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/...
 
@@ -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/).
 
@@ -86,7 +85,6 @@ VictoriaMetrics has the following prominent features:
   * [Prometheus exposition format](#how-to-import-data-in-prometheus-exposition-format).
   * [InfluxDB line protocol](#how-to-send-data-from-influxdb-compatible-agents-such-as-telegraf) over HTTP, TCP and UDP.
   * [Graphite plaintext protocol](#how-to-send-data-from-graphite-compatible-agents-such-as-statsd) with [tags](https://graphite.readthedocs.io/en/latest/tags.html#carbon).
-  * [Statsd plaintext protocol](#how-to-send-data-from-statsd-compatible-clients)
   * [OpenTSDB put message](#sending-data-via-telnet-put-protocol).
   * [HTTP OpenTSDB /api/put requests](#sending-opentsdb-data-via-http-apiput-requests).
   * [JSON line format](#how-to-import-data-in-json-line-format).
@@ -117,7 +115,7 @@ 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.
@@ -139,7 +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
 
@@ -182,24 +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
 
@@ -338,8 +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.
@@ -702,79 +682,6 @@ The `/api/v1/export` endpoint should return the following response:
 {"metric":{"__name__":"measurement_field2","tag1":"value1","tag2":"value2"},"values":[1.23],"timestamps":[1695902762311]}
 ```
 
-## How to send data from StatsD-compatible clients
-
-VictoriaMetrics supports extended StatsD protocol. Currently, it supports `tags` and `value packing` 
-extensions provided by [dogstatsd](https://docs.datadoghq.com/developers/dogstatsd/datagram_shell). 
-During parsing, metric's `<TYPE>` is added as a special label `__statsd_metric_type__`. 
-
-It is strongly advisable to configure streaming aggregation for each metric type. This process serves two primary 
-objectives: 
-* transformation of the StatsD data model into the VictoriaMetrics data model. VictoriaMetrics requires a consistent 
-interval between data points. 
-* minimizing of the disk space utilization and overall resource consumption during data ingestion.
-
-VictoriaMetrics supports the following metric [types](https://docs.datadoghq.com/metrics/types):
-
-* `c` Counter type.
-* `g`  Gauge type.
-* `ms` Timer type.
-* `m` Meters type.
-* `h` Histogram type.
-* `s` Set type with only numeric values.
-* `d` Distribution type.
-
-_The `Not Assigned` type is not supported due to the ambiguity surrounding its aggregation method. 
-The correct aggregation method cannot be determined for the undefined metric._
-
-Enable Statsd receiver in VictoriaMetrics by setting `-statsdListenAddr` command line flag and configure [stream aggregation](https://docs.victoriametrics.com/stream-aggregation/). 
-For instance, the following command will enable StatsD receiver in VictoriaMetrics on TCP and UDP port `8125`:
-
-```console
-/path/to/victoria-metrics-prod -statsdListenAddr=:8125 -streamAggr.config=statsd_aggr.yaml
-```
-
-Example of stream aggregation config:
-
-```yaml
-# statsd_aggr.yaml
-# `last` output will keep the last sample on `interval`
-# for each series that match `{__statsd_metric_type__="g"}` selector
-- match: '{__statsd_metric_type__="g"}'
-  outputs: [last]
-  interval: 1m
-```
-
-Example for writing data with StatsD plaintext protocol to local VictoriaMetrics using `nc`:
-
-```console
-echo "foo.bar:123|g|#tag1:baz" | nc -N localhost 8125
-```
-
-_An arbitrary number of lines delimited by `\n` (aka newline char) can be sent in one go._
-
-Explicit setting of timestamps is not supported for StatsD protocol. Timestamp is set to the current time when 
-VictoriaMetrics or vmagent receives it.
-
-Once ingested, the data can be read via [/api/v1/export](#how-to-export-data-in-json-line-format) endpoint:
-
-```console
-curl -G 'http://localhost:8428/api/v1/export' -d 'match={__name__=~"foo.*"}'
-```
-
-_Please note, with stream aggregation enabled data will become available only after specified aggregation interval._
-
-The `/api/v1/export` endpoint should return the following response:
-
-```json
-{"metric":{"__name__":"foo.bar:1m_last","__statsd_metric_type__":"g","tag1":"baz"},"values":[123],"timestamps":[1715843939000]}
-```
-
-Some examples of compatible statsd clients:
-- [statsd-instrument](https://github.com/Shopify/statsd-instrument)
-- [dogstatsd-ruby](https://github.com/DataDog/dogstatsd-ruby)
-- [go-statsd-client](https://github.com/cactus/go-statsd-client)
-
 ## How to send data from Graphite-compatible agents such as [StatsD](https://github.com/etsy/statsd)
 
 Enable Graphite receiver in VictoriaMetrics by setting `-graphiteListenAddr` command line flag. For instance,
@@ -793,6 +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:
@@ -1188,13 +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
 
@@ -1205,7 +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
 
@@ -1430,7 +1344,6 @@ Additionally, VictoriaMetrics can accept metrics via the following popular data
 * DataDog `submit metrics` API. See [these docs](#how-to-send-data-from-datadog-agent) for details.
 * InfluxDB line protocol. See [these docs](#how-to-send-data-from-influxdb-compatible-agents-such-as-telegraf) for details.
 * Graphite plaintext protocol. See [these docs](#how-to-send-data-from-graphite-compatible-agents-such-as-statsd) for details.
-* Statsd plaintext protocol. See [these docs](#how-to-send-data-from-statsd-compatible-clients) for details.
 * OpenTelemetry http API. See [these docs](#sending-data-via-opentelemetry) for details.
 * OpenTSDB telnet put protocol. See [these docs](#sending-data-via-telnet-put-protocol) for details.
 * OpenTSDB http `/api/put` protocol. See [these docs](#sending-opentsdb-data-via-http-apiput-requests) for details.
@@ -1624,6 +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
@@ -2404,7 +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.
@@ -2430,7 +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`
@@ -2450,7 +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.
 
@@ -2512,7 +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.
 
@@ -2706,7 +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.
 
@@ -2762,7 +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)
@@ -2809,6 +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
@@ -2881,9 +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
@@ -3027,7 +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)
@@ -3076,7 +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/
@@ -3093,14 +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)
@@ -3123,7 +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
@@ -3134,7 +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)
@@ -3206,12 +3171,6 @@ Pass `-help` to VictoriaMetrics in order to see the list of supported command-li
      The following optional suffixes are supported: s (second), m (minute), h (hour), d (day), w (week), y (year). If suffix isn't set, then the duration is counted in months (default 0)
   -sortLabels
      Whether to sort labels for incoming samples before writing them to storage. This may be needed for reducing memory usage at storage when the order of labels in incoming samples is random. For example, if m{k1="v1",k2="v2"} may be sent as m{k2="v2",k1="v1"}. Enabled sorting for labels can slow down ingestion performance a bit
-  -statsd.disableAggregationEnforcement
-    	Whether to disable streaming aggregation requirement check. It's recommended to run statsdServer with pre-configured streaming aggregation to decrease load at database.
-  -statsdListenAddr string
-    	TCP and UDP address to listen for Statsd plaintext data. Usually :8125 must be set. Doesn't work if empty. See also -statsdListenAddr.useProxyProtocol
-  -statsdListenAddr.useProxyProtocol
-    	Whether to use proxy protocol for connections accepted at -statsdListenAddr . See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt
   -storage.cacheSizeIndexDBDataBlocks size
      Overrides max size for indexdb/dataBlocks cache. See https://docs.victoriametrics.com/single-server-victoriametrics/#cache-tuning
      Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB (default 0)

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/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

@@ -97,12 +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
@@ -131,9 +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 {
@@ -158,7 +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)
@@ -174,9 +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"
@@ -221,8 +215,8 @@ func readBulkLine(sc *bufio.Scanner, timeField, msgField string,
 	if ts == 0 {
 		ts = time.Now().UnixNano()
 	}
-	p.RenameField(msgField, "_msg")
-	processLogMessage(ts, p.Fields)
+	logstorage.RenameField(p.Fields, msgField, "_msg")
+	lmp.AddRow(ts, p.Fields)
 	logstorage.PutJSONParser(p)
 
 	return true, nil
@@ -272,9 +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"
 
@@ -10,6 +12,7 @@ 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.
