Compare commits

..

1 Commits

Author SHA1 Message Date
Aliaksandr Valialkin
dd1126dccf app/vmselect/netstorage: fix a typo, which leads to incorrect query results in VictoriaMetrics cluster
The typo has been introduced in the commit 1a254ea20c

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3067
2022-09-08 13:51:14 +03:00
3739 changed files with 126386 additions and 638721 deletions

46
.github/ISSUE_TEMPLATE/bug_report.md vendored Normal file
View File

@@ -0,0 +1,46 @@
---
name: Bug report
about: Create a report to help us improve
title: ''
labels: ''
assignees: ''
---
**Describe the bug**
A clear and concise description of what the bug is.
It would be great to [upgrade](https://docs.victoriametrics.com/#how-to-upgrade)
to [the latest available release](https://github.com/VictoriaMetrics/VictoriaMetrics/releases)
and verify whether the bug is reproducible there.
It's also recommended to read the [troubleshooting docs](https://docs.victoriametrics.com/#troubleshooting).
**To Reproduce**
Steps to reproduce the behavior.
**Expected behavior**
A clear and concise description of what you expected to happen.
**Logs**
Check if any warnings or errors were logged by VictoriaMetrics components
or components in communication with VictoriaMetrics (e.g. Prometheus, Grafana).
**Screenshots**
If applicable, add screenshots to help explain your problem.
For VictoriaMetrics health-state issues please provide full-length screenshots
of Grafana dashboards if possible:
* [Grafana dashboard for single-node VictoriaMetrics](https://grafana.com/dashboards/10229)
* [Grafana dashboard for VictoriaMetrics cluster](https://grafana.com/grafana/dashboards/11176)
See how to setup monitoring here:
* [monitoring for single-node VictoriaMetrics](https://docs.victoriametrics.com/#monitoring)
* [monitoring for VictoriaMetrics cluster](https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html#monitoring)
**Version**
The line returned when passing `--version` command line flag to the binary. For example:
```
$ ./victoria-metrics-prod --version
victoria-metrics-20190730-121249-heads-single-node-0-g671d9e55
```
**Used command-line flags**
Please provide the command-line flags used for running VictoriaMetrics and its components.

View File

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

View File

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

View File

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

View File

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

View File

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

View File

@@ -8,12 +8,10 @@ updates:
directory: "/"
schedule:
interval: "weekly"
open-pull-requests-limit: 0
- package-ecosystem: "bundler"
directory: "/docs"
schedule:
interval: "weekly"
open-pull-requests-limit: 0
interval: "daily"
- package-ecosystem: "gomod"
directory: "/app/vmui/packages/vmui/web"
schedule:

View File

@@ -17,7 +17,7 @@ jobs:
- name: Setup Go
uses: actions/setup-go@main
with:
go-version: 1.20.7
go-version: 1.18
id: go
- name: Code checkout
uses: actions/checkout@master

View File

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

View File

@@ -13,26 +13,12 @@ name: "CodeQL"
on:
push:
branches: [master, cluster]
paths-ignore:
- "docs/**"
- "**.md"
- "**.txt"
- "**.js"
branches: [ master, cluster ]
pull_request:
# The branches below must be a subset of the branches above
branches: [master, cluster]
paths-ignore:
- "docs/**"
- "**.md"
- "**.txt"
- "**.js"
branches: [ master, cluster ]
schedule:
- cron: "30 18 * * 2"
concurrency:
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
cancel-in-progress: true
- cron: '30 18 * * 2'
jobs:
analyze:
@@ -46,47 +32,39 @@ jobs:
strategy:
fail-fast: false
matrix:
language: ["go"]
language: [ 'go', 'javascript' ]
# CodeQL supports [ 'cpp', 'csharp', 'go', 'java', 'javascript', 'python', 'ruby' ]
# Learn more about CodeQL language support at https://git.io/codeql-language-support
steps:
- name: Checkout repository
uses: actions/checkout@v3
- name: Checkout repository
uses: actions/checkout@v3
- name: Set up Go
uses: actions/setup-go@v4
with:
go-version: 1.20.7
check-latest: true
cache: true
if: ${{ matrix.language == 'go' }}
# Initializes the CodeQL tools for scanning.
- name: Initialize CodeQL
uses: github/codeql-action/init@v2
with:
languages: ${{ matrix.language }}
# If you wish to specify custom queries, you can do so here or in a config file.
# By default, queries listed here will override any specified in a config file.
# Prefix the list here with "+" to use these queries and those in the config file.
# queries: ./path/to/local/query, your-org/your-repo/queries@main
# Initializes the CodeQL tools for scanning.
- name: Initialize CodeQL
uses: github/codeql-action/init@v2
with:
languages: ${{ matrix.language }}
# If you wish to specify custom queries, you can do so here or in a config file.
# By default, queries listed here will override any specified in a config file.
# Prefix the list here with "+" to use these queries and those in the config file.
# queries: ./path/to/local/query, your-org/your-repo/queries@main
# Autobuild attempts to build any compiled languages (C/C++, C#, or Java).
# If this step fails, then you should remove it and run the build manually (see below)
- name: Autobuild
uses: github/codeql-action/autobuild@v2
# Autobuild attempts to build any compiled languages (C/C++, C#, or Java).
# If this step fails, then you should remove it and run the build manually (see below)
- name: Autobuild
uses: github/codeql-action/autobuild@v2
# Command-line programs to run using the OS shell.
# 📚 https://git.io/JvXDl
# Command-line programs to run using the OS shell.
# 📚 https://git.io/JvXDl
# If the Autobuild fails above, remove it and uncomment the following three lines
# and modify them (or add more) to build your code if your project
# uses a compiled language
# ✏️ If the Autobuild fails above, remove it and uncomment the following three lines
# and modify them (or add more) to build your code if your project
# uses a compiled language
#- run: |
# make bootstrap
# make release
#- run: |
# make bootstrap
# make release
- name: Perform CodeQL Analysis
uses: github/codeql-action/analyze@v2
- name: Perform CodeQL Analysis
uses: github/codeql-action/analyze@v2

View File

@@ -1,96 +1,47 @@
name: main
on:
push:
branches:
- master
- cluster
paths-ignore:
- "docs/**"
- "**.md"
- 'docs/**'
- '**.md'
pull_request:
branches:
- master
- cluster
paths-ignore:
- "docs/**"
- "**.md"
- 'docs/**'
- '**.md'
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
cancel-in-progress: true
jobs:
lint:
name: lint
build:
name: Build
runs-on: ubuntu-latest
steps:
- name: Code checkout
uses: actions/checkout@v3
- name: Setup Go
uses: actions/setup-go@v4
uses: actions/setup-go@main
with:
go-version: 1.20.7
check-latest: true
cache: true
go-version: 1.18
id: go
- name: Code checkout
uses: actions/checkout@master
- name: Dependencies
run: |
make install-golint
make install-errcheck
make install-golangci-lint
- name: Build
env:
GO111MODULE: on
run: |
export PATH=$PATH:$(go env GOPATH)/bin # temporary fix. See https://github.com/actions/setup-go/issues/14
make check-all
git diff --exit-code
test:
needs: lint
strategy:
matrix:
scenario: ["test-full", "test-pure", "test-full-386"]
name: test
runs-on: ubuntu-latest
steps:
- name: Code checkout
uses: actions/checkout@v3
- name: Setup Go
uses: actions/setup-go@v4
with:
go-version: 1.20.7
check-latest: true
cache: true
- name: run tests
run: |
make ${{ matrix.scenario}}
make test-full
make test-pure
make test-full-386
make victoria-metrics-crossbuild
make vmuitils-crossbuild
- name: Publish coverage
uses: codecov/codecov-action@v3
with:
file: ./coverage.txt
build:
needs: test
name: build
runs-on: ubuntu-latest
steps:
- name: Code checkout
uses: actions/checkout@v3
- name: Setup Go
id: go
uses: actions/setup-go@v4
with:
go-version: 1.20.7
check-latest: true
cache: true
- uses: actions/cache@v3
with:
path: gocache-for-docker
key: gocache-docker-${{ runner.os }}-${{ steps.go.outputs.go-version }}-${{ hashFiles('go.mod') }}
- name: Build
run: |
make victoria-metrics-crossbuild
make vmuitils-crossbuild

View File

@@ -1,53 +0,0 @@
name: publish-docs
on:
push:
branches:
- 'master'
paths:
- 'docs/**'
workflow_dispatch: {}
permissions:
contents: read # This is required for actions/checkout and to commit back image update
deployments: write
jobs:
build:
name: Build
runs-on: ubuntu-latest
steps:
- name: Code checkout
uses: actions/checkout@v3
with:
path: main
- name: Checkout private code
uses: actions/checkout@v3
with:
repository: VictoriaMetrics/vmdocs
token: ${{ secrets.VM_BOT_GH_TOKEN }}
path: docs
- name: Import GPG key
uses: crazy-max/ghaction-import-gpg@v5
with:
gpg_private_key: ${{ secrets.VM_BOT_GPG_PRIVATE_KEY }}
passphrase: ${{ secrets.VM_BOT_PASSPHRASE }}
git_user_signingkey: true
git_commit_gpgsign: true
workdir: docs
- name: Set short git commit SHA
id: vars
run: |
calculatedSha=$(git rev-parse --short ${{ github.sha }})
echo "short_sha=$calculatedSha" >> $GITHUB_OUTPUT
working-directory: main
- name: update code and commit
run: |
rm -rf content
cp -r ../main/docs content
make clean-after-copy
git config --global user.name "${{ steps.import-gpg.outputs.email }}"
git config --global user.email "${{ steps.import-gpg.outputs.email }}"
git add .
git commit -S -m "sync docs with VictoriaMetrics/VictoriaMetrics commit: ${{ steps.vars.outputs.short_sha }}"
git push
working-directory: docs

View File

@@ -1,80 +0,0 @@
name: sandbox-release
on:
release:
types: [published]
permissions:
contents: write
jobs:
deploy-sandbox:
runs-on: ubuntu-latest
steps:
- name: check inputs
if: github.event.release.tag_name == ''
run: exit 1
- name: Check out code
uses: actions/checkout@v3
with:
repository: VictoriaMetrics/ops
token: ${{ secrets.VM_BOT_GH_TOKEN }}
- name: Import GPG key
id: import-gpg
uses: crazy-max/ghaction-import-gpg@v5
with:
gpg_private_key: ${{ secrets.VM_BOT_GPG_PRIVATE_KEY }}
passphrase: ${{ secrets.VM_BOT_PASSPHRASE }}
git_user_signingkey: true
git_commit_gpgsign: true
- name: update image tag
uses: fjogeleit/yaml-update-action@main
with:
valueFile: 'gcp-test/sandbox/manifests/benchmark-vm/vmcluster.yaml'
commitChange: false
createPR: false
changes: |
{
"gcp-test/sandbox/manifests/benchmark-vm/vmcluster.yaml": {
"spec.vminsert.image.tag": "${{ github.event.release.tag_name }}-enterprise-cluster",
"spec.vmselect.image.tag": "${{ github.event.release.tag_name }}-enterprise-cluster",
"spec.vmstorage.image.tag": "${{ github.event.release.tag_name }}-enterprise-cluster"
},
"gcp-test/sandbox/manifests/benchmark-vm/vmsingle.yaml": {
"spec.image.tag": "${{ github.event.release.tag_name }}-enterprise"
},
"gcp-test/sandbox/manifests/monitoring/monitoring-vmagent.yaml": {
"spec.image.tag": "${{ github.event.release.tag_name }}"
},
"gcp-test/sandbox/manifests/monitoring/monitoring-vmcluster.yaml": {
"spec.vminsert.image.tag": "${{ github.event.release.tag_name }}-enterprise-cluster",
"spec.vmselect.image.tag": "${{ github.event.release.tag_name }}-enterprise-cluster",
"spec.vmstorage.image.tag": "${{ github.event.release.tag_name }}-enterprise-cluster"
},
"gcp-test/sandbox/manifests/monitoring/vmalert.yaml": {
"spec.image.tag": "${{ github.event.release.tag_name }}-enterprise"
}
}
- name: commit changes
run: |
git config --global user.name "${{ steps.import-gpg.outputs.email }}"
git config --global user.email "${{ steps.import-gpg.outputs.email }}"
git add .
git commit -S -m "Deploy image tag ${RELEASE_TAG} to sandbox"
env:
RELEASE_TAG: ${{ github.event.release.tag_name }}
- name: Create Pull Request
uses: peter-evans/create-pull-request@v5
with:
author: ${{ github.actor }} <${{ github.actor }}@users.noreply.github.com>
branch: release-automation
token: ${{ secrets.VM_BOT_GH_TOKEN }}
delete-branch: true
title: "release ${{ github.event.release.tag_name }}"
body: |
Release [${{ github.event.release.tag_name }}](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/${{ github.event.release.tag_name }}) to sandbox
> Auto-generated by `Github Actions Bot`

4
.gitignore vendored
View File

@@ -8,7 +8,6 @@
*.test
*.swp
/gocache-for-docker
/victoria-logs-data
/victoria-metrics-data
/vmagent-remotewrite-data
/vmstorage-data
@@ -20,5 +19,4 @@
.DS_store
Gemfile.lock
/_site
_site
*.tmp
_site

View File

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

View File

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

View File

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

201
Makefile
View File

@@ -2,8 +2,7 @@ PKG_PREFIX := github.com/VictoriaMetrics/VictoriaMetrics
DATEINFO_TAG ?= $(shell date -u +'%Y%m%d-%H%M%S')
BUILDINFO_TAG ?= $(shell echo $$(git describe --long --all | tr '/' '-')$$( \
git diff-index --quiet HEAD -- || echo '-dirty-'$$(git diff-index -u HEAD | openssl sha1 | cut -d' ' -f2 | cut -c 1-8)))
LATEST_TAG ?= latest
git diff-index --quiet HEAD -- || echo '-dirty-'$$(git diff-index -u HEAD | openssl sha1 | cut -c 10-17)))
PKG_TAG ?= $(shell git tag -l --points-at HEAD)
ifeq ($(PKG_TAG),)
@@ -21,7 +20,6 @@ include package/release/Makefile
all: \
victoria-metrics-prod \
victoria-logs-prod \
vmagent-prod \
vmalert-prod \
vmauth-prod \
@@ -32,9 +30,8 @@ all: \
clean:
rm -rf bin/*
publish: package-base \
publish: docker-scan \
publish-victoria-metrics \
publish-victoria-logs \
publish-vmagent \
publish-vmalert \
publish-vmauth \
@@ -44,7 +41,6 @@ publish: package-base \
package: \
package-victoria-metrics \
package-victoria-logs \
package-vmagent \
package-vmalert \
package-vmauth \
@@ -144,12 +140,9 @@ vmutils-windows-amd64: \
vmagent-windows-amd64 \
vmalert-windows-amd64 \
vmauth-windows-amd64 \
vmbackup-windows-amd64 \
vmrestore-windows-amd64 \
vmctl-windows-amd64
victoria-metrics-crossbuild: \
victoria-metrics-linux-386 \
victoria-metrics-linux-amd64 \
victoria-metrics-linux-arm64 \
victoria-metrics-linux-arm \
@@ -161,7 +154,6 @@ victoria-metrics-crossbuild: \
victoria-metrics-openbsd-amd64
vmutils-crossbuild: \
vmutils-linux-386 \
vmutils-linux-amd64 \
vmutils-linux-arm64 \
vmutils-linux-arm \
@@ -174,29 +166,26 @@ vmutils-crossbuild: \
vmutils-windows-amd64
publish-release:
git checkout $(TAG) && LATEST_TAG=stable $(MAKE) release publish && \
git checkout $(TAG)-cluster && LATEST_TAG=cluster-stable $(MAKE) release publish && \
git checkout $(TAG)-enterprise && LATEST_TAG=enterprise-stable $(MAKE) release publish && \
git checkout $(TAG)-enterprise-cluster && LATEST_TAG=enterprise-cluster-stable $(MAKE) release publish
git checkout $(TAG) && $(MAKE) release publish && \
git checkout $(TAG)-cluster && $(MAKE) release publish && \
git checkout $(TAG)-enterprise && $(MAKE) release publish && \
git checkout $(TAG)-enterprise-cluster && $(MAKE) release publish && \
git checkout $(TAG) && git push $(TAG) && git push $(TAG)-cluster && \
$(MAKE) github-create-release && \
$(MAKE) github-upload-assets
release: \
release-victoria-metrics \
release-victoria-logs \
release-vmutils
release-victoria-metrics: \
release-victoria-metrics-linux-386 \
release-victoria-metrics-linux-amd64 \
release-victoria-metrics-linux-arm \
release-victoria-metrics-linux-arm64 \
release-victoria-metrics-darwin-amd64 \
release-victoria-metrics-darwin-arm64 \
release-victoria-metrics-freebsd-amd64 \
release-victoria-metrics-openbsd-amd64 \
release-victoria-metrics-windows-amd64
release-victoria-metrics-linux-386:
GOOS=linux GOARCH=386 $(MAKE) release-victoria-metrics-goos-goarch
release-victoria-metrics-openbsd-amd64
release-victoria-metrics-linux-amd64:
GOOS=linux GOARCH=amd64 $(MAKE) release-victoria-metrics-goos-goarch
@@ -219,9 +208,6 @@ release-victoria-metrics-freebsd-amd64:
release-victoria-metrics-openbsd-amd64:
GOOS=openbsd GOARCH=amd64 $(MAKE) release-victoria-metrics-goos-goarch
release-victoria-metrics-windows-amd64:
GOARCH=amd64 $(MAKE) release-victoria-metrics-windows-goarch
release-victoria-metrics-goos-goarch: victoria-metrics-$(GOOS)-$(GOARCH)-prod
cd bin && \
tar --transform="flags=r;s|-$(GOOS)-$(GOARCH)||" -czf victoria-metrics-$(GOOS)-$(GOARCH)-$(PKG_TAG).tar.gz \
@@ -231,75 +217,7 @@ release-victoria-metrics-goos-goarch: victoria-metrics-$(GOOS)-$(GOARCH)-prod
| sed s/-$(GOOS)-$(GOARCH)-prod/-prod/ > victoria-metrics-$(GOOS)-$(GOARCH)-$(PKG_TAG)_checksums.txt
cd bin && rm -rf victoria-metrics-$(GOOS)-$(GOARCH)-prod
release-victoria-metrics-windows-goarch: victoria-metrics-windows-$(GOARCH)-prod
cd bin && \
zip victoria-metrics-windows-$(GOARCH)-$(PKG_TAG).zip \
victoria-metrics-windows-$(GOARCH)-prod.exe \
&& sha256sum victoria-metrics-windows-$(GOARCH)-$(PKG_TAG).zip \
victoria-metrics-windows-$(GOARCH)-prod.exe \
> victoria-metrics-windows-$(GOARCH)-$(PKG_TAG)_checksums.txt
cd bin && rm -rf \
victoria-metrics-windows-$(GOARCH)-prod.exe
release-victoria-logs: \
release-victoria-logs-linux-386 \
release-victoria-logs-linux-amd64 \
release-victoria-logs-linux-arm \
release-victoria-logs-linux-arm64 \
release-victoria-logs-darwin-amd64 \
release-victoria-logs-darwin-arm64 \
release-victoria-logs-freebsd-amd64 \
release-victoria-logs-openbsd-amd64 \
release-victoria-logs-windows-amd64
release-victoria-logs-linux-386:
GOOS=linux GOARCH=386 $(MAKE) release-victoria-logs-goos-goarch
release-victoria-logs-linux-amd64:
GOOS=linux GOARCH=amd64 $(MAKE) release-victoria-logs-goos-goarch
release-victoria-logs-linux-arm:
GOOS=linux GOARCH=arm $(MAKE) release-victoria-logs-goos-goarch
release-victoria-logs-linux-arm64:
GOOS=linux GOARCH=arm64 $(MAKE) release-victoria-logs-goos-goarch
release-victoria-logs-darwin-amd64:
GOOS=darwin GOARCH=amd64 $(MAKE) release-victoria-logs-goos-goarch
release-victoria-logs-darwin-arm64:
GOOS=darwin GOARCH=arm64 $(MAKE) release-victoria-logs-goos-goarch
release-victoria-logs-freebsd-amd64:
GOOS=freebsd GOARCH=amd64 $(MAKE) release-victoria-logs-goos-goarch
release-victoria-logs-openbsd-amd64:
GOOS=openbsd GOARCH=amd64 $(MAKE) release-victoria-logs-goos-goarch
release-victoria-logs-windows-amd64:
GOARCH=amd64 $(MAKE) release-victoria-logs-windows-goarch
release-victoria-logs-goos-goarch: victoria-logs-$(GOOS)-$(GOARCH)-prod
cd bin && \
tar --transform="flags=r;s|-$(GOOS)-$(GOARCH)||" -czf victoria-logs-$(GOOS)-$(GOARCH)-$(PKG_TAG).tar.gz \
victoria-logs-$(GOOS)-$(GOARCH)-prod \
&& sha256sum victoria-logs-$(GOOS)-$(GOARCH)-$(PKG_TAG).tar.gz \
victoria-logs-$(GOOS)-$(GOARCH)-prod \
| sed s/-$(GOOS)-$(GOARCH)-prod/-prod/ > victoria-logs-$(GOOS)-$(GOARCH)-$(PKG_TAG)_checksums.txt
cd bin && rm -rf victoria-logs-$(GOOS)-$(GOARCH)-prod
release-victoria-logs-windows-goarch: victoria-logs-windows-$(GOARCH)-prod
cd bin && \
zip victoria-logs-windows-$(GOARCH)-$(PKG_TAG).zip \
victoria-logs-windows-$(GOARCH)-prod.exe \
&& sha256sum victoria-logs-windows-$(GOARCH)-$(PKG_TAG).zip \
victoria-logs-windows-$(GOARCH)-prod.exe \
> victoria-logs-windows-$(GOARCH)-$(PKG_TAG)_checksums.txt
cd bin && rm -rf \
victoria-logs-windows-$(GOARCH)-prod.exe
release-vmutils: \
release-vmutils-linux-386 \
release-vmutils-linux-amd64 \
release-vmutils-linux-arm64 \
release-vmutils-linux-arm \
@@ -309,9 +227,6 @@ release-vmutils: \
release-vmutils-openbsd-amd64 \
release-vmutils-windows-amd64
release-vmutils-linux-386:
GOOS=linux GOARCH=386 $(MAKE) release-vmutils-goos-goarch
release-vmutils-linux-amd64:
GOOS=linux GOARCH=amd64 $(MAKE) release-vmutils-goos-goarch
@@ -371,33 +286,26 @@ release-vmutils-windows-goarch: \
vmagent-windows-$(GOARCH)-prod \
vmalert-windows-$(GOARCH)-prod \
vmauth-windows-$(GOARCH)-prod \
vmbackup-windows-$(GOARCH)-prod \
vmrestore-windows-$(GOARCH)-prod \
vmctl-windows-$(GOARCH)-prod
cd bin && \
zip vmutils-windows-$(GOARCH)-$(PKG_TAG).zip \
vmagent-windows-$(GOARCH)-prod.exe \
vmalert-windows-$(GOARCH)-prod.exe \
vmauth-windows-$(GOARCH)-prod.exe \
vmbackup-windows-$(GOARCH)-prod.exe \
vmrestore-windows-$(GOARCH)-prod.exe \
vmctl-windows-$(GOARCH)-prod.exe \
&& sha256sum vmutils-windows-$(GOARCH)-$(PKG_TAG).zip \
vmagent-windows-$(GOARCH)-prod.exe \
vmalert-windows-$(GOARCH)-prod.exe \
vmauth-windows-$(GOARCH)-prod.exe \
vmbackup-windows-$(GOARCH)-prod.exe \
vmrestore-windows-$(GOARCH)-prod.exe \
vmctl-windows-$(GOARCH)-prod.exe \
> vmutils-windows-$(GOARCH)-$(PKG_TAG)_checksums.txt
cd bin && rm -rf \
vmagent-windows-$(GOARCH)-prod.exe \
vmalert-windows-$(GOARCH)-prod.exe \
vmauth-windows-$(GOARCH)-prod.exe \
vmbackup-windows-$(GOARCH)-prod.exe \
vmrestore-windows-$(GOARCH)-prod.exe \
vmctl-windows-$(GOARCH)-prod.exe
pprof-cpu:
go tool pprof -trim_path=github.com/VictoriaMetrics/VictoriaMetrics@ $(PPROF_FILE)
@@ -409,7 +317,29 @@ vet:
go vet ./lib/...
go vet ./app/...
check-all: fmt vet golangci-lint govulncheck
lint: install-golint
golint lib/...
golint app/...
install-golint:
which golint || GO111MODULE=off go get golang.org/x/lint/golint
errcheck: install-errcheck
errcheck -exclude=errcheck_excludes.txt ./lib/...
errcheck -exclude=errcheck_excludes.txt ./app/vminsert/...
errcheck -exclude=errcheck_excludes.txt ./app/vmselect/...
errcheck -exclude=errcheck_excludes.txt ./app/vmstorage/...
errcheck -exclude=errcheck_excludes.txt ./app/vmagent/...
errcheck -exclude=errcheck_excludes.txt ./app/vmalert/...
errcheck -exclude=errcheck_excludes.txt ./app/vmauth/...
errcheck -exclude=errcheck_excludes.txt ./app/vmbackup/...
errcheck -exclude=errcheck_excludes.txt ./app/vmrestore/...
errcheck -exclude=errcheck_excludes.txt ./app/vmctl/...
install-errcheck:
which errcheck || GO111MODULE=off go get github.com/kisielk/errcheck
check-all: fmt vet lint errcheck golangci-lint
test:
go test ./lib/... ./app/...
@@ -437,7 +367,7 @@ benchmark-pure:
vendor-update:
go get -u -d ./lib/...
go get -u -d ./app/...
go mod tidy -compat=1.19
go mod tidy -compat=1.18
go mod vendor
app-local:
@@ -456,61 +386,36 @@ quicktemplate-gen: install-qtc
qtc
install-qtc:
which qtc || go install github.com/valyala/quicktemplate/qtc@latest
which qtc || GO111MODULE=off go get github.com/valyala/quicktemplate/qtc
golangci-lint: install-golangci-lint
golangci-lint run
golangci-lint run --exclude '(SA4003|SA1019|SA5011):' -D errcheck -D structcheck --timeout 2m
install-golangci-lint:
which golangci-lint || curl -sSfL https://raw.githubusercontent.com/golangci/golangci-lint/master/install.sh | sh -s -- -b $(shell go env GOPATH)/bin v1.51.2
govulncheck: install-govulncheck
govulncheck ./...
install-govulncheck:
which govulncheck || go install golang.org/x/vuln/cmd/govulncheck@latest
which golangci-lint || curl -sSfL https://raw.githubusercontent.com/golangci/golangci-lint/master/install.sh | sh -s -- -b $(shell go env GOPATH)/bin v1.48.0
install-wwhrd:
which wwhrd || go install github.com/frapposelli/wwhrd@latest
which wwhrd || GO111MODULE=off go get github.com/frapposelli/wwhrd
check-licenses: install-wwhrd
wwhrd check -f .wwhrd.yml
copy-docs:
# The 'printf' function is used instead of 'echo' or 'echo -e' to handle line breaks (e.g. '\n') in the same way on different operating systems (MacOS/Ubuntu Linux/Arch Linux) and their shells (bash/sh/zsh/fish).
# For details, see https://github.com/VictoriaMetrics/VictoriaMetrics/pull/4548#issue-1782796419 and https://stackoverflow.com/questions/8467424/echo-newline-in-bash-prints-literal-n
echo "---" > ${DST}
@if [ ${ORDER} -ne 0 ]; then \
echo "sort: ${ORDER}" >> ${DST}; \
echo "weight: ${ORDER}" >> ${DST}; \
printf "menu:\n docs:\n parent: 'victoriametrics'\n weight: ${ORDER}\n" >> ${DST}; \
fi
echo "title: ${TITLE}" >> ${DST}
@if [ ${OLD_URL} ]; then \
printf "aliases:\n - ${OLD_URL}\n" >> ${DST}; \
fi
echo "---" >> ${DST}
echo "---\nsort: ${ORDER}\n---\n" > ${DST}
cat ${SRC} >> ${DST}
sed -i='.tmp' 's/<img src=\"docs\//<img src=\"/' ${DST}
rm -rf docs/*.tmp
# Copies docs for all components and adds the order/weight tag, title, menu position and alias with the backward compatible link for the old site.
# For ORDER=0 it adds no order tag/weight tag.
# FOR OLD_URL - relative link, used for backward compatibility with the link from documentation based on GitHub pages (old one)
# FOR OLD_URL='' it adds no alias, it should be empty for every new page, don't change it for already existing links.
# Images starting with <img src="docs/ are replaced with <img src="
# Cluster docs are supposed to be ordered as 2nd.
# The rest of docs is ordered manually.
# Copies docs for all components and adds the order tag.
# Cluster docs are supposed to be ordered as 9th.
# For The rest of docs is ordered manually.t
docs-sync:
SRC=README.md DST=docs/README.md OLD_URL='' ORDER=0 TITLE=VictoriaMetrics $(MAKE) copy-docs
SRC=README.md DST=docs/Single-server-VictoriaMetrics.md OLD_URL='/Single-server-VictoriaMetrics.html' TITLE=VictoriaMetrics ORDER=1 $(MAKE) copy-docs
SRC=app/vmagent/README.md DST=docs/vmagent.md OLD_URL='/vmagent.html' ORDER=3 TITLE=vmagent $(MAKE) copy-docs
SRC=app/vmalert/README.md DST=docs/vmalert.md OLD_URL='/vmalert.html' ORDER=4 TITLE=vmalert $(MAKE) copy-docs
SRC=app/vmauth/README.md DST=docs/vmauth.md OLD_URL='/vmauth.html' ORDER=5 TITLE=vmauth $(MAKE) copy-docs
SRC=app/vmbackup/README.md DST=docs/vmbackup.md OLD_URL='/vmbackup.html' ORDER=6 TITLE=vmbackup $(MAKE) copy-docs
SRC=app/vmrestore/README.md DST=docs/vmrestore.md OLD_URL='/vmrestore.html' ORDER=7 TITLE=vmrestore $(MAKE) copy-docs
SRC=app/vmctl/README.md DST=docs/vmctl.md OLD_URL='/vmctl.html' ORDER=8 TITLE=vmctl $(MAKE) copy-docs
SRC=app/vmgateway/README.md DST=docs/vmgateway.md OLD_URL='/vmgateway.html' ORDER=9 TITLE=vmgateway $(MAKE) copy-docs
SRC=app/vmbackupmanager/README.md DST=docs/vmbackupmanager.md OLD_URL='/vmbackupmanager.html' ORDER=10 TITLE=vmbackupmanager $(MAKE) copy-docs
cp README.md docs/README.md
SRC=README.md DST=docs/Single-server-VictoriaMetrics.md ORDER=1 $(MAKE) copy-docs
SRC=app/vmagent/README.md DST=docs/vmagent.md ORDER=3 $(MAKE) copy-docs
SRC=app/vmalert/README.md DST=docs/vmalert.md ORDER=4 $(MAKE) copy-docs
SRC=app/vmauth/README.md DST=docs/vmauth.md ORDER=5 $(MAKE) copy-docs
SRC=app/vmbackup/README.md DST=docs/vmbackup.md ORDER=6 $(MAKE) copy-docs
SRC=app/vmrestore/README.md DST=docs/vmrestore.md ORDER=7 $(MAKE) copy-docs
SRC=app/vmctl/README.md DST=docs/vmctl.md ORDER=8 $(MAKE) copy-docs
SRC=app/vmgateway/README.md DST=docs/vmgateway.md ORDER=9 $(MAKE) copy-docs
SRC=app/vmbackupmanager/README.md DST=docs/vmbackupmanager.md ORDER=10 $(MAKE) copy-docs

908
README.md

File diff suppressed because it is too large Load Diff

View File

@@ -1,14 +0,0 @@
# Security Policy
## Supported Versions
| Version | Supported |
|---------|--------------------|
| [latest release](https://docs.victoriametrics.com/CHANGELOG.html) | :white_check_mark: |
| v1.87.x LTS release | :white_check_mark: |
| v1.79.x LTS release | :white_check_mark: |
| other releases | :x: |
## Reporting a Vulnerability
Please report any security issues to security@victoriametrics.com

View File

@@ -1,103 +0,0 @@
# All these commands must run from repository root.
victoria-logs:
APP_NAME=victoria-logs $(MAKE) app-local
victoria-logs-race:
APP_NAME=victoria-logs RACE=-race $(MAKE) app-local
victoria-logs-prod:
APP_NAME=victoria-logs $(MAKE) app-via-docker
victoria-logs-pure-prod:
APP_NAME=victoria-logs $(MAKE) app-via-docker-pure
victoria-logs-linux-amd64-prod:
APP_NAME=victoria-logs $(MAKE) app-via-docker-linux-amd64
victoria-logs-linux-arm-prod:
APP_NAME=victoria-logs $(MAKE) app-via-docker-linux-arm
victoria-logs-linux-arm64-prod:
APP_NAME=victoria-logs $(MAKE) app-via-docker-linux-arm64
victoria-logs-linux-ppc64le-prod:
APP_NAME=victoria-logs $(MAKE) app-via-docker-linux-ppc64le
victoria-logs-linux-386-prod:
APP_NAME=victoria-logs $(MAKE) app-via-docker-linux-386
victoria-logs-darwin-amd64-prod:
APP_NAME=victoria-logs $(MAKE) app-via-docker-darwin-amd64
victoria-logs-darwin-arm64-prod:
APP_NAME=victoria-logs $(MAKE) app-via-docker-darwin-arm64
victoria-logs-freebsd-amd64-prod:
APP_NAME=victoria-logs $(MAKE) app-via-docker-freebsd-amd64
victoria-logs-openbsd-amd64-prod:
APP_NAME=victoria-logs $(MAKE) app-via-docker-openbsd-amd64
victoria-logs-windows-amd64-prod:
APP_NAME=victoria-logs $(MAKE) app-via-docker-windows-amd64
package-victoria-logs:
APP_NAME=victoria-logs $(MAKE) package-via-docker
package-victoria-logs-pure:
APP_NAME=victoria-logs $(MAKE) package-via-docker-pure
package-victoria-logs-amd64:
APP_NAME=victoria-logs $(MAKE) package-via-docker-amd64
package-victoria-logs-arm:
APP_NAME=victoria-logs $(MAKE) package-via-docker-arm
package-victoria-logs-arm64:
APP_NAME=victoria-logs $(MAKE) package-via-docker-arm64
package-victoria-logs-ppc64le:
APP_NAME=victoria-logs $(MAKE) package-via-docker-ppc64le
package-victoria-logs-386:
APP_NAME=victoria-logs $(MAKE) package-via-docker-386
publish-victoria-logs:
APP_NAME=victoria-logs $(MAKE) publish-via-docker
victoria-logs-linux-amd64:
APP_NAME=victoria-logs CGO_ENABLED=1 GOOS=linux GOARCH=amd64 $(MAKE) app-local-goos-goarch
victoria-logs-linux-arm:
APP_NAME=victoria-logs CGO_ENABLED=0 GOOS=linux GOARCH=arm $(MAKE) app-local-goos-goarch
victoria-logs-linux-arm64:
APP_NAME=victoria-logs CGO_ENABLED=0 GOOS=linux GOARCH=arm64 $(MAKE) app-local-goos-goarch
victoria-logs-linux-ppc64le:
APP_NAME=victoria-logs CGO_ENABLED=0 GOOS=linux GOARCH=ppc64le $(MAKE) app-local-goos-goarch
victoria-logs-linux-s390x:
APP_NAME=victoria-logs CGO_ENABLED=0 GOOS=linux GOARCH=s390x $(MAKE) app-local-goos-goarch
victoria-logs-linux-386:
APP_NAME=victoria-logs CGO_ENABLED=0 GOOS=linux GOARCH=386 $(MAKE) app-local-goos-goarch
victoria-logs-darwin-amd64:
APP_NAME=victoria-logs CGO_ENABLED=0 GOOS=darwin GOARCH=amd64 $(MAKE) app-local-goos-goarch
victoria-logs-darwin-arm64:
APP_NAME=victoria-logs CGO_ENABLED=0 GOOS=darwin GOARCH=arm64 $(MAKE) app-local-goos-goarch
victoria-logs-freebsd-amd64:
APP_NAME=victoria-logs CGO_ENABLED=0 GOOS=freebsd GOARCH=amd64 $(MAKE) app-local-goos-goarch
victoria-logs-openbsd-amd64:
APP_NAME=victoria-logs CGO_ENABLED=0 GOOS=openbsd GOARCH=amd64 $(MAKE) app-local-goos-goarch
victoria-logs-windows-amd64:
GOARCH=amd64 APP_NAME=victoria-logs $(MAKE) app-local-windows-goarch
victoria-logs-pure:
APP_NAME=victoria-logs $(MAKE) app-local-pure

View File

@@ -1,8 +0,0 @@
ARG base_image
FROM $base_image
EXPOSE 8428
ENTRYPOINT ["/victoria-logs-prod"]
ARG src_binary
COPY $src_binary ./victoria-logs-prod

View File

@@ -1,103 +0,0 @@
package main
import (
"flag"
"fmt"
"net/http"
"os"
"time"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vlinsert"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vlselect"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vlstorage"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/buildinfo"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/cgroup"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/envflag"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/fs"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/procutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/pushmetrics"
)
var (
httpListenAddr = flag.String("httpListenAddr", ":9428", "TCP address to listen for http connections. See also -httpListenAddr.useProxyProtocol")
useProxyProtocol = flag.Bool("httpListenAddr.useProxyProtocol", false, "Whether to use proxy protocol for connections accepted at -httpListenAddr . "+
"See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt . "+
"With enabled proxy protocol http server cannot serve regular /metrics endpoint. Use -pushmetrics.url for metrics pushing")
gogc = flag.Int("gogc", 100, "GOGC to use. See https://tip.golang.org/doc/gc-guide")
)
func main() {
// Write flags and help message to stdout, since it is easier to grep or pipe.
flag.CommandLine.SetOutput(os.Stdout)
flag.Usage = usage
envflag.Parse()
cgroup.SetGOGC(*gogc)
buildinfo.Init()
logger.Init()
pushmetrics.Init()
logger.Infof("starting VictoriaLogs at %q...", *httpListenAddr)
startTime := time.Now()
vlstorage.Init()
vlselect.Init()
vlinsert.Init()
go httpserver.Serve(*httpListenAddr, *useProxyProtocol, requestHandler)
logger.Infof("started VictoriaLogs in %.3f seconds; see https://docs.victoriametrics.com/VictoriaLogs/", time.Since(startTime).Seconds())
sig := procutil.WaitForSigterm()
logger.Infof("received signal %s", sig)
logger.Infof("gracefully shutting down webservice at %q", *httpListenAddr)
startTime = time.Now()
if err := httpserver.Stop(*httpListenAddr); err != nil {
logger.Fatalf("cannot stop the webservice: %s", err)
}
logger.Infof("successfully shut down the webservice in %.3f seconds", time.Since(startTime).Seconds())
vlinsert.Stop()
vlselect.Stop()
vlstorage.Stop()
fs.MustStopDirRemover()
logger.Infof("the VictoriaLogs has been stopped in %.3f seconds", time.Since(startTime).Seconds())
}
func requestHandler(w http.ResponseWriter, r *http.Request) bool {
if r.URL.Path == "/" {
if r.Method != http.MethodGet {
return false
}
w.Header().Add("Content-Type", "text/html; charset=utf-8")
fmt.Fprintf(w, "<h2>Single-node VictoriaLogs</h2></br>")
fmt.Fprintf(w, "See docs at <a href='https://docs.victoriametrics.com/VictoriaLogs/'>https://docs.victoriametrics.com/VictoriaLogs/</a></br>")
fmt.Fprintf(w, "Useful endpoints:</br>")
httpserver.WriteAPIHelp(w, [][2]string{
{"select/vmui", "Web UI for VictoriaLogs"},
{"metrics", "available service metrics"},
{"flags", "command-line flags"},
})
return true
}
if vlinsert.RequestHandler(w, r) {
return true
}
if vlselect.RequestHandler(w, r) {
return true
}
return false
}
func usage() {
const s = `
victoria-logs is a log management and analytics service.
See the docs at https://docs.victoriametrics.com/VictoriaLogs/
`
flagutil.Usage(s)
}

