")
-		if metric == nil {
-			return fmt.Errorf("can't find `metric` object in %q", row)
-		}
-		labels := metric.GetObject()
-
-		r := &pi.ms[i]
-		r.Labels = make([]Label, 0, labels.Len())
-		labels.Visit(func(key []byte, v *fastjson.Value) {
-			lv, errLocal := v.StringBytes()
-			if errLocal != nil {
-				err = fmt.Errorf("error when parsing label value %q: %s", v, errLocal)
-				return
-			}
-			r.Labels = append(r.Labels, Label{
-				Name:  string(key),
-				Value: string(lv),
-			})
-		})
+func (r promInstant) metrics() ([]Metric, error) {
+	result := make([]Metric, len(r.Result))
+	for i, res := range r.Result {
+		f, err := strconv.ParseFloat(res.TV[1].(string), 64)
 		if err != nil {
-			return fmt.Errorf("error when parsing `metric` object in %q: %w", row, err)
+			return nil, fmt.Errorf("metric %v, unable to parse float64 from %s: %w", res, res.TV[1], err)
 		}
-
-		value := row.Get("value")
-		if value == nil {
-			return fmt.Errorf("can't find `value` object in %q", row)
-		}
-		sample := value.GetArray()
-		if len(sample) != 2 {
-			return fmt.Errorf("object `value` in %q should contain 2 values, but contains %d instead", row, len(sample))
-		}
-		r.Timestamps = []int64{sample[0].GetInt64()}
-		val, err := sample[1].StringBytes()
-		if err != nil {
-			return fmt.Errorf("error when parsing `value` object %q: %s", sample[1], err)
-		}
-		f, err := strconv.ParseFloat(bytesutil.ToUnsafeString(val), 64)
-		if err != nil {
-			return fmt.Errorf("error when parsing float64 from %s in %q: %w", sample[1], row, err)
-		}
-		r.Values = []float64{f}
+		var m Metric
+		m.SetLabels(res.Labels)
+		m.Timestamps = append(m.Timestamps, int64(res.TV[0].(float64)))
+		m.Values = append(m.Values, f)
+		result[i] = m
 	}
-	return nil
+	return result, nil
 }
 
 type promRange struct {
@@ -180,7 +118,7 @@ func parsePrometheusResponse(req *http.Request, resp *http.Response) (res Result
 	switch r.Data.ResultType {
 	case rtVector:
 		var pi promInstant
-		if err := pi.Unmarshal(r.Data.Result); err != nil {
+		if err := json.Unmarshal(r.Data.Result, &pi.Result); err != nil {
 			return res, fmt.Errorf("unmarshal err %w; \n %#v", err, string(r.Data.Result))
 		}
 		parseFn = pi.metrics
@@ -223,6 +161,9 @@ func (s *VMStorage) setPrometheusInstantReqParams(r *http.Request, query string,
 		r.URL.Path += "/api/v1/query"
 	}
 	q := r.URL.Query()
+	if s.lookBack > 0 {
+		timestamp = timestamp.Add(-s.lookBack)
+	}
 	q.Set("time", timestamp.Format(time.RFC3339))
 	if !*disableStepParam && s.evaluationInterval > 0 { // set step as evaluationInterval by default
 		// always convert to seconds to keep compatibility with older