Fix version mismatch

Signed-off-by: Arkadii Yakovets <ark@victoriametrics.com>

.github/workflows/benchmark.yml

@@ -0,0 +1,56 @@
+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

@@ -0,0 +1,54 @@
+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

@@ -0,0 +1,62 @@
+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-ts.yml

@@ -1,22 +1,27 @@
-name: "CodeQL - JS"
+name: 'CodeQL JS/TS'
 
 on:
   push:
-    branches: [master, cluster]
+    branches:
+      - cluster
+      - master
     paths:
-      - "**.js"
+      - '**.js'
+      - '**.ts'
+      - '**.tsx'
   pull_request:
-    # The branches below must be a subset of the branches above
-    branches: [master, cluster]
+    branches:
+      - cluster
+      - master
     paths:
-      - "**.js"
-  schedule:
-    - cron: "30 18 * * 2"
+      - '**.js'
+      - '**.ts'
+      - '**.tsx'
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
   cancel-in-progress: true
-  
+
 jobs:
   analyze:
     name: Analyze
@@ -26,11 +31,6 @@ 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: ${{ matrix.language }}
+          languages: javascript-typescript
 
       - name: Perform CodeQL Analysis
         uses: github/codeql-action/analyze@v3
         with:
-          category: "javascript"
+          category: 'language:js/ts'

.github/workflows/codeql-analysis.yml

@@ -1,103 +0,0 @@
-# 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

@@ -1,29 +1,27 @@
 name: main
+
 on:
   push:
     branches:
-      - master
       - cluster
-    paths-ignore:
-      - "docs/**"
-      - "**.md"
-      - "dashboards/**"
-      - "deployment/**.yml"
+      - master
+    paths:
+      - '.github/workflows/main.yml'
+      - '**.go'
   pull_request:
     branches:
-      - master
       - cluster
-    paths-ignore:
-      - "docs/**"
-      - "**.md"
-      - "dashboards/**"
-      - "deployment/**.yml"
+      - master
+    paths:
+      - '.github/workflows/main.yml'
+      - '**.go'
+
 permissions:
   contents: read
 
 concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
   cancel-in-progress: true
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
 
 jobs:
   lint:
@@ -37,59 +35,51 @@ jobs:
         id: go
         uses: actions/setup-go@v5
         with:
-          go-version: stable
           cache: false
+          go-version: stable
 
       - name: Cache Go artifacts
         uses: actions/cache@v4
         with:
           path: |
             ~/.cache/go-build
-            ~/go/pkg/mod
             ~/go/bin
+            ~/go/pkg/mod
           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 check-all
-        run: |
-          make check-all
-          git diff --exit-code
+      - name: Run fmt
+        run: make fmt
 
-  build:
-    needs: lint
-    name: build
-    runs-on: ubuntu-latest
-    steps:
-      - name: Code checkout
-        uses: actions/checkout@v4
-
-      - name: Setup Go
-        id: go
-        uses: actions/setup-go@v5
+      - 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:
-          go-version: stable
-          cache: false
+          # The version must match "install-golangci-lint" Makefile target version.
+          version: v1.59.1
 
-      - name: Cache Go artifacts
-        uses: actions/cache@v4
-        with:
-          path: |
-            ~/.cache/go-build
-            ~/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: Run govulncheck
+        run: make govulncheck
 
-      - name: Build
-        run: make crossbuild
+      - name: Check diff
+        run: git diff --exit-code
 
   test:
+    name: test
     needs: lint
+    runs-on: ubuntu-latest
+
     strategy:
       matrix:
-        scenario: ["test-full", "test-pure", "test-full-386"]
-    name: test
-    runs-on: ubuntu-latest
+        scenario:
+          - 'test-full'
+          - 'test-full-386'
+          - 'test-pure'
+
     steps:
       - name: Code checkout
         uses: actions/checkout@v4
@@ -98,20 +88,20 @@ jobs:
         id: go
         uses: actions/setup-go@v5
         with:
-          go-version: stable
           cache: false
+          go-version: stable
 
       - name: Cache Go artifacts
         uses: actions/cache@v4
         with:
           path: |
             ~/.cache/go-build
-            ~/go/pkg/mod
             ~/go/bin
+            ~/go/pkg/mod
           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

@@ -25,7 +25,7 @@ jobs:
           token: ${{ secrets.VM_BOT_GH_TOKEN }}
           path: docs
       - name: Import GPG key
-        uses: crazy-max/ghaction-import-gpg@v5
+        uses: crazy-max/ghaction-import-gpg@v6
         with:
           gpg_private_key: ${{ secrets.VM_BOT_GPG_PRIVATE_KEY }}
           passphrase: ${{ secrets.VM_BOT_PASSPHRASE }}

.gitignore

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

.golangci.yml

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

Makefile

@@ -20,7 +20,6 @@ include app/*/Makefile
 include docs/Makefile
 include deployment/*/Makefile
 include dashboards/Makefile
-include snap/local/Makefile
 include package/release/Makefile
 
 all: \
@@ -440,6 +439,8 @@ vet:
 
 check-all: fmt vet golangci-lint govulncheck
 
+clean-checkers: remove-golangci-lint remove-govulncheck
+
 test:
 	go test ./lib/... ./app/...
 
@@ -466,7 +467,7 @@ benchmark-pure:
 vendor-update:
 	go get -u -d ./lib/...
 	go get -u -d ./app/...
-	go mod tidy -compat=1.21
+	go mod tidy -compat=1.22
 	go mod vendor
 
 app-local:
@@ -492,7 +493,11 @@ golangci-lint: install-golangci-lint
 	golangci-lint run
 
 install-golangci-lint:
-	which golangci-lint || curl -sSfL https://raw.githubusercontent.com/golangci/golangci-lint/master/install.sh | sh -s -- -b $(shell go env GOPATH)/bin v1.57.1
+	# 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`
 
 govulncheck: install-govulncheck
 	govulncheck ./...
@@ -500,6 +505,9 @@ 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
 

README.md

@@ -15,8 +15,7 @@ VictoriaMetrics is a fast, cost-effective and scalable monitoring solution and t
 See [case studies for VictoriaMetrics](https://docs.victoriametrics.com/casestudies/).
 
 VictoriaMetrics is available in [binary releases](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/latest),
-[Docker images](https://hub.docker.com/r/victoriametrics/victoria-metrics/), [Snap packages](https://snapcraft.io/victoriametrics)
-and [source code](https://github.com/VictoriaMetrics/VictoriaMetrics). 
+[Docker images](https://hub.docker.com/r/victoriametrics/victoria-metrics/) and [source code](https://github.com/VictoriaMetrics/VictoriaMetrics). 
 
 Documentation for the cluster version of VictoriaMetrics is available [here](https://docs.victoriametrics.com/cluster-victoriametrics/).
 
@@ -116,12 +115,12 @@ VictoriaMetrics ecosystem contains the following components additionally to [sin
 - [vmalert](https://docs.victoriametrics.com/vmalert/) - a service for processing Prometheus-compatible alerting and recording rules.
 - [vmalert-tool](https://docs.victoriametrics.com/vmalert-tool/) -  a tool for validating alerting and recording rules.
 - [vmauth](https://docs.victoriametrics.com/vmauth/) - authorization proxy and load balancer optimized for VictoriaMetrics products.
-- [vmgateway](https://docs.victoriametrics.com/vmgateway/) - authorization proxy with per-[tenant](https://docs.victoriametrics.com/cluster-victoriametrics/#multitenancy) rate limiting cababilities.
+- [vmgateway](https://docs.victoriametrics.com/vmgateway/) - authorization proxy with per-[tenant](https://docs.victoriametrics.com/cluster-victoriametrics/#multitenancy) rate limiting capabilities.
 - [vmctl](https://docs.victoriametrics.com/vmctl/) - a tool for migrating and copying data between different storage systems for metrics.
 - [vmbackup](https://docs.victoriametrics.com/vmbackup/), [vmrestore](https://docs.victoriametrics.com/vmrestore/) and [vmbackupmanager](https://docs.victoriametrics.com/vmbackupmanager/) -
   tools for creating backups and restoring from backups for VictoriaMetrics data.
 - `vminsert`, `vmselect` and `vmstorage` - components of [VictoriaMetrics cluster](https://docs.victoriametrics.com/cluster-victoriametrics/).
-- [VictoriaLogs](https://docs.victoriametrics.com/VictoriaLogs/) - user-friendly cost-efficient database for logs.
+- [VictoriaLogs](https://docs.victoriametrics.com/victorialogs/) - user-friendly cost-efficient database for logs.
 
 ## Operation
 
@@ -138,7 +137,6 @@ VictoriaMetrics can also be installed via these installation methods:
 * [Ansible role for installing cluster VictoriaMetrics (by VictoriaMetrics)](https://github.com/VictoriaMetrics/ansible-playbooks).
 * [Ansible role for installing cluster VictoriaMetrics (by community)](https://github.com/Slapper/ansible-victoriametrics-cluster-role).
 * [Ansible role for installing single-node VictoriaMetrics (by community)](https://github.com/dreamteam-gg/ansible-victoriametrics-role).
-* [Snap package for VictoriaMetrics](https://snapcraft.io/victoriametrics).
 
 ### How to start VictoriaMetrics
 
@@ -181,24 +179,7 @@ Additionally, all the VictoriaMetrics components allow setting flag values via e
 
 ### Configuration with snap package
 
-Snap package for VictoriaMetrics is available [here](https://snapcraft.io/victoriametrics).
-
-Command-line flags for Snap package can be set with following command:
-
-```sh
-echo 'FLAGS="-selfScrapeInterval=10s -search.logSlowQueryDuration=20s"' > $SNAP_DATA/var/snap/victoriametrics/current/extra_flags
-snap restart victoriametrics
-```
-
-Do not change value for `-storageDataPath` flag, because snap package has limited access to host filesystem.
-
-Changing scrape configuration is possible with text editor:
-
-```sh
-vi $SNAP_DATA/var/snap/victoriametrics/current/etc/victoriametrics-scrape-config.yaml
-```
-
-After changes were made, trigger config re-read with the command `curl 127.0.0.1:8428/-/reload`.
+Snap packages for VictoriaMetrics are supported by community and are available at [https://snapcraft.io/victoriametrics](https://snapcraft.io/victoriametrics).
 
 ### Running as Windows service
 
@@ -337,8 +318,8 @@ This allows Grafana to use a more efficient API to get label values.
 Then build graphs and dashboards for the created datasource using [PromQL](https://prometheus.io/docs/prometheus/latest/querying/basics/)
 or [MetricsQL](https://docs.victoriametrics.com/metricsql/).
 
-Alternatively, use VictoriaMetrics [datasource plugin](https://github.com/VictoriaMetrics/grafana-datasource) with support of extra features. 
-See more in [description](https://github.com/VictoriaMetrics/grafana-datasource#victoriametrics-data-source-for-grafana).
+Alternatively, use VictoriaMetrics [datasource plugin](https://github.com/VictoriaMetrics/victoriametrics-datasource) with support of extra features. 
+See more in [description](https://docs.victoriametrics.com/victoriametrics-datasource/).
 