View File

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

View File

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

View File

@@ -8,8 +8,6 @@ import (
"time"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vminsert"
vminsertcommon "github.com/VictoriaMetrics/VictoriaMetrics/app/vminsert/common"
vminsertrelabel "github.com/VictoriaMetrics/VictoriaMetrics/app/vminsert/relabel"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmselect"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmselect/promql"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmstorage"
@@ -26,19 +24,11 @@ import (
)
var (
httpListenAddr = flag.String("httpListenAddr", ":8428", "TCP address to listen for http connections. See also -httpListenAddr.useProxyProtocol")
useProxyProtocol = flag.Bool("httpListenAddr.useProxyProtocol", false, "Whether to use proxy protocol for connections accepted at -httpListenAddr . "+
"See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt . "+
"With enabled proxy protocol http server cannot serve regular /metrics endpoint. Use -pushmetrics.url for metrics pushing")
httpListenAddr = flag.String("httpListenAddr", ":8428", "TCP address to listen for http connections")
minScrapeInterval = flag.Duration("dedup.minScrapeInterval", 0, "Leave only the last sample in every time series per each discrete interval "+
"equal to -dedup.minScrapeInterval > 0. See https://docs.victoriametrics.com/#deduplication and https://docs.victoriametrics.com/#downsampling")
dryRun = flag.Bool("dryRun", false, "Whether to check config files without running VictoriaMetrics. The following config files are checked: "+
"-promscrape.config, -relabelConfig and -streamAggr.config. Unknown config entries aren't allowed in -promscrape.config by default. "+
"This can be changed with -promscrape.config.strictParse=false command-line flag")
inmemoryDataFlushInterval = flag.Duration("inmemoryDataFlushInterval", 5*time.Second, "The interval for guaranteed saving of in-memory data to disk. "+
"The saved data survives unclean shutdowns such as OOM crash, hardware reset, SIGKILL, etc. "+
"Bigger intervals may help increase the lifetime of flash storage with limited write cycles (e.g. Raspberry PI). "+
"Smaller intervals increase disk IO load. Minimum supported value is 1s")
dryRun = flag.Bool("dryRun", false, "Whether to check only -promscrape.config and then exit. "+
"Unknown config entries aren't allowed in -promscrape.config by default. This can be changed with -promscrape.config.strictParse=false command-line flag")
)
func main() {
@@ -57,26 +47,19 @@ func main() {
if err := promscrape.CheckConfig(); err != nil {
logger.Fatalf("error when checking -promscrape.config: %s", err)
}
if err := vminsertrelabel.CheckRelabelConfig(); err != nil {
logger.Fatalf("error when checking -relabelConfig: %s", err)
}
if err := vminsertcommon.CheckStreamAggrConfig(); err != nil {
logger.Fatalf("error when checking -streamAggr.config: %s", err)
}
logger.Infof("-promscrape.config is ok; exiting with 0 status code")
logger.Infof("-promscrape.config is ok; exitting with 0 status code")
return
}
logger.Infof("starting VictoriaMetrics at %q...", *httpListenAddr)
startTime := time.Now()
storage.SetDedupInterval(*minScrapeInterval)
storage.SetDataFlushInterval(*inmemoryDataFlushInterval)
vmstorage.Init(promql.ResetRollupResultCacheIfNeeded)
vmselect.Init()
vminsert.Init()
startSelfScraper()
go httpserver.Serve(*httpListenAddr, *useProxyProtocol, requestHandler)
go httpserver.Serve(*httpListenAddr, requestHandler)
logger.Infof("started VictoriaMetrics in %.3f seconds", time.Since(startTime).Seconds())
sig := procutil.WaitForSigterm()
@@ -102,7 +85,7 @@ func main() {
func requestHandler(w http.ResponseWriter, r *http.Request) bool {
if r.URL.Path == "/" {
if r.Method != http.MethodGet {
if r.Method != "GET" {
return false
}
w.Header().Add("Content-Type", "text/html; charset=utf-8")
@@ -113,8 +96,6 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
{"vmui", "Web UI"},
{"targets", "status for discovered active targets"},
{"service-discovery", "labels before and after relabeling for discovered targets"},
{"metric-relabel-debug", "debug metric relabeling"},
{"expand-with-exprs", "WITH expressions' tutorial"},
{"api/v1/targets", "advanced information about discovered targets in JSON format"},
{"config", "-promscrape.config contents"},
{"metrics", "available service metrics"},

View File

@@ -129,16 +129,16 @@ func setUp() {
storagePath = filepath.Join(os.TempDir(), testStorageSuffix)
processFlags()
logger.Init()
vmstorage.Init(promql.ResetRollupResultCacheIfNeeded)
vmstorage.InitWithoutMetrics(promql.ResetRollupResultCacheIfNeeded)
vmselect.Init()
vminsert.Init()
go httpserver.Serve(*httpListenAddr, false, requestHandler)
go httpserver.Serve(*httpListenAddr, requestHandler)
readyStorageCheckFunc := func() bool {
resp, err := http.Get(testHealthHTTPPath)
if err != nil {
return false
}
_ = resp.Body.Close()
resp.Body.Close()
return resp.StatusCode == 200
}
if err := waitFor(testStorageInitTimeout, readyStorageCheckFunc); err != nil {
@@ -189,8 +189,10 @@ func tearDown() {
func TestWriteRead(t *testing.T) {
t.Run("write", testWrite)
vmstorage.Storage.DebugFlush()
time.Sleep(1 * time.Second)
vmstorage.Stop()
// open storage after stop in write
vmstorage.InitWithoutMetrics(promql.ResetRollupResultCacheIfNeeded)
t.Run("read", testRead)
}
@@ -259,7 +261,7 @@ func testRead(t *testing.T) {
for _, q := range test.Query {
q = testutil.PopulateTimeTplString(q, insertionTime)
if test.Issue != "" {
test.Issue = "\nRegression in " + test.Issue
test.Issue = "Regression in " + test.Issue
}
switch true {
case strings.HasPrefix(q, "/api/v1/export"):
@@ -282,7 +284,7 @@ func testRead(t *testing.T) {
queryResult := Query{}
httpReadStruct(t, testReadHTTPPath, q, &queryResult)
if err := checkQueryResult(queryResult, test.ResultQuery); err != nil {
t.Fatalf("Query. %s fails with error: %s.%s", q, err, test.Issue)
t.Fatalf("Query. %s fails with error %s.%s", q, err, test.Issue)
}
default:
t.Fatalf("unsupported read query %s", q)
@@ -335,9 +337,7 @@ func tcpWrite(t *testing.T, address string, data string) {
s := newSuite(t)
conn, err := net.Dial("tcp", address)
s.noError(err)
defer func() {
_ = conn.Close()
}()
defer conn.Close()
n, err := conn.Write([]byte(data))
s.noError(err)
s.equalInt(n, len(data))
@@ -348,9 +348,7 @@ func httpReadMetrics(t *testing.T, address, query string) []Metric {
s := newSuite(t)
resp, err := http.Get(address + query)
s.noError(err)
defer func() {
_ = resp.Body.Close()
}()
defer resp.Body.Close()
s.equalInt(resp.StatusCode, 200)
var rows []Metric
for dec := json.NewDecoder(resp.Body); dec.More(); {
@@ -365,9 +363,7 @@ func httpReadStruct(t *testing.T, address, query string, dst interface{}) {
s := newSuite(t)
resp, err := http.Get(address + query)
s.noError(err)
defer func() {
_ = resp.Body.Close()
}()
defer resp.Body.Close()
s.equalInt(resp.StatusCode, 200)
s.noError(json.NewDecoder(resp.Body).Decode(dst))
}

View File

@@ -2,7 +2,7 @@
ARG certs_image
ARG root_image
FROM $certs_image as certs
RUN apk update && apk upgrade && apk --update --no-cache add ca-certificates
RUN apk --update --no-cache add ca-certificates
FROM $root_image
COPY --from=certs /etc/ssl/certs/ca-certificates.crt /etc/ssl/certs/ca-certificates.crt

View File

@@ -85,9 +85,7 @@ func selfScraper(scrapeInterval time.Duration) {
mr.Timestamp = currentTimestamp
mr.Value = r.Value
}
if err := vmstorage.AddRows(mrs); err != nil {
logger.Errorf("cannot store self-scraped metrics: %s", err)
}
vmstorage.AddRows(mrs)
}
}

View File

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

View File

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

View File

@@ -1,20 +0,0 @@
{% stripspace %}
{% func BulkResponse(n int, tookMs int64) %}
{
"took":{%dl tookMs %},
"errors":false,
"items":[
{% for i := 0; i < n; i++ %}
{
"create":{
"status":201
}
}
{% if i+1 < n %},{% endif %}
{% endfor %}
]
}
{% endfunc %}
{% endstripspace %}

View File

@@ -1,69 +0,0 @@
// Code generated by qtc from "bulk_response.qtpl". DO NOT EDIT.
// See https://github.com/valyala/quicktemplate for details.
//line app/vlinsert/elasticsearch/bulk_response.qtpl:3
package elasticsearch
//line app/vlinsert/elasticsearch/bulk_response.qtpl:3
import (
qtio422016 "io"
qt422016 "github.com/valyala/quicktemplate"
)
//line app/vlinsert/elasticsearch/bulk_response.qtpl:3
var (
_ = qtio422016.Copy
_ = qt422016.AcquireByteBuffer
)
//line app/vlinsert/elasticsearch/bulk_response.qtpl:3
func StreamBulkResponse(qw422016 *qt422016.Writer, n int, tookMs int64) {
//line app/vlinsert/elasticsearch/bulk_response.qtpl:3
qw422016.N().S(`{"took":`)
//line app/vlinsert/elasticsearch/bulk_response.qtpl:5
qw422016.N().DL(tookMs)
//line app/vlinsert/elasticsearch/bulk_response.qtpl:5
qw422016.N().S(`,"errors":false,"items":[`)
//line app/vlinsert/elasticsearch/bulk_response.qtpl:8
for i := 0; i < n; i++ {
//line app/vlinsert/elasticsearch/bulk_response.qtpl:8
qw422016.N().S(`{"create":{"status":201}}`)
//line app/vlinsert/elasticsearch/bulk_response.qtpl:14
if i+1 < n {
//line app/vlinsert/elasticsearch/bulk_response.qtpl:14
qw422016.N().S(`,`)
//line app/vlinsert/elasticsearch/bulk_response.qtpl:14
}
//line app/vlinsert/elasticsearch/bulk_response.qtpl:15
}
//line app/vlinsert/elasticsearch/bulk_response.qtpl:15
qw422016.N().S(`]}`)
//line app/vlinsert/elasticsearch/bulk_response.qtpl:18
}
//line app/vlinsert/elasticsearch/bulk_response.qtpl:18
func WriteBulkResponse(qq422016 qtio422016.Writer, n int, tookMs int64) {
//line app/vlinsert/elasticsearch/bulk_response.qtpl:18
qw422016 := qt422016.AcquireWriter(qq422016)
//line app/vlinsert/elasticsearch/bulk_response.qtpl:18
StreamBulkResponse(qw422016, n, tookMs)
//line app/vlinsert/elasticsearch/bulk_response.qtpl:18
qt422016.ReleaseWriter(qw422016)
//line app/vlinsert/elasticsearch/bulk_response.qtpl:18
}
//line app/vlinsert/elasticsearch/bulk_response.qtpl:18
func BulkResponse(n int, tookMs int64) string {
//line app/vlinsert/elasticsearch/bulk_response.qtpl:18
qb422016 := qt422016.AcquireByteBuffer()
//line app/vlinsert/elasticsearch/bulk_response.qtpl:18
WriteBulkResponse(qb422016, n, tookMs)
//line app/vlinsert/elasticsearch/bulk_response.qtpl:18
qs422016 := string(qb422016.B)
//line app/vlinsert/elasticsearch/bulk_response.qtpl:18
qt422016.ReleaseByteBuffer(qb422016)
//line app/vlinsert/elasticsearch/bulk_response.qtpl:18
return qs422016
//line app/vlinsert/elasticsearch/bulk_response.qtpl:18
}

View File

@@ -1,264 +0,0 @@
package elasticsearch
import (
"bufio"
"errors"
"fmt"
"io"
"math"
"net/http"
"strconv"
"strings"
"time"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vlinsert/insertutils"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vlstorage"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/bufferedwriter"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logjson"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
"github.com/VictoriaMetrics/metrics"
)
// RequestHandler processes Elasticsearch insert requests
func RequestHandler(path string, w http.ResponseWriter, r *http.Request) bool {
w.Header().Add("Content-Type", "application/json")
// This header is needed for Logstash
w.Header().Set("X-Elastic-Product", "Elasticsearch")
if strings.HasPrefix(path, "/_ilm/policy") {
// Return fake response for Elasticsearch ilm request.
fmt.Fprintf(w, `{}`)
return true
}
if strings.HasPrefix(path, "/_index_template") {
// Return fake response for Elasticsearch index template request.
fmt.Fprintf(w, `{}`)
return true
}
if strings.HasPrefix(path, "/_ingest") {
// Return fake response for Elasticsearch ingest pipeline request.
// See: https://www.elastic.co/guide/en/elasticsearch/reference/8.8/put-pipeline-api.html
fmt.Fprintf(w, `{}`)
return true
}
if strings.HasPrefix(path, "/_nodes") {
// Return fake response for Elasticsearch nodes discovery request.
// See: https://www.elastic.co/guide/en/elasticsearch/reference/8.8/cluster.html
fmt.Fprintf(w, `{}`)
return true
}
switch path {
case "/":
switch r.Method {
case http.MethodGet:
// Return fake response for Elasticsearch ping request.
// See the latest available version for Elasticsearch at https://github.com/elastic/elasticsearch/releases
fmt.Fprintf(w, `{
"version": {
"number": "8.8.0"
}
}`)
case http.MethodHead:
// Return empty response for Logstash ping request.
}
return true
case "/_license":
// Return fake response for Elasticsearch license request.
fmt.Fprintf(w, `{
"license": {
"uid": "cbff45e7-c553-41f7-ae4f-9205eabd80xx",
"type": "oss",
"status": "active",
"expiry_date_in_millis" : 4000000000000
}
}`)
return true
case "/_bulk":
startTime := time.Now()
bulkRequestsTotal.Inc()
cp, err := insertutils.GetCommonParams(r)
if err != nil {
httpserver.Errorf(w, r, "%s", err)
return true
}
lr := logstorage.GetLogRows(cp.StreamFields, cp.IgnoreFields)
processLogMessage := cp.GetProcessLogMessageFunc(lr)
isGzip := r.Header.Get("Content-Encoding") == "gzip"
n, err := readBulkRequest(r.Body, isGzip, cp.TimeField, cp.MsgField, processLogMessage)
if err != nil {
logger.Warnf("cannot decode log message #%d in /_bulk request: %s", n, err)
return true
}
vlstorage.MustAddRows(lr)
logstorage.PutLogRows(lr)
tookMs := time.Since(startTime).Milliseconds()
bw := bufferedwriter.Get(w)
defer bufferedwriter.Put(bw)
WriteBulkResponse(bw, n, tookMs)
_ = bw.Flush()
return true
default:
return false
}
}
var (
bulkRequestsTotal = metrics.NewCounter(`vl_http_requests_total{path="/insert/elasticsearch/_bulk"}`)
)
func readBulkRequest(r io.Reader, isGzip bool, timeField, msgField string,
processLogMessage func(timestamp int64, fields []logstorage.Field),
) (int, error) {
// See https://www.elastic.co/guide/en/elasticsearch/reference/current/docs-bulk.html
if isGzip {
zr, err := common.GetGzipReader(r)
if err != nil {
return 0, fmt.Errorf("cannot read gzipped _bulk request: %w", err)
}
defer common.PutGzipReader(zr)
r = zr
}
wcr := writeconcurrencylimiter.GetReader(r)
defer writeconcurrencylimiter.PutReader(wcr)
lb := lineBufferPool.Get()
defer lineBufferPool.Put(lb)
lb.B = bytesutil.ResizeNoCopyNoOverallocate(lb.B, insertutils.MaxLineSizeBytes.IntN())
sc := bufio.NewScanner(wcr)
sc.Buffer(lb.B, len(lb.B))
n := 0
nCheckpoint := 0
for {
ok, err := readBulkLine(sc, timeField, msgField, processLogMessage)
wcr.DecConcurrency()
if err != nil || !ok {
rowsIngestedTotal.Add(n - nCheckpoint)
return n, err
}
n++
if batchSize := n - nCheckpoint; n >= 1000 {
rowsIngestedTotal.Add(batchSize)
nCheckpoint = n
}
}
}
var lineBufferPool bytesutil.ByteBufferPool
var rowsIngestedTotal = metrics.NewCounter(`vl_rows_ingested_total{type="elasticsearch_bulk"}`)
func readBulkLine(sc *bufio.Scanner, timeField, msgField string,
processLogMessage func(timestamp int64, fields []logstorage.Field),
) (bool, error) {
var line []byte
// Read the command, must be "create" or "index"
for len(line) == 0 {
if !sc.Scan() {
if err := sc.Err(); err != nil {
if errors.Is(err, bufio.ErrTooLong) {
return false, fmt.Errorf(`cannot read "create" or "index" command, since its size exceeds -insert.maxLineSizeBytes=%d`,
insertutils.MaxLineSizeBytes.IntN())
}
return false, err
}
return false, nil
}
line = sc.Bytes()
}
lineStr := bytesutil.ToUnsafeString(line)
if !strings.Contains(lineStr, `"create"`) && !strings.Contains(lineStr, `"index"`) {
return false, fmt.Errorf(`unexpected command %q; expecting "create" or "index"`, line)
}
// Decode log message
if !sc.Scan() {
if err := sc.Err(); err != nil {
if errors.Is(err, bufio.ErrTooLong) {
return false, fmt.Errorf("cannot read log message, since its size exceeds -insert.maxLineSizeBytes=%d", insertutils.MaxLineSizeBytes.IntN())
}
return false, err
}
return false, fmt.Errorf(`missing log message after the "create" or "index" command`)
}
line = sc.Bytes()
p := logjson.GetParser()
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)
if err != nil {
return false, fmt.Errorf("cannot parse timestamp: %w", err)
}
if ts == 0 {
ts = time.Now().UnixNano()
}
p.RenameField(msgField, "_msg")
processLogMessage(ts, p.Fields)
logjson.PutParser(p)
return true, nil
}
func extractTimestampFromFields(timeField string, fields []logstorage.Field) (int64, error) {
for i := range fields {
f := &fields[i]
if f.Name != timeField {
continue
}
timestamp, err := parseElasticsearchTimestamp(f.Value)
if err != nil {
return 0, err
}
f.Value = ""
return timestamp, nil
}
return 0, nil
}
func parseElasticsearchTimestamp(s string) (int64, error) {
if s == "0" || s == "" {
// Special case - zero or empty timestamp must be substituted
// with the current time by the caller.
return 0, nil
}
if len(s) < len("YYYY-MM-DD") || s[len("YYYY")] != '-' {
// Try parsing timestamp in milliseconds
n, err := strconv.ParseInt(s, 10, 64)
if err != nil {
return 0, fmt.Errorf("cannot parse timestamp in milliseconds from %q: %w", s, err)
}
if n > int64(math.MaxInt64)/1e6 {
return 0, fmt.Errorf("too big timestamp in milliseconds: %d; mustn't exceed %d", n, int64(math.MaxInt64)/1e6)
}
if n < int64(math.MinInt64)/1e6 {
return 0, fmt.Errorf("too small timestamp in milliseconds: %d; must be bigger than %d", n, int64(math.MinInt64)/1e6)
}
n *= 1e6
return n, nil
}
if len(s) == len("YYYY-MM-DD") {
t, err := time.Parse("2006-01-02", s)
if err != nil {
return 0, fmt.Errorf("cannot parse date %q: %w", s, err)
}
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)
}
return t.UnixNano(), nil
}

View File

@@ -1,129 +0,0 @@
package elasticsearch
import (
"bytes"
"compress/gzip"
"fmt"
"reflect"
"strings"
"testing"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
)
func TestReadBulkRequestFailure(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)
}
r := bytes.NewBufferString(data)
rows, err := readBulkRequest(r, false, "_time", "_msg", processLogMessage)
if err == nil {
t.Fatalf("expecting non-empty error")
}
if rows != 0 {
t.Fatalf("unexpected non-zero rows=%d", rows)
}
}
f("foobar")
f(`{}`)
f(`{"create":{}}`)
f(`{"creat":{}}
{}`)
f(`{"create":{}}
foobar`)
}
func TestReadBulkRequestSuccess(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
r := bytes.NewBufferString(data)
rows, err := readBulkRequest(r, false, timeField, msgField, processLogMessage)
if err != nil {
t.Fatalf("unexpected error: %s", err)
}
if rows != rowsExpected {
t.Fatalf("unexpected rows read; got %d; want %d", rows, rowsExpected)
}
if !reflect.DeepEqual(timestamps, timestampsExpected) {
t.Fatalf("unexpected timestamps;\ngot\n%d\nwant\n%d", timestamps, timestampsExpected)
}
if result != resultExpected {
t.Fatalf("unexpected result;\ngot\n%s\nwant\n%s", result, resultExpected)
}
// Read the request with compression
timestamps = nil
result = ""
compressedData := compressData(data)
r = bytes.NewBufferString(compressedData)
rows, err = readBulkRequest(r, true, timeField, msgField, processLogMessage)
if err != nil {
t.Fatalf("unexpected error: %s", err)
}
if rows != rowsExpected {
t.Fatalf("unexpected rows read; got %d; want %d", rows, rowsExpected)
}
if !reflect.DeepEqual(timestamps, timestampsExpected) {
t.Fatalf("unexpected timestamps;\ngot\n%d\nwant\n%d", timestamps, timestampsExpected)
}
if result != resultExpected {
t.Fatalf("unexpected result;\ngot\n%s\nwant\n%s", result, resultExpected)
}
}
// Verify an empty data
f("", "_time", "_msg", 0, nil, "")
f("\n", "_time", "_msg", 0, nil, "")
f("\n\n", "_time", "_msg", 0, nil, "")
// Verify non-empty data
data := `{"create":{"_index":"filebeat-8.8.0"}}
{"@timestamp":"2023-06-06T04:48:11.735Z","log":{"offset":71770,"file":{"path":"/var/log/auth.log"}},"message":"foobar"}
{"create":{"_index":"filebeat-8.8.0"}}
{"@timestamp":"2023-06-06T04:48:12.735Z","message":"baz"}
{"index":{"_index":"filebeat-8.8.0"}}
{"message":"xyz","@timestamp":"2023-06-06T04:48:13.735Z","x":"y"}
`
timeField := "@timestamp"
msgField := "message"
rowsExpected := 3
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"}
`
f(data, timeField, msgField, rowsExpected, timestampsExpected, resultExpected)
}
func compressData(s string) string {
var bb bytes.Buffer
zw := gzip.NewWriter(&bb)
if _, err := zw.Write([]byte(s)); err != nil {
panic(fmt.Errorf("unexpected error when compressing data: %s", err))
}
if err := zw.Close(); err != nil {
panic(fmt.Errorf("unexpected error when closing gzip writer: %s", err))
}
return bb.String()
}

View File

@@ -1,50 +0,0 @@
package elasticsearch
import (
"bytes"
"fmt"
"testing"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
)
func BenchmarkReadBulkRequest(b *testing.B) {
b.Run("gzip:off", func(b *testing.B) {
benchmarkReadBulkRequest(b, false)
})
b.Run("gzip:on", func(b *testing.B) {
benchmarkReadBulkRequest(b, true)
})
}
func benchmarkReadBulkRequest(b *testing.B, isGzip bool) {
data := `{"create":{"_index":"filebeat-8.8.0"}}
{"@timestamp":"2023-06-06T04:48:11.735Z","log":{"offset":71770,"file":{"path":"/var/log/auth.log"}},"message":"foobar"}
{"create":{"_index":"filebeat-8.8.0"}}
{"@timestamp":"2023-06-06T04:48:12.735Z","message":"baz"}
{"create":{"_index":"filebeat-8.8.0"}}
{"message":"xyz","@timestamp":"2023-06-06T04:48:13.735Z","x":"y"}
`
if isGzip {
data = compressData(data)
}
dataBytes := bytesutil.ToUnsafeBytes(data)
timeField := "@timestamp"
msgField := "message"
processLogMessage := func(timestmap int64, fields []logstorage.Field) {}
b.ReportAllocs()
b.SetBytes(int64(len(data)))
b.RunParallel(func(pb *testing.PB) {
r := &bytes.Reader{}
for pb.Next() {
r.Reset(dataBytes)
_, err := readBulkRequest(r, isGzip, timeField, msgField, processLogMessage)
if err != nil {
panic(fmt.Errorf("unexpected error: %s", err))
}
}
})
}

View File

@@ -1,91 +0,0 @@
package insertutils
import (
"net/http"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vlstorage"
"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/metrics"
)
// CommonParams contains common HTTP parameters used by log ingestion APIs.
//
// See https://docs.victoriametrics.com/VictoriaLogs/data-ingestion/#http-parameters
type CommonParams struct {
TenantID logstorage.TenantID
TimeField string
MsgField string
StreamFields []string
IgnoreFields []string
Debug bool
DebugRequestURI string
DebugRemoteAddr string
}
// GetCommonParams returns CommonParams from r.
func GetCommonParams(r *http.Request) (*CommonParams, error) {
// Extract tenantID
tenantID, err := logstorage.GetTenantIDFromRequest(r)
if err != nil {
return nil, err
}
// Extract time field name from _time_field query arg
var timeField = "_time"
if tf := r.FormValue("_time_field"); tf != "" {
timeField = tf
}
// Extract message field name from _msg_field query arg
var msgField = ""
if msgf := r.FormValue("_msg_field"); msgf != "" {
msgField = msgf
}
streamFields := httputils.GetArray(r, "_stream_fields")
ignoreFields := httputils.GetArray(r, "ignore_fields")
debug := httputils.GetBool(r, "debug")
debugRequestURI := ""
debugRemoteAddr := ""
if debug {
debugRequestURI = httpserver.GetRequestURI(r)
debugRemoteAddr = httpserver.GetQuotedRemoteAddr(r)
}
cp := &CommonParams{
TenantID: tenantID,
TimeField: timeField,
MsgField: msgField,
StreamFields: streamFields,
IgnoreFields: ignoreFields,
Debug: debug,
DebugRequestURI: debugRequestURI,
DebugRemoteAddr: debugRemoteAddr,
}
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) {
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)
rowsDroppedTotal.Inc()
return
}
if lr.NeedFlush() {
vlstorage.MustAddRows(lr)
lr.ResetKeepSettings()
}
}
}
var rowsDroppedTotal = metrics.NewCounter(`vl_rows_dropped_total{reason="debug"}`)

View File

@@ -1,10 +0,0 @@
package insertutils
import (
"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
)
var (
// MaxLineSizeBytes is the maximum length of a single line for /insert/* handlers
MaxLineSizeBytes = flagutil.NewBytes("insert.maxLineSizeBytes", 256*1024, "The maximum size of a single line, which can be read by /insert/* handlers")
)

View File

@@ -1,149 +0,0 @@
package jsonline
import (
"bufio"
"errors"
"fmt"
"net/http"
"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"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logjson"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
"github.com/VictoriaMetrics/metrics"
)
// RequestHandler processes jsonline insert requests
func RequestHandler(w http.ResponseWriter, r *http.Request) bool {
w.Header().Add("Content-Type", "application/json")
if r.Method != "POST" {
w.WriteHeader(http.StatusMethodNotAllowed)
return true
}
requestsTotal.Inc()
cp, err := insertutils.GetCommonParams(r)
if err != nil {
httpserver.Errorf(w, r, "%s", err)
return true
}
lr := logstorage.GetLogRows(cp.StreamFields, cp.IgnoreFields)
processLogMessage := cp.GetProcessLogMessageFunc(lr)
reader := r.Body
if r.Header.Get("Content-Encoding") == "gzip" {
zr, err := common.GetGzipReader(reader)
if err != nil {
logger.Errorf("cannot read gzipped _bulk request: %s", err)
return true
}
defer common.PutGzipReader(zr)
reader = zr
}
wcr := writeconcurrencylimiter.GetReader(reader)
defer writeconcurrencylimiter.PutReader(wcr)
lb := lineBufferPool.Get()
defer lineBufferPool.Put(lb)
lb.B = bytesutil.ResizeNoCopyNoOverallocate(lb.B, insertutils.MaxLineSizeBytes.IntN())
sc := bufio.NewScanner(wcr)
sc.Buffer(lb.B, len(lb.B))
n := 0
for {
ok, err := readLine(sc, cp.TimeField, cp.MsgField, processLogMessage)
wcr.DecConcurrency()
if err != nil {
logger.Errorf("cannot read line #%d in /jsonline request: %s", n, err)
break
}
if !ok {
break
}
n++
rowsIngestedTotal.Inc()
}
vlstorage.MustAddRows(lr)
logstorage.PutLogRows(lr)
return true
}
func readLine(sc *bufio.Scanner, timeField, msgField string, processLogMessage func(timestamp int64, fields []logstorage.Field)) (bool, error) {
var line []byte
for len(line) == 0 {
if !sc.Scan() {
if err := sc.Err(); err != nil {
if errors.Is(err, bufio.ErrTooLong) {
return false, fmt.Errorf(`cannot read json line, since its size exceeds -insert.maxLineSizeBytes=%d`, insertutils.MaxLineSizeBytes.IntN())
}
return false, err
}
return false, nil
}
line = sc.Bytes()
}
p := logjson.GetParser()
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)
if err != nil {
return false, fmt.Errorf("cannot parse timestamp: %w", err)
}
if ts == 0 {
ts = time.Now().UnixNano()
}
p.RenameField(msgField, "_msg")
processLogMessage(ts, p.Fields)
logjson.PutParser(p)
return true, nil
}
func extractTimestampFromFields(timeField string, fields []logstorage.Field) (int64, error) {
for i := range fields {
f := &fields[i]
if f.Name != timeField {
continue
}
timestamp, err := parseISO8601Timestamp(f.Value)
if err != nil {
return 0, err
}
f.Value = ""
return timestamp, nil
}
return 0, nil
}
func parseISO8601Timestamp(s string) (int64, error) {
if s == "0" || s == "" {
// Special case for returning the current timestamp.
// It must be automatically converted to the current timestamp by the caller.
return 0, nil
}
t, err := time.Parse(time.RFC3339, s)
if err != nil {
return 0, fmt.Errorf("cannot parse timestamp %q: %w", s, err)
}
return t.UnixNano(), nil
}
var lineBufferPool bytesutil.ByteBufferPool
var (
requestsTotal = metrics.NewCounter(`vl_http_requests_total{path="/insert/jsonline"}`)
rowsIngestedTotal = metrics.NewCounter(`vl_rows_ingested_total{type="jsonline"}`)
)

View File

@@ -1,70 +0,0 @@
package jsonline
import (
"bufio"
"bytes"
"fmt"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
"reflect"
"strings"
"testing"
)
func TestReadBulkRequestSuccess(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
r := bytes.NewBufferString(data)
sc := bufio.NewScanner(r)
rows := 0
for {
ok, err := readLine(sc, timeField, msgField, processLogMessage)
if err != nil {
t.Fatalf("unexpected error: %s", err)
}
if !ok {
break
}
rows++
}
if rows != rowsExpected {
t.Fatalf("unexpected rows read; got %d; want %d", rows, rowsExpected)
}
if !reflect.DeepEqual(timestamps, timestampsExpected) {
t.Fatalf("unexpected timestamps;\ngot\n%d\nwant\n%d", timestamps, timestampsExpected)
}
if result != resultExpected {
t.Fatalf("unexpected result;\ngot\n%s\nwant\n%s", result, resultExpected)
}
}
// Verify non-empty data
data := `{"@timestamp":"2023-06-06T04:48:11.735Z","log":{"offset":71770,"file":{"path":"/var/log/auth.log"}},"message":"foobar"}
{"@timestamp":"2023-06-06T04:48:12.735Z","message":"baz"}
{"message":"xyz","@timestamp":"2023-06-06T04:48:13.735Z","x":"y"}
`
timeField := "@timestamp"
msgField := "message"
rowsExpected := 3
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"}
`
f(data, timeField, msgField, rowsExpected, timestampsExpected, resultExpected)
}

View File

@@ -1,56 +0,0 @@
package loki
import (
"net/http"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vlinsert/insertutils"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
"github.com/VictoriaMetrics/metrics"
)
var (
lokiRequestsJSONTotal = metrics.NewCounter(`vl_http_requests_total{path="/insert/loki/api/v1/push",format="json"}`)
lokiRequestsProtobufTotal = metrics.NewCounter(`vl_http_requests_total{path="/insert/loki/api/v1/push",format="protobuf"}`)
)
// RequestHandler processes Loki insert requests
//
// See https://grafana.com/docs/loki/latest/api/#push-log-entries-to-loki
func RequestHandler(path string, w http.ResponseWriter, r *http.Request) bool {
if path != "/api/v1/push" {
return false
}
contentType := r.Header.Get("Content-Type")
switch contentType {
case "application/json":
lokiRequestsJSONTotal.Inc()
return handleJSON(r, w)
default:
// Protobuf request body should be handled by default accoring to https://grafana.com/docs/loki/latest/api/#push-log-entries-to-loki
lokiRequestsProtobufTotal.Inc()
return handleProtobuf(r, w)
}
}
func getCommonParams(r *http.Request) (*insertutils.CommonParams, error) {
cp, err := insertutils.GetCommonParams(r)
if err != nil {
return nil, err
}
// If parsed tenant is (0,0) it is likely to be default tenant
// Try parsing tenant from Loki headers
if cp.TenantID.AccountID == 0 && cp.TenantID.ProjectID == 0 {
org := r.Header.Get("X-Scope-OrgID")
if org != "" {
tenantID, err := logstorage.GetTenantIDFromString(org)
if err != nil {
return nil, err
}
cp.TenantID = tenantID
}
}
return cp, nil
}

View File

@@ -1,190 +0,0 @@
package loki
import (
"fmt"
"io"
"math"
"net/http"
"strconv"
"time"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vlstorage"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
"github.com/VictoriaMetrics/metrics"
"github.com/valyala/fastjson"
)
var (
rowsIngestedJSONTotal = metrics.NewCounter(`vl_rows_ingested_total{type="loki",format="json"}`)
parserPool fastjson.ParserPool
)
func handleJSON(r *http.Request, w http.ResponseWriter) bool {
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
}
defer common.PutGzipReader(zr)
reader = zr
}
wcr := writeconcurrencylimiter.GetReader(reader)
data, err := io.ReadAll(wcr)
writeconcurrencylimiter.PutReader(wcr)
if err != nil {
httpserver.Errorf(w, r, "cannot read request body: %s", err)
return true
}
cp, err := getCommonParams(r)
if err != nil {
httpserver.Errorf(w, r, "cannot parse common params from request: %s", err)
return true
}
lr := logstorage.GetLogRows(cp.StreamFields, cp.IgnoreFields)
processLogMessage := cp.GetProcessLogMessageFunc(lr)
n, err := parseJSONRequest(data, processLogMessage)
vlstorage.MustAddRows(lr)
logstorage.PutLogRows(lr)
if err != nil {
httpserver.Errorf(w, r, "cannot parse Loki request: %s", err)
return true
}
rowsIngestedJSONTotal.Add(n)
return true
}
func parseJSONRequest(data []byte, processLogMessage func(timestamp int64, fields []logstorage.Field)) (int, error) {
p := parserPool.Get()
defer parserPool.Put(p)
v, err := p.ParseBytes(data)
if err != nil {
return 0, fmt.Errorf("cannot parse JSON request body: %w", err)
}
streamsV := v.Get("streams")
if streamsV == nil {
return 0, fmt.Errorf("missing `streams` item in the parsed JSON: %q", v)
}
streams, err := streamsV.Array()
if err != nil {
return 0, fmt.Errorf("`streams` item in the parsed JSON must contain an array; got %q", streamsV)
}
currentTimestamp := time.Now().UnixNano()
var commonFields []logstorage.Field
rowsIngested := 0
for _, stream := range streams {
// populate common labels from `stream` dict
commonFields = commonFields[:0]
labelsV := stream.Get("stream")
var labels *fastjson.Object
if labelsV != nil {
o, err := labelsV.Object()
if err != nil {
return rowsIngested, fmt.Errorf("`stream` item in the parsed JSON must contain an object; got %q", labelsV)
}
labels = o
}
labels.Visit(func(k []byte, v *fastjson.Value) {
if err != nil {
return
}
vStr, errLocal := v.StringBytes()
if errLocal != nil {
err = fmt.Errorf("unexpected label value type for %q:%q; want string", k, v)
return
}
commonFields = append(commonFields, logstorage.Field{
Name: bytesutil.ToUnsafeString(k),
Value: bytesutil.ToUnsafeString(vStr),
})
})
if err != nil {
return rowsIngested, fmt.Errorf("error when parsing `stream` object: %w", err)
}
// populate messages from `values` array
linesV := stream.Get("values")
if linesV == nil {
return rowsIngested, fmt.Errorf("missing `values` item in the parsed JSON %q", stream)
}
lines, err := linesV.Array()
if err != nil {
return rowsIngested, fmt.Errorf("`values` item in the parsed JSON must contain an array; got %q", linesV)
}
fields := commonFields
for _, line := range lines {
lineA, err := line.Array()
if err != nil {
return rowsIngested, fmt.Errorf("unexpected contents of `values` item; want array; got %q", line)
}
if len(lineA) != 2 {
return rowsIngested, fmt.Errorf("unexpected number of values in `values` item array %q; got %d want 2", line, len(lineA))
}
// parse timestamp
timestamp, err := lineA[0].StringBytes()
if err != nil {
return rowsIngested, fmt.Errorf("unexpected log timestamp type for %q; want string", lineA[0])
}
ts, err := parseLokiTimestamp(bytesutil.ToUnsafeString(timestamp))
if err != nil {
return rowsIngested, fmt.Errorf("cannot parse log timestamp %q: %w", timestamp, err)
}
if ts == 0 {
ts = currentTimestamp
}
// parse log message
msg, err := lineA[1].StringBytes()
if err != nil {
return rowsIngested, fmt.Errorf("unexpected log message type for %q; want string", lineA[1])
}
fields = append(fields[:len(commonFields)], logstorage.Field{
Name: "_msg",
Value: bytesutil.ToUnsafeString(msg),
})
processLogMessage(ts, fields)
}
rowsIngested += len(lines)
}
return rowsIngested, nil
}
func parseLokiTimestamp(s string) (int64, error) {
if s == "" {
// Special case - an empty timestamp must be substituted with the current time by the caller.
return 0, nil
}
n, err := strconv.ParseInt(s, 10, 64)
if err != nil {
// Fall back to parsing floating-point value
f, err := strconv.ParseFloat(s, 64)
if err != nil {
return 0, err
}
if f > math.MaxInt64 {
return 0, fmt.Errorf("too big timestamp in nanoseconds: %v; mustn't exceed %v", f, int64(math.MaxInt64))
}
if f < math.MinInt64 {
return 0, fmt.Errorf("too small timestamp in nanoseconds: %v; must be bigger or equal to %v", f, int64(math.MinInt64))
}
n = int64(f)
}
if n < 0 {
return 0, fmt.Errorf("too small timestamp in nanoseconds: %d; must be bigger than 0", n)
}
return n, nil
}

View File

@@ -1,130 +0,0 @@
package loki
import (
"fmt"
"strings"
"testing"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
)
func TestParseJSONRequestFailure(t *testing.T) {
f := func(s string) {
t.Helper()
n, err := parseJSONRequest([]byte(s), func(timestamp int64, fields []logstorage.Field) {
t.Fatalf("unexpected call to parseJSONRequest callback!")
})
if err == nil {
t.Fatalf("expecting non-nil error")
}
if n != 0 {
t.Fatalf("unexpected number of parsed lines: %d; want 0", n)
}
}
f(``)
// Invalid json
f(`{}`)
f(`[]`)
f(`"foo"`)
f(`123`)
// invalid type for `streams` item
f(`{"streams":123}`)
// Missing `values` item
f(`{"streams":[{}]}`)
// Invalid type for `values` item
f(`{"streams":[{"values":"foobar"}]}`)
// Invalid type for `stream` item
f(`{"streams":[{"stream":[],"values":[]}]}`)
// Invalid type for `values` individual item
f(`{"streams":[{"values":[123]}]}`)
// Invalid length of `values` individual item
f(`{"streams":[{"values":[[]]}]}`)
f(`{"streams":[{"values":[["123"]]}]}`)
f(`{"streams":[{"values":[["123","456","789"]]}]}`)
// Invalid type for timestamp inside `values` individual item
f(`{"streams":[{"values":[[123,"456"]}]}`)
// Invalid type for log message
f(`{"streams":[{"values":[["123",1234]]}]}`)
}
func TestParseJSONRequestSuccess(t *testing.T) {
f := func(s string, 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)
})
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)
}
}
// Empty streams
f(`{"streams":[]}`, ``)
f(`{"streams":[{"values":[]}]}`, ``)
f(`{"streams":[{"stream":{},"values":[]}]}`, ``)
f(`{"streams":[{"stream":{"foo":"bar"},"values":[]}]}`, ``)
// 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"`)
// Non-empty stream labels
f(`{"streams":[{"stream":{
"label1": "value1",
"label2": "value2"
},"values":[
["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"`)
// Multiple streams
f(`{
"streams": [
{
"stream": {
"foo": "bar",
"a": "b"
},
"values": [
["1577836800000000001", "foo bar"],
["1577836900005000002", "abc"]
]
},
{
"stream": {
"x": "y"
},
"values": [
["1877836900005000002", "yx"]
]
}
]
}`, `_time:1577836800000000001 "foo":"bar" "a":"b" "_msg":"foo bar"
_time:1577836900005000002 "foo":"bar" "a":"b" "_msg":"abc"
_time:1877836900005000002 "x":"y" "_msg":"yx"`)
}