@@ -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"
 
@@ -19,13 +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()
@@ -33,27 +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()
@@ -65,31 +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() {
@@ -108,53 +112,24 @@ func readLine(sc *bufio.Scanner, timeField, msgField string, processLogMessage f
 	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)
+	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/vlselect/logsql/hits_response.qtpl

@@ -44,7 +44,7 @@
 		hs := m[k]
 		hs.sort()
 		timestamps := hs.timestamps
-		values := hs.values
+		hits := hs.hits
 	%}
 	"fields":{%s= k %},
 	"timestamps":[
@@ -56,13 +56,14 @@
 		{% endif %}
 	],
 	"values":[
-		{% if len(values) > 0 %}
-			{%s= values[0] %}
-			{% for _, v := range values[1:] %}
-				,{%s= v %}
+		{% if len(hits) > 0 %}
+			{%dul= hits[0] %}
+			{% for _, v := range hits[1:] %}
+				,{%dul= v %}
 			{% endfor %}
 		{% endif %}
-	]
+	],
+	"total":{%dul= hs.hitsTotal %}
 }
 {% endfunc %}
 

app/vlselect/logsql/hits_response.qtpl.go

@@ -149,7 +149,7 @@ func streamhitsSeriesLine(qw422016 *qt422016.Writer, m map[string]*hitsSeries, k
 	hs := m[k]
 	hs.sort()
 	timestamps := hs.timestamps
-	values := hs.values
+	hits := hs.hits
 
 //line app/vlselect/logsql/hits_response.qtpl:48
 	qw422016.N().S(`"fields":`)
@@ -174,46 +174,50 @@ func streamhitsSeriesLine(qw422016 *qt422016.Writer, m map[string]*hitsSeries, k
 //line app/vlselect/logsql/hits_response.qtpl:56
 	qw422016.N().S(`],"values":[`)
 //line app/vlselect/logsql/hits_response.qtpl:59
-	if len(values) > 0 {
+	if len(hits) > 0 {
 //line app/vlselect/logsql/hits_response.qtpl:60
-		qw422016.N().S(values[0])
+		qw422016.N().DUL(hits[0])
 //line app/vlselect/logsql/hits_response.qtpl:61
-		for _, v := range values[1:] {
+		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().S(v)
+			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(`]}`)
-//line app/vlselect/logsql/hits_response.qtpl:67
+	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:67
+//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:67
+//line app/vlselect/logsql/hits_response.qtpl:68
 	qw422016 := qt422016.AcquireWriter(qq422016)
-//line app/vlselect/logsql/hits_response.qtpl:67
+//line app/vlselect/logsql/hits_response.qtpl:68
 	streamhitsSeriesLine(qw422016, m, k)
-//line app/vlselect/logsql/hits_response.qtpl:67
+//line app/vlselect/logsql/hits_response.qtpl:68
 	qt422016.ReleaseWriter(qw422016)
-//line app/vlselect/logsql/hits_response.qtpl:67
+//line app/vlselect/logsql/hits_response.qtpl:68
 }
 
-//line app/vlselect/logsql/hits_response.qtpl:67
+//line app/vlselect/logsql/hits_response.qtpl:68
 func hitsSeriesLine(m map[string]*hitsSeries, k string) string {
-//line app/vlselect/logsql/hits_response.qtpl:67
+//line app/vlselect/logsql/hits_response.qtpl:68
 	qb422016 := qt422016.AcquireByteBuffer()
-//line app/vlselect/logsql/hits_response.qtpl:67
+//line app/vlselect/logsql/hits_response.qtpl:68
 	writehitsSeriesLine(qb422016, m, k)
-//line app/vlselect/logsql/hits_response.qtpl:67
+//line app/vlselect/logsql/hits_response.qtpl:68
 	qs422016 := string(qb422016.B)
-//line app/vlselect/logsql/hits_response.qtpl:67
+//line app/vlselect/logsql/hits_response.qtpl:68
 	qt422016.ReleaseByteBuffer(qb422016)
-//line app/vlselect/logsql/hits_response.qtpl:67
+//line app/vlselect/logsql/hits_response.qtpl:68
 	return qs422016
-//line app/vlselect/logsql/hits_response.qtpl:67
+//line app/vlselect/logsql/hits_response.qtpl:68
 }

app/vlselect/logsql/logsql.go

@@ -6,14 +6,18 @@ import (
 	"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/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"
 )
@@ -56,6 +60,16 @@ func ProcessHitsRequest(ctx context.Context, w http.ResponseWriter, r *http.Requ
 	// 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()
@@ -75,6 +89,10 @@ func ProcessHitsRequest(ctx context.Context, w http.ResponseWriter, r *http.Requ
 		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)
@@ -87,7 +105,8 @@ func ProcessHitsRequest(ctx context.Context, w http.ResponseWriter, r *http.Requ
 				m[k] = hs
 			}
 			hs.timestamps = append(hs.timestamps, timestampStr)
-			hs.values = append(hs.values, hitsStr)
+			hs.hits = append(hs.hits, hits)
+			hs.hitsTotal += hits
 			mLock.Unlock()
 		}
 		blockResultPool.Put(bb)
@@ -99,14 +118,59 @@ func ProcessHitsRequest(ctx context.Context, w http.ResponseWriter, r *http.Requ
 		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
-	values     []string
+	hits       []uint64
 }
 
 func (hs *hitsSeries) sort() {
@@ -119,7 +183,7 @@ func (hs *hitsSeries) Len() int {
 
 func (hs *hitsSeries) Swap(i, j int) {
 	hs.timestamps[i], hs.timestamps[j] = hs.timestamps[j], hs.timestamps[i]
-	hs.values[i], hs.values[j] = hs.values[j], hs.values[i]
+	hs.hits[i], hs.hits[j] = hs.hits[j], hs.hits[i]
 }
 
 func (hs *hitsSeries) Less(i, j int) bool {
@@ -250,6 +314,38 @@ func ProcessStreamFieldValuesRequest(ctx context.Context, w http.ResponseWriter,
 	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
@@ -282,6 +378,187 @@ func ProcessStreamsRequest(ctx context.Context, w http.ResponseWriter, r *http.R
 	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
@@ -298,11 +575,36 @@ func ProcessQueryRequest(ctx context.Context, w http.ResponseWriter, r *http.Req
 		httpserver.Errorf(w, r, "%s", err)
 		return
 	}
-	if limit > 0 {
-		q.AddPipeLimit(uint64(limit))
-	}
 
 	bw := getBufferedWriter(w)
+	defer func() {
+		bw.FlushIgnoreErrors()
+		putBufferedWriter(bw)
+	}()
+	w.Header().Set("Content-Type", "application/stream+json")
+
+	if limit > 0 {
+		if q.CanReturnLastNResults() {
+			rows, err := getLastNQueryResults(ctx, tenantIDs, q, limit)
+			if err != nil {
+				httpserver.Errorf(w, r, "%s", err)
+				return
+			}
+			bb := blockResultPool.Get()
+			b := bb.B
+			for i := range rows {
+				b = logstorage.MarshalFieldsToJSON(b[:0], rows[i].fields)
+				b = append(b, '\n')
+				bw.WriteIgnoreErrors(b)
+			}
+			bb.B = b
+			blockResultPool.Put(bb)
+			return
+		}
+
+		q.AddPipeLimit(uint64(limit))
+	}
+	q.Optimize()
 
 	writeBlock := func(_ uint, timestamps []int64, columns []logstorage.BlockColumn) {
 		if len(columns) == 0 || len(columns[0].Values) == 0 {
@@ -317,20 +619,106 @@ func ProcessQueryRequest(ctx context.Context, w http.ResponseWriter, r *http.Req
 		blockResultPool.Put(bb)
 	}
 
-	w.Header().Set("Content-Type", "application/stream+json")
-	q.Optimize()
-	err = vlstorage.RunQuery(ctx, tenantIDs, q, writeBlock)
-
-	bw.FlushIgnoreErrors()
-	putBufferedWriter(bw)
-
-	if err != nil {
+	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)
@@ -373,10 +761,10 @@ func getTimeNsec(r *http.Request, argName string) (int64, bool, error) {
 	if s == "" {
 		return 0, false, nil
 	}
-	currentTimestamp := float64(time.Now().UnixNano()) / 1e9
-	secs, err := promutils.ParseTimeAt(s, currentTimestamp)
+	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 int64(secs * 1e9), true, nil
+	return nsecs, true, nil
 }

app/vlselect/main.go

@@ -1,6 +1,7 @@
 package vlselect
 
 import (
+	"context"
 	"embed"
 	"flag"
 	"fmt"
@@ -13,7 +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"
 )
 
@@ -23,7 +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 {
@@ -98,47 +98,83 @@ func RequestHandler(w http.ResponseWriter, r *http.Request) bool {
 		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
 		}
 	}
 
+	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
+	}
+
+	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":
@@ -165,6 +201,10 @@ func RequestHandler(w http.ResponseWriter, r *http.Request) bool {
 		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)
@@ -194,5 +234,7 @@ var (
 	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.1c2f4a93.css",
-    "main.js": "./static/js/main.c3285306.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.df7574389d8f8bbcf0c7.md",
+    "static/media/MetricsQL.md": "./static/media/MetricsQL.aaabf95f2c9bf356bde4.md",
     "index.html": "./index.html"
   },
   "entrypoints": [
-    "static/css/main.1c2f4a93.css",
-    "static/js/main.c3285306.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.c3285306.js"></script><link href="./static/css/main.1c2f4a93.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

@@ -5,7 +5,7 @@
 */
 
 /**
- * @remix-run/router v1.15.1
+ * @remix-run/router v1.17.0
  *
  * Copyright (c) Remix Software Inc.
  *
@@ -16,7 +16,7 @@
  */
 
 /**
- * React Router DOM v6.22.1
+ * React Router DOM v6.24.0
  *
  * Copyright (c) Remix Software Inc.
  *
@@ -27,7 +27,7 @@
  */
 
 /**
- * React Router v6.22.1
+ * React Router v6.24.0
  *
  * Copyright (c) Remix Software Inc.
  *

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

@@ -107,7 +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:
@@ -328,6 +328,7 @@ See also [increases_over_time](#increases_over_time).
 
 `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),

app/vlstorage/main.go

@@ -20,10 +20,12 @@ 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; "+
+	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. "+
@@ -49,12 +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()
@@ -142,6 +145,13 @@ func GetStreams(ctx context.Context, tenantIDs []logstorage.TenantID, q *logstor
 	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)

app/vmagent/main.go

@@ -24,7 +24,6 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/prometheusimport"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/promremotewrite"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
-	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/statsd"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/vmimport"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/buildinfo"
@@ -37,7 +36,6 @@ import (
 	influxserver "github.com/VictoriaMetrics/VictoriaMetrics/lib/ingestserver/influx"
 	opentsdbserver "github.com/VictoriaMetrics/VictoriaMetrics/lib/ingestserver/opentsdb"
 	opentsdbhttpserver "github.com/VictoriaMetrics/VictoriaMetrics/lib/ingestserver/opentsdbhttp"
-	statsdserver "github.com/VictoriaMetrics/VictoriaMetrics/lib/ingestserver/statsd"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/procutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promscrape"
@@ -63,12 +61,6 @@ var (
 		"See also -graphiteListenAddr.useProxyProtocol")
 	graphiteUseProxyProtocol = flag.Bool("graphiteListenAddr.useProxyProtocol", false, "Whether to use proxy protocol for connections accepted at -graphiteListenAddr . "+
 		"See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt")
-	statsdListenAddr = flag.String("statsdListenAddr", "", "TCP and UDP address to listen for Statsd plaintext data. Usually :8125 must be set. Doesn't work if empty. "+
-		"See also -statsdListenAddr.useProxyProtocol")
-	statsdUseProxyProtocol = flag.Bool("statsdListenAddr.useProxyProtocol", false, "Whether to use proxy protocol for connections accepted at -statsdListenAddr . "+
-		"See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt")
-	statsdDisableAggregationEnforcemenet = flag.Bool(`statsd.disableAggregationEnforcement`, false, "Whether to disable streaming aggregation requirement check. "+
-		"It's recommended to run statsdServer with pre-configured streaming aggregation to decrease load at database.")
 	opentsdbListenAddr = flag.String("opentsdbListenAddr", "", "TCP and UDP address to listen for OpenTSDB metrics. "+
 		"Telnet put messages and HTTP /api/put messages are simultaneously served on TCP port. "+
 		"Usually :4242 must be set. Doesn't work if empty. See also -opentsdbListenAddr.useProxyProtocol")
@@ -78,8 +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")
@@ -88,7 +80,6 @@ var (
 var (
 	influxServer       *influxserver.Server
 	graphiteServer     *graphiteserver.Server
-	statsdServer       *statsdserver.Server
 	opentsdbServer     *opentsdbserver.Server
 	opentsdbhttpServer *opentsdbhttpserver.Server
 )
@@ -146,12 +137,6 @@ func main() {
 	if len(*graphiteListenAddr) > 0 {
 		graphiteServer = graphiteserver.MustStart(*graphiteListenAddr, *graphiteUseProxyProtocol, graphite.InsertHandler)
 	}
-	if len(*statsdListenAddr) > 0 {
-		if !remotewrite.HasAnyStreamAggrConfigured() && !*statsdDisableAggregationEnforcemenet {
-			logger.Fatalf("streaming aggregation must be configured with enabled statsd server. It's recommended  to aggregate metrics received at statsd listener. This check could be disabled with flag -statsd.disableAggregationEnforcement")
-		}
-		statsdServer = statsdserver.MustStart(*statsdListenAddr, *statsdUseProxyProtocol, statsd.InsertHandler)
-	}
 	if len(*opentsdbListenAddr) > 0 {
 		httpInsertHandler := getOpenTSDBHTTPInsertHandler()
 		opentsdbServer = opentsdbserver.MustStart(*opentsdbListenAddr, *opentsdbUseProxyProtocol, opentsdb.InsertHandler, httpInsertHandler)
@@ -187,9 +172,6 @@ func main() {
 	if len(*graphiteListenAddr) > 0 {
 		graphiteServer.MustStop()
 	}
-	if len(*statsdListenAddr) > 0 {
-		statsdServer.MustStop()
-	}
 	if len(*opentsdbListenAddr) > 0 {
 		opentsdbServer.MustStop()
 	}

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

@@ -38,7 +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")

app/vmagent/remotewrite/pendingseries.go

@@ -109,10 +109,9 @@ type writeRequest struct {
 
 	wr prompbmarshal.WriteRequest
 
-	tss       []prompbmarshal.TimeSeries
-	labels    []prompbmarshal.Label
-	samples   []prompbmarshal.Sample
-	exemplars []prompbmarshal.Exemplar
+	tss     []prompbmarshal.TimeSeries
+	labels  []prompbmarshal.Label
+	samples []prompbmarshal.Sample
 
 	// buf holds labels data
 	buf []byte
@@ -130,7 +129,6 @@ func (wr *writeRequest) reset() {
 	wr.labels = wr.labels[:0]
 
 	wr.samples = wr.samples[:0]
-	wr.exemplars = wr.exemplars[:0]
 	wr.buf = wr.buf[:0]
 }
 
@@ -202,7 +200,6 @@ func (wr *writeRequest) copyTimeSeries(dst, src *prompbmarshal.TimeSeries) {
 	labelsDst := wr.labels
 	labelsLen := len(wr.labels)
 	samplesDst := wr.samples
-	exemplarsDst := wr.exemplars
 	buf := wr.buf
 	for i := range src.Labels {
 		labelsDst = append(labelsDst, prompbmarshal.Label{})
@@ -219,12 +216,8 @@ func (wr *writeRequest) copyTimeSeries(dst, src *prompbmarshal.TimeSeries) {
 	samplesDst = append(samplesDst, src.Samples...)
 	dst.Samples = samplesDst[len(samplesDst)-len(src.Samples):]
 
-	exemplarsDst = append(exemplarsDst, src.Exemplars...)