 Creating a datasource may require [specific permissions](https://grafana.com/docs/grafana/latest/administration/data-source-management/).
 If you don't see an option to create a data source - try contacting system administrator.
@@ -719,6 +700,13 @@ Example for writing data with Graphite plaintext protocol to local VictoriaMetri
 echo "foo.bar.baz;tag1=value1;tag2=value2 123 `date +%s`" | nc -N localhost 2003
 ```
 
+To sanitize ingested metric names and labels according to Prometheus naming convention enable
+`-graphite.sanitizeMetricName` cmd-line flag. When enabled, VictoriaMetrics will apply the following modifications:
+- replace `/`,`@`,`*` with `_`;
+- drop `\`;
+- remove redundant dots, e.g: `metric..name` => `metric.name`;
+- replace characters not matching the expression `^a-zA-Z0-9:._` with `_`.
+
 VictoriaMetrics sets the current time if the timestamp is omitted.
 An arbitrary number of lines delimited by `\n` (aka newline char) can be sent in one go.
 After that the data may be read via [/api/v1/export](#how-to-export-data-in-json-line-format) endpoint:
@@ -1114,13 +1102,13 @@ ROOT_IMAGE=scratch make package-victoria-metrics
 
 VictoriaMetrics can be built with Podman in either rootful or rootless mode.
 
-When building via rootlful Podman, simply add `DOCKER=podman` to the relevant `make` commandline.  To build
+When building via rootful Podman, simply add `DOCKER=podman` to the relevant `make` commandline.  To build
 via rootless Podman, add `DOCKER=podman DOCKER_RUN="podman run --userns=keep-id"` to the `make`
 commandline.
 
 For example: `make victoria-metrics-pure DOCKER=podman DOCKER_RUN="podman run --userns=keep-id"`
 
-Note that `production` builds are not supported via Podman becuase Podman does not support `buildx`.
+Note that `production` builds are not supported via Podman because Podman does not support `buildx`.
 
 ## Start with docker-compose
 
@@ -1131,7 +1119,7 @@ More details may be found [here](https://github.com/VictoriaMetrics/VictoriaMetr
 ## Setting up service
 
 Read [instructions](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/43) on how to set up VictoriaMetrics
-as a service for your OS. A [snap package](https://snapcraft.io/victoriametrics) is available for Ubuntu.
+as a service for your OS.
 
 ## How to work with snapshots
 
@@ -1549,6 +1537,25 @@ Set HTTP request header `Content-Encoding: gzip` when sending gzip-compressed da
 VictoriaMetrics stores the ingested OpenTelemetry [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples) as is without any transformations.
 Pass `-opentelemetry.usePrometheusNaming` command-line flag to VictoriaMetrics for automatic conversion of metric names and labels into Prometheus-compatible format.
 
+Using the following exporter configuration in the opentelemetry collector will allow you to send metrics into VictoriaMetrics:
+
+```yaml
+exporters:
+  otlphttp/victoriametrics:
+    compression: gzip
+    encoding: proto
+    endpoint: http://<collector/vmagent>.<namespace>.svc.cluster.local:<port>/opentelemetry
+```
+Remember to add the exporter to the desired service pipeline in order to activate the exporter.
+```yaml
+service:
+  pipelines:
+    metrics:
+      exporters:
+        - otlphttp/victoriametrics
+      receivers:
+        - otlp
+```
 See [How to use OpenTelemetry metrics with VictoriaMetrics](https://docs.victoriametrics.com/guides/getting-started-with-opentelemetry/).
 
 ## JSON line format
@@ -2082,7 +2089,7 @@ General security recommendations:
 
 - All the VictoriaMetrics components must run in protected private networks without direct access from untrusted networks such as Internet.
   The exception is [vmauth](https://docs.victoriametrics.com/vmauth/) and [vmgateway](https://docs.victoriametrics.com/vmgateway/),
-  which are indended for serving public requests and performing authorization with [TLS termination](https://en.wikipedia.org/wiki/TLS_termination_proxy).
+  which are intended for serving public requests and performing authorization with [TLS termination](https://en.wikipedia.org/wiki/TLS_termination_proxy).
 - All the requests from untrusted networks to VictoriaMetrics components must go through auth proxy such as [vmauth](https://docs.victoriametrics.com/vmauth/)
   or [vmgateway](https://docs.victoriametrics.com/vmgateway/). The proxy must be set up with proper authentication and authorization.
 - Prefer using lists of allowed API endpoints, while disallowing access to other endpoints when configuring [vmauth](https://docs.victoriametrics.com/vmauth/)
@@ -2124,7 +2131,7 @@ All the VictoriaMetrics [Enterprise](https://docs.victoriametrics.com/enterprise
 via [Let's Encrypt service](https://letsencrypt.org/). The following command-line flags must be set in order to enable automatic issuing of TLS certificates:
 
 - `-httpListenAddr` must be set for listening TCP port `443`. For example, `-httpListenAddr=:443`. This port must be accessible by the [Let's Encrypt service](https://letsencrypt.org/).
-- `-tls` must be set in order to accept HTTPS requests at `-httpListenAddr`.
+- `-tls` must be set in order to accept HTTPS requests at `-httpListenAddr`. Note that `-tlcCertFile` and `-tlsKeyFile` aren't needed when automatic TLS certificate issuing is enabled.
 - `-tlsAutocertHosts` must be set to comma-separated list of hosts, which can be reached via `-httpListenAddr`. TLS certificates are automatically issued for these hosts.
 - `-tlsAutocertEmail` must be set to contact email for the issued TLS certificates.
 - `-tlsAutocertCacheDir` may be set to the directory path for persisting the issued TLS certificates between VictoriaMetrics restarts. If this flag isn't set,
@@ -2132,6 +2139,9 @@ via [Let's Encrypt service](https://letsencrypt.org/). The following command-lin
 
 This functionality can be evaluated for free according to [these docs](https://docs.victoriametrics.com/enterprise/).
 
+See also [security recommendations](#security).
+
+
 ## Tuning
 
 * No need in tuning for VictoriaMetrics - it uses reasonable defaults for command-line flags,
@@ -2326,7 +2336,7 @@ and [cardinality explorer docs](#cardinality-explorer).
 
 * If you run VictoriaMetrics on a host with 16 or more CPU cores, then it may be needed to tune the `-search.maxWorkersPerQuery` command-line flag
   in order to improve query performance. If VictoriaMetrics serves big number of concurrent `select` queries, then try reducing the value for this flag.
-  If VcitoriaMetrics serves heavy queries, which select `>10K` of [time series](https://docs.victoriametrics.com/keyconcepts/#time-series) and/or process `>100M`
+  If VictoriaMetrics serves heavy queries, which select `>10K` of [time series](https://docs.victoriametrics.com/keyconcepts/#time-series) and/or process `>100M`
   of [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples) per query, then try setting the value for this flag to the number of available CPU cores.
 
 * VictoriaMetrics buffers incoming data in memory for up to a few seconds before flushing it to persistent storage.
@@ -2352,7 +2362,8 @@ and [cardinality explorer docs](#cardinality-explorer).
 * If VictoriaMetrics doesn't work because of certain parts are corrupted due to disk errors,
   then just remove directories with broken parts. It is safe removing subdirectories under `<-storageDataPath>/data/{big,small}/YYYY_MM` directories
   when VictoriaMetrics isn't running. This recovers VictoriaMetrics at the cost of data loss stored in the deleted broken parts.
-  In the future, `vmrecover` tool will be created for automatic recovering from such errors.
+  The names of broken parts should be present in the error message. If you see that error message is truncated and doesn't contain all the information
+  try increasing `-loggerMaxArgLen` cmd-line flag to higher values to avoid error messages truncation.
 
 * If you see gaps on the graphs, try resetting the cache by sending request to `/internal/resetRollupResultCache`.
   If this removes gaps on the graphs, then it is likely data with timestamps older than `-search.cacheTimestampOffset`
@@ -2372,7 +2383,7 @@ and [cardinality explorer docs](#cardinality-explorer).
 * New time series can be logged if `-logNewSeries` command-line flag is passed to VictoriaMetrics.
 
 * VictoriaMetrics limits the number of labels per each metric with `-maxLabelsPerTimeseries` command-line flag
-  and drops superflouos labels. This prevents from ingesting metrics with too many labels.
+  and drops superfluous labels. This prevents from ingesting metrics with too many labels.
   It is recommended [monitoring](#monitoring) `vm_metrics_with_dropped_labels_total`
   metric in order to determine whether `-maxLabelsPerTimeseries` must be adjusted for your workload.
 
@@ -2434,7 +2445,7 @@ It is also possible removing [rollup result cache](#rollup-result-cache) on star
 
 ## Rollup result cache
 
-VictoriaMetrics caches query responses by default. This allows increasing performance for repated queries
+VictoriaMetrics caches query responses by default. This allows increasing performance for repeated queries
 to [`/api/v1/query`](https://docs.victoriametrics.com/keyconcepts/#instant-query) and [`/api/v1/query_range`](https://docs.victoriametrics.com/keyconcepts/#range-query)
 with the increasing `time`, `start` and `end` query args.
 
@@ -2628,7 +2639,33 @@ If you like VictoriaMetrics and want to contribute, then please [read these docs
 
 Report bugs and propose new features [here](https://github.com/VictoriaMetrics/VictoriaMetrics/issues).
 
-## Images in documentation
+## Documentation
+
+VictoriaMetrics documentation is available at [https://docs.victoriametrics.com/](https://docs.victoriametrics.com/).
+It is built from `*.md` files located in [docs](https://github.com/VictoriaMetrics/VictoriaMetrics/tree/master/docs) folder
+and gets automatically updated once changes are merged to [master](https://github.com/VictoriaMetrics/VictoriaMetrics/tree/master) branch.
+To update the documentation follow the steps below:
+- [Fork](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/about-forks) 
+VictoriaMetrics repo and apply changes to the docs:
+  - To update [the main page](https://docs.victoriametrics.com/) modify [this file](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/README.md).
+  - To update other pages, apply changes to the corresponding file in [docs folder](https://github.com/VictoriaMetrics/VictoriaMetrics/tree/master/docs).
+- If your changes contain an image then see [images in documentation](https://docs.victoriametrics.com/#images-in-documentation).
+- Once changes are made, execute the command below to finalize and sync the changes:
+```sh
+make docs-sync
+```
+- Create [a pull request](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/proposing-changes-to-your-work-with-pull-requests/creating-a-pull-request)
+with proposed changes and wait for it to be merged.
+
+Requirements for changes to docs:
+- Keep backward compatibility of existing links. Avoid changing anchors or deleting pages as they could have been
+used or posted in other docs, GitHub issues, stackoverlow answers, etc. 
+- Keep docs simple. Try using as simple wording as possible.
+- Keep docs consistent. When modifying existing docs, verify that other places referencing to this doc are still relevant.
+- Prefer improving the existing docs instead of adding new ones.
+- Use absolute links.
+
+### Images in documentation
 
 Please, keep image size and number of images per single page low. Keep the docs page as lightweight as possible.
 
@@ -2684,7 +2721,7 @@ Pass `-help` to VictoriaMetrics in order to see the list of supported command-li
   -cacheExpireDuration duration
      Items are removed from in-memory caches after they aren't accessed for this duration. Lower values may reduce memory usage at the cost of higher CPU usage. See also -prevCacheRemovalPercent (default 30m0s)
   -configAuthKey value
-     Authorization key for accessing /config page. It must be passed via authKey query arg
+     Authorization key for accessing /config page. It must be passed via authKey query arg. It overrides httpAuth.* settings.
      Flag value can be read from the given file when using -configAuthKey=file:///abs/path/to/file or -configAuthKey=file://./relative/path/to/file . Flag value can be read from the given http/https url when using -configAuthKey=http://host/path or -configAuthKey=https://host/path
   -csvTrimTimestamp duration
      Trim timestamps when importing csv data to this duration. Minimum practical duration is 1ms. Higher duration (i.e. 1s) may be used for reducing disk space usage for timestamp data (default 1ms)
@@ -2731,6 +2768,8 @@ Pass `-help` to VictoriaMetrics in order to see the list of supported command-li
      Flag value can be read from the given file when using -forceMergeAuthKey=file:///abs/path/to/file or -forceMergeAuthKey=file://./relative/path/to/file . Flag value can be read from the given http/https url when using -forceMergeAuthKey=http://host/path or -forceMergeAuthKey=https://host/path
   -fs.disableMmap
      Whether to use pread() instead of mmap() for reading data files. By default, mmap() is used for 64-bit arches and pread() is used for 32-bit arches, since they cannot read data files bigger than 2^32 bytes in memory. mmap() is usually faster for reading small data chunks than pread()
+  -graphite.sanitizeMetricName
+     Sanitize metric names for the ingested Graphite data. See https://docs.victoriametrics.com/#how-to-send-data-from-graphite-compatible-agents-such-as-statsd
   -graphiteListenAddr string
      TCP and UDP address to listen for Graphite plaintext data. Usually :2003 must be set. Doesn't work if empty. See also -graphiteListenAddr.useProxyProtocol
   -graphiteListenAddr.useProxyProtocol
@@ -2803,9 +2842,9 @@ Pass `-help` to VictoriaMetrics in order to see the list of supported command-li
   -internStringMaxLen int
      The maximum length for strings to intern. A lower limit may save memory at the cost of higher CPU usage. See https://en.wikipedia.org/wiki/String_interning . See also -internStringDisableCache and -internStringCacheExpireDuration (default 500)
   -license string
-     Lisense key for VictoriaMetrics Enterprise. See https://victoriametrics.com/products/enterprise/ . Trial Enterprise license can be obtained from https://victoriametrics.com/products/enterprise/trial/ . This flag is available only in Enterprise binaries. The license key can be also passed via file specified by -licenseFile command-line flag
+     License key for VictoriaMetrics Enterprise. See https://victoriametrics.com/products/enterprise/ . Trial Enterprise license can be obtained from https://victoriametrics.com/products/enterprise/trial/ . This flag is available only in Enterprise binaries. The license key can be also passed via file specified by -licenseFile command-line flag
   -license.forceOffline
-     Whether to enable offline verification for VictoriaMetrics Enterprise license key, which has been passed either via -license or via -licenseFile command-line flag. The issued license key must support offline verification feature. Contact info@victoriametrics.com if you need offline license verification. This flag is avilable only in Enterprise binaries
+     Whether to enable offline verification for VictoriaMetrics Enterprise license key, which has been passed either via -license or via -licenseFile command-line flag. The issued license key must support offline verification feature. Contact info@victoriametrics.com if you need offline license verification. This flag is available only in Enterprise binaries
   -licenseFile string
      Path to file with license key for VictoriaMetrics Enterprise. See https://victoriametrics.com/products/enterprise/ . Trial Enterprise license can be obtained from https://victoriametrics.com/products/enterprise/trial/ . This flag is available only in Enterprise binaries. The license key can be also passed inline via -license command-line flag
   -logNewSeries
@@ -2834,7 +2873,7 @@ Pass `-help` to VictoriaMetrics in order to see the list of supported command-li
      The maximum size in bytes of a single Prometheus remote_write API request
      Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB (default 33554432)
   -maxLabelValueLen int
-     The maximum length of label values in the accepted time series. Longer label values are truncated. In this case the vm_too_long_label_values_total metric at /metrics page is incremented (default 16384)
+     The maximum length of label values in the accepted time series. Longer label values are truncated. In this case the vm_too_long_label_values_total metric at /metrics page is incremented (default 1024)
   -maxLabelsPerTimeseries int
      The maximum number of labels accepted per time series. Superfluous labels are dropped. In this case the vm_metrics_with_dropped_labels_total metric at /metrics page is incremented (default 30)
   -memory.allowedBytes size
@@ -2949,7 +2988,7 @@ Pass `-help` to VictoriaMetrics in order to see the list of supported command-li
   -promscrape.kumaSDCheckInterval duration
      Interval for checking for changes in kuma service discovery. This works only if kuma_sd_configs is configured in '-promscrape.config' file. See https://docs.victoriametrics.com/sd_configs/#kuma_sd_configs for details (default 30s)
   -promscrape.maxDroppedTargets int
-     The maximum number of droppedTargets to show at /api/v1/targets page. Increase this value if your setup drops more scrape targets during relabeling and you need investigating labels for all the dropped targets. Note that the increased number of tracked dropped targets may result in increased memory usage (default 1000)
+     The maximum number of droppedTargets to show at /api/v1/targets page. Increase this value if your setup drops more scrape targets during relabeling and you need investigating labels for all the dropped targets. Note that the increased number of tracked dropped targets may result in increased memory usage (default 10000)
   -promscrape.maxResponseHeadersSize size
      The maximum size of http response headers from Prometheus scrape targets
      Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB (default 4096)
@@ -2998,7 +3037,7 @@ Pass `-help` to VictoriaMetrics in order to see the list of supported command-li
   -relabelConfig string
      Optional path to a file with relabeling rules, which are applied to all the ingested metrics. The path can point either to local file or to http url. See https://docs.victoriametrics.com/#relabeling for details. The config is reloaded on SIGHUP signal
   -reloadAuthKey value
-     Auth key for /-/reload http endpoint. It must be passed as authKey=...
+     Auth key for /-/reload http endpoint. It must be passed via authKey query arg. It overrides httpAuth.* settings.
      Flag value can be read from the given file when using -reloadAuthKey=file:///abs/path/to/file or -reloadAuthKey=file://./relative/path/to/file . Flag value can be read from the given http/https url when using -reloadAuthKey=http://host/path or -reloadAuthKey=https://host/path
   -retentionFilter array
      Retention filter in the format 'filter:retention'. For example, '{env="dev"}:3d' configures the retention for time series with env="dev" label to 3 days. See https://docs.victoriametrics.com/#retention-filters for details. This flag is available only in VictoriaMetrics enterprise. See https://docs.victoriametrics.com/enterprise/
@@ -3015,14 +3054,18 @@ Pass `-help` to VictoriaMetrics in order to see the list of supported command-li
      Whether to disable automatic response cache reset if a sample with timestamp outside -search.cacheTimestampOffset is inserted into VictoriaMetrics
   -search.disableCache
      Whether to disable response caching. This may be useful when ingesting historical data. See https://docs.victoriametrics.com/#backfilling . See also -search.resetRollupResultCacheOnStartup
+  -search.disableImplicitConversion
+     Whether to return an error for queries that rely on implicit subquery conversions, see https://docs.victoriametrics.com/metricsql/#subqueries for details. See also -search.logImplicitConversion
   -search.graphiteMaxPointsPerSeries int
      The maximum number of points per series Graphite render API can return (default 1000000)
   -search.graphiteStorageStep duration
      The interval between datapoints stored in the database. It is used at Graphite Render API handler for normalizing the interval between datapoints in case it isn't normalized. It can be overridden by sending 'storage_step' query arg to /render API or by sending the desired interval via 'Storage-Step' http header during querying /render API (default 10s)
   -search.ignoreExtraFiltersAtLabelsAPI
-     Whether to ignore match[], extra_filters[] and extra_label query args at /api/v1/labels and /api/v1/label/.../values . This may be useful for decreasing load on VictoriaMetrics when extra filters match too many time series. The downside is that suprflouos labels or series could be returned, which do not match the extra filters. See also -search.maxLabelsAPISeries and -search.maxLabelsAPIDuration
+     Whether to ignore match[], extra_filters[] and extra_label query args at /api/v1/labels and /api/v1/label/.../values . This may be useful for decreasing load on VictoriaMetrics when extra filters match too many time series. The downside is that superfluous labels or series could be returned, which do not match the extra filters. See also -search.maxLabelsAPISeries and -search.maxLabelsAPIDuration
   -search.latencyOffset duration
      The time when data points become visible in query results after the collection. It can be overridden on per-query basis via latency_offset arg. Too small value can result in incomplete last points for query results (default 30s)
+  -search.logImplicitConversion
+     Whether to log queries with implicit subquery conversions, see https://docs.victoriametrics.com/metricsql/#subqueries for details. Such conversion can be disabled using -search.disableImplicitConversion
   -search.logQueryMemoryUsage size
      Log query and increment vm_memory_intensive_queries_total metric each time the query requires more memory than specified by this flag. This may help detecting and optimizing heavy queries. Query logging is disabled by default. See also -search.logSlowQueryDuration and -search.maxMemoryPerQuery
      Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB (default 0)
@@ -3045,7 +3088,7 @@ Pass `-help` to VictoriaMetrics in order to see the list of supported command-li
   -search.maxLabelsAPIDuration duration
      The maximum duration for /api/v1/labels, /api/v1/label/.../values and /api/v1/series requests. See also -search.maxLabelsAPISeries and -search.ignoreExtraFiltersAtLabelsAPI (default 5s)
   -search.maxLabelsAPISeries int