View File

@@ -1,78 +0,0 @@
package loki
import (
"fmt"
"strconv"
"testing"
"time"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
)
func BenchmarkParseJSONRequest(b *testing.B) {
for _, streams := range []int{5, 10} {
for _, rows := range []int{100, 1000} {
for _, labels := range []int{10, 50} {
b.Run(fmt.Sprintf("streams_%d/rows_%d/labels_%d", streams, rows, labels), func(b *testing.B) {
benchmarkParseJSONRequest(b, streams, rows, labels)
})
}
}
}
}
func benchmarkParseJSONRequest(b *testing.B, streams, rows, labels int) {
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(timestamp int64, fields []logstorage.Field) {})
if err != nil {
panic(fmt.Errorf("unexpected error: %s", err))
}
}
})
}
func getJSONBody(streams, rows, labels int) []byte {
body := append([]byte{}, `{"streams":[`...)
now := time.Now().UnixNano()
valuePrefix := fmt.Sprintf(`["%d","value_`, now)
for i := 0; i < streams; i++ {
body = append(body, `{"stream":{`...)
for j := 0; j < labels; j++ {
body = append(body, `"label_`...)
body = strconv.AppendInt(body, int64(j), 10)
body = append(body, `":"value_`...)
body = strconv.AppendInt(body, int64(j), 10)
body = append(body, '"')
if j < labels-1 {
body = append(body, ',')
}
}
body = append(body, `}, "values":[`...)
for j := 0; j < rows; j++ {
body = append(body, valuePrefix...)
body = strconv.AppendInt(body, int64(j), 10)
body = append(body, `"]`...)
if j < rows-1 {
body = append(body, ',')
}
}
body = append(body, `]}`...)
if i < streams-1 {
body = append(body, ',')
}
}
body = append(body, `]}`...)
return body
}

View File

@@ -1,171 +0,0 @@
package loki
import (
"fmt"
"io"
"net/http"
"strconv"
"strings"
"sync"
"time"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vlstorage"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
"github.com/VictoriaMetrics/metrics"
"github.com/golang/snappy"
)
var (
rowsIngestedProtobufTotal = metrics.NewCounter(`vl_rows_ingested_total{type="loki",format="protobuf"}`)
bytesBufPool bytesutil.ByteBufferPool
pushReqsPool sync.Pool
)
func handleProtobuf(r *http.Request, w http.ResponseWriter) bool {
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
}
cp, err := getCommonParams(r)
if err != nil {
httpserver.Errorf(w, r, "cannot parse common params from request: %s", err)
return true
}
lr := logstorage.GetLogRows(cp.StreamFields, cp.IgnoreFields)
processLogMessage := cp.GetProcessLogMessageFunc(lr)
n, err := parseProtobufRequest(data, processLogMessage)
vlstorage.MustAddRows(lr)
logstorage.PutLogRows(lr)
if err != nil {
httpserver.Errorf(w, r, "cannot parse loki request: %s", err)
return true
}
rowsIngestedProtobufTotal.Add(n)
return true
}
func parseProtobufRequest(data []byte, processLogMessage func(timestamp int64, fields []logstorage.Field)) (int, error) {
bb := bytesBufPool.Get()
defer bytesBufPool.Put(bb)
buf, err := snappy.Decode(bb.B[:cap(bb.B)], data)
if err != nil {
return 0, fmt.Errorf("cannot decode snappy-encoded request body: %w", err)
}
bb.B = buf
req := getPushRequest()
defer putPushRequest(req)
err = req.Unmarshal(bb.B)
if err != nil {
return 0, fmt.Errorf("cannot parse request body: %s", err)
}
var commonFields []logstorage.Field
rowsIngested := 0
streams := req.Streams
currentTimestamp := time.Now().UnixNano()
for i := range streams {
stream := &streams[i]
// st.Labels contains labels for the stream.
// Labels are same for all entries in the stream.
commonFields, err = parsePromLabels(commonFields[:0], stream.Labels)
if err != nil {
return rowsIngested, fmt.Errorf("cannot parse stream labels %q: %s", stream.Labels, err)
}
fields := commonFields
entries := stream.Entries
for j := range entries {
entry := &entries[j]
fields = append(fields[:len(commonFields)], logstorage.Field{
Name: "_msg",
Value: entry.Line,
})
ts := entry.Timestamp.UnixNano()
if ts == 0 {
ts = currentTimestamp
}
processLogMessage(ts, fields)
}
rowsIngested += len(stream.Entries)
}
return rowsIngested, nil
}
// parsePromLabels parses log fields in Prometheus text exposition format from s, appends them to dst and returns the result.
//
// See test data of promtail for examples: https://github.com/grafana/loki/blob/a24ef7b206e0ca63ee74ca6ecb0a09b745cd2258/pkg/push/types_test.go
func parsePromLabels(dst []logstorage.Field, s string) ([]logstorage.Field, error) {
// Make sure s is wrapped into `{...}`
s = strings.TrimSpace(s)
if len(s) < 2 {
return nil, fmt.Errorf("too short string to parse: %q", s)
}
if s[0] != '{' {
return nil, fmt.Errorf("missing `{` at the beginning of %q", s)
}
if s[len(s)-1] != '}' {
return nil, fmt.Errorf("missing `}` at the end of %q", s)
}
s = s[1 : len(s)-1]
for len(s) > 0 {
// Parse label name
n := strings.IndexByte(s, '=')
if n < 0 {
return nil, fmt.Errorf("cannot find `=` char for label value at %s", s)
}
name := s[:n]
s = s[n+1:]
// Parse label value
qs, err := strconv.QuotedPrefix(s)
if err != nil {
return nil, fmt.Errorf("cannot parse value for label %q at %s: %w", name, s, err)
}
s = s[len(qs):]
value, err := strconv.Unquote(qs)
if err != nil {
return nil, fmt.Errorf("cannot unquote value %q for label %q: %w", qs, name, err)
}
// Append the found field to dst.
dst = append(dst, logstorage.Field{
Name: name,
Value: value,
})
// Check whether there are other labels remaining
if len(s) == 0 {
break
}
if !strings.HasPrefix(s, ",") {
return nil, fmt.Errorf("missing `,` char at %s", s)
}
s = s[1:]
s = strings.TrimPrefix(s, " ")
}
return dst, nil
}
func getPushRequest() *PushRequest {
v := pushReqsPool.Get()
if v == nil {
return &PushRequest{}
}
return v.(*PushRequest)
}
func putPushRequest(req *PushRequest) {
req.Reset()
pushReqsPool.Put(req)
}

View File

@@ -1,171 +0,0 @@
package loki
import (
"fmt"
"strings"
"testing"
"time"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
"github.com/golang/snappy"
)
func TestParseProtobufRequestSuccess(t *testing.T) {
f := func(s string, 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,
},
},
})
})
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)
}
data, err := 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)
})
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)
}
}
// Empty streams
f(`{"streams":[]}`, ``)
f(`{"streams":[{"values":[]}]}`, ``)
f(`{"streams":[{"stream":{},"values":[]}]}`, ``)
f(`{"streams":[{"stream":{"foo":"bar"},"values":[]}]}`, ``)
// 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"`)
// Non-empty stream labels
f(`{"streams":[{"stream":{
"label1": "value1",
"label2": "value2"
},"values":[
["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"`)
// Multiple streams
f(`{
"streams": [
{
"stream": {
"foo": "bar",
"a": "b"
},
"values": [
["1577836800000000001", "foo bar"],
["1577836900005000002", "abc"]
]
},
{
"stream": {
"x": "y"
},
"values": [
["1877836900005000002", "yx"]
]
}
]
}`, `_time:1577836800000000001 "foo":"bar" "a":"b" "_msg":"foo bar"
_time:1577836900005000002 "foo":"bar" "a":"b" "_msg":"abc"
_time:1877836900005000002 "x":"y" "_msg":"yx"`)
}
func TestParsePromLabelsSuccess(t *testing.T) {
f := func(s string) {
t.Helper()
fields, err := parsePromLabels(nil, s)
if err != nil {
t.Fatalf("unexpected error: %s", err)
}
var a []string
for _, f := range fields {
a = append(a, fmt.Sprintf("%s=%q", f.Name, f.Value))
}
result := "{" + strings.Join(a, ", ") + "}"
if result != s {
t.Fatalf("unexpected result;\ngot\n%s\nwant\n%s", result, s)
}
}
f("{}")
f(`{foo="bar"}`)
f(`{foo="bar", baz="x", y="z"}`)
f(`{foo="ba\"r\\z\n", a="", b="\"\\"}`)
}
func TestParsePromLabelsFailure(t *testing.T) {
f := func(s string) {
t.Helper()
fields, err := parsePromLabels(nil, s)
if err == nil {
t.Fatalf("expecting non-nil error")
}
if len(fields) > 0 {
t.Fatalf("unexpected non-empty fields: %s", fields)
}
}
f("")
f("{")
f(`{foo}`)
f(`{foo=bar}`)
f(`{foo="bar}`)
f(`{foo="ba\",r}`)
f(`{foo="bar" baz="aa"}`)
f(`foobar`)
f(`foo{bar="baz"}`)
}

View File

@@ -1,65 +0,0 @@
package loki
import (
"fmt"
"strconv"
"testing"
"time"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
"github.com/golang/snappy"
)
func BenchmarkParseProtobufRequest(b *testing.B) {
for _, streams := range []int{5, 10} {
for _, rows := range []int{100, 1000} {
for _, labels := range []int{10, 50} {
b.Run(fmt.Sprintf("streams_%d/rows_%d/labels_%d", streams, rows, labels), func(b *testing.B) {
benchmarkParseProtobufRequest(b, streams, rows, labels)
})
}
}
}
}
func benchmarkParseProtobufRequest(b *testing.B, streams, rows, labels int) {
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(timestamp int64, fields []logstorage.Field) {})
if err != nil {
panic(fmt.Errorf("unexpected error: %s", err))
}
}
})
}
func getProtobufBody(streams, rows, labels int) []byte {
var pr PushRequest
for i := 0; i < streams; i++ {
var st Stream
st.Labels = `{`
for j := 0; j < labels; j++ {
st.Labels += `label_` + strconv.Itoa(j) + `="value_` + strconv.Itoa(j) + `"`
if j < labels-1 {
st.Labels += `,`
}
}
st.Labels += `}`
for j := 0; j < rows; j++ {
st.Entries = append(st.Entries, Entry{Timestamp: time.Now(), Line: "value_" + strconv.Itoa(j)})
}
pr.Streams = append(pr.Streams, st)
}
body, _ := pr.Marshal()
encodedBody := snappy.Encode(nil, body)
return encodedBody
}

File diff suppressed because it is too large Load Diff

View File

@@ -1,38 +0,0 @@
syntax = "proto3";
// source: https://raw.githubusercontent.com/grafana/loki/main/pkg/push/push.proto
// Licensed under the Apache License, Version 2.0 (the "License");
// https://github.com/grafana/loki/blob/main/pkg/push/LICENSE
package logproto;
import "gogoproto/gogo.proto";
import "google/protobuf/timestamp.proto";
option go_package = "github.com/VictoriaMetrics/VictoriaMetrics/app/vlinsert/loki";
message PushRequest {
repeated StreamAdapter streams = 1 [
(gogoproto.jsontag) = "streams",
(gogoproto.customtype) = "Stream"
];
}
message StreamAdapter {
string labels = 1 [(gogoproto.jsontag) = "labels"];
repeated EntryAdapter entries = 2 [
(gogoproto.nullable) = false,
(gogoproto.jsontag) = "entries"
];
// hash contains the original hash of the stream.
uint64 hash = 3 [(gogoproto.jsontag) = "-"];
}
message EntryAdapter {
google.protobuf.Timestamp timestamp = 1 [
(gogoproto.stdtime) = true,
(gogoproto.nullable) = false,
(gogoproto.jsontag) = "ts"
];
string line = 2 [(gogoproto.jsontag) = "line"];
}

View File

@@ -1,110 +0,0 @@
package loki
// source: https://raw.githubusercontent.com/grafana/loki/main/pkg/push/timestamp.go
// Licensed under the Apache License, Version 2.0 (the "License");
// https://github.com/grafana/loki/blob/main/pkg/push/LICENSE
import (
"errors"
"strconv"
"time"
"github.com/gogo/protobuf/types"
)
const (
// Seconds field of the earliest valid Timestamp.
// This is time.Date(1, 1, 1, 0, 0, 0, 0, time.UTC).Unix().
minValidSeconds = -62135596800
// Seconds field just after the latest valid Timestamp.
// This is time.Date(10000, 1, 1, 0, 0, 0, 0, time.UTC).Unix().
maxValidSeconds = 253402300800
)
// validateTimestamp determines whether a Timestamp is valid.
// A valid timestamp represents a time in the range
// [0001-01-01, 10000-01-01) and has a Nanos field
// in the range [0, 1e9).
//
// If the Timestamp is valid, validateTimestamp returns nil.
// Otherwise, it returns an error that describes
// the problem.
//
// Every valid Timestamp can be represented by a time.Time, but the converse is not true.
func validateTimestamp(ts *types.Timestamp) error {
if ts == nil {
return errors.New("timestamp: nil Timestamp")
}
if ts.Seconds < minValidSeconds {
return errors.New("timestamp: " + formatTimestamp(ts) + " before 0001-01-01")
}
if ts.Seconds >= maxValidSeconds {
return errors.New("timestamp: " + formatTimestamp(ts) + " after 10000-01-01")
}
if ts.Nanos < 0 || ts.Nanos >= 1e9 {
return errors.New("timestamp: " + formatTimestamp(ts) + ": nanos not in range [0, 1e9)")
}
return nil
}
// formatTimestamp is equivalent to fmt.Sprintf("%#v", ts)
// but avoids the escape incurred by using fmt.Sprintf, eliminating
// unnecessary heap allocations.
func formatTimestamp(ts *types.Timestamp) string {
if ts == nil {
return "nil"
}
seconds := strconv.FormatInt(ts.Seconds, 10)
nanos := strconv.FormatInt(int64(ts.Nanos), 10)
return "&types.Timestamp{Seconds: " + seconds + ",\nNanos: " + nanos + ",\n}"
}
func sizeOfStdTime(t time.Time) int {
ts, err := timestampProto(t)
if err != nil {
return 0
}
return ts.Size()
}
func stdTimeMarshalTo(t time.Time, data []byte) (int, error) {
ts, err := timestampProto(t)
if err != nil {
return 0, err
}
return ts.MarshalTo(data)
}
func stdTimeUnmarshal(t *time.Time, data []byte) error {
ts := &types.Timestamp{}
if err := ts.Unmarshal(data); err != nil {
return err
}
tt, err := timestampFromProto(ts)
if err != nil {
return err
}
*t = tt
return nil
}
func timestampFromProto(ts *types.Timestamp) (time.Time, error) {
// Don't return the zero value on error, because corresponds to a valid
// timestamp. Instead return whatever time.Unix gives us.
var t time.Time
if ts == nil {
t = time.Unix(0, 0).UTC() // treat nil like the empty Timestamp
} else {
t = time.Unix(ts.Seconds, int64(ts.Nanos)).UTC()
}
return t, validateTimestamp(ts)
}
func timestampProto(t time.Time) (types.Timestamp, error) {
ts := types.Timestamp{
Seconds: t.Unix(),
Nanos: int32(t.Nanosecond()),
}
return ts, validateTimestamp(&ts)
}

View File

@@ -1,481 +0,0 @@
package loki
// source: https://raw.githubusercontent.com/grafana/loki/main/pkg/push/types.go
// Licensed under the Apache License, Version 2.0 (the "License");
// https://github.com/grafana/loki/blob/main/pkg/push/LICENSE
import (
"fmt"
"io"
"time"
)
// Stream contains a unique labels set as a string and a set of entries for it.
// We are not using the proto generated version but this custom one so that we
// can improve serialization see benchmark.
type Stream struct {
Labels string `protobuf:"bytes,1,opt,name=labels,proto3" json:"labels"`
Entries []Entry `protobuf:"bytes,2,rep,name=entries,proto3,customtype=EntryAdapter" json:"entries"`
Hash uint64 `protobuf:"varint,3,opt,name=hash,proto3" json:"-"`
}
// Entry is a log entry with a timestamp.
type Entry struct {
Timestamp time.Time `protobuf:"bytes,1,opt,name=timestamp,proto3,stdtime" json:"ts"`
Line string `protobuf:"bytes,2,opt,name=line,proto3" json:"line"`
}
// Marshal implements the proto.Marshaler interface.
func (m *Stream) Marshal() (dAtA []byte, err error) {
size := m.Size()
dAtA = make([]byte, size)
n, err := m.MarshalToSizedBuffer(dAtA[:size])
if err != nil {
return nil, err
}
return dAtA[:n], nil
}
// MarshalTo marshals m to dst.
func (m *Stream) MarshalTo(dAtA []byte) (int, error) {
size := m.Size()
return m.MarshalToSizedBuffer(dAtA[:size])
}
// MarshalToSizedBuffer marshals m to the sized buffer.
func (m *Stream) MarshalToSizedBuffer(dAtA []byte) (int, error) {
i := len(dAtA)
_ = i
var l int
_ = l
if m.Hash != 0 {
i = encodeVarintPush(dAtA, i, m.Hash)
i--
dAtA[i] = 0x18
}
if len(m.Entries) > 0 {
for iNdEx := len(m.Entries) - 1; iNdEx >= 0; iNdEx-- {
{
size, err := m.Entries[iNdEx].MarshalToSizedBuffer(dAtA[:i])
if err != nil {
return 0, err
}
i -= size
i = encodeVarintPush(dAtA, i, uint64(size))
}
i--
dAtA[i] = 0x12
}
}
if len(m.Labels) > 0 {
i -= len(m.Labels)
copy(dAtA[i:], m.Labels)
i = encodeVarintPush(dAtA, i, uint64(len(m.Labels)))
i--
dAtA[i] = 0xa
}
return len(dAtA) - i, nil
}
// Marshal implements the proto.Marshaler interface.
func (m *Entry) Marshal() (dAtA []byte, err error) {
size := m.Size()
dAtA = make([]byte, size)
n, err := m.MarshalToSizedBuffer(dAtA[:size])
if err != nil {
return nil, err
}
return dAtA[:n], nil
}
// MarshalTo marshals m to dst.
func (m *Entry) MarshalTo(dAtA []byte) (int, error) {
size := m.Size()
return m.MarshalToSizedBuffer(dAtA[:size])
}
// MarshalToSizedBuffer marshals m to the sized buffer.
func (m *Entry) MarshalToSizedBuffer(dAtA []byte) (int, error) {
i := len(dAtA)
_ = i
var l int
_ = l
if len(m.Line) > 0 {
i -= len(m.Line)
copy(dAtA[i:], m.Line)
i = encodeVarintPush(dAtA, i, uint64(len(m.Line)))
i--
dAtA[i] = 0x12
}
n7, err7 := stdTimeMarshalTo(m.Timestamp, dAtA[i-sizeOfStdTime(m.Timestamp):])
if err7 != nil {
return 0, err7
}
i -= n7
i = encodeVarintPush(dAtA, i, uint64(n7))
i--
dAtA[i] = 0xa
return len(dAtA) - i, nil
}
// Unmarshal unmarshals the given data into m.
func (m *Stream) Unmarshal(dAtA []byte) error {
l := len(dAtA)
iNdEx := 0
for iNdEx < l {
preIndex := iNdEx
var wire uint64
for shift := uint(0); ; shift += 7 {
if shift >= 64 {
return ErrIntOverflowPush
}
if iNdEx >= l {
return io.ErrUnexpectedEOF
}
b := dAtA[iNdEx]
iNdEx++
wire |= uint64(b&0x7F) << shift
if b < 0x80 {
break
}
}
fieldNum := int32(wire >> 3)
wireType := int(wire & 0x7)
if wireType == 4 {
return fmt.Errorf("proto: StreamAdapter: wiretype end group for non-group")
}
if fieldNum <= 0 {
return fmt.Errorf("proto: StreamAdapter: illegal tag %d (wire type %d)", fieldNum, wire)
}
switch fieldNum {
case 1:
if wireType != 2 {
return fmt.Errorf("proto: wrong wireType = %d for field Labels", wireType)
}
var stringLen uint64
for shift := uint(0); ; shift += 7 {
if shift >= 64 {
return ErrIntOverflowPush
}
if iNdEx >= l {
return io.ErrUnexpectedEOF
}
b := dAtA[iNdEx]
iNdEx++
stringLen |= uint64(b&0x7F) << shift
if b < 0x80 {
break
}
}
intStringLen := int(stringLen)
if intStringLen < 0 {
return ErrInvalidLengthPush
}
postIndex := iNdEx + intStringLen
if postIndex < 0 {
return ErrInvalidLengthPush
}
if postIndex > l {
return io.ErrUnexpectedEOF
}
m.Labels = string(dAtA[iNdEx:postIndex])
iNdEx = postIndex
case 2:
if wireType != 2 {
return fmt.Errorf("proto: wrong wireType = %d for field Entries", wireType)
}
var msglen int
for shift := uint(0); ; shift += 7 {
if shift >= 64 {
return ErrIntOverflowPush
}
if iNdEx >= l {
return io.ErrUnexpectedEOF
}
b := dAtA[iNdEx]
iNdEx++
msglen |= int(b&0x7F) << shift
if b < 0x80 {
break
}
}
if msglen < 0 {
return ErrInvalidLengthPush
}
postIndex := iNdEx + msglen
if postIndex < 0 {
return ErrInvalidLengthPush
}
if postIndex > l {
return io.ErrUnexpectedEOF
}
m.Entries = append(m.Entries, Entry{})
if err := m.Entries[len(m.Entries)-1].Unmarshal(dAtA[iNdEx:postIndex]); err != nil {
return err
}
iNdEx = postIndex
case 3:
if wireType != 0 {
return fmt.Errorf("proto: wrong wireType = %d for field Hash", wireType)
}
m.Hash = 0
for shift := uint(0); ; shift += 7 {
if shift >= 64 {
return ErrIntOverflowPush
}
if iNdEx >= l {
return io.ErrUnexpectedEOF
}
b := dAtA[iNdEx]
iNdEx++
m.Hash |= uint64(b&0x7F) << shift
if b < 0x80 {
break
}
}
default:
iNdEx = preIndex
skippy, err := skipPush(dAtA[iNdEx:])
if err != nil {
return err
}
if skippy < 0 {
return ErrInvalidLengthPush
}
if (iNdEx + skippy) < 0 {
return ErrInvalidLengthPush
}
if (iNdEx + skippy) > l {
return io.ErrUnexpectedEOF
}
iNdEx += skippy
}
}
if iNdEx > l {
return io.ErrUnexpectedEOF
}
return nil
}
// Unmarshal unmarshals the given data into m.
func (m *Entry) Unmarshal(dAtA []byte) error {
l := len(dAtA)
iNdEx := 0
for iNdEx < l {
preIndex := iNdEx
var wire uint64
for shift := uint(0); ; shift += 7 {
if shift >= 64 {
return ErrIntOverflowPush
}
if iNdEx >= l {
return io.ErrUnexpectedEOF
}
b := dAtA[iNdEx]
iNdEx++
wire |= uint64(b&0x7F) << shift
if b < 0x80 {
break
}
}
fieldNum := int32(wire >> 3)
wireType := int(wire & 0x7)
if wireType == 4 {
return fmt.Errorf("proto: EntryAdapter: wiretype end group for non-group")
}
if fieldNum <= 0 {
return fmt.Errorf("proto: EntryAdapter: illegal tag %d (wire type %d)", fieldNum, wire)
}
switch fieldNum {
case 1:
if wireType != 2 {
return fmt.Errorf("proto: wrong wireType = %d for field Timestamp", wireType)
}
var msglen int
for shift := uint(0); ; shift += 7 {
if shift >= 64 {
return ErrIntOverflowPush
}
if iNdEx >= l {
return io.ErrUnexpectedEOF
}
b := dAtA[iNdEx]
iNdEx++
msglen |= int(b&0x7F) << shift
if b < 0x80 {
break
}
}
if msglen < 0 {
return ErrInvalidLengthPush
}
postIndex := iNdEx + msglen
if postIndex < 0 {
return ErrInvalidLengthPush
}
if postIndex > l {
return io.ErrUnexpectedEOF
}
if err := stdTimeUnmarshal(&m.Timestamp, dAtA[iNdEx:postIndex]); err != nil {
return err
}
iNdEx = postIndex
case 2:
if wireType != 2 {
return fmt.Errorf("proto: wrong wireType = %d for field Line", wireType)
}
var stringLen uint64
for shift := uint(0); ; shift += 7 {
if shift >= 64 {
return ErrIntOverflowPush
}
if iNdEx >= l {
return io.ErrUnexpectedEOF
}
b := dAtA[iNdEx]
iNdEx++
stringLen |= uint64(b&0x7F) << shift
if b < 0x80 {
break
}
}
intStringLen := int(stringLen)
if intStringLen < 0 {
return ErrInvalidLengthPush
}
postIndex := iNdEx + intStringLen
if postIndex < 0 {
return ErrInvalidLengthPush
}
if postIndex > l {
return io.ErrUnexpectedEOF
}
m.Line = string(dAtA[iNdEx:postIndex])
iNdEx = postIndex
default:
iNdEx = preIndex
skippy, err := skipPush(dAtA[iNdEx:])
if err != nil {
return err
}
if skippy < 0 {
return ErrInvalidLengthPush
}
if (iNdEx + skippy) < 0 {
return ErrInvalidLengthPush
}
if (iNdEx + skippy) > l {
return io.ErrUnexpectedEOF
}
iNdEx += skippy
}
}
if iNdEx > l {
return io.ErrUnexpectedEOF
}
return nil
}
// Size returns the size of the serialized Stream.
func (m *Stream) Size() (n int) {
if m == nil {
return 0
}
var l int
_ = l
l = len(m.Labels)
if l > 0 {
n += 1 + l + sovPush(uint64(l))
}
if len(m.Entries) > 0 {
for _, e := range m.Entries {
l = e.Size()
n += 1 + l + sovPush(uint64(l))
}
}
if m.Hash != 0 {
n += 1 + sovPush(m.Hash)
}
return n
}
// Size returns the size of the serialized Entry
func (m *Entry) Size() (n int) {
if m == nil {
return 0
}
var l int
_ = l
l = sizeOfStdTime(m.Timestamp)
n += 1 + l + sovPush(uint64(l))
l = len(m.Line)
if l > 0 {
n += 1 + l + sovPush(uint64(l))
}
return n
}
// Equal returns true if the two Streams are equal.
func (m *Stream) Equal(that interface{}) bool {
if that == nil {
return m == nil
}
that1, ok := that.(*Stream)
if !ok {
that2, ok := that.(Stream)
if ok {
that1 = &that2
} else {
return false
}
}
if that1 == nil {
return m == nil
} else if m == nil {
return false
}
if m.Labels != that1.Labels {
return false
}
if len(m.Entries) != len(that1.Entries) {
return false
}
for i := range m.Entries {
if !m.Entries[i].Equal(that1.Entries[i]) {
return false
}
}
return m.Hash == that1.Hash
}
// Equal returns true if the two Entries are equal.
func (m *Entry) Equal(that interface{}) bool {
if that == nil {
return m == nil
}
that1, ok := that.(*Entry)
if !ok {
that2, ok := that.(Entry)
if ok {
that1 = &that2
} else {
return false
}
}
if that1 == nil {
return m == nil
} else if m == nil {
return false
}
if !m.Timestamp.Equal(that1.Timestamp) {
return false
}
if m.Line != that1.Line {
return false
}
return true
}

View File

@@ -1,43 +0,0 @@
package vlinsert
import (
"net/http"
"strings"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vlinsert/elasticsearch"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vlinsert/jsonline"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vlinsert/loki"
)
// Init initializes vlinsert
func Init() {
}
// Stop stops vlinsert
func Stop() {
}
// RequestHandler handles insert requests for VictoriaLogs
func RequestHandler(w http.ResponseWriter, r *http.Request) bool {
path := r.URL.Path
if !strings.HasPrefix(path, "/insert/") {
// Skip requests, which do not start with /insert/, since these aren't our requests.
return false
}
path = strings.TrimPrefix(path, "/insert")
path = strings.ReplaceAll(path, "//", "/")
if path == "/jsonline" {
return jsonline.RequestHandler(w, r)
}
switch {
case strings.HasPrefix(path, "/elasticsearch/"):
path = strings.TrimPrefix(path, "/elasticsearch")
return elasticsearch.RequestHandler(path, w, r)
case strings.HasPrefix(path, "/loki/"):
path = strings.TrimPrefix(path, "/loki")
return loki.RequestHandler(path, w, r)
default:
return false
}
}

View File

@@ -1,56 +0,0 @@
package logsql
import (
"net/http"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vlstorage"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
)
var (
maxSortBufferSize = flagutil.NewBytes("select.maxSortBufferSize", 1024*1024, "Query results from /select/logsql/query are automatically sorted by _time "+
"if their summary size doesn't exceed this value; otherwise, query results are streamed in the response without sorting; "+
"too big value for this flag may result in high memory usage since the sorting is performed in memory")
)
// ProcessQueryRequest handles /select/logsql/query request
func ProcessQueryRequest(w http.ResponseWriter, r *http.Request, stopCh <-chan struct{}) {
// Extract tenantID
tenantID, err := logstorage.GetTenantIDFromRequest(r)
if err != nil {
httpserver.Errorf(w, r, "%s", err)
return
}
qStr := r.FormValue("query")
q, err := logstorage.ParseQuery(qStr)
if err != nil {
httpserver.Errorf(w, r, "cannot parse query [%s]: %s", qStr, err)
return
}
w.Header().Set("Content-Type", "application/stream+json; charset=utf-8")
sw := getSortWriter()
sw.Init(w, maxSortBufferSize.IntN())
tenantIDs := []logstorage.TenantID{tenantID}
vlstorage.RunQuery(tenantIDs, q, stopCh, func(columns []logstorage.BlockColumn) {
if len(columns) == 0 {
return
}
rowsCount := len(columns[0].Values)
bb := blockResultPool.Get()
for rowIdx := 0; rowIdx < rowsCount; rowIdx++ {
WriteJSONRow(bb, columns, rowIdx)
}
sw.MustWrite(bb.B)
blockResultPool.Put(bb)
})
sw.FinalFlush()
putSortWriter(sw)
}
var blockResultPool bytesutil.ByteBufferPool

View File

@@ -1,41 +0,0 @@
{% import (
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
) %}
{% stripspace %}
// JSONRow creates JSON row from the given fields.
{% func JSONRow(columns []logstorage.BlockColumn, rowIdx int) %}
{
{% code c := &columns[0] %}
{%q= c.Name %}:{%q= c.Values[rowIdx] %}
{% code columns = columns[1:] %}
{% for colIdx := range columns %}
{% code c := &columns[colIdx] %}
,{%q= c.Name %}:{%q= c.Values[rowIdx] %}
{% endfor %}
}{% newline %}
{% endfunc %}
// JSONRows prints formatted rows
{% func JSONRows(rows [][]logstorage.Field) %}
{% if len(rows) == 0 %}
{% return %}
{% endif %}
{% for _, fields := range rows %}
{
{% if len(fields) > 0 %}
{% code
f := fields[0]
fields = fields[1:]
%}
{%q= f.Name %}:{%q= f.Value %}
{% for _, f := range fields %}
,{%q= f.Name %}:{%q= f.Value %}
{% endfor %}
{% endif %}
}{% newline %}
{% endfor %}
{% endfunc %}
{% endstripspace %}

View File

@@ -1,166 +0,0 @@
// Code generated by qtc from "query_response.qtpl". DO NOT EDIT.
// See https://github.com/valyala/quicktemplate for details.
//line app/vlselect/logsql/query_response.qtpl:1
package logsql
//line app/vlselect/logsql/query_response.qtpl:1
import (
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
)
// JSONRow creates JSON row from the given fields.
//line app/vlselect/logsql/query_response.qtpl:8
import (
qtio422016 "io"
qt422016 "github.com/valyala/quicktemplate"
)
//line app/vlselect/logsql/query_response.qtpl:8
var (
_ = qtio422016.Copy
_ = qt422016.AcquireByteBuffer
)
//line app/vlselect/logsql/query_response.qtpl:8
func StreamJSONRow(qw422016 *qt422016.Writer, columns []logstorage.BlockColumn, rowIdx int) {
//line app/vlselect/logsql/query_response.qtpl:8
qw422016.N().S(`{`)
//line app/vlselect/logsql/query_response.qtpl:10
c := &columns[0]
//line app/vlselect/logsql/query_response.qtpl:11
qw422016.N().Q(c.Name)
//line app/vlselect/logsql/query_response.qtpl:11
qw422016.N().S(`:`)
//line app/vlselect/logsql/query_response.qtpl:11
qw422016.N().Q(c.Values[rowIdx])
//line app/vlselect/logsql/query_response.qtpl:12
columns = columns[1:]
//line app/vlselect/logsql/query_response.qtpl:13
for colIdx := range columns {
//line app/vlselect/logsql/query_response.qtpl:14
c := &columns[colIdx]
//line app/vlselect/logsql/query_response.qtpl:14
qw422016.N().S(`,`)
//line app/vlselect/logsql/query_response.qtpl:15
qw422016.N().Q(c.Name)
//line app/vlselect/logsql/query_response.qtpl:15
qw422016.N().S(`:`)
//line app/vlselect/logsql/query_response.qtpl:15
qw422016.N().Q(c.Values[rowIdx])
//line app/vlselect/logsql/query_response.qtpl:16
}
//line app/vlselect/logsql/query_response.qtpl:16
qw422016.N().S(`}`)
//line app/vlselect/logsql/query_response.qtpl:17
qw422016.N().S(`
`)
//line app/vlselect/logsql/query_response.qtpl:18
}
//line app/vlselect/logsql/query_response.qtpl:18
func WriteJSONRow(qq422016 qtio422016.Writer, columns []logstorage.BlockColumn, rowIdx int) {
//line app/vlselect/logsql/query_response.qtpl:18
qw422016 := qt422016.AcquireWriter(qq422016)
//line app/vlselect/logsql/query_response.qtpl:18
StreamJSONRow(qw422016, columns, rowIdx)
//line app/vlselect/logsql/query_response.qtpl:18
qt422016.ReleaseWriter(qw422016)
//line app/vlselect/logsql/query_response.qtpl:18
}
//line app/vlselect/logsql/query_response.qtpl:18
func JSONRow(columns []logstorage.BlockColumn, rowIdx int) string {
//line app/vlselect/logsql/query_response.qtpl:18
qb422016 := qt422016.AcquireByteBuffer()
//line app/vlselect/logsql/query_response.qtpl:18
WriteJSONRow(qb422016, columns, rowIdx)
//line app/vlselect/logsql/query_response.qtpl:18
qs422016 := string(qb422016.B)
//line app/vlselect/logsql/query_response.qtpl:18
qt422016.ReleaseByteBuffer(qb422016)
//line app/vlselect/logsql/query_response.qtpl:18
return qs422016
//line app/vlselect/logsql/query_response.qtpl:18
}
// JSONRows prints formatted rows
//line app/vlselect/logsql/query_response.qtpl:21
func StreamJSONRows(qw422016 *qt422016.Writer, rows [][]logstorage.Field) {
//line app/vlselect/logsql/query_response.qtpl:22
if len(rows) == 0 {
//line app/vlselect/logsql/query_response.qtpl:23
return
//line app/vlselect/logsql/query_response.qtpl:24
}
//line app/vlselect/logsql/query_response.qtpl:25
for _, fields := range rows {
//line app/vlselect/logsql/query_response.qtpl:25
qw422016.N().S(`{`)
//line app/vlselect/logsql/query_response.qtpl:27
if len(fields) > 0 {
//line app/vlselect/logsql/query_response.qtpl:29
f := fields[0]
fields = fields[1:]
//line app/vlselect/logsql/query_response.qtpl:32
qw422016.N().Q(f.Name)
//line app/vlselect/logsql/query_response.qtpl:32
qw422016.N().S(`:`)
//line app/vlselect/logsql/query_response.qtpl:32
qw422016.N().Q(f.Value)
//line app/vlselect/logsql/query_response.qtpl:33
for _, f := range fields {
//line app/vlselect/logsql/query_response.qtpl:33
qw422016.N().S(`,`)
//line app/vlselect/logsql/query_response.qtpl:34
qw422016.N().Q(f.Name)
//line app/vlselect/logsql/query_response.qtpl:34
qw422016.N().S(`:`)
//line app/vlselect/logsql/query_response.qtpl:34
qw422016.N().Q(f.Value)
//line app/vlselect/logsql/query_response.qtpl:35
}
//line app/vlselect/logsql/query_response.qtpl:36
}
//line app/vlselect/logsql/query_response.qtpl:36
qw422016.N().S(`}`)
//line app/vlselect/logsql/query_response.qtpl:37
qw422016.N().S(`
`)
//line app/vlselect/logsql/query_response.qtpl:38
}
//line app/vlselect/logsql/query_response.qtpl:39
}
//line app/vlselect/logsql/query_response.qtpl:39
func WriteJSONRows(qq422016 qtio422016.Writer, rows [][]logstorage.Field) {
//line app/vlselect/logsql/query_response.qtpl:39
qw422016 := qt422016.AcquireWriter(qq422016)
//line app/vlselect/logsql/query_response.qtpl:39
StreamJSONRows(qw422016, rows)
//line app/vlselect/logsql/query_response.qtpl:39
qt422016.ReleaseWriter(qw422016)
//line app/vlselect/logsql/query_response.qtpl:39
}
//line app/vlselect/logsql/query_response.qtpl:39
func JSONRows(rows [][]logstorage.Field) string {
//line app/vlselect/logsql/query_response.qtpl:39
qb422016 := qt422016.AcquireByteBuffer()
//line app/vlselect/logsql/query_response.qtpl:39
WriteJSONRows(qb422016, rows)
//line app/vlselect/logsql/query_response.qtpl:39
qs422016 := string(qb422016.B)
//line app/vlselect/logsql/query_response.qtpl:39
qt422016.ReleaseByteBuffer(qb422016)
//line app/vlselect/logsql/query_response.qtpl:39
return qs422016
//line app/vlselect/logsql/query_response.qtpl:39
}