-	dst.Exemplars = exemplarsDst[len(exemplarsDst)-len(src.Exemplars):]
-
 	wr.samples = samplesDst
 	wr.labels = labelsDst
-	wr.exemplars = exemplarsDst
 	wr.buf = buf
 }
 
@@ -236,6 +229,7 @@ func tryPushWriteRequest(wr *prompbmarshal.WriteRequest, tryPushBlock func(block
 		// Nothing to push
 		return true
 	}
+
 	marshalConcurrencyCh <- struct{}{}
 
 	bb := writeRequestBufPool.Get()
@@ -272,8 +266,6 @@ func tryPushWriteRequest(wr *prompbmarshal.WriteRequest, tryPushBlock func(block
 	if len(wr.Timeseries) == 1 {
 		// A single time series left. Recursively split its samples into smaller parts if possible.
 		samples := wr.Timeseries[0].Samples
-		exemplars := wr.Timeseries[0].Exemplars
-
 		if len(samples) == 1 {
 			logger.Warnf("dropping a sample for metric with too long labels exceeding -remoteWrite.maxBlockSize=%d bytes", maxUnpackedBlockSize.N)
 			return true
@@ -285,16 +277,11 @@ func tryPushWriteRequest(wr *prompbmarshal.WriteRequest, tryPushBlock func(block
 			return false
 		}
 		wr.Timeseries[0].Samples = samples[n:]
-		// We do not want to send exemplars twice
-		wr.Timeseries[0].Exemplars = nil
-
 		if !tryPushWriteRequest(wr, tryPushBlock, isVMRemoteWrite) {
 			wr.Timeseries[0].Samples = samples
-			wr.Timeseries[0].Exemplars = exemplars
 			return false
 		}
 		wr.Timeseries[0].Samples = samples
-		wr.Timeseries[0].Exemplars = exemplars
 		return true
 	}
 	timeseries := wr.Timeseries

app/vmagent/remotewrite/pendingseries_test.go

@@ -10,8 +10,8 @@ import (
 
 func TestPushWriteRequest(t *testing.T) {
 	rowsCounts := []int{1, 10, 100, 1e3, 1e4}
-	expectedBlockLensProm := []int{248, 1952, 17433, 180381, 1861994}
-	expectedBlockLensVM := []int{170, 575, 4748, 44936, 367096}
+	expectedBlockLensProm := []int{216, 1848, 16424, 169882, 1757876}
+	expectedBlockLensVM := []int{138, 492, 3927, 34995, 288476}
 	for i, rowsCount := range rowsCounts {
 		expectedBlockLenProm := expectedBlockLensProm[i]
 		expectedBlockLenVM := expectedBlockLensVM[i]
@@ -59,20 +59,6 @@ func newTestWriteRequest(seriesCount, labelsCount int) *prompbmarshal.WriteReque
 				Value: fmt.Sprintf("value_%d_%d", i, j),
 			})
 		}
-		exemplar := prompbmarshal.Exemplar{
-			Labels: []prompbmarshal.Label{
-				{
-					Name:  "trace_id",
-					Value: "123456",
-				},
-				{
-					Name:  "log_id",
-					Value: "987654",
-				},
-			},
-			Value:     float64(i),
-			Timestamp: 1000 * int64(i),
-		}
 		wr.Timeseries = append(wr.Timeseries, prompbmarshal.TimeSeries{
 			Labels: labels,
 			Samples: []prompbmarshal.Sample{
@@ -81,10 +67,6 @@ func newTestWriteRequest(seriesCount, labelsCount int) *prompbmarshal.WriteReque
 					Timestamp: 1000 * int64(i),
 				},
 			},
-
-			Exemplars: []prompbmarshal.Exemplar{
-				exemplar,
-			},
 		})
 	}
 	return &wr

app/vmagent/remotewrite/remotewrite.go

@@ -211,7 +211,7 @@ func Init() {
 		}
 		sasGlobal.Store(sas)
 	} else if sasOpts.DedupInterval > 0 {
-		deduplicatorGlobal = streamaggr.NewDeduplicator(pushToRemoteStoragesDropFailed, sasOpts.DedupInterval, sasOpts.DropInputLabels)
+		deduplicatorGlobal = streamaggr.NewDeduplicator(pushToRemoteStoragesDropFailed, sasOpts.DedupInterval, sasOpts.DropInputLabels, sasOpts.Alias)
 	}
 
 	if len(*remoteWriteURLs) > 0 {
@@ -840,7 +840,7 @@ func newRemoteWriteCtx(argIdx int, remoteWriteURL *url.URL, maxInmemoryBlocks in
 		metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reload_successful{path=%q}`, sasFile)).Set(1)
 		metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reload_success_timestamp_seconds{path=%q}`, sasFile)).Set(fasttime.UnixTimestamp())
 	} else if sasOpts.DedupInterval > 0 {
-		rwctx.deduplicator = streamaggr.NewDeduplicator(rwctx.pushInternalTrackDropped, sasOpts.DedupInterval, sasOpts.DropInputLabels)
+		rwctx.deduplicator = streamaggr.NewDeduplicator(rwctx.pushInternalTrackDropped, sasOpts.DedupInterval, sasOpts.DropInputLabels, sasOpts.Alias)
 	}
 
 	return rwctx
@@ -848,7 +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()
 
@@ -875,12 +875,20 @@ func (rwctx *remoteWriteCtx) MustStop() {
 
 // TryPush sends tss series to the configured remote write endpoint
 //
-// TryPush can be called concurrently for multiple remoteWriteCtx,
-// so it shouldn't modify tss entries.
+// 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 {
-	// Apply relabeling
 	var rctx *relabelCtx
 	var v *[]prompbmarshal.TimeSeries
+	defer func() {
+		if rctx == nil {
+			return
+		}
+		*v = prompbmarshal.ResetTimeSeries(tss)
+		tssPool.Put(v)
+		putRelabelCtx(rctx)
+	}()
+
+	// Apply relabeling
 	rcs := allRelabelConfigs.Load()
 	pcs := rcs.perURL[rwctx.idx]
 	if pcs.Len() > 0 {
@@ -916,28 +924,21 @@ func (rwctx *remoteWriteCtx) TryPush(tss []prompbmarshal.TimeSeries, forceDropSa
 		matchIdxsPool.Put(matchIdxs)
 	} else if rwctx.deduplicator != nil {
 		rwctx.deduplicator.Push(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
 	}
 
-	if !ok {
-		rwctx.pushFailures.Inc()
-		if forceDropSamplesOnFailure || rwctx.dropSamplesOnOverload {
-			rwctx.rowsDroppedOnPushFailure.Add(len(tss))
-			return true
-		}
+	// Couldn't push tss to remote storage
+	rwctx.pushFailures.Inc()
+	if forceDropSamplesOnFailure || rwctx.dropSamplesOnOverload {
+		rwctx.rowsDroppedOnPushFailure.Add(len(tss))
+		return true
 	}
-
-	return ok
+	return false
 }
 
 var matchIdxsPool bytesutil.ByteBufferPool
@@ -974,6 +975,15 @@ func (rwctx *remoteWriteCtx) pushInternalTrackDropped(tss []prompbmarshal.TimeSe
 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.
@@ -986,15 +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
+	return pss[idx].TryPush(tss)
 }
 
 var tssPool = &sync.Pool{

app/vmagent/remotewrite/remotewrite_test.go

@@ -3,14 +3,12 @@ package remotewrite
 import (
 	"fmt"
 	"math"
-	"os"
 	"reflect"
 	"testing"
 	"time"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/prometheus"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/streamaggr"
 	"github.com/VictoriaMetrics/metrics"
 )
@@ -79,19 +77,19 @@ func TestRemoteWriteContext_TryPush_ImmutableTimeseries(t *testing.T) {
 			rowsDroppedByRelabel:   metrics.GetOrCreateCounter(`bar`),
 		}
 		if dedupInterval > 0 {
-			rwctx.deduplicator = streamaggr.NewDeduplicator(nil, dedupInterval, nil)
+			rwctx.deduplicator = streamaggr.NewDeduplicator(nil, dedupInterval, nil, "global")
 		}
 
 		if len(streamAggrConfig) > 0 {
-			f := createFile(t, []byte(streamAggrConfig))
-			sas, err := streamaggr.LoadFromFile(f.Name(), nil, nil)
+			sas, err := streamaggr.LoadFromData([]byte(streamAggrConfig), nil, streamaggr.Options{})
 			if err != nil {
 				t.Fatalf("cannot load streamaggr configs: %s", err)
 			}
 			rwctx.sas.Store(sas)
 		}
 
-		inputTss := mustParsePromMetrics(input)
+		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
@@ -165,51 +163,3 @@ metric{env="dev"} 15
 metric{env="bar"} 25
 `)
 }
-
-func mustParsePromMetrics(s string) []prompbmarshal.TimeSeries {
-	var rows prometheus.Rows
-	errLogger := func(s string) {
-		panic(fmt.Errorf("unexpected error when parsing Prometheus metrics: %s", s))
-	}
-	rows.UnmarshalWithErrLogger(s, errLogger)
-	var tss []prompbmarshal.TimeSeries
-	samples := make([]prompbmarshal.Sample, 0, len(rows.Rows))
-	for _, row := range rows.Rows {
-		labels := make([]prompbmarshal.Label, 0, len(row.Tags)+1)
-		labels = append(labels, prompbmarshal.Label{
-			Name:  "__name__",
-			Value: row.Metric,
-		})
-		for _, tag := range row.Tags {
-			labels = append(labels, prompbmarshal.Label{
-				Name:  tag.Key,
-				Value: tag.Value,
-			})
-		}
-		samples = append(samples, prompbmarshal.Sample{
-			Value:     row.Value,
-			Timestamp: row.Timestamp,
-		})
-		ts := prompbmarshal.TimeSeries{
-			Labels:  labels,
-			Samples: samples[len(samples)-1:],
-		}
-		tss = append(tss, ts)
-	}
-	return tss
-}
-
-func createFile(t *testing.T, data []byte) *os.File {
-	t.Helper()
-	f, err := os.CreateTemp("", "")
-	if err != nil {
-		t.Fatal(err)
-	}
-	if err := os.WriteFile(f.Name(), data, 0644); err != nil {
-		t.Fatal(err)
-	}
-	if err := f.Sync(); err != nil {
-		t.Fatal(err)
-	}
-	return f
-}

app/vmagent/remotewrite/streamaggr.go

@@ -36,25 +36,27 @@ var (
 		"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. "+
+	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. By default, only aggregates samples are dropped, while the remaining samples "+
+		"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. By default, only aggregates samples are dropped, while the remaining samples "+
+		"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 . See also -dedup.minScrapeInterval and https://docs.victoriametrics.com/stream-aggregation/#deduplication")
+		"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 . "+
+		"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. 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. "+
+	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 . See https://docs.victoriametrics.com/stream-aggregation/#dropping-unneeded-labels")
+		"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.