-     The maximum number of time series, which could be scanned when searching for the the matching time series at /api/v1/labels and /api/v1/label/.../values. This option allows limiting memory usage and CPU usage. See also -search.maxLabelsAPIDuration, -search.maxTagKeys, -search.maxTagValues and -search.ignoreExtraFiltersAtLabelsAPI (default 1000000)
+     The maximum number of time series, which could be scanned when searching for the matching time series at /api/v1/labels and /api/v1/label/.../values. This option allows limiting memory usage and CPU usage. See also -search.maxLabelsAPIDuration, -search.maxTagKeys, -search.maxTagValues and -search.ignoreExtraFiltersAtLabelsAPI (default 1000000)
   -search.maxLookback duration
      Synonym to -search.lookback-delta from Prometheus. The value is dynamically detected from interval between time series datapoints if not set. It can be overridden on per-query basis via max_lookback arg. See also '-search.maxStalenessInterval' flag, which has the same meaning due to historical reasons
   -search.maxMemoryPerQuery size
@@ -3056,7 +3099,7 @@ Pass `-help` to VictoriaMetrics in order to see the list of supported command-li
   -search.maxPointsSubqueryPerTimeseries int
      The maximum number of points per series, which can be generated by subquery. See https://valyala.medium.com/prometheus-subqueries-in-victoriametrics-9b1492b720b3 (default 100000)
   -search.maxQueryDuration duration
-     The maximum duration for query execution (default 30s)
+     The maximum duration for query execution. It can be overridden on a per-query basis via 'timeout' query arg (default 30s)
   -search.maxQueryLen size
      The maximum search query length in bytes
      Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB (default 16384)

app/victoria-logs/Makefile

@@ -101,3 +101,10 @@ 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/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

@@ -1,7 +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/Makefile

@@ -88,6 +88,9 @@ 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/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/vlinsert/elasticsearch/elasticsearch.go

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

app/vlinsert/elasticsearch/elasticsearch_test.go

@@ -4,23 +4,18 @@ import (
 	"bytes"
 	"compress/gzip"
 	"fmt"
-	"reflect"
-	"strings"
 	"testing"
 
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vlinsert/insertutils"
 )
 
-func TestReadBulkRequestFailure(t *testing.T) {
+func TestReadBulkRequest_Failure(t *testing.T) {
 	f := func(data string) {
 		t.Helper()
 
-		processLogMessage := func(timestamp int64, fields []logstorage.Field) {
-			t.Fatalf("unexpected call to processLogMessage with timestamp=%d, fields=%s", timestamp, fields)
-		}
-
+		tlp := &insertutils.TestLogMessageProcessor{}
 		r := bytes.NewBufferString(data)
-		rows, err := readBulkRequest(r, false, "_time", "_msg", processLogMessage)
+		rows, err := readBulkRequest(r, false, "_time", "_msg", tlp)
 		if err == nil {
 			t.Fatalf("expecting non-empty error")
 		}
@@ -37,58 +32,38 @@ func TestReadBulkRequestFailure(t *testing.T) {
 foobar`)
 }
 
-func TestReadBulkRequestSuccess(t *testing.T) {
+func TestReadBulkRequest_Success(t *testing.T) {
 	f := func(data, timeField, msgField string, rowsExpected int, timestampsExpected []int64, resultExpected string) {
 		t.Helper()
 
-		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
-		}
+		tlp := &insertutils.TestLogMessageProcessor{}
 
 		// Read the request without compression
 		r := bytes.NewBufferString(data)
-		rows, err := readBulkRequest(r, false, timeField, msgField, processLogMessage)
+		rows, err := readBulkRequest(r, false, timeField, msgField, tlp)
 		if err != nil {
 			t.Fatalf("unexpected error: %s", err)
 		}
 		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)
+		if err := tlp.Verify(rowsExpected, timestampsExpected, resultExpected); err != nil {
+			t.Fatal(err)
 		}
 
 		// Read the request with compression
-		timestamps = nil
-		result = ""
+		tlp = &insertutils.TestLogMessageProcessor{}
 		compressedData := compressData(data)
 		r = bytes.NewBufferString(compressedData)
-		rows, err = readBulkRequest(r, true, timeField, msgField, processLogMessage)
+		rows, err = readBulkRequest(r, true, timeField, msgField, tlp)
 		if err != nil {
 			t.Fatalf("unexpected error: %s", err)
 		}
 		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)
+		if err := tlp.Verify(rowsExpected, timestampsExpected, resultExpected); err != nil {
+			t.Fatalf("verification failure after compression: %s", err)
 		}
 	}
 
@@ -111,8 +86,7 @@ func TestReadBulkRequestSuccess(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"
-	processLogMessage := func(_ int64, _ []logstorage.Field) {}
+	blp := &insertutils.BenchmarkLogMessageProcessor{}
 
 	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, processLogMessage)
+			_, err := readBulkRequest(r, isGzip, timeField, msgField, blp)
 			if err != nil {
 				panic(fmt.Errorf("unexpected error: %w", err))
 			}

app/vlinsert/insertutils/common_params.go

@@ -2,6 +2,8 @@ package insertutils
 
 import (
 	"net/http"
+	"sync"
+	"time"
 
 	"github.com/VictoriaMetrics/metrics"
 
@@ -10,11 +12,12 @@ 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
@@ -71,29 +74,126 @@ func GetCommonParams(r *http.Request) (*CommonParams, error) {
 	return cp, nil
 }
 
-// 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
-		}
-
-		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()
-		}
+// 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()
+			}
+		}
+	}()
+}
+
+// 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
+	}
+
+	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

@@ -0,0 +1,53 @@
+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

@@ -0,0 +1,33 @@
+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

@@ -0,0 +1,75 @@
+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

@@ -4,6 +4,7 @@ import (
 	"bufio"
 	"errors"
 	"fmt"
+	"io"
 	"net/http"
 	"time"
 
@@ -12,7 +13,6 @@ 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) bool {
+func RequestHandler(w http.ResponseWriter, r *http.Request) {
 	startTime := time.Now()
 	w.Header().Add("Content-Type", "application/json")
 
 	if r.Method != "POST" {
 		w.WriteHeader(http.StatusMethodNotAllowed)
-		return true
+		return
 	}
 
 	requestsTotal.Inc()
@@ -34,27 +34,40 @@ func RequestHandler(w http.ResponseWriter, r *http.Request) bool {
 	cp, err := insertutils.GetCommonParams(r)
 	if err != nil {
 		httpserver.Errorf(w, r, "%s", err)
-		return true
+		return
 	}
 	if err := vlstorage.CanWriteData(); err != nil {
 		httpserver.Errorf(w, r, "%s", err)
-		return true
+		return
 	}
-	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 _bulk request: %s", err)
-			return true
+			logger.Errorf("cannot read gzipped jsonline request: %s", err)
+			return
 		}
 		defer common.PutGzipReader(zr)
 		reader = zr
 	}
 
-	wcr := writeconcurrencylimiter.GetReader(reader)
+	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)
 	defer writeconcurrencylimiter.PutReader(wcr)
 
 	lb := lineBufferPool.Get()
@@ -66,31 +79,21 @@ func RequestHandler(w http.ResponseWriter, r *http.Request) bool {
 
 	n := 0
 	for {
-		ok, err := readLine(sc, cp.TimeField, cp.MsgField, processLogMessage)
+		ok, err := readLine(sc, timeField, msgField, lmp)
 		wcr.DecConcurrency()
 		if err != nil {
-			logger.Errorf("cannot read line #%d in /jsonline request: %s", n, err)
-			break
+			errorsTotal.Inc()
+			return fmt.Errorf("cannot read line #%d in /jsonline request: %s", n, err)
 		}
 		if !ok {
-			break
+			return nil
 		}
 		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, processLogMessage func(timestamp int64, fields []logstorage.Field)) (bool, error) {
+func readLine(sc *bufio.Scanner, timeField, msgField string, lmp insertutils.LogMessageProcessor) (bool, error) {
 	var line []byte
 	for len(line) == 0 {
 		if !sc.Scan() {
@@ -105,57 +108,28 @@ func readLine(sc *bufio.Scanner, timeField, msgField string, processLogMessage f
 		line = sc.Bytes()
 	}
 
-	p := logjson.GetParser()
+	p := logstorage.GetJSONParser()
 	if err := p.ParseLogMessage(line); err != nil {
 		return false, fmt.Errorf("cannot parse json-encoded log entry: %w", err)
 	}
-	ts, err := extractTimestampFromFields(timeField, p.Fields)
+	ts, err := insertutils.ExtractTimestampRFC3339NanoFromFields(timeField, p.Fields)
 	if err != nil {
-		return false, fmt.Errorf("cannot parse timestamp: %w", err)
+		return false, fmt.Errorf("cannot get timestamp: %w", err)
 	}
-	if ts == 0 {
-		ts = time.Now().UnixNano()
-	}
-	p.RenameField(msgField, "_msg")
-	processLogMessage(ts, p.Fields)
-	logjson.PutParser(p)
+	logstorage.RenameField(p.Fields, msgField, "_msg")
+	lmp.AddRow(ts, p.Fields)
+	logstorage.PutJSONParser(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 (
-	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"}`)
+	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"}`)
 )

app/vlinsert/jsonline/jsonline_test.go

@@ -1,59 +1,27 @@
 package jsonline
 
 import (
-	"bufio"
 	"bytes"
-	"fmt"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
-	"reflect"
-	"strings"
 	"testing"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vlinsert/insertutils"
 )
 
-func TestReadBulkRequestSuccess(t *testing.T) {
+func TestProcessStreamInternal_Success(t *testing.T) {
 	f := func(data, timeField, msgField string, rowsExpected int, timestampsExpected []int64, resultExpected string) {
 		t.Helper()
 
-		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
+		tlp := &insertutils.TestLogMessageProcessor{}
 		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 err := processStreamInternal(r, timeField, msgField, tlp); err != nil {
+			t.Fatalf("unexpected error: %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)
+		if err := tlp.Verify(rowsExpected, timestampsExpected, resultExpected); err != nil {
+			t.Fatal(err)
 		}
 	}
 
-	// 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"}
@@ -64,7 +32,24 @@ func TestReadBulkRequestSuccess(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

@@ -11,7 +11,8 @@ import (
 func RequestHandler(path string, w http.ResponseWriter, r *http.Request) bool {
 	switch path {
 	case "/api/v1/push":
-		return handleInsert(r, w)
+		handleInsert(r, w)
+		return true
 	case "/ready":
 		// See https://grafana.com/docs/loki/latest/api/#identify-ready-loki-instance
 		w.WriteHeader(http.StatusOK)
@@ -23,14 +24,14 @@ 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) bool {
+func handleInsert(r *http.Request, w http.ResponseWriter) {
 	contentType := r.Header.Get("Content-Type")
 	switch contentType {
 	case "application/json":
-		return handleJSON(r, w)
+		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
-		return handleProtobuf(r, w)
+		handleProtobuf(r, w)
 	}
 }
 
@@ -45,7 +46,7 @@ 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.GetTenantIDFromString(org)
+			tenantID, err := logstorage.ParseTenantID(org)
 			if err != nil {
 				return nil, err
 			}

app/vlinsert/loki/loki_json.go

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

app/vlinsert/loki/loki_json_test.go

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

app/vlinsert/loki/loki_json_timing_test.go

@@ -6,7 +6,7 @@ import (
 	"testing"
 	"time"
 
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vlinsert/insertutils"
 )
 
 func BenchmarkParseJSONRequest(b *testing.B) {
@@ -22,12 +22,13 @@ 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, func(_ int64, _ []logstorage.Field) {})
+			_, err := parseJSONRequest(data, blp)
 			if err != nil {
 				panic(fmt.Errorf("unexpected error: %w", err))
 			}

app/vlinsert/loki/loki_protobuf.go

@@ -9,6 +9,7 @@ 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"
@@ -23,53 +24,49 @@ var (
 	pushReqsPool sync.Pool
 )
 
-func handleProtobuf(r *http.Request, w http.ResponseWriter) bool {
+func handleProtobuf(r *http.Request, w http.ResponseWriter) {
 	startTime := time.Now()
-	lokiRequestsProtobufTotal.Inc()
+	requestsProtobufTotal.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 true
+		return
 	}
 
 	cp, err := getCommonParams(r)
 	if err != nil {
 		httpserver.Errorf(w, r, "cannot parse common params from request: %s", err)
-		return true
+		return
 	}
 	if err := vlstorage.CanWriteData(); err != nil {
 		httpserver.Errorf(w, r, "%s", err)
-		return true
+		return
 	}
-	lr := logstorage.GetLogRows(cp.StreamFields, cp.IgnoreFields)
-	processLogMessage := cp.GetProcessLogMessageFunc(lr)
-	n, err := parseProtobufRequest(data, processLogMessage)
-	vlstorage.MustAddRows(lr)
-	logstorage.PutLogRows(lr)
+	lmp := cp.NewLogMessageProcessor()
+	n, err := parseProtobufRequest(data, lmp)
+	lmp.MustClose()
 	if err != nil {
 		httpserver.Errorf(w, r, "cannot parse Loki protobuf request: %s", err)
-		return true
+		return
 	}
 
 	rowsIngestedProtobufTotal.Add(n)
 
-	// update lokiRequestProtobufDuration only for successfully parsed requests
-	// There is no need in updating lokiRequestProtobufDuration for request errors,
+	// update requestProtobufDuration only for successfully parsed requests
+	// There is no need in updating requestProtobufDuration for request errors,
 	// since their timings are usually much smaller than the timing for successful request parsing.
-	lokiRequestProtobufDuration.UpdateDuration(startTime)
-
-	return true
+	requestProtobufDuration.UpdateDuration(startTime)
 }
 
 var (
-	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"}`)
+	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"}`)
 )
 
-func parseProtobufRequest(data []byte, processLogMessage func(timestamp int64, fields []logstorage.Field)) (int, error) {
+func parseProtobufRequest(data []byte, lmp insertutils.LogMessageProcessor) (int, error) {
 	bb := bytesBufPool.Get()
 	defer bytesBufPool.Put(bb)
 
@@ -112,7 +109,7 @@ func parseProtobufRequest(data []byte, processLogMessage func(timestamp int64, f
 			if ts == 0 {
 				ts = currentTimestamp
 			}
-			processLogMessage(ts, fields)
+			lmp.AddRow(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"
 )
 
-func TestParseProtobufRequestSuccess(t *testing.T) {
-	f := func(s string, resultExpected string) {
+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) {
 		t.Helper()
-		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,
-					},
-				},
-			})
-		})
+
+		tlp := &testLogMessageProcessor{}
+		n, err := parseJSONRequest([]byte(s), tlp)
 		if err != nil {
 			t.Fatalf("unexpected error: %s", err)
 		}
-		if n != len(pr.Streams) {
-			t.Fatalf("unexpected number of streams; got %d; want %d", len(pr.Streams), n)
+		if n != len(tlp.pr.Streams) {
+			t.Fatalf("unexpected number of streams; got %d; want %d", len(tlp.pr.Streams), n)
 		}
 
-		data, err := pr.Marshal()
+		data, err := tlp.pr.Marshal()
 		if err != nil {
 			t.Fatalf("unexpected error when marshaling PushRequest: %s", err)
 		}
 		encodedData := snappy.Encode(nil, data)
 
-		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)
-		})
+		tlp2 := &insertutils.TestLogMessageProcessor{}
+		n, err = parseProtobufRequest(encodedData, tlp2)
 		if err != nil {
 			t.Fatalf("unexpected error: %s", 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)
+		if err := tlp2.Verify(n, timestampsExpected, resultExpected); err != nil {
+			t.Fatal(err)
 		}
 	}
 
 	// Empty streams
-	f(`{"streams":[]}`, ``)
-	f(`{"streams":[{"values":[]}]}`, ``)
-	f(`{"streams":[{"stream":{},"values":[]}]}`, ``)
-	f(`{"streams":[{"stream":{"foo":"bar"},"values":[]}]}`, ``)
+	f(`{"streams":[]}`, nil, ``)
+	f(`{"streams":[{"values":[]}]}`, nil, ``)
+	f(`{"streams":[{"stream":{},"values":[]}]}`, nil, ``)
+	f(`{"streams":[{"stream":{"foo":"bar"},"values":[]}]}`, nil, ``)
 
 	// Empty stream labels
-	f(`{"streams":[{"values":[["1577836800000000001", "foo bar"]]}]}`, `_time:1577836800000000001 "_msg":"foo bar"`)
-	f(`{"streams":[{"stream":{},"values":[["1577836800000000001", "foo bar"]]}]}`, `_time:1577836800000000001 "_msg":"foo bar"`)
+	f(`{"streams":[{"values":[["1577836800000000001", "foo bar"]]}]}`, []int64{1577836800000000001}, `{"_msg":"foo bar"}`)
+	f(`{"streams":[{"stream":{},"values":[["1577836800000000001", "foo bar"]]}]}`, []int64{1577836800000000001}, `{"_msg":"foo bar"}`)
 
 	// Non-empty stream labels
 	f(`{"streams":[{"stream":{
@@ -92,9 +92,9 @@ func TestParseProtobufRequestSuccess(t *testing.T) {
 	["1577836800000000001", "foo bar"],
 	["1477836900005000002", "abc"],
 	["147.78369e9", "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"`)
+]}]}`, []int64{1577836800000000001, 1477836900005000002, 147783690000}, `{"label1":"value1","label2":"value2","_msg":"foo bar"}
+{"label1":"value1","label2":"value2","_msg":"abc"}
+{"label1":"value1","label2":"value2","_msg":"foobar"}`)
 
 	// Multiple streams
 	f(`{
@@ -118,12 +118,12 @@ _time:147783690000 "label1":"value1" "label2":"value2" "_msg":"foobar"`)
 			]
 		}
 	]
-}`, `_time:1577836800000000001 "foo":"bar" "a":"b" "_msg":"foo bar"
-_time:1577836900005000002 "foo":"bar" "a":"b" "_msg":"abc"
-_time:1877836900005000002 "x":"y" "_msg":"yx"`)
+}`, []int64{1577836800000000001, 1577836900005000002, 1877836900005000002}, `{"foo":"bar","a":"b","_msg":"foo bar"}
+{"foo":"bar","a":"b","_msg":"abc"}
+{"x":"y","_msg":"yx"}`)
 }
 
-func TestParsePromLabelsSuccess(t *testing.T) {
+func TestParsePromLabels_Success(t *testing.T) {
 	f := func(s string) {
 		t.Helper()
 		fields, err := parsePromLabels(nil, s)
@@ -147,7 +147,7 @@ func TestParsePromLabelsSuccess(t *testing.T) {
 	f(`{foo="ba\"r\\z\n", a="", b="\"\\"}`)
 }
 
-func TestParsePromLabelsFailure(t *testing.T) {
+func TestParsePromLabels_Failure(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/lib/logstorage"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vlinsert/insertutils"
 )
 
 func BenchmarkParseProtobufRequest(b *testing.B) {
@@ -24,12 +24,13 @@ 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, func(_ int64, _ []logstorage.Field) {})
+			_, err := parseProtobufRequest(body, blp)
 			if err != nil {
 				panic(fmt.Errorf("unexpected error: %w", err))
 			}

app/vlinsert/main.go

@@ -7,14 +7,17 @@ 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
@@ -28,7 +31,8 @@ func RequestHandler(w http.ResponseWriter, r *http.Request) bool {
 	path = strings.ReplaceAll(path, "//", "/")
 
 	if path == "/jsonline" {
-		return jsonline.RequestHandler(w, r)
+		jsonline.RequestHandler(w, r)
+		return true
 	}
 	switch {
 	case strings.HasPrefix(path, "/elasticsearch/"):

app/vlinsert/syslog/syslog.go

@@ -0,0 +1,531 @@
+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

@@ -0,0 +1,130 @@
+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

@@ -0,0 +1,7 @@
+# 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

@@ -0,0 +1,158 @@
+# 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

@@ -0,0 +1,344 @@
+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

@@ -0,0 +1,47 @@
+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

@@ -0,0 +1,70 @@
+{% 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

@@ -0,0 +1,223 @@
+// 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

@@ -1,66 +1,770 @@
 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"
 )
 
-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)
+// 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
 	}
 
-	qStr := r.FormValue("query")
-	q, err := logstorage.ParseQuery(qStr)
-	if err != nil {
-		httpserver.Errorf(w, r, "cannot parse query [%s]: %s", qStr, err)
-		return
-	}
-	w.Header().Set("Content-Type", "application/stream+json; charset=utf-8")
+	bw := getBufferedWriter(w)
+	defer func() {
+		bw.FlushIgnoreErrors()
+		putBufferedWriter(bw)
+	}()
+	w.Header().Set("Content-Type", "application/stream+json")
 
-	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 {
+	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
 		}
-		rowsCount := len(columns[0].Values)
 
 		bb := blockResultPool.Get()
-		for rowIdx := 0; rowIdx < rowsCount; rowIdx++ {
-			WriteJSONRow(bb, columns, rowIdx)
+		for i := range timestamps {
+			WriteJSONRow(bb, columns, i)
 		}
-
-		if !sw.TryWrite(bb.B) {
-			cancel()
-		}
-
+		bw.WriteIgnoreErrors(bb.B)
 		blockResultPool.Put(bb)
-	})
-	sw.FinalFlush()
-	putSortWriter(sw)
+	}
+
+	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) {
+	// Extract tenantID
+	tenantID, err := logstorage.GetTenantIDFromRequest(r)
+	if err != nil {
+		return nil, nil, fmt.Errorf("cannot obtain tenanID: %w", err)
+	}
+	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)
+	}
+
+	// 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
+		}
+		if !okEnd {
+			end = math.MaxInt64
+		}
+		q.AddTimeFilter(start, end)
+	}
+
+	return q, tenantIDs, nil
+}
+
+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
+}

app/vlselect/logsql/logsql.qtpl

@@ -0,0 +1,32 @@
+{% 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

@@ -0,0 +1,152 @@
+// 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

@@ -1,290 +0,0 @@
-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)
-		sw.linesWritten += linesLeft
-	}
-	if _, err := sw.w.Write(p); err != nil {
-		return false
-	}
-	return true
-}
-
-func trimLines(p []byte, maxLines int) ([]byte, int) {
-	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

@@ -1,46 +0,0 @@
-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

@@ -14,7 +14,6 @@ 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"
 )
 
@@ -24,7 +23,7 @@ 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")
+	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")
 )
 
 func getDefaultMaxConcurrentRequests() int {
@@ -76,10 +75,9 @@ 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 == "/vmui" {
+	if path == "/select/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.
@@ -88,68 +86,128 @@ func RequestHandler(w http.ResponseWriter, r *http.Request) bool {
 		httpserver.Redirect(w, newURL)
 		return true
 	}
-	if strings.HasPrefix(path, "/vmui/") {
-		if strings.HasPrefix(path, "/vmui/static/") {
+	if strings.HasPrefix(path, "/select/vmui/") {
+		if strings.HasPrefix(path, "/select/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 = path
+		r.URL.Path = strings.TrimPrefix(path, "/select")
 		vmuiFileServer.ServeHTTP(w, r)
 		return true
 	}
 
-	// Limit the number of concurrent queries, which can consume big amounts of CPU.
+	// Limit the number of concurrent queries, which can consume big amounts of CPU time.
 	startTime := time.Now()
 	ctx := r.Context()
-	stopCh := ctx.Done()
+	d := getMaxQueryDuration(r)
+	ctxWithTimeout, cancel := context.WithTimeout(ctx, d)
+	defer cancel()
+
+	stopCh := ctxWithTimeout.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:
-			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,
+			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)
 			}
-			httpserver.Errorf(w, r, "%s", err)
 			return true
 		}
 	}
 
-	ctxWithCancel, cancel := context.WithCancel(ctx)
-	defer cancel()
-	stopCh = ctxWithCancel.Done()
+	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
+	}
 
-	switch {
-	case path == "/logsql/query":