View File

@@ -1,225 +0,0 @@
package logsql
import (
"bytes"
"io"
"sort"
"sync"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logjson"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
)
func getSortWriter() *sortWriter {
v := sortWriterPool.Get()
if v == nil {
return &sortWriter{}
}
return v.(*sortWriter)
}
func putSortWriter(sw *sortWriter) {
sw.reset()
sortWriterPool.Put(sw)
}
var sortWriterPool sync.Pool
// sortWriter expects JSON line stream to be written to it.
//
// It buffers the incoming data until its size reaches maxBufLen.
// Then it streams the buffered data and all the incoming data to w.
//
// The FinalFlush() must be called when all the data is written.
// If the buf isn't empty at FinalFlush() call, then the buffered data
// is sorted by _time field.
type sortWriter struct {
mu sync.Mutex
w io.Writer
maxBufLen int
buf []byte
bufFlushed bool
hasErr bool
}
func (sw *sortWriter) reset() {
sw.w = nil
sw.maxBufLen = 0
sw.buf = sw.buf[:0]
sw.bufFlushed = false
sw.hasErr = false
}
func (sw *sortWriter) Init(w io.Writer, maxBufLen int) {
sw.reset()
sw.w = w
sw.maxBufLen = maxBufLen
}
func (sw *sortWriter) MustWrite(p []byte) {
sw.mu.Lock()
defer sw.mu.Unlock()
if sw.hasErr {
return
}
if sw.bufFlushed {
if _, err := sw.w.Write(p); err != nil {
sw.hasErr = true
}
return
}
if len(sw.buf)+len(p) < sw.maxBufLen {
sw.buf = append(sw.buf, p...)
return
}
sw.bufFlushed = true
if len(sw.buf) > 0 {
if _, err := sw.w.Write(sw.buf); err != nil {
sw.hasErr = true
return
}
sw.buf = sw.buf[:0]
}
if _, err := sw.w.Write(p); err != nil {
sw.hasErr = true
}
}
func (sw *sortWriter) FinalFlush() {
if sw.hasErr || sw.bufFlushed {
return
}
rs := getRowsSorter()
rs.parseRows(sw.buf)
rs.sort()
WriteJSONRows(sw.w, rs.rows)
putRowsSorter(rs)
}
func getRowsSorter() *rowsSorter {
v := rowsSorterPool.Get()
if v == nil {
return &rowsSorter{}
}
return v.(*rowsSorter)
}
func putRowsSorter(rs *rowsSorter) {
rs.reset()
rowsSorterPool.Put(rs)
}
var rowsSorterPool sync.Pool
type rowsSorter struct {
buf []byte
fieldsBuf []logstorage.Field
rows [][]logstorage.Field
times []string
}
func (rs *rowsSorter) reset() {
rs.buf = rs.buf[:0]
fieldsBuf := rs.fieldsBuf
for i := range fieldsBuf {
fieldsBuf[i].Reset()
}
rs.fieldsBuf = fieldsBuf[:0]
rows := rs.rows
for i := range rows {
rows[i] = nil
}
rs.rows = rows[:0]
times := rs.times
for i := range times {
times[i] = ""
}
rs.times = times[:0]
}
func (rs *rowsSorter) parseRows(src []byte) {
rs.reset()
buf := rs.buf
fieldsBuf := rs.fieldsBuf
rows := rs.rows
times := rs.times
p := logjson.GetParser()
for len(src) > 0 {
var line []byte
n := bytes.IndexByte(src, '\n')
if n < 0 {
line = src
src = nil
} else {
line = src[:n]
src = src[n+1:]
}
if len(line) == 0 {
continue
}
if err := p.ParseLogMessage(line); err != nil {
logger.Panicf("BUG: unexpected invalid JSON line: %s", err)
}
timeValue := ""
fieldsBufLen := len(fieldsBuf)
for _, f := range p.Fields {
bufLen := len(buf)
buf = append(buf, f.Name...)
name := bytesutil.ToUnsafeString(buf[bufLen:])
bufLen = len(buf)
buf = append(buf, f.Value...)
value := bytesutil.ToUnsafeString(buf[bufLen:])
fieldsBuf = append(fieldsBuf, logstorage.Field{
Name: name,
Value: value,
})
if name == "_time" {
timeValue = value
}
}
rows = append(rows, fieldsBuf[fieldsBufLen:])
times = append(times, timeValue)
}
logjson.PutParser(p)
rs.buf = buf
rs.fieldsBuf = fieldsBuf
rs.rows = rows
rs.times = times
}
func (rs *rowsSorter) Len() int {
return len(rs.rows)
}
func (rs *rowsSorter) Less(i, j int) bool {
times := rs.times
return times[i] < times[j]
}
func (rs *rowsSorter) Swap(i, j int) {
times := rs.times
rows := rs.rows
times[i], times[j] = times[j], times[i]
rows[i], rows[j] = rows[j], rows[i]
}
func (rs *rowsSorter) sort() {
sort.Sort(rs)
}

View File

@@ -1,39 +0,0 @@
package logsql
import (
"bytes"
"strings"
"testing"
)
func TestSortWriter(t *testing.T) {
f := func(maxBufLen int, data string, expectedResult string) {
t.Helper()
var bb bytes.Buffer
sw := getSortWriter()
sw.Init(&bb, maxBufLen)
for _, s := range strings.Split(data, "\n") {
sw.MustWrite([]byte(s + "\n"))
}
sw.FinalFlush()
putSortWriter(sw)
result := bb.String()
if result != expectedResult {
t.Fatalf("unexpected result;\ngot\n%s\nwant\n%s", result, expectedResult)
}
}
f(100, "", "")
f(100, "{}", "{}\n")
data := `{"_time":"def","_msg":"xxx"}
{"_time":"abc","_msg":"foo"}`
resultExpected := `{"_time":"abc","_msg":"foo"}
{"_time":"def","_msg":"xxx"}
`
f(100, data, resultExpected)
f(10, data, data+"\n")
}

View File

@@ -1,162 +0,0 @@
package vlselect
import (
"embed"
"flag"
"fmt"
"net/http"
"strings"
"time"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vlselect/logsql"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/cgroup"
"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"
)
var (
maxConcurrentRequests = flag.Int("search.maxConcurrentRequests", getDefaultMaxConcurrentRequests(), "The maximum number of concurrent search requests. "+
"It shouldn't be high, since a single request can saturate all the CPU cores, while many concurrently executed requests may require high amounts of memory. "+
"See also -search.maxQueueDuration")
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")
)
func getDefaultMaxConcurrentRequests() int {
n := cgroup.AvailableCPUs()
if n <= 4 {
n *= 2
}
if n > 16 {
// A single request can saturate all the CPU cores, so there is no sense
// in allowing higher number of concurrent requests - they will just contend
// for unavailable CPU time.
n = 16
}
return n
}
// Init initializes vlselect
func Init() {
concurrencyLimitCh = make(chan struct{}, *maxConcurrentRequests)
}
// Stop stops vlselect
func Stop() {
}
var concurrencyLimitCh chan struct{}
var (
concurrencyLimitReached = metrics.NewCounter(`vl_concurrent_select_limit_reached_total`)
concurrencyLimitTimeout = metrics.NewCounter(`vl_concurrent_select_limit_timeout_total`)
_ = metrics.NewGauge(`vl_concurrent_select_capacity`, func() float64 {
return float64(cap(concurrencyLimitCh))
})
_ = metrics.NewGauge(`vl_concurrent_select_current`, func() float64 {
return float64(len(concurrencyLimitCh))
})
)
//go:embed vmui
var vmuiFiles embed.FS
var vmuiFileServer = http.FileServer(http.FS(vmuiFiles))
// RequestHandler handles select requests for VictoriaLogs
func RequestHandler(w http.ResponseWriter, r *http.Request) bool {
path := r.URL.Path
if !strings.HasPrefix(path, "/select/") {
// Skip requests, which do not start with /select/, since these aren't our requests.
return false
}
path = strings.TrimPrefix(path, "/select")
path = strings.ReplaceAll(path, "//", "/")
if path == "/vmui" {
// VMUI access via incomplete url without `/` in the end. Redirect to complete url.
// Use relative redirect, since the hostname and path prefix may be incorrect if VictoriaMetrics
// is hidden behind vmauth or similar proxy.
_ = r.ParseForm()
newURL := "vmui/?" + r.Form.Encode()
httpserver.Redirect(w, newURL)
return true
}
if strings.HasPrefix(path, "/vmui/") {
r.URL.Path = path
vmuiFileServer.ServeHTTP(w, r)
return true
}
// Limit the number of concurrent queries, which can consume big amounts of CPU.
startTime := time.Now()
stopCh := r.Context().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,
}
httpserver.Errorf(w, r, "%s", err)
return true
}
}
switch {
case path == "/logsql/query":
logsqlQueryRequests.Inc()
httpserver.EnableCORS(w, r)
logsql.ProcessQueryRequest(w, r, stopCh)
return true
default:
return false
}
}
// getMaxQueryDuration returns the maximum duration for query from r.
func getMaxQueryDuration(r *http.Request) time.Duration {
dms, err := httputils.GetDuration(r, "timeout", 0)
if err != nil {
dms = 0
}
d := time.Duration(dms) * time.Millisecond
if d <= 0 || d > *maxQueryDuration {
d = *maxQueryDuration
}
return d
}
var (
logsqlQueryRequests = metrics.NewCounter(`vl_http_requests_total{path="/select/logsql/query"}`)
)

Binary file not shown.

Before

Width:  |  Height:  |  Size: 14 KiB

View File

@@ -1,14 +0,0 @@
{
"files": {
"main.css": "./static/css/main.5f461a27.css",
"main.js": "./static/js/main.7566144a.js",
"static/js/522.b5ae4365.chunk.js": "./static/js/522.b5ae4365.chunk.js",
"static/media/Lato-Regular.ttf": "./static/media/Lato-Regular.d714fec1633b69a9c2e9.ttf",
"static/media/Lato-Bold.ttf": "./static/media/Lato-Bold.32360ba4b57802daa4d6.ttf",
"index.html": "./index.html"
},
"entrypoints": [
"static/css/main.5f461a27.css",
"static/js/main.7566144a.js"
]
}

Binary file not shown.

Before

Width:  |  Height:  |  Size: 1.6 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 15 KiB

View File

@@ -1 +0,0 @@
<!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=1,user-scalable=no"/><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.7566144a.js"></script><link href="./static/css/main.5f461a27.css" rel="stylesheet"></head><body><noscript>You need to enable JavaScript to run this app.</noscript><div id="root"></div></body></html>

View File

@@ -1,20 +0,0 @@
{
"short_name": "Victoria Metrics UI",
"name": "Victoria Metrics UI is a metric explorer for Victoria Metrics",
"icons": [
{
"src": "favicon-32x32.png",
"sizes": "32x32",
"type": "image/png"
},
{
"src": "apple-touch-icon.png",
"type": "image/png",
"sizes": "192x192"
}
],
"start_url": ".",
"display": "standalone",
"theme_color": "#000000",
"background_color": "#ffffff"
}

Binary file not shown.

Before

Width:  |  Height:  |  Size: 67 KiB

View File

@@ -1,3 +0,0 @@
# https://www.robotstxt.org/robotstxt.html
User-agent: *
Disallow:

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

View File

@@ -1,40 +0,0 @@
/*!
Copyright (c) 2018 Jed Watson.
Licensed under the MIT License (MIT), see
http://jedwatson.github.io/classnames
*/
/*! regenerator-runtime -- Copyright (c) 2014-present, Facebook, Inc. -- license (MIT): https://github.com/facebook/regenerator/blob/main/LICENSE */
/**
* @remix-run/router v1.7.2
*
* Copyright (c) Remix Software Inc.
*
* This source code is licensed under the MIT license found in the
* LICENSE.md file in the root directory of this source tree.
*
* @license MIT
*/
/**
* React Router DOM v6.14.2
*
* Copyright (c) Remix Software Inc.
*
* This source code is licensed under the MIT license found in the
* LICENSE.md file in the root directory of this source tree.
*
* @license MIT
*/
/**
* React Router v6.14.2
*
* Copyright (c) Remix Software Inc.
*
* This source code is licensed under the MIT license found in the
* LICENSE.md file in the root directory of this source tree.
*
* @license MIT
*/

View File

@@ -1,189 +0,0 @@
package vlstorage
import (
"flag"
"fmt"
"sync"
"time"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/fs"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
"github.com/VictoriaMetrics/metrics"
)
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")
futureRetention = flagutil.NewDuration("futureRetention", "2d", "Log entries with timestamps bigger than now+futureRetention are rejected during data ingestion; "+
"see https://docs.victoriametrics.com/VictoriaLogs/#retention")
storageDataPath = flag.String("storageDataPath", "victoria-logs-data", "Path to directory with the VictoriaLogs data; "+
"see https://docs.victoriametrics.com/VictoriaLogs/#storage")
inmemoryDataFlushInterval = flag.Duration("inmemoryDataFlushInterval", 5*time.Second, "The interval for guaranteed saving of in-memory data to disk. "+
"The saved data survives unclean shutdowns such as OOM crash, hardware reset, SIGKILL, etc. "+
"Bigger intervals may help increase the lifetime of flash storage with limited write cycles (e.g. Raspberry PI). "+
"Smaller intervals increase disk IO load. Minimum supported value is 1s")
logNewStreams = flag.Bool("logNewStreams", false, "Whether to log creation of new streams; this can be useful for debugging of high cardinality issues with log streams; "+
"see https://docs.victoriametrics.com/VictoriaLogs/keyConcepts.html#stream-fields ; see also -logIngestedRows")
logIngestedRows = flag.Bool("logIngestedRows", false, "Whether to log all the ingested log entries; this can be useful for debugging of data ingestion; "+
"see https://docs.victoriametrics.com/VictoriaLogs/data-ingestion/ ; see also -logNewStreams")
)
// Init initializes vlstorage.
//
// Stop must be called when vlstorage is no longer needed
func Init() {
if strg != nil {
logger.Panicf("BUG: Init() has been already called")
}
if retentionPeriod.Msecs < 24*3600*1000 {
logger.Fatalf("-retentionPeriod cannot be smaller than a day; got %s", retentionPeriod)
}
cfg := &logstorage.StorageConfig{
Retention: time.Millisecond * time.Duration(retentionPeriod.Msecs),
FlushInterval: *inmemoryDataFlushInterval,
FutureRetention: time.Millisecond * time.Duration(futureRetention.Msecs),
LogNewStreams: *logNewStreams,
LogIngestedRows: *logIngestedRows,
}
logger.Infof("opening storage at -storageDataPath=%s", *storageDataPath)
startTime := time.Now()
strg = logstorage.MustOpenStorage(*storageDataPath, cfg)
var ss logstorage.StorageStats
strg.UpdateStats(&ss)
logger.Infof("successfully opened storage in %.3f seconds; partsCount: %d; blocksCount: %d; rowsCount: %d; sizeBytes: %d",
time.Since(startTime).Seconds(), ss.FileParts, ss.FileBlocks, ss.FileRowsCount, ss.CompressedFileSize)
storageMetrics = initStorageMetrics(strg)
metrics.RegisterSet(storageMetrics)
}
// Stop stops vlstorage.
func Stop() {
metrics.UnregisterSet(storageMetrics)
storageMetrics = nil
strg.MustClose()
strg = nil
}
var strg *logstorage.Storage
var storageMetrics *metrics.Set
// MustAddRows adds lr to vlstorage
func MustAddRows(lr *logstorage.LogRows) {
strg.MustAddRows(lr)
}
// RunQuery runs the given q and calls processBlock for the returned data blocks
func RunQuery(tenantIDs []logstorage.TenantID, q *logstorage.Query, stopCh <-chan struct{}, processBlock func(columns []logstorage.BlockColumn)) {
strg.RunQuery(tenantIDs, q, stopCh, processBlock)
}
func initStorageMetrics(strg *logstorage.Storage) *metrics.Set {
ssCache := &logstorage.StorageStats{}
var ssCacheLock sync.Mutex
var lastUpdateTime time.Time
m := func() *logstorage.StorageStats {
ssCacheLock.Lock()
defer ssCacheLock.Unlock()
if time.Since(lastUpdateTime) < time.Second {
return ssCache
}
var ss logstorage.StorageStats
strg.UpdateStats(&ss)
ssCache = &ss
lastUpdateTime = time.Now()
return ssCache
}
ms := metrics.NewSet()
ms.NewGauge(fmt.Sprintf(`vl_free_disk_space_bytes{path=%q}`, *storageDataPath), func() float64 {
return float64(fs.MustGetFreeSpace(*storageDataPath))
})
ms.NewGauge(`vl_active_merges{type="inmemory"}`, func() float64 {
return float64(m().InmemoryActiveMerges)
})
ms.NewGauge(`vl_merges_total{type="inmemory"}`, func() float64 {
return float64(m().InmemoryMergesTotal)
})
ms.NewGauge(`vl_active_merges{type="file"}`, func() float64 {
return float64(m().FileActiveMerges)
})
ms.NewGauge(`vl_merges_total{type="file"}`, func() float64 {
return float64(m().FileMergesTotal)
})
ms.NewGauge(`vl_storage_rows{type="inmemory"}`, func() float64 {
return float64(m().InmemoryRowsCount)
})
ms.NewGauge(`vl_storage_rows{type="file"}`, func() float64 {
return float64(m().FileRowsCount)
})
ms.NewGauge(`vl_storage_parts{type="inmemory"}`, func() float64 {
return float64(m().InmemoryParts)
})
ms.NewGauge(`vl_storage_parts{type="file"}`, func() float64 {
return float64(m().FileParts)
})
ms.NewGauge(`vl_storage_blocks{type="inmemory"}`, func() float64 {
return float64(m().InmemoryBlocks)
})
ms.NewGauge(`vl_storage_blocks{type="file"}`, func() float64 {
return float64(m().FileBlocks)
})
ms.NewGauge(`vl_partitions`, func() float64 {
return float64(m().PartitionsCount)
})
ms.NewGauge(`vl_streams_created_total`, func() float64 {
return float64(m().StreamsCreatedTotal)
})
ms.NewGauge(`vl_indexdb_rows`, func() float64 {
return float64(m().IndexdbItemsCount)
})
ms.NewGauge(`vl_indexdb_parts`, func() float64 {
return float64(m().IndexdbPartsCount)
})
ms.NewGauge(`vl_indexdb_blocks`, func() float64 {
return float64(m().IndexdbBlocksCount)
})
ms.NewGauge(`vl_data_size_bytes{type="indexdb"}`, func() float64 {
return float64(m().IndexdbSizeBytes)
})
ms.NewGauge(`vl_data_size_bytes{type="storage"}`, func() float64 {
dm := m()
return float64(dm.CompressedInmemorySize + dm.CompressedFileSize)
})
ms.NewGauge(`vl_compressed_data_size_bytes{type="inmemory"}`, func() float64 {
return float64(m().CompressedInmemorySize)
})
ms.NewGauge(`vl_compressed_data_size_bytes{type="file"}`, func() float64 {
return float64(m().CompressedFileSize)
})
ms.NewGauge(`vl_uncompressed_data_size_bytes{type="inmemory"}`, func() float64 {
return float64(m().UncompressedInmemorySize)
})
ms.NewGauge(`vl_uncompressed_data_size_bytes{type="file"}`, func() float64 {
return float64(m().UncompressedFileSize)
})
ms.NewGauge(`vl_rows_dropped_total{reason="too_big_timestamp"}`, func() float64 {
return float64(m().RowsDroppedTooBigTimestamp)
})
ms.NewGauge(`vl_rows_dropped_total{reason="too_small_timestamp"}`, func() float64 {
return float64(m().RowsDroppedTooSmallTimestamp)
})
return ms
}

View File

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

File diff suppressed because it is too large Load Diff

View File

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

View File

@@ -9,8 +9,8 @@ import (
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
parserCommon "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
parser "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadog"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadog/stream"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
"github.com/VictoriaMetrics/metrics"
)
@@ -28,9 +28,11 @@ func InsertHandlerForHTTP(at *auth.Token, req *http.Request) error {
if err != nil {
return err
}
ce := req.Header.Get("Content-Encoding")
return stream.Parse(req.Body, ce, func(series []parser.Series) error {
return insertRows(at, series, extraLabels)
return writeconcurrencylimiter.Do(func() error {
ce := req.Header.Get("Content-Encoding")
return parser.ParseStream(req.Body, ce, func(series []parser.Series) error {
return insertRows(at, series, extraLabels)
})
})
}
@@ -50,18 +52,10 @@ func insertRows(at *auth.Token, series []parser.Series, extraLabels []prompbmars
Name: "__name__",
Value: ss.Metric,
})
if ss.Host != "" {
labels = append(labels, prompbmarshal.Label{
Name: "host",
Value: ss.Host,
})
}
if ss.Device != "" {
labels = append(labels, prompbmarshal.Label{
Name: "device",
Value: ss.Device,
})
}
labels = append(labels, prompbmarshal.Label{
Name: "host",
Value: ss.Host,
})
for _, tag := range ss.Tags {
name, value := parser.SplitTag(tag)
if name == "host" {

View File

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

View File

@@ -15,14 +15,14 @@ import (
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
parserCommon "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
parser "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/influx"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/influx/stream"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
"github.com/VictoriaMetrics/metrics"
)
var (
measurementFieldSeparator = flag.String("influxMeasurementFieldSeparator", "_", "Separator for '{measurement}{separator}{field_name}' metric name when inserted via InfluxDB line protocol")
skipSingleField = flag.Bool("influxSkipSingleField", false, "Uses '{measurement}' instead of '{measurement}{separator}{field_name}' for metric name if InfluxDB line contains only a single field")
skipSingleField = flag.Bool("influxSkipSingleField", false, "Uses '{measurement}' instead of '{measurement}{separator}{field_name}' for metic name if InfluxDB line contains only a single field")
skipMeasurement = flag.Bool("influxSkipMeasurement", false, "Uses '{field_name}' as a metric name while ignoring '{measurement}' and '-influxMeasurementFieldSeparator'")
dbLabel = flag.String("influxDBLabel", "db", "Default label for the DB name sent over '?db={db_name}' query parameter")
)
@@ -37,8 +37,10 @@ var (
//
// See https://github.com/influxdata/telegraf/tree/master/plugins/inputs/socket_listener/
func InsertHandlerForReader(r io.Reader, isGzipped bool) error {
return stream.Parse(r, isGzipped, "", "", func(db string, rows []parser.Row) error {
return insertRows(nil, db, rows, nil)
return writeconcurrencylimiter.Do(func() error {
return parser.ParseStream(r, isGzipped, "", "", func(db string, rows []parser.Row) error {
return insertRows(nil, db, rows, nil)
})
})
}
@@ -50,13 +52,15 @@ func InsertHandlerForHTTP(at *auth.Token, req *http.Request) error {
if err != nil {
return err
}
isGzipped := req.Header.Get("Content-Encoding") == "gzip"
q := req.URL.Query()
precision := q.Get("precision")
// Read db tag from https://docs.influxdata.com/influxdb/v1.7/tools/api/#write-http-endpoint
db := q.Get("db")
return stream.Parse(req.Body, isGzipped, precision, db, func(db string, rows []parser.Row) error {
return insertRows(at, db, rows, extraLabels)
return writeconcurrencylimiter.Do(func() error {
isGzipped := req.Header.Get("Content-Encoding") == "gzip"
q := req.URL.Query()
precision := q.Get("precision")
// Read db tag from https://docs.influxdata.com/influxdb/v1.7/tools/api/#write-http-endpoint
db := q.Get("db")
return parser.ParseStream(req.Body, isGzipped, precision, db, func(db string, rows []parser.Row) error {
return insertRows(at, db, rows, extraLabels)
})
})
}

View File

@@ -16,7 +16,6 @@ import (
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/graphite"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/influx"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/native"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/opentelemetry"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/opentsdb"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/opentsdbhttp"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/prometheusimport"
@@ -39,37 +38,24 @@ import (
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promscrape"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/pushmetrics"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/writeconcurrencylimiter"
"github.com/VictoriaMetrics/metrics"
)
var (
httpListenAddr = flag.String("httpListenAddr", ":8429", "TCP address to listen for http connections. "+
"Set this flag to empty value in order to disable listening on any port. This mode may be useful for running multiple vmagent instances on the same server. "+
"Note that /targets and /metrics pages aren't available if -httpListenAddr=''. See also -httpListenAddr.useProxyProtocol")
useProxyProtocol = flag.Bool("httpListenAddr.useProxyProtocol", false, "Whether to use proxy protocol for connections accepted at -httpListenAddr . "+
"See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt . "+
"With enabled proxy protocol http server cannot serve regular /metrics endpoint. Use -pushmetrics.url for metrics pushing")
"Note that /targets and /metrics pages aren't available if -httpListenAddr=''")
influxListenAddr = flag.String("influxListenAddr", "", "TCP and UDP address to listen for InfluxDB line protocol data. Usually :8089 must be set. Doesn't work if empty. "+
"This flag isn't needed when ingesting data over HTTP - just send it to http://<vmagent>:8429/write . "+
"See also -influxListenAddr.useProxyProtocol")
influxUseProxyProtocol = flag.Bool("influxListenAddr.useProxyProtocol", false, "Whether to use proxy protocol for connections accepted at -influxListenAddr . "+
"See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt")
graphiteListenAddr = flag.String("graphiteListenAddr", "", "TCP and UDP address to listen for Graphite plaintext data. Usually :2003 must be set. Doesn't work if empty. "+
"See also -graphiteListenAddr.useProxyProtocol")
graphiteUseProxyProtocol = flag.Bool("graphiteListenAddr.useProxyProtocol", false, "Whether to use proxy protocol for connections accepted at -graphiteListenAddr . "+
"See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt")
opentsdbListenAddr = flag.String("opentsdbListenAddr", "", "TCP and UDP address to listen for OpenTSDB metrics. "+
"This flag isn't needed when ingesting data over HTTP - just send it to http://<vmagent>:8429/write")
graphiteListenAddr = flag.String("graphiteListenAddr", "", "TCP and UDP address to listen for Graphite plaintext data. Usually :2003 must be set. Doesn't work if empty")
opentsdbListenAddr = flag.String("opentsdbListenAddr", "", "TCP and UDP address to listen for OpentTSDB metrics. "+
"Telnet put messages and HTTP /api/put messages are simultaneously served on TCP port. "+
"Usually :4242 must be set. Doesn't work if empty. See also -opentsdbListenAddr.useProxyProtocol")
opentsdbUseProxyProtocol = flag.Bool("opentsdbListenAddr.useProxyProtocol", false, "Whether to use proxy protocol for connections accepted at -opentsdbListenAddr . "+
"See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt")
opentsdbHTTPListenAddr = flag.String("opentsdbHTTPListenAddr", "", "TCP address to listen for OpenTSDB HTTP put requests. Usually :4242 must be set. Doesn't work if empty. "+
"See also -opentsdbHTTPListenAddr.useProxyProtocol")
opentsdbHTTPUseProxyProtocol = flag.Bool("opentsdbHTTPListenAddr.useProxyProtocol", false, "Whether to use proxy protocol for connections accepted "+
"at -opentsdbHTTPListenAddr . See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt")
configAuthKey = flag.String("configAuthKey", "", "Authorization key for accessing /config page. It must be passed via authKey query arg")
dryRun = flag.Bool("dryRun", false, "Whether to check config files without running vmagent. The following files are checked: "+
"-promscrape.config, -remoteWrite.relabelConfig, -remoteWrite.urlRelabelConfig, -remoteWrite.streamAggr.config . "+
"Usually :4242 must be set. Doesn't work if empty")
opentsdbHTTPListenAddr = flag.String("opentsdbHTTPListenAddr", "", "TCP address to listen for OpentTSDB HTTP put requests. Usually :4242 must be set. Doesn't work if empty")
configAuthKey = flag.String("configAuthKey", "", "Authorization key for accessing /config page. It must be passed via authKey query arg")
dryRun = flag.Bool("dryRun", false, "Whether to check only config files without running vmagent. The following files are checked: "+
"-promscrape.config, -remoteWrite.relabelConfig, -remoteWrite.urlRelabelConfig . "+
"Unknown config entries aren't allowed in -promscrape.config by default. This can be changed by passing -promscrape.config.strictParse=false command-line flag")
)
@@ -100,20 +86,17 @@ func main() {
if err := promscrape.CheckConfig(); err != nil {
logger.Fatalf("error when checking -promscrape.config: %s", err)
}
logger.Infof("-promscrape.config is ok; exiting with 0 status code")
logger.Infof("-promscrape.config is ok; exitting with 0 status code")
return
}
if *dryRun {
if err := promscrape.CheckConfig(); err != nil {
logger.Fatalf("error when checking -promscrape.config: %s", err)
}
if err := remotewrite.CheckRelabelConfigs(); err != nil {
logger.Fatalf("error when checking relabel configs: %s", err)
}
if err := remotewrite.CheckStreamAggrConfigs(); err != nil {
logger.Fatalf("error when checking -remoteWrite.streamAggr.config: %s", err)
if err := promscrape.CheckConfig(); err != nil {
logger.Fatalf("error when checking -promscrape.config: %s", err)
}
logger.Infof("all the configs are ok; exiting with 0 status code")
logger.Infof("all the configs are ok; exitting with 0 status code")
return
}
@@ -121,27 +104,28 @@ func main() {
startTime := time.Now()
remotewrite.Init()
common.StartUnmarshalWorkers()
writeconcurrencylimiter.Init()
if len(*influxListenAddr) > 0 {
influxServer = influxserver.MustStart(*influxListenAddr, *influxUseProxyProtocol, func(r io.Reader) error {
influxServer = influxserver.MustStart(*influxListenAddr, func(r io.Reader) error {
return influx.InsertHandlerForReader(r, false)
})
}
if len(*graphiteListenAddr) > 0 {
graphiteServer = graphiteserver.MustStart(*graphiteListenAddr, *graphiteUseProxyProtocol, graphite.InsertHandler)
graphiteServer = graphiteserver.MustStart(*graphiteListenAddr, graphite.InsertHandler)
}
if len(*opentsdbListenAddr) > 0 {
httpInsertHandler := getOpenTSDBHTTPInsertHandler()
opentsdbServer = opentsdbserver.MustStart(*opentsdbListenAddr, *opentsdbUseProxyProtocol, opentsdb.InsertHandler, httpInsertHandler)
opentsdbServer = opentsdbserver.MustStart(*opentsdbListenAddr, opentsdb.InsertHandler, httpInsertHandler)
}
if len(*opentsdbHTTPListenAddr) > 0 {
httpInsertHandler := getOpenTSDBHTTPInsertHandler()
opentsdbhttpServer = opentsdbhttpserver.MustStart(*opentsdbHTTPListenAddr, *opentsdbHTTPUseProxyProtocol, httpInsertHandler)
opentsdbhttpServer = opentsdbhttpserver.MustStart(*opentsdbHTTPListenAddr, httpInsertHandler)
}
promscrape.Init(remotewrite.Push)
if len(*httpListenAddr) > 0 {
go httpserver.Serve(*httpListenAddr, *useProxyProtocol, requestHandler)
go httpserver.Serve(*httpListenAddr, requestHandler)
}
logger.Infof("started vmagent in %.3f seconds", time.Since(startTime).Seconds())
@@ -213,7 +197,7 @@ func getAuthTokenFromPath(path string) (*auth.Token, error) {
func requestHandler(w http.ResponseWriter, r *http.Request) bool {
if r.URL.Path == "/" {
if r.Method != http.MethodGet {
if r.Method != "GET" {
return false
}
w.Header().Add("Content-Type", "text/html; charset=utf-8")
@@ -223,7 +207,6 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
httpserver.WriteAPIHelp(w, [][2]string{
{"targets", "status for discovered active targets"},
{"service-discovery", "labels before and after relabeling for discovered targets"},
{"metric-relabel-debug", "debug metric relabeling"},
{"api/v1/targets", "advanced information about discovered targets in JSON format"},
{"config", "-promscrape.config contents"},
{"metrics", "available service metrics"},
@@ -234,33 +217,13 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
}
path := strings.Replace(r.URL.Path, "//", "/", -1)
if strings.HasPrefix(path, "/prometheus/api/v1/import/prometheus") || strings.HasPrefix(path, "/api/v1/import/prometheus") {
prometheusimportRequests.Inc()
if err := prometheusimport.InsertHandler(nil, r); err != nil {
prometheusimportErrors.Inc()
httpserver.Errorf(w, r, "%s", err)
return true
}
statusCode := http.StatusNoContent
if strings.HasPrefix(path, "/prometheus/api/v1/import/prometheus/metrics/job/") ||
strings.HasPrefix(path, "/api/v1/import/prometheus/metrics/job/") {
// Return 200 status code for pushgateway requests.
// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3636
statusCode = http.StatusOK
}
w.WriteHeader(statusCode)
return true
}
if strings.HasPrefix(path, "datadog/") {
// Trim suffix from paths starting from /datadog/ in order to support legacy DataDog agent.
// See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/2670
path = strings.TrimSuffix(path, "/")
}
switch path {
case "/prometheus/api/v1/write", "/api/v1/write":
if common.HandleVMProtoServerHandshake(w, r) {
return true
}
case "/api/v1/write":
prometheusWriteRequests.Inc()
if err := promremotewrite.InsertHandler(nil, r); err != nil {
prometheusWriteErrors.Inc()
@@ -269,7 +232,7 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
}
w.WriteHeader(http.StatusNoContent)
return true
case "/prometheus/api/v1/import", "/api/v1/import":
case "/api/v1/import":
vmimportRequests.Inc()
if err := vmimport.InsertHandler(nil, r); err != nil {
vmimportErrors.Inc()
@@ -278,7 +241,7 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
}
w.WriteHeader(http.StatusNoContent)
return true
case "/prometheus/api/v1/import/csv", "/api/v1/import/csv":
case "/api/v1/import/csv":
csvimportRequests.Inc()
if err := csvimport.InsertHandler(nil, r); err != nil {
csvimportErrors.Inc()
@@ -287,7 +250,16 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
}
w.WriteHeader(http.StatusNoContent)
return true
case "/prometheus/api/v1/import/native", "/api/v1/import/native":
case "/api/v1/import/prometheus":
prometheusimportRequests.Inc()
if err := prometheusimport.InsertHandler(nil, r); err != nil {
prometheusimportErrors.Inc()
httpserver.Errorf(w, r, "%s", err)
return true
}
w.WriteHeader(http.StatusNoContent)
return true
case "/api/v1/import/native":
nativeimportRequests.Inc()
if err := native.InsertHandler(nil, r); err != nil {
nativeimportErrors.Inc()
@@ -296,7 +268,7 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
}
w.WriteHeader(http.StatusNoContent)
return true
case "/influx/write", "/influx/api/v2/write", "/write", "/api/v2/write":
case "/write", "/api/v2/write":
influxWriteRequests.Inc()
if err := influx.InsertHandlerForHTTP(nil, r); err != nil {
influxWriteErrors.Inc()
@@ -305,19 +277,10 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
}
w.WriteHeader(http.StatusNoContent)
return true
case "/influx/query", "/query":
case "/query":
influxQueryRequests.Inc()
influxutils.WriteDatabaseNames(w)
return true
case "/opentelemetry/api/v1/push":
opentelemetryPushRequests.Inc()
if err := opentelemetry.InsertHandler(nil, r); err != nil {
opentelemetryPushErrors.Inc()
httpserver.Errorf(w, r, "%s", err)
return true
}
w.WriteHeader(http.StatusOK)
return true
case "/datadog/api/v1/series":
datadogWriteRequests.Inc()
if err := datadog.InsertHandlerForHTTP(nil, r); err != nil {
@@ -353,29 +316,15 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
w.Header().Set("Content-Type", "application/json")
fmt.Fprintf(w, `{}`)
return true
case "/prometheus/targets", "/targets":
case "/targets":
promscrapeTargetsRequests.Inc()
promscrape.WriteHumanReadableTargetsStatus(w, r)
return true
case "/prometheus/service-discovery", "/service-discovery":
case "/service-discovery":
promscrapeServiceDiscoveryRequests.Inc()
promscrape.WriteServiceDiscovery(w, r)
return true
case "/prometheus/metric-relabel-debug", "/metric-relabel-debug":
promscrapeMetricRelabelDebugRequests.Inc()
promscrape.WriteMetricRelabelDebug(w, r)
return true
case "/prometheus/target-relabel-debug", "/target-relabel-debug":
promscrapeTargetRelabelDebugRequests.Inc()
promscrape.WriteTargetRelabelDebug(w, r)
return true
case "/prometheus/api/v1/targets", "/api/v1/targets":
promscrapeAPIV1TargetsRequests.Inc()
w.Header().Set("Content-Type", "application/json")
state := r.FormValue("state")
promscrape.WriteAPIV1Targets(w, state)
return true
case "/prometheus/target_response", "/target_response":
case "/target_response":
promscrapeTargetResponseRequests.Inc()
if err := promscrape.WriteTargetResponse(w, r); err != nil {
promscrapeTargetResponseErrors.Inc()
@@ -383,17 +332,27 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
return true
}
return true
case "/prometheus/config", "/config":
if !httpserver.CheckAuthFlag(w, r, *configAuthKey, "configAuthKey") {
case "/config":
if *configAuthKey != "" && r.FormValue("authKey") != *configAuthKey {
err := &httpserver.ErrorWithStatusCode{
Err: fmt.Errorf("The provided authKey doesn't match -configAuthKey"),
StatusCode: http.StatusUnauthorized,
}
httpserver.Errorf(w, r, "%s", err)
return true
}
promscrapeConfigRequests.Inc()
w.Header().Set("Content-Type", "text/plain; charset=utf-8")
promscrape.WriteConfigData(w)
return true
case "/prometheus/api/v1/status/config", "/api/v1/status/config":
case "/api/v1/status/config":
// See https://prometheus.io/docs/prometheus/latest/querying/api/#config
if !httpserver.CheckAuthFlag(w, r, *configAuthKey, "configAuthKey") {
if *configAuthKey != "" && r.FormValue("authKey") != *configAuthKey {
err := &httpserver.ErrorWithStatusCode{
Err: fmt.Errorf("The provided authKey doesn't match -configAuthKey"),
StatusCode: http.StatusUnauthorized,
}
httpserver.Errorf(w, r, "%s", err)
return true
}
promscrapeStatusConfigRequests.Inc()
@@ -402,7 +361,13 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
promscrape.WriteConfigData(&bb)
fmt.Fprintf(w, `{"status":"success","data":{"yaml":%q}}`, bb.B)
return true
case "/prometheus/-/reload", "/-/reload":
case "/api/v1/targets":
promscrapeAPIV1TargetsRequests.Inc()
w.Header().Set("Content-Type", "application/json")
state := r.FormValue("state")
promscrape.WriteAPIV1Targets(w, state)
return true
case "/-/reload":
promscrapeConfigReloadRequests.Inc()
procutil.SelfSIGHUP()
w.WriteHeader(http.StatusOK)
@@ -444,16 +409,6 @@ func processMultitenantRequest(w http.ResponseWriter, r *http.Request, path stri
httpserver.Errorf(w, r, "cannot obtain auth token: %s", err)
return true
}
if strings.HasPrefix(p.Suffix, "prometheus/api/v1/import/prometheus") {
prometheusimportRequests.Inc()
if err := prometheusimport.InsertHandler(at, r); err != nil {
prometheusimportErrors.Inc()
httpserver.Errorf(w, r, "%s", err)
return true
}
w.WriteHeader(http.StatusNoContent)
return true
}
if strings.HasPrefix(p.Suffix, "datadog/") {
// Trim suffix from paths starting from /datadog/ in order to support legacy DataDog agent.
// See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/2670
@@ -487,6 +442,15 @@ func processMultitenantRequest(w http.ResponseWriter, r *http.Request, path stri
}
w.WriteHeader(http.StatusNoContent)
return true
case "prometheus/api/v1/import/prometheus":
prometheusimportRequests.Inc()
if err := prometheusimport.InsertHandler(at, r); err != nil {
prometheusimportErrors.Inc()
httpserver.Errorf(w, r, "%s", err)
return true
}
w.WriteHeader(http.StatusNoContent)
return true
case "prometheus/api/v1/import/native":
nativeimportRequests.Inc()
if err := native.InsertHandler(at, r); err != nil {
@@ -509,15 +473,6 @@ func processMultitenantRequest(w http.ResponseWriter, r *http.Request, path stri
influxQueryRequests.Inc()
influxutils.WriteDatabaseNames(w)
return true
case "opentelemetry/api/v1/push":
opentelemetryPushRequests.Inc()
if err := opentelemetry.InsertHandler(at, r); err != nil {
opentelemetryPushErrors.Inc()
httpserver.Errorf(w, r, "%s", err)
return true
}
w.WriteHeader(http.StatusOK)
return true
case "datadog/api/v1/series":
datadogWriteRequests.Inc()
if err := datadog.InsertHandlerForHTTP(at, r); err != nil {
@@ -587,16 +542,9 @@ var (
datadogIntakeRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/datadog/intake", protocol="datadog"}`)
datadogMetadataRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/datadog/api/v1/metadata", protocol="datadog"}`)
opentelemetryPushRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/opentelemetry/api/v1/push", protocol="opentelemetry"}`)
opentelemetryPushErrors = metrics.NewCounter(`vmagent_http_request_errors_total{path="/opentelemetry/api/v1/push", protocol="opentelemetry"}`)
promscrapeTargetsRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/targets"}`)
promscrapeServiceDiscoveryRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/service-discovery"}`)
promscrapeMetricRelabelDebugRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/metric-relabel-debug"}`)
promscrapeTargetRelabelDebugRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/target-relabel-debug"}`)
promscrapeAPIV1TargetsRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/api/v1/targets"}`)
promscrapeAPIV1TargetsRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/api/v1/targets"}`)
promscrapeTargetResponseRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/target_response"}`)
promscrapeTargetResponseErrors = metrics.NewCounter(`vmagent_http_request_errors_total{path="/target_response"}`)

View File

@@ -2,7 +2,7 @@
ARG certs_image
ARG root_image
FROM $certs_image as certs
RUN apk update && apk upgrade && apk --update --no-cache add ca-certificates
RUN apk --update --no-cache add ca-certificates
FROM $root_image
COPY --from=certs /etc/ssl/certs/ca-certificates.crt /etc/ssl/certs/ca-certificates.crt