@@ -76,11 +78,6 @@ func CheckStreamAggrConfigs() error {
 	return nil
 }
 
-// HasAnyStreamAggrConfigured checks if any streaming aggregation config provided
-func HasAnyStreamAggrConfigured() bool {
-	return len(*streamAggrConfig) > 0 || *streamAggrGlobalConfig != ""
-}
-
 func reloadStreamAggrConfigs() {
 	reloadStreamAggrConfig(-1, pushToRemoteStoragesDropFailed)
 	for idx, rwctx := range rwctxs {
@@ -125,28 +122,35 @@ func reloadStreamAggrConfig(idx int, pushFunc streamaggr.PushFunc) {
 	metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reload_success_timestamp_seconds{path=%q}`, path)).Set(fasttime.UnixTimestamp())
 }
 
-func getStreamAggrOpts(idx int) (string, *streamaggr.Options) {
+func getStreamAggrOpts(idx int) (string, streamaggr.Options) {
 	if idx < 0 {
-		return *streamAggrGlobalConfig, &streamaggr.Options{
+		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 "", opts
 	}
-	return streamAggrConfig.GetOptionalArg(idx), &opts
+	return streamAggrConfig.GetOptionalArg(idx), opts
 }
 
-func newStreamAggrConfigWithOpts(pushFunc streamaggr.PushFunc, path string, opts *streamaggr.Options) (*streamaggr.Aggregators, error) {
+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

app/vmagent/statsd/request_handler.go

@@ -1,72 +0,0 @@
-package statsd
-
-import (
-	"io"
-
-	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/common"
-	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
-	parser "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/statsd"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/statsd/stream"
-	"github.com/VictoriaMetrics/metrics"
-)
-
-var (
-	rowsInserted  = metrics.NewCounter(`vmagent_rows_inserted_total{type="statsd"}`)
-	rowsPerInsert = metrics.NewHistogram(`vmagent_rows_per_insert{type="statsd"}`)
-)
-
-// InsertHandler processes remote write for statsd plaintext protocol.
-//
-// See https://github.com/statsd/statsd/blob/master/docs/metric_types.md
-func InsertHandler(r io.Reader) error {
-	return stream.Parse(r, false, func(rows []parser.Row) error {
-		return insertRows(nil, rows)
-	})
-}
-
-func insertRows(at *auth.Token, rows []parser.Row) error {
-	ctx := common.GetPushCtx()
-	defer common.PutPushCtx(ctx)
-
-	tssDst := ctx.WriteRequest.Timeseries[:0]
-	labels := ctx.Labels[:0]
-	samples := ctx.Samples[:0]
-	for i := range rows {
-		r := &rows[i]
-		labelsLen := len(labels)
-		labels = append(labels, prompbmarshal.Label{
-			Name:  "__name__",
-			Value: r.Metric,
-		})
-		for j := range r.Tags {
-			tag := &r.Tags[j]
-			labels = append(labels, prompbmarshal.Label{
-				Name:  tag.Key,
-				Value: tag.Value,
-			})
-		}
-		samplesLen := len(samples)
-		for _, v := range r.Values {
-			samples = append(samples, prompbmarshal.Sample{
-				Value:     v,
-				Timestamp: r.Timestamp,
-			})
-		}
-
-		tssDst = append(tssDst, prompbmarshal.TimeSeries{
-			Labels:  labels[labelsLen:],
-			Samples: samples[samplesLen:],
-		})
-	}
-	ctx.WriteRequest.Timeseries = tssDst
-	ctx.Labels = labels
-	ctx.Samples = samples
-	if !remotewrite.TryPush(at, &ctx.WriteRequest) {
-		return remotewrite.ErrQueueFullHTTPRetry
-	}
-	rowsInserted.Add(len(rows))
-	rowsPerInsert.Update(float64(len(rows)))
-	return nil
-}

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

@@ -18,7 +18,7 @@ import (
 	"github.com/VictoriaMetrics/metricsql"
 )
 
-var numReg = regexp.MustCompile(`\D?\d*\D?`)
+var numReg = regexp.MustCompile(`\D?\d*\.?\d*\D?`)
 
 // series holds input_series defined in the test file
 type series struct {

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

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

@@ -57,9 +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.`)
 )
@@ -105,6 +106,7 @@ func Init(extraParams url.Values) (QuerierBuilder, error) {
 	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/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"
@@ -32,6 +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")
@@ -66,6 +69,7 @@ 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)

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

@@ -31,6 +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")
@@ -71,6 +73,7 @@ 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)

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/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/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
@@ -737,6 +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 {
@@ -801,6 +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 {
@@ -1011,6 +1024,8 @@ func (up *URLPrefix) sanitizeAndInitialize() error {
 		}
 	}
 	up.bus.Store(&bus)
+	up.nextDiscoveryDeadline.Store(0)
+	up.n.Store(0)
 
 	return nil
 }

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

app/vmauth/target_url_test.go

@@ -1,11 +1,15 @@
 package main
 
 import (
+	"context"
 	"fmt"
+	"net"
 	"net/url"
 	"reflect"
 	"strings"
 	"testing"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/netutil"
 )
 
 func TestDropPrefixParts(t *testing.T) {
@@ -92,7 +96,7 @@ func TestCreateTargetURLSuccess(t *testing.T) {
 		u = normalizeURL(u)
 		up, hc := ui.getURLPrefixAndHeaders(u, nil)
 		if up == nil {
-			t.Fatalf("cannot determie backend: %s", err)
+			t.Fatalf("cannot match available backend: %s", err)
 		}
 		bu := up.getBackendURL()
 		target := mergeURLs(bu.url, u, up.dropSrcPathPrefixParts)
@@ -256,6 +260,53 @@ func TestCreateTargetURLSuccess(t *testing.T) {
 	f(ui, `/api/v1/query?query=up{env="prod"}`, `http://vmselect/1/prometheus/api/v1/query?query=up%7Benv%3D%22prod%22%7D`, "", "", nil, "least_loaded", 0)
 	f(ui, `/api/v1/query?query=up{foo="bar",env="dev",pod!=""}`, `http://vmselect/0/prometheus/api/v1/query?query=up%7Bfoo%3D%22bar%22%2Cenv%3D%22dev%22%2Cpod%21%3D%22%22%7D`, "", "", nil, "least_loaded", 0)
 	f(ui, `/api/v1/query?query=up{foo="bar"}`, `http://default-server/api/v1/query?query=up%7Bfoo%3D%22bar%22%7D`, "", "", nil, "least_loaded", 0)
+
+	customResolver := &fakeResolver{
+		Resolver: &net.Resolver{},
+		lookupSRVResults: map[string][]*net.SRV{
+			"vmselect": {
+				{
+					Target: "10.6.142.50",
+					Port:   8481,
+				},
+				{
+					Target: "10.6.142.51",
+					Port:   8481,
+				},
+			},
+		},
+		lookupIPAddrResults: map[string][]net.IPAddr{
+			"vminsert": {
+				{
+					IP: net.ParseIP("10.6.142.52"),
+				},
+			},
+		},
+	}
+	netutil.Resolver = customResolver
+
+	// Discover backendURL
+	allowed := true
+	ui = &UserInfo{
+		URLMaps: []URLMap{
+			{
+				SrcPaths:  getRegexs([]string{"/select/.+"}),
+				URLPrefix: mustParseURL("http://srv+vmselect"),
+			},
+			{
+				SrcPaths:  getRegexs([]string{"/insert/.+"}),
+				URLPrefix: mustParseURL("http://vminsert:8480"),
+			},
+		},
+		DiscoverBackendIPs: &allowed,
+		URLPrefix:          mustParseURL("http://non-exist-dns-addr"),
+	}
+	f(ui, `/select/0/prometheus/api/v1/query?query=up`, "http://10.6.142.51:8481/select/0/prometheus/api/v1/query?query=up", "", "", nil, "least_loaded", 0)
+	// url_prefix counter will be reset, still go to 10.6.142.51
+	f(ui, `/select/0/prometheus/api/v1/query?query=up`, "http://10.6.142.51:8481/select/0/prometheus/api/v1/query?query=up", "", "", nil, "least_loaded", 0)
+	f(ui, `/insert/0/prometheus/api/v1/write`, "http://10.6.142.52:8480/insert/0/prometheus/api/v1/write", "", "", nil, "least_loaded", 0)
+	// unsuccessful dns resolve
+	f(ui, `/test`, "http://non-exist-dns-addr/test", "", "", nil, "least_loaded", 0)
 }
 
 func TestCreateTargetURLFailure(t *testing.T) {
@@ -295,3 +346,29 @@ func headersToString(hs []*Header) string {
 	}
 	return strings.Join(a, "\n")
 }
+
+type fakeResolver struct {
+	Resolver            *net.Resolver
+	lookupSRVResults    map[string][]*net.SRV
+	lookupIPAddrResults map[string][]net.IPAddr
+}
+
+func (r *fakeResolver) LookupSRV(_ context.Context, _, _, name string) (string, []*net.SRV, error) {
+	if results, ok := r.lookupSRVResults[name]; ok {
+		return name, results, nil
+	}
+
+	return name, nil, fmt.Errorf("no srv results found for host: %s", name)
+}
+
+func (r *fakeResolver) LookupIPAddr(_ context.Context, host string) ([]net.IPAddr, error) {
+	if results, ok := r.lookupIPAddrResults[host]; ok {
+		return results, nil
+	}
+
+	return nil, fmt.Errorf("no results found for host: %s", host)
+}
+
+func (r *fakeResolver) LookupMX(_ context.Context, _ string) ([]*net.MX, error) {
+	return nil, nil
+}

app/vmbackup/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/vmctl/barpool/pool.go

@@ -5,37 +5,88 @@ package barpool
 
 import (
 	"fmt"
+	"io"
 	"os"
 
-	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/terminal"
 	"github.com/cheggaaa/pb/v3"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/terminal"
 )
 
+var isDisabled bool
+
+// Disable sets progress bar to be no-op if v==true
+func Disable(v bool) {
+	isDisabled = v
+}
+
 var pool = pb.NewPool()
 
-// Add adds bar to the global pool
-func Add(bar *pb.ProgressBar) { pool.Add(bar) }
+// Bar is an interface for progress bar
+type Bar interface {
+	Add(value int)
+	Increment()
+	Start()
+	Finish()
+	NewProxyReader(r io.Reader) *pb.Reader
+}
+
+type progressBar struct {
+	*pb.ProgressBar
+}
+
+func (pb *progressBar) Finish()       { pb.ProgressBar.Finish() }
+func (pb *progressBar) Start()        { pb.ProgressBar.Start() }
+func (pb *progressBar) Add(value int) { pb.ProgressBar.Add(value) }
+func (pb *progressBar) Increment()    { pb.ProgressBar.Increment() }
+func (pb *progressBar) NewProxyReader(r io.Reader) *pb.Reader {
+	return pb.ProgressBar.NewProxyReader(r)
+}
+
+type progressBarNoOp struct{}
+
+func (pbno *progressBarNoOp) Finish()                               {}
+func (pbno *progressBarNoOp) Start()                                {}
+func (pbno *progressBarNoOp) Add(int)                               {}