+	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":
 		logsqlQueryRequests.Inc()
-		httpserver.EnableCORS(w, r)
-		logsql.ProcessQueryRequest(w, r, stopCh, cancel)
+		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)
 		return true
 	default:
 		return false
@@ -170,5 +228,13 @@ func getMaxQueryDuration(r *http.Request) time.Duration {
 }
 
 var (
-	logsqlQueryRequests = metrics.NewCounter(`vl_http_requests_total{path="/select/logsql/query"}`)
+	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"}`)
 )

app/vlselect/vmui/asset-manifest.json

@@ -1,13 +1,13 @@
 {
   "files": {
-    "main.css": "./static/css/main.bc07cc78.css",
-    "main.js": "./static/js/main.8e7757ef.js",
+    "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.da86c2db4f0b05e286b0.md",
+    "static/media/MetricsQL.md": "./static/media/MetricsQL.aaabf95f2c9bf356bde4.md",
     "index.html": "./index.html"
   },
   "entrypoints": [
-    "static/css/main.bc07cc78.css",
-    "static/js/main.8e7757ef.js"
+    "static/css/main.1041c3d4.css",
+    "static/js/main.8988988c.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.8e7757ef.js"></script><link href="./static/css/main.bc07cc78.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.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>

app/vlselect/vmui/static/js/main.8988988c.js.LICENSE.txt

@@ -0,0 +1,38 @@
+/*!
+	Copyright (c) 2018 Jed Watson.
+	Licensed under the MIT License (MIT), see
+	http://jedwatson.github.io/classnames
+*/
+
+/**
+ * @remix-run/router v1.17.0
+ *
+ * Copyright (c) Remix Software Inc.
+ *
+ * This source code is licensed under the MIT license found in the
+ * LICENSE.md file in the root directory of this source tree.
+ *
+ * @license MIT
+ */
+
+/**
+ * React Router DOM v6.24.0
+ *
+ * Copyright (c) Remix Software Inc.
+ *
+ * This source code is licensed under the MIT license found in the
+ * LICENSE.md file in the root directory of this source tree.
+ *
+ * @license MIT
+ */
+
+/**
+ * React Router v6.24.0
+ *
+ * Copyright (c) Remix Software Inc.
+ *
+ * This source code is licensed under the MIT license found in the
+ * LICENSE.md file in the root directory of this source tree.
+ *
+ * @license MIT
+ */

app/vlselect/vmui/static/media/MetricsQL.aaabf95f2c9bf356bde4.md

@@ -79,6 +79,8 @@ The list of MetricsQL features on top of PromQL:
 * [Series selectors](https://docs.victoriametrics.com/keyconcepts/#filtering) accept multiple `or` filters. For example, `{env="prod",job="a" or env="dev",job="b"}`
   selects series with `{env="prod",job="a"}` or `{env="dev",job="b"}` labels.
   See [these docs](https://docs.victoriametrics.com/keyconcepts/#filtering-by-multiple-or-filters) for details.
+* Support for matching against multiple numeric constants via `q == (C1, ..., CN)` and `q != (C1, ..., CN)` syntax. For example, `status_code == (300, 301, 304)`
+  returns `status_code` metrics with one of `300`, `301` or `304` values.
 * Support for `group_left(*)` and `group_right(*)` for copying all the labels from time series on the `one` side
   of [many-to-one operations](https://prometheus.io/docs/prometheus/latest/querying/operators/#many-to-one-and-one-to-many-vector-matches).
   The copied label names may clash with the existing label names, so MetricsQL provides an ability to add prefix to the copied metric names
@@ -105,7 +107,7 @@ The list of MetricsQL features on top of PromQL:
 * Trailing commas on all the lists are allowed - label filters, function args and with expressions.
   For instance, the following queries are valid: `m{foo="bar",}`, `f(a, b,)`, `WITH (x=y,) x`.
   This simplifies maintenance of multi-line queries.
-* Metric names and label names may contain any unicode letter. For example `температура{город="Київ"}` is a value MetricsQL expression.
+* Metric names and label names may contain any unicode letter. For example `температура{город="Київ"}` is a valid MetricsQL expression.
 * Metric names and labels names may contain escaped chars. For example, `foo\-bar{baz\=aa="b"}` is valid expression.
   It returns time series with name `foo-bar` containing label `baz=aa` with value `b`.
   Additionally, the following escape sequences are supported:
@@ -152,9 +154,9 @@ MetricsQL provides the following functions:
 
 ### Rollup functions
 
-**Rollup functions** (aka range functions or window functions) calculate rollups over **raw samples**
+**Rollup functions** (aka range functions or window functions) calculate rollups over [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
 on the given lookbehind window for the [selected time series](https://docs.victoriametrics.com/keyconcepts/#filtering).
-For example, `avg_over_time(temperature[24h])` calculates the average temperature over raw samples for the last 24 hours.
+For example, `avg_over_time(temperature[24h])` calculates the average temperature over [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples) for the last 24 hours.
 
 Additional details:
 
@@ -184,7 +186,7 @@ The list of supported rollup functions:
 #### absent_over_time
 
 `absent_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which returns 1
-if the given lookbehind window `d` doesn't contain raw samples. Otherwise, it returns an empty result.
+if the given lookbehind window `d` doesn't contain [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples). Otherwise, it returns an empty result.
 
 This function is supported by PromQL.
 
@@ -193,7 +195,7 @@ See also [present_over_time](#present_over_time).
 #### aggr_over_time
 
 `aggr_over_time(("rollup_func1", "rollup_func2", ...), series_selector[d])` is a [rollup function](#rollup-functions),
-which calculates all the listed `rollup_func*` for raw samples on the given lookbehind window `d`.
+which calculates all the listed `rollup_func*` for [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples) on the given lookbehind window `d`.
 The calculations are performed individually per each time series returned
 from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
@@ -203,7 +205,7 @@ would calculate [min_over_time](#min_over_time), [max_over_time](#max_over_time)
 #### ascent_over_time
 
 `ascent_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which calculates
-ascent of raw sample values on the given lookbehind window `d`. The calculations are performed individually
+ascent of [raw sample](https://docs.victoriametrics.com/keyconcepts/#raw-samples) values on the given lookbehind window `d`. The calculations are performed individually
 per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
 This function is useful for tracking height gains in GPS tracking. Metric names are stripped from the resulting rollups.
@@ -215,7 +217,7 @@ See also [descent_over_time](#descent_over_time).
 #### avg_over_time
 
 `avg_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which calculates the average value
-over raw samples on the given lookbehind window `d` per each time series returned
+over [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples) on the given lookbehind window `d` per each time series returned
 from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
 This function is supported by PromQL.
@@ -225,7 +227,7 @@ See also [median_over_time](#median_over_time).
 #### changes
 
 `changes(series_selector[d])` is a [rollup function](#rollup-functions), which calculates the number of times
-the raw samples changed on the given lookbehind window `d` per each time series returned
+the [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples) changed on the given lookbehind window `d` per each time series returned
 from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
 Unlike `changes()` in Prometheus it takes into account the change from the last sample before the given lookbehind window `d`.
@@ -240,7 +242,7 @@ See also [changes_prometheus](#changes_prometheus).
 #### changes_prometheus
 
 `changes_prometheus(series_selector[d])` is a [rollup function](#rollup-functions), which calculates the number of times
-the raw samples changed on the given lookbehind window `d` per each time series returned
+the [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples) changed on the given lookbehind window `d` per each time series returned
 from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
 It doesn't take into account the change from the last sample before the given lookbehind window `d` in the same way as Prometheus does.
@@ -254,7 +256,7 @@ See also [changes](#changes).
 
 #### count_eq_over_time
 
-`count_eq_over_time(series_selector[d], eq)` is a [rollup function](#rollup-functions), which calculates the number of raw samples
+`count_eq_over_time(series_selector[d], eq)` is a [rollup function](#rollup-functions), which calculates the number of [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
 on the given lookbehind window `d`, which are equal to `eq`. It is calculated independently per each time series returned
 from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
@@ -264,7 +266,7 @@ See also [count_over_time](#count_over_time), [share_eq_over_time](#share_eq_ove
 
 #### count_gt_over_time
 
-`count_gt_over_time(series_selector[d], gt)` is a [rollup function](#rollup-functions), which calculates the number of raw samples
+`count_gt_over_time(series_selector[d], gt)` is a [rollup function](#rollup-functions), which calculates the number of [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
 on the given lookbehind window `d`, which are bigger than `gt`. It is calculated independently per each time series returned
 from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
@@ -274,7 +276,7 @@ See also [count_over_time](#count_over_time) and [share_gt_over_time](#share_gt_
 
 #### count_le_over_time
 
-`count_le_over_time(series_selector[d], le)` is a [rollup function](#rollup-functions), which calculates the number of raw samples
+`count_le_over_time(series_selector[d], le)` is a [rollup function](#rollup-functions), which calculates the number of [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
 on the given lookbehind window `d`, which don't exceed `le`. It is calculated independently per each time series returned
 from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
@@ -284,7 +286,7 @@ See also [count_over_time](#count_over_time) and [share_le_over_time](#share_le_
 
 #### count_ne_over_time
 
-`count_ne_over_time(series_selector[d], ne)` is a [rollup function](#rollup-functions), which calculates the number of raw samples
+`count_ne_over_time(series_selector[d], ne)` is a [rollup function](#rollup-functions), which calculates the number of [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
 on the given lookbehind window `d`, which aren't equal to `ne`. It is calculated independently per each time series returned
 from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
@@ -294,7 +296,7 @@ See also [count_over_time](#count_over_time).
 
 #### count_over_time
 
-`count_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which calculates the number of raw samples
+`count_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which calculates the number of [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
 on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
 Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
@@ -305,7 +307,7 @@ See also [count_le_over_time](#count_le_over_time), [count_gt_over_time](#count_
 
 #### count_values_over_time
 
-`count_values_over_time("label", series_selector[d])` is a [rollup function](#rollup-functions), which counts the number of raw samples
+`count_values_over_time("label", series_selector[d])` is a [rollup function](#rollup-functions), which counts the number of [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
 with the same value over the given lookbehind window and stores the counts in a time series with an additional `label`, which contains each initial value.
 The results are calculated independently per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
@@ -315,8 +317,8 @@ See also [count_eq_over_time](#count_eq_over_time), [count_values](#count_values
 
 #### decreases_over_time
 
-`decreases_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which calculates the number of raw sample value decreases
-over the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
+`decreases_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which calculates the number of [raw sample](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
+value decreases over the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
 Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
 
@@ -324,8 +326,9 @@ See also [increases_over_time](#increases_over_time).
 
 #### default_rollup
 
-`default_rollup(series_selector[d])` is a [rollup function](#rollup-functions), which returns the last raw sample value on the given lookbehind window `d`
-per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
+`default_rollup(series_selector[d])` is a [rollup function](#rollup-functions), which returns the last [raw sample](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
+value on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
+Compared to [last_over_time](#last_over_time) it accounts for [staleness markers](https://docs.victoriametrics.com/vmagent/#prometheus-staleness-markers) to detect stale series.
 
 If the lookbehind window is skipped in square brackets, then it is automatically calculated as `max(step, scrape_interval)`, where `step` is the query arg value
 passed to [/api/v1/query_range](https://docs.victoriametrics.com/keyconcepts/#range-query) or [/api/v1/query](https://docs.victoriametrics.com/keyconcepts/#instant-query),
@@ -375,7 +378,7 @@ See also [deriv_fast](#deriv_fast) and [ideriv](#ideriv).
 #### deriv_fast
 
 `deriv_fast(series_selector[d])` is a [rollup function](#rollup-functions), which calculates per-second derivative
-using the first and the last raw samples on the given lookbehind window `d` per each time series returned
+using the first and the last [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples) on the given lookbehind window `d` per each time series returned
 from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
 Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
@@ -384,8 +387,8 @@ See also [deriv](#deriv) and [ideriv](#ideriv).
 
 #### descent_over_time
 
-`descent_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which calculates descent of raw sample values
-on the given lookbehind window `d`. The calculations are performed individually per each time series returned
+`descent_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which calculates descent of [raw sample](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
+values on the given lookbehind window `d`. The calculations are performed individually per each time series returned
 from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
 This function is useful for tracking height loss in GPS tracking.
@@ -396,8 +399,8 @@ See also [ascent_over_time](#ascent_over_time).
 
 #### distinct_over_time
 
-`distinct_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which returns the number of distinct raw sample values
-on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
+`distinct_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which returns the number of unique [raw sample](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
+values on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
 Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
 
@@ -416,15 +419,15 @@ See also [lifetime](#lifetime) and [lag](#lag).
 
 #### first_over_time
 
-`first_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which returns the first raw sample value
-on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
+`first_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which returns the first [raw sample](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
+value on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
 See also [last_over_time](#last_over_time) and [tfirst_over_time](#tfirst_over_time).
 
 #### geomean_over_time
 
 `geomean_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which calculates [geometric mean](https://en.wikipedia.org/wiki/Geometric_mean)
-over raw samples on the given lookbehind window `d` per each time series returned
+over [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples) on the given lookbehind window `d` per each time series returned
 from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
 Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
@@ -432,8 +435,8 @@ Metric names are stripped from the resulting rollups. Add [keep_metric_names](#k
 #### histogram_over_time
 
 `histogram_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which calculates
-[VictoriaMetrics histogram](https://godoc.org/github.com/VictoriaMetrics/metrics#Histogram) over raw samples on the given lookbehind window `d`.
-It is calculated individually per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
+[VictoriaMetrics histogram](https://godoc.org/github.com/VictoriaMetrics/metrics#Histogram) over [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
+on the given lookbehind window `d`. It is calculated individually per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 The resulting histograms are useful to pass to [histogram_quantile](#histogram_quantile) for calculating quantiles
 over multiple [gauges](https://docs.victoriametrics.com/keyconcepts/#gauge).
 For example, the following query calculates median temperature by country over the last 24 hours:
@@ -457,7 +460,7 @@ See also [hoeffding_bound_lower](#hoeffding_bound_lower).
 #### holt_winters
 
 `holt_winters(series_selector[d], sf, tf)` is a [rollup function](#rollup-functions), which calculates Holt-Winters value
-(aka [double exponential smoothing](https://en.wikipedia.org/wiki/Exponential_smoothing#Double_exponential_smoothing)) for raw samples
+(aka [double exponential smoothing](https://en.wikipedia.org/wiki/Exponential_smoothing#Double_exponential_smoothing)) for [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
 over the given lookbehind window `d` using the given smoothing factor `sf` and the given trend factor `tf`.
 Both `sf` and `tf` must be in the range `[0...1]`. It is expected that the [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering)
 returns time series of [gauge type](https://docs.victoriametrics.com/keyconcepts/#gauge).
@@ -468,7 +471,7 @@ See also [range_linear_regression](#range_linear_regression).
 
 #### idelta
 
-`idelta(series_selector[d])` is a [rollup function](#rollup-functions), which calculates the difference between the last two raw samples
+`idelta(series_selector[d])` is a [rollup function](#rollup-functions), which calculates the difference between the last two [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
 on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
 Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
@@ -479,7 +482,8 @@ See also [delta](#delta).
 
 #### ideriv
 
-`ideriv(series_selector[d])` is a [rollup function](#rollup-functions), which calculates the per-second derivative based on the last two raw samples
+`ideriv(series_selector[d])` is a [rollup function](#rollup-functions), which calculates the per-second derivative based
+on the last two [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
 over the given lookbehind window `d`. The derivative is calculated independently per each time series returned
 from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
@@ -522,8 +526,8 @@ while [increase](#increase) ignores the first value in a series if it is too big
 
 #### increases_over_time
 
-`increases_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which calculates the number of raw sample value increases
-over the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
+`increases_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which calculates the number of [raw sample](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
+value increases over the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
 Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
 
@@ -531,14 +535,15 @@ See also [decreases_over_time](#decreases_over_time).
 
 #### integrate
 
-`integrate(series_selector[d])` is a [rollup function](#rollup-functions), which calculates the integral over raw samples on the given lookbehind window `d`
-per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
+`integrate(series_selector[d])` is a [rollup function](#rollup-functions), which calculates the integral over [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
+on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
 Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
 
 #### irate
 
-`irate(series_selector[d])` is a [rollup function](#rollup-functions), which calculates the "instant" per-second increase rate over the last two raw samples
+`irate(series_selector[d])` is a [rollup function](#rollup-functions), which calculates the "instant" per-second increase rate over
+the last two [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
 on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 It is expected that the `series_selector` returns time series of [counter type](https://docs.victoriametrics.com/keyconcepts/#counter).
 
@@ -560,8 +565,8 @@ See also [lifetime](#lifetime) and [duration_over_time](#duration_over_time).
 
 #### last_over_time
 
-`last_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which returns the last raw sample value on the given lookbehind window `d`
-per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
+`last_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which returns the last [raw sample](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
+value on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
 This function is supported by PromQL.
 
@@ -579,13 +584,14 @@ See also [duration_over_time](#duration_over_time) and [lag](#lag).
 #### mad_over_time
 
 `mad_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which calculates [median absolute deviation](https://en.wikipedia.org/wiki/Median_absolute_deviation)
-over raw samples on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
+over [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples) on the given lookbehind window `d` per each time series returned
+from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
 See also [mad](#mad), [range_mad](#range_mad) and [outlier_iqr_over_time](#outlier_iqr_over_time).
 
 #### max_over_time
 
-`max_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which calculates the maximum value over raw samples
+`max_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which calculates the maximum value over [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
 on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
 This function is supported by PromQL.