View File

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

View File

@@ -1,65 +0,0 @@
package opentelemetry
import (
"net/http"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/common"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
parserCommon "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/opentelemetry/stream"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
"github.com/VictoriaMetrics/metrics"
)
var (
rowsInserted = metrics.NewCounter(`vmagent_rows_inserted_total{type="opentelemetry"}`)
rowsTenantInserted = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_rows_total{type="opentelemetry"}`)
rowsPerInsert = metrics.NewHistogram(`vmagent_rows_per_insert{type="opentelemetry"}`)
)
// InsertHandler processes opentelemetry metrics.
func InsertHandler(at *auth.Token, req *http.Request) error {
extraLabels, err := parserCommon.GetExtraLabels(req)
if err != nil {
return err
}
isGzipped := req.Header.Get("Content-Encoding") == "gzip"
return stream.ParseStream(req.Body, isGzipped, func(tss []prompbmarshal.TimeSeries) error {
return insertRows(at, tss, extraLabels)
})
}
func insertRows(at *auth.Token, tss []prompbmarshal.TimeSeries, extraLabels []prompbmarshal.Label) error {
ctx := common.GetPushCtx()
defer common.PutPushCtx(ctx)
rowsTotal := 0
tssDst := ctx.WriteRequest.Timeseries[:0]
labels := ctx.Labels[:0]
samples := ctx.Samples[:0]
for i := range tss {
ts := &tss[i]
rowsTotal += len(ts.Samples)
labelsLen := len(labels)
labels = append(labels, ts.Labels...)
labels = append(labels, extraLabels...)
samplesLen := len(samples)
samples = append(samples, ts.Samples...)
tssDst = append(tssDst, prompbmarshal.TimeSeries{
Labels: labels[labelsLen:],
Samples: samples[samplesLen:],
})
}
ctx.WriteRequest.Timeseries = tssDst
ctx.Labels = labels
ctx.Samples = samples
remotewrite.Push(at, &ctx.WriteRequest)
rowsInserted.Add(rowsTotal)
if at != nil {
rowsTenantInserted.Get(at).Add(rowsTotal)
}
rowsPerInsert.Update(float64(rowsTotal))
return nil
}

View File

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

View File

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

View File

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

View File

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

View File

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

View File

@@ -15,72 +15,62 @@ import (
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/persistentqueue"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promauth"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/timerpool"
"github.com/VictoriaMetrics/metrics"
)
var (
forcePromProto = flagutil.NewArrayBool("remoteWrite.forcePromProto", "Whether to force Prometheus remote write protocol for sending data "+
"to the corresponding -remoteWrite.url . See https://docs.victoriametrics.com/vmagent.html#victoriametrics-remote-write-protocol")
forceVMProto = flagutil.NewArrayBool("remoteWrite.forceVMProto", "Whether to force VictoriaMetrics remote write protocol for sending data "+
"to the corresponding -remoteWrite.url . See https://docs.victoriametrics.com/vmagent.html#victoriametrics-remote-write-protocol")
rateLimit = flagutil.NewArrayInt("remoteWrite.rateLimit", "Optional rate limit in bytes per second for data sent to the corresponding -remoteWrite.url. "+
"By default, the rate limit is disabled. It can be useful for limiting load on remote storage when big amounts of buffered data "+
"By default the rate limit is disabled. It can be useful for limiting load on remote storage when big amounts of buffered data "+
"is sent after temporary unavailability of the remote storage")
sendTimeout = flagutil.NewArrayDuration("remoteWrite.sendTimeout", "Timeout for sending a single block of data to the corresponding -remoteWrite.url (default 1m)")
proxyURL = flagutil.NewArrayString("remoteWrite.proxyURL", "Optional proxy URL for writing data to the corresponding -remoteWrite.url. "+
sendTimeout = flagutil.NewArrayDuration("remoteWrite.sendTimeout", "Timeout for sending a single block of data to the corresponding -remoteWrite.url")
proxyURL = flagutil.NewArray("remoteWrite.proxyURL", "Optional proxy URL for writing data to the corresponding -remoteWrite.url. "+
"Supported proxies: http, https, socks5. Example: -remoteWrite.proxyURL=socks5://proxy:1234")
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 "+
tlsCertFile = flagutil.NewArray("remoteWrite.tlsCertFile", "Optional path to client-side TLS certificate file to use when connecting "+
"to the corresponding -remoteWrite.url")
tlsKeyFile = flagutil.NewArrayString("remoteWrite.tlsKeyFile", "Optional path to client-side TLS certificate key to use when connecting to the corresponding -remoteWrite.url")
tlsCAFile = flagutil.NewArrayString("remoteWrite.tlsCAFile", "Optional path to TLS CA file to use for verifying connections to the corresponding -remoteWrite.url. "+
"By default, system CA is used")
tlsServerName = flagutil.NewArrayString("remoteWrite.tlsServerName", "Optional TLS server name to use for connections to the corresponding -remoteWrite.url. "+
"By default, the server name from -remoteWrite.url is used")
tlsKeyFile = flagutil.NewArray("remoteWrite.tlsKeyFile", "Optional path to client-side TLS certificate key to use when connecting to the corresponding -remoteWrite.url")
tlsCAFile = flagutil.NewArray("remoteWrite.tlsCAFile", "Optional path to TLS CA file to use for verifying connections to the corresponding -remoteWrite.url. "+
"By default system CA is used")
tlsServerName = flagutil.NewArray("remoteWrite.tlsServerName", "Optional TLS server name to use for connections to the corresponding -remoteWrite.url. "+
"By default the server name from -remoteWrite.url is used")
headers = flagutil.NewArrayString("remoteWrite.headers", "Optional HTTP headers to send with each request to the corresponding -remoteWrite.url. "+
headers = flagutil.NewArray("remoteWrite.headers", "Optional HTTP headers to send with each request to the corresponding -remoteWrite.url. "+
"For example, -remoteWrite.headers='My-Auth:foobar' would send 'My-Auth: foobar' HTTP header with every request to the corresponding -remoteWrite.url. "+
"Multiple headers must be delimited by '^^': -remoteWrite.headers='header1:value1^^header2:value2'")
basicAuthUsername = flagutil.NewArrayString("remoteWrite.basicAuth.username", "Optional basic auth username to use for the corresponding -remoteWrite.url")
basicAuthPassword = flagutil.NewArrayString("remoteWrite.basicAuth.password", "Optional basic auth password to use for the corresponding -remoteWrite.url")
basicAuthPasswordFile = flagutil.NewArrayString("remoteWrite.basicAuth.passwordFile", "Optional path to basic auth password to use for the corresponding -remoteWrite.url. "+
basicAuthUsername = flagutil.NewArray("remoteWrite.basicAuth.username", "Optional basic auth username to use for the corresponding -remoteWrite.url")
basicAuthPassword = flagutil.NewArray("remoteWrite.basicAuth.password", "Optional basic auth password to use for the corresponding -remoteWrite.url")
basicAuthPasswordFile = flagutil.NewArray("remoteWrite.basicAuth.passwordFile", "Optional path to basic auth password to use for the corresponding -remoteWrite.url. "+
"The file is re-read every second")
bearerToken = flagutil.NewArrayString("remoteWrite.bearerToken", "Optional bearer auth token to use for the corresponding -remoteWrite.url")
bearerTokenFile = flagutil.NewArrayString("remoteWrite.bearerTokenFile", "Optional path to bearer token file to use for the corresponding -remoteWrite.url. "+
bearerToken = flagutil.NewArray("remoteWrite.bearerToken", "Optional bearer auth token to use for the corresponding -remoteWrite.url")
bearerTokenFile = flagutil.NewArray("remoteWrite.bearerTokenFile", "Optional path to bearer token file to use for the corresponding -remoteWrite.url. "+
"The token is re-read from the file every second")
oauth2ClientID = flagutil.NewArrayString("remoteWrite.oauth2.clientID", "Optional OAuth2 clientID to use for the corresponding -remoteWrite.url")
oauth2ClientSecret = flagutil.NewArrayString("remoteWrite.oauth2.clientSecret", "Optional OAuth2 clientSecret to use for the corresponding -remoteWrite.url")
oauth2ClientSecretFile = flagutil.NewArrayString("remoteWrite.oauth2.clientSecretFile", "Optional OAuth2 clientSecretFile to use for the corresponding -remoteWrite.url")
oauth2TokenURL = flagutil.NewArrayString("remoteWrite.oauth2.tokenUrl", "Optional OAuth2 tokenURL to use for the corresponding -remoteWrite.url")
oauth2Scopes = flagutil.NewArrayString("remoteWrite.oauth2.scopes", "Optional OAuth2 scopes to use for the corresponding -remoteWrite.url. Scopes must be delimited by ';'")
oauth2ClientID = flagutil.NewArray("remoteWrite.oauth2.clientID", "Optional OAuth2 clientID to use for the corresponding -remoteWrite.url")
oauth2ClientSecret = flagutil.NewArray("remoteWrite.oauth2.clientSecret", "Optional OAuth2 clientSecret to use for the corresponding -remoteWrite.url")
oauth2ClientSecretFile = flagutil.NewArray("remoteWrite.oauth2.clientSecretFile", "Optional OAuth2 clientSecretFile to use for the corresponding -remoteWrite.url")
oauth2TokenURL = flagutil.NewArray("remoteWrite.oauth2.tokenUrl", "Optional OAuth2 tokenURL to use for the corresponding -remoteWrite.url")
oauth2Scopes = flagutil.NewArray("remoteWrite.oauth2.scopes", "Optional OAuth2 scopes to use for the corresponding -remoteWrite.url. Scopes must be delimited by ';'")
awsUseSigv4 = flagutil.NewArrayBool("remoteWrite.aws.useSigv4", "Enables SigV4 request signing for the corresponding -remoteWrite.url. "+
"It is expected that other -remoteWrite.aws.* command-line flags are set if sigv4 request signing is enabled")
awsEC2Endpoint = flagutil.NewArrayString("remoteWrite.aws.ec2Endpoint", "Optional AWS EC2 API endpoint to use for the corresponding -remoteWrite.url if -remoteWrite.aws.useSigv4 is set")
awsSTSEndpoint = flagutil.NewArrayString("remoteWrite.aws.stsEndpoint", "Optional AWS STS API endpoint to use for the corresponding -remoteWrite.url if -remoteWrite.aws.useSigv4 is set")
awsRegion = flagutil.NewArrayString("remoteWrite.aws.region", "Optional AWS region to use for the corresponding -remoteWrite.url if -remoteWrite.aws.useSigv4 is set")
awsRoleARN = flagutil.NewArrayString("remoteWrite.aws.roleARN", "Optional AWS roleARN to use for the corresponding -remoteWrite.url if -remoteWrite.aws.useSigv4 is set")
awsAccessKey = flagutil.NewArrayString("remoteWrite.aws.accessKey", "Optional AWS AccessKey to use for the corresponding -remoteWrite.url if -remoteWrite.aws.useSigv4 is set")
awsService = flagutil.NewArrayString("remoteWrite.aws.service", "Optional AWS Service to use for the corresponding -remoteWrite.url if -remoteWrite.aws.useSigv4 is set. "+
awsEC2Endpoint = flagutil.NewArray("remoteWrite.aws.ec2Endpoint", "Optional AWS EC2 API endpoint to use for the corresponding -remoteWrite.url if -remoteWrite.aws.useSigv4 is set")
awsSTSEndpoint = flagutil.NewArray("remoteWrite.aws.stsEndpoint", "Optional AWS STS API endpoint to use for the corresponding -remoteWrite.url if -remoteWrite.aws.useSigv4 is set")
awsRegion = flagutil.NewArray("remoteWrite.aws.region", "Optional AWS region to use for the corresponding -remoteWrite.url if -remoteWrite.aws.useSigv4 is set")
awsRoleARN = flagutil.NewArray("remoteWrite.aws.roleARN", "Optional AWS roleARN to use for the corresponding -remoteWrite.url if -remoteWrite.aws.useSigv4 is set")
awsAccessKey = flagutil.NewArray("remoteWrite.aws.accessKey", "Optional AWS AccessKey to use for the corresponding -remoteWrite.url if -remoteWrite.aws.useSigv4 is set")
awsService = flagutil.NewArray("remoteWrite.aws.service", "Optional AWS Service to use for the corresponding -remoteWrite.url if -remoteWrite.aws.useSigv4 is set. "+
"Defaults to \"aps\"")
awsSecretKey = flagutil.NewArrayString("remoteWrite.aws.secretKey", "Optional AWS SecretKey to use for the corresponding -remoteWrite.url if -remoteWrite.aws.useSigv4 is set")
awsSecretKey = flagutil.NewArray("remoteWrite.aws.secretKey", "Optional AWS SecretKey to use for the corresponding -remoteWrite.url if -remoteWrite.aws.useSigv4 is set")
)
type client struct {
sanitizedURL string
remoteWriteURL string
// Whether to use VictoriaMetrics remote write protocol for sending the data to remoteWriteURL
useVMProto bool
fq *persistentqueue.FastQueue
hc *http.Client
fq *persistentqueue.FastQueue
hc *http.Client
sendBlock func(block []byte) bool
authCfg *promauth.Config
@@ -132,39 +122,19 @@ func newHTTPClient(argIdx int, remoteWriteURL, sanitizedURL string, fq *persiste
}
tr.Proxy = http.ProxyURL(pu)
}
hc := &http.Client{
Transport: tr,
Timeout: sendTimeout.GetOptionalArgOrDefault(argIdx, time.Minute),
}
c := &client{
sanitizedURL: sanitizedURL,
remoteWriteURL: remoteWriteURL,
authCfg: authCfg,
awsCfg: awsCfg,
fq: fq,
hc: hc,
stopCh: make(chan struct{}),
hc: &http.Client{
Transport: tr,
Timeout: sendTimeout.GetOptionalArgOrDefault(argIdx, time.Minute),
},
stopCh: make(chan struct{}),
}
c.sendBlock = c.sendBlockHTTP
useVMProto := forceVMProto.GetOptionalArg(argIdx)
usePromProto := forcePromProto.GetOptionalArg(argIdx)
if useVMProto && usePromProto {
logger.Fatalf("-remoteWrite.useVMProto and -remoteWrite.usePromProto cannot be set simultaneously for -remoteWrite.url=%s", sanitizedURL)
}
if !useVMProto && !usePromProto {
// Auto-detect whether the remote storage supports VictoriaMetrics remote write protocol.
doRequest := func(url string) (*http.Response, error) {
return c.doRequest(url, nil)
}
useVMProto = common.HandleVMProtoClientHandshake(c.remoteWriteURL, doRequest)
if !useVMProto {
logger.Infof("the remote storage at %q doesn't support VictoriaMetrics remote write protocol. Switching to Prometheus remote write protocol. "+
"See https://docs.victoriametrics.com/vmagent.html#victoriametrics-remote-write-protocol", sanitizedURL)
}
}
c.useVMProto = useVMProto
return c
}
@@ -257,7 +227,7 @@ func getAuthConfig(argIdx int) (*promauth.Config, error) {
}
authCfg, err := opts.NewConfig()
if err != nil {
return nil, fmt.Errorf("cannot populate auth config for remoteWrite idx: %d, err: %w", argIdx, err)
return nil, fmt.Errorf("cannot populate OAuth2 config for remoteWrite idx: %d, err: %w", argIdx, err)
}
return authCfg, nil
}
@@ -321,45 +291,38 @@ func (c *client) runWorker() {
}
}
func (c *client) doRequest(url string, body []byte) (*http.Response, error) {
reqBody := bytes.NewBuffer(body)
req, err := http.NewRequest(http.MethodPost, url, reqBody)
if err != nil {
logger.Panicf("BUG: unexpected error from http.NewRequest(%q): %s", url, err)
}
c.authCfg.SetHeaders(req, true)
h := req.Header
h.Set("User-Agent", "vmagent")
h.Set("Content-Type", "application/x-protobuf")
if c.useVMProto {
h.Set("Content-Encoding", "zstd")
h.Set("X-VictoriaMetrics-Remote-Write-Version", "1")
} else {
h.Set("Content-Encoding", "snappy")
h.Set("X-Prometheus-Remote-Write-Version", "0.1.0")
}
if c.awsCfg != nil {
sigv4Hash := awsapi.HashHex(body)
if err := c.awsCfg.SignRequest(req, sigv4Hash); err != nil {
// there is no need in retry, request will be rejected by client.Do and retried by code below
logger.Warnf("cannot sign remoteWrite request with AWS sigv4: %s", err)
}
}
return c.hc.Do(req)
}
// sendBlockHTTP sends the given block to c.remoteWriteURL.
//
// The function returns false only if c.stopCh is closed.
// sendBlockHTTP returns false only if c.stopCh is closed.
// Otherwise it tries sending the block to remote storage indefinitely.
func (c *client) sendBlockHTTP(block []byte) bool {
c.rl.register(len(block), c.stopCh)
retryDuration := time.Second
retriesCount := 0
c.bytesSent.Add(len(block))
c.blocksSent.Inc()
sigv4Hash := ""
if c.awsCfg != nil {
sigv4Hash = awsapi.HashHex(block)
}
again:
req, err := http.NewRequest("POST", c.remoteWriteURL, bytes.NewBuffer(block))
if err != nil {
logger.Panicf("BUG: unexpected error from http.NewRequest(%q): %s", c.sanitizedURL, err)
}
c.authCfg.SetHeaders(req, true)
h := req.Header
h.Set("User-Agent", "vmagent")
h.Set("Content-Type", "application/x-protobuf")
h.Set("Content-Encoding", "snappy")
h.Set("X-Prometheus-Remote-Write-Version", "0.1.0")
if c.awsCfg != nil {
if err := c.awsCfg.SignRequest(req, sigv4Hash); err != nil {
// there is no need in retry, request will be rejected by client.Do and retried by code below
logger.Warnf("cannot sign remoteWrite request with AWS sigv4: %s", err)
}
}
startTime := time.Now()
resp, err := c.doRequest(c.remoteWriteURL, block)
resp, err := c.hc.Do(req)
c.requestDuration.UpdateDuration(startTime)
if err != nil {
c.errorsCount.Inc()
@@ -384,8 +347,6 @@ again:
if statusCode/100 == 2 {
_ = resp.Body.Close()
c.requestsOKCount.Inc()
c.bytesSent.Add(len(block))
c.blocksSent.Inc()
return true
}
metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_requests_total{url=%q, status_code="%d"}`, c.sanitizedURL, statusCode)).Inc()

View File

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

View File

@@ -1,70 +0,0 @@
package remotewrite
import (
"fmt"
"math"
"testing"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
)
func TestPushWriteRequest(t *testing.T) {
rowsCounts := []int{1, 10, 100, 1e3, 1e4}
expectedBlockLensProm := []int{216, 1848, 16424, 169882, 1757876}
expectedBlockLensVM := []int{138, 492, 3927, 34995, 288476}
for i, rowsCount := range rowsCounts {
expectedBlockLenProm := expectedBlockLensProm[i]
expectedBlockLenVM := expectedBlockLensVM[i]
t.Run(fmt.Sprintf("%d", rowsCount), func(t *testing.T) {
testPushWriteRequest(t, rowsCount, expectedBlockLenProm, expectedBlockLenVM)
})
}
}
func testPushWriteRequest(t *testing.T, rowsCount, expectedBlockLenProm, expectedBlockLenVM int) {
f := func(isVMRemoteWrite bool, expectedBlockLen int, tolerancePrc float64) {
t.Helper()
wr := newTestWriteRequest(rowsCount, 20)
pushBlockLen := 0
pushBlock := func(block []byte) {
if pushBlockLen > 0 {
panic(fmt.Errorf("BUG: pushBlock called multiple times; pushBlockLen=%d at first call, len(block)=%d at second call", pushBlockLen, len(block)))
}
pushBlockLen = len(block)
}
pushWriteRequest(wr, pushBlock, isVMRemoteWrite)
if math.Abs(float64(pushBlockLen-expectedBlockLen)/float64(expectedBlockLen)*100) > tolerancePrc {
t.Fatalf("unexpected block len for rowsCount=%d, isVMRemoteWrite=%v; got %d bytes; expecting %d bytes +- %.0f%%",
rowsCount, isVMRemoteWrite, pushBlockLen, expectedBlockLen, tolerancePrc)
}
}
// Check Prometheus remote write
f(false, expectedBlockLenProm, 0)
// Check VictoriaMetrics remote write
f(true, expectedBlockLenVM, 15)
}
func newTestWriteRequest(seriesCount, labelsCount int) *prompbmarshal.WriteRequest {
var wr prompbmarshal.WriteRequest
for i := 0; i < seriesCount; i++ {
var labels []prompbmarshal.Label
for j := 0; j < labelsCount; j++ {
labels = append(labels, prompbmarshal.Label{
Name: fmt.Sprintf("label_%d_%d", i, j),
Value: fmt.Sprintf("value_%d_%d", i, j),
})
}
wr.Timeseries = append(wr.Timeseries, prompbmarshal.TimeSeries{
Labels: labels,
Samples: []prompbmarshal.Sample{
{
Value: float64(i),
Timestamp: 1000 * int64(i),
},
},
})
}
return &wr
}

View File

@@ -1,36 +0,0 @@
package remotewrite
import (
"fmt"
"testing"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
"github.com/golang/snappy"
"github.com/klauspost/compress/s2"
)
func BenchmarkCompressWriteRequestSnappy(b *testing.B) {
b.Run("snappy", func(b *testing.B) {
benchmarkCompressWriteRequest(b, snappy.Encode)
})
b.Run("s2", func(b *testing.B) {
benchmarkCompressWriteRequest(b, s2.EncodeSnappy)
})
}
func benchmarkCompressWriteRequest(b *testing.B, compressFunc func(dst, src []byte) []byte) {
for _, rowsCount := range []int{1, 10, 100, 1e3, 1e4} {
b.Run(fmt.Sprintf("rows_%d", rowsCount), func(b *testing.B) {
wr := newTestWriteRequest(rowsCount, 10)
data := prompbmarshal.MarshalWriteRequest(nil, wr)
b.ReportAllocs()
b.SetBytes(int64(rowsCount))
b.RunParallel(func(pb *testing.PB) {
var zb []byte
for pb.Next() {
zb = compressFunc(zb[:cap(zb)], data)
}
})
})
}
}

View File

@@ -13,19 +13,18 @@ import (
)
var (
unparsedLabelsGlobal = flagutil.NewArrayString("remoteWrite.label", "Optional label in the form 'name=value' to add to all the metrics before sending them to -remoteWrite.url. "+
unparsedLabelsGlobal = flagutil.NewArray("remoteWrite.label", "Optional label in the form 'name=value' to add to all the metrics before sending them to -remoteWrite.url. "+
"Pass multiple -remoteWrite.label flags in order to add multiple labels to metrics before sending them to remote storage")
relabelConfigPathGlobal = flag.String("remoteWrite.relabelConfig", "", "Optional path to file with relabeling configs, which are applied "+
"to all the metrics before sending them to -remoteWrite.url. See also -remoteWrite.urlRelabelConfig. "+
"The path can point either to local file or to http url. "+
"See https://docs.victoriametrics.com/vmagent.html#relabeling")
relabelConfigPaths = flagutil.NewArrayString("remoteWrite.urlRelabelConfig", "Optional path to relabel configs for the corresponding -remoteWrite.url. "+
"See also -remoteWrite.relabelConfig. The path can point either to local file or to http url. "+
"See https://docs.victoriametrics.com/vmagent.html#relabeling")
usePromCompatibleNaming = flag.Bool("usePromCompatibleNaming", false, "Whether to replace characters unsupported by Prometheus with underscores "+
"in the ingested metric names and label names. For example, foo.bar{a.b='c'} is transformed into foo_bar{a_b='c'} during data ingestion if this flag is set. "+
"See https://prometheus.io/docs/concepts/data_model/#metric-names-and-labels")
relabelConfigPathGlobal = flag.String("remoteWrite.relabelConfig", "", "Optional path to file with relabel_config entries. "+
"The path can point either to local file or to http url. These entries are applied to all the metrics "+
"before sending them to -remoteWrite.url. See https://docs.victoriametrics.com/vmagent.html#relabeling for details")
relabelDebugGlobal = flag.Bool("remoteWrite.relabelDebug", false, "Whether to log metrics before and after relabeling with -remoteWrite.relabelConfig. "+
"If the -remoteWrite.relabelDebug is enabled, then the metrics aren't sent to remote storage. This is useful for debugging the relabeling configs")
relabelConfigPaths = flagutil.NewArray("remoteWrite.urlRelabelConfig", "Optional path to relabel config for the corresponding -remoteWrite.url. "+
"The path can point either to local file or to http url")
relabelDebug = flagutil.NewArrayBool("remoteWrite.urlRelabelDebug", "Whether to log metrics before and after relabeling with -remoteWrite.urlRelabelConfig. "+
"If the -remoteWrite.urlRelabelDebug is enabled, then the metrics aren't sent to the corresponding -remoteWrite.url. "+
"This is useful for debugging the relabeling configs")
)
var labelsGlobal []prompbmarshal.Label
@@ -39,7 +38,7 @@ func CheckRelabelConfigs() error {
func loadRelabelConfigs() (*relabelConfigs, error) {
var rcs relabelConfigs
if *relabelConfigPathGlobal != "" {
global, err := promrelabel.LoadRelabelConfigs(*relabelConfigPathGlobal)
global, err := promrelabel.LoadRelabelConfigs(*relabelConfigPathGlobal, *relabelDebugGlobal)
if err != nil {
return nil, fmt.Errorf("cannot load -remoteWrite.relabelConfig=%q: %w", *relabelConfigPathGlobal, err)
}
@@ -55,7 +54,7 @@ func loadRelabelConfigs() (*relabelConfigs, error) {
// Skip empty relabel config.
continue
}
prc, err := promrelabel.LoadRelabelConfigs(path)
prc, err := promrelabel.LoadRelabelConfigs(path, relabelDebug.GetOptionalArg(i))
if err != nil {
return nil, fmt.Errorf("cannot load relabel configs from -remoteWrite.urlRelabelConfig=%q: %w", path, err)
}
@@ -88,7 +87,7 @@ func initLabelsGlobal() {
}
func (rctx *relabelCtx) applyRelabeling(tss []prompbmarshal.TimeSeries, extraLabels []prompbmarshal.Label, pcs *promrelabel.ParsedConfigs) []prompbmarshal.TimeSeries {
if len(extraLabels) == 0 && pcs.Len() == 0 && !*usePromCompatibleNaming {
if len(extraLabels) == 0 && pcs.Len() == 0 {
// Nothing to change.
return tss
}
@@ -108,20 +107,7 @@ func (rctx *relabelCtx) applyRelabeling(tss []prompbmarshal.TimeSeries, extraLab
labels = append(labels, *extraLabel)
}
}
if *usePromCompatibleNaming {
// Replace unsupported Prometheus chars in label names and metric names with underscores.
tmpLabels := labels[labelsLen:]
for j := range tmpLabels {
label := &tmpLabels[j]
if label.Name == "__name__" {
label.Value = promrelabel.SanitizeName(label.Value)
} else {
label.Name = promrelabel.SanitizeName(label.Name)
}
}
}
labels = pcs.Apply(labels, labelsLen)
labels = promrelabel.FinalizeLabels(labels[:labelsLen], labels[labelsLen:])
labels = pcs.Apply(labels, labelsLen, true)
if len(labels) == labelsLen {
// Drop the current time series, since relabeling removed all the labels.
continue

View File

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

View File

@@ -4,61 +4,50 @@ import (
"flag"
"fmt"
"net/url"
"path/filepath"
"strconv"
"sync"
"sync/atomic"
"time"
"github.com/cespare/xxhash/v2"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/bloomfilter"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/cgroup"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/fasttime"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/fs"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/memory"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/persistentqueue"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/procutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/streamaggr"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
"github.com/VictoriaMetrics/metrics"
"github.com/cespare/xxhash/v2"
)
var (
remoteWriteURLs = flagutil.NewArrayString("remoteWrite.url", "Remote storage URL to write data to. It must support either VictoriaMetrics remote write protocol "+
"or Prometheus remote_write protocol. Example url: http://<victoriametrics-host>:8428/api/v1/write . "+
"Pass multiple -remoteWrite.url options in order to replicate the collected data to multiple remote storage systems. "+
"The data can be sharded among the configured remote storage systems if -remoteWrite.shardByURL flag is set. "+
"See also -remoteWrite.multitenantURL")
remoteWriteMultitenantURLs = flagutil.NewArrayString("remoteWrite.multitenantURL", "Base path for multitenant remote storage URL to write data to. "+
remoteWriteURLs = flagutil.NewArray("remoteWrite.url", "Remote storage URL to write data to. It must support Prometheus remote_write API. "+
"It is recommended using VictoriaMetrics as remote storage. Example url: http://<victoriametrics-host>:8428/api/v1/write . "+
"Pass multiple -remoteWrite.url flags in order to replicate data to multiple remote storage systems. See also -remoteWrite.multitenantURL")
remoteWriteMultitenantURLs = flagutil.NewArray("remoteWrite.multitenantURL", "Base path for multitenant remote storage URL to write data to. "+
"See https://docs.victoriametrics.com/vmagent.html#multitenancy for details. Example url: http://<vminsert>:8480 . "+
"Pass multiple -remoteWrite.multitenantURL flags in order to replicate data to multiple remote storage systems. See also -remoteWrite.url")
shardByURL = flag.Bool("remoteWrite.shardByURL", false, "Whether to shard outgoing series across all the remote storage systems enumerated via -remoteWrite.url . "+
"By default the data is replicated across all the -remoteWrite.url . See https://docs.victoriametrics.com/vmagent.html#sharding-among-remote-storages")
tmpDataPath = flag.String("remoteWrite.tmpDataPath", "vmagent-remotewrite-data", "Path to directory where temporary data for remote write component is stored. "+
"See also -remoteWrite.maxDiskUsagePerURL")
keepDanglingQueues = flag.Bool("remoteWrite.keepDanglingQueues", false, "Keep persistent queues contents at -remoteWrite.tmpDataPath in case there are no matching -remoteWrite.url. "+
"Useful when -remoteWrite.url is changed temporarily and persistent queue files will be needed later on.")
queues = flag.Int("remoteWrite.queues", cgroup.AvailableCPUs()*2, "The number of concurrent queues to each -remoteWrite.url. Set more queues if default number of queues "+
"isn't enough for sending high volume of collected data to remote storage. Default value is 2 * numberOfAvailableCPUs")
showRemoteWriteURL = flag.Bool("remoteWrite.showURL", false, "Whether to show -remoteWrite.url in the exported metrics. "+
"It is hidden by default, since it can contain sensitive info such as auth key")
maxPendingBytesPerURL = flagutil.NewArrayBytes("remoteWrite.maxDiskUsagePerURL", "The maximum file-based buffer size in bytes at -remoteWrite.tmpDataPath "+
maxPendingBytesPerURL = flagutil.NewBytes("remoteWrite.maxDiskUsagePerURL", 0, "The maximum file-based buffer size in bytes at -remoteWrite.tmpDataPath "+
"for each -remoteWrite.url. When buffer size reaches the configured maximum, then old data is dropped when adding new data to the buffer. "+
"Buffered data is stored in ~500MB chunks. It is recommended to set the value for this flag to a multiple of the block size 500MB. "+
"Buffered data is stored in ~500MB chunks, so the minimum practical value for this flag is 500MB. "+
"Disk usage is unlimited if the value is set to 0")
significantFigures = flagutil.NewArrayInt("remoteWrite.significantFigures", "The number of significant figures to leave in metric values before writing them "+
"to remote storage. See https://en.wikipedia.org/wiki/Significant_figures . Zero value saves all the significant figures. "+
"This option may be used for improving data compression for the stored metrics. See also -remoteWrite.roundDigits")
roundDigits = flagutil.NewArrayInt("remoteWrite.roundDigits", "Round metric values to this number of decimal digits after the point before writing them to remote storage. "+
"Examples: -remoteWrite.roundDigits=2 would round 1.236 to 1.24, while -remoteWrite.roundDigits=-1 would round 126.78 to 130. "+
"By default, digits rounding is disabled. Set it to 100 for disabling it for a particular remote storage. "+
"By default digits rounding is disabled. Set it to 100 for disabling it for a particular remote storage. "+
"This option may be used for improving data compression for the stored metrics")
sortLabels = flag.Bool("sortLabels", false, `Whether to sort labels for incoming samples before writing them to all the configured remote storage systems. `+
`This may be needed for reducing memory usage at remote storage when the order of labels in incoming samples is random. `+
@@ -68,18 +57,6 @@ var (
"Excess series are logged and dropped. This can be useful for limiting series cardinality. See https://docs.victoriametrics.com/vmagent.html#cardinality-limiter")
maxDailySeries = flag.Int("remoteWrite.maxDailySeries", 0, "The maximum number of unique series vmagent can send to remote storage systems during the last 24 hours. "+
"Excess series are logged and dropped. This can be useful for limiting series churn rate. See https://docs.victoriametrics.com/vmagent.html#cardinality-limiter")
streamAggrConfig = flagutil.NewArrayString("remoteWrite.streamAggr.config", "Optional path to file with stream aggregation config. "+
"See https://docs.victoriametrics.com/stream-aggregation.html . "+
"See also -remoteWrite.streamAggr.keepInput, -remoteWrite.streamAggr.dropInput and -remoteWrite.streamAggr.dedupInterval")
streamAggrKeepInput = flagutil.NewArrayBool("remoteWrite.streamAggr.keepInput", "Whether to keep all the input samples after the aggregation "+
"with -remoteWrite.streamAggr.config. By default, only aggregates samples are dropped, while the remaining samples "+
"are written to the corresponding -remoteWrite.url . See also -remoteWrite.streamAggr.dropInput and https://docs.victoriametrics.com/stream-aggregation.html")
streamAggrDropInput = flagutil.NewArrayBool("remoteWrite.streamAggr.dropInput", "Whether to drop all the input samples after the aggregation "+
"with -remoteWrite.streamAggr.config. By default, only aggregates samples are dropped, while the remaining samples "+
"are written to the corresponding -remoteWrite.url . See also -remoteWrite.streamAggr.keepInput and https://docs.victoriametrics.com/stream-aggregation.html")
streamAggrDedupInterval = flagutil.NewArrayDuration("remoteWrite.streamAggr.dedupInterval", "Input samples are de-duplicated with this interval before being aggregated. "+
"Only the last sample per each time series per each interval is aggregated if the interval is greater than zero")
)
var (
@@ -100,14 +77,12 @@ func MultitenancyEnabled() bool {
}
// Contains the current relabelConfigs.
var allRelabelConfigs atomic.Pointer[relabelConfigs]
var allRelabelConfigs atomic.Value
// maxQueues limits the maximum value for `-remoteWrite.queues`. There is no sense in setting too high value,
// since it may lead to high memory usage due to big number of buffers.
var maxQueues = cgroup.AvailableCPUs() * 16
const persistentQueueDirname = "persistent-queue"
// InitSecretFlags must be called after flag.Parse and before any logging.
func InitSecretFlags() {
if !*showRemoteWriteURL {
@@ -164,8 +139,6 @@ func Init() {
logger.Fatalf("cannot load relabel configs: %s", err)
}
allRelabelConfigs.Store(rcs)
relabelConfigSuccess.Set(1)
relabelConfigTimestamp.Set(fasttime.UnixTimestamp())
if len(*remoteWriteURLs) > 0 {
rwctxsDefault = newRemoteWriteCtxs(nil, *remoteWriteURLs)
@@ -178,56 +151,21 @@ func Init() {
for {
select {
case <-sighupCh:
case <-configReloaderStopCh:
case <-stopCh:
return
}
reloadRelabelConfigs()
reloadStreamAggrConfigs()
logger.Infof("SIGHUP received; reloading relabel configs pointed by -remoteWrite.relabelConfig and -remoteWrite.urlRelabelConfig")
rcs, err := loadRelabelConfigs()
if err != nil {
logger.Errorf("cannot reload relabel configs; preserving the previous configs; error: %s", err)
continue
}
allRelabelConfigs.Store(rcs)
logger.Infof("Successfully reloaded relabel configs")
}
}()
}
func reloadRelabelConfigs() {
relabelConfigReloads.Inc()
logger.Infof("reloading relabel configs pointed by -remoteWrite.relabelConfig and -remoteWrite.urlRelabelConfig")
rcs, err := loadRelabelConfigs()
if err != nil {
relabelConfigReloadErrors.Inc()
relabelConfigSuccess.Set(0)
logger.Errorf("cannot reload relabel configs; preserving the previous configs; error: %s", err)
return
}
allRelabelConfigs.Store(rcs)
relabelConfigSuccess.Set(1)
relabelConfigTimestamp.Set(fasttime.UnixTimestamp())
logger.Infof("successfully reloaded relabel configs")
}
var (
relabelConfigReloads = metrics.NewCounter(`vmagent_relabel_config_reloads_total`)
relabelConfigReloadErrors = metrics.NewCounter(`vmagent_relabel_config_reloads_errors_total`)
relabelConfigSuccess = metrics.NewCounter(`vmagent_relabel_config_last_reload_successful`)
relabelConfigTimestamp = metrics.NewCounter(`vmagent_relabel_config_last_reload_success_timestamp_seconds`)
)
func reloadStreamAggrConfigs() {
if len(*remoteWriteMultitenantURLs) > 0 {
rwctxsMapLock.Lock()
for _, rwctxs := range rwctxsMap {
reinitStreamAggr(rwctxs)
}
rwctxsMapLock.Unlock()
} else {
reinitStreamAggr(rwctxsDefault)
}
}
func reinitStreamAggr(rwctxs []*remoteWriteCtx) {
for _, rwctx := range rwctxs {
rwctx.reinitStreamAggr()
}
}
func newRemoteWriteCtxs(at *auth.Token, urls []string) []*remoteWriteCtx {
if len(urls) == 0 {
logger.Panicf("BUG: urls must be non-empty")
@@ -260,44 +198,17 @@ func newRemoteWriteCtxs(at *auth.Token, urls []string) []*remoteWriteCtx {
}
rwctxs[i] = newRemoteWriteCtx(i, at, remoteWriteURL, maxInmemoryBlocks, sanitizedURL)
}
if !*keepDanglingQueues {
// Remove dangling queues, if any.
// This is required for the case when the number of queues has been changed or URL have been changed.
// See: https://github.com/VictoriaMetrics/VictoriaMetrics/issues/4014
existingQueues := make(map[string]struct{}, len(rwctxs))
for _, rwctx := range rwctxs {
existingQueues[rwctx.fq.Dirname()] = struct{}{}
}
queuesDir := filepath.Join(*tmpDataPath, persistentQueueDirname)
files := fs.MustReadDir(queuesDir)
removed := 0
for _, f := range files {
dirname := f.Name()
if _, ok := existingQueues[dirname]; !ok {
logger.Infof("removing dangling queue %q", dirname)
fullPath := filepath.Join(queuesDir, dirname)
fs.MustRemoveAll(fullPath)
removed++
}
}
if removed > 0 {
logger.Infof("removed %d dangling queues from %q, active queues: %d", removed, *tmpDataPath, len(rwctxs))
}
}
return rwctxs
}
var configReloaderStopCh = make(chan struct{})
var stopCh = make(chan struct{})
var configReloaderWG sync.WaitGroup
// Stop stops remotewrite.
//
// It is expected that nobody calls Push during and after the call to this func.
func Stop() {
close(configReloaderStopCh)
close(stopCh)
configReloaderWG.Wait()
for _, rwctx := range rwctxsDefault {
@@ -324,9 +235,9 @@ func Stop() {
// Push sends wr to remote storage systems set via `-remoteWrite.url`.
//
// If at is nil, then the data is pushed to the configured `-remoteWrite.url`.
// If at isn't nil, the data is pushed to the configured `-remoteWrite.multitenantURL`.
// If at isn't nil, the the data is pushed to the configured `-remoteWrite.multitenantURL`.
//
// Note that wr may be modified by Push because of relabeling and rounding.
// Note that wr may be modified by Push due to relabeling and rounding.
func Push(at *auth.Token, wr *prompbmarshal.WriteRequest) {
if at == nil && len(*remoteWriteMultitenantURLs) > 0 {
// Write data to default tenant if at isn't set while -remoteWrite.multitenantURL is set.
@@ -353,7 +264,7 @@ func Push(at *auth.Token, wr *prompbmarshal.WriteRequest) {
}
var rctx *relabelCtx
rcs := allRelabelConfigs.Load()
rcs := allRelabelConfigs.Load().(*relabelConfigs)
pcsGlobal := rcs.global
if pcsGlobal.Len() > 0 || len(labelsGlobal) > 0 {
rctx = getRelabelCtx()
@@ -407,46 +318,10 @@ func pushBlockToRemoteStorages(rwctxs []*remoteWriteCtx, tssBlock []prompbmarsha
// Nothing to push
return
}
if len(rwctxs) == 1 {
// Fast path - just push data to the configured single remote storage
rwctxs[0].Push(tssBlock)
return
}
// We need to push tssBlock to multiple remote storages.
// This is either sharding or replication depending on -remoteWrite.shardByURL command-line flag value.
if *shardByURL {
// Shard the data among rwctxs
tssByURL := make([][]prompbmarshal.TimeSeries, len(rwctxs))
for _, ts := range tssBlock {
h := getLabelsHash(ts.Labels)
idx := h % uint64(len(tssByURL))
tssByURL[idx] = append(tssByURL[idx], ts)
}
// Push sharded data to remote storages in parallel in order to reduce
// the time needed for sending the data to multiple remote storage systems.
var wg sync.WaitGroup
wg.Add(len(rwctxs))
for i, rwctx := range rwctxs {
tssShard := tssByURL[i]
if len(tssShard) == 0 {
continue
}
go func(rwctx *remoteWriteCtx, tss []prompbmarshal.TimeSeries) {
defer wg.Done()
rwctx.Push(tss)
}(rwctx, tssShard)
}
wg.Wait()
return
}
// Replicate data among rwctxs.
// Push block to remote storages in parallel in order to reduce
// the time needed for sending the data to multiple remote storage systems.
// Push block to remote storages in parallel in order to reduce the time needed for sending the data to multiple remote storage systems.
var wg sync.WaitGroup
wg.Add(len(rwctxs))
for _, rwctx := range rwctxs {
wg.Add(1)
go func(rwctx *remoteWriteCtx) {
defer wg.Done()
rwctx.Push(tssBlock)
@@ -544,14 +419,9 @@ var (
)
type remoteWriteCtx struct {
idx int
fq *persistentqueue.FastQueue
c *client
sas atomic.Pointer[streamaggr.Aggregators]
streamAggrKeepInput bool
streamAggrDropInput bool
idx int
fq *persistentqueue.FastQueue
c *client
pss []*pendingSeries
pssNextIdx uint64
@@ -565,21 +435,14 @@ func newRemoteWriteCtx(argIdx int, at *auth.Token, remoteWriteURL *url.URL, maxI
pqURL.RawQuery = ""
pqURL.Fragment = ""
h := xxhash.Sum64([]byte(pqURL.String()))
queuePath := filepath.Join(*tmpDataPath, persistentQueueDirname, fmt.Sprintf("%d_%016X", argIdx+1, h))
maxPendingBytes := maxPendingBytesPerURL.GetOptionalArgOrDefault(argIdx, 0)
if maxPendingBytes != 0 && maxPendingBytes < persistentqueue.DefaultChunkFileSize {
// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/4195
logger.Warnf("rounding the -remoteWrite.maxDiskUsagePerURL=%d to the minimum supported value: %d", maxPendingBytes, persistentqueue.DefaultChunkFileSize)
maxPendingBytes = persistentqueue.DefaultChunkFileSize
}
fq := persistentqueue.MustOpenFastQueue(queuePath, sanitizedURL, maxInmemoryBlocks, maxPendingBytes)
queuePath := fmt.Sprintf("%s/persistent-queue/%d_%016X", *tmpDataPath, argIdx+1, h)
fq := persistentqueue.MustOpenFastQueue(queuePath, sanitizedURL, maxInmemoryBlocks, maxPendingBytesPerURL.N)
_ = metrics.GetOrCreateGauge(fmt.Sprintf(`vmagent_remotewrite_pending_data_bytes{path=%q, url=%q}`, queuePath, sanitizedURL), func() float64 {
return float64(fq.GetPendingBytes())
})
_ = metrics.GetOrCreateGauge(fmt.Sprintf(`vmagent_remotewrite_pending_inmemory_blocks{path=%q, url=%q}`, queuePath, sanitizedURL), func() float64 {
return float64(fq.GetInmemoryQueueLen())
})
var c *client
switch remoteWriteURL.Scheme {
case "http", "https":
@@ -589,7 +452,6 @@ func newRemoteWriteCtx(argIdx int, at *auth.Token, remoteWriteURL *url.URL, maxI
}
c.init(argIdx, *queues, sanitizedURL)
// Initialize pss
sf := significantFigures.GetOptionalArgOrDefault(argIdx, 0)
rd := roundDigits.GetOptionalArgOrDefault(argIdx, 100)
pssLen := *queues
@@ -600,10 +462,9 @@ func newRemoteWriteCtx(argIdx int, at *auth.Token, remoteWriteURL *url.URL, maxI
}
pss := make([]*pendingSeries, pssLen)
for i := range pss {
pss[i] = newPendingSeries(fq.MustWriteBlock, c.useVMProto, sf, rd)
pss[i] = newPendingSeries(fq.MustWriteBlock, sf, rd)
}
rwctx := &remoteWriteCtx{
return &remoteWriteCtx{
idx: argIdx,
fq: fq,
c: c,
@@ -612,31 +473,9 @@ func newRemoteWriteCtx(argIdx int, at *auth.Token, remoteWriteURL *url.URL, maxI
rowsPushedAfterRelabel: metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_rows_pushed_after_relabel_total{path=%q, url=%q}`, queuePath, sanitizedURL)),
rowsDroppedByRelabel: metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_relabel_metrics_dropped_total{path=%q, url=%q}`, queuePath, sanitizedURL)),
}
// Initialize sas
sasFile := streamAggrConfig.GetOptionalArg(argIdx)
if sasFile != "" {
dedupInterval := streamAggrDedupInterval.GetOptionalArgOrDefault(argIdx, 0)
sas, err := streamaggr.LoadFromFile(sasFile, rwctx.pushInternal, dedupInterval)
if err != nil {
logger.Fatalf("cannot initialize stream aggregators from -remoteWrite.streamAggr.config=%q: %s", sasFile, err)
}
rwctx.sas.Store(sas)
rwctx.streamAggrKeepInput = streamAggrKeepInput.GetOptionalArg(argIdx)
rwctx.streamAggrDropInput = streamAggrDropInput.GetOptionalArg(argIdx)
metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reload_successful{path=%q}`, sasFile)).Set(1)
metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reload_success_timestamp_seconds{path=%q}`, sasFile)).Set(fasttime.UnixTimestamp())
}
return rwctx
}
func (rwctx *remoteWriteCtx) MustStop() {
// sas must be stopped before rwctx is closed
// because sas can write pending series to rwctx.pss if there are any
sas := rwctx.sas.Swap(nil)
sas.MustStop()
for _, ps := range rwctx.pss {
ps.MustStop()
}
@@ -645,7 +484,6 @@ func (rwctx *remoteWriteCtx) MustStop() {
rwctx.fq.UnblockAllReaders()
rwctx.c.MustStop()
rwctx.c = nil
rwctx.fq.MustClose()
rwctx.fq = nil
@@ -654,10 +492,9 @@ func (rwctx *remoteWriteCtx) MustStop() {
}
func (rwctx *remoteWriteCtx) Push(tss []prompbmarshal.TimeSeries) {
// Apply relabeling
var rctx *relabelCtx
var v *[]prompbmarshal.TimeSeries
rcs := allRelabelConfigs.Load()
rcs := allRelabelConfigs.Load().(*relabelConfigs)
pcs := rcs.perURL[rwctx.idx]
if pcs.Len() > 0 {
rctx = getRelabelCtx()
@@ -665,94 +502,26 @@ func (rwctx *remoteWriteCtx) Push(tss []prompbmarshal.TimeSeries) {
// from affecting time series for other remoteWrite.url configs.
// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/467
// and https://github.com/VictoriaMetrics/VictoriaMetrics/issues/599
v = tssPool.Get().(*[]prompbmarshal.TimeSeries)
v = tssRelabelPool.Get().(*[]prompbmarshal.TimeSeries)
tss = append(*v, tss...)
rowsCountBeforeRelabel := getRowsCount(tss)
tss = rctx.applyRelabeling(tss, nil, pcs)
rowsCountAfterRelabel := getRowsCount(tss)
rwctx.rowsDroppedByRelabel.Add(rowsCountBeforeRelabel - rowsCountAfterRelabel)
}
pss := rwctx.pss
idx := atomic.AddUint64(&rwctx.pssNextIdx, 1) % uint64(len(pss))
rowsCount := getRowsCount(tss)
rwctx.rowsPushedAfterRelabel.Add(rowsCount)
// Apply stream aggregation if any
sas := rwctx.sas.Load()
if sas != nil {
matchIdxs := matchIdxsPool.Get()
matchIdxs.B = sas.Push(tss, matchIdxs.B)
if !rwctx.streamAggrKeepInput {
if rctx == nil {
rctx = getRelabelCtx()
// Make a copy of tss before dropping aggregated series
v = tssPool.Get().(*[]prompbmarshal.TimeSeries)
tss = append(*v, tss...)
}
tss = dropAggregatedSeries(tss, matchIdxs.B, rwctx.streamAggrDropInput)
}
matchIdxsPool.Put(matchIdxs)
}
rwctx.pushInternal(tss)
// Return back relabeling contexts to the pool
pss[idx].Push(tss)
if rctx != nil {
*v = prompbmarshal.ResetTimeSeries(tss)
tssPool.Put(v)
tssRelabelPool.Put(v)
putRelabelCtx(rctx)
}
}
var matchIdxsPool bytesutil.ByteBufferPool
func dropAggregatedSeries(src []prompbmarshal.TimeSeries, matchIdxs []byte, dropInput bool) []prompbmarshal.TimeSeries {
dst := src[:0]
for i, match := range matchIdxs {
if match == 0 {
continue
}
dst = append(dst, src[i])
}
tail := src[len(dst):]
_ = prompbmarshal.ResetTimeSeries(tail)
return dst
}
func (rwctx *remoteWriteCtx) pushInternal(tss []prompbmarshal.TimeSeries) {
pss := rwctx.pss
idx := atomic.AddUint64(&rwctx.pssNextIdx, 1) % uint64(len(pss))
pss[idx].Push(tss)
}
func (rwctx *remoteWriteCtx) reinitStreamAggr() {
sas := rwctx.sas.Load()
if sas == nil {
// There is no stream aggregation for rwctx
return
}
sasFile := streamAggrConfig.GetOptionalArg(rwctx.idx)
logger.Infof("reloading stream aggregation configs pointed by -remoteWrite.streamAggr.config=%q", sasFile)
metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reloads_total{path=%q}`, sasFile)).Inc()
dedupInterval := streamAggrDedupInterval.GetOptionalArgOrDefault(rwctx.idx, 0)
sasNew, err := streamaggr.LoadFromFile(sasFile, rwctx.pushInternal, dedupInterval)
if err != nil {
metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reloads_errors_total{path=%q}`, sasFile)).Inc()
metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reload_successful{path=%q}`, sasFile)).Set(0)
logger.Errorf("cannot reload stream aggregation config from -remoteWrite.streamAggr.config=%q; continue using the previously loaded config; error: %s", sasFile, err)
return
}
if !sasNew.Equal(sas) {
sasOld := rwctx.sas.Swap(sasNew)
sasOld.MustStop()
logger.Infof("successfully reloaded stream aggregation configs at -remoteWrite.streamAggr.config=%q", sasFile)
} else {
sasNew.MustStop()
logger.Infof("the config at -remoteWrite.streamAggr.config=%q wasn't changed", sasFile)
}
metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reload_successful{path=%q}`, sasFile)).Set(1)
metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reload_success_timestamp_seconds{path=%q}`, sasFile)).Set(fasttime.UnixTimestamp())
}
var tssPool = &sync.Pool{
var tssRelabelPool = &sync.Pool{
New: func() interface{} {
a := []prompbmarshal.TimeSeries{}
return &a
@@ -766,20 +535,3 @@ func getRowsCount(tss []prompbmarshal.TimeSeries) int {
}
return rowsCount
}
// CheckStreamAggrConfigs checks configs pointed by -remoteWrite.streamAggr.config
func CheckStreamAggrConfigs() error {
pushNoop := func(tss []prompbmarshal.TimeSeries) {}
for idx, sasFile := range *streamAggrConfig {
if sasFile == "" {
continue
}
dedupInterval := streamAggrDedupInterval.GetOptionalArgOrDefault(idx, 0)
sas, err := streamaggr.LoadFromFile(sasFile, pushNoop, dedupInterval)
if err != nil {
return fmt.Errorf("cannot load -remoteWrite.streamAggr.config=%q: %w", sasFile, err)
}
sas.MustStop()
}
return nil
}

View File

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

View File

@@ -73,7 +73,6 @@ test-vmalert:
go test -v -race -cover ./app/vmalert/notifier
go test -v -race -cover ./app/vmalert/config
go test -v -race -cover ./app/vmalert/remotewrite
go test -v -race -cover ./app/vmalert/utils
run-vmalert: vmalert
./bin/vmalert -rule=app/vmalert/config/testdata/rules/rules2-good.rules \
@@ -115,9 +114,6 @@ vmalert-linux-arm64:
vmalert-linux-ppc64le:
APP_NAME=vmalert CGO_ENABLED=0 GOOS=linux GOARCH=ppc64le $(MAKE) app-local-goos-goarch
vmalert-linux-s390x:
APP_NAME=vmalert CGO_ENABLED=0 GOOS=linux GOARCH=s390x $(MAKE) app-local-goos-goarch
vmalert-linux-386:
APP_NAME=vmalert CGO_ENABLED=0 GOOS=linux GOARCH=386 $(MAKE) app-local-goos-goarch

View File

@@ -9,13 +9,6 @@ protocol and require `-remoteWrite.url` to be configured.
Vmalert is heavily inspired by [Prometheus](https://prometheus.io/docs/alerting/latest/overview/)
implementation and aims to be compatible with its syntax.
A [single-node](https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html#vmalert)
or [cluster version](https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html#vmalert)
of VictoriaMetrics are capable of proxying requests to vmalert via `-vmalert.proxyURL` command-line flag.
Use this feature for the following cases:
* for proxying requests from [Grafana Alerting UI](https://grafana.com/docs/grafana/latest/alerting/);
* for accessing vmalerts UI through VictoriaMetrics Web interface.
## Features
* Integration with [VictoriaMetrics](https://github.com/VictoriaMetrics/VictoriaMetrics) TSDB;
@@ -23,14 +16,12 @@ Use this feature for the following cases:
support and expressions validation;
* Prometheus [alerting rules definition format](https://prometheus.io/docs/prometheus/latest/configuration/alerting_rules/#defining-alerting-rules)
support;
* Integration with [Alertmanager](https://github.com/prometheus/alertmanager) starting from [Alertmanager v0.16.0-alpha](https://github.com/prometheus/alertmanager/releases/tag/v0.16.0-alpha.0);
* Integration with [Alertmanager](https://github.com/prometheus/alertmanager) starting from [Alertmanager v0.16.0-aplha](https://github.com/prometheus/alertmanager/releases/tag/v0.16.0-alpha.0);
* Keeps the alerts [state on restarts](#alerts-state-on-restarts);
* Graphite datasource can be used for alerting and recording rules. See [these docs](#graphite);
* Recording and Alerting rules backfilling (aka `replay`). See [these docs](#rules-backfilling);
* Lightweight and without extra dependencies.
* Supports [reusable templates](#reusable-templates) for annotations;
* Load of recording and alerting rules from local filesystem, URL, GCS and S3;
* Detect alerting rules which [don't match any series](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/4039).
* Supports [reusable templates](#reusable-templates) for annotations.
## Limitations
@@ -78,17 +69,16 @@ Then configure `vmalert` accordingly:
-external.label=replica=a # Multiple external labels may be set
```
Note there's a separate `-remoteWrite.url` command-line flag to allow writing results of
Note there's a separate `remoteWrite.url` to allow writing results of
alerting/recording rules into a different storage than the initial data that's
queried. This allows using `vmalert` to aggregate data from a short-term,
high-frequency, high-cardinality storage into a long-term storage with
decreased cardinality and a bigger interval between samples.
See also [stream aggregation](https://docs.victoriametrics.com/stream-aggregation.html).
See the full list of configuration flags in [configuration](#configuration) section.
If you run multiple `vmalert` services for the same datastore or AlertManager - do not forget
to specify different `-external.label` command-line flags in order to define which `vmalert` generated rules or alerts.
to specify different `external.label` flags in order to define which `vmalert` generated rules or alerts.
Configuration for [recording](https://prometheus.io/docs/prometheus/latest/configuration/recording_rules/)
and [alerting](https://prometheus.io/docs/prometheus/latest/configuration/alerting_rules/) rules is very
@@ -130,7 +120,7 @@ name: <string>
# params:
# nocache: ["1"] # disable caching for vmselect
# denyPartialResponse: ["true"] # fail if one or more vmstorage nodes returned an error
# extra_label: ["env=dev"] # apply additional label filter "env=dev" for all requests
# extra_label: ["env=dev"] # apply additional label filter "env=dev" for all requests
# see more details at https://docs.victoriametrics.com#prometheus-querying-api-enhancements
params:
[ <string>: [<string>, ...]]
@@ -141,19 +131,10 @@ params:
# headers:
# - "CustomHeader: foo"
# - "CustomHeader2: bar"
# Headers set via this param have priority over headers set via `-datasource.headers` flag.
# Headers set via this param have priority over headers set via `-datasource.headers` flag.
headers:
[ <string>, ...]
# Optional list of HTTP headers in form `header-name: value`
# applied for all alert notifications sent to notifiers
# generated by rules of this group.
# For example:
# notifier_headers:
# - "TenantID: foo"
notifier_headers:
[ <string>, ...]
# Optional list of labels added to every rule within a group.
# It has priority over the external labels.
# Labels are commonly used for adding environment
@@ -203,24 +184,6 @@ expr: <string>
# as firing once they return.
[ for: <duration> | default = 0s ]
# Alert will continue firing for this long even when the alerting expression no longer has results.
# This allows you to delay alert resolution.
[ keep_firing_for: <duration> | default = 0s ]
# Whether to print debug information into logs.
# Information includes alerts state changes and requests sent to the datasource.
# Please note, that if rule's query params contain sensitive
# information - it will be printed to logs.
# Is applicable to alerting rules only.
# Available starting from https://docs.victoriametrics.com/CHANGELOG.html#v1820
[ debug: <bool> | default = false ]
# Defines the number of rule's updates entries stored in memory
# and available for view on rule's Details page.
# Overrides `rule.updateEntriesLimit` value for this specific rule.
# Available starting from https://docs.victoriametrics.com/CHANGELOG.html#v1860
[ update_entries_limit: <integer> | default 0 ]
# Labels to add or overwrite for each alert.
labels:
[ <labelname>: <tmpl_string> ]
@@ -230,9 +193,9 @@ annotations:
[ <labelname>: <tmpl_string> ]
```
#### Templating
#### Templating
It is allowed to use [Go templating](https://golang.org/pkg/text/template/) in annotations to format data, iterate over
It is allowed to use [Go templating](https://golang.org/pkg/text/template/) in annotations to format data, iterate over
or execute expressions.
The following variables are available in templating:
@@ -243,57 +206,18 @@ The following variables are available in templating:
| $labels or .Labels | The list of labels of the current alert. Use as ".Labels.<label_name>". | {% raw %}Too high number of connections for {{ .Labels.instance }}{% endraw %} |
| $alertID or .AlertID | The current alert's ID generated by vmalert. | {% raw %}Link: vmalert/alert?group_id={{.GroupID}}&alert_id={{.AlertID}}{% endraw %} |
| $groupID or .GroupID | The current alert's group ID generated by vmalert. | {% raw %}Link: vmalert/alert?group_id={{.GroupID}}&alert_id={{.AlertID}}{% endraw %} |
| $expr or .Expr | Alert's expression. Can be used for generating links to Grafana or other systems. | {% raw %}/api/v1/query?query={{ $expr&#124;queryEscape }}{% endraw %} |
| $for or .For | Alert's configured for param. | {% raw %}Number of connections is too high for more than {{ .For }}{% endraw %} |
| $expr or .Expr | Alert's expression. Can be used for generating links to Grafana or other systems. | {% raw %}/api/v1/query?query={{ $expr&#124;quotesEscape&#124;queryEscape }}{% endraw %} |
| $externalLabels or .ExternalLabels | List of labels configured via `-external.label` command-line flag. | {% raw %}Issues with {{ $labels.instance }} (datacenter-{{ $externalLabels.dc }}){% endraw %} |
| $externalURL or .ExternalURL | URL configured via `-external.url` command-line flag. Used for cases when vmalert is hidden behind proxy. | {% raw %}Visit {{ $externalURL }} for more details{% endraw %} |
Additionally, `vmalert` provides some extra templating functions listed [here](#template-functions) and [reusable templates](#reusable-templates).
#### Template functions
`vmalert` provides the following template functions, which can be used during [templating](#templating):
- `args arg0 ... argN` - converts the input args into a map with `arg0`, ..., `argN` keys.
- `externalURL` - returns the value of `-external.url` command-line flag.
- `first` - returns the first result from the input query results returned by `query` function.
- `htmlEscape` - escapes special chars in input string, so it can be safely embedded as a plaintext into HTML.
- `humanize` - converts the input number into human-readable format by adding [metric prefixes](https://en.wikipedia.org/wiki/Metric_prefix).
For example, `100000` is converted into `100K`.
- `humanize1024` - converts the input number into human-readable format with 1024 base.
For example, `1024` is converted into 1ki`.
- `humanizeDuration` - converts the input number in seconds into human-readable duration.
- `humanizePercentage` - converts the input number to percentage. For example, `0.123` is converted into `12.3%`.
- `humanizeTimestamp` - converts the input unix timestamp into human-readable time.
- `jsonEscape` - JSON-encodes the input string.
- `label name` - returns the value of the label with the given `name` from the input query result.
- `match regex` - matches the input string against the provided `regex`.
- `parseDuration` - parses the input string into duration in seconds. For example, `1h` is parsed into `3600`.
- `parseDurationTime` - parses the input string into [time.Duration](https://pkg.go.dev/time#Duration).
- `pathEscape` - escapes the input string, so it can be safely put inside path part of URL.
- `pathPrefix` - returns the path part of the `-external.url` command-line flag.
- `query` - executes the [MetricsQL](https://docs.victoriametrics.com/MetricsQL.html) query against `-datasource.url` and returns the query result.
For example, {% raw %}`{{ query "sort_desc(process_resident_memory_bytes)" | first | value }}`{% endraw %} executes the `sort_desc(process_resident_memory_bytes)`
query at `-datasource.url` and returns the first result.
- `queryEscape` - escapes the input string, so it can be safely put inside [query arg](https://en.wikipedia.org/wiki/Percent-encoding) part of URL.
- `quotesEscape` - escapes the input string, so it can be safely embedded into JSON string.
- `reReplaceAll regex repl` - replaces all the occurrences of the `regex` in input string with the `repl`.
- `safeHtml` - marks the input string as safe to use in HTML context without the need to html-escape it.
- `sortByLabel name` - sorts the input query results by the label with the given `name`.
- `stripDomain` - leaves the first part of the domain. For example, `foo.bar.baz` is converted to `foo`.
The port part is left in the output string. E.g. `foo.bar:1234` is converted into `foo:1234`.
- `stripPort` - strips `port` part from `host:port` input string.
- `strvalue` - returns the metric name from the input query result.
- `title` - converts the first letters of every input word to uppercase.
- `toLower` - converts all the chars in the input string to lowercase.
- `toTime` - converts the input unix timestamp to [time.Time](https://pkg.go.dev/time#Time).
- `toUpper` - converts all the chars in the input string to uppercase.
- `value` - returns the numeric value from the input query result.
Additionally, `vmalert` provides some extra templating functions
listed [here](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/app/vmalert/templates/template.go)
and [reusable templates](#reusable-templates).
#### Reusable templates
Like in Alertmanager you can define [reusable templates](https://prometheus.io/docs/prometheus/latest/configuration/template_examples/#defining-reusable-templates)
to share same templates across annotations. Just define the templates in a file and
to share same templates across annotations. Just define the templates in a file and
set the path via `-rule.templates` flag.
For example, template `grafana.filter` can be defined as following:
@@ -349,36 +273,25 @@ expr: <string>
# Labels to add or overwrite before storing the result.
labels:
[ <labelname>: <labelvalue> ]
# Defines the number of rule's updates entries stored in memory
# and available for view on rule's Details page.
# Overrides `rule.updateEntriesLimit` value for this specific rule.
[ update_entries_limit: <integer> | default 0 ]
```
For recording rules to work `-remoteWrite.url` must be specified.
### Alerts state on restarts
`vmalert` holds alerts state in the memory. Restart of the `vmalert` process will reset the state of all active alerts
in the memory. To prevent `vmalert` from losing the state on restarts configure it to persist the state
to the remote database via the following flags:
`vmalert` has no local storage, so alerts state is stored in the process memory. Hence, after restart of `vmalert`
the process alerts state will be lost. To avoid this situation, `vmalert` should be configured via the following flags:
* `-remoteWrite.url` - URL to VictoriaMetrics (Single) or vminsert (Cluster). `vmalert` will persist alerts state
to the configured address in the form of [time series](https://docs.victoriametrics.com/keyConcepts.html#time-series)
`ALERTS` and `ALERTS_FOR_STATE` via remote-write protocol.
These time series can be queried from VictoriaMetrics just as any other time series.
The state will be persisted to the configured address on each evaluation.
into the configured address in the form of time series named `ALERTS` and `ALERTS_FOR_STATE` via remote-write protocol.
These are regular time series and maybe queried from VM just as any other time series.
The state is stored to the configured address on every rule evaluation.
* `-remoteRead.url` - URL to VictoriaMetrics (Single) or vmselect (Cluster). `vmalert` will try to restore alerts state
from the configured address by querying time series with name `ALERTS_FOR_STATE`. The restore happens only once when
`vmalert` process starts, and only for the configured rules. Config [hot reload](#hot-config-reload) doesn't trigger
state restore.
from configured address by querying time series with name `ALERTS_FOR_STATE`.
Both flags are required for proper state restoration. Restore process may fail if time series are missing
in configured `-remoteRead.url`, weren't updated in the last `1h` (controlled by `-remoteRead.lookback`)
or received state doesn't match current `vmalert` rules configuration. `vmalert` marks successfully restored rules
with `restored` label in [web UI](#web).
or received state doesn't match current `vmalert` rules configuration.
### Multitenancy
@@ -395,7 +308,7 @@ There are the following approaches exist for alerting and recording rules across
rules to `AccountID=123`.
* To specify `tenant` parameter per each alerting and recording group if
[enterprise version of vmalert](https://docs.victoriametrics.com/enterprise.html) is used
[enterprise version of vmalert](https://victoriametrics.com/products/enterprise/) is used
with `-clusterMode` command-line flag. For example:
```yaml
@@ -411,10 +324,6 @@ groups:
# Rules for accountID=456, projectID=789
```
The results of alerting and recording rules contain `vm_account_id` and `vm_project_id` labels
if `-clusterMode` is enabled. These labels can be used during [templating](https://docs.victoriametrics.com/vmalert.html#templating),
and help to identify to which account or project the triggered alert or produced recording belongs.
If `-clusterMode` is enabled, then `-datasource.url`, `-remoteRead.url` and `-remoteWrite.url` must
contain only the hostname without tenant id. For example: `-datasource.url=http://vmselect:8481`.
`vmalert` automatically adds the specified tenant to urls per each recording rule in this case.
@@ -426,25 +335,6 @@ The enterprise version of vmalert is available in `vmutils-*-enterprise.tar.gz`
at [release page](https://github.com/VictoriaMetrics/VictoriaMetrics/releases) and in `*-enterprise`
tags at [Docker Hub](https://hub.docker.com/r/victoriametrics/vmalert/tags).
### Reading rules from object storage
[Enterprise version](https://docs.victoriametrics.com/enterprise.html) of `vmalert` may read alerting and recording rules
from object storage:
- `./bin/vmalert -rule=s3://bucket/dir/alert.rules` would read rules from the given path at S3 bucket
- `./bin/vmalert -rule=gs://bucket/bir/alert.rules` would read rules from the given path at GCS bucket
S3 and GCS paths support only matching by prefix, e.g. `s3://bucket/dir/rule_` matches
all files with prefix `rule_` in the folder `dir`.
The following [command-line flags](#flags) can be used for fine-tuning access to S3 and GCS:
- `-s3.credsFilePath` - path to file with GCS or S3 credentials. Credentials are loaded from default locations if not set.
- `-s3.configFilePath` - path to file with S3 configs. Configs are loaded from default location if not set.
- `-s3.configProfile` - profile name for S3 configs. If no set, the value of the environment variable will be loaded (`AWS_PROFILE` or `AWS_DEFAULT_PROFILE`).
- `-s3.customEndpoint` - custom S3 endpoint for use with S3-compatible storages (e.g. MinIO). S3 is used if not set.
- `-s3.forcePathStyle` - prefixing endpoint with bucket name when set false, true by default.
### Topology examples
The following sections are showing how `vmalert` may be used and configured
@@ -494,7 +384,7 @@ Cluster mode could have multiple `vminsert` and `vmselect` components.
<img alt="vmalert cluster" src="vmalert_cluster.png">
In case when you want to spread the load on these components - add balancers before them and configure
`vmalert` with balancer addresses. Please, see more about VM's cluster architecture
`vmalert` with balancer's addresses. Please, see more about VM's cluster architecture
[here](https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html#architecture-overview).
#### HA vmalert
@@ -519,35 +409,31 @@ Alertmanagers.
To avoid recording rules results and alerts state duplication in VictoriaMetrics server
don't forget to configure [deduplication](https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html#deduplication).
The recommended value for `-dedup.minScrapeInterval` must be multiple of vmalert's `evaluation_interval`.
The recommended value for `-dedup.minScrapeInterval` must be greater or equal to vmalert's `evaluation_interval`.
If you observe inconsistent or "jumping" values in series produced by vmalert, try disabling `-datasource.queryTimeAlignment`
command line flag. Because of alignment, two or more vmalert HA pairs will produce results with the same timestamps.
But due of backfilling (data delivered to the datasource with some delay) values of such results may differ,
command line flag. Because of alignment, two or more vmalert HA pairs will produce results with the same timestamps.
But due of backfilling (data delivered to the datasource with some delay) values of such results may differ,
which would affect deduplication logic and result into "jumping" datapoints.
Alertmanager will automatically deduplicate alerts with identical labels, so ensure that
all `vmalert`s are having the same config.
Don't forget to configure [cluster mode](https://prometheus.io/docs/alerting/latest/alertmanager/)
for Alertmanagers for better reliability. List all Alertmanager URLs in vmalert `-notifier.url`
to ensure [high availability](https://github.com/prometheus/alertmanager#high-availability).
for Alertmanagers for better reliability.
This example uses single-node VM server for the sake of simplicity.
Check how to replace it with [cluster VictoriaMetrics](#cluster-victoriametrics) if needed.
#### Downsampling and aggregation via vmalert
_Please note, [stream aggregation](https://docs.victoriametrics.com/stream-aggregation.html) might be more efficient
for cases when downsampling or aggregation need to be applied **before data gets into the TSDB.**_
`vmalert` can't modify existing data. But it can run arbitrary PromQL/MetricsQL queries
via [recording rules](#recording-rules) and backfill results to the configured `-remoteWrite.url`.
This ability allows to aggregate data. For example, the following rule will calculate the average value for
metric `http_requests` on the `5m` interval:
```yaml
- record: http_requests:avg5m
expr: avg_over_time(http_requests[5m])
- record: http_requests:avg5m
expr: avg_over_time(http_requests[5m])
```
Every time this rule will be evaluated, `vmalert` will backfill its results as a new time series `http_requests:avg5m`
@@ -561,13 +447,13 @@ This ability allows to downsample data. For example, the following config will e
groups:
- name: my_group
interval: 5m
rules:
rules:
- record: http_requests:avg5m
expr: avg_over_time(http_requests[5m])
expr: avg_over_time(http_requests[5m])
```
Ability of `vmalert` to be configured with different `-datasource.url` and `-remoteWrite.url` command-line flags
allows reading data from one data source and backfilling results to another. This helps to build a system
Ability of `vmalert` to be configured with different `datasource.url` and `remoteWrite.url` allows
reading data from one data source and backfilling results to another. This helps to build a system
for aggregating and downsampling the data.
The following example shows how to build a topology where `vmalert` will process data from one cluster
@@ -581,7 +467,7 @@ or reducing resolution) and push results to "cold" cluster.
```
./bin/vmalert -rule=downsampling-rules.yml \ # Path to the file with rules configuration. Supports wildcard
-datasource.url=http://raw-cluster-vmselect:8481/select/0/prometheus # vmselect addr for executing recording rules expressions
-datasource.url=http://raw-cluster-vmselect:8481/select/0/prometheus # vmselect addr for executing recordi ng rules expressions
-remoteWrite.url=http://aggregated-cluster-vminsert:8480/insert/0/prometheus # vminsert addr to persist recording rules results
```
@@ -591,7 +477,7 @@ Please note, [replay](#rules-backfilling) feature may be used for transforming h
Flags `-remoteRead.url` and `-notifier.url` are omitted since we assume only recording rules are used.
See also [stream aggregation](https://docs.victoriametrics.com/stream-aggregation.html) and [downsampling](https://docs.victoriametrics.com/#downsampling).
See also [downsampling docs](https://docs.victoriametrics.com/#downsampling).
#### Multiple remote writes
@@ -603,7 +489,7 @@ we recommend using [vmagent](https://docs.victoriametrics.com/vmagent.html) as f
In this topology, `vmalert` is configured to persist rule results to `vmagent`. And `vmagent`
is configured to fan-out received data to two or more destinations.
Using `vmagent` as a proxy provides additional benefits such as
Using `vmagent` as a proxy provides additional benefits such as
[data persisting when storage is unreachable](https://docs.victoriametrics.com/vmagent.html#replication-and-high-availability),
or time series modification via [relabeling](https://docs.victoriametrics.com/vmagent.html#relabeling).
@@ -618,13 +504,12 @@ or time series modification via [relabeling](https://docs.victoriametrics.com/vm
* `http://<vmalert-addr>/vmalert/api/v1/alert?group_id=<group_id>&alert_id=<alert_id>` - get alert status in JSON format.
Used as alert source in AlertManager.
* `http://<vmalert-addr>/vmalert/alert?group_id=<group_id>&alert_id=<alert_id>` - get alert status in web UI.
* `http://<vmalert-addr>/vmalert/rule?group_id=<group_id>&rule_id=<rule_id>` - get rule status in web UI.
* `http://<vmalert-addr>/metrics` - application metrics.
* `http://<vmalert-addr>/-/reload` - hot configuration reload.
`vmalert` web UI can be accessed from [single-node version of VictoriaMetrics](https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html)
and from [cluster version of VictoriaMetrics](https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html).
This may be used for better integration with Grafana unified alerting system. See the following docs for details:
This may be used for better integraion with Grafana unified alerting system. See the following docs for details:
* [How to query vmalert from single-node VictoriaMetrics](https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html#vmalert)
* [How to query vmalert from VictoriaMetrics cluster](https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html#vmalert)
@@ -645,12 +530,6 @@ can read the same rules configuration as normal, evaluate them on the given time
results via remote write to the configured storage. vmalert supports any PromQL/MetricsQL compatible
data source for backfilling.
Please note, that response caching may lead to unexpected results during and after backfilling process.
In order to avoid this you need to reset cache contents or disable caching when using backfilling
as described in [backfilling docs](https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html#backfilling).
See a blogpost about [Rules backfilling via vmalert](https://victoriametrics.com/blog/rules-replay/).
### How it works
In `replay` mode vmalert works as a cli-tool and exits immediately after work is done.
@@ -733,146 +612,24 @@ There are following non-required `replay` flags:
Progress bar may generate a lot of log records, which is not formatted as standard VictoriaMetrics logger.
It could break logs parsing by external system and generate additional load on it.
See full description for these flags in `./vmalert -help`.
See full description for these flags in `./vmalert --help`.
### Limitations
* Graphite engine isn't supported yet;
* `query` template function is disabled for performance reasons (might be changed in future);
* `limit` group's param has no effect during replay (might be changed in future);
* `keep_firing_for` alerting rule param has no effect during replay (might be changed in future).
## Monitoring
`vmalert` exports various metrics in Prometheus exposition format at `http://vmalert-host:8880/metrics` page.
The default list of alerting rules for these metric can be found [here](https://github.com/VictoriaMetrics/VictoriaMetrics/tree/master/deployment/docker).
We recommend setting up regular scraping of this page either through `vmagent` or by Prometheus so that the exported
metrics may be analyzed later.
Use the official [Grafana dashboard](https://grafana.com/grafana/dashboards/14950-victoriametrics-vmalert/) for `vmalert` overview.
Graphs on this dashboard contain useful hints - hover the `i` icon in the top left corner of each graph in order to read it.
Use the official [Grafana dashboard](https://grafana.com/grafana/dashboards/14950) for `vmalert` overview. Graphs on this dashboard contain useful hints - hover the `i` icon at the top left corner of each graph in order to read it.
If you have suggestions for improvements or have found a bug - please open an issue on github or add
a review to the dashboard.
## Troubleshooting
### Data delay
Data delay is one of the most common issues with rules execution.
vmalert executes configured rules within certain intervals at specifics timestamps.
It expects that the data is already present in configured `-datasource.url` at the moment of time when rule is executed:
<img alt="vmalert expected evaluation" src="vmalert_ts_normal.gif">
Usually, troubles start to appear when data in `-datasource.url` is delayed or absent. In such cases, evaluations
may get empty response from the datasource and produce empty recording rules or reset alerts state:
<img alt="vmalert evaluation when data is delayed" src="vmalert_ts_data_delay.gif">
Try the following recommendations to reduce the chance of hitting the data delay issue:
* Always configure group's `evaluationInterval` to be bigger or at least equal to
[time series resolution](https://docs.victoriametrics.com/keyConcepts.html#time-series-resolution);
* Ensure that `[duration]` value is at least twice bigger than
[time series resolution](https://docs.victoriametrics.com/keyConcepts.html#time-series-resolution). For example,
if expression is `rate(my_metric[2m]) > 0` then ensure that `my_metric` resolution is at least `1m` or better `30s`.
If you use VictoriaMetrics as datasource, `[duration]` can be omitted and VictoriaMetrics will adjust it automatically.
* If you know in advance, that data in datasource is delayed - try changing vmalerts `-datasource.lookback`
command-line flag to add a time shift for evaluations. Or extend `[duration]` to tolerate the delay.
For example, `max_over_time(errors_total[10m]) > 0` will be active even if there is no data in datasource for last `9m`.
* If [time series resolution](https://docs.victoriametrics.com/keyConcepts.html#time-series-resolution)
in datasource is inconsistent or `>=5min` - try changing vmalerts `-datasource.queryStep` command-line flag to specify
how far search query can lookback for the recent datapoint. The recommendation is to have the step
at least two times bigger than the resolution.
> Please note, data delay is inevitable in distributed systems. And it is better to account for it instead of ignoring.
By default, recently written samples to VictoriaMetrics aren't visible for queries for up to 30s
(see `-search.latencyOffset` command-line flag at vmselect). Such delay is needed to eliminate risk of incomplete
data on the moment of querying, since metrics collectors won't be able to deliver the data in time.
### Alerts state
Sometimes, it is not clear why some specific alert fired or didn't fire. It is very important to remember, that
alerts with `for: 0` fire immediately when their expression becomes true. And alerts with `for > 0` will fire only
after multiple consecutive evaluations, and at each evaluation their expression must be true. If at least one evaluation
becomes false, then alert's state resets to the initial state.
If `-remoteWrite.url` command-line flag is configured, vmalert will persist alert's state in form of time series
`ALERTS` and `ALERTS_FOR_STATE` to the specified destination. Such time series can be then queried via
[vmui](https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html#vmui) or Grafana to track how alerts state
changed in time.
vmalert stores last `-rule.updateEntriesLimit` (or `update_entries_limit` [per-rule config](https://docs.victoriametrics.com/vmalert.html#alerting-rules))
state updates for each rule starting from [v1.86](https://docs.victoriametrics.com/CHANGELOG.html#v1860).
To check updates, click on `Details` link next to rule's name on `/vmalert/groups` page
and check the `Last updates` section:
<img alt="vmalert state" src="vmalert_state.png">
Rows in the section represent ordered rule evaluations and their results. The column `curl` contains an example of
HTTP request sent by vmalert to the `-datasource.url` during evaluation. If specific state shows that there were
no samples returned and curl command returns data - then it is very likely there was no data in datasource on the
moment when rule was evaluated.
### Debug mode
vmalert allows configuring more detailed logging for specific alerting rule starting from [v1.82](https://docs.victoriametrics.com/CHANGELOG.html#v1820).
Just set `debug: true` in rule's configuration and vmalert will start printing additional log messages:
```terminal
2022-09-15T13:35:41.155Z DEBUG rule "TestGroup":"Conns" (2601299393013563564) at 2022-09-15T15:35:41+02:00: query returned 0 samples (elapsed: 5.896041ms)
2022-09-15T13:35:56.149Z DEBUG datasource request: executing POST request with params "denyPartialResponse=true&query=sum%28vm_tcplistener_conns%7Binstance%3D%22localhost%3A8429%22%7D%29+by%28instance%29+%3E+0&step=15s&time=1663248945"
2022-09-15T13:35:56.178Z DEBUG rule "TestGroup":"Conns" (2601299393013563564) at 2022-09-15T15:35:56+02:00: query returned 1 samples (elapsed: 28.368208ms)
2022-09-15T13:35:56.178Z DEBUG datasource request: executing POST request with params "denyPartialResponse=true&query=sum%28vm_tcplistener_conns%7Binstance%3D%22localhost%3A8429%22%7D%29&step=15s&time=1663248945"
2022-09-15T13:35:56.179Z DEBUG rule "TestGroup":"Conns" (2601299393013563564) at 2022-09-15T15:35:56+02:00: alert 10705778000901301787 {alertgroup="TestGroup",alertname="Conns",cluster="east-1",instance="localhost:8429",replica="a"} created in state PENDING
...
2022-09-15T13:36:56.153Z DEBUG rule "TestGroup":"Conns" (2601299393013563564) at 2022-09-15T15:36:56+02:00: alert 10705778000901301787 {alertgroup="TestGroup",alertname="Conns",cluster="east-1",instance="localhost:8429",replica="a"} PENDING => FIRING: 1m0s since becoming active at 2022-09-15 15:35:56.126006 +0200 CEST m=+39.384575417
```
### Never-firing alerts
vmalert can detect if alert's expression doesn't match any time series in runtime
starting from [v1.91](https://docs.victoriametrics.com/CHANGELOG.html#v1910). This problem usually happens
when alerting expression selects time series which aren't present in the datasource (i.e. wrong `job` label)
or there is a typo in the series selector (i.e. `env=rpod`). Such alerting rules will be marked with special icon in
vmalerts UI and exposed via `vmalert_alerting_rules_last_evaluation_series_fetched` metric. The metric value will
show how many time series were matched before the filtering by rule's expression. If metric value is `-1`, then
this feature is not supported by the datasource (old versions of VictoriaMetrics). The following expression can be
used to detect rules matching no series:
```
max(vmalert_alerting_rules_last_evaluation_series_fetched) by(group, alertname) == 0
```
See more details [here](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/4039).
This feature is available only if vmalert is using VictoriaMetrics v1.90 or higher as a datasource.
### Series with the same labelset
vmalert can produce the following error message during rules evaluation:
```
result contains metrics with the same labelset after applying rule labels
```
The error means there is a collision between [time series](https://docs.victoriametrics.com/keyConcepts.html#time-series)
after applying extra labels to result.
For example, a rule with `expr: foo > 0` returns two distinct time series in response:
```
foo{bar="baz"} 1
foo{bar="qux"} 2
```
If user configures `-external.label=bar=baz` cmd-line flag to enforce
adding `bar="baz"` label-value pair, then time series won't be distinct anymore:
```
foo{bar="baz"} 1
foo{bar="baz"} 2 # 'bar' label was overriden by `-external.label=bar=baz
```
The same issue can be caused by collision of configured `labels` on [Group](#groups) or [Rule](#rules) levels.
To fix it one should avoid collisions by carefully picking label overrides in configuration.
## Profiling
`vmalert` provides handlers for collecting the following [Go profiles](https://blog.golang.org/profiling-go-programs):
@@ -911,11 +668,11 @@ command-line flags with their descriptions.
The shortlist of configuration flags is the following:
{% raw %}
```console
```
-clusterMode
If clusterMode is enabled, then vmalert automatically adds the tenant specified in config groups to -datasource.url, -remoteWrite.url and -remoteRead.url. See https://docs.victoriametrics.com/vmalert.html#multitenancy . This flag is available only in VictoriaMetrics enterprise. See https://docs.victoriametrics.com/enterprise.html
If clusterMode is enabled, then vmalert automatically adds the tenant specified in config groups to -datasource.url, -remoteWrite.url and -remoteRead.url. See https://docs.victoriametrics.com/vmalert.html#multitenancy
-configCheckInterval duration
Interval for checking for changes in '-rule' or '-notifier.config' files. By default, the checking is disabled. Send SIGHUP signal in order to force config check for changes.
Interval for checking for changes in '-rule' or '-notifier.config' files. By default the checking is disabled. Send SIGHUP signal in order to force config check for changes.
-datasource.appendTypePrefix
Whether to add type prefix to -datasource.url based on the query type. Set to true if sending different query types to the vmselect URL.
-datasource.basicAuth.password string
@@ -930,8 +687,6 @@ The shortlist of configuration flags is the following:
Optional path to bearer token file to use for -datasource.url.
-datasource.disableKeepAlive
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.
-datasource.disableStepParam
Whether to disable adding 'step' param to the issued instant queries. This might be useful when using vmalert with datasources that do not support 'step' param for instant queries, like Google Managed Prometheus. It is not recommended to enable this flag if you use vmalert with VictoriaMetrics.
-datasource.headers string
Optional HTTP extraHeaders to send with each request to the corresponding -datasource.url. For example, -datasource.headers='My-Auth:foobar' would send 'My-Auth: foobar' HTTP header with every request to the corresponding -datasource.url. Multiple headers must be delimited by '^^': -datasource.headers='header1:value1^^header2:value2'
-datasource.lookback duration
@@ -949,9 +704,9 @@ The shortlist of configuration flags is the following:
-datasource.oauth2.tokenUrl string
Optional OAuth2 tokenURL to use for -datasource.url.
-datasource.queryStep duration
How far a value can fallback to when evaluating queries. For example, if -datasource.queryStep=15s then param "step" with value "15s" will be added to every query. If set to 0, rule's evaluation interval will be used instead. (default 5m0s)
queryStep defines how far a value can fallback to when evaluating queries. For example, if datasource.queryStep=15s then param "step" with value "15s" will be added to every query.If queryStep isn't specified, rule's evaluationInterval will be used instead.
-datasource.queryTimeAlignment
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 here https://github.com/VictoriaMetrics/VictoriaMetrics/pull/1257 (default true)
Whether to align "time" parameter with evaluation interval.Alignment supposed to produce deterministic results despite of number of vmalert replicas or time they were started. See more details here https://github.com/VictoriaMetrics/VictoriaMetrics/pull/1257 (default true)
-datasource.roundDigits int
Adds "round_digits" GET param to datasource requests. In VM "round_digits" limits the number of digits after the decimal point in response values.
-datasource.showURL
@@ -967,40 +722,41 @@ The shortlist of configuration flags is the following:
-datasource.tlsServerName string
Optional TLS server name to use for connections to -datasource.url. By default, the server name from -datasource.url is used
-datasource.url string
Datasource compatible with Prometheus HTTP API. It can be single node VictoriaMetrics or vmselect URL. Required parameter. E.g. http://127.0.0.1:8428 . See also -remoteRead.disablePathAppend and -datasource.showURL
Datasource compatible with Prometheus HTTP API. It can be single node VictoriaMetrics or vmselect URL. Required parameter. E.g. http://127.0.0.1:8428 . See also '-datasource.disablePathAppend', '-datasource.showURL'.
-defaultTenant.graphite string
Default tenant for Graphite alerting groups. See https://docs.victoriametrics.com/vmalert.html#multitenancy .This flag is available only in VictoriaMetrics enterprise. See https://docs.victoriametrics.com/enterprise.html
Default tenant for Graphite alerting groups. See https://docs.victoriametrics.com/vmalert.html#multitenancy
-defaultTenant.prometheus string
Default tenant for Prometheus alerting groups. See https://docs.victoriametrics.com/vmalert.html#multitenancy . This flag is available only in VictoriaMetrics enterprise. See https://docs.victoriametrics.com/enterprise.html
Default tenant for Prometheus alerting groups. See https://docs.victoriametrics.com/vmalert.html#multitenancy
-disableAlertgroupLabel
Whether to disable adding group's Name as label to generated alerts and time series.
-dryRun
-dryRun -rule
Whether to check only config files without running vmalert. The rules file are validated. The -rule flag must be specified.
-enableTCP6
Whether to enable IPv6 for listening and dialing. By default, only IPv4 TCP and UDP are used
Whether to enable IPv6 for listening and dialing. By default only IPv4 TCP and UDP is used
-envflag.enable
Whether to enable reading flags from environment variables in addition to the command line. Command line flag values have priority over values from environment vars. Flags are read only from the command line if this flag isn't set. See https://docs.victoriametrics.com/#environment-variables for more details
Whether to enable reading flags from environment variables additionally to command line. Command line flag values have priority over values from environment vars. Flags are read only from command line if this flag isn't set. See https://docs.victoriametrics.com/#environment-variables for more details
-envflag.prefix string
Prefix for environment variables if -envflag.enable is set
-eula
By specifying this flag, you confirm that you have an enterprise license and accept the EULA https://victoriametrics.com/assets/VM_EULA.pdf . This flag is available only in VictoriaMetrics enterprise. See https://docs.victoriametrics.com/enterprise.html
By specifying this flag, you confirm that you have an enterprise license and accept the EULA https://victoriametrics.com/assets/VM_EULA.pdf
-evaluationInterval duration
How often to evaluate the rules (default 1m0s)
-external.alert.source string
External Alert Source allows to override the Source link for alerts sent to AlertManager for cases where you want to build a custom link to Grafana, Prometheus or any other service. Supports templating - see https://docs.victoriametrics.com/vmalert.html#templating . For example, link to Grafana: -external.alert.source='explore?orgId=1&left={"datasource":"VictoriaMetrics","queries":[{"expr":{{$expr|jsonEscape|queryEscape}},"refId":"A"}],"range":{"from":"now-1h","to":"now"}}'. Link to VMUI: -external.alert.source='vmui/#/?g0.expr={{.Expr|queryEscape}}'. If empty 'vmalert/alert?group_id={{.GroupID}}&alert_id={{.AlertID}}' is used.
External 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. For example, link to Grafana: 'explore?orgId=1&left=[\"now-1h\",\"now\",\"VictoriaMetrics\",{\"expr\": \"{{$expr|quotesEscape|crlfEscape|queryEscape}}\"},{\"mode\":\"Metrics\"},{\"ui\":[true,true,true,\"none\"]}]'. (default "{{.ExternalURL}}/vmalert/alert?group_id={{.GroupID}}&alert_id={{.AlertID}}")
-external.label array
Optional label in the form 'Name=value' to add to all generated recording rules and alerts. Pass multiple -label flags in order to add multiple label sets.
Supports an array of values separated by comma or specified via multiple flags.
-external.url string
External URL is used as alert's source for sent alerts to the notifier. By default, hostname is used as address.
External URL is used as alert's source for sent alerts to the notifier
-flagsAuthKey string
Auth key for /flags endpoint. It must be passed via authKey query arg. It overrides httpAuth.* settings
-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()
Whether to use pread() instead of mmap() for reading data files. By default mmap() is used for 64-bit arches and pread() is used for 32-bit arches, since they cannot read data files bigger than 2^32 bytes in memory. mmap() is usually faster for reading small data chunks than pread()
-http.connTimeout duration
Incoming http connections are closed after the configured timeout. This may help to spread the incoming load among a cluster of services behind a load balancer. Please note that the real timeout may be bigger by up to 10% as a protection against the thundering herd problem (default 2m0s)
-http.disableResponseCompression
Disable compression of HTTP responses to save CPU resources. By default, compression is enabled to save network bandwidth
Disable compression of HTTP responses to save CPU resources. By default compression is enabled to save network bandwidth
-http.idleConnTimeout duration
Timeout for incoming idle http connections (default 1m0s)
-http.maxGracefulShutdownDuration duration
@@ -1010,27 +766,17 @@ The shortlist of configuration flags is the following:
-http.shutdownDelay duration
Optional delay before http server shutdown. During this delay, the server returns non-OK responses from /health page, so load balancers can route new requests to other servers
-httpAuth.password string
Password for HTTP server's Basic Auth. The authentication is disabled if -httpAuth.username is empty
Password for HTTP Basic Auth. The authentication is disabled if -httpAuth.username is empty
-httpAuth.username string
Username for HTTP server's Basic Auth. The authentication is disabled if empty. See also -httpAuth.password
Username for HTTP Basic Auth. The authentication is disabled if empty. See also -httpAuth.password
-httpListenAddr string
Address to listen for http connections. See also -httpListenAddr.useProxyProtocol (default ":8880")
-httpListenAddr.useProxyProtocol
Whether to use proxy protocol for connections accepted at -httpListenAddr . See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt . With enabled proxy protocol http server cannot serve regular /metrics endpoint. Use -pushmetrics.url for metrics pushing
-internStringCacheExpireDuration duration
The expiry duration for caches for interned strings. See https://en.wikipedia.org/wiki/String_interning . See also -internStringMaxLen and -internStringDisableCache (default 6m0s)
-internStringDisableCache
Whether to disable caches for interned strings. This may reduce memory usage at the cost of higher CPU usage. See https://en.wikipedia.org/wiki/String_interning . See also -internStringCacheExpireDuration and -internStringMaxLen
-internStringMaxLen int
The maximum length for strings to intern. 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)
Address to listen for http connections (default ":8880")
-loggerDisableTimestamps
Whether to disable writing timestamps in logs
-loggerErrorsPerSecondLimit int
Per-second limit on the number of ERROR messages. If more than the given number of errors are emitted per second, the remaining errors are suppressed. Zero values disable the rate limit
-loggerFormat string
Format for logs. Possible values: default, json (default "default")
-loggerJSONFields string
Allows renaming fields in JSON formatted logs. Example: "ts:timestamp,msg:message" renames "ts" to "timestamp" and "msg" to "message". Supported fields: ts, level, caller, msg
-loggerLevel string
Minimum level of errors to log. Possible values: INFO, WARN, ERROR, FATAL, PANIC (default "INFO")
-loggerOutput string
@@ -1040,10 +786,10 @@ The shortlist of configuration flags is the following:
-loggerWarnsPerSecondLimit int
Per-second limit on the number of WARN messages. If more than the given number of warns are emitted per second, then the remaining warns are suppressed. Zero values disable the rate limit
-memory.allowedBytes size
Allowed size of system memory VictoriaMetrics caches may occupy. This option overrides -memory.allowedPercent if set to a non-zero value. Too low a value may increase the cache miss rate usually resulting in higher CPU and disk IO usage. Too high a value may evict too much data from the OS page cache resulting in higher disk IO usage
Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB (default 0)
Allowed size of system memory VictoriaMetrics caches may occupy. This option overrides -memory.allowedPercent if set to a non-zero value. Too low a value may increase the cache miss rate usually resulting in higher CPU and disk IO usage. Too high a value may evict too much data from OS page cache resulting in higher disk IO usage
Supports the following optional suffixes for size values: KB, MB, GB, KiB, MiB, GiB (default 0)
-memory.allowedPercent float
Allowed percent of system memory VictoriaMetrics caches may occupy. See also -memory.allowedBytes. Too low a value may increase cache miss rate usually resulting in higher CPU and disk IO usage. Too high a value may evict too much data from the OS page cache which will result in higher disk IO usage (default 60)
Allowed percent of system memory VictoriaMetrics caches may occupy. See also -memory.allowedBytes. Too low a value may increase cache miss rate usually resulting in higher CPU and disk IO usage. Too high a value may evict too much data from OS page cache which will result in higher disk IO usage (default 60)
-metricsAuthKey string
Auth key for /metrics endpoint. It must be passed via authKey query arg. It overrides httpAuth.* settings
-notifier.basicAuth.password array
@@ -1081,7 +827,7 @@ The shortlist of configuration flags is the following:
-notifier.suppressDuplicateTargetErrors
Whether to suppress 'duplicate target' errors during discovery
-notifier.tlsCAFile array
Optional path to TLS CA file to use for verifying connections to -notifier.url. By default, system CA is used
Optional path to TLS CA file to use for verifying connections to -notifier.url. By default system CA is used
Supports an array of values separated by comma or specified via multiple flags.
-notifier.tlsCertFile array
Optional path to client-side TLS certificate file to use when connecting to -notifier.url
@@ -1093,32 +839,30 @@ The shortlist of configuration flags is the following:
Optional path to client-side TLS certificate key to use when connecting to -notifier.url
Supports an array of values separated by comma or specified via multiple flags.
-notifier.tlsServerName array
Optional TLS server name to use for connections to -notifier.url. By default, the server name from -notifier.url is used
Optional TLS server name to use for connections to -notifier.url. By default the server name from -notifier.url is used
Supports an array of values separated by comma or specified via multiple flags.
-notifier.url array
Prometheus Alertmanager URL, e.g. http://127.0.0.1:9093. List all Alertmanager URLs if it runs in the cluster mode to ensure high availability.
Prometheus alertmanager URL, e.g. http://127.0.0.1:9093
Supports an array of values separated by comma or specified via multiple flags.
-notifier.blackhole bool
Whether to blackhole alerting notifications. Enable this flag if you want vmalert to evaluate alerting rules without sending any notifications to external receivers (eg. alertmanager). `-notifier.url`, `-notifier.config` and `-notifier.blackhole` are mutually exclusive.
-pprofAuthKey string
Auth key for /debug/pprof/* endpoints. It must be passed via authKey query arg. It overrides httpAuth.* settings
-promscrape.consul.waitTime duration
Wait time used by Consul service discovery. Default value is used if not set
-promscrape.consulSDCheckInterval duration
Interval for checking for changes in Consul. This works only if consul_sd_configs is configured in '-promscrape.config' file. See https://docs.victoriametrics.com/sd_configs.html#consul_sd_configs for details (default 30s)
Interval for checking for changes in Consul. This works only if consul_sd_configs is configured in '-promscrape.config' file. See https://prometheus.io/docs/prometheus/latest/configuration/configuration/#consul_sd_config for details (default 30s)
-promscrape.discovery.concurrency int
The maximum number of concurrent requests to Prometheus autodiscovery API (Consul, Kubernetes, etc.) (default 100)
-promscrape.discovery.concurrentWaitTime duration
The maximum duration for waiting to perform API requests if more than -promscrape.discovery.concurrency requests are simultaneously performed (default 1m0s)
-promscrape.dnsSDCheckInterval duration
Interval for checking for changes in dns. This works only if dns_sd_configs is configured in '-promscrape.config' file. See https://docs.victoriametrics.com/sd_configs.html#dns_sd_configs for details (default 30s)
Interval for checking for changes in dns. This works only if dns_sd_configs is configured in '-promscrape.config' file. See https://prometheus.io/docs/prometheus/latest/configuration/configuration/#dns_sd_config for details (default 30s)
-pushmetrics.extraLabel array
Optional labels to add to metrics pushed to -pushmetrics.url . For example, -pushmetrics.extraLabel='instance="foo"' adds instance="foo" label to all the metrics pushed to -pushmetrics.url
Supports an array of values separated by comma or specified via multiple flags.
-pushmetrics.interval duration
Interval for pushing metrics to -pushmetrics.url (default 10s)
-pushmetrics.url array
Optional URL to push metrics exposed at /metrics page. See https://docs.victoriametrics.com/#push-metrics . By default, metrics exposed at /metrics page aren't pushed to any remote storage
Optional URL to push metrics exposed at /metrics page. See https://docs.victoriametrics.com/#push-metrics . By default metrics exposed at /metrics page aren't pushed to any remote storage
Supports an array of values separated by comma or specified via multiple flags.
-remoteRead.basicAuth.password string
Optional basic auth password for -remoteRead.url
@@ -1135,7 +879,7 @@ The shortlist of configuration flags is the following:
-remoteRead.headers string
Optional HTTP headers to send with each request to the corresponding -remoteRead.url. For example, -remoteRead.headers='My-Auth:foobar' would send 'My-Auth: foobar' HTTP header with every request to the corresponding -remoteRead.url. Multiple headers must be delimited by '^^': -remoteRead.headers='header1:value1^^header2:value2'
-remoteRead.ignoreRestoreErrors
Whether to ignore errors from remote storage when restoring alerts state on startup. DEPRECATED - this flag has no effect and will be removed in the next releases. (default true)
Whether to ignore errors from remote storage when restoring alerts state on startup. (default true)
-remoteRead.lookback duration
Lookback defines how far to look into past for alerts timeseries. For example, if lookback=1h then range from now() to now()-1h will be scanned. (default 1h0m0s)
-remoteRead.oauth2.clientID string
@@ -1151,7 +895,7 @@ The shortlist of configuration flags is the following:
-remoteRead.showURL
Whether to show -remoteRead.url in the exported metrics. It is hidden by default, since it can contain sensitive info such as auth key
-remoteRead.tlsCAFile string
Optional path to TLS CA file to use for verifying connections to -remoteRead.url. By default, system CA is used
Optional path to TLS CA file to use for verifying connections to -remoteRead.url. By default system CA is used
-remoteRead.tlsCertFile string
Optional path to client-side TLS certificate file to use when connecting to -remoteRead.url
-remoteRead.tlsInsecureSkipVerify
@@ -1159,7 +903,7 @@ The shortlist of configuration flags is the following:
-remoteRead.tlsKeyFile string
Optional path to client-side TLS certificate key to use when connecting to -remoteRead.url
-remoteRead.tlsServerName string
Optional TLS server name to use for connections to -remoteRead.url. By default, the server name from -remoteRead.url is used
Optional TLS server name to use for connections to -remoteRead.url. By default the server name from -remoteRead.url is used
-remoteRead.url vmalert
Optional URL to datasource compatible with Prometheus HTTP API. It can be single node VictoriaMetrics or vmselect.Remote read is used to restore alerts state.This configuration makes sense only if vmalert was configured with `remoteWrite.url` before and has been successfully persisted its state. E.g. http://127.0.0.1:8428. See also '-remoteRead.disablePathAppend', '-remoteRead.showURL'.
-remoteWrite.basicAuth.password string
@@ -1181,7 +925,7 @@ The shortlist of configuration flags is the following:
-remoteWrite.headers string
Optional HTTP headers to send with each request to the corresponding -remoteWrite.url. For example, -remoteWrite.headers='My-Auth:foobar' would send 'My-Auth: foobar' HTTP header with every request to the corresponding -remoteWrite.url. Multiple headers must be delimited by '^^': -remoteWrite.headers='header1:value1^^header2:value2'
-remoteWrite.maxBatchSize int
Defines max number of timeseries to be flushed at once (default 1000)
Defines defines max number of timeseries to be flushed at once (default 1000)
-remoteWrite.maxQueueSize int
Defines the max number of pending datapoints to remote write endpoint (default 100000)
-remoteWrite.oauth2.clientID string
@@ -1194,16 +938,10 @@ The shortlist of configuration flags is the following:
Optional OAuth2 scopes to use for -notifier.url. Scopes must be delimited by ';'.
-remoteWrite.oauth2.tokenUrl string
Optional OAuth2 tokenURL to use for -notifier.url.
-remoteWrite.retryMaxTime duration
The max time spent on retry attempts for the failed remote-write request. Change this value if it is expected for remoteWrite.url to be unreachable for more than -remoteWrite.retryMaxTime. See also -remoteWrite.retryMinInterval (default 30s)
-remoteWrite.retryMinInterval duration
The minimum delay between retry attempts. Every next retry attempt will double the delay to prevent hammering of remote database. See also -remoteWrite.retryMaxInterval (default 1s)
-remoteWrite.sendTimeout duration
Timeout for sending data to the configured -remoteWrite.url. (default 30s)
-remoteWrite.showURL
Whether to show -remoteWrite.url in the exported metrics. It is hidden by default, since it can contain sensitive info such as auth key
-remoteWrite.tlsCAFile string
Optional path to TLS CA file to use for verifying connections to -remoteWrite.url. By default, system CA is used
Optional path to TLS CA file to use for verifying connections to -remoteWrite.url. By default system CA is used
-remoteWrite.tlsCertFile string
Optional path to client-side TLS certificate file to use when connecting to -remoteWrite.url
-remoteWrite.tlsInsecureSkipVerify
@@ -1211,74 +949,48 @@ The shortlist of configuration flags is the following:
-remoteWrite.tlsKeyFile string
Optional path to client-side TLS certificate key to use when connecting to -remoteWrite.url
-remoteWrite.tlsServerName string
Optional TLS server name to use for connections to -remoteWrite.url. By default, the server name from -remoteWrite.url is used
Optional TLS server name to use for connections to -remoteWrite.url. By default the server name from -remoteWrite.url is used
-remoteWrite.url string
Optional URL to VictoriaMetrics or vminsert where to persist alerts state and recording rules results in form of timeseries. For example, if -remoteWrite.url=http://127.0.0.1:8428 is specified, then the alerts state will be written to http://127.0.0.1:8428/api/v1/write . See also -remoteWrite.disablePathAppend, '-remoteWrite.showURL'.
-replay.disableProgressBar
Whether to disable rendering progress bars during the replay. Progress bar rendering might be verbose or break the logs parsing, so it is recommended to be disabled when not used in interactive mode.
-replay.maxDatapointsPerQuery /query_range
Max number of data points expected in one request. It affects the max time range for every /query_range request during the replay. The higher the value, the less requests will be made during replay. (default 1000)
-replay.maxDatapointsPerQuery int
Max number of data points expected in one request. The higher the value, the less requests will be made during replay. (default 1000)
-replay.ruleRetryAttempts int
Defines how many retries to make before giving up on rule if request for it returns an error. (default 5)
-replay.rulesDelay duration
Delay between rules evaluation within the group. Could be important if there are chained rules inside the group and processing need to wait for previous rule results to be persisted by remote storage before evaluating the next rule.Keep it equal or bigger than -remoteWrite.flushInterval. (default 1s)
Delay between rules evaluation within the group. Could be important if there are chained rules inside of the groupand processing need to wait for previous rule results to be persisted by remote storage before evaluating the next rule.Keep it equal or bigger than -remoteWrite.flushInterval. (default 1s)
-replay.timeFrom string
The time filter in RFC3339 format to select time series with timestamp equal or higher than provided value. E.g. '2020-01-01T20:07:00Z'
-replay.timeTo string
The time filter in RFC3339 format to select timeseries with timestamp equal or lower than provided value. E.g. '2020-01-01T20:07:00Z'
-rule array
Path to the files or http url with alerting and/or recording rules.
Supports hierarchical patterns and regexpes.
Path to the file with alert rules.
Supports patterns. Flag can be specified multiple times.
Examples:
-rule="/path/to/file". Path to a single file with alerting rules.
-rule="http://<some-server-addr>/path/to/rules". HTTP URL to a page with alerting rules.
-rule="dir/*.yaml" -rule="/*.yaml" -rule="gcs://vmalert-rules/tenant_%{TENANT_ID}/prod".
-rule="dir/**/*.yaml". Includes all the .yaml files in "dir" subfolders recursively.
-rule="/path/to/file". Path to a single file with alerting rules
-rule="dir/*.yaml" -rule="/*.yaml". Relative path to all .yaml files in "dir" folder,
absolute path to all .yaml files in root.
Rule files may contain %{ENV_VAR} placeholders, which are substituted by the corresponding env vars.
Enterprise version of vmalert supports S3 and GCS paths to rules.
For example: gs://bucket/path/to/rules, s3://bucket/path/to/rules
S3 and GCS paths support only matching by prefix, e.g. s3://bucket/dir/rule_ matches
all files with prefix rule_ in folder dir.
See https://docs.victoriametrics.com/vmalert.html#reading-rules-from-object-storage
Supports an array of values separated by comma or specified via multiple flags.
-rule.configCheckInterval duration
Interval for checking for changes in '-rule' files. By default the checking is disabled. Send SIGHUP signal in order to force config check for changes. DEPRECATED - see '-configCheckInterval' instead
-rule.maxResolveDuration duration
Limits the maximum duration for automatic alert expiration, which by default is 4 times evaluationInterval of the parent group.
Limits the maximum duration for automatic alert expiration, which is by default equal to 3 evaluation intervals of the parent group.
-rule.resendDelay duration
Minimum amount of time to wait before resending an alert to notifier
-rule.templates array
Path or glob pattern to location with go template definitions
for rules annotations templating. Flag can be specified multiple times.
for rules annotations templating. Flag can be specified multiple times.
Examples:
-rule.templates="/path/to/file". Path to a single file with go templates
-rule.templates="dir/*.tpl" -rule.templates="/*.tpl". Relative path to all .tpl files in "dir" folder,
absolute path to all .tpl files in root.
-rule.templates="dir/**/*.tpl". Includes all the .tpl files in "dir" subfolders recursively.
Supports an array of values separated by comma or specified via multiple flags.
-rule.updateEntriesLimit int
Defines the max number of rule's state updates stored in-memory. Rule's updates are available on rule's Details page and are used for debugging purposes. The number of stored updates can be overridden per rule via update_entries_limit param. (default 20)
-rule.validateExpressions
Whether to validate rules expressions via MetricsQL engine (default true)
-rule.validateTemplates
Whether to validate annotation and label templates (default true)
-s2a_enable_appengine_dialer
If true, opportunistically use AppEngine-specific dialer to call S2A.
-s2a_timeout duration
Timeout enforced on the connection to the S2A service for handshake. (default 3s)
-s3.configFilePath string
Path to file with S3 configs. Configs are loaded from default location if not set.
See https://docs.aws.amazon.com/general/latest/gr/aws-security-credentials.html . This flag is available only in VictoriaMetrics enterprise. See https://docs.victoriametrics.com/enterprise.html
-s3.configProfile string
Profile name for S3 configs. If no set, the value of the environment variable will be loaded (AWS_PROFILE or AWS_DEFAULT_PROFILE), or if both not set, DefaultSharedConfigProfile is used. This flag is available only in VictoriaMetrics enterprise. See https://docs.victoriametrics.com/enterprise.html
-s3.credsFilePath string
Path to file with GCS or S3 credentials. Credentials are loaded from default locations if not set.
See https://cloud.google.com/iam/docs/creating-managing-service-account-keys and https://docs.aws.amazon.com/general/latest/gr/aws-security-credentials.html . This flag is available only in VictoriaMetrics enterprise. See https://docs.victoriametrics.com/enterprise.html
-s3.customEndpoint string
Custom S3 endpoint for use with S3-compatible storages (e.g. MinIO). S3 is used if not set. This flag is available only in VictoriaMetrics enterprise. See https://docs.victoriametrics.com/enterprise.html
-s3.forcePathStyle
Prefixing endpoint with bucket name when set false, true by default. This flag is available only in VictoriaMetrics enterprise. See https://docs.victoriametrics.com/enterprise.html (default true)
-tls
Whether to enable TLS for incoming HTTP requests at -httpListenAddr (aka https). -tlsCertFile and -tlsKeyFile must be set if -tls is set
-tlsCertFile string
@@ -1288,8 +1000,6 @@ The shortlist of configuration flags is the following:
Supports an array of values separated by comma or specified via multiple flags.
-tlsKeyFile string
Path to file with TLS key if -tls is set. The provided key file is automatically re-read every second, so it can be dynamically updated
-tlsMinVersion string
Optional minimum TLS version to use for incoming requests over HTTPS if -tls is set. Supported values: TLS10, TLS11, TLS12, TLS13
-version
Show VictoriaMetrics version
```
@@ -1339,8 +1049,8 @@ The configuration file allows to configure static notifiers, discover notifiers
and [DNS](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#dns_sd_config):
For example:
```yaml
static_configs:
```
static_configs:
- targets:
- localhost:9093
- localhost:9095
@@ -1349,7 +1059,7 @@ consul_sd_configs:
- server: localhost:8500
services:
- alertmanager
dns_sd_configs:
- names:
- my.domain.com
@@ -1357,14 +1067,12 @@ dns_sd_configs:
port: 9093
```
The list of configured or discovered Notifiers can be explored via [UI](#web).
If Alertmanager runs in cluster mode then all its URLs needs to be available during discovery
to ensure [high availability](https://github.com/prometheus/alertmanager#high-availability).
The list of configured or discovered Notifiers can be explored via [UI](#Web).
The configuration file [specification](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/app/vmalert/notifier/config.go)
is the following:
```yaml
```
# Per-target Notifier timeout when pushing alerts.
[ timeout: <duration> | default = 10s ]
@@ -1379,7 +1087,7 @@ is the following:
# password and password_file are mutually exclusive.
basic_auth:
[ username: <string> ]
[ password: <string> ]
[ password: <secret> ]
[ password_file: <string> ]
# Optional `Authorization` header configuration.
@@ -1398,41 +1106,10 @@ authorization:
tls_config:
[ <tls_config> ]
# Configures Bearer authentication token via string
bearer_token: <string>
# or by passing path to the file with token.
bearer_token_file: <string>
# Configures OAuth 2.0 authentication
# see https://prometheus.io/docs/prometheus/latest/configuration/configuration/#oauth2
oauth2:
[ <oauth2_config> ]
# Optional list of HTTP headers in form `header-name: value`
# applied for all requests to notifiers
# For example:
# headers:
# - "CustomHeader: foo"
# - "CustomHeader2: bar"
headers:
[ <string>, ...]
# List of labeled statically configured Notifiers.
#
# Each list of targets may be additionally instructed with
# authorization params. Target's authorization params will
# inherit params from global authorization params if there
# are no conflicts.
static_configs:
[ - targets: ]
[ - '<host>' ]
[ oauth2 ]
[ basic_auth ]
[ authorization ]
[ tls_config ]
[ bearer_token ]
[ bearer_token_file ]
[ headers ]
targets:
[ - '<host>' ]
# List of Consul service discovery configurations.
# See https://prometheus.io/docs/prometheus/latest/configuration/configuration/#consul_sd_config
@@ -1483,7 +1160,6 @@ docker push my-repo:my-version-name
```
To run the built image in `victoria-metrics-k8s-stack` or `VMAlert` CR object apply the following config change:
```yaml
kind: VMAlert
spec:
@@ -1494,14 +1170,14 @@ spec:
### Development build
1. [Install Go](https://golang.org/doc/install). The minimum supported version is Go 1.19.
1. Run `make vmalert` from the root folder of [the repository](https://github.com/VictoriaMetrics/VictoriaMetrics).
1. [Install Go](https://golang.org/doc/install). The minimum supported version is Go 1.18.
2. Run `make vmalert` from the root folder of [the repository](https://github.com/VictoriaMetrics/VictoriaMetrics).
It builds `vmalert` binary and puts it into the `bin` folder.
### Production build
1. [Install docker](https://docs.docker.com/install/).
1. Run `make vmalert-prod` from the root folder of [the repository](https://github.com/VictoriaMetrics/VictoriaMetrics).
2. Run `make vmalert-prod` from the root folder of [the repository](https://github.com/VictoriaMetrics/VictoriaMetrics).
It builds `vmalert-prod` binary and puts it into the `bin` folder.
### ARM build
@@ -1510,12 +1186,12 @@ ARM build may run on Raspberry Pi or on [energy-efficient ARM servers](https://b
### Development ARM build
1. [Install Go](https://golang.org/doc/install). The minimum supported version is Go 1.19.
1. Run `make vmalert-linux-arm` or `make vmalert-linux-arm64` from the root folder of [the repository](https://github.com/VictoriaMetrics/VictoriaMetrics).
1. [Install Go](https://golang.org/doc/install). The minimum supported version is Go 1.18.
2. Run `make vmalert-linux-arm` or `make vmalert-linux-arm64` from the root folder of [the repository](https://github.com/VictoriaMetrics/VictoriaMetrics).
It builds `vmalert-linux-arm` or `vmalert-linux-arm64` binary respectively and puts it into the `bin` folder.
### Production ARM build
1. [Install docker](https://docs.docker.com/install/).
1. Run `make vmalert-linux-arm-prod` or `make vmalert-linux-arm64-prod` from the root folder of [the repository](https://github.com/VictoriaMetrics/VictoriaMetrics).
2. Run `make vmalert-linux-arm-prod` or `make vmalert-linux-arm64-prod` from the root folder of [the repository](https://github.com/VictoriaMetrics/VictoriaMetrics).
It builds `vmalert-linux-arm-prod` or `vmalert-linux-arm64-prod` binary respectively and puts it into the `bin` folder.

View File

@@ -6,7 +6,6 @@ import (
"hash/fnv"
"sort"
"strconv"
"strings"
"sync"
"time"
@@ -21,76 +20,72 @@ import (
// AlertingRule is basic alert entity
type AlertingRule struct {
Type config.Type
RuleID uint64
Name string
Expr string
For time.Duration
KeepFiringFor time.Duration
Labels map[string]string
Annotations map[string]string
GroupID uint64
GroupName string
EvalInterval time.Duration
Debug bool
Type config.Type
RuleID uint64
Name string
Expr string
For time.Duration
Labels map[string]string
Annotations map[string]string
GroupID uint64
GroupName string
EvalInterval time.Duration
q datasource.Querier
alertsMu sync.RWMutex
// guard status fields
mu sync.RWMutex
// stores list of active alerts
alerts map[uint64]*notifier.Alert
// state stores recent state changes
// during evaluations
state *ruleState
// stores last moment of time Exec was called
lastExecTime time.Time
// stores the duration of the last Exec call
lastExecDuration time.Duration
// stores last error that happened in Exec func
// resets on every successful Exec
// may be used as Health state
lastExecError error
// stores the number of samples returned during
// the last evaluation
lastExecSamples int
metrics *alertingRuleMetrics
}
type alertingRuleMetrics struct {
errors *utils.Gauge
pending *utils.Gauge
active *utils.Gauge
samples *utils.Gauge
seriesFetched *utils.Gauge
errors *utils.Gauge
pending *utils.Gauge
active *utils.Gauge
samples *utils.Gauge
}
func newAlertingRule(qb datasource.QuerierBuilder, group *Group, cfg config.Rule) *AlertingRule {
ar := &AlertingRule{
Type: group.Type,
RuleID: cfg.ID,
Name: cfg.Alert,
Expr: cfg.Expr,
For: cfg.For.Duration(),
KeepFiringFor: cfg.KeepFiringFor.Duration(),
Labels: cfg.Labels,
Annotations: cfg.Annotations,
GroupID: group.ID(),
GroupName: group.Name,
EvalInterval: group.Interval,
Debug: cfg.Debug,
Type: group.Type,
RuleID: cfg.ID,
Name: cfg.Alert,
Expr: cfg.Expr,
For: cfg.For.Duration(),
Labels: cfg.Labels,
Annotations: cfg.Annotations,
GroupID: group.ID(),
GroupName: group.Name,
EvalInterval: group.Interval,
q: qb.BuildWithParams(datasource.QuerierParams{
DataSourceType: group.Type.String(),
EvaluationInterval: group.Interval,
QueryParams: group.Params,
Headers: group.Headers,
Debug: cfg.Debug,
}),
alerts: make(map[uint64]*notifier.Alert),
metrics: &alertingRuleMetrics{},
}
if cfg.UpdateEntriesLimit != nil {
ar.state = newRuleState(*cfg.UpdateEntriesLimit)
} else {
ar.state = newRuleState(*ruleUpdateEntriesLimit)
}
labels := fmt.Sprintf(`alertname=%q, group=%q, id="%d"`, ar.Name, group.Name, ar.ID())
ar.metrics.pending = utils.GetOrCreateGauge(fmt.Sprintf(`vmalert_alerts_pending{%s}`, labels),
func() float64 {
ar.alertsMu.RLock()
defer ar.alertsMu.RUnlock()
ar.mu.RLock()
defer ar.mu.RUnlock()
var num int
for _, a := range ar.alerts {
if a.State == notifier.StatePending {
@@ -101,8 +96,8 @@ func newAlertingRule(qb datasource.QuerierBuilder, group *Group, cfg config.Rule
})
ar.metrics.active = utils.GetOrCreateGauge(fmt.Sprintf(`vmalert_alerts_firing{%s}`, labels),
func() float64 {
ar.alertsMu.RLock()
defer ar.alertsMu.RUnlock()
ar.mu.RLock()
defer ar.mu.RUnlock()
var num int
for _, a := range ar.alerts {
if a.State == notifier.StateFiring {
@@ -113,31 +108,18 @@ func newAlertingRule(qb datasource.QuerierBuilder, group *Group, cfg config.Rule
})
ar.metrics.errors = utils.GetOrCreateGauge(fmt.Sprintf(`vmalert_alerting_rules_error{%s}`, labels),
func() float64 {
e := ar.state.getLast()
if e.err == nil {
ar.mu.RLock()
defer ar.mu.RUnlock()
if ar.lastExecError == nil {
return 0
}
return 1
})
ar.metrics.samples = utils.GetOrCreateGauge(fmt.Sprintf(`vmalert_alerting_rules_last_evaluation_samples{%s}`, labels),
func() float64 {
e := ar.state.getLast()
return float64(e.samples)
})
ar.metrics.seriesFetched = utils.GetOrCreateGauge(fmt.Sprintf(`vmalert_alerting_rules_last_evaluation_series_fetched{%s}`, labels),
func() float64 {
e := ar.state.getLast()
if e.seriesFetched == nil {
// means seriesFetched is unsupported
return -1
}
seriesFetched := float64(*e.seriesFetched)
if seriesFetched == 0 && e.samples > 0 {
// `alert: 0.95` will fetch no series
// but will get one time series in response.
seriesFetched = float64(e.samples)
}
return seriesFetched
ar.mu.RLock()
defer ar.mu.RUnlock()
return float64(ar.lastExecSamples)
})
return ar
}
@@ -148,7 +130,6 @@ func (ar *AlertingRule) Close() {
ar.metrics.pending.Unregister()
ar.metrics.errors.Unregister()
ar.metrics.samples.Unregister()
ar.metrics.seriesFetched.Unregister()
}
// String implements Stringer interface
@@ -162,42 +143,12 @@ func (ar *AlertingRule) ID() uint64 {
return ar.RuleID
}
func (ar *AlertingRule) logDebugf(at time.Time, a *notifier.Alert, format string, args ...interface{}) {
if !ar.Debug {
return
}
prefix := fmt.Sprintf("DEBUG rule %q:%q (%d) at %v: ",
ar.GroupName, ar.Name, ar.RuleID, at.Format(time.RFC3339))
if a != nil {
labelKeys := make([]string, len(a.Labels))
var i int
for k := range a.Labels {
labelKeys[i] = k
i++
}
sort.Strings(labelKeys)
labels := make([]string, len(labelKeys))
for i, l := range labelKeys {
labels[i] = fmt.Sprintf("%s=%q", l, a.Labels[l])
}
labelsStr := strings.Join(labels, ",")
prefix += fmt.Sprintf("alert %d {%s} ", a.ID, labelsStr)
}
msg := fmt.Sprintf(format, args...)
logger.Infof("%s", prefix+msg)
}
type labelSet struct {
// origin labels extracted from received time series
// plus extra labels (group labels, service labels like alertNameLabel).
// in case of conflicts, origin labels from time series preferred.
// used for templating annotations
// origin labels from series
// used for templating
origin map[string]string
// processed labels includes origin labels
// plus extra labels (group labels, service labels like alertNameLabel).
// in case of conflicts, extra labels are preferred.
// used as labels attached to notifier.Alert and ALERTS series written to remote storage.
// processed labels with additional data
// used as Alert labels
processed map[string]string
}
@@ -205,7 +156,7 @@ type labelSet struct {
// to labelSet which contains original and processed labels.
func (ar *AlertingRule) toLabels(m datasource.Metric, qFn templates.QueryFn) (*labelSet, error) {
ls := &labelSet{
origin: make(map[string]string),
origin: make(map[string]string, len(m.Labels)),
processed: make(map[string]string),
}
for _, l := range m.Labels {
@@ -227,23 +178,14 @@ func (ar *AlertingRule) toLabels(m datasource.Metric, qFn templates.QueryFn) (*l
}
for k, v := range extraLabels {
ls.processed[k] = v
if _, ok := ls.origin[k]; !ok {
ls.origin[k] = v
}
}
// set additional labels to identify group and rule name
if ar.Name != "" {
ls.processed[alertNameLabel] = ar.Name
if _, ok := ls.origin[alertNameLabel]; !ok {
ls.origin[alertNameLabel] = ar.Name
}
}
if !*disableAlertGroupLabel && ar.GroupName != "" {
ls.processed[alertGroupNameLabel] = ar.GroupName
if _, ok := ls.origin[alertGroupNameLabel]; !ok {
ls.origin[alertGroupNameLabel] = ar.GroupName
}
}
return ls, nil
}
@@ -253,7 +195,7 @@ func (ar *AlertingRule) toLabels(m datasource.Metric, qFn templates.QueryFn) (*l
// to get time series for backfilling.
// It returns ALERT and ALERT_FOR_STATE time series as result.
func (ar *AlertingRule) ExecRange(ctx context.Context, start, end time.Time) ([]prompbmarshal.TimeSeries, error) {
res, err := ar.q.QueryRange(ctx, ar.Expr, start, end)
series, err := ar.q.QueryRange(ctx, ar.Expr, start, end)
if err != nil {
return nil, err
}
@@ -261,7 +203,7 @@ func (ar *AlertingRule) ExecRange(ctx context.Context, start, end time.Time) ([]
qFn := func(query string) ([]datasource.Metric, error) {
return nil, fmt.Errorf("`query` template isn't supported in replay mode")
}
for _, s := range res.Data {
for _, s := range series {
a, err := ar.newAlert(s, nil, time.Time{}, qFn) // initial alert
if err != nil {
return nil, fmt.Errorf("failed to create alert: %s", err)
@@ -301,56 +243,39 @@ const resolvedRetention = 15 * time.Minute
// Based on the Querier results AlertingRule maintains notifier.Alerts
func (ar *AlertingRule) Exec(ctx context.Context, ts time.Time, limit int) ([]prompbmarshal.TimeSeries, error) {
start := time.Now()
res, req, err := ar.q.Query(ctx, ar.Expr, ts)
curState := ruleStateEntry{
time: start,
at: ts,
duration: time.Since(start),
samples: len(res.Data),
seriesFetched: res.SeriesFetched,
err: err,
curl: requestToCurl(req),
}
defer func() {
ar.state.add(curState)
}()
ar.alertsMu.Lock()
defer ar.alertsMu.Unlock()
qMetrics, err := ar.q.Query(ctx, ar.Expr, ts)
ar.mu.Lock()
defer ar.mu.Unlock()
ar.lastExecTime = start
ar.lastExecDuration = time.Since(start)
ar.lastExecError = err
ar.lastExecSamples = len(qMetrics)
if err != nil {
return nil, fmt.Errorf("failed to execute query %q: %w", ar.Expr, err)
}
ar.logDebugf(ts, nil, "query returned %d samples (elapsed: %s)", curState.samples, curState.duration)
for h, a := range ar.alerts {
// cleanup inactive alerts from previous Exec
if a.State == notifier.StateInactive && ts.Sub(a.ResolvedAt) > resolvedRetention {
ar.logDebugf(ts, a, "deleted as inactive")
delete(ar.alerts, h)
}
}
qFn := func(query string) ([]datasource.Metric, error) {
res, _, err := ar.q.Query(ctx, query, ts)
return res.Data, err
}
qFn := func(query string) ([]datasource.Metric, error) { return ar.q.Query(ctx, query, ts) }
updated := make(map[uint64]struct{})
// update list of active alerts
for _, m := range res.Data {
for _, m := range qMetrics {
ls, err := ar.toLabels(m, qFn)
if err != nil {
curState.err = fmt.Errorf("failed to expand labels: %s", err)
return nil, curState.err
return nil, fmt.Errorf("failed to expand labels: %s", err)
}
h := hash(ls.processed)
if _, ok := updated[h]; ok {
// duplicate may be caused by extra labels
// conflicting with the metric labels
curState.err = fmt.Errorf("labels %v: %w", ls.processed, errDuplicate)
return nil, curState.err
ar.lastExecError = fmt.Errorf("labels %v: %w", ls.processed, errDuplicate)
return nil, ar.lastExecError
}
updated[h] = struct{}{}
if a, ok := ar.alerts[h]; ok {
@@ -360,27 +285,28 @@ func (ar *AlertingRule) Exec(ctx context.Context, ts time.Time, limit int) ([]pr
// back to notifier.StatePending
a.State = notifier.StatePending
a.ActiveAt = ts
ar.logDebugf(ts, a, "INACTIVE => PENDING")
}
a.Value = m.Values[0]
// re-exec template since Value or query can be used in annotations
a.Annotations, err = a.ExecTemplate(qFn, ls.origin, ar.Annotations)
if err != nil {
return nil, err
if a.Value != m.Values[0] {
// update Value field with latest value
a.Value = m.Values[0]
// and re-exec template since Value can be used
// in annotations
a.Annotations, err = a.ExecTemplate(qFn, ls.origin, ar.Annotations)
if err != nil {
return nil, err
}
}
a.KeepFiringSince = time.Time{}
continue
}
a, err := ar.newAlert(m, ls, start, qFn)
a, err := ar.newAlert(m, ls, ar.lastExecTime, qFn)
if err != nil {
curState.err = fmt.Errorf("failed to create alert: %w", err)
return nil, curState.err
ar.lastExecError = err
return nil, fmt.Errorf("failed to create alert: %w", err)
}
a.ID = h
a.State = notifier.StatePending
a.ActiveAt = ts
ar.alerts[h] = a
ar.logDebugf(ts, a, "created in state PENDING")
}
var numActivePending int
for h, a := range ar.alerts {
@@ -391,40 +317,24 @@ func (ar *AlertingRule) Exec(ctx context.Context, ts time.Time, limit int) ([]pr
// alert was in Pending state - it is not
// active anymore
delete(ar.alerts, h)
ar.logDebugf(ts, a, "PENDING => DELETED: is absent in current evaluation round")
continue
}
// check if alert should keep StateFiring if rule has
// `keep_firing_for` field
if a.State == notifier.StateFiring {
if ar.KeepFiringFor > 0 {
if a.KeepFiringSince.IsZero() {
a.KeepFiringSince = ts
}
}
// alerts with ar.KeepFiringFor>0 may remain FIRING
// even if their expression isn't true anymore
if ts.Sub(a.KeepFiringSince) > ar.KeepFiringFor {
a.State = notifier.StateInactive
a.ResolvedAt = ts
ar.logDebugf(ts, a, "FIRING => INACTIVE: is absent in current evaluation round")
continue
}
ar.logDebugf(ts, a, "KEEP_FIRING: will keep firing for %fs since %v", ar.KeepFiringFor.Seconds(), a.KeepFiringSince)
a.State = notifier.StateInactive
a.ResolvedAt = ts
}
continue
}
numActivePending++
if a.State == notifier.StatePending && ts.Sub(a.ActiveAt) >= ar.For {
a.State = notifier.StateFiring
a.Start = ts
alertsFired.Inc()
ar.logDebugf(ts, a, "PENDING => FIRING: %s since becoming active at %v", ts.Sub(a.ActiveAt), a.ActiveAt)
}
}
if limit > 0 && numActivePending > limit {
ar.alerts = map[uint64]*notifier.Alert{}
curState.err = fmt.Errorf("exec exceeded limit of %d with %d alerts", limit, numActivePending)
return nil, curState.err
return nil, fmt.Errorf("exec exceeded limit of %d with %d alerts", limit, numActivePending)
}
return ar.toTimeSeries(ts.Unix()), nil
}
@@ -451,13 +361,10 @@ func (ar *AlertingRule) UpdateWith(r Rule) error {
}
ar.Expr = nr.Expr
ar.For = nr.For
ar.KeepFiringFor = nr.KeepFiringFor
ar.Labels = nr.Labels
ar.Annotations = nr.Annotations
ar.EvalInterval = nr.EvalInterval
ar.Debug = nr.Debug
ar.q = nr.q
ar.state = nr.state
return nil
}
@@ -497,7 +404,6 @@ func (ar *AlertingRule) newAlert(m datasource.Metric, ls *labelSet, start time.T
Value: m.Values[0],
ActiveAt: start,
Expr: ar.Expr,
For: ar.For,
}
a.Annotations, err = a.ExecTemplate(qFn, ls.origin, ar.Annotations)
return a, err
@@ -505,8 +411,8 @@ func (ar *AlertingRule) newAlert(m datasource.Metric, ls *labelSet, start time.T
// AlertAPI generates APIAlert object from alert by its id(hash)
func (ar *AlertingRule) AlertAPI(id uint64) *APIAlert {
ar.alertsMu.RLock()
defer ar.alertsMu.RUnlock()
ar.mu.RLock()
defer ar.mu.RUnlock()
a, ok := ar.alerts[id]
if !ok {
return nil
@@ -514,36 +420,30 @@ func (ar *AlertingRule) AlertAPI(id uint64) *APIAlert {
return ar.newAlertAPI(*a)
}
// ToAPI returns Rule representation in form of APIRule
// Isn't thread-safe. Call must be protected by AlertingRule mutex.
// ToAPI returns Rule representation in form
// of APIRule
func (ar *AlertingRule) ToAPI() APIRule {
lastState := ar.state.getLast()
r := APIRule{
Type: "alerting",
DatasourceType: ar.Type.String(),
Name: ar.Name,
Query: ar.Expr,
Duration: ar.For.Seconds(),
KeepFiringFor: ar.KeepFiringFor.Seconds(),
Labels: ar.Labels,
Annotations: ar.Annotations,
LastEvaluation: lastState.time,
EvaluationTime: lastState.duration.Seconds(),
Health: "ok",
State: "inactive",
Alerts: ar.AlertsToAPI(),
LastSamples: lastState.samples,
LastSeriesFetched: lastState.seriesFetched,
MaxUpdates: ar.state.size(),
Updates: ar.state.getAll(),
Debug: ar.Debug,
Type: "alerting",
DatasourceType: ar.Type.String(),
Name: ar.Name,
Query: ar.Expr,
Duration: ar.For.Seconds(),
Labels: ar.Labels,
Annotations: ar.Annotations,
LastEvaluation: ar.lastExecTime,
EvaluationTime: ar.lastExecDuration.Seconds(),
Health: "ok",
State: "inactive",
Alerts: ar.AlertsToAPI(),
LastSamples: ar.lastExecSamples,
// encode as strings to avoid rounding in JSON
ID: fmt.Sprintf("%d", ar.ID()),
GroupID: fmt.Sprintf("%d", ar.GroupID),
}
if lastState.err != nil {
r.LastError = lastState.err.Error()
if ar.lastExecError != nil {
r.LastError = ar.lastExecError.Error()
r.Health = "err"
}
// satisfy APIRule.State logic
@@ -563,14 +463,14 @@ func (ar *AlertingRule) ToAPI() APIRule {
// AlertsToAPI generates list of APIAlert objects from existing alerts
func (ar *AlertingRule) AlertsToAPI() []*APIAlert {
var alerts []*APIAlert
ar.alertsMu.RLock()
ar.mu.RLock()
for _, a := range ar.alerts {
if a.State == notifier.StateInactive {
continue
}
alerts = append(alerts, ar.newAlertAPI(*a))
}
ar.alertsMu.RUnlock()
ar.mu.RUnlock()
return alerts
}
@@ -593,9 +493,6 @@ func (ar *AlertingRule) newAlertAPI(a notifier.Alert) *APIAlert {
if alertURLGeneratorFn != nil {
aa.SourceLink = alertURLGeneratorFn(a)
}
if a.State == notifier.StateFiring && !a.KeepFiringSince.IsZero() {
aa.Stabilizing = true
}
return aa
}
@@ -646,60 +543,51 @@ func alertForToTimeSeries(a *notifier.Alert, timestamp int64) prompbmarshal.Time
return newTimeSeries([]float64{float64(a.ActiveAt.Unix())}, []int64{timestamp}, labels)
}
// Restore restores the value of ActiveAt field for active alerts,
// based on previously written time series `alertForStateMetricName`.
// Only rules with For > 0 can be restored.
func (ar *AlertingRule) Restore(ctx context.Context, q datasource.Querier, ts time.Time, lookback time.Duration) error {
if ar.For < 1 {
return nil
// Restore restores the state of active alerts basing on previously written time series.
// Restore restores only ActiveAt field. Field State will be always Pending and supposed
// to be updated on next Exec, as well as Value field.
// Only rules with For > 0 will be restored.
func (ar *AlertingRule) Restore(ctx context.Context, q datasource.Querier, lookback time.Duration, labels map[string]string) error {
if q == nil {
return fmt.Errorf("querier is nil")
}
ar.alertsMu.Lock()
defer ar.alertsMu.Unlock()
ts := time.Now()
qFn := func(query string) ([]datasource.Metric, error) { return ar.q.Query(ctx, query, ts) }
if len(ar.alerts) < 1 {
return nil
// account for external labels in filter
var labelsFilter string
for k, v := range labels {
labelsFilter += fmt.Sprintf(",%s=%q", k, v)
}
for _, a := range ar.alerts {
if a.Restored || a.State != notifier.StatePending {
continue
expr := fmt.Sprintf("last_over_time(%s{alertname=%q%s}[%ds])",
alertForStateMetricName, ar.Name, labelsFilter, int(lookback.Seconds()))
qMetrics, err := q.Query(ctx, expr, ts)
if err != nil {
return err
}
for _, m := range qMetrics {
ls := &labelSet{
origin: make(map[string]string, len(m.Labels)),
processed: make(map[string]string, len(m.Labels)),
}
var labelsFilter []string
for k, v := range a.Labels {
labelsFilter = append(labelsFilter, fmt.Sprintf("%s=%q", k, v))
for _, l := range m.Labels {
if l.Name == "__name__" {
continue
}
ls.origin[l.Name] = l.Value
ls.processed[l.Name] = l.Value
}
sort.Strings(labelsFilter)
expr := fmt.Sprintf("last_over_time(%s{%s}[%ds])",
alertForStateMetricName, strings.Join(labelsFilter, ","), int(lookback.Seconds()))
ar.logDebugf(ts, nil, "restoring alert state via query %q", expr)
res, _, err := q.Query(ctx, expr, ts)
a, err := ar.newAlert(m, ls, time.Unix(int64(m.Values[0]), 0), qFn)
if err != nil {
return err
return fmt.Errorf("failed to create alert: %w", err)
}
qMetrics := res.Data
if len(qMetrics) < 1 {
ar.logDebugf(ts, nil, "no response was received from restore query")
continue
}
// only one series expected in response
m := qMetrics[0]
// __name__ supposed to be alertForStateMetricName
m.DelLabel("__name__")
// we assume that restore query contains all label matchers,
// so all received labels will match anyway if their number is equal.
if len(m.Labels) != len(a.Labels) {
ar.logDebugf(ts, nil, "state restore query returned not expected label-set %v", m.Labels)
continue
}
a.ActiveAt = time.Unix(int64(m.Values[0]), 0)
a.ID = hash(ls.processed)
a.State = notifier.StatePending
a.Restored = true
ar.alerts[a.ID] = a
logger.Infof("alert %q (%d) restored to state at %v", a.Name, a.ID, a.ActiveAt)
}
return nil

View File

@@ -6,15 +6,12 @@ import (
"reflect"
"sort"
"strings"
"sync"
"testing"
"time"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/config"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promutils"
)
func TestAlertingRule_ToTimeSeries(t *testing.T) {
@@ -113,7 +110,7 @@ func TestAlertingRule_Exec(t *testing.T) {
testCases := []struct {
rule *AlertingRule
steps [][]datasource.Metric
expAlerts map[int][]testAlert
expAlerts []testAlert
}{
{
newTestAlertingRule("empty", 0),
@@ -125,8 +122,50 @@ func TestAlertingRule_Exec(t *testing.T) {
[][]datasource.Metric{
{datasource.Metric{Values: []float64{1}, Timestamps: []int64{1}}},
},
map[int][]testAlert{
0: {{alert: &notifier.Alert{State: notifier.StateFiring}}},
[]testAlert{
{alert: &notifier.Alert{State: notifier.StateFiring}},
},
},
{
newTestAlertingRule("single-firing", 0),
[][]datasource.Metric{
{metricWithLabels(t, "name", "foo")},
},
[]testAlert{
{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateFiring}},
},
},
{
newTestAlertingRule("single-firing=>inactive", 0),
[][]datasource.Metric{
{metricWithLabels(t, "name", "foo")},
{},
},
[]testAlert{
{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateInactive}},
},
},
{
newTestAlertingRule("single-firing=>inactive=>firing", 0),
[][]datasource.Metric{
{metricWithLabels(t, "name", "foo")},
{},
{metricWithLabels(t, "name", "foo")},
},
[]testAlert{
{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateFiring}},
},
},
{
newTestAlertingRule("single-firing=>inactive=>firing=>inactive", 0),
[][]datasource.Metric{
{metricWithLabels(t, "name", "foo")},
{},
{metricWithLabels(t, "name", "foo")},
{},
},
[]testAlert{
{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateInactive}},
},
},
{
@@ -138,16 +177,12 @@ func TestAlertingRule_Exec(t *testing.T) {
{},
{},
},
map[int][]testAlert{
0: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateFiring}}},
1: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateInactive}}},
2: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateFiring}}},
3: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateInactive}}},
4: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateInactive}}},
[]testAlert{
{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateInactive}},
},
},
{
newTestAlertingRule("single-firing=>inactive=>firing=>inactive=>inactive=>firing", 0),
newTestAlertingRule("single-firing=>inactive=>firing=>inactive=>empty=>firing", 0),
[][]datasource.Metric{
{metricWithLabels(t, "name", "foo")},
{},
@@ -156,13 +191,8 @@ func TestAlertingRule_Exec(t *testing.T) {
{},
{metricWithLabels(t, "name", "foo")},
},
map[int][]testAlert{
0: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateFiring}}},
1: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateInactive}}},
2: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateFiring}}},
3: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateInactive}}},
4: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateInactive}}},
5: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateFiring}}},
[]testAlert{
{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateFiring}},
},
},
{
@@ -174,12 +204,10 @@ func TestAlertingRule_Exec(t *testing.T) {
metricWithLabels(t, "name", "foo2"),
},
},
map[int][]testAlert{
0: {
{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateFiring}},
{labels: []string{"name", "foo1"}, alert: &notifier.Alert{State: notifier.StateFiring}},
{labels: []string{"name", "foo2"}, alert: &notifier.Alert{State: notifier.StateFiring}},
},
[]testAlert{
{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateFiring}},
{labels: []string{"name", "foo1"}, alert: &notifier.Alert{State: notifier.StateFiring}},
{labels: []string{"name", "foo2"}, alert: &notifier.Alert{State: notifier.StateFiring}},
},
},
{
@@ -192,19 +220,10 @@ func TestAlertingRule_Exec(t *testing.T) {
// 1: fire first alert
// 2: fire second alert, set first inactive
// 3: fire third alert, set second inactive
map[int][]testAlert{
0: {
{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateFiring}},
},
1: {
{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateInactive}},
{labels: []string{"name", "foo1"}, alert: &notifier.Alert{State: notifier.StateFiring}},
},
2: {
{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateInactive}},
{labels: []string{"name", "foo1"}, alert: &notifier.Alert{State: notifier.StateInactive}},
{labels: []string{"name", "foo2"}, alert: &notifier.Alert{State: notifier.StateFiring}},
},
[]testAlert{
{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateInactive}},
{labels: []string{"name", "foo1"}, alert: &notifier.Alert{State: notifier.StateInactive}},
{labels: []string{"name", "foo2"}, alert: &notifier.Alert{State: notifier.StateFiring}},
},
},
{
@@ -212,8 +231,8 @@ func TestAlertingRule_Exec(t *testing.T) {
[][]datasource.Metric{
{metricWithLabels(t, "name", "foo")},
},
map[int][]testAlert{
0: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StatePending}}},
[]testAlert{
{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StatePending}},
},
},
{
@@ -222,9 +241,8 @@ func TestAlertingRule_Exec(t *testing.T) {
{metricWithLabels(t, "name", "foo")},
{metricWithLabels(t, "name", "foo")},
},
map[int][]testAlert{
0: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StatePending}}},
1: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateFiring}}},
[]testAlert{
{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateFiring}},
},
},
{
@@ -232,13 +250,34 @@ func TestAlertingRule_Exec(t *testing.T) {
[][]datasource.Metric{
{metricWithLabels(t, "name", "foo")},
{metricWithLabels(t, "name", "foo")},
// empty step to delete pending alerts
// empty step to reset and delete pending alerts
{},
},
map[int][]testAlert{
0: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StatePending}}},
1: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StatePending}}},
2: {},
nil,
},
{
newTestAlertingRule("for-pending=>firing=>inactive", defaultStep),
[][]datasource.Metric{
{metricWithLabels(t, "name", "foo")},
{metricWithLabels(t, "name", "foo")},
// empty step to reset pending alerts
{},
},
[]testAlert{
{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateInactive}},
},
},
{
newTestAlertingRule("for-pending=>firing=>inactive=>pending", defaultStep),
[][]datasource.Metric{
{metricWithLabels(t, "name", "foo")},
{metricWithLabels(t, "name", "foo")},
// empty step to reset pending alerts
{},
{metricWithLabels(t, "name", "foo")},
},
[]testAlert{
{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StatePending}},
},
},
{
@@ -246,57 +285,13 @@ func TestAlertingRule_Exec(t *testing.T) {
[][]datasource.Metric{
{metricWithLabels(t, "name", "foo")},
{metricWithLabels(t, "name", "foo")},
// empty step to set alert inactive
// empty step to reset pending alerts
{},
{metricWithLabels(t, "name", "foo")},
{metricWithLabels(t, "name", "foo")},
},
map[int][]testAlert{
0: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StatePending}}},
1: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateFiring}}},
2: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateInactive}}},
3: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StatePending}}},
4: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateFiring}}},
},
},
{
newTestAlertingRuleWithKeepFiring("for-pending=>firing=>keepfiring=>firing", defaultStep, defaultStep),
[][]datasource.Metric{
{metricWithLabels(t, "name", "foo")},
{metricWithLabels(t, "name", "foo")},
// empty step to keep firing
{},
{metricWithLabels(t, "name", "foo")},
},
map[int][]testAlert{
0: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StatePending}}},
1: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateFiring}}},
2: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateFiring}}},
3: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateFiring}}},
},
},
{
newTestAlertingRuleWithKeepFiring("for-pending=>firing=>keepfiring=>keepfiring=>inactive=>pending=>firing", defaultStep, 2*defaultStep),
[][]datasource.Metric{
{metricWithLabels(t, "name", "foo")},
{metricWithLabels(t, "name", "foo")},
// empty step to keep firing
{},
// another empty step to keep firing
{},
// empty step to set alert inactive
{},
{metricWithLabels(t, "name", "foo")},
{metricWithLabels(t, "name", "foo")},
},
map[int][]testAlert{
0: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StatePending}}},
1: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateFiring}}},
2: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateFiring}}},
3: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateFiring}}},
4: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateInactive}}},
5: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StatePending}}},
6: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateFiring}}},
[]testAlert{
{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateFiring}},
},
},
}
@@ -306,7 +301,7 @@ func TestAlertingRule_Exec(t *testing.T) {
fq := &fakeQuerier{}
tc.rule.q = fq
tc.rule.GroupID = fakeGroup.ID()
for i, step := range tc.steps {
for _, step := range tc.steps {
fq.reset()
fq.add(step...)
if _, err := tc.rule.Exec(context.TODO(), time.Now(), 0); err != nil {
@@ -314,31 +309,28 @@ func TestAlertingRule_Exec(t *testing.T) {
}
// artificial delay between applying steps
time.Sleep(defaultStep)
if _, ok := tc.expAlerts[i]; !ok {
continue
}
if len(tc.rule.alerts) != len(tc.expAlerts) {
t.Fatalf("expected %d alerts; got %d", len(tc.expAlerts), len(tc.rule.alerts))
}
expAlerts := make(map[uint64]*notifier.Alert)
for _, ta := range tc.expAlerts {
labels := make(map[string]string)
for i := 0; i < len(ta.labels); i += 2 {
k, v := ta.labels[i], ta.labels[i+1]
labels[k] = v
}
if len(tc.rule.alerts) != len(tc.expAlerts[i]) {
t.Fatalf("evalIndex %d: expected %d alerts; got %d", i, len(tc.expAlerts[i]), len(tc.rule.alerts))
labels[alertNameLabel] = tc.rule.Name
h := hash(labels)
expAlerts[h] = ta.alert
}
for key, exp := range expAlerts {
got, ok := tc.rule.alerts[key]
if !ok {
t.Fatalf("expected to have key %d", key)
}
expAlerts := make(map[uint64]*notifier.Alert)
for _, ta := range tc.expAlerts[i] {
labels := make(map[string]string)
for i := 0; i < len(ta.labels); i += 2 {
k, v := ta.labels[i], ta.labels[i+1]
labels[k] = v
}
labels[alertNameLabel] = tc.rule.Name
h := hash(labels)
expAlerts[h] = ta.alert
}
for key, exp := range expAlerts {
got, ok := tc.rule.alerts[key]
if !ok {
t.Fatalf("evalIndex %d: expected to have key %d", i, key)
}
if got.State != exp.State {
t.Fatalf("evalIndex %d: expected state %d; got %d", i, exp.State, got.State)
}
if got.State != exp.State {
t.Fatalf("expected state %d; got %d", exp.State, got.State)
}
}
})
@@ -510,156 +502,118 @@ func TestAlertingRule_ExecRange(t *testing.T) {
}
}
func TestGroup_Restore(t *testing.T) {
defaultTS := time.Now()
fqr := &fakeQuerierWithRegistry{}
fn := func(rules []config.Rule, expAlerts map[uint64]*notifier.Alert) {
t.Helper()
defer fqr.reset()
for _, r := range rules {
fqr.set(r.Expr, metricWithValueAndLabels(t, 0, "__name__", r.Alert))
}
fg := newGroup(config.Group{Name: "TestRestore", Rules: rules}, fqr, time.Second, nil)
wg := sync.WaitGroup{}
wg.Add(1)
go func() {
nts := func() []notifier.Notifier { return []notifier.Notifier{&fakeNotifier{}} }
fg.start(context.Background(), nts, nil, fqr)
wg.Done()
}()
fg.close()
wg.Wait()
gotAlerts := make(map[uint64]*notifier.Alert)
for _, rs := range fg.Rules {
alerts := rs.(*AlertingRule).alerts
for k, v := range alerts {
if !v.Restored {
// set not restored alerts to predictable timestamp
v.ActiveAt = defaultTS
func TestAlertingRule_Restore(t *testing.T) {
testCases := []struct {
rule *AlertingRule
metrics []datasource.Metric
expAlerts map[uint64]*notifier.Alert
}{
{
newTestRuleWithLabels("no extra labels"),
[]datasource.Metric{
metricWithValueAndLabels(t, float64(time.Now().Truncate(time.Hour).Unix()),
"__name__", alertForStateMetricName,
),
},
map[uint64]*notifier.Alert{
hash(nil): {State: notifier.StatePending,
ActiveAt: time.Now().Truncate(time.Hour)},
},
},
{
newTestRuleWithLabels("metric labels"),
[]datasource.Metric{
metricWithValueAndLabels(t, float64(time.Now().Truncate(time.Hour).Unix()),
"__name__", alertForStateMetricName,
alertNameLabel, "metric labels",
alertGroupNameLabel, "groupID",
"foo", "bar",
"namespace", "baz",
),
},
map[uint64]*notifier.Alert{
hash(map[string]string{
alertNameLabel: "metric labels",
alertGroupNameLabel: "groupID",
"foo": "bar",
"namespace": "baz",
}): {State: notifier.StatePending,
ActiveAt: time.Now().Truncate(time.Hour)},
},
},
{
newTestRuleWithLabels("rule labels", "source", "vm"),
[]datasource.Metric{
metricWithValueAndLabels(t, float64(time.Now().Truncate(time.Hour).Unix()),
"__name__", alertForStateMetricName,
"foo", "bar",
"namespace", "baz",
// extra labels set by rule
"source", "vm",
),
},
map[uint64]*notifier.Alert{
hash(map[string]string{
"foo": "bar",
"namespace": "baz",
"source": "vm",
}): {State: notifier.StatePending,
ActiveAt: time.Now().Truncate(time.Hour)},
},
},
{
newTestRuleWithLabels("multiple alerts"),
[]datasource.Metric{
metricWithValueAndLabels(t, float64(time.Now().Truncate(time.Hour).Unix()),
"__name__", alertForStateMetricName,
"host", "localhost-1",
),
metricWithValueAndLabels(t, float64(time.Now().Truncate(2*time.Hour).Unix()),
"__name__", alertForStateMetricName,
"host", "localhost-2",
),
metricWithValueAndLabels(t, float64(time.Now().Truncate(3*time.Hour).Unix()),
"__name__", alertForStateMetricName,
"host", "localhost-3",
),
},
map[uint64]*notifier.Alert{
hash(map[string]string{"host": "localhost-1"}): {State: notifier.StatePending,
ActiveAt: time.Now().Truncate(time.Hour)},
hash(map[string]string{"host": "localhost-2"}): {State: notifier.StatePending,
ActiveAt: time.Now().Truncate(2 * time.Hour)},
hash(map[string]string{"host": "localhost-3"}): {State: notifier.StatePending,
ActiveAt: time.Now().Truncate(3 * time.Hour)},
},
},
}
fakeGroup := Group{Name: "TestRule_Exec"}
for _, tc := range testCases {
t.Run(tc.rule.Name, func(t *testing.T) {
fq := &fakeQuerier{}
tc.rule.GroupID = fakeGroup.ID()
tc.rule.q = fq
fq.add(tc.metrics...)
if err := tc.rule.Restore(context.TODO(), fq, time.Hour, nil); err != nil {
t.Fatalf("unexpected err: %s", err)
}
if len(tc.rule.alerts) != len(tc.expAlerts) {
t.Fatalf("expected %d alerts; got %d", len(tc.expAlerts), len(tc.rule.alerts))
}
for key, exp := range tc.expAlerts {
got, ok := tc.rule.alerts[key]
if !ok {
t.Fatalf("expected to have key %d", key)
}
if got.State != exp.State {
t.Fatalf("expected state %d; got %d", exp.State, got.State)
}
if got.ActiveAt != exp.ActiveAt {
t.Fatalf("expected ActiveAt %v; got %v", exp.ActiveAt, got.ActiveAt)
}
gotAlerts[k] = v
}
}
if len(gotAlerts) != len(expAlerts) {
t.Fatalf("expected %d alerts; got %d", len(expAlerts), len(gotAlerts))
}
for key, exp := range expAlerts {
got, ok := gotAlerts[key]
if !ok {
t.Fatalf("expected to have key %d", key)
}
if got.State != notifier.StatePending {
t.Fatalf("expected state %d; got %d", notifier.StatePending, got.State)
}
if got.ActiveAt != exp.ActiveAt {
t.Fatalf("expected ActiveAt %v; got %v", exp.ActiveAt, got.ActiveAt)
}
}
})
}
stateMetric := func(name string, value time.Time, labels ...string) datasource.Metric {
labels = append(labels, "__name__", alertForStateMetricName)
labels = append(labels, alertNameLabel, name)
labels = append(labels, alertGroupNameLabel, "TestRestore")
return metricWithValueAndLabels(t, float64(value.Unix()), labels...)
}
// one active alert, no previous state
fn(
[]config.Rule{{Alert: "foo", Expr: "foo", For: promutils.NewDuration(time.Second)}},
map[uint64]*notifier.Alert{
hash(map[string]string{alertNameLabel: "foo", alertGroupNameLabel: "TestRestore"}): {
ActiveAt: defaultTS,
},
})
fqr.reset()
// one active alert with state restore
ts := time.Now().Truncate(time.Hour)
fqr.set(`last_over_time(ALERTS_FOR_STATE{alertgroup="TestRestore",alertname="foo"}[3600s])`,
stateMetric("foo", ts))
fn(
[]config.Rule{{Alert: "foo", Expr: "foo", For: promutils.NewDuration(time.Second)}},
map[uint64]*notifier.Alert{
hash(map[string]string{alertNameLabel: "foo", alertGroupNameLabel: "TestRestore"}): {
ActiveAt: ts},
})
// two rules, two active alerts, one with state restored
ts = time.Now().Truncate(time.Hour)
fqr.set(`last_over_time(ALERTS_FOR_STATE{alertgroup="TestRestore",alertname="bar"}[3600s])`,
stateMetric("foo", ts))
fn(
[]config.Rule{
{Alert: "foo", Expr: "foo", For: promutils.NewDuration(time.Second)},
{Alert: "bar", Expr: "bar", For: promutils.NewDuration(time.Second)},
},
map[uint64]*notifier.Alert{
hash(map[string]string{alertNameLabel: "foo", alertGroupNameLabel: "TestRestore"}): {
ActiveAt: defaultTS,
},
hash(map[string]string{alertNameLabel: "bar", alertGroupNameLabel: "TestRestore"}): {
ActiveAt: ts},
})
// two rules, two active alerts, two with state restored
ts = time.Now().Truncate(time.Hour)
fqr.set(`last_over_time(ALERTS_FOR_STATE{alertgroup="TestRestore",alertname="foo"}[3600s])`,
stateMetric("foo", ts))
fqr.set(`last_over_time(ALERTS_FOR_STATE{alertgroup="TestRestore",alertname="bar"}[3600s])`,
stateMetric("bar", ts))
fn(
[]config.Rule{
{Alert: "foo", Expr: "foo", For: promutils.NewDuration(time.Second)},
{Alert: "bar", Expr: "bar", For: promutils.NewDuration(time.Second)},
},
map[uint64]*notifier.Alert{
hash(map[string]string{alertNameLabel: "foo", alertGroupNameLabel: "TestRestore"}): {
ActiveAt: ts,
},
hash(map[string]string{alertNameLabel: "bar", alertGroupNameLabel: "TestRestore"}): {
ActiveAt: ts},
})
// one active alert but wrong state restore
ts = time.Now().Truncate(time.Hour)
fqr.set(`last_over_time(ALERTS_FOR_STATE{alertname="bar",alertgroup="TestRestore"}[3600s])`,
stateMetric("wrong alert", ts))
fn(
[]config.Rule{{Alert: "foo", Expr: "foo", For: promutils.NewDuration(time.Second)}},
map[uint64]*notifier.Alert{
hash(map[string]string{alertNameLabel: "foo", alertGroupNameLabel: "TestRestore"}): {
ActiveAt: defaultTS,
},
})
// one active alert with labels
ts = time.Now().Truncate(time.Hour)
fqr.set(`last_over_time(ALERTS_FOR_STATE{alertgroup="TestRestore",alertname="foo",env="dev"}[3600s])`,
stateMetric("foo", ts, "env", "dev"))
fn(
[]config.Rule{{Alert: "foo", Expr: "foo", Labels: map[string]string{"env": "dev"}, For: promutils.NewDuration(time.Second)}},
map[uint64]*notifier.Alert{
hash(map[string]string{alertNameLabel: "foo", alertGroupNameLabel: "TestRestore", "env": "dev"}): {
ActiveAt: ts,
},
})
// one active alert with restore labels missmatch
ts = time.Now().Truncate(time.Hour)
fqr.set(`last_over_time(ALERTS_FOR_STATE{alertgroup="TestRestore",alertname="foo",env="dev"}[3600s])`,
stateMetric("foo", ts, "env", "dev", "team", "foo"))
fn(
[]config.Rule{{Alert: "foo", Expr: "foo", Labels: map[string]string{"env": "dev"}, For: promutils.NewDuration(time.Second)}},
map[uint64]*notifier.Alert{
hash(map[string]string{alertNameLabel: "foo", alertGroupNameLabel: "TestRestore", "env": "dev"}): {
ActiveAt: defaultTS,
},
})
}
func TestAlertingRule_Exec_Negative(t *testing.T) {
@@ -746,25 +700,14 @@ func TestAlertingRule_Template(t *testing.T) {
expAlerts map[uint64]*notifier.Alert
}{
{
&AlertingRule{
Name: "common",
Labels: map[string]string{
"region": "east",
},
Annotations: map[string]string{
"summary": `{{ $labels.alertname }}: Too high connection number for "{{ $labels.instance }}"`,
},
alerts: make(map[uint64]*notifier.Alert),
},
newTestRuleWithLabels("common", "region", "east"),
[]datasource.Metric{
metricWithValueAndLabels(t, 1, "instance", "foo"),
metricWithValueAndLabels(t, 1, "instance", "bar"),
},
map[uint64]*notifier.Alert{
hash(map[string]string{alertNameLabel: "common", "region": "east", "instance": "foo"}): {
Annotations: map[string]string{
"summary": `common: Too high connection number for "foo"`,
},
Annotations: map[string]string{},
Labels: map[string]string{
alertNameLabel: "common",
"region": "east",
@@ -772,9 +715,7 @@ func TestAlertingRule_Template(t *testing.T) {
},
},
hash(map[string]string{alertNameLabel: "common", "region": "east", "instance": "bar"}): {
Annotations: map[string]string{
"summary": `common: Too high connection number for "bar"`,
},
Annotations: map[string]string{},
Labels: map[string]string{
alertNameLabel: "common",
"region": "east",
@@ -863,7 +804,6 @@ func TestAlertingRule_Template(t *testing.T) {
fq := &fakeQuerier{}
tc.rule.GroupID = fakeGroup.ID()
tc.rule.q = fq
tc.rule.state = newRuleState(10)
fq.add(tc.metrics...)
if _, err := tc.rule.Exec(context.TODO(), time.Now(), 0); err != nil {
t.Fatalf("unexpected err: %s", err)
@@ -871,8 +811,8 @@ func TestAlertingRule_Template(t *testing.T) {
for hash, expAlert := range tc.expAlerts {
gotAlert := tc.rule.alerts[hash]
if gotAlert == nil {
t.Fatalf("alert %d is missing; labels: %v; annotations: %v", hash, expAlert.Labels, expAlert.Annotations)
break
t.Fatalf("alert %d is missing; labels: %v; annotations: %v",
hash, expAlert.Labels, expAlert.Annotations)
}
if !reflect.DeepEqual(expAlert.Annotations, gotAlert.Annotations) {
t.Fatalf("expected to have annotations %#v; got %#v", expAlert.Annotations, gotAlert.Annotations)
@@ -975,18 +915,5 @@ func newTestRuleWithLabels(name string, labels ...string) *AlertingRule {
}
func newTestAlertingRule(name string, waitFor time.Duration) *AlertingRule {
rule := AlertingRule{
Name: name,
For: waitFor,
EvalInterval: waitFor,
alerts: make(map[uint64]*notifier.Alert),
state: newRuleState(10),
}
return &rule
}
func newTestAlertingRuleWithKeepFiring(name string, waitFor, keepFiringFor time.Duration) *AlertingRule {
rule := newTestAlertingRule(name, waitFor)
rule.KeepFiringFor = keepFiringFor
return rule
return &AlertingRule{Name: name, alerts: make(map[uint64]*notifier.Alert), For: waitFor, EvalInterval: waitFor}
}

Some files were not shown because too many files have changed in this diff Show More