+func (pbno *progressBarNoOp) Increment()                            {}
+func (pbno *progressBarNoOp) NewProxyReader(_ io.Reader) *pb.Reader { return nil }
 
 // Start starts the global pool
 // Must be called after all progress bars were added
-func Start() error { return pool.Start() }
+func Start() error {
+	if isDisabled {
+		return nil
+	}
+	return pool.Start()
+}
 
 // Stop stops the global pool
-func Stop() { _ = pool.Stop() }
+func Stop() {
+	if isDisabled {
+		return
+	}
+	_ = pool.Stop()
+}
 
 // AddWithTemplate adds bar with the given template
 // to the global pool
-func AddWithTemplate(format string, total int) *pb.ProgressBar {
+func AddWithTemplate(format string, total int) Bar {
+	if isDisabled {
+		return &progressBarNoOp{}
+	}
 	tpl := getTemplate(format)
 	bar := pb.ProgressBarTemplate(tpl).New(total)
-	Add(bar)
-	return bar
+	pool.Add(bar)
+	return &progressBar{bar}
 }
 
 // NewSingleProgress returns progress bar with given template
-func NewSingleProgress(format string, total int) *pb.ProgressBar {
+func NewSingleProgress(format string, total int) Bar {
+	if isDisabled {
+		return &progressBarNoOp{}
+	}
 	tpl := getTemplate(format)
-	return pb.ProgressBarTemplate(tpl).New(total)
+	return &progressBar{pb.ProgressBarTemplate(tpl).New(total)}
 }
 
 func getTemplate(format string) string {

app/vmctl/flags.go

@@ -10,8 +10,9 @@ import (
 )
 
 const (
-	globalSilent  = "s"
-	globalVerbose = "verbose"
+	globalSilent             = "s"
+	globalVerbose            = "verbose"
+	globalDisableProgressBar = "disable-progress-bar"
 )
 
 var (
@@ -26,6 +27,11 @@ var (
 			Value: false,
 			Usage: "Whether to enable verbosity in logs output.",
 		},
+		&cli.BoolFlag{
+			Name:  globalDisableProgressBar,
+			Value: false,
+			Usage: "Whether to disable progress bar during the import.",
+		},
 	}
 )
 
@@ -39,7 +45,6 @@ const (
 	vmBatchSize          = "vm-batch-size"
 	vmSignificantFigures = "vm-significant-figures"
 	vmRoundDigits        = "vm-round-digits"
-	vmDisableProgressBar = "vm-disable-progress-bar"
 	vmCertFile           = "vm-cert-file"
 	vmKeyFile            = "vm-key-file"
 	vmCAFile             = "vm-CA-file"
@@ -120,10 +125,6 @@ var (
 			Usage: "Optional data transfer rate limit in bytes per second.\n" +
 				"By default, the rate limit is disabled. It can be useful for limiting load on configured via '--vmAddr' destination.",
 		},
-		&cli.BoolFlag{
-			Name:  vmDisableProgressBar,
-			Usage: "Whether to disable progress bar per each worker during the import.",
-		},
 		&cli.StringFlag{
 			Name:  vmCertFile,
 			Usage: "Optional path to client-side TLS certificate file to use when connecting to '--vmAddr'",

app/vmctl/influx.go

@@ -18,14 +18,14 @@ type influxProcessor struct {
 	separator   string
 	skipDbLabel bool
 	promMode    bool
-	isSilent    bool
 	isVerbose   bool
 }
 
-func newInfluxProcessor(ic *influx.Client, im *vm.Importer, cc int, separator string, skipDbLabel, promMode, silent, verbose bool) *influxProcessor {
+func newInfluxProcessor(ic *influx.Client, im *vm.Importer, cc int, separator string, skipDbLabel, promMode, verbose bool) *influxProcessor {
 	if cc < 1 {
 		cc = 1
 	}
+
 	return &influxProcessor{
 		ic:          ic,
 		im:          im,
@@ -33,7 +33,6 @@ func newInfluxProcessor(ic *influx.Client, im *vm.Importer, cc int, separator st
 		separator:   separator,
 		skipDbLabel: skipDbLabel,
 		promMode:    promMode,
-		isSilent:    silent,
 		isVerbose:   verbose,
 	}
 }
@@ -48,7 +47,7 @@ func (ip *influxProcessor) run() error {
 	}
 
 	question := fmt.Sprintf("Found %d timeseries to import. Continue?", len(series))
-	if !ip.isSilent && !prompt(question) {
+	if !prompt(question) {
 		return nil
 	}
 

app/vmctl/main.go

@@ -16,6 +16,7 @@ import (
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/auth"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/backoff"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/barpool"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/native"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/remoteread"
 
@@ -37,15 +38,23 @@ func main() {
 
 	ctx, cancelCtx := context.WithCancel(context.Background())
 	start := time.Now()
+	beforeFn := func(c *cli.Context) error {
+		isSilent = c.Bool(globalSilent)
+		if c.Bool(globalDisableProgressBar) {
+			barpool.Disable(true)
+		}
+		return nil
+	}
 	app := &cli.App{
 		Name:    "vmctl",
 		Usage:   "VictoriaMetrics command-line tool",
 		Version: buildinfo.Version,
 		Commands: []*cli.Command{
 			{
-				Name:  "opentsdb",
-				Usage: "Migrate time series from OpenTSDB",
-				Flags: mergeFlags(globalFlags, otsdbFlags, vmFlags),
+				Name:   "opentsdb",
+				Usage:  "Migrate time series from OpenTSDB",
+				Flags:  mergeFlags(globalFlags, otsdbFlags, vmFlags),
+				Before: beforeFn,
 				Action: func(c *cli.Context) error {
 					fmt.Println("OpenTSDB import mode")
 
@@ -81,22 +90,20 @@ func main() {
 					if err != nil {
 						return fmt.Errorf("failed to init VM configuration: %s", err)
 					}
-					// disable progress bars since openTSDB implementation
-					// does not use progress bar pool
-					vmCfg.DisableProgressBar = true
 					importer, err := vm.NewImporter(ctx, vmCfg)
 					if err != nil {
 						return fmt.Errorf("failed to create VM importer: %s", err)
 					}
 
-					otsdbProcessor := newOtsdbProcessor(otsdbClient, importer, c.Int(otsdbConcurrency), c.Bool(globalSilent), c.Bool(globalVerbose))
+					otsdbProcessor := newOtsdbProcessor(otsdbClient, importer, c.Int(otsdbConcurrency), c.Bool(globalVerbose))
 					return otsdbProcessor.run()
 				},
 			},
 			{
-				Name:  "influx",
-				Usage: "Migrate time series from InfluxDB",
-				Flags: mergeFlags(globalFlags, influxFlags, vmFlags),
+				Name:   "influx",
+				Usage:  "Migrate time series from InfluxDB",
+				Flags:  mergeFlags(globalFlags, influxFlags, vmFlags),
+				Before: beforeFn,
 				Action: func(c *cli.Context) error {
 					fmt.Println("InfluxDB import mode")
 
@@ -148,15 +155,15 @@ func main() {
 						c.String(influxMeasurementFieldSeparator),
 						c.Bool(influxSkipDatabaseLabel),
 						c.Bool(influxPrometheusMode),
-						c.Bool(globalSilent),
 						c.Bool(globalVerbose))
 					return processor.run()
 				},
 			},
 			{
-				Name:  "remote-read",
-				Usage: "Migrate time series via Prometheus remote-read protocol",
-				Flags: mergeFlags(globalFlags, remoteReadFlags, vmFlags),
+				Name:   "remote-read",
+				Usage:  "Migrate time series via Prometheus remote-read protocol",
+				Flags:  mergeFlags(globalFlags, remoteReadFlags, vmFlags),
+				Before: beforeFn,
 				Action: func(c *cli.Context) error {
 					fmt.Println("Remote-read import mode")
 
@@ -209,16 +216,16 @@ func main() {
 							timeReverse: c.Bool(remoteReadFilterTimeReverse),
 						},
 						cc:        c.Int(remoteReadConcurrency),
-						isSilent:  c.Bool(globalSilent),
 						isVerbose: c.Bool(globalVerbose),
 					}
 					return rmp.run(ctx)
 				},
 			},
 			{
-				Name:  "prometheus",
-				Usage: "Migrate time series from Prometheus",
-				Flags: mergeFlags(globalFlags, promFlags, vmFlags),
+				Name:   "prometheus",
+				Usage:  "Migrate time series from Prometheus",
+				Flags:  mergeFlags(globalFlags, promFlags, vmFlags),
+				Before: beforeFn,
 				Action: func(c *cli.Context) error {
 					fmt.Println("Prometheus import mode")
 
@@ -245,17 +252,19 @@ func main() {
 						return fmt.Errorf("failed to create prometheus client: %s", err)
 					}
 					pp := prometheusProcessor{
-						cl: cl,
-						im: importer,
-						cc: c.Int(promConcurrency),
+						cl:        cl,
+						im:        importer,
+						cc:        c.Int(promConcurrency),
+						isVerbose: c.Bool(globalVerbose),
 					}
-					return pp.run(c.Bool(globalSilent), c.Bool(globalVerbose))
+					return pp.run()
 				},
 			},
 			{
-				Name:  "vm-native",
-				Usage: "Migrate time series between VictoriaMetrics installations via native binary format",
-				Flags: mergeFlags(globalFlags, vmNativeFlags),
+				Name:   "vm-native",
+				Usage:  "Migrate time series between VictoriaMetrics installations via native binary format",
+				Flags:  mergeFlags(globalFlags, vmNativeFlags),
+				Before: beforeFn,
 				Action: func(c *cli.Context) error {
 					fmt.Println("VictoriaMetrics Native import mode")
 
@@ -344,7 +353,6 @@ func main() {
 						backoff:                  backoff.New(),
 						cc:                       c.Int(vmConcurrency),
 						disablePerMetricRequests: c.Bool(vmNativeDisablePerMetricMigration),
-						isSilent:                 c.Bool(globalSilent),
 						isNative:                 !c.Bool(vmNativeDisableBinaryProtocol),
 					}
 					return p.run(ctx)
@@ -360,6 +368,7 @@ func main() {
 						Value: false,
 					},
 				},
+				Before: beforeFn,
 				Action: func(c *cli.Context) error {
 					common.StartUnmarshalWorkers()
 					blockPath := c.Args().First()
@@ -433,6 +442,5 @@ func initConfigVM(c *cli.Context) (vm.Config, error) {
 		RoundDigits:        c.Int(vmRoundDigits),
 		ExtraLabels:        c.StringSlice(vmExtraLabel),
 		RateLimit:          c.Int64(vmRateLimit),
-		DisableProgressBar: c.Bool(vmDisableProgressBar),
 	}, nil
 }

app/vmctl/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/vmctl/opentsdb.go

@@ -15,7 +15,6 @@ type otsdbProcessor struct {
 	oc        *opentsdb.Client
 	im        *vm.Importer
 	otsdbcc   int
-	isSilent  bool
 	isVerbose bool
 }
 
@@ -26,7 +25,7 @@ type queryObj struct {
 	StartTime int64
 }
 
-func newOtsdbProcessor(oc *opentsdb.Client, im *vm.Importer, otsdbcc int, silent, verbose bool) *otsdbProcessor {
+func newOtsdbProcessor(oc *opentsdb.Client, im *vm.Importer, otsdbcc int, verbose bool) *otsdbProcessor {
 	if otsdbcc < 1 {
 		otsdbcc = 1