@@ -594,7 +600,7 @@ See also [tmax_over_time](#tmax_over_time).
 
 #### median_over_time
 
-`median_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which calculates median value over raw samples
+`median_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which calculates median value over [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
 on the given lookbehind window `d` per each time series returned
 from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
@@ -602,7 +608,7 @@ See also [avg_over_time](#avg_over_time).
 
 #### min_over_time
 
-`min_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which calculates the minimum value over raw samples
+`min_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which calculates the minimum value over [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
 on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
 This function is supported by PromQL.
@@ -612,15 +618,16 @@ See also [tmin_over_time](#tmin_over_time).
 #### mode_over_time
 
 `mode_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which calculates [mode](https://en.wikipedia.org/wiki/Mode_(statistics))
-for raw samples on the given lookbehind window `d`. It is calculated individually per each time series returned
-from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering). It is expected that raw sample values are discrete.
+for [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples) on the given lookbehind window `d`. It is calculated individually per each time series returned
+from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering). It is expected that [raw sample](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
+values are discrete.
 
 #### outlier_iqr_over_time
 
 `outlier_iqr_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which returns the last sample on the given lookbehind window `d`
 if its value is either smaller than the `q25-1.5*iqr` or bigger than `q75+1.5*iqr` where:
-- `iqr` is an [Interquartile range](https://en.wikipedia.org/wiki/Interquartile_range) over raw samples on the lookbehind window `d`
-- `q25` and `q75` are 25th and 75th [percentiles](https://en.wikipedia.org/wiki/Percentile) over raw samples on the lookbehind window `d`.
+- `iqr` is an [Interquartile range](https://en.wikipedia.org/wiki/Interquartile_range) over [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples) on the lookbehind window `d`
+- `q25` and `q75` are 25th and 75th [percentiles](https://en.wikipedia.org/wiki/Percentile) over [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples) on the lookbehind window `d`.
 
 The `outlier_iqr_over_time()` is useful for detecting anomalies in gauge values based on the previous history of values.
 For example, `outlier_iqr_over_time(memory_usage_bytes[1h])` triggers when `memory_usage_bytes` suddenly goes outside the usual value range for the last hour.
@@ -630,8 +637,8 @@ See also [outliers_iqr](#outliers_iqr).
 #### predict_linear
 
 `predict_linear(series_selector[d], t)` is a [rollup function](#rollup-functions), which calculates the value `t` seconds in the future using
-linear interpolation over raw samples on the given lookbehind window `d`. The predicted value is calculated individually per each time series
-returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
+linear interpolation over [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples) on the given lookbehind window `d`.
+The predicted value is calculated individually per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
 This function is supported by PromQL.
 
@@ -639,7 +646,7 @@ See also [range_linear_regression](#range_linear_regression).
 
 #### present_over_time
 
-`present_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which returns 1 if there is at least a single raw sample
+`present_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which returns 1 if there is at least a single [raw sample](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
 on the given lookbehind window `d`. Otherwise, an empty result is returned.
 
 Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
@@ -648,7 +655,7 @@ This function is supported by PromQL.
 
 #### quantile_over_time
 
-`quantile_over_time(phi, series_selector[d])` is a [rollup function](#rollup-functions), which calculates `phi`-quantile over raw samples
+`quantile_over_time(phi, series_selector[d])` is a [rollup function](#rollup-functions), which calculates `phi`-quantile over [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
 on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 The `phi` value must be in the range `[0...1]`.
 
@@ -659,7 +666,7 @@ See also [quantiles_over_time](#quantiles_over_time).
 #### quantiles_over_time
 
 `quantiles_over_time("phiLabel", phi1, ..., phiN, series_selector[d])` is a [rollup function](#rollup-functions), which calculates `phi*`-quantiles
-over raw samples on the given lookbehind window `d` per each time series returned
+over [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples) on the given lookbehind window `d` per each time series returned
 from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 The function returns individual series per each `phi*` with `{phiLabel="phi*"}` label. `phi*` values must be in the range `[0...1]`.
 
@@ -667,7 +674,7 @@ See also [quantile_over_time](#quantile_over_time).
 
 #### range_over_time
 
-`range_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which calculates value range over raw samples
+`range_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which calculates value range over [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
 on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 E.g. it calculates `max_over_time(series_selector[d]) - min_over_time(series_selector[d])`.
 
@@ -692,7 +699,7 @@ See also [irate](#irate) and [rollup_rate](#rollup_rate).
 
 #### rate_over_sum
 
-`rate_over_sum(series_selector[d])` is a [rollup function](#rollup-functions), which calculates per-second rate over the sum of raw samples
+`rate_over_sum(series_selector[d])` is a [rollup function](#rollup-functions), which calculates per-second rate over the sum of [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
 on the given lookbehind window `d`. The calculations are performed individually per each time series returned
 from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
@@ -711,7 +718,7 @@ This function is supported by PromQL.
 
 #### rollup
 
-`rollup(series_selector[d])` is a [rollup function](#rollup-functions), which calculates `min`, `max` and `avg` values for raw samples
+`rollup(series_selector[d])` is a [rollup function](#rollup-functions), which calculates `min`, `max` and `avg` values for [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
 on the given lookbehind window `d` and returns them in time series with `rollup="min"`, `rollup="max"` and `rollup="avg"` additional labels.
 These values are calculated individually per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
@@ -721,7 +728,8 @@ See also [label_match](#label_match).
 #### rollup_candlestick
 
 `rollup_candlestick(series_selector[d])` is a [rollup function](#rollup-functions), which calculates `open`, `high`, `low` and `close` values (aka OHLC)
-over raw samples on the given lookbehind window `d` and returns them in time series with `rollup="open"`, `rollup="high"`, `rollup="low"` and `rollup="close"` additional labels.
+over [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples) on the given lookbehind window `d` and returns them in time series
+with `rollup="open"`, `rollup="high"`, `rollup="low"` and `rollup="close"` additional labels.
 The calculations are performed individually per each time series returned
 from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering). This function is useful for financial applications.
 
@@ -730,7 +738,7 @@ See also [label_match](#label_match).
 
 #### rollup_delta
 
-`rollup_delta(series_selector[d])` is a [rollup function](#rollup-functions), which calculates differences between adjacent raw samples
+`rollup_delta(series_selector[d])` is a [rollup function](#rollup-functions), which calculates differences between adjacent [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
 on the given lookbehind window `d` and returns `min`, `max` and `avg` values for the calculated differences
 and returns them in time series with `rollup="min"`, `rollup="max"` and `rollup="avg"` additional labels.
 The calculations are performed individually per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
@@ -745,8 +753,8 @@ See also [rollup_increase](#rollup_increase).
 #### rollup_deriv
 
 `rollup_deriv(series_selector[d])` is a [rollup function](#rollup-functions), which calculates per-second derivatives
-for adjacent raw samples on the given lookbehind window `d` and returns `min`, `max` and `avg` values for the calculated per-second derivatives
-and returns them in time series with `rollup="min"`, `rollup="max"` and `rollup="avg"` additional labels.
+for adjacent [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples) on the given lookbehind window `d` and returns `min`, `max` and `avg` values
+for the calculated per-second derivatives and returns them in time series with `rollup="min"`, `rollup="max"` and `rollup="avg"` additional labels.
 The calculations are performed individually per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
 Optional 2nd argument `"min"`, `"max"` or `"avg"` can be passed to keep only one calculation result and without adding a label.
@@ -756,7 +764,7 @@ Metric names are stripped from the resulting rollups. Add [keep_metric_names](#k
 
 #### rollup_increase
 
-`rollup_increase(series_selector[d])` is a [rollup function](#rollup-functions), which calculates increases for adjacent raw samples
+`rollup_increase(series_selector[d])` is a [rollup function](#rollup-functions), which calculates increases for adjacent [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
 on the given lookbehind window `d` and returns `min`, `max` and `avg` values for the calculated increases
 and returns them in time series with `rollup="min"`, `rollup="max"` and `rollup="avg"` additional labels.
 The calculations are performed individually per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
@@ -768,7 +776,8 @@ Metric names are stripped from the resulting rollups. Add [keep_metric_names](#k
 
 #### rollup_rate
 
-`rollup_rate(series_selector[d])` is a [rollup function](#rollup-functions), which calculates per-second change rates for adjacent raw samples
+`rollup_rate(series_selector[d])` is a [rollup function](#rollup-functions), which calculates per-second change rates
+for adjacent [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
 on the given lookbehind window `d` and returns `min`, `max` and `avg` values for the calculated per-second change rates
 and returns them in time series with `rollup="min"`, `rollup="max"` and `rollup="avg"` additional labels.
 
@@ -785,7 +794,7 @@ Metric names are stripped from the resulting rollups. Add [keep_metric_names](#k
 #### rollup_scrape_interval
 
 `rollup_scrape_interval(series_selector[d])` is a [rollup function](#rollup-functions), which calculates the interval in seconds between
-adjacent raw samples on the given lookbehind window `d` and returns `min`, `max` and `avg` values for the calculated interval
+adjacent [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples) on the given lookbehind window `d` and returns `min`, `max` and `avg` values for the calculated interval
 and returns them in time series with `rollup="min"`, `rollup="max"` and `rollup="avg"` additional labels.
 The calculations are performed individually per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
@@ -796,7 +805,8 @@ Metric names are stripped from the resulting rollups. Add [keep_metric_names](#k
 
 #### scrape_interval
 
-`scrape_interval(series_selector[d])` is a [rollup function](#rollup-functions), which calculates the average interval in seconds between raw samples
+`scrape_interval(series_selector[d])` is a [rollup function](#rollup-functions), which calculates the average interval in seconds
+between [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
 on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
 Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
@@ -805,7 +815,8 @@ See also [rollup_scrape_interval](#rollup_scrape_interval).
 
 #### share_gt_over_time
 
-`share_gt_over_time(series_selector[d], gt)` is a [rollup function](#rollup-functions), which returns share (in the range `[0...1]`) of raw samples
+`share_gt_over_time(series_selector[d], gt)` is a [rollup function](#rollup-functions), which returns share (in the range `[0...1]`)
+of [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
 on the given lookbehind window `d`, which are bigger than `gt`. It is calculated independently per each time series returned
 from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
@@ -817,7 +828,8 @@ See also [share_le_over_time](#share_le_over_time) and [count_gt_over_time](#cou
 
 #### share_le_over_time
 
-`share_le_over_time(series_selector[d], le)` is a [rollup function](#rollup-functions), which returns share (in the range `[0...1]`) of raw samples
+`share_le_over_time(series_selector[d], le)` is a [rollup function](#rollup-functions), which returns share (in the range `[0...1]`)
+of [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
 on the given lookbehind window `d`, which are smaller or equal to `le`. It is calculated independently per each time series returned
 from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
@@ -830,7 +842,8 @@ See also [share_gt_over_time](#share_gt_over_time) and [count_le_over_time](#cou
 
 #### share_eq_over_time
 
-`share_eq_over_time(series_selector[d], eq)` is a [rollup function](#rollup-functions), which returns share (in the range `[0...1]`) of raw samples
+`share_eq_over_time(series_selector[d], eq)` is a [rollup function](#rollup-functions), which returns share (in the range `[0...1]`)
+of [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
 on the given lookbehind window `d`, which are equal to `eq`. It is calculated independently per each time series returned
 from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
@@ -848,7 +861,7 @@ Metric names are stripped from the resulting rollups. Add [keep_metric_names](#k
 
 #### stddev_over_time
 
-`stddev_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which calculates standard deviation over raw samples
+`stddev_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which calculates standard deviation over [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
 on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
 Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
@@ -859,7 +872,7 @@ See also [stdvar_over_time](#stdvar_over_time).
 
 #### stdvar_over_time
 
-`stdvar_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which calculates standard variance over raw samples
+`stdvar_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which calculates standard variance over [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
 on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
 Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
@@ -870,8 +883,8 @@ See also [stddev_over_time](#stddev_over_time).
 
 #### sum_eq_over_time
 
-`sum_eq_over_time(series_selector[d], eq)` is a [rollup function](#rollup-function), which calculates the sum of raw sample values equal to `eq`
-on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
+`sum_eq_over_time(series_selector[d], eq)` is a [rollup function](#rollup-function), which calculates the sum of [raw sample](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
+values equal to `eq` on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
 Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
 
@@ -879,8 +892,8 @@ See also [sum_over_time](#sum_over_time) and [count_eq_over_time](#count_eq_over
 
 #### sum_gt_over_time
 
-`sum_gt_over_time(series_selector[d], gt)` is a [rollup function](#rollup-function), which calculates the sum of raw sample values bigger than `gt`
-on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
+`sum_gt_over_time(series_selector[d], gt)` is a [rollup function](#rollup-function), which calculates the sum of [raw sample](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
+values bigger than `gt` on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
 Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
 
@@ -888,8 +901,8 @@ See also [sum_over_time](#sum_over_time) and [count_gt_over_time](#count_gt_over
 
 #### sum_le_over_time
 
-`sum_le_over_time(series_selector[d], le)` is a [rollup function](#rollup-function), which calculates the sum of raw sample values smaller or equal to `le`
-on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
+`sum_le_over_time(series_selector[d], le)` is a [rollup function](#rollup-function), which calculates the sum of [raw sample](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
+values smaller or equal to `le` on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
 Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
 
@@ -897,7 +910,7 @@ See also [sum_over_time](#sum_over_time) and [count_le_over_time](#count_le_over
 
 #### sum_over_time
 
-`sum_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which calculates the sum of raw sample values
+`sum_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which calculates the sum of [raw sample](https://docs.victoriametrics.com/keyconcepts/#raw-samples) values
 on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
 Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
@@ -906,14 +919,15 @@ This function is supported by PromQL.
 
 #### sum2_over_time
 
-`sum2_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which calculates the sum of squares for raw sample values
-on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
+`sum2_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which calculates the sum of squares for [raw sample](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
+values on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
 Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
 
 #### timestamp
 
-`timestamp(series_selector[d])` is a [rollup function](#rollup-functions), which returns the timestamp in seconds with millisecond precision for the last raw sample
+`timestamp(series_selector[d])` is a [rollup function](#rollup-functions), which returns the timestamp in seconds with millisecond precision
+for the last [raw sample](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
 on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
 Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
@@ -924,7 +938,8 @@ See also [time](#time) and [now](#now).
 
 #### timestamp_with_name
 
-`timestamp_with_name(series_selector[d])` is a [rollup function](#rollup-functions), which returns the timestamp in seconds with millisecond precision for the last raw sample
+`timestamp_with_name(series_selector[d])` is a [rollup function](#rollup-functions), which returns the timestamp in seconds with millisecond precision
+for the last [raw sample](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
 on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
 Metric names are preserved in the resulting rollups.
@@ -933,7 +948,8 @@ See also [timestamp](#timestamp) and [keep_metric_names](#keep_metric_names) mod
 
 #### tfirst_over_time
 
-`tfirst_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which returns the timestamp in seconds with millisecond precision for the first raw sample
+`tfirst_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which returns the timestamp in seconds with millisecond precision
+for the first [raw sample](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
 on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
 Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
@@ -957,7 +973,8 @@ See also [tlast_change_over_time](#tlast_change_over_time).
 
 #### tmax_over_time
 
-`tmax_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which returns the timestamp in seconds with millisecond precision for the raw sample
+`tmax_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which returns the timestamp in seconds with millisecond precision
+for the [raw sample](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
 with the maximum value on the given lookbehind window `d`. It is calculated independently per each time series returned
 from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
@@ -967,7 +984,8 @@ See also [max_over_time](#max_over_time).
 
 #### tmin_over_time
 
-`tmin_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which returns the timestamp in seconds with millisecond precision for the raw sample
+`tmin_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which returns the timestamp in seconds with millisecond precision
+for the [raw sample](https://docs.victoriametrics.com/keyconcepts/#raw-samples)
 with the minimum value on the given lookbehind window `d`. It is calculated independently per each time series returned
 from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
@@ -978,7 +996,7 @@ See also [min_over_time](#min_over_time).
 #### zscore_over_time
 
 `zscore_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which returns [z-score](https://en.wikipedia.org/wiki/Standard_score)
-for raw samples on the given lookbehind window `d`. It is calculated independently per each time series returned
+for [raw samples](https://docs.victoriametrics.com/keyconcepts/#raw-samples) on the given lookbehind window `d`. It is calculated independently per each time series returned
 from the given [series_selector](https://docs.victoriametrics.com/keyconcepts/#filtering).
 
 Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
@@ -2212,6 +2230,7 @@ Any [rollup function](#rollup-functions) for something other than [series select
 Nested rollup functions can be implicit thanks to the [implicit query conversions](#implicit-query-conversions).
 For example, `delta(sum(m))` is implicitly converted to `delta(sum(default_rollup(m))[1i:1i])`, so it becomes a subquery,
 since it contains [default_rollup](#default_rollup) nested into [delta](#delta).
+This behavior can be disabled or logged via cmd-line flags `-search.disableImplicitConversion` and `-search.logImplicitConversion` since v1.101.0.
 
 VictoriaMetrics performs subqueries in the following way:
 
@@ -2244,4 +2263,5 @@ VictoriaMetrics performs the following implicit conversions for incoming queries
   For example, `avg_over_time(rate(http_requests_total[5m])[1h])` is automatically converted to `avg_over_time(rate(http_requests_total[5m])[1h:1i])`.
 * If something other than [series selector](https://docs.victoriametrics.com/keyconcepts/#filtering)
   is passed to [rollup function](#rollup-functions), then a [subquery](#subqueries) with `1i` lookbehind window and `1i` step is automatically formed.
-  For example, `rate(sum(up))` is automatically converted to `rate((sum(default_rollup(up)))[1i:1i])`.
+  For example, `rate(sum(up))` is automatically converted to `rate((sum(default_rollup(up)))[1i:1i])`. 
+  This behavior can be disabled or logged via cmd-line flags `-search.disableImplicitConversion` and `-search.logImplicitConversion` since v1.101.0.

app/vlstorage/main.go

@@ -1,10 +1,11 @@
 package vlstorage
 
 import (
+	"context"
 	"flag"
 	"fmt"
+	"io"
 	"net/http"
-	"sync"
 	"time"
 
 	"github.com/VictoriaMetrics/metrics"
@@ -19,19 +20,21 @@ 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 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")
 	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 with the 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 where to store 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.html#stream-fields ; see also -logIngestedRows")
+		"see https://docs.victoriametrics.com/victorialogs/keyconcepts/#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")
 )
@@ -48,12 +51,13 @@ func Init() {
 		logger.Fatalf("-retentionPeriod cannot be smaller than a day; got %s", retentionPeriod)
 	}
 	cfg := &logstorage.StorageConfig{
-		Retention:             retentionPeriod.Duration(),
-		FlushInterval:         *inmemoryDataFlushInterval,
-		FutureRetention:       futureRetention.Duration(),
-		LogNewStreams:         *logNewStreams,
-		LogIngestedRows:       *logIngestedRows,
-		MinFreeDiskSpaceBytes: minFreeDiskSpaceBytes.N,
+		Retention:              retentionPeriod.Duration(),
+		MaxDiskSpaceUsageBytes: maxDiskSpaceUsageBytes.N,
+		FlushInterval:          *inmemoryDataFlushInterval,
+		FutureRetention:        futureRetention.Duration(),
+		LogNewStreams:          *logNewStreams,
+		LogIngestedRows:        *logIngestedRows,
+		MinFreeDiskSpaceBytes:  minFreeDiskSpaceBytes.N,
 	}
 	logger.Infof("opening storage at -storageDataPath=%s", *storageDataPath)
 	startTime := time.Now()
@@ -61,10 +65,16 @@ func Init() {
 
 	var ss logstorage.StorageStats
 	strg.UpdateStats(&ss)
-	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)
+	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)
 
+	// register storage metrics
+	storageMetrics = metrics.NewSet()
+	storageMetrics.RegisterMetricsWriter(func(w io.Writer) {
+		writeStorageMetrics(w, strg)
+	})
 	metrics.RegisterSet(storageMetrics)
 }
 
@@ -99,117 +109,99 @@ func MustAddRows(lr *logstorage.LogRows) {
 	strg.MustAddRows(lr)
 }
 
-// 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)
+// 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)
 }
 
-func initStorageMetrics(strg *logstorage.Storage) *metrics.Set {
-	ssCache := &logstorage.StorageStats{}
-	var ssCacheLock sync.Mutex
-	var lastUpdateTime time.Time
+// 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)
+}
 
-	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
+// 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
 	}
+	metrics.WriteGaugeUint64(w, fmt.Sprintf(`vl_storage_is_read_only{path=%q}`, *storageDataPath), isReadOnly)
 
-	ms := metrics.NewSet()
+	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.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.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(`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_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_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_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_partitions`, func() float64 {
-		return float64(m().PartitionsCount)
-	})
-	ms.NewGauge(`vl_streams_created_total`, func() float64 {
-		return float64(m().StreamsCreatedTotal)
-	})
+	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_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_partitions`, ss.PartitionsCount)
+	metrics.WriteCounterUint64(w, `vl_streams_created_total`, ss.StreamsCreatedTotal)
 
-	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_indexdb_rows`, ss.IndexdbItemsCount)
+	metrics.WriteGaugeUint64(w, `vl_indexdb_parts`, ss.IndexdbPartsCount)
+	metrics.WriteGaugeUint64(w, `vl_indexdb_blocks`, ss.IndexdbBlocksCount)
 
-	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_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_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_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)
 
-	return ms
+	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)
 }

app/vmagent/Makefile

@@ -88,6 +88,9 @@ 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/main.go

@@ -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")
-	reloadAuthKey = flagutil.NewPassword("reloadAuthKey", "Auth key for /-/reload http endpoint. It must be passed as authKey=...")
+	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.")
 	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")

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/remotewrite/client.go

@@ -11,8 +11,11 @@ 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"
@@ -20,7 +23,6 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/ratelimiter"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/timerpool"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/timeutil"
-	"github.com/VictoriaMetrics/metrics"
 )
 
 var (
@@ -36,7 +38,7 @@ var (
 	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 estabilishing tls connections to the corresponding -remoteWrite.url")
+	tlsHandshakeTimeout   = flagutil.NewArrayDuration("remoteWrite.tlsHandshakeTimeout", 20*time.Second, "The timeout for establishing 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")
@@ -118,7 +120,7 @@ func newHTTPClient(argIdx int, remoteWriteURL, sanitizedURL string, fq *persiste
 		logger.Fatalf("cannot initialize AWS Config for -remoteWrite.url=%q: %s", remoteWriteURL, err)
 	}
 	tr := &http.Transport{
-		DialContext:         statDial,
+		DialContext:         httputils.GetStatDialFunc("vmagent_remotewrite"),
 		TLSHandshakeTimeout: tlsHandshakeTimeout.GetOptionalArg(argIdx),
 		MaxConnsPerHost:     2 * concurrency,
 		MaxIdleConnsPerHost: 2 * concurrency,
@@ -298,6 +300,11 @@ 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)

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 to remote storage")
+			t.Fatalf("cannot push data 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

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

app/vmagent/remotewrite/remotewrite.go

@@ -29,7 +29,6 @@ import (
 	"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"
 )
@@ -39,10 +38,6 @@ 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/#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/#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 "+
 		"according to https://docs.victoriametrics.com/#how-to-import-time-series-data ."+
@@ -92,40 +87,18 @@ var (
 	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")
 
-	streamAggrConfig = flagutil.NewArrayString("remoteWrite.streamAggr.config", "Optional path to file with stream aggregation config. "+
-		"See https://docs.victoriametrics.com/stream-aggregation/ . "+
-		"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/")
-	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/")
-	streamAggrDedupInterval = flagutil.NewArrayDuration("remoteWrite.streamAggr.dedupInterval", 0, "Input samples are de-duplicated with this interval before optional aggregation "+
-		"with -remoteWrite.streamAggr.config . 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 . 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. 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")
-	streamAggrDropInputLabels = flagutil.NewArrayString("streamAggr.dropInputLabels", "An optional list of labels to drop from samples "+
-		"before stream de-duplication and aggregation . See https://docs.victoriametrics.com/stream-aggregation/#dropping-unneeded-labels")
-
-	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/#disabling-on-disk-persistence ."+
+	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 ."+
 		"See also -remoteWrite.dropSamplesOnOverload")
-	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/#disabling-on-disk-persistence")
+	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")
 )
 
 var (
-	// rwctxsDefault contains statically populated entries when -remoteWrite.url is specified.
-	rwctxsDefault []*remoteWriteCtx
+	// rwctxs contains statically populated entries when -remoteWrite.url is specified.
+	rwctxs []*remoteWriteCtx
 
-	// rwctxsMap contains dynamically populated entries when -remoteWrite.multitenantURL is specified.
-	rwctxsMap     = make(map[tenantmetrics.TenantID][]*remoteWriteCtx)
-	rwctxsMapLock sync.Mutex
-
-	// Data without tenant id is written to defaultAuthToken if -remoteWrite.multitenantURL is specified.
+	// Data without tenant id is written to defaultAuthToken if -enableMultitenantHandlers is specified.
 	defaultAuthToken = &auth.Token{}
 
 	// ErrQueueFullHTTPRetry must be returned when TryPush() returns false.
@@ -135,16 +108,25 @@ var (
 			"see https://docs.victoriametrics.com/vmagent/#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 or -remoteWrite.multitenantURL is specified.
+// MultitenancyEnabled returns true if -enableMultitenantHandlers is specified.
 func MultitenancyEnabled() bool {
-	return *enableMultitenantHandlers || len(*remoteWriteMultitenantURLs) > 0
+	return *enableMultitenantHandlers
 }
 
 // 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
@@ -170,11 +152,8 @@ var (
 //
 // Stop must be called for graceful shutdown.
 func Init() {
-	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 len(*remoteWriteURLs) == 0 {
+		logger.Fatalf("at least one `-remoteWrite.url` command-line flag must be set")
 	}
 	if *maxHourlySeries > 0 {
 		hourlySeriesLimiter = bloomfilter.NewLimiter(*maxHourlySeries, time.Hour)
@@ -224,9 +203,29 @@ func Init() {
 	relabelConfigSuccess.Set(1)
 	relabelConfigTimestamp.Set(fasttime.UnixTimestamp())
 
-	if len(*remoteWriteURLs) > 0 {
-		rwctxsDefault = newRemoteWriteCtxs(nil, *remoteWriteURLs)
+	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)
+	}
+
+	disableOnDiskQueueAll = true
+	for _, v := range *disableOnDiskQueue {
+		if !v {
+			disableOnDiskQueueAll = false
+			break
+		}
+	}
+
 	dropDanglingQueues()
 
 	// Start config reloader.
@@ -249,12 +248,6 @@ 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
@@ -262,8 +255,8 @@ func dropDanglingQueues() {
 	// 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(rwctxsDefault))
-	for _, rwctx := range rwctxsDefault {
+	existingQueues := make(map[string]struct{}, len(rwctxs))
+	for _, rwctx := range rwctxs {
 		existingQueues[rwctx.fq.Dirname()] = struct{}{}
 	}
 
@@ -280,7 +273,7 @@ func dropDanglingQueues() {
 		}
 	}
 	if removed > 0 {
-		logger.Infof("removed %d dangling queues from %q, active queues: %d", removed, *tmpDataPath, len(rwctxsDefault))
+		logger.Infof("removed %d dangling queues from %q, active queues: %d", removed, *tmpDataPath, len(rwctxs))
 	}
 }
 
@@ -307,24 +300,6 @@ 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")
@@ -360,8 +335,10 @@ func newRemoteWriteCtxs(at *auth.Token, urls []string) []*remoteWriteCtx {
 	return rwctxs
 }
 
-var configReloaderStopCh = make(chan struct{})
-var configReloaderWG sync.WaitGroup
+var (
+	configReloaderStopCh = make(chan struct{})
+	configReloaderWG     sync.WaitGroup
+)
 
 // StartIngestionRateLimiter starts ingestion rate limiter.
 //
@@ -399,18 +376,16 @@ func Stop() {
 	close(configReloaderStopCh)
 	configReloaderWG.Wait()
 
-	for _, rwctx := range rwctxsDefault {
+	sasGlobal.Load().MustStop()
+	if deduplicatorGlobal != nil {
+		deduplicatorGlobal.MustStop()
+		deduplicatorGlobal = nil
+	}
+
+	for _, rwctx := range rwctxs {
 		rwctx.MustStop()
 	}
-	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
+	rwctxs = nil
 
 	if sl := hourlySeriesLimiter; sl != nil {
 		sl.MustStop()
@@ -420,30 +395,24 @@ func Stop() {
 	}
 }
 
-// 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 pushes wr to the configured remote storage systems set via -remoteWrite.url
 //
 // 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 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 tries sending wr to the configured remote storage systems set via -remoteWrite.url
 //
 // 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, *dropSamplesOnOverload)
+	return tryPush(at, wr, false)
 }
 
-func tryPush(at *auth.Token, wr *prompbmarshal.WriteRequest, dropSamplesOnFailure bool) bool {
+func tryPush(at *auth.Token, wr *prompbmarshal.WriteRequest, forceDropSamplesOnFailure bool) bool {
 	tss := wr.Timeseries
 
 	if at == nil && MultitenancyEnabled() {
@@ -452,41 +421,25 @@ func tryPush(at *auth.Token, wr *prompbmarshal.WriteRequest, dropSamplesOnFailur
 	}
 
 	var tenantRctx *relabelCtx
-	var rwctxs []*remoteWriteCtx
-	if at == nil {
-		rwctxs = rwctxsDefault
-	} else if len(*remoteWriteMultitenantURLs) == 0 {
+	if at != nil {
 		// 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)
 
-	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.
+	// 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 {
 		for _, rwctx := range rwctxs {
 			if rwctx.fq.IsWriteBlocked() {
-				pushFailures.Inc()
-				if dropSamplesOnFailure {
+				rwctx.pushFailures.Inc()
+				if forceDropSamplesOnFailure || rwctx.dropSamplesOnOverload {
 					// Just drop samples
-					samplesDropped.Add(rowsCount)
-					return true
+					rwctx.rowsDroppedOnPushFailure.Add(rowsCount)
+					continue
 				}
 				return false
 			}
@@ -505,6 +458,8 @@ func tryPush(at *auth.Token, wr *prompbmarshal.WriteRequest, dropSamplesOnFailur
 	// 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
@@ -539,27 +494,31 @@ func tryPush(at *auth.Token, wr *prompbmarshal.WriteRequest, dropSamplesOnFailur
 		}
 		sortLabelsIfNeeded(tssBlock)
 		tssBlock = limitSeriesCardinality(tssBlock)
-		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
+		if sas.IsEnabled() {
+			matchIdxs := matchIdxsPool.Get()
+			matchIdxs.B = sas.Push(tssBlock, matchIdxs.B)
+			if !*streamAggrGlobalKeepInput {
+				tssBlock = dropAggregatedSeries(tssBlock, matchIdxs.B, *streamAggrGlobalDropInput)
 			}
+			matchIdxsPool.Put(matchIdxs)
+		} else if deduplicatorGlobal != nil {
+			deduplicatorGlobal.Push(tssBlock)
+			tssBlock = tssBlock[:0]
+		}
+		if !tryPushBlockToRemoteStorages(tssBlock, forceDropSamplesOnFailure) {
 			return false
 		}
 	}
 	return true
 }
 
-var (
-	samplesDropped = metrics.NewCounter(`vmagent_remotewrite_samples_dropped_total`)
-	pushFailures   = metrics.NewCounter(`vmagent_remotewrite_push_failures_total`)
-)
+func pushToRemoteStoragesDropFailed(tss []prompbmarshal.TimeSeries) {
+	if tryPushBlockToRemoteStorages(tss, true) {
+		return
+	}
+}
 
-func tryPushBlockToRemoteStorages(rwctxs []*remoteWriteCtx, tssBlock []prompbmarshal.TimeSeries) bool {
+func tryPushBlockToRemoteStorages(tssBlock []prompbmarshal.TimeSeries, forceDropSamplesOnFailure bool) bool {
 	if len(tssBlock) == 0 {
 		// Nothing to push
 		return true
@@ -567,7 +526,7 @@ func tryPushBlockToRemoteStorages(rwctxs []*remoteWriteCtx, tssBlock []prompbmar
 
 	if len(rwctxs) == 1 {
 		// Fast path - just push data to the configured single remote storage
-		return rwctxs[0].TryPush(tssBlock)
+		return rwctxs[0].TryPush(tssBlock, forceDropSamplesOnFailure)
 	}
 
 	// We need to push tssBlock to multiple remote storages.
@@ -578,7 +537,7 @@ func tryPushBlockToRemoteStorages(rwctxs []*remoteWriteCtx, tssBlock []prompbmar
 		if replicas <= 0 {
 			replicas = 1
 		}
-		return tryShardingBlockAmongRemoteStorages(rwctxs, tssBlock, replicas)
+		return tryShardingBlockAmongRemoteStorages(tssBlock, replicas, forceDropSamplesOnFailure)
 	}
 
 	// Replicate tssBlock samples among rwctxs.
@@ -590,7 +549,7 @@ func tryPushBlockToRemoteStorages(rwctxs []*remoteWriteCtx, tssBlock []prompbmar
 	for _, rwctx := range rwctxs {
 		go func(rwctx *remoteWriteCtx) {
 			defer wg.Done()
-			if !rwctx.TryPush(tssBlock) {
+			if !rwctx.TryPush(tssBlock, forceDropSamplesOnFailure) {
 				anyPushFailed.Store(true)
 			}
 		}(rwctx)
@@ -599,7 +558,7 @@ func tryPushBlockToRemoteStorages(rwctxs []*remoteWriteCtx, tssBlock []prompbmar
 	return !anyPushFailed.Load()
 }
 
-func tryShardingBlockAmongRemoteStorages(rwctxs []*remoteWriteCtx, tssBlock []prompbmarshal.TimeSeries, replicas int) bool {
+func tryShardingBlockAmongRemoteStorages(tssBlock []prompbmarshal.TimeSeries, replicas int, forceDropSamplesOnFailure bool) bool {
 	x := getTSSShards(len(rwctxs))
 	defer putTSSShards(x)
 
@@ -653,7 +612,7 @@ func tryShardingBlockAmongRemoteStorages(rwctxs []*remoteWriteCtx, tssBlock []pr
 		wg.Add(1)
 		go func(rwctx *remoteWriteCtx, tss []prompbmarshal.TimeSeries) {
 			defer wg.Done()
-			if !rwctx.TryPush(tss) {
+			if !rwctx.TryPush(tss, forceDropSamplesOnFailure) {
 				anyPushFailed.Store(true)
 			}
 		}(rwctx, shard)
@@ -786,14 +745,19 @@ type remoteWriteCtx struct {
 	sas          atomic.Pointer[streamaggr.Aggregators]
 	deduplicator *streamaggr.Deduplicator
 
-	streamAggrKeepInput bool
-	streamAggrDropInput bool
+	streamAggrKeepInput   bool
+	streamAggrDropInput   bool
+	disableOnDiskQueue    bool
+	dropSamplesOnOverload bool
 
 	pss        []*pendingSeries
 	pssNextIdx atomic.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 {
@@ -809,7 +773,8 @@ 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
 	}
-	fq := persistentqueue.MustOpenFastQueue(queuePath, sanitizedURL, maxInmemoryBlocks, maxPendingBytes, *disableOnDiskQueue)
+	isPQDisabled := disableOnDiskQueue.GetOptionalArg(argIdx)
+	fq := persistentqueue.MustOpenFastQueue(queuePath, sanitizedURL, maxInmemoryBlocks, maxPendingBytes, isPQDisabled)
 	_ = metrics.GetOrCreateGauge(fmt.Sprintf(`vmagent_remotewrite_pending_data_bytes{path=%q, url=%q}`, queuePath, sanitizedURL), func() float64 {
 		return float64(fq.GetPendingBytes())
 	})
@@ -852,22 +817,20 @@ 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 := streamAggrConfig.GetOptionalArg(argIdx)
-	dedupInterval := streamAggrDedupInterval.GetOptionalArg(argIdx)
-	ignoreOldSamples := streamAggrIgnoreOldSamples.GetOptionalArg(argIdx)
+	sasFile, sasOpts := getStreamAggrOpts(argIdx)
 	if sasFile != "" {
-		opts := &streamaggr.Options{
-			DedupInterval:        dedupInterval,
-			DropInputLabels:      *streamAggrDropInputLabels,
-			IgnoreOldSamples:     ignoreOldSamples,
-			IgnoreFirstIntervals: *streamAggrIgnoreFirstIntervals,
-		}
-		sas, err := streamaggr.LoadFromFile(sasFile, rwctx.pushInternalTrackDropped, opts)
+		sas, err := newStreamAggrConfig(argIdx, rwctx.pushInternalTrackDropped)
 		if err != nil {
 			logger.Fatalf("cannot initialize stream aggregators from -remoteWrite.streamAggr.config=%q: %s", sasFile, err)
 		}
@@ -876,8 +839,8 @@ 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 dedupInterval > 0 {
-		rwctx.deduplicator = streamaggr.NewDeduplicator(rwctx.pushInternalTrackDropped, dedupInterval, *streamAggrDropInputLabels)
+	} else if sasOpts.DedupInterval > 0 {
+		rwctx.deduplicator = streamaggr.NewDeduplicator(rwctx.pushInternalTrackDropped, sasOpts.DedupInterval, sasOpts.DropInputLabels, sasOpts.Alias)
 	}
 
 	return rwctx
@@ -885,7 +848,7 @@ func newRemoteWriteCtx(argIdx int, remoteWriteURL *url.URL, maxInmemoryBlocks in
 
 func (rwctx *remoteWriteCtx) MustStop() {
 	// sas and deduplicator must be stopped before rwctx is closed
-	// because sas can write pending series to rwctx.pss if there are any
+	// because they can write pending series to rwctx.pss if there are any
 	sas := rwctx.sas.Swap(nil)
 	sas.MustStop()
 
@@ -910,10 +873,22 @@ func (rwctx *remoteWriteCtx) MustStop() {
 	rwctx.rowsDroppedByRelabel = nil
 }
 
-func (rwctx *remoteWriteCtx) TryPush(tss []prompbmarshal.TimeSeries) bool {
-	// Apply relabeling
+// 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 {
 	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 {
@@ -934,7 +909,7 @@ func (rwctx *remoteWriteCtx) TryPush(tss []prompbmarshal.TimeSeries) bool {
 
 	// Apply stream aggregation or deduplication if they are configured
 	sas := rwctx.sas.Load()
-	if sas != nil {
+	if sas.IsEnabled() {
 		matchIdxs := matchIdxsPool.Get()
 		matchIdxs.B = sas.Push(tss, matchIdxs.B)
 		if !rwctx.streamAggrKeepInput {
@@ -949,21 +924,21 @@ func (rwctx *remoteWriteCtx) TryPush(tss []prompbmarshal.TimeSeries) bool {
 		matchIdxsPool.Put(matchIdxs)
 	} else if rwctx.deduplicator != nil {
 		rwctx.deduplicator.Push(tss)
-		clear(tss)
-		tss = tss[:0]
+		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)
+	// Try pushing tss to remote storage
+	if rwctx.tryPushInternal(tss) {
+		return true
 	}
 
-	return ok
+	// Couldn't push tss to remote storage
+	rwctx.pushFailures.Inc()
+	if forceDropSamplesOnFailure || rwctx.dropSamplesOnOverload {
+		rwctx.rowsDroppedOnPushFailure.Add(len(tss))
+		return true
+	}
+	return false
 }
 
 var matchIdxsPool bytesutil.ByteBufferPool
@@ -987,19 +962,28 @@ func (rwctx *remoteWriteCtx) pushInternalTrackDropped(tss []prompbmarshal.TimeSe
 	if rwctx.tryPushInternal(tss) {
 		return
 	}
-	if !*disableOnDiskQueue {
+	if !rwctx.disableOnDiskQueue {
 		logger.Panicf("BUG: tryPushInternal must return true if -remoteWrite.disableOnDiskQueue isn't set")
 	}
-	pushFailures.Inc()
-	if *dropSamplesOnOverload {
+	rwctx.pushFailures.Inc()
+	if dropSamplesOnOverload.GetOptionalArg(rwctx.idx) {
 		rowsCount := getRowsCount(tss)
-		samplesDropped.Add(rowsCount)
+		rwctx.rowsDroppedOnPushFailure.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.
@@ -1012,49 +996,7 @@ func (rwctx *remoteWriteCtx) tryPushInternal(tss []prompbmarshal.TimeSeries) boo
 	pss := rwctx.pss
 	idx := rwctx.pssNextIdx.Add(1) % uint64(len(pss))
 
-	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()
-	opts := &streamaggr.Options{
-		DedupInterval:    streamAggrDedupInterval.GetOptionalArg(rwctx.idx),
-		DropInputLabels:  *streamAggrDropInputLabels,
-		IgnoreOldSamples: streamAggrIgnoreOldSamples.GetOptionalArg(rwctx.idx),
-	}
-	sasNew, err := streamaggr.LoadFromFile(sasFile, rwctx.pushInternalTrackDropped, opts)
-	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())
+	return pss[idx].TryPush(tss)
 }
 
 var tssPool = &sync.Pool{
@@ -1072,27 +1014,6 @@ func getRowsCount(tss []prompbmarshal.TimeSeries) int {
 	return rowsCount
 }
 
-// CheckStreamAggrConfigs checks configs pointed by -remoteWrite.streamAggr.config
-func CheckStreamAggrConfigs() error {
-	pushNoop := func(_ []prompbmarshal.TimeSeries) {}
-	for idx, sasFile := range *streamAggrConfig {
-		if sasFile == "" {
-			continue
-		}
-		opts := &streamaggr.Options{
-			DedupInterval:    streamAggrDedupInterval.GetOptionalArg(idx),
-			DropInputLabels:  *streamAggrDropInputLabels,
-			IgnoreOldSamples: streamAggrIgnoreOldSamples.GetOptionalArg(idx),
-		}
-		sas, err := streamaggr.LoadFromFile(sasFile, pushNoop, opts)
-		if err != nil {
-			return fmt.Errorf("cannot load -remoteWrite.streamAggr.config=%q: %w", sasFile, err)
-		}
-		sas.MustStop()
-	}
-	return nil
-}
-
 func newMapFromStrings(a []string) map[string]struct{} {
 	m := make(map[string]struct{}, len(a))
 	for _, s := range a {

app/vmagent/remotewrite/remotewrite_test.go

@@ -3,9 +3,14 @@ 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) {
@@ -46,3 +51,115 @@ func TestGetLabelsHash_Distribution(t *testing.T) {
 	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

@@ -1,73 +0,0 @@
-package remotewrite
-
-import (
-	"context"
-	"net"
-	"sync/atomic"
-
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/netutil"
-	"github.com/VictoriaMetrics/metrics"
-)
-
-func statDial(ctx context.Context, _, addr string) (conn net.Conn, err error) {
-	network := netutil.GetTCPNetwork()
-	conn, err = netutil.DialMaybeSRV(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 atomic.Int32
-	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 sc.closed.Add(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

@@ -0,0 +1,164 @@
+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

@@ -26,8 +26,14 @@ 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:    "files to run unittest with. Supports an array of values separated by comma or specified via multiple flags.",
+						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.
+ `,
 						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

@@ -18,6 +18,8 @@ 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"`
@@ -86,13 +88,12 @@ 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 := reg.FindAllString(item, -1)
+		vals := numReg.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+1x4",
-			[]sequenceValue{{Value: 1}, {Value: 2}, {Value: 3}, {Value: 4}, {Value: 5}},
+			"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}},
 			false,
 		},
 		{

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

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

app/vmalert-tool/unittest/unittest.go

@@ -9,10 +9,12 @@ 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"
@@ -66,36 +68,38 @@ func UnitTest(files []string, disableGroupLabel bool) bool {
 	defer vminsert.Stop()
 	defer vmselect.Stop()
 	disableAlertgroupLabel = disableGroupLabel
-	return rulesUnitTest(files)
-}
 
-func rulesUnitTest(files []string) bool {
+	testfiles, err := config.ReadFromFS(files)
+	if err != nil {
+		fmt.Println("  FAILED")
+		fmt.Printf("\nfailed to read test files: \n%v", err)
+	}
 	var failed bool
-	for _, f := range files {
-		if err := ruleUnitTest(f); err != nil {
+	for fileName, file := range testfiles {
+		if err := ruleUnitTest(fileName, file); err != nil {
 			fmt.Println("  FAILED")
-			fmt.Printf("\nfailed to run unit test for file %q: \n%v", f, err)
+			fmt.Printf("\nfailed to run unit test for file %q: \n%v", file, err)
 			failed = true
 		} else {
 			fmt.Println("  SUCCESS")
 		}
 	}
+
 	return failed
 }
 
-func ruleUnitTest(filename string) []error {
+func ruleUnitTest(filename string, content []byte) []error {
 	fmt.Println("\nUnit Testing: ", filename)
-	b, err := os.ReadFile(filename)
-	if err != nil {
-		return []error{fmt.Errorf("failed to read file: %w", err)}
-	}
-
 	var unitTestInp unitTestFile
-	if err := yaml.UnmarshalStrict(b, &unitTestInp); err != nil {
+	if err := yaml.UnmarshalStrict(content, &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)}
+
+	// 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)
+		}
 	}
 
 	if unitTestInp.EvaluationInterval.Duration() == 0 {
@@ -139,24 +143,24 @@ func verifyTestGroup(group testGroup) error {
 	}
 	for _, at := range group.AlertRuleTests {
 		if at.Alertname == "" {
-			return fmt.Errorf("\n%s    missing required filed \"alertname\"", testGroupName)
+			return fmt.Errorf("\n%s    missing required field \"alertname\"", testGroupName)
 		}
 		if !disableAlertgroupLabel && at.GroupName == "" {
-			return fmt.Errorf("\n%s    missing required filed \"groupname\" when flag \"disableAlertGroupLabel\" is false", testGroupName)
+			return fmt.Errorf("\n%s    missing required field \"groupname\" when flag \"disableAlertgroupLabel\" is false", testGroupName)
 		}
 		if disableAlertgroupLabel && at.GroupName != "" {
-			return fmt.Errorf("\n%s    shouldn't set filed \"groupname\" when flag \"disableAlertGroupLabel\" is true", testGroupName)
+			return fmt.Errorf("\n%s    shouldn't set field \"groupname\" when flag \"disableAlertgroupLabel\" is true", testGroupName)
 		}
 		if at.EvalTime == nil {
-			return fmt.Errorf("\n%s    missing required filed \"eval_time\"", testGroupName)
+			return fmt.Errorf("\n%s    missing required field \"eval_time\"", testGroupName)
 		}
 	}
 	for _, et := range group.MetricsqlExprTests {
 		if et.Expr == "" {
-			return fmt.Errorf("\n%s    missing required filed \"expr\"", testGroupName)
+			return fmt.Errorf("\n%s    missing required field \"expr\"", testGroupName)
 		}
 		if et.EvalTime == nil {
-			return fmt.Errorf("\n%s    missing required filed \"eval_time\"", testGroupName)
+			return fmt.Errorf("\n%s    missing required field \"eval_time\"", testGroupName)
 		}
 	}
 	return nil
@@ -235,30 +239,6 @@ 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()
@@ -316,11 +296,15 @@ 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
@@ -374,7 +358,7 @@ 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

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

@@ -15,8 +15,9 @@ import (
 )
 
 var (
-	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")
+	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")
 	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")
@@ -56,9 +57,10 @@ 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.`)
-	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.`)
+	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.`)
 	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.`)
 )
@@ -98,11 +100,13 @@ func Init(extraParams url.Values) (QuerierBuilder, error) {
 	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{}

app/vmalert/datasource/vm.go

@@ -11,6 +11,7 @@ import (
 	"time"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/netutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promauth"
 )
 
@@ -140,7 +141,7 @@ func (s *VMStorage) Query(ctx context.Context, query string, ts time.Time) (Resu
 	}
 	resp, err := s.do(req)
 	if err != nil {
-		if !errors.Is(err, io.EOF) && !errors.Is(err, io.ErrUnexpectedEOF) {
+		if !errors.Is(err, io.EOF) && !errors.Is(err, io.ErrUnexpectedEOF) && !netutil.IsTrivialNetworkError(err) {
 			// Return unexpected error to the caller.
 			return Result{}, nil, err
 		}
@@ -185,7 +186,7 @@ func (s *VMStorage) QueryRange(ctx context.Context, query string, start, end tim
 	}
 	resp, err := s.do(req)
 	if err != nil {
-		if !errors.Is(err, io.EOF) && !errors.Is(err, io.ErrUnexpectedEOF) {
+		if !errors.Is(err, io.EOF) && !errors.Is(err, io.ErrUnexpectedEOF) && !netutil.IsTrivialNetworkError(err) {
 			// Return unexpected error to the caller.
 			return res, err
 		}

app/vmalert/datasource/vm_prom_api.go

@@ -7,6 +7,10 @@ import (
 	"net/http"
 	"strconv"
 	"time"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
+
+	"github.com/valyala/fastjson"
 )
 
 var (
@@ -31,27 +35,85 @@ type promResponse struct {
 	} `json:"stats,omitempty"`
 }
 
+// see https://prometheus.io/docs/prometheus/latest/querying/api/#instant-queries
 type promInstant struct {
-	Result []struct {
-		Labels map[string]string `json:"metric"`
-		TV     [2]interface{}    `json:"value"`
-	} `json:"result"`
+	// ms is populated after Unmarshal call
+	ms []Metric
 }
 
-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 nil, fmt.Errorf("metric %v, unable to parse float64 from %s: %w", res, res.TV[1], err)
-		}
-		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
+// 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
 	}
-	return result, nil
+
+	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),
+			})
+		})
+		if err != nil {
+			return fmt.Errorf("error when parsing `metric` object in %q: %w", row, 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}
+	}
+	return nil
 }
 
 type promRange struct {
@@ -118,7 +180,7 @@ func parsePrometheusResponse(req *http.Request, resp *http.Response) (res Result
 	switch r.Data.ResultType {
 	case rtVector:
 		var pi promInstant
-		if err := json.Unmarshal(r.Data.Result, &pi.Result); err != nil {
+		if err := pi.Unmarshal(r.Data.Result); err != nil {
 			return res, fmt.Errorf("unmarshal err %w; \n %#v", err, string(r.Data.Result))
 		}
 		parseFn = pi.metrics

app/vmalert/datasource/vm_prom_api_test.go

@@ -1,20 +1,73 @@
 package datasource
 
 import (
-	"encoding/json"
+	"reflect"
 	"testing"
 )
 
-func BenchmarkMetrics(b *testing.B) {
-	payload := []byte(`[{"metric":{"__name__":"vm_rows"},"value":[1583786142,"13763"]},{"metric":{"__name__":"vm_requests", "foo":"bar", "baz": "qux"},"value":[1583786140,"2000"]}]`)
-
-	var pi promInstant
-	if err := json.Unmarshal(payload, &pi.Result); err != nil {
-		b.Fatalf(err.Error())
-	}
-	b.Run("Instant", func(b *testing.B) {
-		for i := 0; i < b.N; i++ {
-			_, _ = pi.metrics()
+func TestPromInstant_UnmarshalPositive(t *testing.T) {
+	f := func(data string, exp []Metric) {
+		t.Helper()
+		var pi promInstant
+		err := pi.Unmarshal([]byte(data))
+		if err != nil {
+			t.Fatalf("unexpected unmarshal err %v; \n %v", err, string(data))
 		}
+		got, _ := pi.metrics()
+		if !reflect.DeepEqual(got, exp) {
+			t.Fatalf("expected to get:\n%v\ngot instead:\n%v", exp, got)
+		}
+	}
+
+	f(`[{"metric":{"__name__":"up"},"value":[1583780000,"42"]}]`, []Metric{
+		{
+			Labels:     []Label{{Name: "__name__", Value: "up"}},
+			Timestamps: []int64{1583780000},
+			Values:     []float64{42},
+		},
+	})
+	f(`[
+{"metric":{"__name__":"up"},"value":[1583780000,"42"]},
+{"metric":{"__name__":"foo"},"value":[1583780001,"7"]},
+{"metric":{"__name__":"baz", "instance":"bar"},"value":[1583780002,"8"]}]`, []Metric{
+		{
+			Labels:     []Label{{Name: "__name__", Value: "up"}},
+			Timestamps: []int64{1583780000},
+			Values:     []float64{42},
+		},
+		{
+			Labels:     []Label{{Name: "__name__", Value: "foo"}},
+			Timestamps: []int64{1583780001},
+			Values:     []float64{7},
+		},
+		{
+			Labels:     []Label{{Name: "__name__", Value: "baz"}, {Name: "instance", Value: "bar"}},
+			Timestamps: []int64{1583780002},
+			Values:     []float64{8},
+		},
 	})
 }
+
+func TestPromInstant_UnmarshalNegative(t *testing.T) {
+	f := func(data string) {
+		t.Helper()
+		var pi promInstant
+		err := pi.Unmarshal([]byte(data))
+		if err == nil {
+			t.Fatalf("expected to get an error; got nil instead")
+		}
+	}
+	f(``)
+	f(`foo`)
+	f(`[{"metric":{"__name__":"up"},"value":[1583780000,"42"]},`)
+	f(`[{"metric":{"__name__"},"value":[1583780000,"42"]},`)
+	// no `metric` object
+	f(`[{"value":[1583780000,"42"]}]`)
+	// no `value` object
+	f(`[{"metric":{"__name__":"up"}}]`)
+	// less than 2 values in `value` object
+	f(`[{"metric":{"__name__":"up"},"value":["42"]}]`)
+	f(`[{"metric":{"__name__":"up"},"value":[1583780000]}]`)
+	// non-numeric sample value
+	f(`[{"metric":{"__name__":"up"},"value":[1583780000,"foo"]}]`)
+}

app/vmalert/datasource/vm_prom_api_timing_test.go

@@ -0,0 +1,43 @@
+package datasource
+
+import (
+	"bytes"
+	"io"
+	"net/http"
+	"os"
+	"testing"
+)
+
+func BenchmarkMetrics(b *testing.B) {
+	payload := []byte(`[{"metric":{"__name__":"vm_rows"},"value":[1583786142,"13763"]},{"metric":{"__name__":"vm_requests", "foo":"bar", "baz": "qux"},"value":[1583786140,"2000"]}]`)
+
+	var pi promInstant
+	if err := pi.Unmarshal(payload); err != nil {
+		b.Fatalf(err.Error())
+	}
+	b.Run("Instant", func(b *testing.B) {
+		for i := 0; i < b.N; i++ {
+			_, _ = pi.metrics()
+		}
+	})
+}
+
+func BenchmarkParsePrometheusResponse(b *testing.B) {
+	req, _ := http.NewRequest("GET", "", nil)
+	resp := &http.Response{StatusCode: http.StatusOK}
+	data, err := os.ReadFile("testdata/instant_response.json")
+	if err != nil {
+		b.Fatalf("error while reading file: %s", err)
+	}
+	resp.Body = io.NopCloser(bytes.NewReader(data))
+
+	b.Run("Instant", func(b *testing.B) {
+		for i := 0; i < b.N; i++ {
+			_, err := parsePrometheusResponse(req, resp)
+			if err != nil {
+				b.Fatalf("unexpected parse err: %s", err)
+			}
+			resp.Body = io.NopCloser(bytes.NewReader(data))
+		}
+	})
+}

app/vmalert/main.go

@@ -72,7 +72,7 @@ absolute path to all .tpl files in root.
 	externalAlertSource = flag.String("external.alert.source", "", `External Alert Source allows to override the Source link for alerts sent to AlertManager `+
 		`for cases where you want to build a custom link to Grafana, Prometheus or any other service. `+
 		`Supports templating - see https://docs.victoriametrics.com/vmalert/#templating . `+
-		`For example, link to Grafana: -external.alert.source='explore?orgId=1&left={"datasource":"VictoriaMetrics","queries":[{"expr":{{$expr|jsonEscape|queryEscape}},"refId":"A"}],"range":{"from":"now-1h","to":"now"}}'. `+
+		`For example, link to Grafana: -external.alert.source='explore?orgId=1&left={"datasource":"VictoriaMetrics","queries":[{"expr":{{.Expr|jsonEscape|queryEscape}},"refId":"A"}],"range":{"from":"now-1h","to":"now"}}'. `+
 		`Link to VMUI: -external.alert.source='vmui/#/?g0.expr={{.Expr|queryEscape}}'. `+
 		`If empty 'vmalert/alert?group_id={{.GroupID}}&alert_id={{.AlertID}}' is used.`)
 	externalLabels = flagutil.NewArrayString("external.label", "Optional label in the form 'Name=value' to add to all generated recording rules and alerts. "+
@@ -132,7 +132,7 @@ func main() {
 		validateTplFn = notifier.ValidateTemplates
 	}
 
-	if *replayFrom != "" || *replayTo != "" {
+	if *replayFrom != "" {
 		rw, err := remotewrite.Init(context.Background())
 		if err != nil {
 			logger.Fatalf("failed to init remoteWrite: %s", err)
@@ -153,6 +153,7 @@ func main() {
 		if err := replay(groupsCfg, q, rw); err != nil {
 			logger.Fatalf("replay failed: %s", err)
 		}
+		logger.Infof("replay succeed!")
 		return
 	}
 

app/vmalert/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/notifier/alertmanager.go

@@ -145,7 +145,7 @@ func NewAlertManager(alertManagerURL string, fn AlertURLGenerator, authCfg proma
 	aCfg, err := utils.AuthConfig(
 		utils.WithBasicAuth(ba.Username, ba.Password.String(), ba.PasswordFile),
 		utils.WithBearer(authCfg.BearerToken.String(), authCfg.BearerTokenFile),
-		utils.WithOAuth(oauth.ClientID, oauth.ClientSecretFile, oauth.ClientSecretFile, oauth.TokenURL, strings.Join(oauth.Scopes, ";"), oauth.EndpointParams))
+		utils.WithOAuth(oauth.ClientID, oauth.ClientSecret.String(), oauth.ClientSecretFile, oauth.TokenURL, strings.Join(oauth.Scopes, ";"), oauth.EndpointParams))
 	if err != nil {
 		return nil, fmt.Errorf("failed to configure auth: %w", err)
 	}

app/vmalert/remoteread/init.go

@@ -4,6 +4,7 @@ import (
 	"flag"
 	"fmt"
 	"net/http"
+	"time"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/utils"
@@ -15,7 +16,8 @@ var (
 	addr = flag.String("remoteRead.url", "", "Optional URL to datasource compatible with Prometheus HTTP API. It can be single node VictoriaMetrics or vmselect."+
 		"Remote read is used to restore alerts state."+
 		"This configuration makes sense only if `vmalert` was configured with `remoteWrite.url` before and has been successfully persisted its state. "+
-		"E.g. http://127.0.0.1:8428. See also '-remoteRead.disablePathAppend', '-remoteRead.showURL'.")
+		"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', '-remoteRead.showURL'.")
 
 	showRemoteReadURL = flag.Bool("remoteRead.showURL", false, "Whether to show -remoteRead.url in the exported metrics. "+
 		"It is hidden by default, since it can contain sensitive info such as auth key")
@@ -31,6 +33,8 @@ var (
 	bearerToken     = flag.String("remoteRead.bearerToken", "", "Optional bearer auth token to use for -remoteRead.url.")
 	bearerTokenFile = flag.String("remoteRead.bearerTokenFile", "", "Optional path to bearer token file to use for -remoteRead.url.")
 
+	idleConnectionTimeout = flag.Duration("remoteRead.idleConnTimeout", 50*time.Second, `Defines a duration for idle (keep-alive connections) to exist. Consider settings this value less to the value of "-http.idleConnTimeout". It must prevent possible "write: broken pipe" and "read: connection reset by peer" errors.`)
+
 	tlsInsecureSkipVerify = flag.Bool("remoteRead.tlsInsecureSkipVerify", false, "Whether to skip tls verification when connecting to -remoteRead.url")
 	tlsCertFile           = flag.String("remoteRead.tlsCertFile", "", "Optional path to client-side TLS certificate file to use when connecting to -remoteRead.url")
 	tlsKeyFile            = flag.String("remoteRead.tlsKeyFile", "", "Optional path to client-side TLS certificate key to use when connecting to -remoteRead.url")
@@ -65,6 +69,8 @@ func Init() (datasource.QuerierBuilder, error) {
 	if err != nil {
 		return nil, fmt.Errorf("failed to create transport: %w", err)
 	}
+	tr.IdleConnTimeout = *idleConnectionTimeout
+	tr.DialContext = httputils.GetStatDialFunc("vmalert_remoteread")
 
 	endpointParams, err := flagutil.ParseJSONMap(*oauth2EndpointParams)
 	if err != nil {

app/vmalert/remotewrite/client.go

@@ -16,6 +16,7 @@ import (
 	"github.com/golang/snappy"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/netutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promauth"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
 	"github.com/VictoriaMetrics/metrics"
@@ -211,6 +212,9 @@ var (
 	})
 )
 
+// GetDroppedRows returns value of droppedRows metric
+func GetDroppedRows() int64 { return int64(droppedRows.Get()) }
+
 // flush is a blocking function that marshals WriteRequest and sends
 // it to remote-write endpoint. Flush performs limited amount of retries
 // if request fails.
@@ -235,7 +239,7 @@ func (c *Client) flush(ctx context.Context, wr *prompbmarshal.WriteRequest) {
 L:
 	for attempts := 0; ; attempts++ {
 		err := c.send(ctx, b)
-		if errors.Is(err, io.EOF) {
+		if err != nil && (errors.Is(err, io.EOF) || netutil.IsTrivialNetworkError(err)) {
 			// Something in the middle between client and destination might be closing
 			// the connection. So we do a one more attempt in hope request will succeed.
 			err = c.send(ctx, b)

app/vmalert/remotewrite/init.go

@@ -13,7 +13,9 @@ import (
 
 var (
 	addr = flag.String("remoteWrite.url", "", "Optional URL to VictoriaMetrics or vminsert where to persist alerts state "+
-		"and recording rules results in form of timeseries. For example, if -remoteWrite.url=http://127.0.0.1:8428 is specified, "+
+		"and recording rules results in form of timeseries. "+
+		"Supports address in the form of IP address with a port (e.g., 127.0.0.1:8428) or DNS SRV record. "+
+		"For example, if -remoteWrite.url=http://127.0.0.1:8428 is specified, "+
 		"then the alerts state will be written to http://127.0.0.1:8428/api/v1/write . See also -remoteWrite.disablePathAppend, '-remoteWrite.showURL'.")
 	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")
@@ -29,6 +31,8 @@ var (
 	bearerToken     = flag.String("remoteWrite.bearerToken", "", "Optional bearer auth token to use for -remoteWrite.url.")
 	bearerTokenFile = flag.String("remoteWrite.bearerTokenFile", "", "Optional path to bearer token file to use for -remoteWrite.url.")
 
+	idleConnectionTimeout = flag.Duration("remoteWrite.idleConnTimeout", 50*time.Second, `Defines a duration for idle (keep-alive connections) to exist. Consider settings this value less to the value of "-http.idleConnTimeout". It must prevent possible "write: broken pipe" and "read: connection reset by peer" errors.`)
+
 	maxQueueSize  = flag.Int("remoteWrite.maxQueueSize", 1e5, "Defines the max number of pending datapoints to remote write endpoint")
 	maxBatchSize  = flag.Int("remoteWrite.maxBatchSize", 1e3, "Defines max number of timeseries to be flushed at once")
 	concurrency   = flag.Int("remoteWrite.concurrency", 1, "Defines number of writers for concurrent writing into remote write endpoint")
@@ -69,6 +73,8 @@ func Init(ctx context.Context) (*Client, error) {
 	if err != nil {
 		return nil, fmt.Errorf("failed to create transport: %w", err)
 	}
+	t.IdleConnTimeout = *idleConnectionTimeout
+	t.DialContext = httputils.GetStatDialFunc("vmalert_remotewrite")
 
 	endpointParams, err := flagutil.ParseJSONMap(*oauth2EndpointParams)
 	if err != nil {

app/vmalert/replay.go

@@ -15,9 +15,10 @@ import (
 
 var (
 	replayFrom = flag.String("replay.timeFrom", "",
-		"The time filter in RFC3339 format to select time series with timestamp equal or higher than provided value. E.g. '2020-01-01T20:07:00Z'")
+		"The time filter in RFC3339 format to start the replay from. E.g. '2020-01-01T20:07:00Z'")
 	replayTo = flag.String("replay.timeTo", "",
-		"The time filter in RFC3339 format to select timeseries with timestamp equal or lower than provided value. E.g. '2020-01-01T20:07:00Z'")
+		"The time filter in RFC3339 format to finish the replay by. E.g. '2020-01-01T20:07:00Z'. "+
+			"By default, is set to the current time.")
 	replayRulesDelay = flag.Duration("replay.rulesDelay", time.Second,
 		"Delay between rules evaluation within the group. Could be important if there are chained rules inside the group "+
 			"and processing need to wait for previous rule results to be persisted by remote storage before evaluating the next rule."+
@@ -36,14 +37,20 @@ func replay(groupsCfg []config.Group, qb datasource.QuerierBuilder, rw remotewri
 	}
 	tFrom, err := time.Parse(time.RFC3339, *replayFrom)
 	if err != nil {
-		return fmt.Errorf("failed to parse %q: %w", *replayFrom, err)
+		return fmt.Errorf("failed to parse replay.timeFrom=%q: %w", *replayFrom, err)
 	}
-	tTo, err := time.Parse(time.RFC3339, *replayTo)
-	if err != nil {
-		return fmt.Errorf("failed to parse %q: %w", *replayTo, err)
+
+	// use tFrom location for default value, otherwise filters could have different locations
+	tTo := time.Now().In(tFrom.Location())
+	if *replayTo != "" {
+		tTo, err = time.Parse(time.RFC3339, *replayTo)
+		if err != nil {
+			return fmt.Errorf("failed to parse replay.timeTo=%q: %w", *replayTo, err)
+		}
 	}
+
 	if !tTo.After(tFrom) {
-		return fmt.Errorf("replay.timeTo must be bigger than replay.timeFrom")
+		return fmt.Errorf("replay.timeTo=%v must be bigger than replay.timeFrom=%v", tTo, tFrom)
 	}
 	labels := make(map[string]string)
 	for _, s := range *externalLabels {
@@ -68,9 +75,13 @@ func replay(groupsCfg []config.Group, qb datasource.QuerierBuilder, rw remotewri
 		ng := rule.NewGroup(cfg, qb, *evaluationInterval, labels)
 		total += ng.Replay(tFrom, tTo, rw, *replayMaxDatapoints, *replayRuleRetryAttempts, *replayRulesDelay, *disableProgressBar)
 	}
-	logger.Infof("replay finished! Imported %d samples", total)
-	if rw != nil {
-		return rw.Close()
+	logger.Infof("replay evaluation finished, generated %d samples", total)
+	if err := rw.Close(); err != nil {
+		return err
+	}
+	droppedRows := remotewrite.GetDroppedRows()
+	if droppedRows > 0 {
+		return fmt.Errorf("failed to push all generated samples to remote write url, dropped %d samples out of %d", droppedRows, total)
 	}
 	return nil
 }

app/vmalert/replay_test.go

@@ -8,6 +8,7 @@ import (
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/config"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/remotewrite"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promutils"
 )
 
@@ -161,7 +162,7 @@ func TestReplay(t *testing.T) {
 			*replayFrom = tc.from
 			*replayTo = tc.to
 			*replayMaxDatapoints = tc.maxDP
-			if err := replay(tc.cfg, tc.qb, nil); err != nil {
+			if err := replay(tc.cfg, tc.qb, &remotewrite.DebugClient{}); err != nil {
 				t.Fatalf("replay failed: %s", err)
 			}
 			if len(tc.qb.registry) > 0 {

app/vmalert/rule/group.go

@@ -9,10 +9,11 @@ import (
 	"hash/fnv"
 	"net/url"
 	"strconv"
-	"strings"
 	"sync"
 	"time"
 
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
+
 	"github.com/cheggaaa/pb/v3"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/config"
@@ -724,13 +725,19 @@ func (e *executor) exec(ctx context.Context, r Rule, ts time.Time, resolveDurati
 	return errGr.Err()
 }
 
+var bbPool bytesutil.ByteBufferPool
+
 // getStaleSeries checks whether there are stale series from previously sent ones.
 func (e *executor) getStaleSeries(r Rule, tss []prompbmarshal.TimeSeries, timestamp time.Time) []prompbmarshal.TimeSeries {
+	bb := bbPool.Get()
+	defer bbPool.Put(bb)
+
 	ruleLabels := make(map[string][]prompbmarshal.Label, len(tss))
 	for _, ts := range tss {
-		// convert labels to strings so we can compare with previously sent series
-		key := labelsToString(ts.Labels)
-		ruleLabels[key] = ts.Labels
+		// convert labels to strings, so we can compare with previously sent series
+		bb.B = labelsToString(bb.B, ts.Labels)
+		ruleLabels[string(bb.B)] = ts.Labels
+		bb.Reset()
 	}
 
 	rID := r.ID()
@@ -776,21 +783,20 @@ func (e *executor) purgeStaleSeries(activeRules []Rule) {
 	e.previouslySentSeriesToRWMu.Unlock()
 }
 
-func labelsToString(labels []prompbmarshal.Label) string {
-	var b strings.Builder
-	b.WriteRune('{')
+func labelsToString(dst []byte, labels []prompbmarshal.Label) []byte {
+	dst = append(dst, '{')
 	for i, label := range labels {
 		if len(label.Name) == 0 {
-			b.WriteString("__name__")
+			dst = append(dst, "__name__"...)
 		} else {
-			b.WriteString(label.Name)
+			dst = append(dst, label.Name...)
 		}
-		b.WriteRune('=')
-		b.WriteString(strconv.Quote(label.Value))
+		dst = append(dst, '=')
+		dst = strconv.AppendQuote(dst, label.Value)
 		if i < len(labels)-1 {
-			b.WriteRune(',')
+			dst = append(dst, ',')
 		}
 	}
-	b.WriteRune('}')
-	return b.String()
+	dst = append(dst, '}')
+	return dst
 }

app/vmalert/rule/group_timing_test.go

@@ -0,0 +1,36 @@
+package rule
+
+import (
+	"fmt"
+	"testing"
+	"time"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
+)
+
+func BenchmarkGetStaleSeries(b *testing.B) {
+	ts := time.Now()
+	n := 100
+	payload := make([]prompbmarshal.TimeSeries, n)
+	for i := 0; i < n; i++ {
+		s := fmt.Sprintf("%d", i)
+		labels := toPromLabels(b,
+			"__name__", "foo", ""+
+				"instance", s,
+			"job", s,
+			"state", s,
+		)
+		payload = append(payload, newTimeSeriesPB([]float64{1}, []int64{ts.Unix()}, labels))
+	}
+
+	e := &executor{
+		previouslySentSeriesToRW: make(map[uint64]map[string][]prompbmarshal.Label),
+	}
+	ar := &AlertingRule{RuleID: 1}
+
+	b.ResetTimer()
+	b.ReportAllocs()
+	for i := 0; i < b.N; i++ {
+		e.getStaleSeries(ar, payload, ts)
+	}
+}

app/vmalert/rule/rule.go

@@ -32,7 +32,7 @@ type Rule interface {
 	close()
 }
 
-var errDuplicate = errors.New("result contains metrics with the same labelset after applying rule labels. See https://docs.victoriametrics.com/vmalert/#series-with-the-same-labelset for details")
+var errDuplicate = errors.New("result contains metrics with the same labelset during evaluation. See https://docs.victoriametrics.com/vmalert/#series-with-the-same-labelset for details")
 
 type ruleState struct {
 	sync.RWMutex

app/vmalert/rule/test_helpers.go

@@ -95,7 +95,7 @@ func metricWithLabels(t *testing.T, labels ...string) datasource.Metric {
 	return m
 }
 
-func toPromLabels(t *testing.T, labels ...string) []prompbmarshal.Label {
+func toPromLabels(t testing.TB, labels ...string) []prompbmarshal.Label {
 	t.Helper()
 	if len(labels) == 0 || len(labels)%2 != 0 {
 		t.Fatalf("expected to get even number of labels")

app/vmalert/web.go

@@ -19,7 +19,7 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/procutil"
 )
 
-var reloadAuthKey = flagutil.NewPassword("reloadAuthKey", "Auth key for /-/reload http endpoint. It must be passed as authKey=...")
+var reloadAuthKey = flagutil.NewPassword("reloadAuthKey", "Auth key for /-/reload http endpoint. It must be passed via authKey query arg. It overrides httpAuth.* settings.")
 
 var (
 	apiLinks = [][2]string{
@@ -30,9 +30,9 @@ var (
 		{fmt.Sprintf("api/v1/alert?%s=<int>&%s=<int>", paramGroupID, paramAlertID), "get alert status by group and alert ID"},
 	}
 	systemLinks = [][2]string{
-		{"/flags", "command-line flags"},
-		{"/metrics", "list of application metrics"},
-		{"/-/reload", "reload configuration"},
+		{"flags", "command-line flags"},
+		{"metrics", "list of application metrics"},
+		{"-/reload", "reload configuration"},
 	}
 	navItems = []tpl.NavItem{
 		{Name: "vmalert", Url: "."},
@@ -176,7 +176,6 @@ func (rh *requestHandler) handler(w http.ResponseWriter, r *http.Request) bool {
 		return true
 
 	default:
-		httpserver.Errorf(w, r, "unsupported path requested: %q ", r.URL.Path)
 		return false
 	}
 }

app/vmauth/Makefile

@@ -87,6 +87,9 @@ vmauth-linux-ppc64le:
 vmauth-linux-s390x:
 	APP_NAME=vmauth CGO_ENABLED=0 GOOS=linux GOARCH=s390x $(MAKE) app-local-goos-goarch
 
+vmauth-linux-loong64:
+	APP_NAME=vmauth CGO_ENABLED=0 GOOS=linux GOARCH=loong64 $(MAKE) app-local-goos-goarch
+
 vmauth-linux-386:
 	APP_NAME=vmauth CGO_ENABLED=0 GOOS=linux GOARCH=386 $(MAKE) app-local-goos-goarch
 

app/vmauth/auth_config.go

@@ -83,6 +83,7 @@ type UserInfo struct {
 
 	concurrencyLimitCh      chan struct{}
 	concurrencyLimitReached *metrics.Counter
+	overrideHostHeader      bool
 
 	rt http.RoundTripper
 
@@ -149,6 +150,15 @@ func (h *Header) MarshalYAML() (interface{}, error) {
 	return h.sOriginal, nil
 }
 
+func overrideHostHeader(headers []*Header) bool {
+	for _, h := range headers {
+		if h.Name == "Host" && h.Value == "" {
+			return true
+		}
+	}
+	return false
+}
+
 // URLMap is a mapping from source paths to target urls.
 type URLMap struct {
 	// SrcPaths is an optional list of regular expressions, which must match the request path.
@@ -353,7 +363,7 @@ func (up *URLPrefix) discoverBackendAddrsIfNeeded() {
 				logger.Warnf("cannot discover backend SRV records for %s: %s; use it literally", bu, err)
 				resolvedAddrs = []string{host}
 			} else {
-				resolvedAddrs := make([]string, len(addrs))
+				resolvedAddrs = make([]string, len(addrs))
 				for i, addr := range addrs {
 					resolvedAddrs[i] = fmt.Sprintf("%s:%d", addr.Target, addr.Port)
 				}
@@ -380,6 +390,7 @@ func (up *URLPrefix) discoverBackendAddrsIfNeeded() {
 	var busNew []*backendURL
 	for _, bu := range up.busOriginal {
 		host := bu.Hostname()
+		host = strings.TrimPrefix(host, "srv+")
 		port := bu.Port()
 		for _, addr := range hostToAddrs[host] {
 			buCopy := *bu
@@ -693,6 +704,14 @@ func loadAuthConfig() (bool, error) {
 	authConfig.Store(ac)
 	authConfigData.Store(&data)
 	authUsers.Store(&m)
+	if prevAc != nil {
+		// explicilty unregister metrics, since all summary type metrics
+		// are registered at global state of metrics package
+		// and must be removed from it to release memory.
+		// Metrics must be unregistered only after atomic.Value.Store calls above
+		// Otherwise it may lead to metric gaps, since UnregisterAllMetrics is slow operation
+		prevAc.ms.UnregisterAllMetrics()
+	}
 
 	return true, nil
 }
@@ -729,6 +748,7 @@ func parseAuthConfig(data []byte) (*AuthConfig, error) {
 		if err := ui.initURLs(); err != nil {
 			return nil, err
 		}
+		ui.overrideHostHeader = overrideHostHeader(ui.HeadersConf.RequestHeaders)
 
 		metricLabels, err := ui.getMetricLabels()
 		if err != nil {
@@ -793,6 +813,7 @@ func parseAuthConfigUsers(ac *AuthConfig) (map[string]*UserInfo, error) {
 		_ = ac.ms.GetOrCreateGauge(`vmauth_user_concurrent_requests_current`+metricLabels, func() float64 {
 			return float64(len(ui.concurrencyLimitCh))
 		})
+		ui.overrideHostHeader = overrideHostHeader(ui.HeadersConf.RequestHeaders)
 
 		rt, err := newRoundTripper(ui.TLSCAFile, ui.TLSCertFile, ui.TLSKeyFile, ui.TLSServerName, ui.TLSInsecureSkipVerify)
 		if err != nil {
@@ -1003,6 +1024,8 @@ func (up *URLPrefix) sanitizeAndInitialize() error {
 		}
 	}
 	up.bus.Store(&bus)
+	up.nextDiscoveryDeadline.Store(0)
+	up.n.Store(0)
 
 	return nil
 }

app/vmauth/auth_config_test.go

@@ -685,6 +685,70 @@ func isSetBool(boolP *bool, expectedValue bool) bool {
 	return *boolP == expectedValue
 }
 
+func TestGetLeastLoadedBackendURL(t *testing.T) {
+	up := mustParseURLs([]string{
+		"http://node1:343",
+		"http://node2:343",
+		"http://node3:343",
+	})
+	up.loadBalancingPolicy = "least_loaded"
+
+	fn := func(ns ...int) {
+		t.Helper()
+		bus := up.bus.Load()
+		pbus := *bus
+		for i, b := range pbus {
+			got := int(b.concurrentRequests.Load())
+			exp := ns[i]
+			if got != exp {
+				t.Fatalf("expected %q to have %d concurrent requests; got %d instead", b.url, exp, got)
+			}
+		}
+	}
+
+	up.getBackendURL()
+	fn(0, 1, 0)
+	up.getBackendURL()
+	fn(0, 1, 1)
+	up.getBackendURL()
+	fn(1, 1, 1)
+
+	up.getBackendURL()
+	up.getBackendURL()
+	fn(1, 2, 2)
+
+	bus := up.bus.Load()
+	pbus := *bus
+	pbus[0].concurrentRequests.Add(2)
+	pbus[2].concurrentRequests.Add(5)
+	fn(3, 2, 7)
+
+	up.getBackendURL()
+	fn(3, 3, 7)
+
+	up.getBackendURL()
+	fn(3, 4, 7)
+
+	up.getBackendURL()
+	fn(4, 4, 7)
+
+	up.getBackendURL()
+	fn(5, 4, 7)
+
+	up.getBackendURL()
+	fn(5, 5, 7)
+
+	up.getBackendURL()
+	fn(6, 5, 7)
+
+	up.getBackendURL()
+	fn(6, 6, 7)
+
+	up.getBackendURL()
+	up.getBackendURL()
+	fn(7, 7, 7)
+}
+
 func getRegexs(paths []string) []*Regex {
 	var sps []*Regex
 	for _, path := range paths {

app/vmauth/main.go

@@ -37,18 +37,20 @@ var (
 		"With enabled proxy protocol http server cannot serve regular /metrics endpoint. Use -pushmetrics.url for metrics pushing")
 	maxIdleConnsPerBackend = flag.Int("maxIdleConnsPerBackend", 100, "The maximum number of idle connections vmauth can open per each backend host. "+
 		"See also -maxConcurrentRequests")
+	idleConnTimeout = flag.Duration("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.`)
 	responseTimeout       = flag.Duration("responseTimeout", 5*time.Minute, "The timeout for receiving a response from backend")
 	maxConcurrentRequests = flag.Int("maxConcurrentRequests", 1000, "The maximum number of concurrent requests vmauth can process. Other requests are rejected with "+
 		"'429 Too Many Requests' http status code. See also -maxConcurrentPerUserRequests and -maxIdleConnsPerBackend command-line options")
 	maxConcurrentPerUserRequests = flag.Int("maxConcurrentPerUserRequests", 300, "The maximum number of concurrent requests vmauth can process per each configured user. "+
 		"Other requests are rejected with '429 Too Many Requests' http status code. See also -maxConcurrentRequests command-line option and max_concurrent_requests option "+
 		"in per-user config")
-	reloadAuthKey        = flagutil.NewPassword("reloadAuthKey", "Auth key for /-/reload http endpoint. It must be passed as authKey=...")
+	reloadAuthKey        = flagutil.NewPassword("reloadAuthKey", "Auth key for /-/reload http endpoint. It must be passed via authKey query arg. It overrides httpAuth.* settings.")
 	logInvalidAuthTokens = flag.Bool("logInvalidAuthTokens", false, "Whether to log requests with invalid auth tokens. "+
 		`Such requests are always counted at vmauth_http_request_errors_total{reason="invalid_auth_token"} metric, which is exposed at /metrics page`)
 	failTimeout               = flag.Duration("failTimeout", 3*time.Second, "Sets a delay period for load balancing to skip a malfunctioning backend")
 	maxRequestBodySizeToRetry = flagutil.NewBytes("maxRequestBodySizeToRetry", 16*1024, "The maximum request body size, which can be cached and re-tried at other backends. "+
-		"Bigger values may require more memory")
+		"Bigger values may require more memory. Negative or zero values disable request body caching and retries.")
 	backendTLSInsecureSkipVerify = flag.Bool("backend.tlsInsecureSkipVerify", false, "Whether to skip TLS verification when connecting to backends over HTTPS. "+
 		"See https://docs.victoriametrics.com/vmauth/#backend-tls-setup")
 	backendTLSCAFile = flag.String("backend.TLSCAFile", "", "Optional path to TLS root CA file, which is used for TLS verification when connecting to backends over HTTPS. "+
@@ -198,12 +200,13 @@ func processRequest(w http.ResponseWriter, r *http.Request, ui *UserInfo) {
 		up, hc = ui.DefaultURL, ui.HeadersConf
 		isDefault = true
 	}
-	maxAttempts := up.getBackendsCount()
-	if maxAttempts > 1 {
-		r.Body = &readTrackingBody{
-			r: r.Body,
-		}
+	// caching makes sense only for positive non zero size
+	if maxRequestBodySizeToRetry.IntN() > 0 {
+		rtb := getReadTrackingBody(r.Body, int(r.ContentLength))
+		defer putReadTrackingBody(rtb)
+		r.Body = rtb
 	}
+	maxAttempts := up.getBackendsCount()
 	for i := 0; i < maxAttempts; i++ {
 		bu := up.getBackendURL()
 		targetURL := bu.url
@@ -235,7 +238,7 @@ func tryProcessingRequest(w http.ResponseWriter, r *http.Request, targetURL *url
 	req := sanitizeRequestHeaders(r)
 	req.URL = targetURL
 
-	if req.URL.Scheme == "https" {
+	if req.URL.Scheme == "https" || ui.overrideHostHeader {
 		// Override req.Host only for https requests, since https server verifies hostnames during TLS handshake,
 		// so it expects the targetURL.Host in the request.
 		// There is no need in overriding the req.Host for http requests, since it is expected that backend server
@@ -243,8 +246,10 @@ func tryProcessingRequest(w http.ResponseWriter, r *http.Request, targetURL *url
 		req.Host = targetURL.Host
 	}
 	updateHeadersByConfig(req.Header, hc.RequestHeaders)
-	res, err := ui.rt.RoundTrip(req)
+	var trivialRetries int
 	rtb, rtbOK := req.Body.(*readTrackingBody)
+again:
+	res, err := ui.rt.RoundTrip(req)
 	if err != nil {
 		if errors.Is(err, context.Canceled) || errors.Is(err, context.DeadlineExceeded) {
 			// Do not retry canceled or timed out requests
@@ -267,6 +272,12 @@ func tryProcessingRequest(w http.ResponseWriter, r *http.Request, targetURL *url
 			ui.backendErrors.Inc()
 			return true
 		}
+		// one time retry trivial network errors, such as proxy idle timeout misconfiguration
+		// or socket close by OS
+		if (netutil.IsTrivialNetworkError(err) || errors.Is(err, io.EOF)) && trivialRetries < 1 {
+			trivialRetries++
+			goto again
+		}
 		// Retry the request if its body wasn't read yet. This usually means that the backend isn't reachable.
 		remoteAddr := httpserver.GetQuotedRemoteAddr(r)
 		// NOTE: do not use httpserver.GetRequestURI
@@ -434,6 +445,7 @@ func newRoundTripper(caFileOpt, certFileOpt, keyFileOpt, serverNameOpt string, i
 	tr.ResponseHeaderTimeout = *responseTimeout
 	// Automatic compression must be disabled in order to fix https://github.com/VictoriaMetrics/VictoriaMetrics/issues/535
 	tr.DisableCompression = true
+	tr.IdleConnTimeout = *idleConnTimeout
 	tr.MaxIdleConnsPerHost = *maxIdleConnsPerBackend
 	if tr.MaxIdleConns != 0 && tr.MaxIdleConns < tr.MaxIdleConnsPerHost {
 		tr.MaxIdleConns = tr.MaxIdleConnsPerHost
@@ -494,9 +506,6 @@ type readTrackingBody struct {
 	// bufComplete is set to true when buf contains complete request body read from r.
 	bufComplete bool
 
-	// needReadBuf is set to true when Read() must be performed from buf instead of r.
-	needReadBuf bool
-
 	// offset is an offset at buf for the next data read if needReadBuf is set to true.
 	offset int
 }
@@ -504,50 +513,63 @@ type readTrackingBody struct {
 // Read implements io.Reader interface
 // tracks body reading requests
 func (rtb *readTrackingBody) Read(p []byte) (int, error) {
-	if rtb.needReadBuf {
-		if rtb.offset >= len(rtb.buf) {
-			return 0, io.EOF
+	if rtb.offset < len(rtb.buf) {
+		if rtb.cannotRetry {
+			return 0, fmt.Errorf("cannot retry reading data from buf")
 		}
-		n := copy(p, rtb.buf[rtb.offset:])
-		rtb.offset += n
-		return n, nil
+		nb := copy(p, rtb.buf[rtb.offset:])
+		rtb.offset += nb
+		if rtb.bufComplete {
+			if rtb.offset == len(rtb.buf) {
+				return nb, io.EOF
+			}
+			return nb, nil
+		}
+		if nb < len(p) {
+			nr, err := rtb.readFromStream(p[nb:])
+			return nb + nr, err
+		}
+		return nb, nil
 	}
+	if rtb.bufComplete {
+		return 0, io.EOF
+	}
+	return rtb.readFromStream(p)
+}
 
+func (rtb *readTrackingBody) readFromStream(p []byte) (int, error) {
 	if rtb.r == nil {
 		return 0, fmt.Errorf("cannot read data after closing the reader")
 	}
-
 	n, err := rtb.r.Read(p)
 	if rtb.cannotRetry {
 		return n, err
 	}
-	if len(rtb.buf)+n > maxRequestBodySizeToRetry.IntN() {
+	if rtb.offset+n > maxRequestBodySizeToRetry.IntN() {
+		rtb.cannotRetry = true
+	}
+	if n > 0 {
+		rtb.offset += n
+		rtb.buf = append(rtb.buf, p[:n]...)
+	}
+	if err != nil {
+		if err == io.EOF {
+			rtb.bufComplete = true
+			return n, err
+		}
 		rtb.cannotRetry = true
 		return n, err
 	}
-	rtb.buf = append(rtb.buf, p[:n]...)
-	if err == io.EOF {
-		rtb.bufComplete = true
-	}
-	return n, err
+	return n, nil
 }
 
 func (rtb *readTrackingBody) canRetry() bool {
-	if rtb.cannotRetry {
-		return false
-	}
-	if len(rtb.buf) > 0 && !rtb.needReadBuf {
-		return false
-	}
-	return true
+	return !rtb.cannotRetry
 }
 
 // Close implements io.Closer interface.
 func (rtb *readTrackingBody) Close() error {
 	rtb.offset = 0
-	if rtb.bufComplete {
-		rtb.needReadBuf = true
-	}
 
 	// Close rtb.r only if the request body is completely read or if it is too big.
 	// http.Roundtrip performs body.Close call even without any Read calls,
@@ -563,3 +585,38 @@ func (rtb *readTrackingBody) Close() error {
 
 	return nil
 }
+
+var readTrackingBodyPool sync.Pool
+
+func getReadTrackingBody(origin io.ReadCloser, b int) *readTrackingBody {
+	bufSize := 1024
+	if b > 0 && b < maxRequestBodySizeToRetry.IntN() {
+		bufSize = b
+	}
+	v := readTrackingBodyPool.Get()
+	if v == nil {
+		v = &readTrackingBody{
+			buf: make([]byte, 0, bufSize),
+		}
+	}
+	rtb := v.(*readTrackingBody)
+	rtb.r = origin
+	if bufSize > cap(rtb.buf) {
+		rtb.buf = make([]byte, 0, bufSize)
+	}
+
+	return rtb
+}
+
+func putReadTrackingBody(rtb *readTrackingBody) {
+	if rtb.r != nil {
+		_ = rtb.r.Close()
+	}
+	rtb.r = nil
+	rtb.buf = rtb.buf[:0]
+	rtb.offset = 0
+	rtb.cannotRetry = false
+	rtb.bufComplete = false
+
+	readTrackingBodyPool.Put(rtb)
+}

app/vmauth/main_test.go

@@ -55,9 +55,6 @@ func TestReadTrackingBodyRetryFailure(t *testing.T) {
 		if n != 1 {
 			t.Fatalf("unexpected number of bytes read; got %d; want 1", n)
 		}
-		if rtb.canRetry() {
-			t.Fatalf("canRetry() must return false")
-		}
 		data, err := io.ReadAll(rtb)
 		if err != nil {
 			t.Fatalf("unexpected error when reading all the data: %s", err)
@@ -85,6 +82,128 @@ func TestReadTrackingBodyRetryFailure(t *testing.T) {
 	f(newTestString(2 * maxRequestBodySizeToRetry.IntN()))
 }
 
+// request body not over maxRequestBodySizeToRetry
+// 1. When writing data downstream, buf only caches part of the data because the downstream connection is disconnected.
+// 2. retry request: because buf caches some data, first read buf and then read stream when retrying
+// 3. retry request: the data has been read to buf in the second step. if the request fails, retry to read all buf later.
+func TestRetryReadSuccessAfterPartialRead(t *testing.T) {
+	f := func(s string) {
+		rtb := &readTrackingBody{
+			r:   io.NopCloser(bytes.NewBufferString(s)),
+			buf: make([]byte, 0, len(s)),
+		}
+
+		var data []byte
+		var err error
+		halfSize := len(s) / 2
+		if halfSize == 0 {
+			halfSize = 100
+		}
+		buf := make([]byte, halfSize)
+		var n int
+
+		// read part of the data
+		n, err = rtb.Read(buf[:])
+		data = append(data, buf[:n]...)
+		if err != nil && err != io.EOF {
+			t.Fatalf("unexpected error: %s", err)
+		}
+
+		// request failed when output stream is closed (eg: server connection reset)
+		// would close the reader
+		if err := rtb.Close(); err != nil {
+			t.Fatalf("unexpected error when closing readTrackingBody: %s", err)
+		}
+		if !rtb.canRetry() {
+			t.Fatalf("canRetry() must return true")
+		}
+
+		// retry read (read buf + remaining data)
+		data = data[:0]
+		err = nil
+		for err == nil {
+			n, err = rtb.Read(buf[:])
+			data = append(data, buf[:n]...)
+		}
+		if err != io.EOF {
+			t.Fatalf("unexpected error: %s", err)
+		}
+		if string(data) != s {
+			t.Fatalf("unexpected data read; got\n%s\nwant\n%s", data, s)
+		}
+		// cannotRetry return false
+		// because the request data is not over maxRequestBodySizeToRetry limit
+		if !rtb.canRetry() {
+			t.Fatalf("canRetry() must return true")
+		}
+	}
+
+	f("")
+	f("foo")
+	f("foobar")
+	f(newTestString(maxRequestBodySizeToRetry.IntN()))
+}
+
+// request body over maxRequestBodySizeToRetry
+// 1. When writing data downstream, buf only caches part of the data because the downstream connection is disconnected.
+// 2. retry request: because buf caches some data, first read buf and then read stream when retrying
+// 3. retry request: the data has been read to buf in the second step. if the request fails, retry to read all buf later.
+func TestRetryReadSuccessAfterPartialReadAndCannotRetryAgain(t *testing.T) {
+	f := func(s string) {
+		rtb := &readTrackingBody{
+			r:   io.NopCloser(bytes.NewBufferString(s)),
+			buf: make([]byte, 0, len(s)),
+		}
+
+		var data []byte
+		var err error
+		halfSize := len(s) / 2
+		if halfSize == 0 {
+			halfSize = 100
+		}
+		buf := make([]byte, halfSize)
+		var n int
+
+		// read part of the data
+		n, err = rtb.Read(buf[:])
+		data = append(data, buf[:n]...)
+		if err != nil && err != io.EOF {
+			t.Fatalf("unexpected error: %s", err)
+		}
+
+		// request failed when output stream is closed (eg: server connection reset)
+		if err := rtb.Close(); err != nil {
+			t.Fatalf("unexpected error when closing readTrackingBody: %s", err)
+		}
+		if !rtb.canRetry() {
+			t.Fatalf("canRetry() must return true")
+		}
+
+		// retry read (read buf + remaining data)
+		data = data[:0]
+		err = nil
+		for err == nil {
+			n, err = rtb.Read(buf[:])
+			data = append(data, buf[:n]...)
+		}
+		if err != io.EOF {
+			t.Fatalf("unexpected error: %s", err)
+		}
+		if string(data) != s {
+			t.Fatalf("unexpected data read; got\n%s\nwant\n%s", data, s)
+		}
+
+		// cannotRetry returns true
+		// because the request data is over maxRequestBodySizeToRetry limit
+		if rtb.canRetry() {
+			t.Fatalf("canRetry() must return false")
+		}
+	}
+
+	f(newTestString(maxRequestBodySizeToRetry.IntN() + 1))
+	f(newTestString(2 * maxRequestBodySizeToRetry.IntN()))
+}
+
 func newTestString(sLen int) string {
 	return string(make([]byte, sLen))
 }

app/vmauth/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