 	}
@@ -34,7 +33,6 @@ func newOtsdbProcessor(oc *opentsdb.Client, im *vm.Importer, otsdbcc int, silent
 		oc:        oc,
 		im:        im,
 		otsdbcc:   otsdbcc,
-		isSilent:  silent,
 		isVerbose: verbose,
 	}
 }
@@ -55,7 +53,7 @@ func (op *otsdbProcessor) run() error {
 	}
 
 	question := fmt.Sprintf("Found %d metrics to import. Continue?", len(metrics))
-	if !op.isSilent && !prompt(question) {
+	if !prompt(question) {
 		return nil
 	}
 	op.im.ResetStats()

app/vmctl/prometheus.go

@@ -5,11 +5,12 @@ import (
 	"log"
 	"sync"
 
+	"github.com/prometheus/prometheus/tsdb"
+	"github.com/prometheus/prometheus/tsdb/chunkenc"
+
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/barpool"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/prometheus"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/vm"
-	"github.com/prometheus/prometheus/tsdb"
-	"github.com/prometheus/prometheus/tsdb/chunkenc"
 )
 
 type prometheusProcessor struct {
@@ -24,9 +25,12 @@ type prometheusProcessor struct {
 	// and defines number of concurrently
 	// running snapshot block readers
 	cc int
+
+	// isVerbose enables verbose output
+	isVerbose bool
 }
 
-func (pp *prometheusProcessor) run(silent, verbose bool) error {
+func (pp *prometheusProcessor) run() error {
 	blocks, err := pp.cl.Explore()
 	if err != nil {
 		return fmt.Errorf("explore failed: %s", err)
@@ -35,12 +39,11 @@ func (pp *prometheusProcessor) run(silent, verbose bool) error {
 		return fmt.Errorf("found no blocks to import")
 	}
 	question := fmt.Sprintf("Found %d blocks to import. Continue?", len(blocks))
-	if !silent && !prompt(question) {
+	if !prompt(question) {
 		return nil
 	}
 
 	bar := barpool.AddWithTemplate(fmt.Sprintf(barTpl, "Processing blocks"), len(blocks))
-
 	if err := barpool.Start(); err != nil {
 		return err
 	}
@@ -72,7 +75,7 @@ func (pp *prometheusProcessor) run(silent, verbose bool) error {
 			return fmt.Errorf("prometheus error: %s", promErr)
 		case vmErr := <-pp.im.Errors():
 			close(blockReadersCh)
-			return fmt.Errorf("import process failed: %s", wrapErr(vmErr, verbose))
+			return fmt.Errorf("import process failed: %s", wrapErr(vmErr, pp.isVerbose))
 		case blockReadersCh <- br:
 		}
 	}
@@ -85,7 +88,7 @@ func (pp *prometheusProcessor) run(silent, verbose bool) error {
 	// drain import errors channel
 	for vmErr := range pp.im.Errors() {
 		if vmErr.Err != nil {
-			return fmt.Errorf("import process failed: %s", wrapErr(vmErr, verbose))
+			return fmt.Errorf("import process failed: %s", wrapErr(vmErr, pp.isVerbose))
 		}
 	}
 	for err := range errCh {

app/vmctl/prometheus/prometheus.go

@@ -54,7 +54,7 @@ func (f filter) inRange(min, max int64) bool {
 // NewClient creates and validates new Client
 // with given Config
 func NewClient(cfg Config) (*Client, error) {
-	db, err := tsdb.OpenDBReadOnly(cfg.Snapshot, nil)
+	db, err := tsdb.OpenDBReadOnly(cfg.Snapshot, "", nil)
 	if err != nil {
 		return nil, fmt.Errorf("failed to open snapshot %q: %s", cfg.Snapshot, err)
 	}

app/vmctl/prometheus_test.go

@@ -25,6 +25,9 @@ const (
 // This test simulates close process if user abort it
 func Test_prometheusProcessor_run(t *testing.T) {
 	t.Skip()
+
+	defer func() { isSilent = false }()
+
 	type fields struct {
 		cfg    prometheus.Config
 		vmCfg  vm.Config
@@ -117,11 +120,12 @@ func Test_prometheusProcessor_run(t *testing.T) {
 		t.Run(tt.name, func(t *testing.T) {
 			client := tt.fields.cl(tt.fields.cfg)
 			importer := tt.fields.im(tt.fields.vmCfg)
-
+			isSilent = tt.args.silent
 			pp := &prometheusProcessor{
-				cl: client,
-				im: importer,
-				cc: tt.fields.cc,
+				cl:        client,
+				im:        importer,
+				cc:        tt.fields.cc,
+				isVerbose: tt.args.verbose,
 			}
 
 			// we should answer on prompt
@@ -157,7 +161,7 @@ func Test_prometheusProcessor_run(t *testing.T) {
 				go tt.fields.closer(importer)
 			}
 
-			if err := pp.run(tt.args.silent, tt.args.verbose); (err != nil) != tt.wantErr {
+			if err := pp.run(); (err != nil) != tt.wantErr {
 				t.Errorf("run() error = %v, wantErr %v", err, tt.wantErr)
 			}
 		})

app/vmctl/remote_read_test.go

@@ -6,14 +6,21 @@ import (
 	"testing"
 	"time"
 
+	"github.com/prometheus/prometheus/prompb"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/barpool"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/remoteread"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/stepper"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/testdata/servers_integration_test"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/vm"
-	"github.com/prometheus/prometheus/prompb"
 )
 
 func TestRemoteRead(t *testing.T) {
+	barpool.Disable(true)
+	defer func() {
+		barpool.Disable(false)
+	}()
+	defer func() { isSilent = false }()
 
 	var testCases = []struct {
 		name             string
@@ -31,7 +38,7 @@ func TestRemoteRead(t *testing.T) {
 		{
 			name:             "step minute on minute time range",
 			remoteReadConfig: remoteread.Config{Addr: "", LabelName: "__name__", LabelValue: ".*"},
-			vmCfg:            vm.Config{Addr: "", Concurrency: 1, DisableProgressBar: true},
+			vmCfg:            vm.Config{Addr: "", Concurrency: 1},
 			start:            "2022-11-26T11:23:05+02:00",
 			end:              "2022-11-26T11:24:05+02:00",
 			numOfSamples:     2,
@@ -62,7 +69,7 @@ func TestRemoteRead(t *testing.T) {
 		{
 			name:             "step month on month time range",
 			remoteReadConfig: remoteread.Config{Addr: "", LabelName: "__name__", LabelValue: ".*"},
-			vmCfg: vm.Config{Addr: "", Concurrency: 1, DisableProgressBar: true,
+			vmCfg: vm.Config{Addr: "", Concurrency: 1,
 				Transport: http.DefaultTransport.(*http.Transport)},
 			start:            "2022-09-26T11:23:05+02:00",
 			end:              "2022-11-26T11:24:05+02:00",
@@ -157,7 +164,6 @@ func TestRemoteRead(t *testing.T) {
 					chunk:     tt.chunk,
 				},
 				cc:        1,
-				isSilent:  true,
 				isVerbose: false,
 			}
 
@@ -170,6 +176,11 @@ func TestRemoteRead(t *testing.T) {
 }
 
 func TestSteamRemoteRead(t *testing.T) {
+	barpool.Disable(true)
+	defer func() {
+		barpool.Disable(false)
+	}()
+	defer func() { isSilent = false }()
 
 	var testCases = []struct {
 		name             string
@@ -187,7 +198,7 @@ func TestSteamRemoteRead(t *testing.T) {
 		{
 			name:             "step minute on minute time range",
 			remoteReadConfig: remoteread.Config{Addr: "", LabelName: "__name__", LabelValue: ".*", UseStream: true},
-			vmCfg:            vm.Config{Addr: "", Concurrency: 1, DisableProgressBar: true},
+			vmCfg:            vm.Config{Addr: "", Concurrency: 1},
 			start:            "2022-11-26T11:23:05+02:00",
 			end:              "2022-11-26T11:24:05+02:00",
 			numOfSamples:     2,
@@ -218,7 +229,7 @@ func TestSteamRemoteRead(t *testing.T) {
 		{
 			name:             "step month on month time range",
 			remoteReadConfig: remoteread.Config{Addr: "", LabelName: "__name__", LabelValue: ".*", UseStream: true},
-			vmCfg:            vm.Config{Addr: "", Concurrency: 1, DisableProgressBar: true},
+			vmCfg:            vm.Config{Addr: "", Concurrency: 1},
 			start:            "2022-09-26T11:23:05+02:00",
 			end:              "2022-11-26T11:24:05+02:00",
 			numOfSamples:     2,
@@ -312,7 +323,6 @@ func TestSteamRemoteRead(t *testing.T) {
 					chunk:     tt.chunk,
 				},
 				cc:        1,
-				isSilent:  true,
 				isVerbose: false,
 			}
 

app/vmctl/remoteread.go

@@ -7,8 +7,6 @@ import (
 	"sync"
 	"time"
 
-	"github.com/cheggaaa/pb/v3"
-
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/barpool"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/remoteread"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/stepper"
@@ -22,7 +20,6 @@ type remoteReadProcessor struct {
 	src *remoteread.Client
 
 	cc        int
-	isSilent  bool
 	isVerbose bool
 }
 
@@ -50,21 +47,17 @@ func (rrp *remoteReadProcessor) run(ctx context.Context) error {
 
 	question := fmt.Sprintf("Selected time range %q - %q will be split into %d ranges according to %q step. Continue?",
 		rrp.filter.timeStart.String(), rrp.filter.timeEnd.String(), len(ranges), rrp.filter.chunk)
-	if !rrp.isSilent && !prompt(question) {
+	if !prompt(question) {
 		return nil
 	}
 
-	var bar *pb.ProgressBar
-	if !rrp.isSilent {
-		bar = barpool.AddWithTemplate(fmt.Sprintf(barTpl, "Processing ranges"), len(ranges))
-		if err := barpool.Start(); err != nil {
-			return err
-		}
+	bar := barpool.AddWithTemplate(fmt.Sprintf(barTpl, "Processing ranges"), len(ranges))
+	if err := barpool.Start(); err != nil {
+		return err
 	}
+
 	defer func() {
-		if !rrp.isSilent {
-			barpool.Stop()
-		}
+		barpool.Stop()
 		log.Println("Import finished!")
 		log.Print(rrp.dst.Stats())
 	}()
@@ -82,9 +75,7 @@ func (rrp *remoteReadProcessor) run(ctx context.Context) error {
 					errCh <- fmt.Errorf("request failed for: %s", err)
 					return
 				}
-				if bar != nil {
-					bar.Increment()
-				}
+				bar.Increment()
 			}
 		}()
 	}

app/vmctl/utils.go

@@ -12,7 +12,13 @@ import (
 
 const barTpl = `{{ blue "%s:" }} {{ counters . }} {{ bar . "[" "█" (cycle . "█") "▒" "]" }} {{ percent . }}`
 
+// isSilent should be inited in main
+var isSilent bool
+
 func prompt(question string) bool {
+	if isSilent {
+		return true
+	}
 	isTerminal := terminal.IsTerminal(int(os.Stdout.Fd()))
 	if !isTerminal {
 		return true

app/vmctl/vm/vm.go

@@ -16,7 +16,6 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/barpool"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/limiter"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/decimal"
-	"github.com/cheggaaa/pb/v3"
 )
 
 // Config contains list of params to configure
@@ -55,8 +54,6 @@ type Config struct {
 	// RateLimit defines a data transfer speed in bytes per second.
 	// Is applied to each worker (see Concurrency) independently.
 	RateLimit int64
-	// Whether to disable progress bar per VM worker
-	DisableProgressBar bool
 }
 
 // Importer performs insertion of timeseries
@@ -159,12 +156,10 @@ func NewImporter(ctx context.Context, cfg Config) (*Importer, error) {
 
 	im.wg.Add(int(cfg.Concurrency))
 	for i := 0; i < int(cfg.Concurrency); i++ {
-		var bar *pb.ProgressBar
-		if !cfg.DisableProgressBar {
-			pbPrefix := fmt.Sprintf(`{{ green "VM worker %d:" }}`, i)
-			bar = barpool.AddWithTemplate(pbPrefix+pbTpl, 0)
-		}
-		go func(bar *pb.ProgressBar) {
+		pbPrefix := fmt.Sprintf(`{{ green "VM worker %d:" }}`, i)
+		bar := barpool.AddWithTemplate(pbPrefix+pbTpl, 0)
+
+		go func(bar barpool.Bar) {
 			defer im.wg.Done()
 			im.startWorker(ctx, bar, cfg.BatchSize, cfg.SignificantFigures, cfg.RoundDigits)
 		}(bar)
@@ -217,7 +212,7 @@ func (im *Importer) Close() {
 	})
 }
 
-func (im *Importer) startWorker(ctx context.Context, bar *pb.ProgressBar, batchSize, significantFigures, roundDigits int) {
+func (im *Importer) startWorker(ctx context.Context, bar barpool.Bar, batchSize, significantFigures, roundDigits int) {
 	var batch []*TimeSeries
 	var dataPoints int
 	var waitForBatch time.Time
@@ -252,9 +247,7 @@ func (im *Importer) startWorker(ctx context.Context, bar *pb.ProgressBar, batchS
 			batch = append(batch, ts)
 			dataPoints += len(ts.Values)
 
-			if bar != nil {
-				bar.Add(len(ts.Values))
-			}
+			bar.Add(len(ts.Values))
 
 			if dataPoints < batchSize {
 				continue

app/vmctl/vm_native.go

@@ -9,8 +9,6 @@ import (
 	"sync"
 	"time"
 
-	"github.com/cheggaaa/pb/v3"
-
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/backoff"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/barpool"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/limiter"
@@ -33,7 +31,6 @@ type vmNativeProcessor struct {
 	rateLimit    int64
 	interCluster bool
 	cc           int
-	isSilent     bool
 	isNative     bool
 
 	disablePerMetricRequests bool
@@ -82,13 +79,13 @@ func (p *vmNativeProcessor) run(ctx context.Context) error {
 			return fmt.Errorf("failed to get tenants: %w", err)
 		}
 		question := fmt.Sprintf("The following tenants were discovered: %s.\n Continue?", tenants)
-		if !p.isSilent && !prompt(question) {
+		if !prompt(question) {
 			return nil
 		}
 	}
 
 	for _, tenantID := range tenants {
-		err := p.runBackfilling(ctx, tenantID, ranges, p.isSilent)
+		err := p.runBackfilling(ctx, tenantID, ranges)
 		if err != nil {
 			return fmt.Errorf("migration failed: %s", err)
 		}
@@ -100,7 +97,7 @@ func (p *vmNativeProcessor) run(ctx context.Context) error {
 	return nil
 }
 
-func (p *vmNativeProcessor) do(ctx context.Context, f native.Filter, srcURL, dstURL string, bar *pb.ProgressBar) error {
+func (p *vmNativeProcessor) do(ctx context.Context, f native.Filter, srcURL, dstURL string, bar barpool.Bar) error {
 
 	retryableFunc := func() error { return p.runSingle(ctx, f, srcURL, dstURL, bar) }
 	attempts, err := p.backoff.Retry(ctx, retryableFunc)
@@ -114,15 +111,18 @@ func (p *vmNativeProcessor) do(ctx context.Context, f native.Filter, srcURL, dst
 	return nil
 }
 
-func (p *vmNativeProcessor) runSingle(ctx context.Context, f native.Filter, srcURL, dstURL string, bar *pb.ProgressBar) error {
+func (p *vmNativeProcessor) runSingle(ctx context.Context, f native.Filter, srcURL, dstURL string, bar barpool.Bar) error {
 	reader, err := p.src.ExportPipe(ctx, srcURL, f)
 	if err != nil {
 		return fmt.Errorf("failed to init export pipe: %w", err)
 	}
 
-	if p.disablePerMetricRequests && bar != nil {
-		fmt.Printf("Continue import process with filter %s:\n", f.String())
-		reader = bar.NewProxyReader(reader)
+	if p.disablePerMetricRequests {
+		pr := bar.NewProxyReader(reader)
+		if pr != nil {
+			reader = bar.NewProxyReader(reader)
+			fmt.Printf("Continue import process with filter %s:\n", f.String())
+		}
 	}
 
 	pr, pw := io.Pipe()
@@ -155,7 +155,7 @@ func (p *vmNativeProcessor) runSingle(ctx context.Context, f native.Filter, srcU
 	return <-importCh
 }
 
-func (p *vmNativeProcessor) runBackfilling(ctx context.Context, tenantID string, ranges [][]time.Time, silent bool) error {
+func (p *vmNativeProcessor) runBackfilling(ctx context.Context, tenantID string, ranges [][]time.Time) error {
 	exportAddr := nativeExportAddr
 	importAddr := nativeImportAddr
 	if p.isNative {
@@ -194,7 +194,7 @@ func (p *vmNativeProcessor) runBackfilling(ctx context.Context, tenantID string,
 		"": ranges,
 	}
 	if !p.disablePerMetricRequests {
-		metrics, err = p.explore(ctx, p.src, tenantID, ranges, silent)
+		metrics, err = p.explore(ctx, p.src, tenantID, ranges)
 		if err != nil {
 			return fmt.Errorf("failed to explore metric names: %s", err)
 		}
@@ -216,26 +216,24 @@ func (p *vmNativeProcessor) runBackfilling(ctx context.Context, tenantID string,
 		// do not prompt for intercluster because there could be many tenants,
 		// and we don't want to interrupt the process when moving to the next tenant.
 		question := foundSeriesMsg + ". Continue?"
-		if !silent && !prompt(question) {
+		if !prompt(question) {
 			return nil
 		}
 	} else {
 		log.Print(foundSeriesMsg)
 	}
 
-	var bar *pb.ProgressBar
 	barPrefix := "Requests to make"
 	if p.interCluster {
 		barPrefix = fmt.Sprintf("Requests to make for tenant %s", tenantID)
 	}
-	if !silent {
-		bar = barpool.NewSingleProgress(fmt.Sprintf(nativeWithBackoffTpl, barPrefix), requestsToMake)
-		if p.disablePerMetricRequests {
-			bar = barpool.NewSingleProgress(nativeSingleProcessTpl, 0)
-		}
-		bar.Start()
-		defer bar.Finish()
+
+	bar := barpool.NewSingleProgress(fmt.Sprintf(nativeWithBackoffTpl, barPrefix), requestsToMake)
+	if p.disablePerMetricRequests {
+		bar = barpool.NewSingleProgress(nativeSingleProcessTpl, 0)
 	}
+	bar.Start()
+	defer bar.Finish()
 
 	filterCh := make(chan native.Filter)
 	errCh := make(chan error, p.cc)
@@ -251,9 +249,7 @@ func (p *vmNativeProcessor) runBackfilling(ctx context.Context, tenantID string,
 						errCh <- err
 						return
 					}
-					if bar != nil {
-						bar.Increment()
-					}
+					bar.Increment()
 				} else {
 					if err := p.runSingle(ctx, f, srcURL, dstURL, bar); err != nil {
 						errCh <- err
@@ -298,15 +294,12 @@ func (p *vmNativeProcessor) runBackfilling(ctx context.Context, tenantID string,
 	return nil
 }
 
-func (p *vmNativeProcessor) explore(ctx context.Context, src *native.Client, tenantID string, ranges [][]time.Time, silent bool) (map[string][][]time.Time, error) {
+func (p *vmNativeProcessor) explore(ctx context.Context, src *native.Client, tenantID string, ranges [][]time.Time) (map[string][][]time.Time, error) {
 	log.Printf("Exploring metrics...")
 
-	var bar *pb.ProgressBar
-	if !silent {
-		bar = barpool.NewSingleProgress(fmt.Sprintf(nativeWithBackoffTpl, "Explore requests to make"), len(ranges))
-		bar.Start()
-		defer bar.Finish()
-	}
+	bar := barpool.NewSingleProgress(fmt.Sprintf(nativeWithBackoffTpl, "Explore requests to make"), len(ranges))
+	bar.Start()
+	defer bar.Finish()
 
 	metrics := make(map[string][][]time.Time)
 	for _, r := range ranges {
@@ -317,9 +310,7 @@ func (p *vmNativeProcessor) explore(ctx context.Context, src *native.Client, ten
 		for i := range ms {
 			metrics[ms[i]] = append(metrics[ms[i]], r)
 		}
-		if bar != nil {
-			bar.Increment()
-		}
+		bar.Increment()
 	}
 	return metrics, nil
 }

app/vmctl/vm_native_test.go

@@ -4,6 +4,7 @@ import (
 	"context"
 	"flag"
 	"fmt"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/barpool"
 	"log"
 	"net/http"
 	"os"
@@ -37,6 +38,12 @@ func Test_vmNativeProcessor_run(t *testing.T) {
 		}
 	}()
 
+	barpool.Disable(true)
+	defer func() {
+		barpool.Disable(false)
+	}()
+	defer func() { isSilent = false }()
+
 	type fields struct {
 		filter       native.Filter
 		dst          *native.Client
@@ -218,6 +225,7 @@ func Test_vmNativeProcessor_run(t *testing.T) {
 				HTTPClient:  &http.Client{Transport: &http.Transport{DisableKeepAlives: false}},
 			}
 
+			isSilent = tt.args.silent
 			p := &vmNativeProcessor{
 				filter:       tt.fields.filter,
 				dst:          tt.fields.dst,
@@ -227,7 +235,6 @@ func Test_vmNativeProcessor_run(t *testing.T) {
 				rateLimit:    tt.fields.rateLimit,
 				interCluster: tt.fields.interCluster,
 				cc:           tt.fields.cc,
-				isSilent:     tt.args.silent,
 				isNative:     true,
 			}
 

app/vminsert/common/streamaggr.go

@@ -32,10 +32,10 @@ var (
 		"See also -streamAggr.dropInputLabels and -dedup.minScrapeInterval and https://docs.victoriametrics.com/stream-aggregation/#deduplication")
 	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")
-	streamAggrIgnoreFirstIntervals = flag.Int("streamAggr.ignoreFirstIntervals", 0, "Number of aggregation intervals to skip after the start. Increase this value if you observe incorrect aggregation results after restarts. It could be caused by receiving unordered delayed data from clients pushing data into the database. "+
-		"See https://docs.victoriametrics.com/stream-aggregation/#ignore-aggregation-intervals-on-start")
 	streamAggrIgnoreOldSamples = flag.Bool("streamAggr.ignoreOldSamples", false, "Whether to ignore input samples with old timestamps outside the current aggregation interval. "+
 		"See https://docs.victoriametrics.com/stream-aggregation/#ignoring-old-samples")
+	streamAggrIgnoreFirstIntervals = flag.Int("streamAggr.ignoreFirstIntervals", 0, "Number of aggregation intervals to skip after the start. Increase this value if you observe incorrect aggregation results after restarts. It could be caused by receiving unordered delayed data from clients pushing data into the database. "+
+		"See https://docs.victoriametrics.com/stream-aggregation/#ignore-aggregation-intervals-on-start")
 )
 
 var (
@@ -57,11 +57,12 @@ func CheckStreamAggrConfig() error {
 		return nil
 	}
 	pushNoop := func(_ []prompbmarshal.TimeSeries) {}
-	opts := &streamaggr.Options{
+	opts := streamaggr.Options{
 		DedupInterval:        *streamAggrDedupInterval,
 		DropInputLabels:      *streamAggrDropInputLabels,
 		IgnoreOldSamples:     *streamAggrIgnoreOldSamples,
 		IgnoreFirstIntervals: *streamAggrIgnoreFirstIntervals,
+		Alias:                "global",
 	}
 	sas, err := streamaggr.LoadFromFile(*streamAggrConfig, pushNoop, opts)
 	if err != nil {
@@ -71,31 +72,28 @@ func CheckStreamAggrConfig() error {
 	return nil
 }
 
-// HasStreamAggrConfigured checks if streamAggr config provided
-func HasStreamAggrConfigured() bool {
-	return *streamAggrConfig != ""
-}
-
 // InitStreamAggr must be called after flag.Parse and before using the common package.
 //
 // MustStopStreamAggr must be called when stream aggr is no longer needed.
 func InitStreamAggr() {
 	saCfgReloaderStopCh = make(chan struct{})
+	rwctx := "global"
 
 	if *streamAggrConfig == "" {
 		if *streamAggrDedupInterval > 0 {
-			deduplicator = streamaggr.NewDeduplicator(pushAggregateSeries, *streamAggrDedupInterval, *streamAggrDropInputLabels)
+			deduplicator = streamaggr.NewDeduplicator(pushAggregateSeries, *streamAggrDedupInterval, *streamAggrDropInputLabels, rwctx)
 		}
 		return
 	}
 
 	sighupCh := procutil.NewSighupChan()
 
-	opts := &streamaggr.Options{
+	opts := streamaggr.Options{
 		DedupInterval:        *streamAggrDedupInterval,
 		DropInputLabels:      *streamAggrDropInputLabels,
 		IgnoreOldSamples:     *streamAggrIgnoreOldSamples,
 		IgnoreFirstIntervals: *streamAggrIgnoreFirstIntervals,
+		Alias:                rwctx,
 	}
 	sas, err := streamaggr.LoadFromFile(*streamAggrConfig, pushAggregateSeries, opts)
 	if err != nil {
@@ -125,11 +123,12 @@ func reloadStreamAggrConfig() {
 	logger.Infof("reloading -streamAggr.config=%q", *streamAggrConfig)
 	saCfgReloads.Inc()
 
-	opts := &streamaggr.Options{
+	opts := streamaggr.Options{
 		DedupInterval:        *streamAggrDedupInterval,
 		DropInputLabels:      *streamAggrDropInputLabels,
 		IgnoreOldSamples:     *streamAggrIgnoreOldSamples,
 		IgnoreFirstIntervals: *streamAggrIgnoreFirstIntervals,
+		Alias:                "global",
 	}
 	sasNew, err := streamaggr.LoadFromFile(*streamAggrConfig, pushAggregateSeries, opts)
 	if err != nil {

app/vminsert/main.go

@@ -26,7 +26,6 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vminsert/prompush"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vminsert/promremotewrite"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vminsert/relabel"
-	"github.com/VictoriaMetrics/VictoriaMetrics/app/vminsert/statsd"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vminsert/vmimport"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
@@ -37,8 +36,6 @@ import (
 	influxserver "github.com/VictoriaMetrics/VictoriaMetrics/lib/ingestserver/influx"
 	opentsdbserver "github.com/VictoriaMetrics/VictoriaMetrics/lib/ingestserver/opentsdb"
 	opentsdbhttpserver "github.com/VictoriaMetrics/VictoriaMetrics/lib/ingestserver/opentsdbhttp"
-	statsdserver "github.com/VictoriaMetrics/VictoriaMetrics/lib/ingestserver/statsd"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/procutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promscrape"
@@ -52,12 +49,6 @@ var (
 		"See also -graphiteListenAddr.useProxyProtocol")
 	graphiteUseProxyProtocol = flag.Bool("graphiteListenAddr.useProxyProtocol", false, "Whether to use proxy protocol for connections accepted at -graphiteListenAddr . "+
 		"See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt")
-	statsdListenAddr = flag.String("statsdListenAddr", "", "TCP and UDP address to listen for Statsd plaintext data. Usually :8125 must be set. Doesn't work if empty. "+
-		"See also -statsdListenAddr.useProxyProtocol")
-	statsdUseProxyProtocol = flag.Bool("statsdListenAddr.useProxyProtocol", false, "Whether to use proxy protocol for connections accepted at -statsdListenAddr . "+
-		"See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt")
-	statsdDisableAggregationEnforcemenet = flag.Bool(`statsd.disableAggregationEnforcement`, false, "Whether to disable streaming aggregation requirement check. "+
-		"It's recommended to run statsdServer with pre-configured streaming aggregation to decrease load at database.")
 	influxListenAddr = flag.String("influxListenAddr", "", "TCP and UDP address to listen for InfluxDB line protocol data. Usually :8089 must be set. Doesn't work if empty. "+
 		"This flag isn't needed when ingesting data over HTTP - just send it to http://<victoriametrics>:8428/write . "+
 		"See also -influxListenAddr.useProxyProtocol")
@@ -73,15 +64,14 @@ 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.")
 	maxLabelsPerTimeseries = flag.Int("maxLabelsPerTimeseries", 30, "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")
 	maxLabelValueLen       = flag.Int("maxLabelValueLen", 1024, "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")
 )
 
 var (
 	graphiteServer     *graphiteserver.Server
-	statsdServer       *statsdserver.Server
 	influxServer       *influxserver.Server
 	opentsdbServer     *opentsdbserver.Server
 	opentsdbhttpServer *opentsdbhttpserver.Server
@@ -102,12 +92,6 @@ func Init() {
 	if len(*graphiteListenAddr) > 0 {
 		graphiteServer = graphiteserver.MustStart(*graphiteListenAddr, *graphiteUseProxyProtocol, graphite.InsertHandler)
 	}
-	if len(*statsdListenAddr) > 0 {
-		if !vminsertCommon.HasStreamAggrConfigured() && !*statsdDisableAggregationEnforcemenet {
-			logger.Fatalf("streaming aggregation must be configured with enabled statsd server. It's recommended  to aggregate metrics received at statsd listener. This check could be disabled with flag -statsd.disableAggregationEnforcement")
-		}
-		statsdServer = statsdserver.MustStart(*statsdListenAddr, *statsdUseProxyProtocol, statsd.InsertHandler)
-	}
 	if len(*influxListenAddr) > 0 {
 		influxServer = influxserver.MustStart(*influxListenAddr, *influxUseProxyProtocol, influx.InsertHandlerForReader)
 	}
@@ -128,9 +112,6 @@ func Stop() {
 	if len(*graphiteListenAddr) > 0 {
 		graphiteServer.MustStop()
 	}
-	if len(*statsdListenAddr) > 0 {
-		statsdServer.MustStop()
-	}
 	if len(*influxListenAddr) > 0 {
 		influxServer.MustStop()
 	}

app/vminsert/statsd/request_handler.go

@@ -1,60 +0,0 @@
-package statsd
-
-import (
-	"io"
-
-	"github.com/VictoriaMetrics/VictoriaMetrics/app/vminsert/common"
-	"github.com/VictoriaMetrics/VictoriaMetrics/app/vminsert/relabel"
-	parser "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/statsd"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/statsd/stream"
-	"github.com/VictoriaMetrics/metrics"
-)
-
-var (
-	rowsInserted  = metrics.NewCounter(`vm_rows_inserted_total{type="statsd"}`)
-	rowsPerInsert = metrics.NewHistogram(`vm_rows_per_insert{type="statsd"}`)
-)
-
-// InsertHandler processes remote write for statsd protocol with tags.
-//
-// https://github.com/statsd/statsd/blob/master/docs/metric_types.md
-func InsertHandler(r io.Reader) error {
-	return stream.Parse(r, false, insertRows)
-}
-
-func insertRows(rows []parser.Row) error {
-	ctx := common.GetInsertCtx()
-	defer common.PutInsertCtx(ctx)
-
-	ctx.Reset(len(rows))
-	hasRelabeling := relabel.HasRelabeling()
-	for i := range rows {
-		r := &rows[i]
-		ctx.Labels = ctx.Labels[:0]
-		ctx.AddLabel("", r.Metric)
-		for j := range r.Tags {
-			tag := &r.Tags[j]
-			ctx.AddLabel(tag.Key, tag.Value)
-		}
-		if hasRelabeling {
-			ctx.ApplyRelabeling()
-		}
-		if len(ctx.Labels) == 0 {
-			// Skip metric without labels.
-			continue
-		}
-		ctx.SortLabelsIfNeeded()
-		var metricName []byte
-		var err error
-		for _, v := range r.Values {
-			metricName, err = ctx.WriteDataPointExt(metricName, ctx.Labels, r.Timestamp, v)
-			if err != nil {
-				return err
-			}
-		}
-
-	}
-	rowsInserted.Add(len(rows))
-	rowsPerInsert.Update(float64(len(rows)))
-	return ctx.FlushBufs()
-}

app/vmrestore/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/vmselect/main.go

@@ -138,7 +138,7 @@ func RequestHandler(w http.ResponseWriter, r *http.Request) bool {
 			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",
+			logger.Infof("client has canceled the request after %.3f seconds: remoteAddr=%s, requestURI: %q",
 				time.Since(startTime).Seconds(), remoteAddr, requestURI)
 			return true
 		case <-t.C: