Compare commits

..

4 Commits

Author SHA1 Message Date
Jiekun
7a4e0a0683 feature: [logger] update comments 2025-07-10 19:04:13 +08:00
Jiekun
74b00630fd feature: [logger] simplify codes 2025-07-10 19:00:23 +08:00
Jiekun
b9866b74cb feature: [logger] adjust logger path format 2025-07-10 18:48:56 +08:00
Jiekun
c013992b83 feature: [logger] adjust logger path format when using in vendor and other repo 2025-07-10 18:16:54 +08:00
3142 changed files with 128186 additions and 562594 deletions

View File

@@ -5,7 +5,7 @@ body:
- type: textarea
id: describe-the-component
attributes:
label: Is your question related to a specific component?
label: Is your question request related to a specific component?
placeholder: |
VictoriaMetrics, vmagent, vmalert, vmui, etc...
validations:

View File

@@ -1,23 +0,0 @@
# Project Overview
VictoriaMetrics is a fast, cost-saving, and scalable solution for monitoring and managing time series data. It delivers high performance and reliability, making it an ideal choice for businesses of all sizes.
## Folder Structure
- `/app`: Contains the compilable binaries.
- `/lib`: Contains the golang reusable libraries
- `/docs/victoriametrics`: Contains documentation for the project.
- `/apptest/tests`: Contains integration tests.
## Libraries and Frameworks
- Backend: Golang, no framework. Use third-party libraries sparingly.
- Frontend: React.
## Code review guidelines
Ensure the feature or bugfix includes a changelog entry in /docs/victoriametrics/changelog/CHANGELOG.md.
Verify the entry is under the ## tip section and matches the structure and style of existing entries.
Chore-only changes may be omitted from the changelog.

View File

@@ -1,48 +0,0 @@
#!/usr/bin/env sh
set -e
CHANGELOG_FILE="docs/victoriametrics/changelog/CHANGELOG.md"
GITHUB_BASE_REF=${GITHUB_BASE_REF:-"master"}
GIT_REMOTE=${GIT_REMOTE:-"origin"}
git diff "${GIT_REMOTE}/${GITHUB_BASE_REF}"...HEAD -- $CHANGELOG_FILE > diff.txt
if ! grep -q "^+" diff.txt; then
echo "No additions in CHANGELOG.md"
exit 0
fi
ADDED_LINES=$(grep "^+\S" diff.txt | sed 's/^+//')
START_TIP=$(grep -n "^## tip" "$CHANGELOG_FILE" | head -1 | cut -d: -f1)
if [ -z "$START_TIP" ]; then
echo "ERROR: ${CHANGELOG_FILE} does not contain a ## tip section"
exit 1
fi
END_TIP=$(awk "NR>$START_TIP && /^## / {print NR; exit}" "${CHANGELOG_FILE}")
if [ -z "$END_TIP" ]; then
END_TIP=$(wc -l < "$CHANGELOG_FILE")
fi
BAD=0
while IFS= read -r line; do
# Grep exact line inside the file and get line numbers
MATCHES=$(grep -n -F "$line" "$CHANGELOG_FILE" | cut -d: -f1)
for m in $MATCHES; do
if [ "$m" -lt "$START_TIP" ] || [ "$m" -gt "$END_TIP" ]; then
echo "'$line' on line ${m} is outside ## tip section (lines ${START_TIP}-${END_TIP})"
BAD=1
fi
done
done << EOF
$ADDED_LINES
EOF
if [ "$BAD" -ne 0 ]; then
echo "CHANGELOG modifications must be placed inside the ## tip section."
exit 1
fi
echo "CHANGELOG modifications are valid."

View File

@@ -7,20 +7,16 @@ on:
- master
paths:
- '**.go'
- '**/Dockerfile'
- '**/Dockerfile*' # The trailing * is for app/vmui/Dockerfile-*.
- '**/Makefile'
- '!app/vmui/**'
- '.github/workflows/build.yml'
pull_request:
branches:
- cluster
- master
paths:
- '**.go'
- '**/Dockerfile'
- '**/Dockerfile*' # The trailing * is for app/vmui/Dockerfile-*.
- '**/Makefile'
- '!app/vmui/**'
- '.github/workflows/build.yml'
permissions:
contents: read
@@ -31,50 +27,28 @@ concurrency:
jobs:
build:
name: ${{ matrix.os }}-${{ matrix.arch }}
name: Build
runs-on: ubuntu-latest
strategy:
fail-fast: false
matrix:
include:
- os: linux
arch: 386
- os: linux
arch: amd64
- os: linux
arch: arm64
- os: linux
arch: arm
- os: linux
arch: ppc64le
- os: linux
arch: s390x
- os: darwin
arch: amd64
- os: darwin
arch: arm64
- os: freebsd
arch: amd64
- os: openbsd
arch: amd64
- os: windows
arch: amd64
steps:
- name: Code checkout
uses: actions/checkout@v6
uses: actions/checkout@v4
- name: Setup Go
id: go
uses: actions/setup-go@v6
uses: actions/setup-go@v5
with:
cache-dependency-path: |
go.sum
Makefile
app/**/Makefile
go-version: stable
cache: false
- name: Build victoria-metrics for ${{ matrix.os }}-${{ matrix.arch }}
run: make victoria-metrics-${{ matrix.os }}-${{ matrix.arch }}
- name: Cache Go artifacts
uses: actions/cache@v4
with:
path: |
~/.cache/go-build
~/go/bin
~/go/pkg/mod
key: go-artifacts-${{ runner.os }}-crossbuild-${{ steps.go.outputs.go-version }}-${{ hashFiles('go.sum', 'Makefile', 'app/**/Makefile') }}
restore-keys: go-artifacts-${{ runner.os }}-crossbuild-
- name: Build vmutils for ${{ matrix.os }}-${{ matrix.arch }}
run: make vmutils-${{ matrix.os }}-${{ matrix.arch }}
- name: Run crossbuild
run: make crossbuild

View File

@@ -1,19 +0,0 @@
name: 'changelog-linter'
on:
pull_request:
paths:
- "docs/victoriametrics/changelog/CHANGELOG.md"
jobs:
tip-lint:
runs-on: 'ubuntu-latest'
steps:
- uses: 'actions/checkout@v6'
with:
# needed for proper diff
fetch-depth: 0
- name: 'Validate that changelog changes are under ## tip'
run: |
GITHUB_BASE_REF=${{ github.base_ref }} ./.github/scripts/lint-changelog-tip.sh

View File

@@ -1,37 +0,0 @@
name: check-commit-signed
on:
pull_request:
jobs:
check-commit-signed:
runs-on: ubuntu-latest
steps:
- name: Checkout code
uses: actions/checkout@v6
with:
fetch-depth: 0 # we need full history for commit verification
- name: Check commit signatures
run: |
if [ "${{ github.event_name }}" != "pull_request" ]; then
echo "Not a PR event, skipping signature check"
exit 0
fi
RANGE="${{ github.event.pull_request.base.sha }}..${{ github.event.pull_request.head.sha }}"
echo "Checking commits in PR range: $RANGE"
if [ -z "$(git rev-list $RANGE)" ]; then
echo "No new commits in this PR, skipping signature check"
exit 0
fi
unsigned=$(git log --pretty="%H %G?" $RANGE | grep -vE " (G|E)$" || true)
if [ -n "$unsigned" ]; then
echo "Found unsigned commits:"
echo "$unsigned"
exit 1
fi
echo "All commits in PR are signed (G or E)"

View File

@@ -19,7 +19,7 @@ jobs:
- name: Setup Go
id: go
uses: actions/setup-go@v6
uses: actions/setup-go@v5
with:
go-version: stable
cache: false

View File

@@ -29,11 +29,11 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@v6
uses: actions/checkout@v4
- name: Set up Go
id: go
uses: actions/setup-go@v6
uses: actions/setup-go@v5
with:
cache: false
go-version: stable
@@ -49,14 +49,14 @@ jobs:
restore-keys: go-artifacts-${{ runner.os }}-codeql-analyze-
- name: Initialize CodeQL
uses: github/codeql-action/init@v4
uses: github/codeql-action/init@v3
with:
languages: go
- name: Autobuild
uses: github/codeql-action/autobuild@v4
uses: github/codeql-action/autobuild@v3
- name: Perform CodeQL Analysis
uses: github/codeql-action/analyze@v4
uses: github/codeql-action/analyze@v3
with:
category: 'language:go'

View File

@@ -0,0 +1,46 @@
name: 'CodeQL JS/TS'
on:
push:
branches:
- cluster
- master
paths:
- '**.js'
- '**.ts'
- '**.tsx'
pull_request:
branches:
- cluster
- master
paths:
- '**.js'
- '**.ts'
- '**.tsx'
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
steps:
- name: Checkout repository
uses: actions/checkout@v4
- name: Initialize CodeQL
uses: github/codeql-action/init@v3
with:
languages: javascript-typescript
- name: Perform CodeQL Analysis
uses: github/codeql-action/analyze@v3
with:
category: 'language:js/ts'

View File

@@ -16,12 +16,12 @@ jobs:
runs-on: ubuntu-latest
steps:
- name: Code checkout
uses: actions/checkout@v6
uses: actions/checkout@v4
with:
path: __vm
- name: Checkout private code
uses: actions/checkout@v6
uses: actions/checkout@v4
with:
repository: VictoriaMetrics/vmdocs
token: ${{ secrets.VM_BOT_GH_TOKEN }}

122
.github/workflows/main.yml vendored Normal file
View File

@@ -0,0 +1,122 @@
name: main
on:
push:
branches:
- cluster
- master
paths:
- '**.go'
pull_request:
branches:
- cluster
- master
paths:
- '**.go'
permissions:
contents: read
concurrency:
cancel-in-progress: true
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
jobs:
lint:
name: lint
runs-on: ubuntu-latest
steps:
- name: Code checkout
uses: actions/checkout@v4
- name: Setup Go
id: go
uses: actions/setup-go@v5
with:
cache: false
go-version: stable
- name: Cache Go artifacts
uses: actions/cache@v4
with:
path: |
~/.cache/go-build
~/go/bin
~/go/pkg/mod
key: go-artifacts-${{ runner.os }}-check-all-${{ steps.go.outputs.go-version }}-${{ hashFiles('go.sum', 'Makefile', 'app/**/Makefile') }}
restore-keys: go-artifacts-${{ runner.os }}-check-all-
- name: Run check-all
run: |
make check-all
git diff --exit-code
test:
name: test
needs: lint
runs-on: ubuntu-latest
strategy:
matrix:
scenario:
- 'test-full'
- 'test-full-386'
- 'test-pure'
steps:
- name: Code checkout
uses: actions/checkout@v4
- name: Setup Go
id: go
uses: actions/setup-go@v5
with:
cache: false
go-version: stable
- name: Cache Go artifacts
uses: actions/cache@v4
with:
path: |
~/.cache/go-build
~/go/bin
~/go/pkg/mod
key: go-artifacts-${{ runner.os }}-${{ matrix.scenario }}-${{ steps.go.outputs.go-version }}-${{ hashFiles('go.sum', 'Makefile', 'app/**/Makefile') }}
restore-keys: go-artifacts-${{ runner.os }}-${{ matrix.scenario }}-
- name: Run tests
run: GOGC=10 make ${{ matrix.scenario}}
- name: Publish coverage
uses: codecov/codecov-action@v5
with:
files: ./coverage.txt
integration-test:
name: integration-test
needs: [lint, test]
runs-on: ubuntu-latest
steps:
- name: Code checkout
uses: actions/checkout@v4
- name: Setup Go
id: go
uses: actions/setup-go@v5
with:
cache: false
go-version: stable
- name: Cache Go artifacts
uses: actions/cache@v4
with:
path: |
~/.cache/go-build
~/go/bin
~/go/pkg/mod
key: go-artifacts-${{ runner.os }}-${{ matrix.scenario }}-${{ steps.go.outputs.go-version }}-${{ hashFiles('go.sum', 'Makefile', 'app/**/Makefile') }}
restore-keys: go-artifacts-${{ runner.os }}-${{ matrix.scenario }}-
- name: Run integration tests
run: make integration-test

View File

@@ -1,113 +0,0 @@
name: test
on:
push:
branches:
- cluster
- master
paths:
- '**.go'
- 'go.*'
- '.github/workflows/main.yml'
pull_request:
branches:
- cluster
- master
paths:
- '**.go'
- 'go.*'
- '.github/workflows/main.yml'
permissions:
contents: read
concurrency:
cancel-in-progress: true
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
jobs:
lint:
name: lint
runs-on: ubuntu-latest
steps:
- name: Code checkout
uses: actions/checkout@v6
- name: Setup Go
id: go
uses: actions/setup-go@v6
with:
cache-dependency-path: |
go.sum
Makefile
app/**/Makefile
go-version: stable
- name: Cache golangci-lint
uses: actions/cache@v4
with:
path: |
~/.cache/golangci-lint
~/go/bin
key: golangci-lint-${{ runner.os }}-${{ hashFiles('.golangci.yml') }}
- name: Run check-all
run: |
make check-all
git diff --exit-code
unit:
name: unit
runs-on: ubuntu-latest
strategy:
matrix:
scenario:
- 'test-full'
- 'test-full-386'
- 'test-pure'
steps:
- name: Code checkout
uses: actions/checkout@v6
- name: Setup Go
id: go
uses: actions/setup-go@v6
with:
cache-dependency-path: |
go.sum
Makefile
app/**/Makefile
go-version: stable
- name: Run tests
run: GOGC=10 make ${{ matrix.scenario}}
- name: Publish coverage
uses: codecov/codecov-action@v5
with:
files: ./coverage.txt
integration:
name: integration
runs-on: ubuntu-latest
steps:
- name: Code checkout
uses: actions/checkout@v6
- name: Setup Go
id: go
uses: actions/setup-go@v6
with:
cache-dependency-path: |
go.sum
Makefile
app/**/Makefile
go-version: stable
- name: Run integration tests
run: make integration-test

View File

@@ -1,82 +0,0 @@
name: vmui
on:
push:
branches:
- cluster
- master
paths:
- 'app/vmui/packages/vmui/**'
- '.github/workflows/vmui.yml'
pull_request:
branches:
- cluster
- master
paths:
- 'app/vmui/packages/vmui/**'
- '.github/workflows/vmui.yml'
permissions:
contents: read
packages: read
pull-requests: read
checks: write
concurrency:
cancel-in-progress: true
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
jobs:
vmui-checks:
name: VMUI Checks (lint, test, typecheck)
runs-on: ubuntu-latest
steps:
- name: Code checkout
uses: actions/checkout@v6
- name: Setup Node
uses: actions/setup-node@v6
with:
node-version: '24.x'
- name: Cache node-modules
uses: actions/cache@v4
with:
path: |
app/vmui/packages/vmui/node_modules
key: vmui-artifacts-${{ runner.os }}-${{ hashFiles('package-lock.json') }}
restore-keys: vmui-artifacts-${{ runner.os }}-
- name: Run lint
id: lint
run: make vmui-lint
continue-on-error: true
- name: Run tests
id: test
run: make vmui-test
continue-on-error: true
- name: Run typecheck
id: typecheck
run: make vmui-typecheck
continue-on-error: true
- name: Annotate Code Linting Results
uses: ataylorme/eslint-annotate-action@v3
with:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
report-json: app/vmui/packages/vmui/vmui-lint-report.json
- name: Check overall status
run: |
echo "Lint status: ${{ steps.lint.outcome }}"
echo "Test status: ${{ steps.test.outcome }}"
echo "Typecheck status: ${{ steps.typecheck.outcome }}"
if [[ "${{ steps.lint.outcome }}" == "failure" || "${{ steps.test.outcome }}" == "failure" || "${{ steps.typecheck.outcome }}" == "failure" ]]; then
echo "One or more checks failed"
exit 1
else
echo "All checks passed"
fi

View File

@@ -1,29 +1,22 @@
version: "2"
run:
timeout: 2m
linters:
settings:
errcheck:
exclude-functions:
- fmt.Fprintf
- fmt.Fprint
- (net/http.ResponseWriter).Write
exclusions:
generated: lax
presets:
- common-false-positives
- legacy
- std-error-handling
rules:
- linters:
- staticcheck
text: 'SA(4003|1019|5011):'
paths:
- third_party$
- builtin$
- examples$
formatters:
exclusions:
generated: lax
paths:
- third_party$
- builtin$
- examples$
enable:
- revive
issues:
exclude-rules:
- linters:
- staticcheck
text: "SA(4003|1019|5011):"
include:
- EXC0012
- EXC0014
linters-settings:
errcheck:
exclude-functions:
- "fmt.Fprintf"
- "fmt.Fprint"
- "(net/http.ResponseWriter).Write"

195
Makefile
View File

@@ -11,14 +11,11 @@ ifeq ($(PKG_TAG),)
PKG_TAG := $(BUILDINFO_TAG)
endif
EXTRA_DOCKER_TAG_SUFFIX ?=
EXTRA_GO_BUILD_TAGS ?=
EXTRA_DOCKER_TAG_SUFFIX ?= EXTRA_DOCKER_TAG_SUFFIX
GO_BUILDINFO = -X '$(PKG_PREFIX)/lib/buildinfo.Version=$(APP_NAME)-$(DATEINFO_TAG)-$(BUILDINFO_TAG)'
TAR_OWNERSHIP ?= --owner=1000 --group=1000
GOLANGCI_LINT_VERSION := 2.7.2
.PHONY: $(MAKECMDGOALS)
include app/*/Makefile
@@ -27,10 +24,11 @@ include docs/Makefile
include deployment/*/Makefile
include dashboards/Makefile
include package/release/Makefile
include benchmarks/Makefile
all: \
victoria-metrics-prod \
victoria-logs-prod \
vlogscli-prod \
vmagent-prod \
vmalert-prod \
vmalert-tool-prod \
@@ -54,6 +52,8 @@ publish: \
package: \
package-victoria-metrics \
package-victoria-logs \
package-vlogscli \
package-vmagent \
package-vmalert \
package-vmalert-tool \
@@ -125,15 +125,6 @@ vmutils-linux-ppc64le: \
vmrestore-linux-ppc64le \
vmctl-linux-ppc64le
vmutils-linux-s390x: \
vmagent-linux-s390x \
vmalert-linux-s390x \
vmalert-tool-linux-s390x \
vmauth-linux-s390x \
vmbackup-linux-s390x \
vmrestore-linux-s390x \
vmctl-linux-s390x
vmutils-darwin-amd64: \
vmagent-darwin-amd64 \
vmalert-darwin-amd64 \
@@ -179,11 +170,9 @@ vmutils-windows-amd64: \
vmrestore-windows-amd64 \
vmctl-windows-amd64
# When adding a new crossbuild target, please also add it to the .github/workflows/build.yml
crossbuild:
$(MAKE_PARALLEL) victoria-metrics-crossbuild vmutils-crossbuild
# When adding a new crossbuild target, please also add it to the .github/workflows/build.yml
victoria-metrics-crossbuild: \
victoria-metrics-linux-386 \
victoria-metrics-linux-amd64 \
@@ -196,7 +185,6 @@ victoria-metrics-crossbuild: \
victoria-metrics-openbsd-amd64 \
victoria-metrics-windows-amd64
# When adding a new crossbuild target, please also add it to the .github/workflows/build.yml
vmutils-crossbuild: \
vmutils-linux-386 \
vmutils-linux-amd64 \
@@ -249,6 +237,10 @@ publish-latest:
PKG_TAG=$(TAG)-enterprise APP_NAME=vmgateway $(MAKE) publish-via-docker-latest
PKG_TAG=$(TAG)-enterprise APP_NAME=vmbackupmanager $(MAKE) publish-via-docker-latest
publish-victoria-logs-latest:
PKG_TAG=$(TAG) APP_NAME=victoria-logs $(MAKE) publish-via-docker-latest
PKG_TAG=$(TAG) APP_NAME=vlogscli $(MAKE) publish-via-docker-latest
publish-release:
rm -rf bin/*
git checkout $(TAG) && $(MAKE) release && $(MAKE) publish && \
@@ -266,7 +258,6 @@ release-victoria-metrics: \
release-victoria-metrics-linux-amd64 \
release-victoria-metrics-linux-arm \
release-victoria-metrics-linux-arm64 \
release-victoria-metrics-linux-s390x \
release-victoria-metrics-darwin-amd64 \
release-victoria-metrics-darwin-arm64 \
release-victoria-metrics-freebsd-amd64 \
@@ -285,9 +276,6 @@ release-victoria-metrics-linux-arm:
release-victoria-metrics-linux-arm64:
GOOS=linux GOARCH=arm64 $(MAKE) release-victoria-metrics-goos-goarch
release-victoria-metrics-linux-s390x:
GOOS=linux GOARCH=s390x $(MAKE) release-victoria-metrics-goos-goarch
release-victoria-metrics-darwin-amd64:
GOOS=darwin GOARCH=amd64 $(MAKE) release-victoria-metrics-goos-goarch
@@ -322,12 +310,133 @@ release-victoria-metrics-windows-goarch: victoria-metrics-windows-$(GOARCH)-prod
cd bin && rm -rf \
victoria-metrics-windows-$(GOARCH)-prod.exe
release-victoria-logs-bundle: \
release-victoria-logs \
release-vlogscli
publish-victoria-logs-bundle: \
publish-victoria-logs \
publish-vlogscli
release-victoria-logs:
$(MAKE_PARALLEL) 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 $(TAR_OWNERSHIP) --transform="flags=r;s|-$(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-vlogscli:
$(MAKE_PARALLEL) release-vlogscli-linux-386 \
release-vlogscli-linux-amd64 \
release-vlogscli-linux-arm \
release-vlogscli-linux-arm64 \
release-vlogscli-darwin-amd64 \
release-vlogscli-darwin-arm64 \
release-vlogscli-freebsd-amd64 \
release-vlogscli-openbsd-amd64 \
release-vlogscli-windows-amd64
release-vlogscli-linux-386:
GOOS=linux GOARCH=386 $(MAKE) release-vlogscli-goos-goarch
release-vlogscli-linux-amd64:
GOOS=linux GOARCH=amd64 $(MAKE) release-vlogscli-goos-goarch
release-vlogscli-linux-arm:
GOOS=linux GOARCH=arm $(MAKE) release-vlogscli-goos-goarch
release-vlogscli-linux-arm64:
GOOS=linux GOARCH=arm64 $(MAKE) release-vlogscli-goos-goarch
release-vlogscli-darwin-amd64:
GOOS=darwin GOARCH=amd64 $(MAKE) release-vlogscli-goos-goarch
release-vlogscli-darwin-arm64:
GOOS=darwin GOARCH=arm64 $(MAKE) release-vlogscli-goos-goarch
release-vlogscli-freebsd-amd64:
GOOS=freebsd GOARCH=amd64 $(MAKE) release-vlogscli-goos-goarch
release-vlogscli-openbsd-amd64:
GOOS=openbsd GOARCH=amd64 $(MAKE) release-vlogscli-goos-goarch
release-vlogscli-windows-amd64:
GOARCH=amd64 $(MAKE) release-vlogscli-windows-goarch
release-vlogscli-goos-goarch: vlogscli-$(GOOS)-$(GOARCH)-prod
cd bin && \
tar $(TAR_OWNERSHIP) --transform="flags=r;s|-$(GOOS)-$(GOARCH)||" -czf vlogscli-$(GOOS)-$(GOARCH)-$(PKG_TAG).tar.gz \
vlogscli-$(GOOS)-$(GOARCH)-prod \
&& sha256sum vlogscli-$(GOOS)-$(GOARCH)-$(PKG_TAG).tar.gz \
vlogscli-$(GOOS)-$(GOARCH)-prod \
| sed s/-$(GOOS)-$(GOARCH)-prod/-prod/ > vlogscli-$(GOOS)-$(GOARCH)-$(PKG_TAG)_checksums.txt
cd bin && rm -rf vlogscli-$(GOOS)-$(GOARCH)-prod
release-vlogscli-windows-goarch: vlogscli-windows-$(GOARCH)-prod
cd bin && \
zip vlogscli-windows-$(GOARCH)-$(PKG_TAG).zip \
vlogscli-windows-$(GOARCH)-prod.exe \
&& sha256sum vlogscli-windows-$(GOARCH)-$(PKG_TAG).zip \
vlogscli-windows-$(GOARCH)-prod.exe \
> vlogscli-windows-$(GOARCH)-$(PKG_TAG)_checksums.txt
cd bin && rm -rf \
vlogscli-windows-$(GOARCH)-prod.exe
release-vmutils: \
release-vmutils-linux-386 \
release-vmutils-linux-amd64 \
release-vmutils-linux-arm64 \
release-vmutils-linux-arm \
release-vmutils-linux-s390x \
release-vmutils-darwin-amd64 \
release-vmutils-darwin-arm64 \
release-vmutils-freebsd-amd64 \
@@ -346,9 +455,6 @@ release-vmutils-linux-arm64:
release-vmutils-linux-arm:
GOOS=linux GOARCH=arm $(MAKE) release-vmutils-goos-goarch
release-vmutils-linux-s390x:
GOOS=linux GOARCH=s390x $(MAKE) release-vmutils-goos-goarch
release-vmutils-darwin-amd64:
GOOS=darwin GOARCH=amd64 $(MAKE) release-vmutils-goos-goarch
@@ -435,7 +541,7 @@ release-vmutils-windows-goarch: \
vmctl-windows-$(GOARCH)-prod.exe
pprof-cpu:
go tool pprof -trim_path=github.com/VictoriaMetrics/VictoriaMetrics $(PPROF_FILE)
go tool pprof -trim_path=github.com/VictoriaMetrics/VictoriaMetrics@ $(PPROF_FILE)
fmt:
gofmt -l -w -s ./lib
@@ -466,28 +572,8 @@ test-full:
test-full-386:
GOEXPERIMENT=synctest GOARCH=386 go test -coverprofile=coverage.txt -covermode=atomic ./lib/... ./app/...
integration-test:
$(MAKE) apptest
apptest:
$(MAKE) victoria-metrics vmagent vmalert vmauth vmctl vmbackup vmrestore
go test ./apptest/... -skip="^Test(Cluster|Legacy).*"
integration-test-legacy: victoria-metrics vmbackup vmrestore
OS=$$(uname | tr '[:upper:]' '[:lower:]'); \
ARCH=$$(uname -m | tr '[:upper:]' '[:lower:]' | sed 's/x86_64/amd64/'); \
VERSION=v1.132.0; \
VMSINGLE=victoria-metrics-$${OS}-$${ARCH}-$${VERSION}.tar.gz; \
VMCLUSTER=victoria-metrics-$${OS}-$${ARCH}-$${VERSION}-cluster.tar.gz; \
URL=https://github.com/VictoriaMetrics/VictoriaMetrics/releases/download/$${VERSION}; \
DIR=/tmp/$${VERSION}; \
test -d $${DIR} || (mkdir $${DIR} && \
curl --output-dir /tmp -LO $${URL}/$${VMSINGLE} && tar xzf /tmp/$${VMSINGLE} -C $${DIR} && \
curl --output-dir /tmp -LO $${URL}/$${VMCLUSTER} && tar xzf /tmp/$${VMCLUSTER} -C $${DIR} \
); \
VM_LEGACY_VMSINGLE_PATH=$${DIR}/victoria-metrics-prod \
VM_LEGACY_VMSTORAGE_PATH=$${DIR}/vmstorage-prod \
go test ./apptest/tests -run="^TestLegacySingle.*"
integration-test: victoria-metrics vmagent vmalert vmauth vmctl vmbackup vmrestore
go test ./apptest/... -skip="^TestCluster.*"
benchmark:
GOEXPERIMENT=synctest go test -bench=. ./lib/...
@@ -504,20 +590,19 @@ vendor-update:
go mod vendor
app-local:
CGO_ENABLED=1 go build $(RACE) -ldflags "$(GO_BUILDINFO)" -tags "$(EXTRA_GO_BUILD_TAGS)" -o bin/$(APP_NAME)$(RACE) $(PKG_PREFIX)/app/$(APP_NAME)
CGO_ENABLED=1 go build $(RACE) -ldflags "$(GO_BUILDINFO)" -o bin/$(APP_NAME)$(RACE) $(PKG_PREFIX)/app/$(APP_NAME)
app-local-pure:
CGO_ENABLED=0 go build $(RACE) -ldflags "$(GO_BUILDINFO)" -tags "$(EXTRA_GO_BUILD_TAGS)" -o bin/$(APP_NAME)-pure$(RACE) $(PKG_PREFIX)/app/$(APP_NAME)
CGO_ENABLED=0 go build $(RACE) -ldflags "$(GO_BUILDINFO)" -o bin/$(APP_NAME)-pure$(RACE) $(PKG_PREFIX)/app/$(APP_NAME)
app-local-goos-goarch:
CGO_ENABLED=$(CGO_ENABLED) GOOS=$(GOOS) GOARCH=$(GOARCH) go build $(RACE) -ldflags "$(GO_BUILDINFO)" -tags "$(EXTRA_GO_BUILD_TAGS)" -o bin/$(APP_NAME)-$(GOOS)-$(GOARCH)$(RACE) $(PKG_PREFIX)/app/$(APP_NAME)
CGO_ENABLED=$(CGO_ENABLED) GOOS=$(GOOS) GOARCH=$(GOARCH) go build $(RACE) -ldflags "$(GO_BUILDINFO)" -o bin/$(APP_NAME)-$(GOOS)-$(GOARCH)$(RACE) $(PKG_PREFIX)/app/$(APP_NAME)
app-local-windows-goarch:
CGO_ENABLED=0 GOOS=windows GOARCH=$(GOARCH) go build $(RACE) -ldflags "$(GO_BUILDINFO)" -tags "$(EXTRA_GO_BUILD_TAGS)" -o bin/$(APP_NAME)-windows-$(GOARCH)$(RACE).exe $(PKG_PREFIX)/app/$(APP_NAME)
CGO_ENABLED=0 GOOS=windows GOARCH=$(GOARCH) go build $(RACE) -ldflags "$(GO_BUILDINFO)" -o bin/$(APP_NAME)-windows-$(GOARCH)$(RACE).exe $(PKG_PREFIX)/app/$(APP_NAME)
quicktemplate-gen: install-qtc
qtc -dir=lib
qtc -dir=app
qtc
install-qtc:
which qtc || go install github.com/valyala/quicktemplate/qtc@latest
@@ -527,7 +612,7 @@ golangci-lint: install-golangci-lint
GOEXPERIMENT=synctest golangci-lint run
install-golangci-lint:
which golangci-lint && (golangci-lint --version | grep -q $(GOLANGCI_LINT_VERSION)) || curl -sSfL https://raw.githubusercontent.com/golangci/golangci-lint/master/install.sh | sh -s -- -b $(shell go env GOPATH)/bin v$(GOLANGCI_LINT_VERSION)
which golangci-lint || curl -sSfL https://raw.githubusercontent.com/golangci/golangci-lint/master/install.sh | sh -s -- -b $(shell go env GOPATH)/bin v1.64.7
remove-golangci-lint:
rm -rf `which golangci-lint`

View File

@@ -3,7 +3,7 @@
[![Latest Release](https://img.shields.io/github/v/release/VictoriaMetrics/VictoriaMetrics?sort=semver&label=&filter=!*-victorialogs&logo=github&labelColor=gray&color=gray&link=https%3A%2F%2Fgithub.com%2FVictoriaMetrics%2FVictoriaMetrics%2Freleases%2Flatest)](https://github.com/VictoriaMetrics/VictoriaMetrics/releases)
![Docker Pulls](https://img.shields.io/docker/pulls/victoriametrics/victoria-metrics?label=&logo=docker&logoColor=white&labelColor=2496ED&color=2496ED&link=https%3A%2F%2Fhub.docker.com%2Fr%2Fvictoriametrics%2Fvictoria-metrics)
[![Go Report](https://goreportcard.com/badge/github.com/VictoriaMetrics/VictoriaMetrics?link=https%3A%2F%2Fgoreportcard.com%2Freport%2Fgithub.com%2FVictoriaMetrics%2FVictoriaMetrics)](https://goreportcard.com/report/github.com/VictoriaMetrics/VictoriaMetrics)
[![Build Status](https://github.com/VictoriaMetrics/VictoriaMetrics/actions/workflows/build.yml/badge.svg?branch=master&link=https%3A%2F%2Fgithub.com%2FVictoriaMetrics%2FVictoriaMetrics%2Factions)](https://github.com/VictoriaMetrics/VictoriaMetrics/actions/workflows/build.yml)
[![Build Status](https://github.com/VictoriaMetrics/VictoriaMetrics/actions/workflows/main.yml/badge.svg?branch=master&link=https%3A%2F%2Fgithub.com%2FVictoriaMetrics%2FVictoriaMetrics%2Factions)](https://github.com/VictoriaMetrics/VictoriaMetrics/actions/workflows/main.yml)
[![codecov](https://codecov.io/gh/VictoriaMetrics/VictoriaMetrics/branch/master/graph/badge.svg?link=https%3A%2F%2Fcodecov.io%2Fgh%2FVictoriaMetrics%2FVictoriaMetrics)](https://app.codecov.io/gh/VictoriaMetrics/VictoriaMetrics)
[![License](https://img.shields.io/github/license/VictoriaMetrics/VictoriaMetrics?labelColor=green&label=&link=https%3A%2F%2Fgithub.com%2FVictoriaMetrics%2FVictoriaMetrics%2Fblob%2Fmaster%2FLICENSE)](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/LICENSE)
![Slack](https://img.shields.io/badge/Join-4A154B?logo=slack&link=https%3A%2F%2Fslack.victoriametrics.com)

View File

@@ -4,11 +4,12 @@
The following versions of VictoriaMetrics receive regular security fixes:
| Version | Supported |
|--------------------------------------------------------------------------------|--------------------|
| [Latest release](https://docs.victoriametrics.com/victoriametrics/changelog/) | :white_check_mark: |
| [LTS releases](https://docs.victoriametrics.com/victoriametrics/lts-releases/) | :white_check_mark: |
| other releases | :x: |
| Version | Supported |
|---------|--------------------|
| [latest release](https://docs.victoriametrics.com/victoriametrics/changelog/) | :white_check_mark: |
| v1.102.x [LTS line](https://docs.victoriametrics.com/victoriametrics/lts-releases/) | :white_check_mark: |
| v1.110.x [LTS line](https://docs.victoriametrics.com/victoriametrics/lts-releases/) | :white_check_mark: |
| other releases | :x: |
See [this page](https://victoriametrics.com/security/) for more details.

View File

@@ -27,9 +27,6 @@ victoria-metrics-linux-ppc64le-prod:
victoria-metrics-linux-386-prod:
APP_NAME=victoria-metrics $(MAKE) app-via-docker-linux-386
victoria-metrics-linux-s390x-prod:
APP_NAME=victoria-metrics $(MAKE) app-via-docker-linux-s390x
victoria-metrics-darwin-amd64-prod:
APP_NAME=victoria-metrics $(MAKE) app-via-docker-darwin-amd64

View File

@@ -17,6 +17,7 @@ import (
"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"
@@ -124,6 +125,8 @@ func main() {
vmstorage.Stop()
vmselect.Stop()
fs.MustStopDirRemover()
logger.Infof("the VictoriaMetrics has been stopped in %.3f seconds", time.Since(startTime).Seconds())
}
@@ -169,7 +172,7 @@ func usage() {
const s = `
victoria-metrics is a time series database and monitoring solution.
See the docs at https://docs.victoriametrics.com/victoriametrics/
See the docs at https://docs.victoriametrics.com/
`
flagutil.Usage(s)
}

View File

@@ -10,11 +10,9 @@ import (
"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/decimal"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prommetadata"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/prometheus"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/storage"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/storage/metricsmetadata"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/timeserieslimits"
)
@@ -50,9 +48,8 @@ func selfScraper(scrapeInterval time.Duration) {
var bb bytesutil.ByteBuffer
var rows prometheus.Rows
var metadataRows prometheus.MetadataRows
var mrs []storage.MetricRow
var labels []prompb.Label
var labels []prompbmarshal.Label
t := time.NewTicker(scrapeInterval)
f := func(currentTime time.Time, sendStaleMarkers bool) {
currentTimestamp := currentTime.UnixNano() / 1e6
@@ -60,12 +57,7 @@ func selfScraper(scrapeInterval time.Duration) {
appmetrics.WritePrometheusMetrics(&bb)
s := bytesutil.ToUnsafeString(bb.B)
rows.Reset()
// Parse metrics and optionally metadata when enabled
if prommetadata.IsEnabled() {
rows, metadataRows = prometheus.UnmarshalWithMetadata(rows, metadataRows, s, nil)
} else {
rows.UnmarshalWithErrLogger(s, nil)
}
rows.Unmarshal(s)
mrs = mrs[:0]
for i := range rows.Rows {
r := &rows.Rows[i]
@@ -98,19 +90,6 @@ func selfScraper(scrapeInterval time.Duration) {
if err := vmstorage.AddRows(mrs); err != nil {
logger.Errorf("cannot store self-scraped metrics: %s", err)
}
if len(metadataRows.Rows) > 0 {
mms := make([]metricsmetadata.Row, 0, len(metadataRows.Rows))
for _, mm := range metadataRows.Rows {
mms = append(mms, metricsmetadata.Row{
MetricFamilyName: bytesutil.ToUnsafeBytes(mm.Metric),
Help: bytesutil.ToUnsafeBytes(mm.Help),
Type: mm.Type,
})
}
if err := vmstorage.AddMetadataRows(mms); err != nil {
logger.Errorf("cannot store self-scraped metrics metadata: %s", err)
}
}
}
for {
select {
@@ -125,11 +104,11 @@ func selfScraper(scrapeInterval time.Duration) {
}
}
func addLabel(dst []prompb.Label, key, value string) []prompb.Label {
func addLabel(dst []prompbmarshal.Label, key, value string) []prompbmarshal.Label {
if len(dst) < cap(dst) {
dst = dst[:len(dst)+1]
} else {
dst = append(dst, prompb.Label{})
dst = append(dst, prompbmarshal.Label{})
}
lb := &dst[len(dst)-1]
lb.Name = key

View File

@@ -27,9 +27,6 @@ vmagent-linux-ppc64le-prod:
vmagent-linux-386-prod:
APP_NAME=vmagent $(MAKE) app-via-docker-linux-386
vmagent-linux-s390x-prod:
APP_NAME=vmagent $(MAKE) app-via-docker-linux-s390x
vmagent-darwin-amd64-prod:
APP_NAME=vmagent $(MAKE) app-via-docker-darwin-amd64

View File

@@ -3,7 +3,7 @@ package common
import (
"sync"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
)
@@ -12,13 +12,13 @@ type PushCtx struct {
// WriteRequest contains the WriteRequest, which must be pushed later to remote storage.
//
// The actual labels and samples for the time series are stored in Labels and Samples fields.
WriteRequest prompb.WriteRequest
WriteRequest prompbmarshal.WriteRequest
// Labels contains flat list of all the labels used in WriteRequest.
Labels []prompb.Label
Labels []prompbmarshal.Label
// Samples contains flat list of all the samples used in WriteRequest.
Samples []prompb.Sample
Samples []prompbmarshal.Sample
}
// Reset resets ctx.

View File

@@ -6,7 +6,7 @@ import (
"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/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/csvimport"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/csvimport/stream"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/protoparserutil"
@@ -31,7 +31,7 @@ func InsertHandler(at *auth.Token, req *http.Request) error {
})
}
func insertRows(at *auth.Token, rows []csvimport.Row, extraLabels []prompb.Label) error {
func insertRows(at *auth.Token, rows []csvimport.Row, extraLabels []prompbmarshal.Label) error {
ctx := common.GetPushCtx()
defer common.PutPushCtx(ctx)
@@ -41,23 +41,23 @@ func insertRows(at *auth.Token, rows []csvimport.Row, extraLabels []prompb.Label
for i := range rows {
r := &rows[i]
labelsLen := len(labels)
labels = append(labels, prompb.Label{
labels = append(labels, prompbmarshal.Label{
Name: "__name__",
Value: r.Metric,
})
for j := range r.Tags {
tag := &r.Tags[j]
labels = append(labels, prompb.Label{
labels = append(labels, prompbmarshal.Label{
Name: tag.Key,
Value: tag.Value,
})
}
labels = append(labels, extraLabels...)
samples = append(samples, prompb.Sample{
samples = append(samples, prompbmarshal.Sample{
Value: r.Value,
Timestamp: r.Timestamp,
})
tssDst = append(tssDst, prompb.TimeSeries{
tssDst = append(tssDst, prompbmarshal.TimeSeries{
Labels: labels[labelsLen:],
Samples: samples[len(samples)-1:],
})

View File

@@ -6,7 +6,7 @@ import (
"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/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadogsketches"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadogsketches/stream"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadogutil"
@@ -33,7 +33,7 @@ func InsertHandlerForHTTP(at *auth.Token, req *http.Request) error {
})
}
func insertRows(at *auth.Token, sketches []*datadogsketches.Sketch, extraLabels []prompb.Label) error {
func insertRows(at *auth.Token, sketches []*datadogsketches.Sketch, extraLabels []prompbmarshal.Label) error {
ctx := common.GetPushCtx()
defer common.PutPushCtx(ctx)
@@ -45,12 +45,12 @@ func insertRows(at *auth.Token, sketches []*datadogsketches.Sketch, extraLabels
ms := sketch.ToSummary()
for _, m := range ms {
labelsLen := len(labels)
labels = append(labels, prompb.Label{
labels = append(labels, prompbmarshal.Label{
Name: "__name__",
Value: m.Name,
})
for _, label := range m.Labels {
labels = append(labels, prompb.Label{
labels = append(labels, prompbmarshal.Label{
Name: label.Name,
Value: label.Value,
})
@@ -60,7 +60,7 @@ func insertRows(at *auth.Token, sketches []*datadogsketches.Sketch, extraLabels
if name == "host" {
name = "exported_host"
}
labels = append(labels, prompb.Label{
labels = append(labels, prompbmarshal.Label{
Name: name,
Value: value,
})
@@ -68,13 +68,13 @@ func insertRows(at *auth.Token, sketches []*datadogsketches.Sketch, extraLabels
labels = append(labels, extraLabels...)
samplesLen := len(samples)
for _, p := range m.Points {
samples = append(samples, prompb.Sample{
samples = append(samples, prompbmarshal.Sample{
Timestamp: p.Timestamp,
Value: p.Value,
})
}
rowsTotal += len(m.Points)
tssDst = append(tssDst, prompb.TimeSeries{
tssDst = append(tssDst, prompbmarshal.TimeSeries{
Labels: labels[labelsLen:],
Samples: samples[samplesLen:],
})

View File

@@ -6,7 +6,7 @@ import (
"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/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadogutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadogv1"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadogv1/stream"
@@ -33,7 +33,7 @@ func InsertHandlerForHTTP(at *auth.Token, req *http.Request) error {
})
}
func insertRows(at *auth.Token, series []datadogv1.Series, extraLabels []prompb.Label) error {
func insertRows(at *auth.Token, series []datadogv1.Series, extraLabels []prompbmarshal.Label) error {
ctx := common.GetPushCtx()
defer common.PutPushCtx(ctx)
@@ -45,18 +45,18 @@ func insertRows(at *auth.Token, series []datadogv1.Series, extraLabels []prompb.
ss := &series[i]
rowsTotal += len(ss.Points)
labelsLen := len(labels)
labels = append(labels, prompb.Label{
labels = append(labels, prompbmarshal.Label{
Name: "__name__",
Value: ss.Metric,
})
if ss.Host != "" {
labels = append(labels, prompb.Label{
labels = append(labels, prompbmarshal.Label{
Name: "host",
Value: ss.Host,
})
}
if ss.Device != "" {
labels = append(labels, prompb.Label{
labels = append(labels, prompbmarshal.Label{
Name: "device",
Value: ss.Device,
})
@@ -66,7 +66,7 @@ func insertRows(at *auth.Token, series []datadogv1.Series, extraLabels []prompb.
if name == "host" {
name = "exported_host"
}
labels = append(labels, prompb.Label{
labels = append(labels, prompbmarshal.Label{
Name: name,
Value: value,
})
@@ -74,12 +74,12 @@ func insertRows(at *auth.Token, series []datadogv1.Series, extraLabels []prompb.
labels = append(labels, extraLabels...)
samplesLen := len(samples)
for _, pt := range ss.Points {
samples = append(samples, prompb.Sample{
samples = append(samples, prompbmarshal.Sample{
Timestamp: pt.Timestamp(),
Value: pt.Value(),
})
}
tssDst = append(tssDst, prompb.TimeSeries{
tssDst = append(tssDst, prompbmarshal.TimeSeries{
Labels: labels[labelsLen:],
Samples: samples[samplesLen:],
})

View File

@@ -6,7 +6,7 @@ import (
"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/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadogutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadogv2"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadogv2/stream"
@@ -36,7 +36,7 @@ func InsertHandlerForHTTP(at *auth.Token, req *http.Request) error {
})
}
func insertRows(at *auth.Token, series []datadogv2.Series, extraLabels []prompb.Label) error {
func insertRows(at *auth.Token, series []datadogv2.Series, extraLabels []prompbmarshal.Label) error {
ctx := common.GetPushCtx()
defer common.PutPushCtx(ctx)
@@ -48,18 +48,18 @@ func insertRows(at *auth.Token, series []datadogv2.Series, extraLabels []prompb.
ss := &series[i]
rowsTotal += len(ss.Points)
labelsLen := len(labels)
labels = append(labels, prompb.Label{
labels = append(labels, prompbmarshal.Label{
Name: "__name__",
Value: ss.Metric,
})
for _, rs := range ss.Resources {
labels = append(labels, prompb.Label{
labels = append(labels, prompbmarshal.Label{
Name: rs.Type,
Value: rs.Name,
})
}
if ss.SourceTypeName != "" {
labels = append(labels, prompb.Label{
labels = append(labels, prompbmarshal.Label{
Name: "source_type_name",
Value: ss.SourceTypeName,
})
@@ -69,7 +69,7 @@ func insertRows(at *auth.Token, series []datadogv2.Series, extraLabels []prompb.
if name == "host" {
name = "exported_host"
}
labels = append(labels, prompb.Label{
labels = append(labels, prompbmarshal.Label{
Name: name,
Value: value,
})
@@ -77,12 +77,12 @@ func insertRows(at *auth.Token, series []datadogv2.Series, extraLabels []prompb.
labels = append(labels, extraLabels...)
samplesLen := len(samples)
for _, pt := range ss.Points {
samples = append(samples, prompb.Sample{
samples = append(samples, prompbmarshal.Sample{
Timestamp: pt.Timestamp * 1000,
Value: pt.Value,
})
}
tssDst = append(tssDst, prompb.TimeSeries{
tssDst = append(tssDst, prompbmarshal.TimeSeries{
Labels: labels[labelsLen:],
Samples: samples[samplesLen:],
})

View File

@@ -6,7 +6,7 @@ import (
"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/prompb"
"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/metrics"
@@ -36,22 +36,22 @@ func insertRows(at *auth.Token, rows []parser.Row) error {
for i := range rows {
r := &rows[i]
labelsLen := len(labels)
labels = append(labels, prompb.Label{
labels = append(labels, prompbmarshal.Label{
Name: "__name__",
Value: r.Metric,
})
for j := range r.Tags {
tag := &r.Tags[j]
labels = append(labels, prompb.Label{
labels = append(labels, prompbmarshal.Label{
Name: tag.Key,
Value: tag.Value,
})
}
samples = append(samples, prompb.Sample{
samples = append(samples, prompbmarshal.Sample{
Value: r.Value,
Timestamp: r.Timestamp,
})
tssDst = append(tssDst, prompb.TimeSeries{
tssDst = append(tssDst, prompbmarshal.TimeSeries{
Labels: labels[labelsLen:],
Samples: samples[len(samples)-1:],
})

View File

@@ -10,7 +10,7 @@ import (
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/influx"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/influx/stream"
@@ -60,7 +60,7 @@ func InsertHandlerForHTTP(at *auth.Token, req *http.Request) error {
})
}
func insertRows(at *auth.Token, db string, rows []influx.Row, extraLabels []prompb.Label) error {
func insertRows(at *auth.Token, db string, rows []influx.Row, extraLabels []prompbmarshal.Label) error {
ctx := getPushCtx()
defer putPushCtx(ctx)
@@ -80,13 +80,13 @@ func insertRows(at *auth.Token, db string, rows []influx.Row, extraLabels []prom
if tag.Key == *dbLabel {
hasDBKey = true
}
commonLabels = append(commonLabels, prompb.Label{
commonLabels = append(commonLabels, prompbmarshal.Label{
Name: tag.Key,
Value: tag.Value,
})
}
if len(db) > 0 && !hasDBKey {
commonLabels = append(commonLabels, prompb.Label{
commonLabels = append(commonLabels, prompbmarshal.Label{
Name: *dbLabel,
Value: db,
})
@@ -110,16 +110,16 @@ func insertRows(at *auth.Token, db string, rows []influx.Row, extraLabels []prom
}
metricGroup := bytesutil.ToUnsafeString(buf[bufLen:])
labelsLen := len(labels)
labels = append(labels, prompb.Label{
labels = append(labels, prompbmarshal.Label{
Name: "__name__",
Value: metricGroup,
})
labels = append(labels, commonLabels...)
samples = append(samples, prompb.Sample{
samples = append(samples, prompbmarshal.Sample{
Timestamp: r.Timestamp,
Value: f.Value,
})
tssDst = append(tssDst, prompb.TimeSeries{
tssDst = append(tssDst, prompbmarshal.TimeSeries{
Labels: labels[labelsLen:],
Samples: samples[len(samples)-1:],
})
@@ -144,7 +144,7 @@ func insertRows(at *auth.Token, db string, rows []influx.Row, extraLabels []prom
type pushCtx struct {
ctx common.PushCtx
commonLabels []prompb.Label
commonLabels []prompbmarshal.Label
metricGroupBuf []byte
buf []byte
}

View File

@@ -27,7 +27,6 @@ import (
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/promremotewrite"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/vmimport"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/zabbixconnector"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/buildinfo"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
@@ -75,7 +74,7 @@ var (
"See also -opentsdbHTTPListenAddr.useProxyProtocol")
opentsdbHTTPUseProxyProtocol = flag.Bool("opentsdbHTTPListenAddr.useProxyProtocol", false, "Whether to use proxy protocol for connections accepted "+
"at -opentsdbHTTPListenAddr . See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt")
configAuthKey = flagutil.NewPassword("configAuthKey", "Authorization key for accessing /config and /remotewrite-.*-config pages. It must be passed via authKey query arg. It overrides -httpAuth.*")
configAuthKey = flagutil.NewPassword("configAuthKey", "Authorization key for accessing /config page. It must be passed via authKey query arg. It overrides -httpAuth.*")
reloadAuthKey = flagutil.NewPassword("reloadAuthKey", "Auth key for /-/reload http endpoint. It must be passed via authKey query arg. It overrides -httpAuth.*")
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 . "+
@@ -207,7 +206,7 @@ func main() {
func getOpenTSDBHTTPInsertHandler() func(req *http.Request) error {
if !remotewrite.MultitenancyEnabled() {
return func(req *http.Request) error {
path := strings.ReplaceAll(req.URL.Path, "//", "/")
path := strings.Replace(req.URL.Path, "//", "/", -1)
if path != "/api/put" {
return fmt.Errorf("unsupported path requested: %q; expecting '/api/put'", path)
}
@@ -215,7 +214,7 @@ func getOpenTSDBHTTPInsertHandler() func(req *http.Request) error {
}
}
return func(req *http.Request) error {
path := strings.ReplaceAll(req.URL.Path, "//", "/")
path := strings.Replace(req.URL.Path, "//", "/", -1)
at, err := getAuthTokenFromPath(path)
if err != nil {
return fmt.Errorf("cannot obtain auth token from path %q: %w", path, err)
@@ -253,8 +252,6 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
{"metric-relabel-debug", "debug metric relabeling"},
{"api/v1/targets", "advanced information about discovered targets in JSON format"},
{"config", "-promscrape.config contents"},
{"remotewrite-relabel-config", "-remoteWrite.relabelConfig contents"},
{"remotewrite-url-relabel-config", "-remoteWrite.urlRelabelConfig contents"},
{"metrics", "available service metrics"},
{"flags", "command-line flags"},
{"-/reload", "reload configuration"},
@@ -262,7 +259,7 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
return true
}
path := strings.ReplaceAll(r.URL.Path, "//", "/")
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 {
@@ -351,17 +348,6 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
}
firehose.WriteSuccessResponse(w, r)
return true
case "/zabbixconnector/api/v1/history":
zabbixconnectorHistoryRequests.Inc()
if err := zabbixconnector.InsertHandlerForHTTP(nil, r); err != nil {
zabbixconnectorHistoryErrors.Inc()
w.Header().Set("Content-Type", "application/json")
w.WriteHeader(http.StatusBadRequest)
fmt.Fprintf(w, `{"error":%q}`, err.Error())
return true
}
w.WriteHeader(http.StatusOK)
return true
case "/newrelic":
newrelicCheckRequest.Inc()
w.Header().Set("Content-Type", "application/json")
@@ -491,42 +477,6 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
promscrape.WriteConfigData(&bb)
fmt.Fprintf(w, `{"status":"success","data":{"yaml":%s}}`, stringsutil.JSONString(string(bb.B)))
return true
case "/remotewrite-relabel-config":
if !httpserver.CheckAuthFlag(w, r, configAuthKey) {
return true
}
remoteWriteRelabelConfigRequests.Inc()
w.Header().Set("Content-Type", "text/plain; charset=utf-8")
remotewrite.WriteRelabelConfigData(w)
return true
case "/api/v1/status/remotewrite-relabel-config":
if !httpserver.CheckAuthFlag(w, r, configAuthKey) {
return true
}
remoteWriteStatusRelabelConfigRequests.Inc()
w.Header().Set("Content-Type", "application/json")
var bb bytesutil.ByteBuffer
remotewrite.WriteRelabelConfigData(&bb)
fmt.Fprintf(w, `{"status":"success","data":{"yaml":%s}}`, stringsutil.JSONString(string(bb.B)))
return true
case "/remotewrite-url-relabel-config":
if !httpserver.CheckAuthFlag(w, r, configAuthKey) {
return true
}
remoteWriteURLRelabelConfigRequests.Inc()
w.Header().Set("Content-Type", "text/plain; charset=utf-8")
remotewrite.WriteURLRelabelConfigData(w)
return true
case "/api/v1/status/remotewrite-url-relabel-config":
if !httpserver.CheckAuthFlag(w, r, configAuthKey) {
return true
}
remoteWriteStatusURLRelabelConfigRequests.Inc()
w.Header().Set("Content-Type", "application/json")
var bb bytesutil.ByteBuffer
remotewrite.WriteURLRelabelConfigData(&bb)
fmt.Fprintf(w, `{"status":"success","data":{"yaml":%s}}`, stringsutil.JSONString(string(bb.B)))
return true
case "/prometheus/-/reload", "/-/reload":
if !httpserver.CheckAuthFlag(w, r, reloadAuthKey) {
return true
@@ -656,17 +606,6 @@ func processMultitenantRequest(w http.ResponseWriter, r *http.Request, path stri
}
firehose.WriteSuccessResponse(w, r)
return true
case "zabbixconnector/api/v1/history":
zabbixconnectorHistoryRequests.Inc()
if err := zabbixconnector.InsertHandlerForHTTP(at, r); err != nil {
zabbixconnectorHistoryErrors.Inc()
w.Header().Set("Content-Type", "application/json")
w.WriteHeader(http.StatusBadRequest)
fmt.Fprintf(w, `{"error":%q}`, err.Error())
return true
}
w.WriteHeader(http.StatusOK)
return true
case "newrelic":
newrelicCheckRequest.Inc()
w.Header().Set("Content-Type", "application/json")
@@ -788,9 +727,6 @@ var (
opentelemetryPushRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/opentelemetry/v1/metrics", protocol="opentelemetry"}`)
opentelemetryPushErrors = metrics.NewCounter(`vmagent_http_request_errors_total{path="/opentelemetry/v1/metrics", protocol="opentelemetry"}`)
zabbixconnectorHistoryRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/zabbixconnector/api/v1/history", protocol="zabbixconnector"}`)
zabbixconnectorHistoryErrors = metrics.NewCounter(`vmagent_http_request_errors_total{path="/zabbixconnector/api/v1/history", protocol="zabbixconnector"}`)
newrelicWriteRequests = metrics.NewCounter(`vm_http_requests_total{path="/newrelic/infra/v2/metrics/events/bulk", protocol="newrelic"}`)
newrelicWriteErrors = metrics.NewCounter(`vm_http_request_errors_total{path="/newrelic/infra/v2/metrics/events/bulk", protocol="newrelic"}`)
@@ -811,12 +747,6 @@ var (
promscrapeConfigRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/config"}`)
promscrapeStatusConfigRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/api/v1/status/config"}`)
remoteWriteRelabelConfigRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/remotewrite-relabel-config"}`)
remoteWriteStatusRelabelConfigRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/api/v1/status/remotewrite-relabel-config"}`)
remoteWriteURLRelabelConfigRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/remotewrite-url-relabel-config"}`)
remoteWriteStatusURLRelabelConfigRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/api/v1/status/remotewrite-url-relabel-config"}`)
promscrapeConfigReloadRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/-/reload"}`)
)

View File

@@ -8,7 +8,7 @@ import (
"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/native/stream"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/protoparserutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
@@ -35,7 +35,7 @@ func InsertHandler(at *auth.Token, req *http.Request) error {
})
}
func insertRows(at *auth.Token, block *stream.Block, extraLabels []prompb.Label) error {
func insertRows(at *auth.Token, block *stream.Block, extraLabels []prompbmarshal.Label) error {
ctx := common.GetPushCtx()
defer common.PutPushCtx(ctx)
@@ -53,13 +53,13 @@ func insertRows(at *auth.Token, block *stream.Block, extraLabels []prompb.Label)
samples := ctx.Samples[:0]
mn := &block.MetricName
labelsLen := len(labels)
labels = append(labels, prompb.Label{
labels = append(labels, prompbmarshal.Label{
Name: "__name__",
Value: bytesutil.ToUnsafeString(mn.MetricGroup),
})
for j := range mn.Tags {
tag := &mn.Tags[j]
labels = append(labels, prompb.Label{
labels = append(labels, prompbmarshal.Label{
Name: bytesutil.ToUnsafeString(tag.Key),
Value: bytesutil.ToUnsafeString(tag.Value),
})
@@ -72,12 +72,12 @@ func insertRows(at *auth.Token, block *stream.Block, extraLabels []prompb.Label)
}
samplesLen := len(samples)
for j, value := range values {
samples = append(samples, prompb.Sample{
samples = append(samples, prompbmarshal.Sample{
Value: value,
Timestamp: timestamps[j],
})
}
tssDst = append(tssDst, prompb.TimeSeries{
tssDst = append(tssDst, prompbmarshal.TimeSeries{
Labels: labels[labelsLen:],
Samples: samples[samplesLen:],
})

View File

@@ -9,7 +9,7 @@ import (
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/newrelic"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/newrelic/stream"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/protoparserutil"
@@ -34,7 +34,7 @@ func InsertHandlerForHTTP(at *auth.Token, req *http.Request) error {
})
}
func insertRows(at *auth.Token, rows []newrelic.Row, extraLabels []prompb.Label) error {
func insertRows(at *auth.Token, rows []newrelic.Row, extraLabels []prompbmarshal.Label) error {
ctx := common.GetPushCtx()
defer common.PutPushCtx(ctx)
@@ -49,22 +49,22 @@ func insertRows(at *auth.Token, rows []newrelic.Row, extraLabels []prompb.Label)
for j := range srcSamples {
s := &srcSamples[j]
labelsLen := len(labels)
labels = append(labels, prompb.Label{
labels = append(labels, prompbmarshal.Label{
Name: "__name__",
Value: bytesutil.ToUnsafeString(s.Name),
})
for k := range tags {
t := &tags[k]
labels = append(labels, prompb.Label{
labels = append(labels, prompbmarshal.Label{
Name: bytesutil.ToUnsafeString(t.Key),
Value: bytesutil.ToUnsafeString(t.Value),
})
}
samples = append(samples, prompb.Sample{
samples = append(samples, prompbmarshal.Sample{
Value: s.Value,
Timestamp: r.Timestamp,
})
tssDst = append(tssDst, prompb.TimeSeries{
tssDst = append(tssDst, prompbmarshal.TimeSeries{
Labels: labels[labelsLen:],
Samples: samples[len(samples)-1:],
})
@@ -78,7 +78,7 @@ func insertRows(at *auth.Token, rows []newrelic.Row, extraLabels []prompb.Label)
if !remotewrite.TryPush(at, &ctx.WriteRequest) {
return remotewrite.ErrQueueFullHTTPRetry
}
rowsInserted.Add(samplesCount)
rowsInserted.Add(len(rows))
if at != nil {
rowsTenantInserted.Get(at).Add(samplesCount)
}

View File

@@ -2,14 +2,12 @@ package opentelemetry
import (
"fmt"
"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/prommetadata"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/opentelemetry/firehose"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/opentelemetry/stream"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/protoparserutil"
@@ -18,20 +16,11 @@ import (
)
var (
rowsInserted = metrics.NewCounter(`vmagent_rows_inserted_total{type="opentelemetry"}`)
metadataInserted = metrics.NewCounter(`vmagent_metadata_inserted_total{type="opentelemetry"}`)
rowsTenantInserted = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_rows_total{type="opentelemetry"}`)
metadataTenantInserted = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_metadata_total{type="opentelemetry"}`)
rowsPerInsert = metrics.NewHistogram(`vmagent_rows_per_insert{type="opentelemetry"}`)
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"}`)
)
// InsertHandlerForReader processes metrics from given reader.
func InsertHandlerForReader(at *auth.Token, r io.Reader, encoding string) error {
return stream.ParseStream(r, encoding, nil, func(tss []prompb.TimeSeries, mms []prompb.MetricMetadata) error {
return insertRows(at, tss, mms, nil)
})
}
// InsertHandler processes opentelemetry metrics.
func InsertHandler(at *auth.Token, req *http.Request) error {
extraLabels, err := protoparserutil.GetExtraLabels(req)
@@ -47,12 +36,12 @@ func InsertHandler(at *auth.Token, req *http.Request) error {
return fmt.Errorf("json encoding isn't supported for opentelemetry format. Use protobuf encoding")
}
}
return stream.ParseStream(req.Body, encoding, processBody, func(tss []prompb.TimeSeries, mms []prompb.MetricMetadata) error {
return insertRows(at, tss, mms, extraLabels)
return stream.ParseStream(req.Body, encoding, processBody, func(tss []prompbmarshal.TimeSeries) error {
return insertRows(at, tss, extraLabels)
})
}
func insertRows(at *auth.Token, tss []prompb.TimeSeries, mms []prompb.MetricMetadata, extraLabels []prompb.Label) error {
func insertRows(at *auth.Token, tss []prompbmarshal.TimeSeries, extraLabels []prompbmarshal.Label) error {
ctx := common.GetPushCtx()
defer common.PutPushCtx(ctx)
@@ -68,39 +57,20 @@ func insertRows(at *auth.Token, tss []prompb.TimeSeries, mms []prompb.MetricMeta
labels = append(labels, extraLabels...)
samplesLen := len(samples)
samples = append(samples, ts.Samples...)
tssDst = append(tssDst, prompb.TimeSeries{
tssDst = append(tssDst, prompbmarshal.TimeSeries{
Labels: labels[labelsLen:],
Samples: samples[samplesLen:],
})
}
ctx.WriteRequest.Timeseries = tssDst
var metadataTotal int
if prommetadata.IsEnabled() {
var accountID, projectID uint32
if at != nil {
accountID = at.AccountID
projectID = at.ProjectID
for i := range mms {
mm := &mms[i]
mm.AccountID = accountID
mm.ProjectID = projectID
}
}
ctx.WriteRequest.Metadata = mms
metadataTotal = len(mms)
}
ctx.Labels = labels
ctx.Samples = samples
if !remotewrite.TryPush(at, &ctx.WriteRequest) {
return remotewrite.ErrQueueFullHTTPRetry
}
rowsInserted.Add(rowsTotal)
metadataInserted.Add(metadataTotal)
if at != nil {
rowsTenantInserted.Get(at).Add(rowsTotal)
metadataTenantInserted.Get(at).Add(metadataTotal)
}
rowsPerInsert.Update(float64(rowsTotal))
return nil

View File

@@ -5,7 +5,7 @@ import (
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/common"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"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/metrics"
@@ -33,22 +33,22 @@ func insertRows(rows []parser.Row) error {
for i := range rows {
r := &rows[i]
labelsLen := len(labels)
labels = append(labels, prompb.Label{
labels = append(labels, prompbmarshal.Label{
Name: "__name__",
Value: r.Metric,
})
for j := range r.Tags {
tag := &r.Tags[j]
labels = append(labels, prompb.Label{
labels = append(labels, prompbmarshal.Label{
Name: tag.Key,
Value: tag.Value,
})
}
samples = append(samples, prompb.Sample{
samples = append(samples, prompbmarshal.Sample{
Value: r.Value,
Timestamp: r.Timestamp,
})
tssDst = append(tssDst, prompb.TimeSeries{
tssDst = append(tssDst, prompbmarshal.TimeSeries{
Labels: labels[labelsLen:],
Samples: samples[len(samples)-1:],
})

View File

@@ -6,7 +6,7 @@ import (
"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/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/opentsdbhttp"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/opentsdbhttp/stream"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/protoparserutil"
@@ -30,7 +30,7 @@ func InsertHandler(at *auth.Token, req *http.Request) error {
})
}
func insertRows(at *auth.Token, rows []opentsdbhttp.Row, extraLabels []prompb.Label) error {
func insertRows(at *auth.Token, rows []opentsdbhttp.Row, extraLabels []prompbmarshal.Label) error {
ctx := common.GetPushCtx()
defer common.PutPushCtx(ctx)
@@ -40,23 +40,23 @@ func insertRows(at *auth.Token, rows []opentsdbhttp.Row, extraLabels []prompb.La
for i := range rows {
r := &rows[i]
labelsLen := len(labels)
labels = append(labels, prompb.Label{
labels = append(labels, prompbmarshal.Label{
Name: "__name__",
Value: r.Metric,
})
for j := range r.Tags {
tag := &r.Tags[j]
labels = append(labels, prompb.Label{
labels = append(labels, prompbmarshal.Label{
Name: tag.Key,
Value: tag.Value,
})
}
labels = append(labels, extraLabels...)
samples = append(samples, prompb.Sample{
samples = append(samples, prompbmarshal.Sample{
Value: r.Value,
Timestamp: r.Timestamp,
})
tssDst = append(tssDst, prompb.TimeSeries{
tssDst = append(tssDst, prompbmarshal.TimeSeries{
Labels: labels[labelsLen:],
Samples: samples[len(samples)-1:],
})

View File

@@ -7,8 +7,7 @@ import (
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prommetadata"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/prometheus"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/prometheus/stream"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/protoparserutil"
@@ -17,12 +16,9 @@ import (
)
var (
rowsInserted = metrics.NewCounter(`vmagent_rows_inserted_total{type="prometheus"}`)
metadataInserted = metrics.NewCounter(`vmagent_metadata_inserted_total{type="prometheus"}`)
rowsTenantInserted = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_rows_total{type="prometheus"}`)
metadataTenantInserted = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_metadata_total{type="prometheus"}`)
rowsPerInsert = metrics.NewHistogram(`vmagent_rows_per_insert{type="prometheus"}`)
rowsInserted = metrics.NewCounter(`vmagent_rows_inserted_total{type="prometheus"}`)
rowsTenantInserted = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_rows_total{type="prometheus"}`)
rowsPerInsert = metrics.NewHistogram(`vmagent_rows_per_insert{type="prometheus"}`)
)
// InsertHandler processes `/api/v1/import/prometheus` request.
@@ -36,74 +32,53 @@ func InsertHandler(at *auth.Token, req *http.Request) error {
return err
}
encoding := req.Header.Get("Content-Encoding")
return stream.Parse(req.Body, defaultTimestamp, encoding, true, prommetadata.IsEnabled(), func(rows []prometheus.Row, mms []prometheus.Metadata) error {
return insertRows(at, rows, mms, extraLabels)
return stream.Parse(req.Body, defaultTimestamp, encoding, true, func(rows []prometheus.Row) error {
return insertRows(at, rows, extraLabels)
}, func(s string) {
httpserver.LogError(req, s)
})
}
func insertRows(at *auth.Token, rows []prometheus.Row, mms []prometheus.Metadata, extraLabels []prompb.Label) error {
func insertRows(at *auth.Token, rows []prometheus.Row, extraLabels []prompbmarshal.Label) error {
ctx := common.GetPushCtx()
defer common.PutPushCtx(ctx)
tssDst := ctx.WriteRequest.Timeseries[:0]
mmsDst := ctx.WriteRequest.Metadata[:0]
labels := ctx.Labels[:0]
samples := ctx.Samples[:0]
for i := range rows {
r := &rows[i]
labelsLen := len(labels)
labels = append(labels, prompb.Label{
labels = append(labels, prompbmarshal.Label{
Name: "__name__",
Value: r.Metric,
})
for j := range r.Tags {
tag := &r.Tags[j]
labels = append(labels, prompb.Label{
labels = append(labels, prompbmarshal.Label{
Name: tag.Key,
Value: tag.Value,
})
}
labels = append(labels, extraLabels...)
samples = append(samples, prompb.Sample{
samples = append(samples, prompbmarshal.Sample{
Value: r.Value,
Timestamp: r.Timestamp,
})
tssDst = append(tssDst, prompb.TimeSeries{
tssDst = append(tssDst, prompbmarshal.TimeSeries{
Labels: labels[labelsLen:],
Samples: samples[len(samples)-1:],
})
}
var accountID, projectID uint32
if at != nil {
accountID = at.AccountID
projectID = at.ProjectID
}
for i := range mms {
mm := &mms[i]
mmsDst = append(mmsDst, prompb.MetricMetadata{
MetricFamilyName: mm.Metric,
Help: mm.Help,
Type: mm.Type,
// there is no unit in Prometheus exposition formats
AccountID: accountID,
ProjectID: projectID,
})
}
ctx.WriteRequest.Timeseries = tssDst
ctx.WriteRequest.Metadata = mmsDst
ctx.Labels = labels
ctx.Samples = samples
if !remotewrite.TryPush(at, &ctx.WriteRequest) {
return remotewrite.ErrQueueFullHTTPRetry
}
rowsInserted.Add(len(rows))
metadataInserted.Add(len(mms))
if at != nil {
rowsTenantInserted.Get(at).Add(len(rows))
metadataTenantInserted.Get(at).Add(len(mms))
}
rowsPerInsert.Update(float64(len(rows)))
return nil

View File

@@ -55,6 +55,6 @@ func tearDown() {
srv.Close()
logger.ResetOutputForTest()
tmpDataDir := flag.Lookup("remoteWrite.tmpDataPath").Value.String()
fs.MustRemoveDir(tmpDataDir)
fs.MustRemoveAll(tmpDataDir)
}

View File

@@ -6,8 +6,8 @@ import (
"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/prommetadata"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/promremotewrite/stream"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/protoparserutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
@@ -15,11 +15,9 @@ import (
)
var (
rowsInserted = metrics.NewCounter(`vmagent_rows_inserted_total{type="promremotewrite"}`)
metadataInserted = metrics.NewCounter(`vmagent_metadata_inserted_total{type="promremotewrite"}`)
rowsTenantInserted = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_rows_total{type="promremotewrite"}`)
metadataTenantInserted = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_metadata_total{type="promremotewrite"}`)
rowsPerInsert = metrics.NewHistogram(`vmagent_rows_per_insert{type="promremotewrite"}`)
rowsInserted = metrics.NewCounter(`vmagent_rows_inserted_total{type="promremotewrite"}`)
rowsTenantInserted = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_rows_total{type="promremotewrite"}`)
rowsPerInsert = metrics.NewHistogram(`vmagent_rows_per_insert{type="promremotewrite"}`)
)
// InsertHandler processes remote write for prometheus.
@@ -29,18 +27,17 @@ func InsertHandler(at *auth.Token, req *http.Request) error {
return err
}
isVMRemoteWrite := req.Header.Get("Content-Encoding") == "zstd"
return stream.Parse(req.Body, isVMRemoteWrite, func(tss []prompb.TimeSeries, mms []prompb.MetricMetadata) error {
return insertRows(at, tss, mms, extraLabels)
return stream.Parse(req.Body, isVMRemoteWrite, func(tss []prompb.TimeSeries) error {
return insertRows(at, tss, extraLabels)
})
}
func insertRows(at *auth.Token, timeseries []prompb.TimeSeries, mms []prompb.MetricMetadata, extraLabels []prompb.Label) error {
func insertRows(at *auth.Token, timeseries []prompb.TimeSeries, extraLabels []prompbmarshal.Label) error {
ctx := common.GetPushCtx()
defer common.PutPushCtx(ctx)
rowsTotal := 0
tssDst := ctx.WriteRequest.Timeseries[:0]
mmsDst := ctx.WriteRequest.Metadata[:0]
labels := ctx.Labels[:0]
samples := ctx.Samples[:0]
for i := range timeseries {
@@ -49,7 +46,7 @@ func insertRows(at *auth.Token, timeseries []prompb.TimeSeries, mms []prompb.Met
labelsLen := len(labels)
for i := range ts.Labels {
label := &ts.Labels[i]
labels = append(labels, prompb.Label{
labels = append(labels, prompbmarshal.Label{
Name: label.Name,
Value: label.Value,
})
@@ -58,41 +55,17 @@ func insertRows(at *auth.Token, timeseries []prompb.TimeSeries, mms []prompb.Met
samplesLen := len(samples)
for i := range ts.Samples {
sample := &ts.Samples[i]
samples = append(samples, prompb.Sample{
samples = append(samples, prompbmarshal.Sample{
Value: sample.Value,
Timestamp: sample.Timestamp,
})
}
tssDst = append(tssDst, prompb.TimeSeries{
tssDst = append(tssDst, prompbmarshal.TimeSeries{
Labels: labels[labelsLen:],
Samples: samples[samplesLen:],
})
}
ctx.WriteRequest.Timeseries = tssDst
var metadataTotal int
if prommetadata.IsEnabled() {
var accountID, projectID uint32
if at != nil {
accountID = at.AccountID
projectID = at.ProjectID
}
for i := range mms {
mm := &mms[i]
mmsDst = append(mmsDst, prompb.MetricMetadata{
MetricFamilyName: mm.MetricFamilyName,
Help: mm.Help,
Type: mm.Type,
Unit: mm.Unit,
AccountID: accountID,
ProjectID: projectID,
})
}
ctx.WriteRequest.Metadata = mmsDst
metadataTotal = len(mms)
}
ctx.Labels = labels
ctx.Samples = samples
if !remotewrite.TryPush(at, &ctx.WriteRequest) {
@@ -101,9 +74,7 @@ func insertRows(at *auth.Token, timeseries []prompb.TimeSeries, mms []prompb.Met
rowsInserted.Add(rowsTotal)
if at != nil {
rowsTenantInserted.Get(at).Add(rowsTotal)
metadataTenantInserted.Get(at).Add(metadataTotal)
}
metadataInserted.Add(metadataTotal)
rowsPerInsert.Update(float64(rowsTotal))
return nil
}

View File

@@ -15,6 +15,7 @@ import (
"github.com/VictoriaMetrics/VictoriaMetrics/lib/awsapi"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/encoding"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/encoding/zstd"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/httputil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
@@ -447,8 +448,7 @@ again:
}
metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_requests_total{url=%q, status_code="%d"}`, c.sanitizedURL, statusCode)).Inc()
switch statusCode {
case 409:
if statusCode == 409 {
logBlockRejected(block, c.sanitizedURL, resp)
// Just drop block on 409 status code like Prometheus does.
@@ -461,28 +461,22 @@ again:
// - Remote Write v2 specification explicitly specifies a `415 Unsupported Media Type` for unsupported encodings.
// - Real-world implementations of v1 use both 400 and 415 status codes.
// See more in research: https://github.com/VictoriaMetrics/VictoriaMetrics/pull/8462#issuecomment-2786918054
case 415, 400:
} else if statusCode == 415 || statusCode == 400 {
if c.canDowngradeVMProto.Swap(false) {
logger.Infof("received unsupported media type or bad request from remote storage at %q. Downgrading protocol from VictoriaMetrics to Prometheus remote write for all future requests. "+
"See https://docs.victoriametrics.com/victoriametrics/vmagent/#victoriametrics-remote-write-protocol", c.sanitizedURL)
c.useVMProto.Store(false)
}
if encoding.IsZstd(block) {
logger.Infof("received unsupported media type or bad request from remote storage at %q. Re-packing the block to Prometheus remote write and retrying."+
"See https://docs.victoriametrics.com/victoriametrics/vmagent/#victoriametrics-remote-write-protocol", c.sanitizedURL)
zstdBlockLen := len(block)
block, err = repackBlockFromZstdToSnappy(block)
if err == nil {
if c.canDowngradeVMProto.Swap(false) {
logger.Infof("received unsupported media type or bad request from remote storage at %q. Downgrading protocol from VictoriaMetrics to Prometheus remote write for all future requests. "+
"See https://docs.victoriametrics.com/victoriametrics/vmagent/#victoriametrics-remote-write-protocol", c.sanitizedURL)
c.useVMProto.Store(false)
}
block = mustRepackBlockFromZstdToSnappy(block)
c.retriesCount.Inc()
_ = resp.Body.Close()
goto again
}
logger.Warnf("failed to repack zstd block (%s bytes) to snappy: %s; The block will be rejected. "+
"Possible cause: ungraceful shutdown leading to persisted queue corruption.",
zstdBlockLen, err)
c.retriesCount.Inc()
_ = resp.Body.Close()
goto again
}
// Just drop snappy blocks on 400 or 415 status codes like Prometheus does.
@@ -544,21 +538,14 @@ func getRetryDuration(retryAfterDuration, retryDuration, maxRetryDuration time.D
return retryDuration
}
// repackBlockFromZstdToSnappy repacks the given zstd-compressed block to snappy-compressed block.
//
// The input block may be corrupted, for example, if vmagent was shut down ungracefully and
// failed to properly update the persisted queue files. In such cases, zstd decompression
// will fail and an error will be returned.
//
// For more details, see: https://github.com/VictoriaMetrics/VictoriaMetrics/issues/9417
func repackBlockFromZstdToSnappy(zstdBlock []byte) ([]byte, error) {
func mustRepackBlockFromZstdToSnappy(zstdBlock []byte) []byte {
plainBlock := make([]byte, 0, len(zstdBlock)*2)
plainBlock, err := encoding.DecompressZSTD(plainBlock, zstdBlock)
plainBlock, err := zstd.Decompress(plainBlock, zstdBlock)
if err != nil {
return nil, err
logger.Panicf("FATAL: cannot re-pack block with size %d bytes from Zstd to Snappy: %s", len(zstdBlock), err)
}
return snappy.Encode(nil, plainBlock), nil
return snappy.Encode(nil, plainBlock)
}
func logBlockRejected(block []byte, sanitizedURL string, resp *http.Response) {

View File

@@ -25,7 +25,7 @@ func TestCalculateRetryDuration(t *testing.T) {
expectMaxDuration := helper(expectMinDuration)
expectMinDuration = expectMinDuration - (1000 * time.Millisecond) // Avoid edge case when calculating time.Until(now)
if retryDuration < expectMinDuration || retryDuration > expectMaxDuration {
if !(retryDuration >= expectMinDuration && retryDuration <= expectMaxDuration) {
t.Fatalf(
"incorrect retry duration, want (ms): [%d, %d], got (ms): %d",
expectMinDuration.Milliseconds(), expectMaxDuration.Milliseconds(),
@@ -93,7 +93,10 @@ func TestParseRetryAfterHeader(t *testing.T) {
// helper calculate the max possible time duration calculated by timeutil.AddJitterToDuration.
func helper(d time.Duration) time.Duration {
dv := min(d/10, 10*time.Second)
dv := d / 10
if dv > 10*time.Second {
dv = 10 * time.Second
}
return d + dv
}
@@ -102,10 +105,7 @@ func TestRepackBlockFromZstdToSnappy(t *testing.T) {
expectedPlainBlock := []byte(`foobar`)
zstdBlock := encoding.CompressZSTDLevel(nil, expectedPlainBlock, 1)
snappyBlock, err := repackBlockFromZstdToSnappy(zstdBlock)
if err != nil {
t.Fatalf("unexpected error: %s", err)
}
snappyBlock := mustRepackBlockFromZstdToSnappy(zstdBlock)
actualPlainBlock, err := snappy.Decode(nil, snappyBlock)
if err != nil {
@@ -116,14 +116,3 @@ func TestRepackBlockFromZstdToSnappy(t *testing.T) {
t.Fatalf("unexpected plain block; got %q; want %q", actualPlainBlock, expectedPlainBlock)
}
}
func TestRepackBlockFromZstdToSnappyInvalidBlock(t *testing.T) {
snappyBlock, err := repackBlockFromZstdToSnappy([]byte("invalid zstd block"))
if err == nil {
t.Fatalf("expected error for invalid zstd block; got nil")
}
if len(snappyBlock) != 0 {
t.Fatalf("expected empty snappy block; got %d bytes", len(snappyBlock))
}
}

View File

@@ -14,7 +14,7 @@ import (
"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/persistentqueue"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/slicesutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/timeutil"
@@ -24,10 +24,9 @@ import (
var (
flushInterval = flag.Duration("remoteWrite.flushInterval", time.Second, "Interval for flushing the data to remote storage. "+
"This option takes effect only when less than -remoteWrite.maxRowsPerBlock data points per -remoteWrite.flushInterval are pushed to -remoteWrite.url")
"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")
maxMetadataPerBlock = flag.Int("remoteWrite.maxMetadataPerBlock", 5000, "The maximum number of metadata 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/victoriametrics/vmagent/#victoriametrics-remote-write-protocol")
@@ -61,16 +60,9 @@ func (ps *pendingSeries) MustStop() {
ps.periodicFlusherWG.Wait()
}
func (ps *pendingSeries) TryPushTimeSeries(tss []prompb.TimeSeries) bool {
func (ps *pendingSeries) TryPush(tss []prompbmarshal.TimeSeries) bool {
ps.mu.Lock()
ok := ps.wr.tryPushTimeSeries(tss)
ps.mu.Unlock()
return ok
}
func (ps *pendingSeries) TryPushMetadata(mms []prompb.MetricMetadata) bool {
ps.mu.Lock()
ok := ps.wr.tryPushMetadata(mms)
ok := ps.wr.tryPush(tss)
ps.mu.Unlock()
return ok
}
@@ -116,37 +108,29 @@ type writeRequest struct {
// How many decimal digits after point must be left before sending the writeRequest to fq.
roundDigits int
wr prompb.WriteRequest
wr prompbmarshal.WriteRequest
tss []prompb.TimeSeries
mms []prompb.MetricMetadata
labels []prompb.Label
samples []prompb.Sample
tss []prompbmarshal.TimeSeries
labels []prompbmarshal.Label
samples []prompbmarshal.Sample
// buf holds labels data
buf []byte
// metadatabuf holds metadata data
metadatabuf []byte
}
func (wr *writeRequest) reset() {
// Do not reset lastFlushTime, fq, isVMRemoteWrite, significantFigures and roundDigits, since they are reused.
wr.wr.Timeseries = nil
wr.wr.Metadata = nil
clear(wr.tss)
wr.tss = wr.tss[:0]
clear(wr.mms)
wr.mms = wr.mms[:0]
promrelabel.CleanLabels(wr.labels)
wr.labels = wr.labels[:0]
wr.samples = wr.samples[:0]
wr.buf = wr.buf[:0]
wr.metadatabuf = wr.metadatabuf[:0]
}
// mustFlushOnStop force pushes wr data into wr.fq
@@ -154,7 +138,6 @@ func (wr *writeRequest) reset() {
// This is needed in order to properly save in-memory data to persistent queue on graceful shutdown.
func (wr *writeRequest) mustFlushOnStop() {
wr.wr.Timeseries = wr.tss
wr.wr.Metadata = wr.mms
if !tryPushWriteRequest(&wr.wr, wr.mustWriteBlock, wr.isVMRemoteWrite.Load()) {
logger.Panicf("BUG: final flush must always return true")
}
@@ -168,7 +151,6 @@ func (wr *writeRequest) mustWriteBlock(block []byte) bool {
func (wr *writeRequest) tryFlush() bool {
wr.wr.Timeseries = wr.tss
wr.wr.Metadata = wr.mms
wr.lastFlushTime.Store(fasttime.UnixTimestamp())
if !tryPushWriteRequest(&wr.wr, wr.fq.TryWriteBlock, wr.isVMRemoteWrite.Load()) {
return false
@@ -177,7 +159,7 @@ func (wr *writeRequest) tryFlush() bool {
return true
}
func adjustSampleValues(samples []prompb.Sample, significantFigures, roundDigits int) {
func adjustSampleValues(samples []prompbmarshal.Sample, significantFigures, roundDigits int) {
if n := significantFigures; n > 0 {
for i := range samples {
s := &samples[i]
@@ -192,49 +174,7 @@ func adjustSampleValues(samples []prompb.Sample, significantFigures, roundDigits
}
}
func (wr *writeRequest) tryPushMetadata(mms []prompb.MetricMetadata) bool {
mmdDst := wr.mms
maxMetadataPerBlock := *maxMetadataPerBlock
for i := range mms {
if len(wr.mms) >= maxMetadataPerBlock {
if !wr.tryFlush() {
return false
}
mmdDst = wr.mms
}
mmSrc := &mms[i]
mmdDst = append(mmdDst, prompb.MetricMetadata{})
wr.copyMetadata(&mmdDst[len(mmdDst)-1], mmSrc)
}
wr.mms = mmdDst
return true
}
func (wr *writeRequest) copyMetadata(dst, src *prompb.MetricMetadata) {
// Direct copy for non-string fields, which are safe by value.
dst.Type = src.Type
dst.Unit = src.Unit
// Pre-allocate memory for all string fields.
neededBufLen := len(src.MetricFamilyName) + len(src.Help)
bufLen := len(wr.metadatabuf)
wr.metadatabuf = slicesutil.SetLength(wr.metadatabuf, bufLen+neededBufLen)
buf := wr.metadatabuf[:bufLen]
// Copy MetricFamilyName
bufLen = len(buf)
buf = append(buf, src.MetricFamilyName...)
dst.MetricFamilyName = bytesutil.ToUnsafeString(buf[bufLen:])
// Copy Help
bufLen = len(buf)
buf = append(buf, src.Help...)
dst.Help = bytesutil.ToUnsafeString(buf[bufLen:])
wr.metadatabuf = buf
}
func (wr *writeRequest) tryPushTimeSeries(src []prompb.TimeSeries) bool {
func (wr *writeRequest) tryPush(src []prompbmarshal.TimeSeries) bool {
tssDst := wr.tss
maxSamplesPerBlock := *maxRowsPerBlock
// Allow up to 10x of labels per each block on average.
@@ -249,7 +189,7 @@ func (wr *writeRequest) tryPushTimeSeries(src []prompb.TimeSeries) bool {
}
tsSrc := &src[i]
adjustSampleValues(tsSrc.Samples, wr.significantFigures, wr.roundDigits)
tssDst = append(tssDst, prompb.TimeSeries{})
tssDst = append(tssDst, prompbmarshal.TimeSeries{})
wr.copyTimeSeries(&tssDst[len(tssDst)-1], tsSrc)
}
@@ -257,7 +197,7 @@ func (wr *writeRequest) tryPushTimeSeries(src []prompb.TimeSeries) bool {
return true
}
func (wr *writeRequest) copyTimeSeries(dst, src *prompb.TimeSeries) {
func (wr *writeRequest) copyTimeSeries(dst, src *prompbmarshal.TimeSeries) {
labelsSrc := src.Labels
// Pre-allocate memory for labels.
@@ -300,8 +240,8 @@ func (wr *writeRequest) copyTimeSeries(dst, src *prompb.TimeSeries) {
// marshalConcurrency limits the maximum number of concurrent workers, which marshal and compress WriteRequest.
var marshalConcurrencyCh = make(chan struct{}, cgroup.AvailableCPUs())
func tryPushWriteRequest(wr *prompb.WriteRequest, tryPushBlock func(block []byte) bool, isVMRemoteWrite bool) bool {
if wr.IsEmpty() {
func tryPushWriteRequest(wr *prompbmarshal.WriteRequest, tryPushBlock func(block []byte) bool, isVMRemoteWrite bool) bool {
if len(wr.Timeseries) == 0 {
// Nothing to push
return true
}
@@ -327,7 +267,6 @@ func tryPushWriteRequest(wr *prompb.WriteRequest, tryPushBlock func(block []byte
compressBufPool.Put(zb)
if ok {
blockSizeRows.Update(float64(len(wr.Timeseries)))
blockMetadataRows.Update(float64(len(wr.Metadata)))
blockSizeBytes.Update(float64(zbLen))
}
return ok
@@ -339,86 +278,47 @@ func tryPushWriteRequest(wr *prompb.WriteRequest, tryPushBlock func(block []byte
<-marshalConcurrencyCh
}
// Split timeseries or metadata into two smaller blocks
switch len(wr.Timeseries) {
case 0:
if len(wr.Metadata) == 1 {
logger.Warnf("dropping a metadata exceeding -remoteWrite.maxBlockSize=%d bytes", maxUnpackedBlockSize.N)
return true
}
metadata := wr.Metadata
n := len(metadata) / 2
wr.Metadata = metadata[:n]
if !tryPushWriteRequest(wr, tryPushBlock, isVMRemoteWrite) {
wr.Metadata = metadata
return false
}
wr.Metadata = metadata[n:]
if !tryPushWriteRequest(wr, tryPushBlock, isVMRemoteWrite) {
wr.Metadata = metadata
return false
}
wr.Metadata = metadata
return true
case 1:
// A single time series left. Recursively split its samples and metadata into smaller parts if possible.
// Too big block. Recursively split it into smaller parts if possible.
if len(wr.Timeseries) == 1 {
// A single time series left. Recursively split its samples into smaller parts if possible.
samples := wr.Timeseries[0].Samples
metaData := wr.Metadata
if len(samples) == 1 && len(metaData) <= 1 {
logger.Warnf("dropping a sample for metric and %d metadata which are exceeding -remoteWrite.maxBlockSize=%d bytes", len(metaData), maxUnpackedBlockSize.N)
if len(samples) == 1 {
logger.Warnf("dropping a sample for metric with too long labels exceeding -remoteWrite.maxBlockSize=%d bytes", maxUnpackedBlockSize.N)
return true
}
n := len(samples) / 2
m := len(metaData) / 2
wr.Timeseries[0].Samples = samples[:n]
wr.Metadata = metaData[:m]
if !tryPushWriteRequest(wr, tryPushBlock, isVMRemoteWrite) {
wr.Timeseries[0].Samples = samples
wr.Metadata = metaData
return false
}
wr.Timeseries[0].Samples = samples[n:]
wr.Metadata = metaData[m:]
if !tryPushWriteRequest(wr, tryPushBlock, isVMRemoteWrite) {
wr.Timeseries[0].Samples = samples
wr.Metadata = metaData
return false
}
wr.Timeseries[0].Samples = samples
wr.Metadata = metaData
return true
default:
// Split both timeseries and metadata.
timeseries := wr.Timeseries
metaData := wr.Metadata
n := len(timeseries) / 2
m := len(metaData) / 2
wr.Timeseries = timeseries[:n]
wr.Metadata = metaData[:m]
if !tryPushWriteRequest(wr, tryPushBlock, isVMRemoteWrite) {
wr.Timeseries = timeseries
wr.Metadata = metaData
return false
}
wr.Timeseries = timeseries[n:]
wr.Metadata = metaData[m:]
if !tryPushWriteRequest(wr, tryPushBlock, isVMRemoteWrite) {
wr.Timeseries = timeseries
wr.Metadata = metaData
return false
}
wr.Timeseries = timeseries
wr.Metadata = metaData
return true
}
timeseries := wr.Timeseries
n := len(timeseries) / 2
wr.Timeseries = timeseries[:n]
if !tryPushWriteRequest(wr, tryPushBlock, isVMRemoteWrite) {
wr.Timeseries = timeseries
return false
}
wr.Timeseries = timeseries[n:]
if !tryPushWriteRequest(wr, tryPushBlock, isVMRemoteWrite) {
wr.Timeseries = timeseries
return false
}
wr.Timeseries = timeseries
return true
}
var (
blockSizeBytes = metrics.NewHistogram(`vmagent_remotewrite_block_size_bytes`)
blockSizeRows = metrics.NewHistogram(`vmagent_remotewrite_block_size_rows`)
blockMetadataRows = metrics.NewHistogram(`vmagent_remotewrite_block_metadata_rows`)
blockSizeBytes = metrics.NewHistogram(`vmagent_remotewrite_block_size_bytes`)
blockSizeRows = metrics.NewHistogram(`vmagent_remotewrite_block_size_rows`)
)
var (

View File

@@ -5,7 +5,7 @@ import (
"math"
"testing"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
)
func TestPushWriteRequest(t *testing.T) {
@@ -49,19 +49,19 @@ func testPushWriteRequest(t *testing.T, rowsCount, expectedBlockLenProm, expecte
f(true, expectedBlockLenVM, 15)
}
func newTestWriteRequest(seriesCount, labelsCount int) *prompb.WriteRequest {
var wr prompb.WriteRequest
func newTestWriteRequest(seriesCount, labelsCount int) *prompbmarshal.WriteRequest {
var wr prompbmarshal.WriteRequest
for i := 0; i < seriesCount; i++ {
var labels []prompb.Label
var labels []prompbmarshal.Label
for j := 0; j < labelsCount; j++ {
labels = append(labels, prompb.Label{
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, prompb.TimeSeries{
wr.Timeseries = append(wr.Timeseries, prompbmarshal.TimeSeries{
Labels: labels,
Samples: []prompb.Sample{
Samples: []prompbmarshal.Sample{
{
Value: float64(i),
Timestamp: 1000 * int64(i),

View File

@@ -3,18 +3,15 @@ package remotewrite
import (
"flag"
"fmt"
"io"
"strconv"
"strings"
"sync"
"sync/atomic"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/fasttime"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
"go.yaml.in/yaml/v3"
"github.com/VictoriaMetrics/metrics"
)
@@ -35,12 +32,9 @@ var (
"See https://prometheus.io/docs/concepts/data_model/#metric-names-and-labels")
)
var labelsGlobal []prompbmarshal.Label
var (
labelsGlobal []prompb.Label
remoteWriteRelabelConfigData atomic.Pointer[[]byte]
remoteWriteURLRelabelConfigData atomic.Pointer[[]interface{}]
relabelConfigReloads *metrics.Counter
relabelConfigReloadErrors *metrics.Counter
relabelConfigSuccess *metrics.Gauge
@@ -73,42 +67,6 @@ func initRelabelConfigs() {
}
}
// WriteRelabelConfigData writes -remoteWrite.relabelConfig contents to w
func WriteRelabelConfigData(w io.Writer) {
p := remoteWriteRelabelConfigData.Load()
if p == nil {
// Nothing to write to w
return
}
_, _ = w.Write(*p)
}
// WriteURLRelabelConfigData writes -remoteWrite.urlRelabelConfig contents to w
func WriteURLRelabelConfigData(w io.Writer) {
p := remoteWriteURLRelabelConfigData.Load()
if p == nil {
// Nothing to write to w
return
}
type urlRelabelCfg struct {
Url string `yaml:"url"`
RelabelConfig interface{} `yaml:"relabel_config"`
}
var cs []urlRelabelCfg
for i, url := range *remoteWriteURLs {
cfgData := (*p)[i]
if !*showRemoteWriteURL {
url = fmt.Sprintf("%d:secret-url", i+1)
}
cs = append(cs, urlRelabelCfg{
Url: url,
RelabelConfig: cfgData,
})
}
d, _ := yaml.Marshal(cs)
_, _ = w.Write(d)
}
func reloadRelabelConfigs() {
rcs := allRelabelConfigs.Load()
if !rcs.isSet() {
@@ -132,42 +90,28 @@ func reloadRelabelConfigs() {
func loadRelabelConfigs() (*relabelConfigs, error) {
var rcs relabelConfigs
if *relabelConfigPathGlobal != "" {
global, rawCfg, err := promrelabel.LoadRelabelConfigs(*relabelConfigPathGlobal)
global, err := promrelabel.LoadRelabelConfigs(*relabelConfigPathGlobal)
if err != nil {
return nil, fmt.Errorf("cannot load -remoteWrite.relabelConfig=%q: %w", *relabelConfigPathGlobal, err)
}
remoteWriteRelabelConfigData.Store(&rawCfg)
rcs.global = global
}
if len(*relabelConfigPaths) > len(*remoteWriteURLs) {
return nil, fmt.Errorf("too many -remoteWrite.urlRelabelConfig args: %d; it mustn't exceed the number of -remoteWrite.url args: %d",
len(*relabelConfigPaths), (len(*remoteWriteURLs)))
}
var urlRelabelCfgs []interface{}
rcs.perURL = make([]*promrelabel.ParsedConfigs, len(*remoteWriteURLs))
for i, path := range *relabelConfigPaths {
if len(path) == 0 {
urlRelabelCfgs = append(urlRelabelCfgs, nil)
// Skip empty relabel config.
continue
}
prc, rawCfg, err := promrelabel.LoadRelabelConfigs(path)
prc, err := promrelabel.LoadRelabelConfigs(path)
if err != nil {
return nil, fmt.Errorf("cannot load relabel configs from -remoteWrite.urlRelabelConfig=%q: %w", path, err)
}
rcs.perURL[i] = prc
var parsedCfg interface{}
_ = yaml.Unmarshal(rawCfg, &parsedCfg)
urlRelabelCfgs = append(urlRelabelCfgs, parsedCfg)
}
if len(*remoteWriteURLs) > len(*relabelConfigPaths) {
// fill the urlRelabelCfgs with empty relabel configs if not set
for i := len(*relabelConfigPaths); i < len(*remoteWriteURLs); i++ {
urlRelabelCfgs = append(urlRelabelCfgs, nil)
}
}
remoteWriteURLRelabelConfigData.Store(&urlRelabelCfgs)
return &rcs, nil
}
@@ -202,14 +146,14 @@ func initLabelsGlobal() {
if n < 0 {
logger.Fatalf("missing '=' in `-remoteWrite.label`. It must contain label in the form `name=value`; got %q", s)
}
labelsGlobal = append(labelsGlobal, prompb.Label{
labelsGlobal = append(labelsGlobal, prompbmarshal.Label{
Name: s[:n],
Value: s[n+1:],
})
}
}
func (rctx *relabelCtx) applyRelabeling(tss []prompb.TimeSeries, pcs *promrelabel.ParsedConfigs) []prompb.TimeSeries {
func (rctx *relabelCtx) applyRelabeling(tss []prompbmarshal.TimeSeries, pcs *promrelabel.ParsedConfigs) []prompbmarshal.TimeSeries {
if pcs.Len() == 0 && !*usePromCompatibleNaming {
// Nothing to change.
return tss
@@ -230,7 +174,7 @@ func (rctx *relabelCtx) applyRelabeling(tss []prompb.TimeSeries, pcs *promrelabe
if *usePromCompatibleNaming {
fixPromCompatibleNaming(labels[labelsLen:])
}
tssDst = append(tssDst, prompb.TimeSeries{
tssDst = append(tssDst, prompbmarshal.TimeSeries{
Labels: labels[labelsLen:],
Samples: ts.Samples,
})
@@ -239,7 +183,7 @@ func (rctx *relabelCtx) applyRelabeling(tss []prompb.TimeSeries, pcs *promrelabe
return tssDst
}
func (rctx *relabelCtx) appendExtraLabels(tss []prompb.TimeSeries, extraLabels []prompb.Label) {
func (rctx *relabelCtx) appendExtraLabels(tss []prompbmarshal.TimeSeries, extraLabels []prompbmarshal.Label) {
if len(extraLabels) == 0 {
return
}
@@ -263,7 +207,7 @@ func (rctx *relabelCtx) appendExtraLabels(tss []prompb.TimeSeries, extraLabels [
rctx.labels = labels
}
func (rctx *relabelCtx) tenantToLabels(tss []prompb.TimeSeries, accountID, projectID uint32) {
func (rctx *relabelCtx) tenantToLabels(tss []prompbmarshal.TimeSeries, accountID, projectID uint32) {
rctx.reset()
accountIDStr := strconv.FormatUint(uint64(accountID), 10)
projectIDStr := strconv.FormatUint(uint64(projectID), 10)
@@ -278,11 +222,11 @@ func (rctx *relabelCtx) tenantToLabels(tss []prompb.TimeSeries, accountID, proje
}
labels = append(labels, label)
}
labels = append(labels, prompb.Label{
labels = append(labels, prompbmarshal.Label{
Name: "vm_account_id",
Value: accountIDStr,
})
labels = append(labels, prompb.Label{
labels = append(labels, prompbmarshal.Label{
Name: "vm_project_id",
Value: projectIDStr,
})
@@ -293,7 +237,7 @@ func (rctx *relabelCtx) tenantToLabels(tss []prompb.TimeSeries, accountID, proje
type relabelCtx struct {
// pool for labels, which are used during the relabeling.
labels []prompb.Label
labels []prompbmarshal.Label
}
func (rctx *relabelCtx) reset() {
@@ -316,7 +260,7 @@ func putRelabelCtx(rctx *relabelCtx) {
relabelCtxPool.Put(rctx)
}
func fixPromCompatibleNaming(labels []prompb.Label) {
func fixPromCompatibleNaming(labels []prompbmarshal.Label) {
// Replace unsupported Prometheus chars in label names and metric names with underscores.
for i := range labels {
label := &labels[i]

View File

@@ -4,7 +4,7 @@ import (
"reflect"
"testing"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promutil"
)
@@ -39,7 +39,7 @@ func TestApplyRelabeling(t *testing.T) {
}
func TestAppendExtraLabels(t *testing.T) {
f := func(extraLabels []prompb.Label, sTss, sExpTss string) {
f := func(extraLabels []prompbmarshal.Label, sTss, sExpTss string) {
t.Helper()
rctx := &relabelCtx{}
tss, expTss := parseSeries(sTss), parseSeries(sExpTss)
@@ -50,19 +50,19 @@ func TestAppendExtraLabels(t *testing.T) {
}
f(nil, "up", "up")
f([]prompb.Label{{Name: "foo", Value: "bar"}}, "up", `up{foo="bar"}`)
f([]prompb.Label{{Name: "foo", Value: "bar"}}, `up{foo="baz"}`, `up{foo="bar"}`)
f([]prompb.Label{{Name: "baz", Value: "qux"}}, `up{foo="baz"}`, `up{foo="baz",baz="qux"}`)
f([]prompbmarshal.Label{{Name: "foo", Value: "bar"}}, "up", `up{foo="bar"}`)
f([]prompbmarshal.Label{{Name: "foo", Value: "bar"}}, `up{foo="baz"}`, `up{foo="bar"}`)
f([]prompbmarshal.Label{{Name: "baz", Value: "qux"}}, `up{foo="baz"}`, `up{foo="baz",baz="qux"}`)
oldVal := *usePromCompatibleNaming
*usePromCompatibleNaming = true
f([]prompb.Label{{Name: "foo.bar", Value: "baz"}}, "up", `up{foo.bar="baz"}`)
f([]prompbmarshal.Label{{Name: "foo.bar", Value: "baz"}}, "up", `up{foo.bar="baz"}`)
*usePromCompatibleNaming = oldVal
}
func parseSeries(data string) []prompb.TimeSeries {
var tss []prompb.TimeSeries
tss = append(tss, prompb.TimeSeries{
func parseSeries(data string) []prompbmarshal.TimeSeries {
var tss []prompbmarshal.TimeSeries
tss = append(tss, prompbmarshal.TimeSeries{
Labels: promutil.MustNewLabelsFromString(data).GetLabels(),
})
return tss

View File

@@ -23,11 +23,10 @@ import (
"github.com/VictoriaMetrics/VictoriaMetrics/lib/memory"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/persistentqueue"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/procutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/ratelimiter"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/slicesutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/streamaggr"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/timeserieslimits"
"github.com/VictoriaMetrics/metrics"
@@ -210,7 +209,7 @@ func Init() {
// In this case it is impossible to prevent from sending many duplicates of samples passed to TryPush() to all the configured -remoteWrite.url
// if these samples couldn't be sent to the -remoteWrite.url with the disabled persistent queue. So it is better sending samples
// to the remaining -remoteWrite.url and dropping them on the blocked queue.
dropSamplesOnFailureGlobal = *dropSamplesOnOverload || disableOnDiskQueueAny && len(*remoteWriteURLs) > 1
dropSamplesOnFailureGlobal = *dropSamplesOnOverload || disableOnDiskQueueAny && len(disableOnDiskQueues) > 1
dropDanglingQueues()
@@ -254,7 +253,7 @@ func dropDanglingQueues() {
if _, ok := existingQueues[dirname]; !ok {
logger.Infof("removing dangling queue %q", dirname)
fullPath := filepath.Join(queuesDir, dirname)
fs.MustRemoveDir(fullPath)
fs.MustRemoveAll(fullPath)
removed++
}
}
@@ -373,7 +372,7 @@ func Stop() {
// PushDropSamplesOnFailure drops wr samples if they cannot be sent to -remoteWrite.url by any reason.
//
// PushDropSamplesOnFailure can modify wr contents.
func PushDropSamplesOnFailure(at *auth.Token, wr *prompb.WriteRequest) {
func PushDropSamplesOnFailure(at *auth.Token, wr *prompbmarshal.WriteRequest) {
_ = tryPush(at, wr, true)
}
@@ -383,13 +382,19 @@ func PushDropSamplesOnFailure(at *auth.Token, wr *prompb.WriteRequest) {
// TryPush may send partial data from wr on unsuccessful attempt, so repeated call for the same wr may send the data multiple times.
//
// The caller must return ErrQueueFullHTTPRetry to the client, which sends wr, if TryPush returns false.
func TryPush(at *auth.Token, wr *prompb.WriteRequest) bool {
func TryPush(at *auth.Token, wr *prompbmarshal.WriteRequest) bool {
return tryPush(at, wr, dropSamplesOnFailureGlobal)
}
func tryPush(at *auth.Token, wr *prompb.WriteRequest, forceDropSamplesOnFailure bool) bool {
func tryPush(at *auth.Token, wr *prompbmarshal.WriteRequest, forceDropSamplesOnFailure bool) bool {
tss := wr.Timeseries
mms := wr.Metadata
var tenantRctx *relabelCtx
if at != nil {
// Convert at to (vm_account_id, vm_project_id) labels.
tenantRctx = getRelabelCtx()
defer putRelabelCtx(tenantRctx)
}
// Quick check whether writes to configured remote storage systems are blocked.
// This allows saving CPU time spent on relabeling and block compression
@@ -406,23 +411,6 @@ func tryPush(at *auth.Token, wr *prompb.WriteRequest, forceDropSamplesOnFailure
return true
}
// Push metadata separately from time series, since it doesn't need sharding,
// relabeling, stream aggregation, deduplication, etc.
if !tryPushMetadataToRemoteStorages(rwctxs, mms, forceDropSamplesOnFailure) {
return false
}
if len(tss) == 0 {
return true
}
var tenantRctx *relabelCtx
if at != nil {
// Convert at to (vm_account_id, vm_project_id) labels.
tenantRctx = getRelabelCtx()
defer putRelabelCtx(tenantRctx)
}
var rctx *relabelCtx
rcs := allRelabelConfigs.Load()
pcsGlobal := rcs.global
@@ -486,9 +474,6 @@ func tryPush(at *auth.Token, wr *prompb.WriteRequest, forceDropSamplesOnFailure
matchIdxs.B = sas.Push(tssBlock, matchIdxs.B)
if !*streamAggrGlobalKeepInput {
tssBlock = dropAggregatedSeries(tssBlock, matchIdxs.B, *streamAggrGlobalDropInput)
} else if *streamAggrGlobalDropInput {
// if both keep_input and drop_input are true, we keep only the aggregated series
tssBlock = dropUnaggregatedSeries(tssBlock, matchIdxs.B)
}
matchIdxsPool.Put(matchIdxs)
}
@@ -496,7 +481,7 @@ func tryPush(at *auth.Token, wr *prompb.WriteRequest, forceDropSamplesOnFailure
deduplicatorGlobal.Push(tssBlock)
tssBlock = tssBlock[:0]
}
if !tryPushTimeSeriesToRemoteStorages(rwctxs, tssBlock, forceDropSamplesOnFailure) {
if !tryPushBlockToRemoteStorages(rwctxs, tssBlock, forceDropSamplesOnFailure) {
return false
}
}
@@ -507,7 +492,7 @@ func tryPush(at *auth.Token, wr *prompb.WriteRequest, forceDropSamplesOnFailure
// returns only the unblocked rwctx.
//
// calculateHealthyRwctxIdx will rely on the order of rwctx to be in ascending order.
func getEligibleRemoteWriteCtxs(tss []prompb.TimeSeries, forceDropSamplesOnFailure bool) ([]*remoteWriteCtx, bool) {
func getEligibleRemoteWriteCtxs(tss []prompbmarshal.TimeSeries, forceDropSamplesOnFailure bool) ([]*remoteWriteCtx, bool) {
if !disableOnDiskQueueAny {
return rwctxsGlobal, true
}
@@ -535,49 +520,18 @@ func getEligibleRemoteWriteCtxs(tss []prompb.TimeSeries, forceDropSamplesOnFailu
return rwctxs, true
}
func pushTimeSeriesToRemoteStoragesTrackDropped(tss []prompb.TimeSeries) {
func pushToRemoteStoragesTrackDropped(tss []prompbmarshal.TimeSeries) {
rwctxs, _ := getEligibleRemoteWriteCtxs(tss, true)
if len(rwctxs) == 0 {
return
}
if !tryPushTimeSeriesToRemoteStorages(rwctxs, tss, true) {
logger.Panicf("BUG: tryPushTimeSeriesToRemoteStorages() must return true when forceDropSamplesOnFailure=true")
if !tryPushBlockToRemoteStorages(rwctxs, tss, true) {
logger.Panicf("BUG: tryPushBlockToRemoteStorages() must return true when forceDropSamplesOnFailure=true")
}
}
func tryPushMetadataToRemoteStorages(rwctxs []*remoteWriteCtx, mms []prompb.MetricMetadata, forceDropSamplesOnFailure bool) bool {
if len(mms) == 0 {
// Nothing to push
return true
}
// Do not shard metadata even if -remoteWrite.shardByURL is set, just replicate it among rwctxs.
// Since metadata is usually small and there is no guarantee that metadata can be sent to
// the same remote storage with the corresponding metrics.
//
// Push metadata to remote storage systems in parallel to reduce
// the time needed for sending the data to multiple remote storage systems.
var wg sync.WaitGroup
wg.Add(len(rwctxs))
var anyPushFailed atomic.Bool
for _, rwctx := range rwctxs {
go func(rwctx *remoteWriteCtx) {
defer wg.Done()
if !rwctx.tryPushMetadataInternal(mms) {
rwctx.pushFailures.Inc()
if forceDropSamplesOnFailure {
rwctx.metadataDroppedOnPushFailure.Add(len(mms))
return
}
anyPushFailed.Store(true)
}
}(rwctx)
}
wg.Wait()
return !anyPushFailed.Load()
}
func tryPushTimeSeriesToRemoteStorages(rwctxs []*remoteWriteCtx, tssBlock []prompb.TimeSeries, forceDropSamplesOnFailure bool) bool {
func tryPushBlockToRemoteStorages(rwctxs []*remoteWriteCtx, tssBlock []prompbmarshal.TimeSeries, forceDropSamplesOnFailure bool) bool {
if len(tssBlock) == 0 {
// Nothing to push
return true
@@ -585,7 +539,7 @@ func tryPushTimeSeriesToRemoteStorages(rwctxs []*remoteWriteCtx, tssBlock []prom
if len(rwctxs) == 1 {
// Fast path - just push data to the configured single remote storage
return rwctxs[0].TryPushTimeSeries(tssBlock, forceDropSamplesOnFailure)
return rwctxs[0].TryPush(tssBlock, forceDropSamplesOnFailure)
}
// We need to push tssBlock to multiple remote storages.
@@ -596,11 +550,11 @@ func tryPushTimeSeriesToRemoteStorages(rwctxs []*remoteWriteCtx, tssBlock []prom
if replicas <= 0 {
replicas = 1
}
return tryShardingTimeSeriesAmongRemoteStorages(rwctxs, tssBlock, replicas, forceDropSamplesOnFailure)
return tryShardingBlockAmongRemoteStorages(rwctxs, tssBlock, replicas, forceDropSamplesOnFailure)
}
// Replicate tssBlock samples among rwctxs.
// Push tssBlock to remote storage systems in parallel to reduce
// Push tssBlock to remote storage systems in parallel in order to reduce
// the time needed for sending the data to multiple remote storage systems.
var wg sync.WaitGroup
wg.Add(len(rwctxs))
@@ -608,7 +562,7 @@ func tryPushTimeSeriesToRemoteStorages(rwctxs []*remoteWriteCtx, tssBlock []prom
for _, rwctx := range rwctxs {
go func(rwctx *remoteWriteCtx) {
defer wg.Done()
if !rwctx.TryPushTimeSeries(tssBlock, forceDropSamplesOnFailure) {
if !rwctx.TryPush(tssBlock, forceDropSamplesOnFailure) {
anyPushFailed.Store(true)
}
}(rwctx)
@@ -617,7 +571,7 @@ func tryPushTimeSeriesToRemoteStorages(rwctxs []*remoteWriteCtx, tssBlock []prom
return !anyPushFailed.Load()
}
func tryShardingTimeSeriesAmongRemoteStorages(rwctxs []*remoteWriteCtx, tssBlock []prompb.TimeSeries, replicas int, forceDropSamplesOnFailure bool) bool {
func tryShardingBlockAmongRemoteStorages(rwctxs []*remoteWriteCtx, tssBlock []prompbmarshal.TimeSeries, replicas int, forceDropSamplesOnFailure bool) bool {
x := getTSSShards(len(rwctxs))
defer putTSSShards(x)
@@ -634,9 +588,9 @@ func tryShardingTimeSeriesAmongRemoteStorages(rwctxs []*remoteWriteCtx, tssBlock
continue
}
wg.Add(1)
go func(rwctx *remoteWriteCtx, tss []prompb.TimeSeries) {
go func(rwctx *remoteWriteCtx, tss []prompbmarshal.TimeSeries) {
defer wg.Done()
if !rwctx.TryPushTimeSeries(tss, forceDropSamplesOnFailure) {
if !rwctx.TryPush(tss, forceDropSamplesOnFailure) {
anyPushFailed.Store(true)
}
}(rwctx, shard)
@@ -670,7 +624,7 @@ func calculateHealthyRwctxIdx(healthyRwctxs []*remoteWriteCtx) ([]int, []int) {
}
// shardAmountRemoteWriteCtx distribute time series to shards by consistent hashing.
func shardAmountRemoteWriteCtx(tssBlock []prompb.TimeSeries, shards [][]prompb.TimeSeries, rwctxs []*remoteWriteCtx, replicas int) {
func shardAmountRemoteWriteCtx(tssBlock []prompbmarshal.TimeSeries, shards [][]prompbmarshal.TimeSeries, rwctxs []*remoteWriteCtx, replicas int) {
tmpLabels := promutil.GetLabels()
defer promutil.PutLabels(tmpLabels)
@@ -726,7 +680,7 @@ func shardAmountRemoteWriteCtx(tssBlock []prompb.TimeSeries, shards [][]prompb.T
}
type tssShards struct {
shards [][]prompb.TimeSeries
shards [][]prompbmarshal.TimeSeries
}
func getTSSShards(n int) *tssShards {
@@ -736,7 +690,7 @@ func getTSSShards(n int) *tssShards {
}
x := v.(*tssShards)
if cap(x.shards) < n {
x.shards = make([][]prompb.TimeSeries, n)
x.shards = make([][]prompbmarshal.TimeSeries, n)
}
x.shards = x.shards[:n]
return x
@@ -754,7 +708,7 @@ func putTSSShards(x *tssShards) {
var tssShardsPool sync.Pool
// sortLabelsIfNeeded sorts labels if -sortLabels command-line flag is set.
func sortLabelsIfNeeded(tss []prompb.TimeSeries) {
func sortLabelsIfNeeded(tss []prompbmarshal.TimeSeries) {
if !*sortLabels {
return
}
@@ -763,11 +717,11 @@ func sortLabelsIfNeeded(tss []prompb.TimeSeries) {
}
}
func limitSeriesCardinality(tss []prompb.TimeSeries) []prompb.TimeSeries {
func limitSeriesCardinality(tss []prompbmarshal.TimeSeries) []prompbmarshal.TimeSeries {
if hourlySeriesLimiter == nil && dailySeriesLimiter == nil {
return tss
}
dst := make([]prompb.TimeSeries, 0, len(tss))
dst := make([]prompbmarshal.TimeSeries, 0, len(tss))
for i := range tss {
labels := tss[i].Labels
h := getLabelsHash(labels)
@@ -794,7 +748,7 @@ var (
dailySeriesLimitRowsDropped = metrics.NewCounter(`vmagent_daily_series_limit_rows_dropped_total`)
)
func getLabelsHash(labels []prompb.Label) uint64 {
func getLabelsHash(labels []prompbmarshal.Label) uint64 {
bb := labelsHashBufPool.Get()
b := bb.B[:0]
for _, label := range labels {
@@ -809,12 +763,12 @@ func getLabelsHash(labels []prompb.Label) uint64 {
var labelsHashBufPool bytesutil.ByteBufferPool
func logSkippedSeries(labels []prompb.Label, flagName string, flagValue int) {
func logSkippedSeries(labels []prompbmarshal.Label, flagName string, flagValue int) {
select {
case <-logSkippedSeriesTicker.C:
// Do not use logger.WithThrottler() here, since this will increase CPU usage
// because every call to logSkippedSeries will result to a call to prompb.LabelsToString.
logger.Warnf("skip series %s because %s=%d reached", prompb.LabelsToString(labels), flagName, flagValue)
// because every call to logSkippedSeries will result to a call to prompbmarshal.LabelsToString.
logger.Warnf("skip series %s because %s=%d reached", prompbmarshal.LabelsToString(labels), flagName, flagValue)
default:
}
}
@@ -843,9 +797,8 @@ type remoteWriteCtx struct {
rowsPushedAfterRelabel *metrics.Counter
rowsDroppedByRelabel *metrics.Counter
pushFailures *metrics.Counter
metadataDroppedOnPushFailure *metrics.Counter
rowsDroppedOnPushFailure *metrics.Counter
pushFailures *metrics.Counter
rowsDroppedOnPushFailure *metrics.Counter
}
func newRemoteWriteCtx(argIdx int, remoteWriteURL *url.URL, maxInmemoryBlocks int, sanitizedURL string) *remoteWriteCtx {
@@ -909,9 +862,8 @@ func newRemoteWriteCtx(argIdx int, remoteWriteURL *url.URL, maxInmemoryBlocks in
rowsPushedAfterRelabel: metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_rows_pushed_after_relabel_total{path=%q,url=%q}`, queuePath, sanitizedURL)),
rowsDroppedByRelabel: metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_relabel_metrics_dropped_total{path=%q,url=%q}`, queuePath, sanitizedURL)),
pushFailures: metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_push_failures_total{path=%q,url=%q}`, queuePath, sanitizedURL)),
metadataDroppedOnPushFailure: metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_metadata_dropped_total{path=%q,url=%q}`, queuePath, sanitizedURL)),
rowsDroppedOnPushFailure: metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_samples_dropped_total{path=%q,url=%q}`, queuePath, sanitizedURL)),
pushFailures: metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_push_failures_total{path=%q,url=%q}`, queuePath, sanitizedURL)),
rowsDroppedOnPushFailure: metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_samples_dropped_total{path=%q,url=%q}`, queuePath, sanitizedURL)),
}
rwctx.initStreamAggrConfig()
@@ -945,17 +897,17 @@ func (rwctx *remoteWriteCtx) MustStop() {
rwctx.rowsDroppedByRelabel = nil
}
// TryPushTimeSeries sends tss series to the configured remote write endpoint
// TryPush sends tss series to the configured remote write endpoint
//
// TryPushTimeSeries doesn't modify tss, so tss can be passed concurrently to TryPush across distinct rwctx instances.
func (rwctx *remoteWriteCtx) TryPushTimeSeries(tss []prompb.TimeSeries, forceDropSamplesOnFailure bool) bool {
// TryPush doesn't modify tss, so tss can be passed concurrently to TryPush across distinct rwctx instances.
func (rwctx *remoteWriteCtx) TryPush(tss []prompbmarshal.TimeSeries, forceDropSamplesOnFailure bool) bool {
var rctx *relabelCtx
var v *[]prompb.TimeSeries
var v *[]prompbmarshal.TimeSeries
defer func() {
if rctx == nil {
return
}
*v = prompb.ResetTimeSeries(tss)
*v = prompbmarshal.ResetTimeSeries(tss)
tssPool.Put(v)
putRelabelCtx(rctx)
}()
@@ -969,7 +921,7 @@ func (rwctx *remoteWriteCtx) TryPushTimeSeries(tss []prompb.TimeSeries, forceDro
// 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().(*[]prompb.TimeSeries)
v = tssPool.Get().(*[]prompbmarshal.TimeSeries)
tss = append(*v, tss...)
rowsCountBeforeRelabel := getRowsCount(tss)
tss = rctx.applyRelabeling(tss, pcs)
@@ -988,21 +940,11 @@ func (rwctx *remoteWriteCtx) TryPushTimeSeries(tss []prompb.TimeSeries, forceDro
if rctx == nil {
rctx = getRelabelCtx()
// Make a copy of tss before dropping aggregated series
v = tssPool.Get().(*[]prompb.TimeSeries)
v = tssPool.Get().(*[]prompbmarshal.TimeSeries)
tss = append(*v, tss...)
}
tss = dropAggregatedSeries(tss, matchIdxs.B, rwctx.streamAggrDropInput)
} else if rwctx.streamAggrDropInput {
// if both keep_input and drop_input are true, we keep only the aggregated series
if rctx == nil {
rctx = getRelabelCtx()
// Make a copy of tss before dropping aggregated series
v = tssPool.Get().(*[]prompb.TimeSeries)
tss = append(*v, tss...)
}
tss = dropUnaggregatedSeries(tss, matchIdxs.B)
}
matchIdxsPool.Put(matchIdxs)
}
if rwctx.deduplicator != nil {
@@ -1011,7 +953,7 @@ func (rwctx *remoteWriteCtx) TryPushTimeSeries(tss []prompb.TimeSeries, forceDro
}
// Try pushing tss to remote storage
if rwctx.tryPushTimeSeriesInternal(tss) {
if rwctx.tryPushInternal(tss) {
return true
}
@@ -1025,10 +967,9 @@ func (rwctx *remoteWriteCtx) TryPushTimeSeries(tss []prompb.TimeSeries, forceDro
return false
}
var matchIdxsPool slicesutil.BufferPool[uint32]
var matchIdxsPool bytesutil.ByteBufferPool
// dropAggregatedSeries drops matched series, also the unmatched if dropInput is true.
func dropAggregatedSeries(src []prompb.TimeSeries, matchIdxs []uint32, dropInput bool) []prompb.TimeSeries {
func dropAggregatedSeries(src []prompbmarshal.TimeSeries, matchIdxs []byte, dropInput bool) []prompbmarshal.TimeSeries {
dst := src[:0]
if !dropInput {
for i, match := range matchIdxs {
@@ -1043,22 +984,8 @@ func dropAggregatedSeries(src []prompb.TimeSeries, matchIdxs []uint32, dropInput
return dst
}
// dropUnaggregatedSeries drops unmatched series.
func dropUnaggregatedSeries(src []prompb.TimeSeries, matchIdxs []uint32) []prompb.TimeSeries {
dst := src[:0]
for i, match := range matchIdxs {
if match == 0 {
continue
}
dst = append(dst, src[i])
}
tail := src[len(dst):]
clear(tail)
return dst
}
func (rwctx *remoteWriteCtx) pushInternalTrackDropped(tss []prompb.TimeSeries) {
if rwctx.tryPushTimeSeriesInternal(tss) {
func (rwctx *remoteWriteCtx) pushInternalTrackDropped(tss []prompbmarshal.TimeSeries) {
if rwctx.tryPushInternal(tss) {
return
}
if !rwctx.fq.IsPersistentQueueDisabled() {
@@ -1069,21 +996,14 @@ func (rwctx *remoteWriteCtx) pushInternalTrackDropped(tss []prompb.TimeSeries) {
rwctx.rowsDroppedOnPushFailure.Add(rowsCount)
}
func (rwctx *remoteWriteCtx) tryPushMetadataInternal(mms []prompb.MetricMetadata) bool {
pss := rwctx.pss
idx := rwctx.pssNextIdx.Add(1) % uint64(len(pss))
return pss[idx].TryPushMetadata(mms)
}
func (rwctx *remoteWriteCtx) tryPushTimeSeriesInternal(tss []prompb.TimeSeries) bool {
func (rwctx *remoteWriteCtx) tryPushInternal(tss []prompbmarshal.TimeSeries) bool {
var rctx *relabelCtx
var v *[]prompb.TimeSeries
var v *[]prompbmarshal.TimeSeries
defer func() {
if rctx == nil {
return
}
*v = prompb.ResetTimeSeries(tss)
*v = prompbmarshal.ResetTimeSeries(tss)
tssPool.Put(v)
putRelabelCtx(rctx)
}()
@@ -1092,7 +1012,7 @@ func (rwctx *remoteWriteCtx) tryPushTimeSeriesInternal(tss []prompb.TimeSeries)
// Make a copy of tss before adding extra labels in order to prevent
// from affecting time series for other remoteWrite.url configs.
rctx = getRelabelCtx()
v = tssPool.Get().(*[]prompb.TimeSeries)
v = tssPool.Get().(*[]prompbmarshal.TimeSeries)
tss = append(*v, tss...)
rctx.appendExtraLabels(tss, labelsGlobal)
}
@@ -1100,17 +1020,17 @@ func (rwctx *remoteWriteCtx) tryPushTimeSeriesInternal(tss []prompb.TimeSeries)
pss := rwctx.pss
idx := rwctx.pssNextIdx.Add(1) % uint64(len(pss))
return pss[idx].TryPushTimeSeries(tss)
return pss[idx].TryPush(tss)
}
var tssPool = &sync.Pool{
New: func() any {
a := []prompb.TimeSeries{}
a := []prompbmarshal.TimeSeries{}
return &a
},
}
func getRowsCount(tss []prompb.TimeSeries) int {
func getRowsCount(tss []prompbmarshal.TimeSeries) int {
rowsCount := 0
for _, ts := range tss {
rowsCount += len(ts.Samples)

View File

@@ -10,9 +10,7 @@ import (
"time"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/consistenthash"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/fs"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/persistentqueue"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/prometheus"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/streamaggr"
@@ -27,14 +25,14 @@ func TestGetLabelsHash_Distribution(t *testing.T) {
// Distribute itemsCount hashes returned by getLabelsHash() across bucketsCount buckets.
itemsCount := 1_000 * bucketsCount
m := make([]int, bucketsCount)
var labels []prompb.Label
var labels []prompbmarshal.Label
for i := 0; i < itemsCount; i++ {
labels = append(labels[:0], prompb.Label{
labels = append(labels[:0], prompbmarshal.Label{
Name: "__name__",
Value: fmt.Sprintf("some_name_%d", i),
})
for j := 0; j < 10; j++ {
labels = append(labels, prompb.Label{
labels = append(labels, prompbmarshal.Label{
Name: fmt.Sprintf("label_%d", j),
Value: fmt.Sprintf("value_%d_%d", i, j),
})
@@ -59,8 +57,8 @@ func TestGetLabelsHash_Distribution(t *testing.T) {
f(10)
}
func TestRemoteWriteContext_TryPushTimeSeries(t *testing.T) {
f := func(streamAggrConfig, relabelConfig string, enableWindows bool, dedupInterval time.Duration, keepInput, dropInput bool, input string, expectedRowsPushedAfterRelabel, expectedPushedSample int) {
func TestRemoteWriteContext_TryPush_ImmutableTimeseries(t *testing.T) {
f := func(streamAggrConfig, relabelConfig string, enableWindows bool, dedupInterval time.Duration, keepInput, dropInput bool, input string) {
t.Helper()
perURLRelabel, err := promrelabel.ParseRelabelConfigsData([]byte(relabelConfig))
if err != nil {
@@ -73,16 +71,10 @@ func TestRemoteWriteContext_TryPushTimeSeries(t *testing.T) {
}
allRelabelConfigs.Store(rcs)
path := "fast-queue-write-test"
fs.MustRemoveDir(path)
fq := persistentqueue.MustOpenFastQueue(path, "test", 100, 0, false)
defer fs.MustRemoveDir(path)
defer fq.MustClose()
pss := make([]*pendingSeries, 1)
isVMProto := &atomic.Bool{}
isVMProto.Store(true)
pss[0] = newPendingSeries(fq, isVMProto, 0, 100)
pss[0] = newPendingSeries(nil, isVMProto, 0, 100)
rwctx := &remoteWriteCtx{
idx: 0,
streamAggrKeepInput: keepInput,
@@ -91,14 +83,12 @@ func TestRemoteWriteContext_TryPushTimeSeries(t *testing.T) {
rowsPushedAfterRelabel: metrics.GetOrCreateCounter(`foo`),
rowsDroppedByRelabel: metrics.GetOrCreateCounter(`bar`),
}
defer metrics.UnregisterAllMetrics()
if dedupInterval > 0 {
rwctx.deduplicator = streamaggr.NewDeduplicator(nil, enableWindows, dedupInterval, nil, "dedup-global")
}
if streamAggrConfig != "" {
pushNoop := func(_ []prompb.TimeSeries) {}
pushNoop := func(_ []prompbmarshal.TimeSeries) {}
opts := streamaggr.Options{
EnableWindows: enableWindows,
}
@@ -112,29 +102,25 @@ func TestRemoteWriteContext_TryPushTimeSeries(t *testing.T) {
offsetMsecs := time.Now().UnixMilli()
inputTss := prometheus.MustParsePromMetrics(input, offsetMsecs)
expectedTss := make([]prompb.TimeSeries, len(inputTss))
expectedTss := make([]prompbmarshal.TimeSeries, len(inputTss))
// check inputTss is not modified after TryPushTimeSeries
// copy inputTss to make sure it is not mutated during TryPush call
copy(expectedTss, inputTss)
if !rwctx.TryPushTimeSeries(inputTss, false) {
if !rwctx.TryPush(inputTss, false) {
t.Fatalf("cannot push samples to rwctx")
}
if int(rwctx.rowsPushedAfterRelabel.Get()) != expectedRowsPushedAfterRelabel {
t.Fatalf("unexpected number of rows after relabel; got %d; want %d", rwctx.rowsPushedAfterRelabel.Get(), expectedRowsPushedAfterRelabel)
}
if len(pss[0].wr.tss) != expectedPushedSample {
t.Fatalf("unexpected number of pushed samples; got %d; want %d", len(pss[0].wr.tss), expectedPushedSample)
}
if !reflect.DeepEqual(expectedTss, inputTss) {
t.Fatalf("unexpected samples;\ngot\n%v\nwant\n%v", inputTss, expectedTss)
}
}
// relabeling
f(``, `
f(`
- interval: 1m
outputs: [sum_samples]
- interval: 2m
outputs: [count_series]
`, `
- action: keep
source_labels: [env]
regex: "dev"
@@ -143,66 +129,53 @@ metric{env="dev"} 10
metric{env="bar"} 20
metric{env="dev"} 15
metric{env="bar"} 25
`, 2, 2)
// relabeling + aggregation
f(`
- match: '{env="dev"}'
interval: 1m
outputs: [sum_samples]
`, `
- action: keep
source_labels: [env]
regex: ".*"
`, false, 0, false, false, `
metric{env="dev"} 10
metric{env="bar"} 20
metric{env="dev"} 15
metric{env="bar"} 25
`, 4, 2)
// aggregation + keepInput
f(`
- match: '{env="dev"}'
interval: 1m
outputs: [sum_samples]
`, ``, false, 0, true, false, `
metric{env="dev"} 10
metric{env="bar"} 20
metric{env="dev"} 15
metric{env="bar"} 25
`, 4, 4)
// aggregation + dropInput
f(`
- match: '{env="dev"}'
interval: 1m
outputs: [sum_samples]
`, ``, false, 0, false, true, `
metric{env="dev"} 10
metric{env="bar"} 20
metric{env="dev"} 15
metric{env="bar"} 25
`, 4, 0)
// aggregation + keepInput + dropInput
f(`
- match: '{env="dev"}'
interval: 1m
outputs: [sum_samples]
`, ``, false, 0, true, true, `
metric{env="dev"} 10
metric{env="bar"} 20
metric{env="bar"} 25
`, 3, 1)
// aggregation + deduplication
`)
f(``, ``, true, time.Hour, false, false, `
metric{env="dev"} 10
metric{env="foo"} 20
metric{env="dev"} 15
metric{env="foo"} 25
`, 4, 0)
`)
f(``, `
- action: keep
source_labels: [env]
regex: "dev"
`, true, time.Hour, false, false, `
metric{env="dev"} 10
metric{env="bar"} 20
metric{env="dev"} 15
metric{env="bar"} 25
`)
f(``, `
- action: keep
source_labels: [env]
regex: "dev"
`, true, time.Hour, true, false, `
metric{env="test"} 10
metric{env="dev"} 20
metric{env="foo"} 15
metric{env="dev"} 25
`)
f(``, `
- action: keep
source_labels: [env]
regex: "dev"
`, true, time.Hour, false, true, `
metric{env="foo"} 10
metric{env="dev"} 20
metric{env="foo"} 15
metric{env="dev"} 25
`)
f(``, `
- action: keep
source_labels: [env]
regex: "dev"
`, true, time.Hour, true, true, `
metric{env="dev"} 10
metric{env="test"} 20
metric{env="dev"} 15
metric{env="bar"} 25
`)
}
func TestShardAmountRemoteWriteCtx(t *testing.T) {
@@ -247,16 +220,16 @@ func TestShardAmountRemoteWriteCtx(t *testing.T) {
seriesCount := 100000
// build 1000000 series
tssBlock := make([]prompb.TimeSeries, 0, seriesCount)
tssBlock := make([]prompbmarshal.TimeSeries, 0, seriesCount)
for i := 0; i < seriesCount; i++ {
tssBlock = append(tssBlock, prompb.TimeSeries{
Labels: []prompb.Label{
tssBlock = append(tssBlock, prompbmarshal.TimeSeries{
Labels: []prompbmarshal.Label{
{
Name: "label",
Value: strconv.Itoa(i),
},
},
Samples: []prompb.Sample{
Samples: []prompbmarshal.Sample{
{
Timestamp: 0,
Value: 0,
@@ -285,7 +258,7 @@ func TestShardAmountRemoteWriteCtx(t *testing.T) {
for i, nodeIdx := range healthyIdx {
for _, ts := range shards[i] {
// add it to node[nodeIdx]'s active time series
activeTimeSeriesByNodes[nodeIdx][prompb.LabelsToString(ts.Labels)] = struct{}{}
activeTimeSeriesByNodes[nodeIdx][prompbmarshal.LabelsToString(ts.Labels)] = struct{}{}
}
}
@@ -308,7 +281,7 @@ func TestShardAmountRemoteWriteCtx(t *testing.T) {
for i, nodeIdx := range healthyIdx {
for _, ts := range shards[i] {
// add it to node[nodeIdx]'s active time series
activeTimeSeriesByNodes[nodeIdx][prompb.LabelsToString(ts.Labels)] = struct{}{}
activeTimeSeriesByNodes[nodeIdx][prompbmarshal.LabelsToString(ts.Labels)] = struct{}{}
}
}

View File

@@ -8,7 +8,7 @@ import (
"github.com/VictoriaMetrics/VictoriaMetrics/lib/fasttime"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/streamaggr"
"github.com/VictoriaMetrics/metrics"
)
@@ -18,12 +18,12 @@ var (
streamAggrGlobalConfig = flag.String("streamAggr.config", "", "Optional path to file with stream aggregation config. "+
"See https://docs.victoriametrics.com/victoriametrics/stream-aggregation/ . "+
"See also -streamAggr.keepInput, -streamAggr.dropInput and -streamAggr.dedupInterval")
streamAggrGlobalKeepInput = flag.Bool("streamAggr.keepInput", false, "Whether to keep input samples that match any rule in "+
"-streamAggr.config. By default, matched raw samples are aggregated and dropped, while unmatched samples "+
"are written to the remote storage. See also -streamAggr.dropInput and https://docs.victoriametrics.com/victoriametrics/stream-aggregation/")
streamAggrGlobalDropInput = flag.Bool("streamAggr.dropInput", false, "Whether to drop input samples that not matching any rule in "+
"-streamAggr.config. By default, only matched raw samples are dropped, while unmatched samples "+
"are written to the remote storage. See also -streamAggr.keepInput and https://docs.victoriametrics.com/victoriametrics/stream-aggregation/")
streamAggrGlobalKeepInput = flag.Bool("streamAggr.keepInput", false, "Whether to keep all the input samples after the aggregation "+
"with -streamAggr.config. By default, only aggregates samples are dropped, while the remaining samples "+
"are written to remote storages write. See also -streamAggr.dropInput and https://docs.victoriametrics.com/victoriametrics/stream-aggregation/")
streamAggrGlobalDropInput = flag.Bool("streamAggr.dropInput", false, "Whether to drop all the input samples after the aggregation "+
"with -remoteWrite.streamAggr.config. By default, only aggregates samples are dropped, while the remaining samples "+
"are written to remote storages write. See also -streamAggr.keepInput and https://docs.victoriametrics.com/victoriametrics/stream-aggregation/")
streamAggrGlobalDedupInterval = flag.Duration("streamAggr.dedupInterval", 0, "Input samples are de-duplicated with this interval on "+
"aggregator before optional aggregation with -streamAggr.config . "+
"See also -dedup.minScrapeInterval and https://docs.victoriametrics.com/victoriametrics/stream-aggregation/#deduplication")
@@ -43,11 +43,11 @@ var (
streamAggrConfig = flagutil.NewArrayString("remoteWrite.streamAggr.config", "Optional path to file with stream aggregation config for the corresponding -remoteWrite.url. "+
"See https://docs.victoriametrics.com/victoriametrics/stream-aggregation/ . "+
"See also -remoteWrite.streamAggr.keepInput, -remoteWrite.streamAggr.dropInput and -remoteWrite.streamAggr.dedupInterval")
streamAggrDropInput = flagutil.NewArrayBool("remoteWrite.streamAggr.dropInput", "Whether to drop input samples that not matching any rule in "+
"the corresponding -remoteWrite.streamAggr.config. By default, only matched raw samples are dropped, while unmatched samples "+
streamAggrDropInput = flagutil.NewArrayBool("remoteWrite.streamAggr.dropInput", "Whether to drop all the input samples after the aggregation "+
"with -remoteWrite.streamAggr.config at the corresponding -remoteWrite.url. By default, only aggregates samples are dropped, while the remaining samples "+
"are written to the corresponding -remoteWrite.url . See also -remoteWrite.streamAggr.keepInput and https://docs.victoriametrics.com/victoriametrics/stream-aggregation/")
streamAggrKeepInput = flagutil.NewArrayBool("remoteWrite.streamAggr.keepInput", "Whether to keep input samples that match any rule in "+
"the corresponding -remoteWrite.streamAggr.config. By default, matched raw samples are aggregated and dropped, while unmatched samples "+
streamAggrKeepInput = flagutil.NewArrayBool("remoteWrite.streamAggr.keepInput", "Whether to keep all the input samples after the aggregation "+
"with -remoteWrite.streamAggr.config at the corresponding -remoteWrite.url. By default, only aggregates samples are dropped, while the remaining samples "+
"are written to the corresponding -remoteWrite.url . See also -remoteWrite.streamAggr.dropInput and https://docs.victoriametrics.com/victoriametrics/stream-aggregation/")
streamAggrDedupInterval = flagutil.NewArrayDuration("remoteWrite.streamAggr.dedupInterval", 0, "Input samples are de-duplicated with this interval before optional aggregation "+
"with -remoteWrite.streamAggr.config at the corresponding -remoteWrite.url. See also -dedup.minScrapeInterval and https://docs.victoriametrics.com/victoriametrics/stream-aggregation/#deduplication")
@@ -80,7 +80,7 @@ func CheckStreamAggrConfigs() error {
return fmt.Errorf("too many -remoteWrite.streamAggr.config args: %d; it mustn't exceed the number of -remoteWrite.url args: %d", len(*streamAggrConfig), len(*remoteWriteURLs))
}
pushNoop := func(_ []prompb.TimeSeries) {}
pushNoop := func(_ []prompbmarshal.TimeSeries) {}
for idx := range *streamAggrConfig {
sas, err := newStreamAggrConfigPerURL(idx, pushNoop)
if err != nil {
@@ -141,7 +141,7 @@ func initStreamAggrConfigGlobal() {
}
dedupInterval := *streamAggrGlobalDedupInterval
if dedupInterval > 0 {
deduplicatorGlobal = streamaggr.NewDeduplicator(pushTimeSeriesToRemoteStoragesTrackDropped, *streamAggrGlobalEnableWindows, dedupInterval, *streamAggrGlobalDropInputLabels, "dedup-global")
deduplicatorGlobal = streamaggr.NewDeduplicator(pushToRemoteStoragesTrackDropped, *streamAggrGlobalEnableWindows, dedupInterval, *streamAggrGlobalDropInputLabels, "dedup-global")
}
}
@@ -216,7 +216,7 @@ func newStreamAggrConfigGlobal() (*streamaggr.Aggregators, error) {
EnableWindows: *streamAggrGlobalEnableWindows,
}
sas, err := streamaggr.LoadFromFile(path, pushTimeSeriesToRemoteStoragesTrackDropped, opts, "global")
sas, err := streamaggr.LoadFromFile(path, pushToRemoteStoragesTrackDropped, opts, "global")
if err != nil {
return nil, fmt.Errorf("cannot load -streamAggr.config=%q: %w", *streamAggrGlobalConfig, err)
}

View File

@@ -8,7 +8,7 @@ import (
"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/protoparserutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/vmimport"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/vmimport/stream"
@@ -36,7 +36,7 @@ func InsertHandler(at *auth.Token, req *http.Request) error {
})
}
func insertRows(at *auth.Token, rows []vmimport.Row, extraLabels []prompb.Label) error {
func insertRows(at *auth.Token, rows []vmimport.Row, extraLabels []prompbmarshal.Label) error {
ctx := common.GetPushCtx()
defer common.PutPushCtx(ctx)
@@ -50,7 +50,7 @@ func insertRows(at *auth.Token, rows []vmimport.Row, extraLabels []prompb.Label)
labelsLen := len(labels)
for j := range r.Tags {
tag := &r.Tags[j]
labels = append(labels, prompb.Label{
labels = append(labels, prompbmarshal.Label{
Name: bytesutil.ToUnsafeString(tag.Key),
Value: bytesutil.ToUnsafeString(tag.Value),
})
@@ -63,12 +63,12 @@ func insertRows(at *auth.Token, rows []vmimport.Row, extraLabels []prompb.Label)
}
samplesLen := len(samples)
for j, value := range values {
samples = append(samples, prompb.Sample{
samples = append(samples, prompbmarshal.Sample{
Value: value,
Timestamp: timestamps[j],
})
}
tssDst = append(tssDst, prompb.TimeSeries{
tssDst = append(tssDst, prompbmarshal.TimeSeries{
Labels: labels[labelsLen:],
Samples: samples[samplesLen:],
})

View File

@@ -1,80 +0,0 @@
package zabbixconnector
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/bytesutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/protoparserutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/zabbixconnector"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/zabbixconnector/stream"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
"github.com/VictoriaMetrics/metrics"
)
var (
rowsInserted = metrics.NewCounter(`vmagent_rows_inserted_total{type="zabbixconnector"}`)
rowsTenantInserted = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_rows_total{type="zabbixconnector"}`)
rowsPerInsert = metrics.NewHistogram(`vmagent_rows_per_insert{type="zabbixconnector"}`)
)
// InsertHandlerForHTTP processes remote write for ZabbixConnector POST /zabbixconnector/v1/history request.
func InsertHandlerForHTTP(at *auth.Token, req *http.Request) error {
extraLabels, err := protoparserutil.GetExtraLabels(req)
if err != nil {
return err
}
encoding := req.Header.Get("Content-Encoding")
return stream.Parse(req.Body, encoding, func(rows []zabbixconnector.Row) error {
return insertRows(at, rows, extraLabels)
})
}
func insertRows(at *auth.Token, rows []zabbixconnector.Row, extraLabels []prompb.Label) error {
ctx := common.GetPushCtx()
defer common.PutPushCtx(ctx)
rowsTotal := len(rows)
tssDst := ctx.WriteRequest.Timeseries[:0]
labels := ctx.Labels[:0]
samples := ctx.Samples[:0]
for i := range rows {
r := &rows[i]
labelsLen := len(labels)
for j := range r.Tags {
tag := &r.Tags[j]
labels = append(labels, prompb.Label{
Name: bytesutil.ToUnsafeString(tag.Key),
Value: bytesutil.ToUnsafeString(tag.Value),
})
}
labels = append(labels, extraLabels...)
samplesLen := len(samples)
samples = append(samples, prompb.Sample{
Value: r.Value,
Timestamp: r.Timestamp,
})
tssDst = append(tssDst, prompb.TimeSeries{
Labels: labels[labelsLen:],
Samples: samples[samplesLen:],
})
}
ctx.WriteRequest.Timeseries = tssDst
ctx.Labels = labels
ctx.Samples = samples
if !remotewrite.TryPush(at, &ctx.WriteRequest) {
return remotewrite.ErrQueueFullHTTPRetry
}
rowsInserted.Add(rowsTotal)
if at != nil {
rowsTenantInserted.Get(at).Add(rowsTotal)
}
rowsPerInsert.Update(float64(rowsTotal))
return nil
}

View File

@@ -27,9 +27,6 @@ vmalert-tool-linux-ppc64le-prod:
vmalert-tool-linux-386-prod:
APP_NAME=vmalert-tool $(MAKE) app-via-docker-linux-386
vmalert-tool-linux-s390x-prod:
APP_NAME=vmalert-tool $(MAKE) app-via-docker-linux-s390x
vmalert-tool-darwin-amd64-prod:
APP_NAME=vmalert-tool $(MAKE) app-via-docker-darwin-amd64

View File

@@ -9,7 +9,7 @@ import (
"time"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promutil"
"github.com/VictoriaMetrics/metricsql"
)
@@ -49,7 +49,7 @@ Outer:
}
var expSamples []parsedSample
for _, s := range mt.ExpSamples {
expLb := []prompb.Label{}
expLb := []prompbmarshal.Label{}
if s.Labels != "" {
metricsqlExpr, err := metricsql.Parse(s.Labels)
if err != nil {
@@ -65,7 +65,7 @@ Outer:
}
if len(metricsqlMetricExpr.LabelFilterss) > 0 {
for _, l := range metricsqlMetricExpr.LabelFilterss[0] {
expLb = append(expLb, prompb.Label{
expLb = append(expLb, prompbmarshal.Label{
Name: l.Label,
Value: l.Value,
})

View File

@@ -15,10 +15,6 @@ groups:
- alert: SameAlertNameWithDifferentGroup
expr: absent(test)
for: 1m
- alert: AlertWithTemplate
expr: test
annotations:
queryAnno: '{{ query "foo" | first | value }}'
- name: group2
rules:

View File

@@ -10,9 +10,7 @@ tests:
input_series:
- series: "test"
values: "_x5 1x5 _ stale"
- series: "foo"
values: "1x20"
alert_rule_test:
- eval_time: 1m
groupname: group1
@@ -34,14 +32,6 @@ tests:
groupname: group1
alertname: SameAlertNameWithDifferentGroup
exp_alerts: []
- eval_time: 6m
groupname: group1
alertname: AlertWithTemplate
exp_alerts:
- exp_labels:
cluster: prod
exp_annotations:
queryAnno: '1'
metricsql_expr_test:
- expr: test
@@ -60,8 +50,6 @@ tests:
values: "0+0x1440"
- series: "test"
values: "0+1x1440"
- series: "foo"
values: "1x20"
metricsql_expr_test:
- expr: count(ALERTS) by (alertgroup, alertname, alertstate)
@@ -71,8 +59,6 @@ tests:
value: 1
- labels: '{alertgroup="group1", alertname="InstanceDown", alertstate="pending"}'
value: 1
- labels: '{alertgroup="group1", alertname="AlertWithTemplate", alertstate="firing"}'
value: 1
- expr: t1
eval_time: 4m
exp_samples:

View File

@@ -19,6 +19,7 @@ import (
"gopkg.in/yaml.v2"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/config"
vmalertconfig "github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/config"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
@@ -34,7 +35,6 @@ import (
"github.com/VictoriaMetrics/VictoriaMetrics/lib/fs"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/netutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promutil"
"github.com/VictoriaMetrics/metrics"
)
@@ -85,8 +85,7 @@ func UnitTest(files []string, disableGroupLabel bool, externalLabels []string, e
defer server.Close()
} else {
httpListenAddr = httpListenPort
ln, err := net.Listen(netutil.GetTCPNetwork(), fmt.Sprintf(":%s", httpListenPort))
ln, err := net.Listen("tcp", fmt.Sprintf(":%s", httpListenPort))
if err != nil {
logger.Fatalf("cannot listen on port %s: %v", httpListenPort, err)
}
@@ -108,12 +107,12 @@ func UnitTest(files []string, disableGroupLabel bool, externalLabels []string, e
vminsert.Init()
vmselect.Init()
// storagePath will be created again when closing vmselect, so remove it again.
defer fs.MustRemoveDir(storagePath)
defer fs.MustRemoveAll(storagePath)
defer vminsert.Stop()
defer vmselect.Stop()
disableAlertgroupLabel = disableGroupLabel
testfiles, err := vmalertconfig.ReadFromFS(files)
testfiles, err := config.ReadFromFS(files)
if err != nil {
logger.Fatalf("failed to load test files %q: %v", files, err)
}
@@ -132,7 +131,7 @@ func UnitTest(files []string, disableGroupLabel bool, externalLabels []string, e
}
labels[s[:n]] = s[n+1:]
}
err = notifier.Init(labels, externalURL)
_, err = notifier.Init(nil, labels, externalURL)
if err != nil {
logger.Fatalf("failed to init notifier: %v", err)
}
@@ -305,7 +304,7 @@ checkCheck:
func tearDown() {
vmstorage.Stop()
metrics.UnregisterAllMetrics()
fs.MustRemoveDir(storagePath)
fs.MustRemoveAll(storagePath)
}
func (tg *testGroup) test(evalInterval time.Duration, groupOrderMap map[string]int, testGroups []vmalertconfig.Group, externalLabels map[string]string) (checkErrs []error) {
@@ -368,7 +367,6 @@ func (tg *testGroup) test(evalInterval time.Duration, groupOrderMap map[string]i
mergedExternalLabels[k] = v
}
ng := rule.NewGroup(group, q, time.Minute, mergedExternalLabels)
ng.Init()
groups = append(groups, ng)
}
@@ -379,7 +377,7 @@ func (tg *testGroup) test(evalInterval time.Duration, groupOrderMap map[string]i
if len(g.Rules) == 0 {
continue
}
errs := g.ExecOnce(context.Background(), rw, ts)
errs := g.ExecOnce(context.Background(), func() []notifier.Notifier { return nil }, rw, ts)
for err := range errs {
if err != nil {
checkErrs = append(checkErrs, fmt.Errorf("\nfailed to exec group: %q, time: %s, err: %w", g.Name,

View File

@@ -27,9 +27,6 @@ vmalert-linux-ppc64le-prod:
vmalert-linux-386-prod:
APP_NAME=vmalert $(MAKE) app-via-docker-linux-386
vmalert-linux-s390x-prod:
APP_NAME=vmalert $(MAKE) app-via-docker-linux-s390x
vmalert-darwin-amd64-prod:
APP_NAME=vmalert $(MAKE) app-via-docker-darwin-amd64

View File

@@ -31,7 +31,7 @@ type Group struct {
// EvalDelay will adjust the `time` parameter of rule evaluation requests to compensate intentional query delay from datasource.
// see https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5155
EvalDelay *promutil.Duration `yaml:"eval_delay,omitempty"`
Limit *int `yaml:"limit,omitempty"`
Limit int `yaml:"limit,omitempty"`
Rules []Rule `yaml:"rules"`
Concurrency int `yaml:"concurrency"`
// Labels is a set of label value pairs, that will be added to every rule.
@@ -91,8 +91,8 @@ func (g *Group) Validate(validateTplFn ValidateTplFn, validateExpressions bool)
if g.EvalOffset != nil && g.EvalDelay != nil {
return fmt.Errorf("eval_offset cannot be used with eval_delay")
}
if g.Limit != nil && *g.Limit < 0 {
return fmt.Errorf("invalid limit %d, shouldn't be less than 0", *g.Limit)
if g.Limit < 0 {
return fmt.Errorf("invalid limit %d, shouldn't be less than 0", g.Limit)
}
if g.Concurrency < 0 {
return fmt.Errorf("invalid concurrency %d, shouldn't be less than 0", g.Concurrency)
@@ -295,7 +295,10 @@ func parse(files map[string][]byte, validateTplFn ValidateTplFn, validateExpress
}
func parseConfig(data []byte) ([]Group, error) {
data = envtemplate.ReplaceBytes(data)
data, err := envtemplate.ReplaceBytes(data)
if err != nil {
return nil, fmt.Errorf("cannot expand environment vars: %w", err)
}
var result []Group
type cfgFile struct {
@@ -307,13 +310,13 @@ func parseConfig(data []byte) ([]Group, error) {
decoder := yaml.NewDecoder(bytes.NewReader(data))
for {
var cf cfgFile
if err := decoder.Decode(&cf); err != nil {
if err = decoder.Decode(&cf); err != nil {
if err == io.EOF { // EOF indicates no more documents to read
break
}
return nil, err
}
if err := checkOverflow(cf.XXX, "config"); err != nil {
if err = checkOverflow(cf.XXX, "config"); err != nil {
return nil, err
}
result = append(result, cf.Groups...)

View File

@@ -116,7 +116,7 @@ func TestParse_Failure(t *testing.T) {
f([]string{"testdata/rules/rules_interval_bad.rules"}, "eval_offset should be smaller than interval")
f([]string{"testdata/rules/rules0-bad.rules"}, "unexpected token")
f([]string{"testdata/dir/rules0-bad.rules"}, "invalid annotations")
f([]string{"testdata/dir/rules0-bad.rules"}, "error parsing annotation")
f([]string{"testdata/dir/rules1-bad.rules"}, "duplicate in file")
f([]string{"testdata/dir/rules2-bad.rules"}, "function \"unknown\" not defined")
f([]string{"testdata/dir/rules3-bad.rules"}, "either `record` or `alert` must be set")
@@ -181,10 +181,9 @@ func TestGroupValidate_Failure(t *testing.T) {
EvalOffset: promutil.NewDuration(2 * time.Minute),
}, false, "eval_offset should be smaller than interval")
limit := -1
f(&Group{
Name: "wrong limit",
Limit: &limit,
Limit: -1,
}, false, "invalid limit")
f(&Group{
@@ -343,6 +342,7 @@ func TestGroupValidate_Failure(t *testing.T) {
},
},
}, true, "bad prometheus expr")
}
func TestGroupValidate_Success(t *testing.T) {

View File

@@ -173,26 +173,22 @@ func (c *Client) Query(ctx context.Context, query string, ts time.Time) (Result,
return Result{}, nil, fmt.Errorf("second attempt: %w", err)
}
}
defer func() { _ = resp.Body.Close() }()
// Process the received response.
var parseFn func(resp *http.Response) (Result, error)
var parseFn func(req *http.Request, resp *http.Response) (Result, error)
switch c.dataSourceType {
case datasourcePrometheus:
parseFn = parsePrometheusInstantResponse
parseFn = parsePrometheusResponse
case datasourceGraphite:
parseFn = parseGraphiteResponse
case datasourceVLogs:
parseFn = parseVLogsInstantResponse
parseFn = parseVLogsResponse
default:
logger.Panicf("BUG: unsupported datasource type %q to parse query response", c.dataSourceType)
}
result, err := parseFn(resp)
if err != nil {
return Result{}, nil, fmt.Errorf("error parsing response from %q: %w", req.URL.Redacted(), err)
}
return result, req, nil
result, err := parseFn(req, resp)
_ = resp.Body.Close()
return result, req, err
}
// QueryRange executes the given query on the given time range.
@@ -233,23 +229,19 @@ func (c *Client) QueryRange(ctx context.Context, query string, start, end time.T
return res, fmt.Errorf("second attempt: %w", err)
}
}
defer func() { _ = resp.Body.Close() }()
// Process the received response.
var parseFn func(resp *http.Response) (Result, error)
var parseFn func(req *http.Request, resp *http.Response) (Result, error)
switch c.dataSourceType {
case datasourcePrometheus:
parseFn = parsePrometheusRangeResponse
parseFn = parsePrometheusResponse
case datasourceVLogs:
parseFn = parseVLogsRangeResponse
parseFn = parseVLogsResponse
default:
logger.Panicf("BUG: unsupported datasource type %q to parse query range response", c.dataSourceType)
}
res, err = parseFn(resp)
if err != nil {
return Result{}, fmt.Errorf("error parsing response from %q: %w", req.URL.Redacted(), err)
}
res, err = parseFn(req, resp)
_ = resp.Body.Close()
return res, err
}

View File

@@ -33,10 +33,10 @@ func (r graphiteResponse) metrics() []Metric {
return ms
}
func parseGraphiteResponse(resp *http.Response) (Result, error) {
func parseGraphiteResponse(req *http.Request, resp *http.Response) (Result, error) {
r := &graphiteResponse{}
if err := json.NewDecoder(resp.Body).Decode(r); err != nil {
return Result{}, fmt.Errorf("error parsing graphite metrics: %w", err)
return Result{}, fmt.Errorf("error parsing graphite metrics for %s: %w", req.URL.Redacted(), err)
}
return Result{Data: r.metrics()}, nil
}

View File

@@ -9,7 +9,7 @@ import (
"time"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
"github.com/valyala/fastjson"
)
@@ -85,14 +85,14 @@ func (pi *promInstant) Unmarshal(b []byte) error {
labels := metric.GetObject()
r := &pi.ms[i]
r.Labels = make([]prompb.Label, 0, labels.Len())
r.Labels = make([]prompbmarshal.Label, 0, labels.Len())
labels.Visit(func(key []byte, v *fastjson.Value) {
lv, errLocal := v.StringBytes()
if errLocal != nil {
err = fmt.Errorf("error when parsing label value %q: %s", v, errLocal)
return
}
r.Labels = append(r.Labels, prompb.Label{
r.Labels = append(r.Labels, prompbmarshal.Label{
Name: string(key),
Value: string(lv),
})
@@ -172,26 +172,17 @@ const (
rtVector, rtMatrix, rScalar = "vector", "matrix", "scalar"
)
func parsePromResponse(resp *http.Response) (*promResponse, error) {
func parsePrometheusResponse(req *http.Request, resp *http.Response) (res Result, err error) {
r := &promResponse{}
if err := json.NewDecoder(resp.Body).Decode(r); err != nil {
return nil, fmt.Errorf("failed to decode response: %w", err)
if err = json.NewDecoder(resp.Body).Decode(r); err != nil {
return res, fmt.Errorf("error parsing response from %s: %w", req.URL.Redacted(), err)
}
if r.Status == statusError {
return nil, fmt.Errorf("response error %q: %s", r.ErrorType, r.Error)
return res, fmt.Errorf("response error, query: %s, errorType: %s, error: %s", req.URL.Redacted(), r.ErrorType, r.Error)
}
if r.Status != statusSuccess {
return nil, fmt.Errorf("unknown response status %q", r.Status)
return res, fmt.Errorf("unknown status: %s, Expected success or error", r.Status)
}
return r, nil
}
func parsePrometheusInstantResponse(resp *http.Response) (res Result, err error) {
r, err := parsePromResponse(resp)
if err != nil {
return res, fmt.Errorf("failed to parse response: %w", err)
}
var parseFn func() ([]Metric, error)
switch r.Data.ResultType {
case rtVector:
@@ -200,6 +191,12 @@ func parsePrometheusInstantResponse(resp *http.Response) (res Result, err error)
return res, fmt.Errorf("unmarshal err %w; \n %#v", err, string(r.Data.Result))
}
parseFn = pi.metrics
case rtMatrix:
var pr promRange
if err := json.Unmarshal(r.Data.Result, &pr.Result); err != nil {
return res, err
}
parseFn = pr.metrics
case rScalar:
var ps promScalar
if err := json.Unmarshal(r.Data.Result, &ps); err != nil {
@@ -209,6 +206,7 @@ func parsePrometheusInstantResponse(resp *http.Response) (res Result, err error)
default:
return res, fmt.Errorf("unknown result type %q", r.Data.ResultType)
}
ms, err := parseFn()
if err != nil {
return res, err
@@ -224,34 +222,6 @@ func parsePrometheusInstantResponse(resp *http.Response) (res Result, err error)
return res, nil
}
func parsePrometheusRangeResponse(resp *http.Response) (res Result, err error) {
r, err := parsePromResponse(resp)
if err != nil {
return res, fmt.Errorf("failed to parse response: %w", err)
}
if r.Data.ResultType != rtMatrix {
return res, fmt.Errorf("unexpected result type %q; expected result type %q", r.Data.ResultType, rtMatrix)
}
var pr promRange
if err := json.Unmarshal(r.Data.Result, &pr.Result); err != nil {
return res, err
}
ms, err := pr.metrics()
if err != nil {
return res, err
}
res = Result{Data: ms, IsPartial: r.IsPartial}
if r.Stats.SeriesFetched != nil {
intV, err := strconv.Atoi(*r.Stats.SeriesFetched)
if err != nil {
return res, fmt.Errorf("failed to convert stats.seriesFetched to int: %w", err)
}
res.SeriesFetched = &intV
}
return res, nil
}
func (c *Client) setPrometheusInstantReqParams(r *http.Request, query string, timestamp time.Time) {
if c.appendTypePrefix {
r.URL.Path += "/prometheus"

View File

@@ -14,7 +14,7 @@ import (
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/vmalertutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promauth"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
)
var (
@@ -65,23 +65,21 @@ func TestVMInstantQuery(t *testing.T) {
case 3:
w.Write([]byte(`{"status":"unknown"}`))
case 4:
w.Write([]byte(`{"status":"success","data":{"resultType":"vector"}}`))
w.Write([]byte(`{"status":"success","data":{"resultType":"matrix"}}`))
case 5:
w.Write([]byte(`{"status":"success","data":{"resultType":"matrix","result":[{"metric":{"__name__":"vm_rows"},"values":[[1583786142,"13763"]]}]}}`))
case 6:
w.Write([]byte(`{"status":"success","data":{"resultType":"vector","result":[{"metric":{"__name__":"vm_rows","foo":"bar"},"value":[1583786142,"13763"]},{"metric":{"__name__":"vm_requests","foo":"baz"},"value":[1583786140,"2000"]}]}}`))
case 7:
case 6:
w.Write([]byte(`{"status":"success","data":{"resultType":"scalar","result":[1583786142, "1"]}}`))
case 8:
case 7:
w.Write([]byte(`{"status":"success","data":{"resultType":"scalar","result":[1583786142, "1"]},"stats":{"seriesFetched": "42"}}`))
case 9:
case 8:
w.Write([]byte(`{"status":"success", "isPartial":true, "data":{"resultType":"scalar","result":[1583786142, "1"]}}`))
}
})
mux.HandleFunc("/render", func(w http.ResponseWriter, _ *http.Request) {
c++
switch c {
case 10:
case 9:
w.Write([]byte(`[{"target":"constantLine(10)","tags":{"name":"constantLine(10)"},"datapoints":[[10,1611758343],[10,1611758373],[10,1611758403]]}]`))
}
})
@@ -104,9 +102,9 @@ func TestVMInstantQuery(t *testing.T) {
t.Fatalf("failed to parse 'time' query param %q: %s", timeParam, err)
}
switch c {
case 11:
case 10:
w.Write([]byte("[]"))
case 12:
case 11:
w.Write([]byte(`{"status":"success","data":{"resultType":"vector","result":[{"metric":{"__name__":"total","foo":"bar"},"value":[1583786142,"13763"]},{"metric":{"__name__":"total","foo":"baz"},"value":[1583786140,"2000"]}]}}`))
}
})
@@ -125,7 +123,6 @@ func TestVMInstantQuery(t *testing.T) {
ts := time.Now()
expErr := func(query, err string) {
t.Helper()
_, _, gotErr := pq.Query(ctx, query, ts)
if gotErr == nil {
t.Fatalf("expected %q got nil", err)
@@ -138,11 +135,10 @@ func TestVMInstantQuery(t *testing.T) {
expErr(vmQuery, "500") // 0
expErr(vmQuery, "error parsing response") // 1
expErr(vmQuery, "response error") // 2
expErr(vmQuery, "unknown response status") // 3
expErr(vmQuery, "unknown status") // 3
expErr(vmQuery, "unexpected end of JSON input") // 4
expErr(vmQuery, "unknown result type") // 5
res, _, err := pq.Query(ctx, vmQuery, ts) // 6 - vector
res, _, err := pq.Query(ctx, vmQuery, ts) // 5 - vector
if err != nil {
t.Fatalf("unexpected %s", err)
}
@@ -151,19 +147,19 @@ func TestVMInstantQuery(t *testing.T) {
}
expected := []Metric{
{
Labels: []prompb.Label{{Value: "vm_rows", Name: "__name__"}, {Value: "bar", Name: "foo"}},
Labels: []prompbmarshal.Label{{Value: "vm_rows", Name: "__name__"}, {Value: "bar", Name: "foo"}},
Timestamps: []int64{1583786142},
Values: []float64{13763},
},
{
Labels: []prompb.Label{{Value: "vm_requests", Name: "__name__"}, {Value: "baz", Name: "foo"}},
Labels: []prompbmarshal.Label{{Value: "vm_requests", Name: "__name__"}, {Value: "baz", Name: "foo"}},
Timestamps: []int64{1583786140},
Values: []float64{2000},
},
}
metricsEqual(t, res.Data, expected)
res, req, err := pq.Query(ctx, vmQuery, ts) // 7 - scalar
res, req, err := pq.Query(ctx, vmQuery, ts) // 6 - scalar
if err != nil {
t.Fatalf("unexpected %s", err)
}
@@ -188,7 +184,7 @@ func TestVMInstantQuery(t *testing.T) {
res.SeriesFetched)
}
res, _, err = pq.Query(ctx, vmQuery, ts) // 8 - scalar with stats
res, _, err = pq.Query(ctx, vmQuery, ts) // 7 - scalar with stats
if err != nil {
t.Fatalf("unexpected %s", err)
}
@@ -209,7 +205,7 @@ func TestVMInstantQuery(t *testing.T) {
*res.SeriesFetched)
}
res, _, err = pq.Query(ctx, vmQuery, ts) // 9
res, _, err = pq.Query(ctx, vmQuery, ts) // 8
if err != nil {
t.Fatalf("unexpected %s", err)
}
@@ -220,7 +216,7 @@ func TestVMInstantQuery(t *testing.T) {
// test graphite
gq := s.BuildWithParams(QuerierParams{DataSourceType: string(datasourceGraphite)})
res, _, err = gq.Query(ctx, queryRender, ts) // 10 - graphite
res, _, err = gq.Query(ctx, queryRender, ts) // 9 - graphite
if err != nil {
t.Fatalf("unexpected %s", err)
}
@@ -229,7 +225,7 @@ func TestVMInstantQuery(t *testing.T) {
}
exp := []Metric{
{
Labels: []prompb.Label{{Value: "constantLine(10)", Name: "name"}},
Labels: []prompbmarshal.Label{{Value: "constantLine(10)", Name: "name"}},
Timestamps: []int64{1611758403},
Values: []float64{10},
},
@@ -240,9 +236,9 @@ func TestVMInstantQuery(t *testing.T) {
vlogs := datasourceVLogs
pq = s.BuildWithParams(QuerierParams{DataSourceType: string(vlogs), EvaluationInterval: 15 * time.Second})
expErr(vlogsQuery, "error parsing response") // 11
expErr(vlogsQuery, "error parsing response") // 10
res, _, err = pq.Query(ctx, vlogsQuery, ts) // 12
res, _, err = pq.Query(ctx, vlogsQuery, ts) // 11
if err != nil {
t.Fatalf("unexpected %s", err)
}
@@ -251,12 +247,12 @@ func TestVMInstantQuery(t *testing.T) {
}
expected = []Metric{
{
Labels: []prompb.Label{{Value: "total", Name: "stats_result"}, {Value: "bar", Name: "foo"}},
Labels: []prompbmarshal.Label{{Value: "total", Name: "stats_result"}, {Value: "bar", Name: "foo"}},
Timestamps: []int64{1583786142},
Values: []float64{13763},
},
{
Labels: []prompb.Label{{Value: "total", Name: "stats_result"}, {Value: "baz", Name: "foo"}},
Labels: []prompbmarshal.Label{{Value: "total", Name: "stats_result"}, {Value: "baz", Name: "foo"}},
Timestamps: []int64{1583786140},
Values: []float64{2000},
},
@@ -394,8 +390,6 @@ func TestVMRangeQuery(t *testing.T) {
switch c {
case 0:
w.Write([]byte(`{"status":"success","data":{"resultType":"matrix","result":[{"metric":{"__name__":"vm_rows"},"values":[[1583786142,"13763"]]}]}}`))
case 1:
w.Write([]byte(`{"status":"success","data":{"resultType":"vector","result":[1583786142, "1"]}}`))
}
})
mux.HandleFunc("/select/logsql/stats_query_range", func(w http.ResponseWriter, r *http.Request) {
@@ -428,7 +422,7 @@ func TestVMRangeQuery(t *testing.T) {
t.Fatalf("expected 'step' query param to be 60s; got %q instead", step)
}
switch c {
case 2:
case 1:
w.Write([]byte(`{"status":"success","data":{"resultType":"matrix","result":[{"metric":{"__name__":"total"},"values":[[1583786142,"10"]]}]}}`))
}
})
@@ -452,16 +446,16 @@ func TestVMRangeQuery(t *testing.T) {
start, end := time.Now().Add(-time.Minute), time.Now()
res, err := pq.QueryRange(ctx, vmQuery, start, end) // case 0
res, err := pq.QueryRange(ctx, vmQuery, start, end)
if err != nil {
t.Fatalf("unexpected %s", err)
}
m := res.Data
if len(m) != 1 {
t.Fatalf("expected 1 metric got %d in %+v", len(m), m)
t.Fatalf("expected 1 metric got %d in %+v", len(m), m)
}
expected := Metric{
Labels: []prompb.Label{{Value: "vm_rows", Name: "__name__"}},
Labels: []prompbmarshal.Label{{Value: "vm_rows", Name: "__name__"}},
Timestamps: []int64{1583786142},
Values: []float64{13763},
}
@@ -469,9 +463,6 @@ func TestVMRangeQuery(t *testing.T) {
t.Fatalf("unexpected metric %+v want %+v", m[0], expected)
}
_, err = pq.QueryRange(ctx, vmQuery, start, end) // case 1
expectError(t, err, "unexpected result type")
// test unsupported graphite
gq := s.BuildWithParams(QuerierParams{DataSourceType: string(datasourceGraphite)})
@@ -495,7 +486,7 @@ func TestVMRangeQuery(t *testing.T) {
t.Fatalf("expected 1 metric got %d in %+v", len(m), m)
}
expected = Metric{
Labels: []prompb.Label{{Value: "total", Name: "stats_result"}},
Labels: []prompbmarshal.Label{{Value: "total", Name: "stats_result"}},
Timestamps: []int64{1583786142},
Values: []float64{10},
}

View File

@@ -40,28 +40,8 @@ func (c *Client) setVLogsRangeReqParams(r *http.Request, query string, start, en
c.setReqParams(r, query)
}
func parseVLogsInstantResponse(resp *http.Response) (res Result, err error) {
res, err = parsePrometheusInstantResponse(resp)
if err != nil {
return Result{}, err
}
for i := range res.Data {
m := &res.Data[i]
for j := range m.Labels {
// reserve the stats func result name with a new label `stats_result` instead of dropping it,
// since there could be multiple stats results in a single query, for instance:
// _time:5m | stats quantile(0.5, request_duration_seconds) p50, quantile(0.9, request_duration_seconds) p90
if m.Labels[j].Name == "__name__" {
m.Labels[j].Name = "stats_result"
break
}
}
}
return
}
func parseVLogsRangeResponse(resp *http.Response) (res Result, err error) {
res, err = parsePrometheusRangeResponse(resp)
func parseVLogsResponse(req *http.Request, resp *http.Response) (res Result, err error) {
res, err = parsePrometheusResponse(req, resp)
if err != nil {
return Result{}, err
}

View File

@@ -9,7 +9,7 @@ import (
"strconv"
"time"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
)
// Querier interface wraps Query and QueryRange methods
@@ -60,7 +60,7 @@ type QuerierParams struct {
// Metric is the basic entity which should be return by datasource
type Metric struct {
Labels []prompb.Label
Labels []prompbmarshal.Label
Timestamps []int64
Values []float64
}
@@ -79,7 +79,7 @@ func (m *Metric) SetLabel(key, value string) {
// AddLabel appends the given label to the label set
func (m *Metric) AddLabel(key, value string) {
m.Labels = append(m.Labels, prompb.Label{Name: key, Value: value})
m.Labels = append(m.Labels, prompbmarshal.Label{Name: key, Value: value})
}
// DelLabel deletes the given label from the label set
@@ -103,7 +103,7 @@ func (m *Metric) Label(key string) string {
}
// Labels is collection of Label
type Labels []prompb.Label
type Labels []prompbmarshal.Label
func (ls Labels) Len() int { return len(ls) }
func (ls Labels) Swap(i, j int) { ls[i], ls[j] = ls[j], ls[i] }
@@ -132,7 +132,10 @@ func (ls Labels) String() string {
// a=[]Label{{Name: "a", Value: "2"}},b=[]Label{{Name: "a", Value: "1"}}, return 1
// a=[]Label{{Name: "a", Value: "1"}},b=[]Label{{Name: "a", Value: "1"}}, return 0
func LabelCompare(a, b Labels) int {
l := min(len(b), len(a))
l := len(a)
if len(b) < l {
l = len(b)
}
for i := 0; i < l; i++ {
if a[i].Name != b[i].Name {
@@ -155,7 +158,7 @@ func LabelCompare(a, b Labels) int {
// ConvertToLabels convert map to Labels
func ConvertToLabels(m map[string]string) (labelset Labels) {
for k, v := range m {
labelset = append(labelset, prompb.Label{
labelset = append(labelset, prompbmarshal.Label{
Name: k,
Value: v,
})

View File

@@ -4,7 +4,7 @@ import (
"reflect"
"testing"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
)
func TestPromInstant_UnmarshalPositive(t *testing.T) {
@@ -23,7 +23,7 @@ func TestPromInstant_UnmarshalPositive(t *testing.T) {
f(`[{"metric":{"__name__":"up"},"value":[1583780000,"42"]}]`, []Metric{
{
Labels: []prompb.Label{{Name: "__name__", Value: "up"}},
Labels: []prompbmarshal.Label{{Name: "__name__", Value: "up"}},
Timestamps: []int64{1583780000},
Values: []float64{42},
},
@@ -33,17 +33,17 @@ func TestPromInstant_UnmarshalPositive(t *testing.T) {
{"metric":{"__name__":"foo"},"value":[1583780001,"7"]},
{"metric":{"__name__":"baz", "instance":"bar"},"value":[1583780002,"8"]}]`, []Metric{
{
Labels: []prompb.Label{{Name: "__name__", Value: "up"}},
Labels: []prompbmarshal.Label{{Name: "__name__", Value: "up"}},
Timestamps: []int64{1583780000},
Values: []float64{42},
},
{
Labels: []prompb.Label{{Name: "__name__", Value: "foo"}},
Labels: []prompbmarshal.Label{{Name: "__name__", Value: "foo"}},
Timestamps: []int64{1583780001},
Values: []float64{7},
},
{
Labels: []prompb.Label{{Name: "__name__", Value: "baz"}, {Name: "instance", Value: "bar"}},
Labels: []prompbmarshal.Label{{Name: "__name__", Value: "baz"}, {Name: "instance", Value: "bar"}},
Timestamps: []int64{1583780002},
Values: []float64{8},
},

View File

@@ -7,6 +7,7 @@ import (
"net/url"
"os"
"sort"
"strconv"
"strings"
"sync"
"time"
@@ -76,13 +77,14 @@ absolute path to all .tpl files in root.
`Link to VMUI: -external.alert.source='vmui/#/?g0.expr={{.Expr|queryEscape}}'. `+
`If empty 'vmalert/alert?group_id={{.GroupID}}&alert_id={{.AlertID}}' is used.`)
externalLabels = flagutil.NewArrayString("external.label", "Optional label in the form 'Name=value' to add to all generated recording rules and alerts. "+
"In case of conflicts, original labels are kept with prefix 'exported_'.")
"In case of conflicts, original labels are kept with prefix `exported_`.")
dryRun = flag.Bool("dryRun", false, "Whether to check only config files without running vmalert. The rules file are validated. The -rule flag must be specified.")
)
var (
extURL *url.URL
alertURLGeneratorFn notifier.AlertURLGenerator
extURL *url.URL
)
func main() {
@@ -119,7 +121,7 @@ func main() {
return
}
err = notifier.InitAlertURLGeneratorFn(extURL, *externalAlertSource, *validateTemplates)
alertURLGeneratorFn, err = getAlertURLGenerator(extURL, *externalAlertSource, *validateTemplates)
if err != nil {
logger.Fatalf("failed to init `external.alert.source`: %s", err)
}
@@ -226,13 +228,14 @@ func newManager(ctx context.Context) (*manager, error) {
labels[s[:n]] = s[n+1:]
}
err = notifier.Init(labels, *externalURL)
nts, err := notifier.Init(alertURLGeneratorFn, labels, *externalURL)
if err != nil {
return nil, fmt.Errorf("failed to init notifier: %w", err)
}
manager := &manager{
groups: make(map[uint64]*rule.Group),
querierBuilder: q,
notifiers: nts,
labels: labels,
}
rw, err := remotewrite.Init(ctx)
@@ -289,6 +292,35 @@ func getHostnameAsExternalURL(addr string, isSecure bool) (*url.URL, error) {
return url.Parse(fmt.Sprintf("%s%s%s", schema, hname, port))
}
func getAlertURLGenerator(externalURL *url.URL, externalAlertSource string, validateTemplate bool) (notifier.AlertURLGenerator, error) {
if externalAlertSource == "" {
return func(a notifier.Alert) string {
gID, aID := strconv.FormatUint(a.GroupID, 10), strconv.FormatUint(a.ID, 10)
return fmt.Sprintf("%s/vmalert/alert?%s=%s&%s=%s", externalURL, paramGroupID, gID, paramAlertID, aID)
}, nil
}
if validateTemplate {
if err := notifier.ValidateTemplates(map[string]string{
"tpl": externalAlertSource,
}); err != nil {
return nil, fmt.Errorf("error validating source template %s: %w", externalAlertSource, err)
}
}
m := map[string]string{
"tpl": externalAlertSource,
}
return func(alert notifier.Alert) string {
qFn := func(_ string) ([]datasource.Metric, error) {
return nil, fmt.Errorf("`query` template isn't supported for alert source template")
}
templated, err := alert.ExecTemplate(qFn, alert.Labels, m)
if err != nil {
logger.Errorf("cannot template alert source: %s", err)
}
return fmt.Sprintf("%s/%s", externalURL, templated["tpl"])
}, nil
}
func usage() {
const s = `
vmalert processes alerts and recording rules.

View File

@@ -12,7 +12,6 @@ import (
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/remotewrite"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/rule"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/fs"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/procutil"
)
@@ -49,6 +48,30 @@ func TestGetExternalURL(t *testing.T) {
}
}
func TestGetAlertURLGenerator(t *testing.T) {
testAlert := notifier.Alert{GroupID: 42, ID: 2, Value: 4, Labels: map[string]string{"tenant": "baz"}}
u, _ := url.Parse("https://victoriametrics.com/path")
fn, err := getAlertURLGenerator(u, "", false)
if err != nil {
t.Fatalf("unexpected error %s", err)
}
exp := fmt.Sprintf("https://victoriametrics.com/path/vmalert/alert?%s=42&%s=2", paramGroupID, paramAlertID)
if exp != fn(testAlert) {
t.Fatalf("unexpected url want %s, got %s", exp, fn(testAlert))
}
_, err = getAlertURLGenerator(nil, "foo?{{invalid}}", true)
if err == nil {
t.Fatalf("expected template validation error got nil")
}
fn, err = getAlertURLGenerator(u, "foo?query={{$value}}&ds={{ $labels.tenant }}", true)
if err != nil {
t.Fatalf("unexpected error %s", err)
}
if exp := "https://victoriametrics.com/path/foo?query=4&ds=baz"; exp != fn(testAlert) {
t.Fatalf("unexpected url want %s, got %s", exp, fn(testAlert))
}
}
func TestConfigReload(t *testing.T) {
originalRulePath := *rulePath
originalExternalURL := extURL
@@ -85,8 +108,8 @@ groups:
if err != nil {
t.Fatal(err)
}
defer fs.MustRemovePath(f.Name())
writeToFile(f.Name(), rules1)
defer func() { _ = os.Remove(f.Name()) }()
writeToFile(t, f.Name(), rules1)
*configCheckInterval = 200 * time.Millisecond
*rulePath = []string{f.Name()}
@@ -96,10 +119,9 @@ groups:
querierBuilder: &datasource.FakeQuerier{},
groups: make(map[uint64]*rule.Group),
labels: map[string]string{},
notifiers: func() []notifier.Notifier { return []notifier.Notifier{&notifier.FakeNotifier{}} },
rw: &remotewrite.Client{},
}
_, cleanup := notifier.InitFakeNotifier()
defer cleanup()
syncCh := make(chan struct{})
sighupCh := procutil.NewSighupChan()
@@ -142,7 +164,7 @@ groups:
t.Fatalf("expected to have exactly 1 group loaded; got %d", groupsLen)
}
writeToFile(f.Name(), rules2)
writeToFile(t, f.Name(), rules2)
time.Sleep(*configCheckInterval * 2)
checkCfg(nil)
groupsLen = lenLocked(m)
@@ -150,7 +172,7 @@ groups:
t.Fatalf("expected to have exactly 2 groups loaded; got %d", groupsLen)
}
writeToFile(f.Name(), rules1)
writeToFile(t, f.Name(), rules1)
procutil.SelfSIGHUP()
time.Sleep(*configCheckInterval / 2)
checkCfg(nil)
@@ -159,7 +181,7 @@ groups:
t.Fatalf("expected to have exactly 1 group loaded; got %d", groupsLen)
}
writeToFile(f.Name(), `corrupted`)
writeToFile(t, f.Name(), `corrupted`)
procutil.SelfSIGHUP()
time.Sleep(*configCheckInterval / 2)
checkCfg(fmt.Errorf("config error"))
@@ -172,6 +194,10 @@ groups:
<-syncCh
}
func writeToFile(file, b string) {
fs.MustWriteSync(file, []byte(b))
func writeToFile(t *testing.T, file, b string) {
t.Helper()
err := os.WriteFile(file, []byte(b), 0644)
if err != nil {
t.Fatal(err)
}
}

View File

@@ -3,7 +3,6 @@ package main
import (
"context"
"fmt"
"strconv"
"sync"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/config"
@@ -17,6 +16,7 @@ import (
// manager controls group states
type manager struct {
querierBuilder datasource.QuerierBuilder
notifiers func() []notifier.Notifier
rw remotewrite.RWClient
// remote read builder.
@@ -29,8 +29,25 @@ type manager struct {
groups map[uint64]*rule.Group
}
// groupAPI generates apiGroup object from group by its ID(hash)
func (m *manager) groupAPI(gID uint64) (*rule.ApiGroup, error) {
// ruleAPI generates apiRule object from alert by its ID(hash)
func (m *manager) ruleAPI(gID, rID uint64) (apiRule, error) {
m.groupsMu.RLock()
defer m.groupsMu.RUnlock()
g, ok := m.groups[gID]
if !ok {
return apiRule{}, fmt.Errorf("can't find group with id %d", gID)
}
for _, rule := range g.Rules {
if rule.ID() == rID {
return ruleToAPI(rule), nil
}
}
return apiRule{}, fmt.Errorf("can't find rule with id %d in group %q", rID, g.Name)
}
// alertAPI generates apiAlert object from alert by its ID(hash)
func (m *manager) alertAPI(gID, aID uint64) (*apiAlert, error) {
m.groupsMu.RLock()
defer m.groupsMu.RUnlock()
@@ -38,47 +55,13 @@ func (m *manager) groupAPI(gID uint64) (*rule.ApiGroup, error) {
if !ok {
return nil, fmt.Errorf("can't find group with id %d", gID)
}
return g.ToAPI(), nil
}
// ruleAPI generates apiRule object from alert by its ID(hash)
func (m *manager) ruleAPI(gID, rID uint64) (rule.ApiRule, error) {
m.groupsMu.RLock()
defer m.groupsMu.RUnlock()
group, ok := m.groups[gID]
if !ok {
return rule.ApiRule{}, fmt.Errorf("can't find group with id %d", gID)
}
g := group.ToAPI()
ruleID := strconv.FormatUint(rID, 10)
for _, r := range g.Rules {
if r.ID == ruleID {
return r, nil
}
}
return rule.ApiRule{}, fmt.Errorf("can't find rule with id %d in group %q", rID, g.Name)
}
// alertAPI generates apiAlert object from alert by its ID(hash)
func (m *manager) alertAPI(gID, aID uint64) (*rule.ApiAlert, error) {
m.groupsMu.RLock()
defer m.groupsMu.RUnlock()
group, ok := m.groups[gID]
if !ok {
return nil, fmt.Errorf("can't find group with id %d", gID)
}
g := group.ToAPI()
for _, r := range g.Rules {
if r.Type != rule.TypeAlerting {
ar, ok := r.(*rule.AlertingRule)
if !ok {
continue
}
alertID := strconv.FormatUint(aID, 10)
for _, a := range r.Alerts {
if a.ID == alertID {
return a, nil
}
if apiAlert := alertToAPI(ar, aID); apiAlert != nil {
return apiAlert, nil
}
}
return nil, fmt.Errorf("can't find alert with id %d in group %q", aID, g.Name)
@@ -99,16 +82,17 @@ func (m *manager) close() {
}
func (m *manager) startGroup(ctx context.Context, g *rule.Group, restore bool) error {
m.wg.Add(1)
id := g.GetID()
g.Init()
m.wg.Go(func() {
go func() {
defer m.wg.Done()
if restore {
g.Start(ctx, m.rw, m.rr)
g.Start(ctx, m.notifiers, m.rw, m.rr)
} else {
g.Start(ctx, m.rw, nil)
g.Start(ctx, m.notifiers, m.rw, nil)
}
})
}()
m.groups[id] = g
return nil
}
@@ -135,7 +119,7 @@ func (m *manager) update(ctx context.Context, groupsCfg []config.Group, restore
if rrPresent && m.rw == nil {
return fmt.Errorf("config contains recording rules but `-remoteWrite.url` isn't set")
}
if arPresent && notifier.GetTargets() == nil {
if arPresent && m.notifiers == nil {
return fmt.Errorf("config contains alerting rules but neither `-notifier.url` nor `-notifier.config` nor `-notifier.blackhole` aren't set")
}
@@ -172,15 +156,15 @@ func (m *manager) update(ctx context.Context, groupsCfg []config.Group, restore
if len(toUpdate) > 0 {
var wg sync.WaitGroup
for _, item := range toUpdate {
oldG := item.old
newG := item.new
wg.Go(func() {
// cancel evaluation so the Update will be applied as fast as possible.
// it is important to call InterruptEval before the update, because cancel fn
// can be re-assigned during the update.
oldG.InterruptEval()
oldG.UpdateWith(newG)
})
wg.Add(1)
// cancel evaluation so the Update will be applied as fast as possible.
// it is important to call InterruptEval before the update, because cancel fn
// can be re-assigned during the update.
item.old.InterruptEval()
go func(oldGroup *rule.Group, newGroup *rule.Group) {
oldGroup.UpdateWith(newGroup)
wg.Done()
}(item.old, item.new)
}
wg.Wait()
}

View File

@@ -40,11 +40,10 @@ func TestManagerEmptyRulesDir(t *testing.T) {
// execution of configuration update.
// Should be executed with -race flag
func TestManagerUpdateConcurrent(t *testing.T) {
_, cleanup := notifier.InitFakeNotifier()
defer cleanup()
m := &manager{
groups: make(map[uint64]*rule.Group),
querierBuilder: &datasource.FakeQuerier{},
notifiers: func() []notifier.Notifier { return []notifier.Notifier{&notifier.FakeNotifier{}} },
}
paths := []string{
"config/testdata/dir/rules0-good.rules",
@@ -128,9 +127,8 @@ func TestManagerUpdate_Success(t *testing.T) {
m := &manager{
groups: make(map[uint64]*rule.Group),
querierBuilder: &datasource.FakeQuerier{},
notifiers: func() []notifier.Notifier { return []notifier.Notifier{&notifier.FakeNotifier{}} },
}
_, cleanup := notifier.InitFakeNotifier()
defer cleanup()
cfgInit := loadCfg(t, []string{initPath}, true, true)
if err := m.update(ctx, cfgInit, false); err != nil {
@@ -279,8 +277,7 @@ func TestManagerUpdate_Failure(t *testing.T) {
rw: rw,
}
if notifiers != nil {
_, cleanup := notifier.InitFakeNotifier()
defer cleanup()
m.notifiers = func() []notifier.Notifier { return notifiers }
}
err := m.update(context.Background(), []config.Group{cfg}, false)
if err == nil {

View File

@@ -10,7 +10,7 @@ import (
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/templates"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/vmalertutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
)
@@ -166,8 +166,8 @@ func templateAnnotations(annotations map[string]string, data AlertTplData, tmpl
ctmpl, _ := tmpl.Clone()
ctmpl = ctmpl.Option("missingkey=zero")
if err := templateAnnotation(&buf, builder.String(), tData, ctmpl, execute); err != nil {
r[key] = err.Error()
eg.Add(fmt.Errorf("(key: %q, value: %q): %w", key, text, err))
r[key] = text
eg.Add(fmt.Errorf("key %q, template %q: %w", key, text, err))
continue
}
r[key] = buf.String()
@@ -184,21 +184,21 @@ type tplData struct {
func templateAnnotation(dst io.Writer, text string, data tplData, tpl *textTpl.Template, execute bool) error {
tpl, err := tpl.Parse(text)
if err != nil {
return fmt.Errorf("error parsing template: %w", err)
return fmt.Errorf("error parsing annotation template: %w", err)
}
if !execute {
return nil
}
if err = tpl.Execute(dst, data); err != nil {
return fmt.Errorf("error evaluating template: %w", err)
return fmt.Errorf("error evaluating annotation template: %w", err)
}
return nil
}
func (a Alert) applyRelabelingIfNeeded(relabelCfg *promrelabel.ParsedConfigs) []prompb.Label {
var labels []prompb.Label
func (a Alert) applyRelabelingIfNeeded(relabelCfg *promrelabel.ParsedConfigs) []prompbmarshal.Label {
var labels []prompbmarshal.Label
for k, v := range a.Labels {
labels = append(labels, prompb.Label{
labels = append(labels, prompbmarshal.Label{
Name: promrelabel.SanitizeMetricName(k),
Value: v,
})

View File

@@ -7,7 +7,7 @@ import (
"time"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
)
@@ -20,7 +20,7 @@ func TestAlertExecTemplate(t *testing.T) {
)
extLabels["cluster"] = extCluster
extLabels["dc"] = extDC
err := Init(extLabels, extURL)
_, err := Init(nil, extLabels, extURL)
checkErr(t, err)
f := func(alert *Alert, annotations map[string]string, tplExpected map[string]string) {
@@ -33,7 +33,7 @@ func TestAlertExecTemplate(t *testing.T) {
qFn := func(_ string) ([]datasource.Metric, error) {
return []datasource.Metric{
{
Labels: []prompb.Label{
Labels: []prompbmarshal.Label{
{Name: "foo", Value: "bar"},
{Name: "baz", Value: "qux"},
},
@@ -41,7 +41,7 @@ func TestAlertExecTemplate(t *testing.T) {
Timestamps: []int64{1},
},
{
Labels: []prompb.Label{
Labels: []prompbmarshal.Label{
{Name: "foo", Value: "garply"},
{Name: "baz", Value: "fred"},
},
@@ -213,7 +213,7 @@ func TestAlertExecTemplate(t *testing.T) {
}
func TestAlert_toPromLabels(t *testing.T) {
fn := func(labels map[string]string, exp []prompb.Label, relabel *promrelabel.ParsedConfigs) {
fn := func(labels map[string]string, exp []prompbmarshal.Label, relabel *promrelabel.ParsedConfigs) {
t.Helper()
a := Alert{Labels: labels}
got := a.applyRelabelingIfNeeded(relabel)
@@ -226,12 +226,12 @@ func TestAlert_toPromLabels(t *testing.T) {
fn(nil, nil, nil)
fn(
map[string]string{"foo": "bar", "a": "baz"}, // unsorted
[]prompb.Label{{Name: "a", Value: "baz"}, {Name: "foo", Value: "bar"}},
[]prompbmarshal.Label{{Name: "a", Value: "baz"}, {Name: "foo", Value: "bar"}},
nil,
)
fn(
map[string]string{"foo.bar": "baz", "service!name": "qux"},
[]prompb.Label{{Name: "foo_bar", Value: "baz"}, {Name: "service_name", Value: "qux"}},
[]prompbmarshal.Label{{Name: "foo_bar", Value: "baz"}, {Name: "service_name", Value: "qux"}},
nil,
)
@@ -247,17 +247,17 @@ func TestAlert_toPromLabels(t *testing.T) {
fn(
map[string]string{"a": "baz"},
[]prompb.Label{{Name: "a", Value: "baz"}, {Name: "foo", Value: "aaa"}},
[]prompbmarshal.Label{{Name: "a", Value: "baz"}, {Name: "foo", Value: "aaa"}},
pcs,
)
fn(
map[string]string{"foo": "bar", "a": "baz"},
[]prompb.Label{{Name: "a", Value: "baz"}, {Name: "foo", Value: "aaa"}},
[]prompbmarshal.Label{{Name: "a", Value: "baz"}, {Name: "foo", Value: "aaa"}},
pcs,
)
fn(
map[string]string{"qux": "bar", "env": "prod", "environment": "production"},
[]prompb.Label{{Name: "foo", Value: "aaa"}, {Name: "qux", Value: "bar"}},
[]prompbmarshal.Label{{Name: "foo", Value: "aaa"}, {Name: "qux", Value: "bar"}},
pcs,
)
}

View File

@@ -3,7 +3,6 @@ package notifier
import (
"bytes"
"context"
"errors"
"fmt"
"io"
"net/http"
@@ -16,18 +15,17 @@ import (
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/vmalertutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/httputil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promauth"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
)
// AlertManager represents integration provider with Prometheus alert manager
// https://github.com/prometheus/alertmanager
type AlertManager struct {
addr *url.URL
argFunc AlertURLGenerator
client *http.Client
timeout time.Duration
lastError string
addr *url.URL
argFunc AlertURLGenerator
client *http.Client
timeout time.Duration
authCfg *promauth.Config
// stores already parsed RelabelConfigs object
@@ -73,42 +71,24 @@ func (am AlertManager) Addr() string {
return am.addr.Redacted()
}
func (am *AlertManager) LastError() string {
return am.lastError
}
// Send an alert or resolve message
func (am *AlertManager) Send(ctx context.Context, alerts []Alert, alertLabels [][]prompb.Label, headers map[string]string) error {
if len(alerts) != len(alertLabels) {
return fmt.Errorf("mismatched number of alerts and label sets after global alert relabeling")
}
func (am *AlertManager) Send(ctx context.Context, alerts []Alert, headers map[string]string) error {
am.metrics.alertsSent.Add(len(alerts))
startTime := time.Now()
err := am.send(ctx, alerts, alertLabels, headers)
err := am.send(ctx, alerts, headers)
am.metrics.alertsSendDuration.UpdateDuration(startTime)
if err != nil {
// the context can be cancelled on graceful shutdown
// or on group update. So no need to handle the error as usual.
if errors.Is(err, context.Canceled) {
return nil
}
am.metrics.alertsSendErrors.Add(len(alerts))
am.lastError = err.Error()
} else {
am.lastError = ""
}
return err
}
func (am *AlertManager) send(ctx context.Context, alerts []Alert, alertLabels [][]prompb.Label, headers map[string]string) error {
func (am *AlertManager) send(ctx context.Context, alerts []Alert, headers map[string]string) error {
b := &bytes.Buffer{}
alertsToSend := make([]Alert, 0, len(alerts))
lblss := make([][]prompb.Label, 0, len(alerts))
for i, a := range alerts {
lbls := alertLabels[i]
if am.relabelConfigs != nil {
lbls = am.relabelConfigs.Apply(lbls, 0)
}
lblss := make([][]prompbmarshal.Label, 0, len(alerts))
for _, a := range alerts {
lbls := a.applyRelabelingIfNeeded(am.relabelConfigs)
if len(lbls) == 0 {
continue
}

View File

@@ -1,11 +1,11 @@
{% import (
"time"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
) %}
{% stripspace %}
{% func amRequest(alerts []Alert, generatorURL func(Alert) string, lblss [][]prompb.Label) %}
{% func amRequest(alerts []Alert, generatorURL func(Alert) string, lblss [][]prompbmarshal.Label) %}
[
{% for i, alert := range alerts %}
{% code lbls := lblss[i] %}

View File

@@ -8,7 +8,7 @@ package notifier
import (
"time"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
)
//line app/vmalert/notifier/alertmanager_request.qtpl:8
@@ -25,7 +25,7 @@ var (
)
//line app/vmalert/notifier/alertmanager_request.qtpl:8
func streamamRequest(qw422016 *qt422016.Writer, alerts []Alert, generatorURL func(Alert) string, lblss [][]prompb.Label) {
func streamamRequest(qw422016 *qt422016.Writer, alerts []Alert, generatorURL func(Alert) string, lblss [][]prompbmarshal.Label) {
//line app/vmalert/notifier/alertmanager_request.qtpl:8
qw422016.N().S(`[`)
//line app/vmalert/notifier/alertmanager_request.qtpl:10
@@ -114,7 +114,7 @@ func streamamRequest(qw422016 *qt422016.Writer, alerts []Alert, generatorURL fun
}
//line app/vmalert/notifier/alertmanager_request.qtpl:35
func writeamRequest(qq422016 qtio422016.Writer, alerts []Alert, generatorURL func(Alert) string, lblss [][]prompb.Label) {
func writeamRequest(qq422016 qtio422016.Writer, alerts []Alert, generatorURL func(Alert) string, lblss [][]prompbmarshal.Label) {
//line app/vmalert/notifier/alertmanager_request.qtpl:35
qw422016 := qt422016.AcquireWriter(qq422016)
//line app/vmalert/notifier/alertmanager_request.qtpl:35
@@ -125,7 +125,7 @@ func writeamRequest(qq422016 qtio422016.Writer, alerts []Alert, generatorURL fun
}
//line app/vmalert/notifier/alertmanager_request.qtpl:35
func amRequest(alerts []Alert, generatorURL func(Alert) string, lblss [][]prompb.Label) string {
func amRequest(alerts []Alert, generatorURL func(Alert) string, lblss [][]prompbmarshal.Label) string {
//line app/vmalert/notifier/alertmanager_request.qtpl:35
qb422016 := qt422016.AcquireByteBuffer()
//line app/vmalert/notifier/alertmanager_request.qtpl:35

View File

@@ -11,7 +11,6 @@ import (
"time"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promauth"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
)
@@ -146,11 +145,11 @@ func TestAlertManager_Send(t *testing.T) {
t.Fatalf("unexpected error: %s", err)
}
if err := am.Send(context.Background(), []Alert{{Labels: map[string]string{"a": "b"}}}, [][]prompb.Label{{{Name: "a", Value: "b"}}}, nil); err == nil {
if err := am.Send(context.Background(), []Alert{{Labels: map[string]string{"a": "b"}}}, nil); err == nil {
t.Fatalf("expected connection error got nil")
}
if err := am.Send(context.Background(), []Alert{{Labels: map[string]string{"a": "b"}}}, [][]prompb.Label{{{Name: "a", Value: "b"}}}, nil); err == nil {
if err := am.Send(context.Background(), []Alert{{Labels: map[string]string{"a": "b"}}}, nil); err == nil {
t.Fatalf("expected wrong http code error got nil")
}
@@ -161,7 +160,7 @@ func TestAlertManager_Send(t *testing.T) {
End: time.Now().UTC(),
Labels: map[string]string{"alertname": "alert0"},
Annotations: map[string]string{"a": "b", "c": "d"},
}}, [][]prompb.Label{{{Name: "alertname", Value: "alert0"}}}, map[string]string{headerKey: "bar"}); err != nil {
}}, map[string]string{headerKey: "bar"}); err != nil {
t.Fatalf("unexpected error %s", err)
}
@@ -175,7 +174,7 @@ func TestAlertManager_Send(t *testing.T) {
Name: "alert2",
Labels: map[string]string{"rule": "test", "tenant": "1"},
},
}, [][]prompb.Label{{{Name: "rule", Value: "test"}, {Name: "tenant", Value: "0"}}, {{Name: "rule", Value: "test"}, {Name: "tenant", Value: "1"}}}, map[string]string{headerKey: "bar"}); err != nil {
}, map[string]string{headerKey: "bar"}); err != nil {
t.Fatalf("unexpected error %s", err)
}
@@ -188,7 +187,7 @@ func TestAlertManager_Send(t *testing.T) {
Name: "alert2",
Labels: map[string]string{},
},
}, [][]prompb.Label{{{Name: "rule", Value: "test"}}, {{}}}, map[string]string{}); err != nil {
}, map[string]string{}); err != nil {
t.Fatalf("unexpected error %s", err)
}

View File

@@ -27,9 +27,15 @@ type Config struct {
// PathPrefix is added to URL path before adding alertManagerPath value
PathPrefix string `yaml:"path_prefix,omitempty"`
ConsulSDConfigs []ConsulSDConfigs `yaml:"consul_sd_configs,omitempty"`
DNSSDConfigs []DNSSDConfigs `yaml:"dns_sd_configs,omitempty"`
StaticConfigs []StaticConfig `yaml:"static_configs,omitempty"`
// ConsulSDConfigs contains list of settings for service discovery via Consul
// see https://prometheus.io/docs/prometheus/latest/configuration/configuration/#consul_sd_config
ConsulSDConfigs []consul.SDConfig `yaml:"consul_sd_configs,omitempty"`
// DNSSDConfigs contains list of settings for service discovery via DNS.
// See https://prometheus.io/docs/prometheus/latest/configuration/configuration/#dns_sd_config
DNSSDConfigs []dns.SDConfig `yaml:"dns_sd_configs,omitempty"`
// StaticConfigs contains list of static targets
StaticConfigs []StaticConfig `yaml:"static_configs,omitempty"`
// HTTPClientConfig contains HTTP configuration for Notifier clients
HTTPClientConfig promauth.HTTPClientConfig `yaml:",inline"`
@@ -56,29 +62,14 @@ type Config struct {
parsedAlertRelabelConfigs *promrelabel.ParsedConfigs
}
// staticConfig contains list of static targets in the following form:
// StaticConfig contains list of static targets in the following form:
//
// targets:
// [ - '<host>' ]
type StaticConfig struct {
Targets []string `yaml:"targets"`
// HTTPClientConfig contains HTTP configuration for the Targets
HTTPClientConfig promauth.HTTPClientConfig `yaml:",inline"`
AlertRelabelConfigs []promrelabel.RelabelConfig `yaml:"alert_relabel_configs,omitempty"`
}
// ConsulSDConfigs contains list of settings for service discovery via Consul,
// see https://prometheus.io/docs/prometheus/latest/configuration/configuration/#consul_sd_config
type ConsulSDConfigs struct {
consul.SDConfig `yaml:",inline"`
AlertRelabelConfigs []promrelabel.RelabelConfig `yaml:"alert_relabel_configs,omitempty"`
}
// DNSSDConfigs contains list of settings for service discovery via DNS,
// See https://prometheus.io/docs/prometheus/latest/configuration/configuration/#dns_sd_config
type DNSSDConfigs struct {
dns.SDConfig `yaml:",inline"`
AlertRelabelConfigs []promrelabel.RelabelConfig `yaml:"alert_relabel_configs,omitempty"`
HTTPClientConfig promauth.HTTPClientConfig `yaml:",inline"`
}
// UnmarshalYAML implements the yaml.Unmarshaler interface.
@@ -104,31 +95,6 @@ func (cfg *Config) UnmarshalYAML(unmarshal func(any) error) error {
}
cfg.parsedAlertRelabelConfigs = arCfg
for _, s := range cfg.StaticConfigs {
if len(s.AlertRelabelConfigs) > 0 {
_, err := promrelabel.ParseRelabelConfigs(s.AlertRelabelConfigs)
if err != nil {
return fmt.Errorf("failed to parse alert_relabel_configs in static_config: %w", err)
}
}
}
for _, s := range cfg.ConsulSDConfigs {
if len(s.AlertRelabelConfigs) > 0 {
_, err := promrelabel.ParseRelabelConfigs(s.AlertRelabelConfigs)
if err != nil {
return fmt.Errorf("failed to parse alert_relabel_configs in consul_sd_config: %w", err)
}
}
}
for _, s := range cfg.DNSSDConfigs {
if len(s.AlertRelabelConfigs) > 0 {
_, err := promrelabel.ParseRelabelConfigs(s.AlertRelabelConfigs)
if err != nil {
return fmt.Errorf("failed to parse alert_relabel_configs in dns_sd_config: %w", err)
}
}
}
b, err := yaml.Marshal(cfg)
if err != nil {
return fmt.Errorf("failed to marshal configuration for checksum: %w", err)

View File

@@ -35,6 +35,4 @@ func TestParseConfig_Failure(t *testing.T) {
f("testdata/unknownFields.bad.yaml", "unknown field")
f("non-existing-file", "error reading")
f("testdata/consul.bad.yaml", "failed to parse alert_relabel_configs in consul_sd_config")
f("testdata/dns.bad.yaml", "failed to parse alert relabeling config")
}

View File

@@ -8,7 +8,6 @@ import (
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promauth"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promscrape/discovery/consul"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promscrape/discovery/dns"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promutil"
@@ -29,7 +28,11 @@ type configWatcher struct {
targets map[TargetType][]Target
}
func newWatcher(cfg *Config, gen AlertURLGenerator) (*configWatcher, error) {
func newWatcher(path string, gen AlertURLGenerator) (*configWatcher, error) {
cfg, err := parseConfig(path)
if err != nil {
return nil, err
}
cw := &configWatcher{
cfg: cfg,
wg: sync.WaitGroup{},
@@ -85,15 +88,18 @@ func (cw *configWatcher) reload(path string) error {
return cw.start()
}
func (cw *configWatcher) add(typeK TargetType, interval time.Duration, targetsFn getTargets) error {
targetMetadata, errors := getTargetMetadata(targetsFn, cw.cfg)
func (cw *configWatcher) add(typeK TargetType, interval time.Duration, labelsFn getLabels) error {
targetMetadata, errors := getTargetMetadata(labelsFn, cw.cfg)
for _, err := range errors {
return fmt.Errorf("failed to init notifier for %q: %w", typeK, err)
}
cw.updateTargets(typeK, targetMetadata, cw.cfg, cw.genFn)
cw.wg.Go(func() {
cw.wg.Add(1)
go func() {
defer cw.wg.Done()
ticker := time.NewTicker(interval)
defer ticker.Stop()
@@ -103,77 +109,62 @@ func (cw *configWatcher) add(typeK TargetType, interval time.Duration, targetsFn
return
case <-ticker.C:
}
targetMetadata, errors := getTargetMetadata(targetsFn, cw.cfg)
targetMetadata, errors := getTargetMetadata(labelsFn, cw.cfg)
for _, err := range errors {
logger.Errorf("failed to init notifier for %q: %w", typeK, err)
}
cw.updateTargets(typeK, targetMetadata, cw.cfg, cw.genFn)
}
})
}()
return nil
}
type targetMetadata struct {
*promutil.Labels
alertRelabelConfigs *promrelabel.ParsedConfigs
}
func getTargetMetadata(targetsFn getTargets, cfg *Config) (map[string]targetMetadata, []error) {
metaLabelsList, alertRelabelCfgs, err := targetsFn()
func getTargetMetadata(labelsFn getLabels, cfg *Config) (map[string]*promutil.Labels, []error) {
metaLabels, err := labelsFn()
if err != nil {
return nil, []error{fmt.Errorf("failed to get labels: %w", err)}
}
targetMts := make(map[string]targetMetadata, len(metaLabelsList))
targetMetadata := make(map[string]*promutil.Labels, len(metaLabels))
var errors []error
duplicates := make(map[string]struct{})
for i := range metaLabelsList {
metaLabels := metaLabelsList[i]
alertRelabelCfg := alertRelabelCfgs[i]
for _, labels := range metaLabels {
target := labels.Get("__address__")
u, processedLabels, err := parseLabels(target, labels, cfg)
if err != nil {
errors = append(errors, err)
continue
}
if len(u) == 0 {
continue
}
// check for duplicated targets
// targets with same address but different alert_relabel_configs are still considered duplicates since it's mostly due to misconfiguration and could cause duplicated notifications.
if _, ok := duplicates[u]; ok {
if !*suppressDuplicateTargetErrors {
logger.Errorf("skipping duplicate target with identical address %q; "+
"make sure service discovery and relabeling is set up properly; "+
"original labels: %s; resulting labels: %s",
u, labels, processedLabels)
}
continue
}
duplicates[u] = struct{}{}
targetMts[u] = targetMetadata{
Labels: processedLabels,
alertRelabelConfigs: alertRelabelCfg,
}
for _, labels := range metaLabels {
target := labels.Get("__address__")
u, processedLabels, err := parseLabels(target, labels, cfg)
if err != nil {
errors = append(errors, err)
continue
}
if len(u) == 0 {
continue
}
if _, ok := duplicates[u]; ok { // check for duplicates
if !*suppressDuplicateTargetErrors {
logger.Errorf("skipping duplicate target with identical address %q; "+
"make sure service discovery and relabeling is set up properly; "+
"original labels: %s; resulting labels: %s",
u, labels, processedLabels)
}
continue
}
duplicates[u] = struct{}{}
targetMetadata[u] = processedLabels
}
return targetMts, errors
return targetMetadata, errors
}
type getTargets func() ([][]*promutil.Labels, []*promrelabel.ParsedConfigs, error)
type getLabels func() ([]*promutil.Labels, error)
func (cw *configWatcher) start() error {
if len(cw.cfg.StaticConfigs) > 0 {
var targets []Target
for i, cfg := range cw.cfg.StaticConfigs {
alertRelabelConfig, _ := promrelabel.ParseRelabelConfigs(cw.cfg.StaticConfigs[i].AlertRelabelConfigs)
for _, cfg := range cw.cfg.StaticConfigs {
httpCfg := mergeHTTPClientConfigs(cw.cfg.HTTPClientConfig, cfg.HTTPClientConfig)
for _, target := range cfg.Targets {
address, labels, err := parseLabels(target, nil, cw.cfg)
if err != nil {
return fmt.Errorf("failed to parse labels for target %q: %w", target, err)
}
notifier, err := NewAlertManager(address, cw.genFn, httpCfg, alertRelabelConfig, cw.cfg.Timeout.Duration())
notifier, err := NewAlertManager(address, cw.genFn, httpCfg, cw.cfg.parsedAlertRelabelConfigs, cw.cfg.Timeout.Duration())
if err != nil {
return fmt.Errorf("failed to init alertmanager for addr %q: %w", address, err)
}
@@ -187,20 +178,17 @@ func (cw *configWatcher) start() error {
}
if len(cw.cfg.ConsulSDConfigs) > 0 {
err := cw.add(TargetConsul, *consul.SDCheckInterval, func() ([][]*promutil.Labels, []*promrelabel.ParsedConfigs, error) {
var labels [][]*promutil.Labels
var alertRelabelConfigs []*promrelabel.ParsedConfigs
err := cw.add(TargetConsul, *consul.SDCheckInterval, func() ([]*promutil.Labels, error) {
var labels []*promutil.Labels
for i := range cw.cfg.ConsulSDConfigs {
alertRelabelConfig, _ := promrelabel.ParseRelabelConfigs(cw.cfg.ConsulSDConfigs[i].AlertRelabelConfigs)
sdc := &cw.cfg.ConsulSDConfigs[i]
targetLabels, err := sdc.GetLabels(cw.cfg.baseDir)
if err != nil {
return nil, nil, fmt.Errorf("got labels err: %w", err)
return nil, fmt.Errorf("got labels err: %w", err)
}
labels = append(labels, targetLabels)
alertRelabelConfigs = append(alertRelabelConfigs, alertRelabelConfig)
labels = append(labels, targetLabels...)
}
return labels, alertRelabelConfigs, nil
return labels, nil
})
if err != nil {
return fmt.Errorf("failed to start consulSD discovery: %w", err)
@@ -208,21 +196,17 @@ func (cw *configWatcher) start() error {
}
if len(cw.cfg.DNSSDConfigs) > 0 {
err := cw.add(TargetDNS, *dns.SDCheckInterval, func() ([][]*promutil.Labels, []*promrelabel.ParsedConfigs, error) {
var labels [][]*promutil.Labels
var alertRelabelConfigs []*promrelabel.ParsedConfigs
err := cw.add(TargetDNS, *dns.SDCheckInterval, func() ([]*promutil.Labels, error) {
var labels []*promutil.Labels
for i := range cw.cfg.DNSSDConfigs {
alertRelabelConfig, _ := promrelabel.ParseRelabelConfigs(cw.cfg.DNSSDConfigs[i].AlertRelabelConfigs)
sdc := &cw.cfg.DNSSDConfigs[i]
targetLabels, err := sdc.GetLabels(cw.cfg.baseDir)
if err != nil {
return nil, nil, fmt.Errorf("got labels err: %w", err)
return nil, fmt.Errorf("got labels err: %w", err)
}
labels = append(labels, targetLabels)
alertRelabelConfigs = append(alertRelabelConfigs, alertRelabelConfig)
labels = append(labels, targetLabels...)
}
return labels, alertRelabelConfigs, nil
return labels, nil
})
if err != nil {
return fmt.Errorf("failed to start DNSSD discovery: %w", err)
@@ -256,30 +240,30 @@ func (cw *configWatcher) setTargets(key TargetType, targets []Target) {
cw.targetsMu.Unlock()
}
func (cw *configWatcher) updateTargets(key TargetType, targetMts map[string]targetMetadata, cfg *Config, genFn AlertURLGenerator) {
func (cw *configWatcher) updateTargets(key TargetType, targetMetadata map[string]*promutil.Labels, cfg *Config, genFn AlertURLGenerator) {
cw.targetsMu.Lock()
defer cw.targetsMu.Unlock()
oldTargets := cw.targets[key]
var updatedTargets []Target
for _, ot := range oldTargets {
if _, ok := targetMts[ot.Addr()]; !ok {
if _, ok := targetMetadata[ot.Addr()]; !ok {
// if target not exists in currentTargets, close it
ot.Close()
ot.Notifier.Close()
} else {
updatedTargets = append(updatedTargets, ot)
delete(targetMts, ot.Addr())
delete(targetMetadata, ot.Addr())
}
}
// create new resources for the new targets
for addr, metadata := range targetMts {
am, err := NewAlertManager(addr, genFn, cfg.HTTPClientConfig, metadata.alertRelabelConfigs, cfg.Timeout.Duration())
for addr, labels := range targetMetadata {
am, err := NewAlertManager(addr, genFn, cfg.HTTPClientConfig, cfg.parsedAlertRelabelConfigs, cfg.Timeout.Duration())
if err != nil {
logger.Errorf("failed to init %s notifier with addr %q: %w", key, addr, err)
continue
}
updatedTargets = append(updatedTargets, Target{
Notifier: am,
Labels: metadata.Labels,
Labels: labels,
})
}

View File

@@ -7,11 +7,9 @@ import (
"net/http/httptest"
"os"
"sync"
"sync/atomic"
"testing"
"time"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/fs"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promauth"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promscrape/discovery/consul"
)
@@ -21,19 +19,15 @@ func TestConfigWatcherReload(t *testing.T) {
if err != nil {
t.Fatal(err)
}
defer fs.MustRemovePath(f.Name())
defer func() { _ = os.Remove(f.Name()) }()
writeToFile(f.Name(), `
writeToFile(t, f.Name(), `
static_configs:
- targets:
- localhost:9093
- localhost:9094
`)
cfg, err := parseConfig(f.Name())
if err != nil {
t.Fatalf("failed to parse config: %s", err)
}
cw, err := newWatcher(cfg, nil)
cw, err := newWatcher(f.Name(), nil)
if err != nil {
t.Fatalf("failed to start config watcher: %s", err)
}
@@ -47,9 +41,9 @@ static_configs:
if err != nil {
t.Fatal(err)
}
defer fs.MustRemovePath(f2.Name())
defer func() { _ = os.Remove(f2.Name()) }()
writeToFile(f2.Name(), `
writeToFile(t, f2.Name(), `
static_configs:
- targets:
- 127.0.0.1:9093
@@ -79,73 +73,42 @@ func TestConfigWatcherStart(t *testing.T) {
if err != nil {
t.Fatal(err)
}
defer fs.MustRemovePath(consulSDFile.Name())
defer func() { _ = os.Remove(consulSDFile.Name()) }()
writeToFile(consulSDFile.Name(), fmt.Sprintf(`
writeToFile(t, consulSDFile.Name(), fmt.Sprintf(`
scheme: https
path_prefix: proxy
consul_sd_configs:
- server: %s
services:
- alertmanager
- server: %s
services:
- alertmanager
alert_relabel_configs:
- target_label: "foo"
replacement: "tar"
`, consulSDServer.URL, consulSDServer.URL))
`, consulSDServer.URL))
cfg, err := parseConfig(consulSDFile.Name())
if err != nil {
t.Fatalf("failed to parse config: %s", err)
}
cw, err := newWatcher(cfg, nil)
cw, err := newWatcher(consulSDFile.Name(), nil)
if err != nil {
t.Fatalf("failed to start config watcher: %s", err)
}
defer cw.mustStop()
if len(cw.notifiers()) != 3 {
t.Fatalf("expected to get 3 notifiers; got %d", len(cw.notifiers()))
if len(cw.notifiers()) != 2 {
t.Fatalf("expected to get 2 notifiers; got %d", len(cw.notifiers()))
}
expAddr1 := fmt.Sprintf("https://%s/proxy/api/v2/alerts", fakeConsulService1)
expAddr2 := fmt.Sprintf("https://%s/proxy/api/v2/alerts", fakeConsulService2)
expAddr3 := fmt.Sprintf("https://%s/proxy/api/v2/alerts", fakeConsulService3)
n1, n2, n3 := cw.notifiers()[0], cw.notifiers()[1], cw.notifiers()[2]
n1, n2 := cw.notifiers()[0], cw.notifiers()[1]
if n1.Addr() != expAddr1 {
t.Fatalf("exp address %q; got %q", expAddr1, n1.Addr())
}
if n2.Addr() != expAddr2 {
t.Fatalf("exp address %q; got %q", expAddr2, n2.Addr())
}
if n3.Addr() != expAddr3 {
t.Fatalf("exp address %q; got %q", expAddr3, n3.Addr())
}
if n1.(*AlertManager).relabelConfigs.String() != "" {
t.Fatalf("unexpected relabel configs: %q", n1.(*AlertManager).relabelConfigs.String())
}
if n2.(*AlertManager).relabelConfigs.String() != "" {
t.Fatalf("unexpected relabel configs: %q", n2.(*AlertManager).relabelConfigs.String())
}
if n3.(*AlertManager).relabelConfigs.String() != "- target_label: foo\n replacement: tar\n" {
t.Fatalf("unexpected relabel configs: %q", n3.(*AlertManager).relabelConfigs.String())
}
f := func() bool { return len(cw.notifiers()) == 1 }
if !waitFor(f, time.Second) {
t.Fatalf("expected to get 1 notifiers; got %d", len(cw.notifiers()))
}
n3 = cw.notifiers()[0]
if n3.Addr() != expAddr3 {
t.Fatalf("exp address %q; got %q", expAddr3, n3.Addr())
}
if n3.(*AlertManager).relabelConfigs.String() != "- target_label: foo\n replacement: tar\n" {
t.Fatalf("unexpected relabel configs: %q", n3.(*AlertManager).relabelConfigs.String())
}
}
// TestConfigWatcherReloadConcurrent supposed to test concurrent
@@ -161,9 +124,9 @@ func TestConfigWatcherReloadConcurrent(t *testing.T) {
if err != nil {
t.Fatal(err)
}
defer fs.MustRemovePath(consulSDFile.Name())
defer func() { _ = os.Remove(consulSDFile.Name()) }()
writeToFile(consulSDFile.Name(), fmt.Sprintf(`
writeToFile(t, consulSDFile.Name(), fmt.Sprintf(`
consul_sd_configs:
- server: %s
services:
@@ -177,9 +140,9 @@ consul_sd_configs:
if err != nil {
t.Fatal(err)
}
defer fs.MustRemovePath(staticAndConsulSDFile.Name())
defer func() { _ = os.Remove(staticAndConsulSDFile.Name()) }()
writeToFile(staticAndConsulSDFile.Name(), fmt.Sprintf(`
writeToFile(t, staticAndConsulSDFile.Name(), fmt.Sprintf(`
static_configs:
- targets:
- localhost:9093
@@ -200,11 +163,7 @@ consul_sd_configs:
"unknownFields.bad.yaml",
}
cfg, err := parseConfig(paths[0])
if err != nil {
t.Fatalf("failed to parse config: %s", err)
}
cw, err := newWatcher(cfg, nil)
cw, err := newWatcher(paths[0], nil)
if err != nil {
t.Fatalf("failed to start config watcher: %s", err)
}
@@ -228,8 +187,9 @@ consul_sd_configs:
wg.Wait()
}
func writeToFile(file, b string) {
fs.MustWriteSync(file, []byte(b))
func writeToFile(t *testing.T, file, b string) {
t.Helper()
checkErr(t, os.WriteFile(file, []byte(b), 0644))
}
func checkErr(t *testing.T, err error) {
@@ -242,11 +202,10 @@ func checkErr(t *testing.T, err error) {
const (
fakeConsulService1 = "127.0.0.1:9093"
fakeConsulService2 = "127.0.0.1:9095"
fakeConsulService3 = "127.0.0.1:9097"
)
func newFakeConsulServer() *httptest.Server {
var requestCount atomic.Int32
requestCount := 0
mux := http.NewServeMux()
mux.HandleFunc("/v1/agent/self", func(rw http.ResponseWriter, _ *http.Request) {
rw.Write([]byte(`{"Config": {"Datacenter": "dc1"}}`))
@@ -261,7 +220,7 @@ func newFakeConsulServer() *httptest.Server {
}`))
})
mux.HandleFunc("/v1/health/service/alertmanager", func(rw http.ResponseWriter, _ *http.Request) {
if requestCount.Load() == 0 {
if requestCount == 0 {
rw.Header().Set("X-Consul-Index", "1")
rw.Write([]byte(`
[
@@ -401,7 +360,7 @@ func newFakeConsulServer() *httptest.Server {
}
]`))
}
requestCount.Add(1)
requestCount++
})
return httptest.NewServer(mux)

View File

@@ -5,8 +5,6 @@ import (
"fmt"
"sync"
"time"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
)
// FakeNotifier is a mock notifier
@@ -17,32 +15,14 @@ type FakeNotifier struct {
counter int
}
// InitFakeNotifier initializes global notifier to FakeNotifier,
// and returns a cleanup function to restore the original getActiveNotifiers.
func InitFakeNotifier() (*FakeNotifier, func()) {
originalGetActiveNotifiers := getActiveNotifiers
fn := &FakeNotifier{}
getActiveNotifiers = func() []Notifier {
return []Notifier{fn}
}
return fn, func() {
getActiveNotifiers = originalGetActiveNotifiers
}
}
// Close does nothing
func (*FakeNotifier) Close() {}
// LastError returns last error message
func (*FakeNotifier) LastError() string {
return ""
}
// Addr returns ""
func (*FakeNotifier) Addr() string { return "" }
// Send sets alerts and increases counter
func (fn *FakeNotifier) Send(_ context.Context, alerts []Alert, _ [][]prompb.Label, _ map[string]string) error {
func (fn *FakeNotifier) Send(_ context.Context, alerts []Alert, _ map[string]string) error {
fn.Lock()
defer fn.Unlock()
fn.counter += len(alerts)

View File

@@ -1,22 +1,14 @@
package notifier
import (
"context"
"flag"
"fmt"
"net/url"
"strconv"
"strings"
"sync"
"time"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/vmalertutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promauth"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promutil"
)
@@ -65,61 +57,11 @@ var (
sendTimeout = flagutil.NewArrayDuration("notifier.sendTimeout", 10*time.Second, "Timeout when sending alerts to the corresponding -notifier.url")
)
// AlertURLGeneratorFn returns a URL to the passed alert object.
// Call InitAlertURLGeneratorFn before using this function.
var AlertURLGeneratorFn AlertURLGenerator
// InitAlertURLGeneratorFn populates AlertURLGeneratorFn
func InitAlertURLGeneratorFn(externalURL *url.URL, externalAlertSource string, validateTemplate bool) error {
if externalAlertSource == "" {
AlertURLGeneratorFn = func(a Alert) string {
gID, aID := strconv.FormatUint(a.GroupID, 10), strconv.FormatUint(a.ID, 10)
return fmt.Sprintf("%s/vmalert/alert?%s=%s&%s=%s", externalURL, "group_id", gID, "alert_id", aID)
}
return nil
}
if validateTemplate {
if err := ValidateTemplates(map[string]string{
"tpl": externalAlertSource,
}); err != nil {
return fmt.Errorf("error validating source template %s: %w", externalAlertSource, err)
}
}
m := map[string]string{
"tpl": externalAlertSource,
}
AlertURLGeneratorFn = func(alert Alert) string {
qFn := func(_ string) ([]datasource.Metric, error) {
return nil, fmt.Errorf("`query` template isn't supported for alert source template")
}
templated, err := alert.ExecTemplate(qFn, alert.Labels, m)
if err != nil {
logger.Errorf("cannot template alert source: %s", err)
}
return fmt.Sprintf("%s/%s", externalURL, templated["tpl"])
}
return nil
}
var (
// getActiveNotifiers returns the current list of Notifier objects.
getActiveNotifiers func() []Notifier
// globalRelabelCfg stores the parsed alert relabeling config from the config file if there is
globalRelabelCfg *promrelabel.ParsedConfigs
// cw holds a configWatcher for configPath configuration file
// configWatcher provides a list of Notifier objects discovered
// from static config or via service discovery.
// cw is not nil only if configPath is provided.
cw *configWatcher
// externalLabels is a global variable for holding external labels configured via flags
// It is supposed to be inited via Init function only.
externalLabels map[string]string
// externalURL is a global variable for holding external URL value configured via flag
// It is supposed to be inited via Init function only.
externalURL string
)
// cw holds a configWatcher for configPath configuration file
// configWatcher provides a list of Notifier objects discovered
// from static config or via service discovery.
// cw is not nil only if configPath is provided.
var cw *configWatcher
// Reload checks the changes in configPath configuration file
// and applies changes if any.
@@ -130,62 +72,66 @@ func Reload() error {
return cw.reload(*configPath)
}
var staticNotifiersFn func() []Notifier
var (
// externalLabels is a global variable for holding external labels configured via flags
// It is supposed to be inited via Init function only.
externalLabels map[string]string
// externalURL is a global variable for holding external URL value configured via flag
// It is supposed to be inited via Init function only.
externalURL string
)
// Init returns a function for retrieving actual list of Notifier objects.
// Init works in two mods:
// - configuration via flags (for backward compatibility). Is always static
// and don't support live reloads.
// - configuration via file. Supports live reloads and service discovery.
//
// Init returns an error if both mods are used.
func Init(extLabels map[string]string, extURL string) error {
func Init(gen AlertURLGenerator, extLabels map[string]string, extURL string) (func() []Notifier, error) {
externalURL = extURL
externalLabels = extLabels
_, err := url.Parse(externalURL)
if err != nil {
return fmt.Errorf("failed to parse external URL: %w", err)
return nil, fmt.Errorf("failed to parse external URL: %w", err)
}
if *blackHole {
if len(*addrs) > 0 || *configPath != "" {
return fmt.Errorf("only one of -notifier.blackhole, -notifier.url and -notifier.config flags must be specified")
return nil, fmt.Errorf("only one of -notifier.blackhole, -notifier.url and -notifier.config flags must be specified")
}
notifier := newBlackHoleNotifier()
getActiveNotifiers = func() []Notifier {
staticNotifiersFn = func() []Notifier {
return []Notifier{notifier}
}
return nil
return staticNotifiersFn, nil
}
if *configPath == "" && len(*addrs) == 0 {
return nil
return nil, nil
}
if *configPath != "" && len(*addrs) > 0 {
return fmt.Errorf("only one of -notifier.config or -notifier.url flags must be specified")
return nil, fmt.Errorf("only one of -notifier.config or -notifier.url flags must be specified")
}
if len(*addrs) > 0 {
notifiers, err := notifiersFromFlags(AlertURLGeneratorFn)
notifiers, err := notifiersFromFlags(gen)
if err != nil {
return fmt.Errorf("failed to create notifier from flag values: %w", err)
return nil, fmt.Errorf("failed to create notifier from flag values: %w", err)
}
getActiveNotifiers = func() []Notifier {
staticNotifiersFn = func() []Notifier {
return notifiers
}
return nil
return staticNotifiersFn, nil
}
cfg, err := parseConfig(*configPath)
cw, err = newWatcher(*configPath, gen)
if err != nil {
return err
return nil, fmt.Errorf("failed to init config watcher: %w", err)
}
if cfg.AlertRelabelConfigs != nil {
globalRelabelCfg = cfg.parsedAlertRelabelConfigs
}
cw, err = newWatcher(cfg, AlertURLGeneratorFn)
if err != nil {
return fmt.Errorf("failed to init config watcher: %w", err)
}
getActiveNotifiers = cw.notifiers
return nil
return cw.notifiers, nil
}
// InitSecretFlags must be called after flag.Parse and before any logging
@@ -260,57 +206,23 @@ const (
// GetTargets returns list of static or discovered targets
// via notifier configuration.
//
// Must be called after Init.
func GetTargets() map[TargetType][]Target {
if getActiveNotifiers == nil {
return nil
}
var targets = make(map[TargetType][]Target)
// use cached targets from configWatcher instead of getActiveNotifiers for the extra target labels
if staticNotifiersFn != nil {
for _, ns := range staticNotifiersFn() {
targets[TargetStatic] = append(targets[TargetStatic], Target{
Notifier: ns,
})
}
}
if cw != nil {
cw.targetsMu.RLock()
for key, ns := range cw.targets {
targets[key] = append(targets[key], ns...)
}
cw.targetsMu.RUnlock()
return targets
}
// static notifiers don't have labels
for _, ns := range getActiveNotifiers() {
targets[TargetStatic] = append(targets[TargetStatic], Target{
Notifier: ns,
})
}
return targets
}
// Send sends alerts to all active notifiers
func Send(ctx context.Context, alerts []Alert, notifierHeaders map[string]string) *vmalertutil.ErrGroup {
alertsToSend := make([]Alert, 0, len(alerts))
lblss := make([][]prompb.Label, 0, len(alerts))
// apply global relabel config first without modifying original alerts in alerts
for _, a := range alerts {
lbls := a.applyRelabelingIfNeeded(globalRelabelCfg)
if len(lbls) == 0 {
continue
}
alertsToSend = append(alertsToSend, a)
lblss = append(lblss, lbls)
}
errGr := new(vmalertutil.ErrGroup)
wg := sync.WaitGroup{}
activeNotifiers := getActiveNotifiers()
for i := range activeNotifiers {
nt := activeNotifiers[i]
wg.Go(func() {
if err := nt.Send(ctx, alertsToSend, lblss, notifierHeaders); err != nil {
errGr.Add(fmt.Errorf("failed to send alerts to addr %q: %w", nt.Addr(), err))
}
})
}
wg.Wait()
return errGr
}

View File

@@ -1,17 +1,9 @@
package notifier
import (
"context"
"encoding/json"
"fmt"
"net/http"
"net/http/httptest"
"net/url"
"os"
"testing"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/fs"
)
func TestInit(t *testing.T) {
@@ -20,13 +12,14 @@ func TestInit(t *testing.T) {
*addrs = flagutil.ArrayString{"127.0.0.1", "127.0.0.2"}
err := Init(nil, "")
fn, err := Init(nil, nil, "")
if err != nil {
t.Fatalf("%s", err)
}
if len(getActiveNotifiers()) != 2 {
t.Fatalf("expected to get 2 notifiers; got %d", len(getActiveNotifiers()))
nfs := fn()
if len(nfs) != 2 {
t.Fatalf("expected to get 2 notifiers; got %d", len(nfs))
}
targets := GetTargets()
@@ -59,7 +52,7 @@ func TestInitNegative(t *testing.T) {
*configPath = path
*addrs = flagutil.ArrayString{addr}
*blackHole = bh
if err := Init(nil, ""); err == nil {
if _, err := Init(nil, nil, ""); err == nil {
t.Fatalf("expected to get error; got nil instead")
}
}
@@ -76,13 +69,14 @@ func TestBlackHole(t *testing.T) {
*blackHole = true
err := Init(nil, "")
fn, err := Init(nil, nil, "")
if err != nil {
t.Fatalf("%s", err)
}
if len(getActiveNotifiers()) != 1 {
t.Fatalf("expected to get 1 notifier; got %d", len(getActiveNotifiers()))
nfs := fn()
if len(nfs) != 1 {
t.Fatalf("expected to get 1 notifier; got %d", len(nfs))
}
targets := GetTargets()
@@ -97,112 +91,3 @@ func TestBlackHole(t *testing.T) {
t.Fatalf("expected to get \"blackhole\"; got %q instead", nf1.Addr())
}
}
func TestGetAlertURLGenerator(t *testing.T) {
oldAlertURLGeneratorFn := AlertURLGeneratorFn
defer func() { AlertURLGeneratorFn = oldAlertURLGeneratorFn }()
testAlert := Alert{GroupID: 42, ID: 2, Value: 4, Labels: map[string]string{"tenant": "baz"}}
u, _ := url.Parse("https://victoriametrics.com/path")
err := InitAlertURLGeneratorFn(u, "", false)
if err != nil {
t.Fatalf("unexpected error %s", err)
}
exp := fmt.Sprintf("https://victoriametrics.com/path/vmalert/alert?%s=42&%s=2", "group_id", "alert_id")
if exp != AlertURLGeneratorFn(testAlert) {
t.Fatalf("unexpected url want %s, got %s", exp, AlertURLGeneratorFn(testAlert))
}
err = InitAlertURLGeneratorFn(nil, "foo?{{invalid}}", true)
if err == nil {
t.Fatalf("expected template validation error got nil")
}
err = InitAlertURLGeneratorFn(u, "foo?query={{$value}}&ds={{ $labels.tenant }}", true)
if err != nil {
t.Fatalf("unexpected error %s", err)
}
if exp := "https://victoriametrics.com/path/foo?query=4&ds=baz"; exp != AlertURLGeneratorFn(testAlert) {
t.Fatalf("unexpected url want %s, got %s", exp, AlertURLGeneratorFn(testAlert))
}
}
func TestSendAlerts(t *testing.T) {
oldAlertURLGeneratorFn := AlertURLGeneratorFn
defer func() { AlertURLGeneratorFn = oldAlertURLGeneratorFn }()
AlertURLGeneratorFn = func(alert Alert) string {
return ""
}
mux := http.NewServeMux()
mux.HandleFunc("/", func(_ http.ResponseWriter, _ *http.Request) {
t.Fatalf("should not be called")
})
mux.HandleFunc(alertManagerPath, func(w http.ResponseWriter, r *http.Request) {
var a []struct {
Labels map[string]string `json:"labels"`
}
if err := json.NewDecoder(r.Body).Decode(&a); err != nil {
t.Fatalf("can not unmarshal data into alert %s", err)
}
if len(a) != 2 {
t.Fatalf("expected 2 alert in array got %d", len(a))
}
if len(a[0].Labels) != 4 {
t.Fatalf("expected 4 labels got %d", len(a[0].Labels))
}
if a[0].Labels["env"] != "prod" {
t.Fatalf("expected env label to be prod during relabeling, got %s", a[0].Labels["env"])
}
if a[0].Labels["c"] != "baz" {
t.Fatalf("expected c label to be baz during relabeling, got %s", a[0].Labels["c"])
}
if len(a[1].Labels) != 1 {
t.Fatalf("expected 1 labels got %d", len(a[1].Labels))
}
})
srv := httptest.NewServer(mux)
defer srv.Close()
f, err := os.CreateTemp("", "")
if err != nil {
t.Fatal(err)
}
defer fs.MustRemovePath(f.Name())
rawConfig := `
static_configs:
- targets:
- %s
alert_relabel_configs:
- source_labels: [b]
target_label: "c"
alert_relabel_configs:
- source_labels: [a]
target_label: "b"
- target_label: "env"
replacement: "prod"
`
config := fmt.Sprintf(rawConfig, srv.URL+alertManagerPath)
writeToFile(f.Name(), config)
oldConfigPath := configPath
defer func() { configPath = oldConfigPath }()
*configPath = f.Name()
err = Init(nil, "")
if err != nil {
t.Fatalf("unexpected error when parse notifier config: %s", err)
}
firingAlerts := []Alert{
{
Name: "alert1",
Labels: map[string]string{"a": "baz"},
},
{
Name: "alert2",
Labels: map[string]string{},
},
}
errG := Send(context.Background(), firingAlerts, nil)
if errG.Err() != nil {
t.Fatalf("unexpected error when sending alerts: %s", err)
}
}

View File

@@ -1,21 +1,15 @@
package notifier
import (
"context"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
)
import "context"
// Notifier is a common interface for alert manager provider
type Notifier interface {
// Send sends the given list of alerts.
// Returns an error if fails to send the alerts.
// Must unblock if the given ctx is cancelled.
Send(ctx context.Context, alerts []Alert, alertLabels [][]prompb.Label, notifierHeaders map[string]string) error
Send(ctx context.Context, alerts []Alert, notifierHeaders map[string]string) error
// Addr returns address where alerts are sent.
Addr() string
// LastError returns error, that occured during last attempt to send data
LastError() string
// Close is a destructor for the Notifier
Close()
}

View File

@@ -1,10 +1,6 @@
package notifier
import (
"context"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
)
import "context"
// blackHoleNotifier is a Notifier stub, used when no notifications need
// to be sent.
@@ -14,7 +10,7 @@ type blackHoleNotifier struct {
}
// Send will send no notifications, but increase the metric.
func (bh *blackHoleNotifier) Send(_ context.Context, alerts []Alert, _ [][]prompb.Label, _ map[string]string) error { //nolint:revive
func (bh *blackHoleNotifier) Send(_ context.Context, alerts []Alert, _ map[string]string) error { //nolint:revive
bh.metrics.alertsSent.Add(len(alerts))
return nil
}
@@ -29,11 +25,6 @@ func (bh *blackHoleNotifier) Close() {
bh.metrics.close()
}
// LastError return last notifier's error
func (bh *blackHoleNotifier) LastError() string {
return ""
}
// newBlackHoleNotifier creates a new blackHoleNotifier
func newBlackHoleNotifier() *blackHoleNotifier {
address := "blackhole"

View File

@@ -5,7 +5,6 @@ import (
"testing"
"time"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
metricset "github.com/VictoriaMetrics/metrics"
)
@@ -17,7 +16,7 @@ func TestBlackHoleNotifier_Send(t *testing.T) {
Start: time.Now().UTC(),
End: time.Now().UTC(),
Annotations: map[string]string{"a": "b", "c": "d", "e": "f"},
}}, [][]prompb.Label{{}}, nil); err != nil {
}}, nil); err != nil {
t.Fatalf("unexpected error %s", err)
}
@@ -35,7 +34,7 @@ func TestBlackHoleNotifier_Close(t *testing.T) {
Start: time.Now().UTC(),
End: time.Now().UTC(),
Annotations: map[string]string{"a": "b", "c": "d", "e": "f"},
}}, [][]prompb.Label{{}}, nil); err != nil {
}}, nil); err != nil {
t.Fatalf("unexpected error %s", err)
}

View File

@@ -1,19 +0,0 @@
consul_sd_configs:
- server: localhost:8500
scheme: http
services:
- alertmanager
alert_relabel_configs:
- action: keep
source_labels: [env]
regex: "prod"
- server: localhost:8500
services:
- consul
alert_relabel_configs:
- action: keep
source_labels: [env]
regex: "(abc"
alert_relabel_configs:
- target_label: "foo"
replacement: "aaa"

View File

@@ -1,13 +0,0 @@
dns_sd_configs:
- names:
- cloudflare.com
type: 'A'
port: 9093
relabel_configs:
- source_labels: [__meta_dns_name]
replacement: '${1}'
target_label: dns_name
alert_relabel_configs:
- action: keep
source_labels: [env]
regex: "(abc"

View File

@@ -2,19 +2,12 @@ static_configs:
- targets:
- localhost:9093
- localhost:9095
alert_relabel_configs:
- action: keep
source_labels: [env]
regex: "static"
consul_sd_configs:
- server: localhost:8500
scheme: http
services:
- alertmanager
alert_relabel_configs:
- action: keep
source_labels: [env]
regex: "consul"
- server: localhost:8500
services:
- consul
@@ -24,10 +17,6 @@ dns_sd_configs:
- cloudflare.com
type: 'A'
port: 9093
alert_relabel_configs:
- action: keep
source_labels: [env]
regex: "dns"
relabel_configs:
- source_labels: [__meta_consul_tags]
@@ -36,4 +25,4 @@ relabel_configs:
target_label: __scheme__
- source_labels: [__meta_dns_name]
replacement: '${1}'
target_label: dns_name
target_label: dns_name

View File

@@ -1,14 +1,22 @@
headers:
- 'CustomHeader: foo'
static_configs:
- targets:
- http://192.168.0.101:9093
alert_relabel_configs:
- target_label: "foo"
replacement: "aaa"
- localhost:9093
- localhost:9095
- https://localhost:9093/test/api/v2/alerts
basic_auth:
username: foo
password: bar
- targets:
- http://192.168.0.101:9093
alert_relabel_configs:
- target_label: "foo"
replacement: "ccc"
- localhost:9096
- localhost:9097
basic_auth:
username: foo
password: baz
alert_relabel_configs:
- target_label: "foo"
replacement: "aaa"

View File

@@ -1,19 +0,0 @@
package notifier
// ApiNotifier represents a Notifier configuration for WEB view
type ApiNotifier struct {
// Kind is a Notifier type
Kind TargetType `json:"kind"`
// Targets is a list of Notifier targets
Targets []*ApiTarget `json:"targets"`
}
// ApiTarget represents a specific Notifier target for WEB view
type ApiTarget struct {
// Address is a URL for sending notifications
Address string `json:"address"`
// Labels is a list of labels to add to each sent notification
Labels map[string]string `json:"labels"`
// LastError contains the error faced while sending to notifier.
LastError string `json:"lastError"`
}

View File

@@ -14,9 +14,9 @@ import (
)
var (
addr = flag.String("remoteRead.url", "", "Optional URL to datasource compatible with MetricsQL. 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. "+
addr = flag.String("remoteRead.url", "", "Optional URL to datasource compatible with MetricsQL. 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. "+
"Supports address in the form of IP address with a port (e.g., http://127.0.0.1:8428) or DNS SRV record. "+
"See also '-remoteRead.disablePathAppend', '-remoteRead.showURL'.")

View File

@@ -20,7 +20,7 @@ import (
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/netutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promauth"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
"github.com/VictoriaMetrics/metrics"
)
@@ -46,7 +46,7 @@ type Client struct {
addr string
c *http.Client
authCfg *promauth.Config
input chan prompb.TimeSeries
input chan prompbmarshal.TimeSeries
flushInterval time.Duration
maxBatchSize int
maxQueueSize int
@@ -110,7 +110,7 @@ func NewClient(ctx context.Context, cfg Config) (*Client, error) {
maxBatchSize: cfg.MaxBatchSize,
maxQueueSize: cfg.MaxQueueSize,
doneCh: make(chan struct{}),
input: make(chan prompb.TimeSeries, cfg.MaxQueueSize),
input: make(chan prompbmarshal.TimeSeries, cfg.MaxQueueSize),
}
for i := 0; i < cc; i++ {
@@ -121,7 +121,7 @@ func NewClient(ctx context.Context, cfg Config) (*Client, error) {
// Push adds timeseries into queue for writing into remote storage.
// Push returns and error if client is stopped or if queue is full.
func (c *Client) Push(s prompb.TimeSeries) error {
func (c *Client) Push(s prompbmarshal.TimeSeries) error {
rwTotal.Inc()
select {
case <-c.doneCh:
@@ -158,7 +158,7 @@ func (c *Client) Close() error {
func (c *Client) run(ctx context.Context) {
ticker := time.NewTicker(c.flushInterval)
wr := &prompb.WriteRequest{}
wr := &prompbmarshal.WriteRequest{}
shutdown := func() {
lastCtx, cancel := context.WithTimeout(context.Background(), defaultWriteTimeout)
@@ -173,8 +173,9 @@ func (c *Client) run(ctx context.Context) {
cancel()
}
c.wg.Go(func() {
c.wg.Add(1)
go func() {
defer c.wg.Done()
defer ticker.Stop()
for {
select {
@@ -196,7 +197,7 @@ func (c *Client) run(ctx context.Context) {
}
}
}
})
}()
}
var (
@@ -220,7 +221,7 @@ func GetDroppedRows() int { return int(droppedRows.Get()) }
// flush is a blocking function that marshals WriteRequest and sends
// it to remote-write endpoint. Flush performs limited amount of retries
// if request fails.
func (c *Client) flush(ctx context.Context, wr *prompb.WriteRequest) {
func (c *Client) flush(ctx context.Context, wr *prompbmarshal.WriteRequest) {
if len(wr.Timeseries) < 1 {
return
}

View File

@@ -15,6 +15,7 @@ import (
"github.com/golang/snappy"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
)
func TestClient_Push(t *testing.T) {
@@ -45,8 +46,8 @@ func TestClient_Push(t *testing.T) {
r := rand.New(rand.NewSource(1))
const rowsN = int(1e4)
for i := 0; i < rowsN; i++ {
s := prompb.TimeSeries{
Samples: []prompb.Sample{{
s := prompbmarshal.TimeSeries{
Samples: []prompbmarshal.Sample{{
Value: r.Float64(),
Timestamp: time.Now().Unix(),
}},
@@ -103,7 +104,7 @@ func TestClient_run_maxBatchSizeDuringShutdown(t *testing.T) {
// push time series to the client.
for i := 0; i < pushCnt; i++ {
if err = rwClient.Push(prompb.TimeSeries{}); err != nil {
if err = rwClient.Push(prompbmarshal.TimeSeries{}); err != nil {
t.Fatalf("cannot time series to the client: %s", err)
}
}
@@ -182,9 +183,8 @@ func (rw *rwServer) handler(w http.ResponseWriter, r *http.Request) {
rw.err(w, fmt.Errorf("decode err: %w", err))
return
}
wru := &prompb.WriteRequestUnmarshaler{}
wr, err := wru.UnmarshalProtobuf(b)
if err != nil {
wr := &prompb.WriteRequest{}
if err := wr.UnmarshalProtobuf(b); err != nil {
rw.err(w, fmt.Errorf("unmarhsal err: %w", err))
return
}

View File

@@ -13,7 +13,7 @@ import (
"github.com/VictoriaMetrics/VictoriaMetrics/lib/httputil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promauth"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
)
// DebugClient won't push series periodically, but will write data to remote endpoint
@@ -48,10 +48,10 @@ func NewDebugClient() (*DebugClient, error) {
}
// Push sends the given timeseries to the remote storage.
func (c *DebugClient) Push(s prompb.TimeSeries) error {
func (c *DebugClient) Push(s prompbmarshal.TimeSeries) error {
c.wg.Add(1)
defer c.wg.Done()
wr := &prompb.WriteRequest{Timeseries: []prompb.TimeSeries{s}}
wr := &prompbmarshal.WriteRequest{Timeseries: []prompbmarshal.TimeSeries{s}}
data := wr.MarshalProtobuf(nil)
return c.send(data)

View File

@@ -4,7 +4,7 @@ import (
"testing"
"time"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
)
func TestDebugClient_Push(t *testing.T) {
@@ -23,8 +23,8 @@ func TestDebugClient_Push(t *testing.T) {
const rowsN = 100
var sent int
for i := 0; i < rowsN; i++ {
s := prompb.TimeSeries{
Samples: []prompb.Sample{{
s := prompbmarshal.TimeSeries{
Samples: []prompbmarshal.Sample{{
Value: float64(i),
Timestamp: time.Now().Unix(),
}},

View File

@@ -1,13 +1,13 @@
package remotewrite
import (
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
)
// RWClient represents an HTTP client for pushing data via remote write protocol
type RWClient interface {
// Push pushes the give time series to remote storage
Push(s prompb.TimeSeries) error
Push(s prompbmarshal.TimeSeries) error
// Close stops the client. Client can't be reused after Close call.
Close() error
}

View File

@@ -28,8 +28,8 @@ var (
"Defines how many retries to make before giving up on rule if request for it returns an error.")
disableProgressBar = flag.Bool("replay.disableProgressBar", false, "Whether to disable rendering progress bars during the replay. "+
"Progress bar rendering might be verbose or break the logs parsing, so it is recommended to be disabled when not used in interactive mode.")
ruleEvaluationConcurrency = flag.Int("replay.ruleEvaluationConcurrency", 1, "The maximum number of concurrent '/query_range' requests when replay recording rule or alerting rule with for=0. "+
"Increasing this value when replaying for a long time, since each request is limited by -replay.maxDatapointsPerQuery.")
ruleEvaluationConcurrency = flag.Int("replay.ruleEvaluationConcurrency", 1, "The maximum number of concurrent `/query_range` requests for a single rule. "+
"Increasing this value when replaying for a long time and a single request range is limited by `-replay.maxDatapointsPerQuery`.")
)
func replay(groupsCfg []config.Group, qb datasource.QuerierBuilder, rw remotewrite.RWClient) (totalRows, droppedRows int, err error) {

View File

@@ -8,7 +8,7 @@ import (
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/config"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promutil"
)
@@ -23,7 +23,7 @@ func (fr *fakeReplayQuerier) BuildWithParams(_ datasource.QuerierParams) datasou
type fakeRWClient struct{}
func (fc *fakeRWClient) Push(_ prompb.TimeSeries) error {
func (fc *fakeRWClient) Push(_ prompbmarshal.TimeSeries) error {
return nil
}
@@ -246,33 +246,24 @@ func TestReplay(t *testing.T) {
// multiple rules + rule concurrency + group concurrency
f("2021-01-01T12:00:00.000Z", "2021-01-01T12:02:30.000Z", 1, 3, 0, []config.Group{
{Rules: []config.Rule{{Alert: "foo-group-single-concurrent", For: promutil.NewDuration(30 * time.Second), Expr: "sum(up) > 1"}, {Alert: "bar-group-single-concurrent", Expr: "max(up) < 1"}}, Concurrency: 2}}, &fakeReplayQuerier{
{Rules: []config.Rule{{Alert: "foo-group-single-concurrent", Expr: "sum(up) > 1"}, {Alert: "bar-group-single-concurrent", Expr: "max(up) < 1"}}, Concurrency: 2}}, &fakeReplayQuerier{
registry: map[string]map[string][]datasource.Metric{
"sum(up) > 1": {
"12:00:00+12:01:00": {{
Timestamps: []int64{1609502460},
Values: []float64{1},
}},
"12:00:00+12:01:00": {},
"12:01:00+12:02:00": {{
Timestamps: []int64{1609502520},
Values: []float64{1},
}},
"12:02:00+12:02:30": {{
Timestamps: []int64{1609502580},
Timestamps: []int64{1},
Values: []float64{1},
}},
"12:02:00+12:02:30": {},
},
"max(up) < 1": {
"12:00:00+12:01:00": {{
Timestamps: []int64{1609502460},
Values: []float64{1},
}},
"12:00:00+12:01:00": {},
"12:01:00+12:02:00": {{
Timestamps: []int64{1609502520},
Timestamps: []int64{1},
Values: []float64{1},
}},
"12:02:00+12:02:30": {},
},
},
}, 10)
}, 4)
}

View File

@@ -2,7 +2,6 @@ package rule
import (
"context"
"errors"
"fmt"
"hash/fnv"
"math"
@@ -20,7 +19,7 @@ import (
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/vmalertutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/decimal"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
)
@@ -188,54 +187,6 @@ func (ar *AlertingRule) ID() uint64 {
return ar.RuleID
}
// ToAPI returns ApiRule representation of ar
func (ar *AlertingRule) ToAPI() ApiRule {
state := ar.state
lastState := state.getLast()
r := ApiRule{
Type: TypeAlerting,
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: state.size(),
Updates: state.getAll(),
Debug: ar.Debug,
// encode as strings to avoid rounding in JSON
ID: fmt.Sprintf("%d", ar.ID()),
GroupID: fmt.Sprintf("%d", ar.GroupID),
GroupName: ar.GroupName,
File: ar.File,
}
if lastState.Err != nil {
r.LastError = lastState.Err.Error()
r.Health = "err"
}
// satisfy apiRule.State logic
if len(r.Alerts) > 0 {
r.State = notifier.StatePending.String()
stateFiring := notifier.StateFiring.String()
for _, a := range r.Alerts {
if a.State == stateFiring {
r.State = stateFiring
break
}
}
}
return r
}
// GetAlerts returns active alerts of rule
func (ar *AlertingRule) GetAlerts() []*notifier.Alert {
ar.alertsMu.RLock()
@@ -247,6 +198,16 @@ func (ar *AlertingRule) GetAlerts() []*notifier.Alert {
return alerts
}
// GetAlert returns alert if id exists
func (ar *AlertingRule) GetAlert(id uint64) *notifier.Alert {
ar.alertsMu.RLock()
defer ar.alertsMu.RUnlock()
if ar.alerts == nil {
return nil
}
return ar.alerts[id]
}
func (ar *AlertingRule) logDebugf(at time.Time, a *notifier.Alert, format string, args ...any) {
if !ar.Debug {
return
@@ -312,11 +273,6 @@ type labelSet struct {
// On k conflicts in origin set, the original value is preferred and copied
// to processed with `exported_%k` key. The copy happens only if passed v isn't equal to origin[k] value.
func (ls *labelSet) add(k, v string) {
// do not add label with empty value, since it has no meaning.
// see https://github.com/VictoriaMetrics/VictoriaMetrics/issues/9984
if v == "" {
return
}
ls.processed[k] = v
ov, ok := ls.origin[k]
if !ok {
@@ -351,6 +307,9 @@ func (ar *AlertingRule) toLabels(m datasource.Metric, qFn templates.QueryFn) (*l
Value: m.Values[0],
Expr: ar.Expr,
})
if err != nil {
return nil, fmt.Errorf("failed to expand labels: %w", err)
}
for k, v := range extraLabels {
ls.add(k, v)
}
@@ -361,7 +320,7 @@ func (ar *AlertingRule) toLabels(m datasource.Metric, qFn templates.QueryFn) (*l
if !*disableAlertGroupLabel && ar.GroupName != "" {
ls.add(alertGroupNameLabel, ar.GroupName)
}
return ls, err
return ls, nil
}
// execRange executes alerting rule on the given time range similarly to exec.
@@ -369,12 +328,12 @@ func (ar *AlertingRule) toLabels(m datasource.Metric, qFn templates.QueryFn) (*l
// as this function modifies AlertingRule alerts state.
// It is not thread safe.
// It returns ALERT and ALERT_FOR_STATE time series as a result.
func (ar *AlertingRule) execRange(ctx context.Context, start, end time.Time) ([]prompb.TimeSeries, error) {
func (ar *AlertingRule) execRange(ctx context.Context, start, end time.Time) ([]prompbmarshal.TimeSeries, error) {
res, err := ar.q.QueryRange(ctx, ar.Expr, start, end)
if err != nil {
return nil, err
}
var result []prompb.TimeSeries
var result []prompbmarshal.TimeSeries
holdAlertState := make(map[uint64]*notifier.Alert)
qFn := func(_ string) ([]datasource.Metric, error) {
logger.Warnf("`query` template isn't supported in replay mode, mocked data is used")
@@ -382,15 +341,11 @@ func (ar *AlertingRule) execRange(ctx context.Context, start, end time.Time) ([]
return []datasource.Metric{{Timestamps: []int64{0}, Values: []float64{math.NaN()}}}, nil
}
for _, s := range res.Data {
ls, err := ar.expandLabelTemplates(s, qFn)
ls, as, err := ar.expandTemplates(s, qFn, time.Time{})
if err != nil {
return nil, err
return nil, fmt.Errorf("failed to expand templates: %s", err)
}
alertID := hash(ls.processed)
as, err := ar.expandAnnotationTemplates(s, qFn, time.Time{}, ls)
if err != nil {
return nil, err
}
a := ar.newAlert(s, time.Time{}, ls.processed, as) // initial alert
prevT := time.Time{}
@@ -408,7 +363,7 @@ func (ar *AlertingRule) execRange(ctx context.Context, start, end time.Time) ([]
a.State = notifier.StatePending
a.ActiveAt = at
// re-template the annotations as active timestamp is changed
a.Annotations, _ = ar.expandAnnotationTemplates(s, qFn, at, ls)
_, a.Annotations, _ = ar.expandTemplates(s, qFn, at)
a.Start = time.Time{}
} else if at.Sub(a.ActiveAt) >= ar.For && a.State != notifier.StateFiring {
a.State = notifier.StateFiring
@@ -421,15 +376,13 @@ func (ar *AlertingRule) execRange(ctx context.Context, start, end time.Time) ([]
}
result = append(result, ar.alertToTimeSeries(a, s.Timestamps[i])...)
// if for>0, save alert's state on last iteration, so it can be used on the next execRange call
if ar.For > 0 && at.Equal(end) {
// save alert's state on last iteration, so it can be used on the next execRange call
if at.Equal(end) {
holdAlertState[alertID] = a
}
}
}
if len(holdAlertState) > 0 {
ar.alerts = holdAlertState
}
ar.alerts = holdAlertState
return result, nil
}
@@ -439,7 +392,7 @@ const resolvedRetention = 15 * time.Minute
// exec executes AlertingRule expression via the given Querier.
// Based on the Querier results AlertingRule maintains notifier.Alerts
func (ar *AlertingRule) exec(ctx context.Context, ts time.Time, limit int) ([]prompb.TimeSeries, error) {
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 := StateEntry{
@@ -454,7 +407,7 @@ func (ar *AlertingRule) exec(ctx context.Context, ts time.Time, limit int) ([]pr
defer func() {
ar.state.add(curState)
if curState.Err != nil && !errors.Is(curState.Err, context.Canceled) {
if curState.Err != nil {
ar.metrics.errors.Inc()
}
}()
@@ -475,25 +428,10 @@ func (ar *AlertingRule) exec(ctx context.Context, ts time.Time, limit int) ([]pr
expandedLabels := make([]*labelSet, len(res.Data))
expandedAnnotations := make([]map[string]string, len(res.Data))
for i, m := range res.Data {
ls, err := ar.expandLabelTemplates(m, qFn)
ls, as, err := ar.expandTemplates(m, qFn, ts)
if err != nil {
// only set error in current state, but do not break alert processing
curState.Err = err
logger.Errorf("got templating error in rule %s: %q", ar.Name, err)
}
at := ts
alertID := hash(ls.processed)
if a, ok := ar.alerts[alertID]; ok {
// modify activeAt for annotation templating if the alert has already triggered(in state Pending or Firing)
if a.State != notifier.StateInactive {
at = a.ActiveAt
}
}
as, err := ar.expandAnnotationTemplates(m, qFn, at, ls)
if err != nil {
// only set error in current state, but do not break alert processing
curState.Err = err
logger.Errorf("got templating error in rule %s: %q", ar.Name, err)
curState.Err = fmt.Errorf("failed to expand templates: %w", err)
return nil, curState.Err
}
expandedLabels[i] = ls
expandedAnnotations[i] = as
@@ -535,7 +473,6 @@ func (ar *AlertingRule) exec(ctx context.Context, ts time.Time, limit int) ([]pr
a.KeepFiringSince = time.Time{}
continue
}
a := ar.newAlert(m, ts, labels.processed, annotations)
a.ID = alertID
a.State = notifier.StatePending
@@ -543,7 +480,7 @@ func (ar *AlertingRule) exec(ctx context.Context, ts time.Time, limit int) ([]pr
ar.logDebugf(ts, a, "created in state PENDING")
}
var numActivePending int
var tss []prompb.TimeSeries
var tss []prompbmarshal.TimeSeries
for h, a := range ar.alerts {
// if alert wasn't updated in this iteration
// means it is resolved already
@@ -599,15 +536,12 @@ func (ar *AlertingRule) exec(ctx context.Context, ts time.Time, limit int) ([]pr
return append(tss, ar.toTimeSeries(ts.Unix())...), nil
}
func (ar *AlertingRule) expandLabelTemplates(m datasource.Metric, qFn templates.QueryFn) (*labelSet, error) {
func (ar *AlertingRule) expandTemplates(m datasource.Metric, qFn templates.QueryFn, ts time.Time) (*labelSet, map[string]string, error) {
ls, err := ar.toLabels(m, qFn)
if err != nil {
return ls, fmt.Errorf("failed to expand label templates: %s", err)
return nil, nil, fmt.Errorf("failed to expand labels: %w", err)
}
return ls, nil
}
func (ar *AlertingRule) expandAnnotationTemplates(m datasource.Metric, qFn templates.QueryFn, activeAt time.Time, ls *labelSet) (map[string]string, error) {
tplData := notifier.AlertTplData{
Value: m.Values[0],
Type: ar.Type.String(),
@@ -615,19 +549,19 @@ func (ar *AlertingRule) expandAnnotationTemplates(m datasource.Metric, qFn templ
Expr: ar.Expr,
AlertID: hash(ls.processed),
GroupID: ar.GroupID,
ActiveAt: activeAt,
ActiveAt: ts,
For: ar.For,
}
as, err := notifier.ExecTemplate(qFn, ar.Annotations, tplData)
if err != nil {
return as, fmt.Errorf("failed to expand annotation templates: %s", err)
return nil, nil, fmt.Errorf("failed to template annotations: %w", err)
}
return as, nil
return ls, as, nil
}
// toTimeSeries creates `ALERTS` and `ALERTS_FOR_STATE` for active alerts
func (ar *AlertingRule) toTimeSeries(timestamp int64) []prompb.TimeSeries {
var tss []prompb.TimeSeries
func (ar *AlertingRule) toTimeSeries(timestamp int64) []prompbmarshal.TimeSeries {
var tss []prompbmarshal.TimeSeries
for _, a := range ar.alerts {
if a.State == notifier.StateInactive {
continue
@@ -698,67 +632,67 @@ const (
)
// alertToTimeSeries converts the given alert with the given timestamp to time series
func (ar *AlertingRule) alertToTimeSeries(a *notifier.Alert, timestamp int64) []prompb.TimeSeries {
return []prompb.TimeSeries{
func (ar *AlertingRule) alertToTimeSeries(a *notifier.Alert, timestamp int64) []prompbmarshal.TimeSeries {
return []prompbmarshal.TimeSeries{
alertToTimeSeries(a, timestamp),
alertForToTimeSeries(a, timestamp),
}
}
func alertToTimeSeries(a *notifier.Alert, timestamp int64) prompb.TimeSeries {
labels := make([]prompb.Label, 0, len(a.Labels)+2)
func alertToTimeSeries(a *notifier.Alert, timestamp int64) prompbmarshal.TimeSeries {
labels := make([]prompbmarshal.Label, 0, len(a.Labels)+2)
for k, v := range a.Labels {
labels = append(labels, prompb.Label{
labels = append(labels, prompbmarshal.Label{
Name: k,
Value: v,
})
}
// __name__ already been dropped, no need to check duplication
labels = append(labels, prompb.Label{Name: "__name__", Value: alertMetricName})
labels = append(labels, prompbmarshal.Label{Name: "__name__", Value: alertMetricName})
if ol := promrelabel.GetLabelByName(labels, alertStateLabel); ol != nil {
ol.Value = a.State.String()
} else {
labels = append(labels, prompb.Label{Name: alertStateLabel, Value: a.State.String()})
labels = append(labels, prompbmarshal.Label{Name: alertStateLabel, Value: a.State.String()})
}
return newTimeSeries([]float64{1}, []int64{timestamp}, labels)
}
// alertForToTimeSeries returns a time series that represents
// state of active alerts, where value is time when alert become active
func alertForToTimeSeries(a *notifier.Alert, timestamp int64) prompb.TimeSeries {
labels := make([]prompb.Label, 0, len(a.Labels)+1)
func alertForToTimeSeries(a *notifier.Alert, timestamp int64) prompbmarshal.TimeSeries {
labels := make([]prompbmarshal.Label, 0, len(a.Labels)+1)
for k, v := range a.Labels {
labels = append(labels, prompb.Label{
labels = append(labels, prompbmarshal.Label{
Name: k,
Value: v,
})
}
// __name__ already been dropped, no need to check duplication
labels = append(labels, prompb.Label{Name: "__name__", Value: alertForStateMetricName})
labels = append(labels, prompbmarshal.Label{Name: "__name__", Value: alertForStateMetricName})
return newTimeSeries([]float64{float64(a.ActiveAt.Unix())}, []int64{timestamp}, labels)
}
// pendingAlertStaleTimeSeries returns stale `ALERTS` and `ALERTS_FOR_STATE` time series
// for alerts which changed their state from Pending to Inactive or Firing.
func pendingAlertStaleTimeSeries(ls map[string]string, timestamp int64, includeAlertForState bool) []prompb.TimeSeries {
var result []prompb.TimeSeries
baseLabels := make([]prompb.Label, 0, len(ls)+1)
func pendingAlertStaleTimeSeries(ls map[string]string, timestamp int64, includeAlertForState bool) []prompbmarshal.TimeSeries {
var result []prompbmarshal.TimeSeries
baseLabels := make([]prompbmarshal.Label, 0, len(ls)+1)
for k, v := range ls {
baseLabels = append(baseLabels, prompb.Label{
baseLabels = append(baseLabels, prompbmarshal.Label{
Name: k,
Value: v,
})
}
alertsLabels := make([]prompb.Label, 0, len(ls)+2)
alertsLabels := make([]prompbmarshal.Label, 0, len(ls)+2)
alertsLabels = append(alertsLabels, baseLabels...)
// __name__ already been dropped, no need to check duplication
alertsLabels = append(alertsLabels, prompb.Label{Name: "__name__", Value: alertMetricName})
alertsLabels = append(alertsLabels, prompb.Label{Name: alertStateLabel, Value: notifier.StatePending.String()})
alertsLabels = append(alertsLabels, prompbmarshal.Label{Name: "__name__", Value: alertMetricName})
alertsLabels = append(alertsLabels, prompbmarshal.Label{Name: alertStateLabel, Value: notifier.StatePending.String()})
result = append(result, newTimeSeries([]float64{decimal.StaleNaN}, []int64{timestamp}, alertsLabels))
if includeAlertForState {
baseLabels = append(baseLabels, prompb.Label{Name: "__name__", Value: alertForStateMetricName})
baseLabels = append(baseLabels, prompbmarshal.Label{Name: "__name__", Value: alertForStateMetricName})
result = append(result, newTimeSeries([]float64{decimal.StaleNaN}, []int64{timestamp}, baseLabels))
}
return result
@@ -766,24 +700,24 @@ func pendingAlertStaleTimeSeries(ls map[string]string, timestamp int64, includeA
// firingAlertStaleTimeSeries returns stale `ALERTS` and `ALERTS_FOR_STATE` time series
// for alerts which changed their state from Firing to Inactive.
func firingAlertStaleTimeSeries(ls map[string]string, timestamp int64) []prompb.TimeSeries {
baseLabels := make([]prompb.Label, 0, len(ls)+1)
func firingAlertStaleTimeSeries(ls map[string]string, timestamp int64) []prompbmarshal.TimeSeries {
baseLabels := make([]prompbmarshal.Label, 0, len(ls)+1)
for k, v := range ls {
baseLabels = append(baseLabels, prompb.Label{
baseLabels = append(baseLabels, prompbmarshal.Label{
Name: k,
Value: v,
})
}
alertsLabels := make([]prompb.Label, 0, len(ls)+2)
alertsLabels := make([]prompbmarshal.Label, 0, len(ls)+2)
alertsLabels = append(alertsLabels, baseLabels...)
// __name__ already been dropped, no need to check duplication
alertsLabels = append(alertsLabels, prompb.Label{Name: "__name__", Value: alertMetricName})
alertsLabels = append(alertsLabels, prompb.Label{Name: alertStateLabel, Value: notifier.StateFiring.String()})
alertsLabels = append(alertsLabels, prompbmarshal.Label{Name: "__name__", Value: alertMetricName})
alertsLabels = append(alertsLabels, prompbmarshal.Label{Name: alertStateLabel, Value: notifier.StateFiring.String()})
baseLabels = append(baseLabels, prompb.Label{Name: "__name__", Value: alertForStateMetricName})
baseLabels = append(baseLabels, prompbmarshal.Label{Name: "__name__", Value: alertForStateMetricName})
return []prompb.TimeSeries{
return []prompbmarshal.TimeSeries{
newTimeSeries([]float64{decimal.StaleNaN}, []int64{timestamp}, alertsLabels),
newTimeSeries([]float64{decimal.StaleNaN}, []int64{timestamp}, baseLabels),
}

View File

@@ -6,11 +6,9 @@ import (
"fmt"
"reflect"
"sort"
"strconv"
"strings"
"sync"
"testing"
"testing/synctest"
"time"
"github.com/VictoriaMetrics/metrics"
@@ -20,7 +18,7 @@ import (
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/vmalertutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/decimal"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promutil"
)
@@ -53,7 +51,7 @@ func TestNewAlertingRule(t *testing.T) {
func TestAlertingRuleToTimeSeries(t *testing.T) {
timestamp := time.Now()
f := func(rule *AlertingRule, alert *notifier.Alert, tssExpected []prompb.TimeSeries) {
f := func(rule *AlertingRule, alert *notifier.Alert, tssExpected []prompbmarshal.TimeSeries) {
t.Helper()
rule.alerts[alert.ID] = alert
@@ -66,8 +64,8 @@ func TestAlertingRuleToTimeSeries(t *testing.T) {
f(newTestAlertingRule("instant", 0), &notifier.Alert{
State: notifier.StateFiring,
ActiveAt: timestamp.Add(time.Second),
}, []prompb.TimeSeries{
newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()}, []prompb.Label{
}, []prompbmarshal.TimeSeries{
newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()}, []prompbmarshal.Label{
{
Name: "__name__",
Value: alertMetricName,
@@ -79,7 +77,7 @@ func TestAlertingRuleToTimeSeries(t *testing.T) {
}),
newTimeSeries([]float64{float64(timestamp.Add(time.Second).Unix())},
[]int64{timestamp.UnixNano()},
[]prompb.Label{
[]prompbmarshal.Label{
{
Name: "__name__",
Value: alertForStateMetricName,
@@ -93,9 +91,9 @@ func TestAlertingRuleToTimeSeries(t *testing.T) {
"job": "foo",
"instance": "bar",
},
}, []prompb.TimeSeries{
}, []prompbmarshal.TimeSeries{
newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()},
[]prompb.Label{
[]prompbmarshal.Label{
{
Name: "__name__",
Value: alertMetricName,
@@ -115,7 +113,7 @@ func TestAlertingRuleToTimeSeries(t *testing.T) {
}),
newTimeSeries([]float64{float64(timestamp.Add(time.Second).Unix())},
[]int64{timestamp.UnixNano()},
[]prompb.Label{
[]prompbmarshal.Label{
{
Name: "__name__",
Value: alertForStateMetricName,
@@ -136,8 +134,8 @@ func TestAlertingRuleToTimeSeries(t *testing.T) {
Labels: map[string]string{
alertStateLabel: "foo",
},
}, []prompb.TimeSeries{
newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()}, []prompb.Label{
}, []prompbmarshal.TimeSeries{
newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()}, []prompbmarshal.Label{
{
Name: "__name__",
Value: alertMetricName,
@@ -149,7 +147,7 @@ func TestAlertingRuleToTimeSeries(t *testing.T) {
}),
newTimeSeries([]float64{float64(timestamp.Add(time.Second).Unix())},
[]int64{timestamp.UnixNano()},
[]prompb.Label{
[]prompbmarshal.Label{
{
Name: "__name__",
Value: alertForStateMetricName,
@@ -164,8 +162,8 @@ func TestAlertingRuleToTimeSeries(t *testing.T) {
f(newTestAlertingRule("for", time.Second), &notifier.Alert{
State: notifier.StateFiring,
ActiveAt: timestamp.Add(time.Second),
}, []prompb.TimeSeries{
newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()}, []prompb.Label{
}, []prompbmarshal.TimeSeries{
newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()}, []prompbmarshal.Label{
{
Name: "__name__",
Value: alertMetricName,
@@ -177,7 +175,7 @@ func TestAlertingRuleToTimeSeries(t *testing.T) {
}),
newTimeSeries([]float64{float64(timestamp.Add(time.Second).Unix())},
[]int64{timestamp.UnixNano()},
[]prompb.Label{
[]prompbmarshal.Label{
{
Name: "__name__",
Value: alertForStateMetricName,
@@ -188,8 +186,8 @@ func TestAlertingRuleToTimeSeries(t *testing.T) {
f(newTestAlertingRule("for pending", 10*time.Second), &notifier.Alert{
State: notifier.StatePending,
ActiveAt: timestamp.Add(time.Second),
}, []prompb.TimeSeries{
newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()}, []prompb.Label{
}, []prompbmarshal.TimeSeries{
newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()}, []prompbmarshal.Label{
{
Name: "__name__",
Value: alertMetricName,
@@ -199,7 +197,7 @@ func TestAlertingRuleToTimeSeries(t *testing.T) {
Value: notifier.StatePending.String(),
},
}),
newTimeSeries([]float64{float64(timestamp.Add(time.Second).Unix())}, []int64{timestamp.UnixNano()}, []prompb.Label{
newTimeSeries([]float64{float64(timestamp.Add(time.Second).Unix())}, []int64{timestamp.UnixNano()}, []prompbmarshal.Label{
{
Name: "__name__",
Value: alertForStateMetricName,
@@ -217,7 +215,7 @@ func TestAlertingRule_Exec(t *testing.T) {
ts, _ := time.Parse(time.RFC3339, "2024-10-29T00:00:00Z")
f := func(rule *AlertingRule, steps [][]datasource.Metric, alertsExpected map[int][]testAlert, tssExpected map[int][]prompb.TimeSeries) {
f := func(rule *AlertingRule, steps [][]datasource.Metric, alertsExpected map[int][]testAlert, tssExpected map[int][]prompbmarshal.TimeSeries) {
t.Helper()
fq := &datasource.FakeQuerier{}
@@ -269,15 +267,8 @@ func TestAlertingRule_Exec(t *testing.T) {
if got.State != exp.State {
t.Fatalf("evalIndex %d: expected state %d; got %d", i, exp.State, got.State)
}
if rule.Annotations != nil && exp.Annotations != nil {
if !reflect.DeepEqual(got.Annotations, exp.Annotations) {
t.Fatalf("evalIndex %d: expected annotations %v; got %v", i, exp.Annotations, got.Annotations)
}
}
}
}
// reset ts for next test
ts, _ = time.Parse(time.RFC3339, "2024-10-29T00:00:00Z")
}
f(newTestAlertingRule("empty", 0), [][]datasource.Metric{}, nil, nil)
@@ -287,15 +278,15 @@ func TestAlertingRule_Exec(t *testing.T) {
}, map[int][]testAlert{
0: {{alert: &notifier.Alert{State: notifier.StateFiring}}},
},
map[int][]prompb.TimeSeries{
map[int][]prompbmarshal.TimeSeries{
0: {
{
Labels: []prompb.Label{{Name: "__name__", Value: alertMetricName}, {Name: "alertname", Value: "empty_labels"}, {Name: "alertstate", Value: "firing"}},
Samples: []prompb.Sample{{Value: 1, Timestamp: ts.UnixNano() / 1e6}},
Labels: []prompbmarshal.Label{{Name: "__name__", Value: alertMetricName}, {Name: "alertname", Value: "empty_labels"}, {Name: "alertstate", Value: "firing"}},
Samples: []prompbmarshal.Sample{{Value: 1, Timestamp: ts.UnixNano() / 1e6}},
},
{
Labels: []prompb.Label{{Name: "__name__", Value: alertForStateMetricName}, {Name: "alertname", Value: "empty_labels"}},
Samples: []prompb.Sample{{Value: float64(ts.Unix()), Timestamp: ts.UnixNano() / 1e6}},
Labels: []prompbmarshal.Label{{Name: "__name__", Value: alertForStateMetricName}, {Name: "alertname", Value: "empty_labels"}},
Samples: []prompbmarshal.Sample{{Value: float64(ts.Unix()), Timestamp: ts.UnixNano() / 1e6}},
},
},
})
@@ -312,35 +303,35 @@ func TestAlertingRule_Exec(t *testing.T) {
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}}},
}, map[int][]prompb.TimeSeries{
}, map[int][]prompbmarshal.TimeSeries{
0: {
{
Labels: []prompb.Label{{Name: "__name__", Value: alertMetricName}, {Name: "alertname", Value: "single-firing=>inactive=>firing=>inactive=>inactive"}, {Name: "alertstate", Value: "firing"}, {Name: "name", Value: "foo"}},
Samples: []prompb.Sample{{Value: 1, Timestamp: ts.UnixNano() / 1e6}},
Labels: []prompbmarshal.Label{{Name: "__name__", Value: alertMetricName}, {Name: "alertname", Value: "single-firing=>inactive=>firing=>inactive=>inactive"}, {Name: "alertstate", Value: "firing"}, {Name: "name", Value: "foo"}},
Samples: []prompbmarshal.Sample{{Value: 1, Timestamp: ts.UnixNano() / 1e6}},
},
{
Labels: []prompb.Label{{Name: "__name__", Value: alertForStateMetricName}, {Name: "alertname", Value: "single-firing=>inactive=>firing=>inactive=>inactive"}, {Name: "name", Value: "foo"}},
Samples: []prompb.Sample{{Value: float64(ts.Unix()), Timestamp: ts.UnixNano() / 1e6}},
Labels: []prompbmarshal.Label{{Name: "__name__", Value: alertForStateMetricName}, {Name: "alertname", Value: "single-firing=>inactive=>firing=>inactive=>inactive"}, {Name: "name", Value: "foo"}},
Samples: []prompbmarshal.Sample{{Value: float64(ts.Unix()), Timestamp: ts.UnixNano() / 1e6}},
},
},
1: {
{
Labels: []prompb.Label{{Name: "__name__", Value: alertMetricName}, {Name: "alertname", Value: "single-firing=>inactive=>firing=>inactive=>inactive"}, {Name: "alertstate", Value: "firing"}, {Name: "name", Value: "foo"}},
Samples: []prompb.Sample{{Value: decimal.StaleNaN, Timestamp: ts.Add(defaultStep).UnixNano() / 1e6}},
Labels: []prompbmarshal.Label{{Name: "__name__", Value: alertMetricName}, {Name: "alertname", Value: "single-firing=>inactive=>firing=>inactive=>inactive"}, {Name: "alertstate", Value: "firing"}, {Name: "name", Value: "foo"}},
Samples: []prompbmarshal.Sample{{Value: decimal.StaleNaN, Timestamp: ts.Add(defaultStep).UnixNano() / 1e6}},
},
{
Labels: []prompb.Label{{Name: "__name__", Value: alertForStateMetricName}, {Name: "alertname", Value: "single-firing=>inactive=>firing=>inactive=>inactive"}, {Name: "name", Value: "foo"}},
Samples: []prompb.Sample{{Value: decimal.StaleNaN, Timestamp: ts.Add(defaultStep).UnixNano() / 1e6}},
Labels: []prompbmarshal.Label{{Name: "__name__", Value: alertForStateMetricName}, {Name: "alertname", Value: "single-firing=>inactive=>firing=>inactive=>inactive"}, {Name: "name", Value: "foo"}},
Samples: []prompbmarshal.Sample{{Value: decimal.StaleNaN, Timestamp: ts.Add(defaultStep).UnixNano() / 1e6}},
},
},
2: {
{
Labels: []prompb.Label{{Name: "__name__", Value: alertMetricName}, {Name: "alertname", Value: "single-firing=>inactive=>firing=>inactive=>inactive"}, {Name: "alertstate", Value: "firing"}, {Name: "name", Value: "foo"}},
Samples: []prompb.Sample{{Value: 1, Timestamp: ts.Add(2*defaultStep).UnixNano() / 1e6}},
Labels: []prompbmarshal.Label{{Name: "__name__", Value: alertMetricName}, {Name: "alertname", Value: "single-firing=>inactive=>firing=>inactive=>inactive"}, {Name: "alertstate", Value: "firing"}, {Name: "name", Value: "foo"}},
Samples: []prompbmarshal.Sample{{Value: 1, Timestamp: ts.Add(2*defaultStep).UnixNano() / 1e6}},
},
{
Labels: []prompb.Label{{Name: "__name__", Value: alertForStateMetricName}, {Name: "alertname", Value: "single-firing=>inactive=>firing=>inactive=>inactive"}, {Name: "name", Value: "foo"}},
Samples: []prompb.Sample{{Value: float64(ts.Add(2 * defaultStep).Unix()), Timestamp: ts.Add(2*defaultStep).UnixNano() / 1e6}},
Labels: []prompbmarshal.Label{{Name: "__name__", Value: alertForStateMetricName}, {Name: "alertname", Value: "single-firing=>inactive=>firing=>inactive=>inactive"}, {Name: "name", Value: "foo"}},
Samples: []prompbmarshal.Sample{{Value: float64(ts.Add(2 * defaultStep).Unix()), Timestamp: ts.Add(2*defaultStep).UnixNano() / 1e6}},
},
},
})
@@ -395,55 +386,55 @@ func TestAlertingRule_Exec(t *testing.T) {
{labels: []string{"name", "foo1"}, alert: &notifier.Alert{State: notifier.StateInactive}},
{labels: []string{"name", "foo2"}, alert: &notifier.Alert{State: notifier.StateFiring}},
},
}, map[int][]prompb.TimeSeries{
}, map[int][]prompbmarshal.TimeSeries{
0: {
{
Labels: []prompb.Label{{Name: "__name__", Value: alertMetricName}, {Name: "alertname", Value: "multiple-steps-firing"}, {Name: "alertstate", Value: "firing"}, {Name: "name", Value: "foo"}},
Samples: []prompb.Sample{{Value: 1, Timestamp: ts.UnixNano() / 1e6}},
Labels: []prompbmarshal.Label{{Name: "__name__", Value: alertMetricName}, {Name: "alertname", Value: "multiple-steps-firing"}, {Name: "alertstate", Value: "firing"}, {Name: "name", Value: "foo"}},
Samples: []prompbmarshal.Sample{{Value: 1, Timestamp: ts.UnixNano() / 1e6}},
},
{
Labels: []prompb.Label{{Name: "__name__", Value: alertForStateMetricName}, {Name: "alertname", Value: "multiple-steps-firing"}, {Name: "name", Value: "foo"}},
Samples: []prompb.Sample{{Value: float64(ts.Unix()), Timestamp: ts.UnixNano() / 1e6}},
Labels: []prompbmarshal.Label{{Name: "__name__", Value: alertForStateMetricName}, {Name: "alertname", Value: "multiple-steps-firing"}, {Name: "name", Value: "foo"}},
Samples: []prompbmarshal.Sample{{Value: float64(ts.Unix()), Timestamp: ts.UnixNano() / 1e6}},
},
},
1: {
// stale time series for foo, `firing -> inactive`
{
Labels: []prompb.Label{{Name: "__name__", Value: alertMetricName}, {Name: "alertname", Value: "multiple-steps-firing"}, {Name: "alertstate", Value: "firing"}, {Name: "name", Value: "foo"}},
Samples: []prompb.Sample{{Value: decimal.StaleNaN, Timestamp: ts.Add(defaultStep).UnixNano() / 1e6}},
Labels: []prompbmarshal.Label{{Name: "__name__", Value: alertMetricName}, {Name: "alertname", Value: "multiple-steps-firing"}, {Name: "alertstate", Value: "firing"}, {Name: "name", Value: "foo"}},
Samples: []prompbmarshal.Sample{{Value: decimal.StaleNaN, Timestamp: ts.Add(defaultStep).UnixNano() / 1e6}},
},
{
Labels: []prompb.Label{{Name: "__name__", Value: alertForStateMetricName}, {Name: "alertname", Value: "multiple-steps-firing"}, {Name: "name", Value: "foo"}},
Samples: []prompb.Sample{{Value: decimal.StaleNaN, Timestamp: ts.Add(defaultStep).UnixNano() / 1e6}},
Labels: []prompbmarshal.Label{{Name: "__name__", Value: alertForStateMetricName}, {Name: "alertname", Value: "multiple-steps-firing"}, {Name: "name", Value: "foo"}},
Samples: []prompbmarshal.Sample{{Value: decimal.StaleNaN, Timestamp: ts.Add(defaultStep).UnixNano() / 1e6}},
},
// new time series for foo1
{
Labels: []prompb.Label{{Name: "__name__", Value: alertMetricName}, {Name: "alertname", Value: "multiple-steps-firing"}, {Name: "alertstate", Value: "firing"}, {Name: "name", Value: "foo1"}},
Samples: []prompb.Sample{{Value: 1, Timestamp: ts.Add(defaultStep).UnixNano() / 1e6}},
Labels: []prompbmarshal.Label{{Name: "__name__", Value: alertMetricName}, {Name: "alertname", Value: "multiple-steps-firing"}, {Name: "alertstate", Value: "firing"}, {Name: "name", Value: "foo1"}},
Samples: []prompbmarshal.Sample{{Value: 1, Timestamp: ts.Add(defaultStep).UnixNano() / 1e6}},
},
{
Labels: []prompb.Label{{Name: "__name__", Value: alertForStateMetricName}, {Name: "alertname", Value: "multiple-steps-firing"}, {Name: "name", Value: "foo1"}},
Samples: []prompb.Sample{{Value: float64(ts.Add(defaultStep).Unix()), Timestamp: ts.Add(defaultStep).UnixNano() / 1e6}},
Labels: []prompbmarshal.Label{{Name: "__name__", Value: alertForStateMetricName}, {Name: "alertname", Value: "multiple-steps-firing"}, {Name: "name", Value: "foo1"}},
Samples: []prompbmarshal.Sample{{Value: float64(ts.Add(defaultStep).Unix()), Timestamp: ts.Add(defaultStep).UnixNano() / 1e6}},
},
},
2: {
// stale time series for foo1
{
Labels: []prompb.Label{{Name: "__name__", Value: alertMetricName}, {Name: "alertname", Value: "multiple-steps-firing"}, {Name: "alertstate", Value: "firing"}, {Name: "name", Value: "foo1"}},
Samples: []prompb.Sample{{Value: decimal.StaleNaN, Timestamp: ts.Add(2*defaultStep).UnixNano() / 1e6}},
Labels: []prompbmarshal.Label{{Name: "__name__", Value: alertMetricName}, {Name: "alertname", Value: "multiple-steps-firing"}, {Name: "alertstate", Value: "firing"}, {Name: "name", Value: "foo1"}},
Samples: []prompbmarshal.Sample{{Value: decimal.StaleNaN, Timestamp: ts.Add(2*defaultStep).UnixNano() / 1e6}},
},
{
Labels: []prompb.Label{{Name: "__name__", Value: alertForStateMetricName}, {Name: "alertname", Value: "multiple-steps-firing"}, {Name: "name", Value: "foo1"}},
Samples: []prompb.Sample{{Value: decimal.StaleNaN, Timestamp: ts.Add(2*defaultStep).UnixNano() / 1e6}},
Labels: []prompbmarshal.Label{{Name: "__name__", Value: alertForStateMetricName}, {Name: "alertname", Value: "multiple-steps-firing"}, {Name: "name", Value: "foo1"}},
Samples: []prompbmarshal.Sample{{Value: decimal.StaleNaN, Timestamp: ts.Add(2*defaultStep).UnixNano() / 1e6}},
},
// new time series for foo2
{
Labels: []prompb.Label{{Name: "__name__", Value: alertMetricName}, {Name: "alertname", Value: "multiple-steps-firing"}, {Name: "alertstate", Value: "firing"}, {Name: "name", Value: "foo2"}},
Samples: []prompb.Sample{{Value: 1, Timestamp: ts.Add(2*defaultStep).UnixNano() / 1e6}},
Labels: []prompbmarshal.Label{{Name: "__name__", Value: alertMetricName}, {Name: "alertname", Value: "multiple-steps-firing"}, {Name: "alertstate", Value: "firing"}, {Name: "name", Value: "foo2"}},
Samples: []prompbmarshal.Sample{{Value: 1, Timestamp: ts.Add(2*defaultStep).UnixNano() / 1e6}},
},
{
Labels: []prompb.Label{{Name: "__name__", Value: alertForStateMetricName}, {Name: "alertname", Value: "multiple-steps-firing"}, {Name: "name", Value: "foo2"}},
Samples: []prompb.Sample{{Value: float64(ts.Add(2 * defaultStep).Unix()), Timestamp: ts.Add(2*defaultStep).UnixNano() / 1e6}},
Labels: []prompbmarshal.Label{{Name: "__name__", Value: alertForStateMetricName}, {Name: "alertname", Value: "multiple-steps-firing"}, {Name: "name", Value: "foo2"}},
Samples: []prompbmarshal.Sample{{Value: float64(ts.Add(2 * defaultStep).Unix()), Timestamp: ts.Add(2*defaultStep).UnixNano() / 1e6}},
},
},
})
@@ -460,30 +451,30 @@ func TestAlertingRule_Exec(t *testing.T) {
}, 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}}},
}, map[int][]prompb.TimeSeries{
}, map[int][]prompbmarshal.TimeSeries{
0: {
{
Labels: []prompb.Label{{Name: "__name__", Value: alertMetricName}, {Name: "alertname", Value: "for-fired"}, {Name: "alertstate", Value: "pending"}, {Name: "name", Value: "foo"}},
Samples: []prompb.Sample{{Value: 1, Timestamp: ts.UnixNano() / 1e6}},
Labels: []prompbmarshal.Label{{Name: "__name__", Value: alertMetricName}, {Name: "alertname", Value: "for-fired"}, {Name: "alertstate", Value: "pending"}, {Name: "name", Value: "foo"}},
Samples: []prompbmarshal.Sample{{Value: 1, Timestamp: ts.UnixNano() / 1e6}},
},
{
Labels: []prompb.Label{{Name: "__name__", Value: alertForStateMetricName}, {Name: "alertname", Value: "for-fired"}, {Name: "name", Value: "foo"}},
Samples: []prompb.Sample{{Value: float64(ts.Unix()), Timestamp: ts.UnixNano() / 1e6}},
Labels: []prompbmarshal.Label{{Name: "__name__", Value: alertForStateMetricName}, {Name: "alertname", Value: "for-fired"}, {Name: "name", Value: "foo"}},
Samples: []prompbmarshal.Sample{{Value: float64(ts.Unix()), Timestamp: ts.UnixNano() / 1e6}},
},
},
1: {
// stale time series for `pending -> firing`
{
Labels: []prompb.Label{{Name: "__name__", Value: alertMetricName}, {Name: "alertname", Value: "for-fired"}, {Name: "alertstate", Value: "pending"}, {Name: "name", Value: "foo"}},
Samples: []prompb.Sample{{Value: decimal.StaleNaN, Timestamp: ts.Add(defaultStep).UnixNano() / 1e6}},
Labels: []prompbmarshal.Label{{Name: "__name__", Value: alertMetricName}, {Name: "alertname", Value: "for-fired"}, {Name: "alertstate", Value: "pending"}, {Name: "name", Value: "foo"}},
Samples: []prompbmarshal.Sample{{Value: decimal.StaleNaN, Timestamp: ts.Add(defaultStep).UnixNano() / 1e6}},
},
{
Labels: []prompb.Label{{Name: "__name__", Value: alertMetricName}, {Name: "alertname", Value: "for-fired"}, {Name: "alertstate", Value: "firing"}, {Name: "name", Value: "foo"}},
Samples: []prompb.Sample{{Value: 1, Timestamp: ts.Add(defaultStep).UnixNano() / 1e6}},
Labels: []prompbmarshal.Label{{Name: "__name__", Value: alertMetricName}, {Name: "alertname", Value: "for-fired"}, {Name: "alertstate", Value: "firing"}, {Name: "name", Value: "foo"}},
Samples: []prompbmarshal.Sample{{Value: 1, Timestamp: ts.Add(defaultStep).UnixNano() / 1e6}},
},
{
Labels: []prompb.Label{{Name: "__name__", Value: alertForStateMetricName}, {Name: "alertname", Value: "for-fired"}, {Name: "name", Value: "foo"}},
Samples: []prompb.Sample{{Value: float64(ts.Add(defaultStep).Unix()), Timestamp: ts.Add(defaultStep).UnixNano() / 1e6}},
Labels: []prompbmarshal.Label{{Name: "__name__", Value: alertForStateMetricName}, {Name: "alertname", Value: "for-fired"}, {Name: "name", Value: "foo"}},
Samples: []prompbmarshal.Sample{{Value: float64(ts.Add(defaultStep).Unix()), Timestamp: ts.Add(defaultStep).UnixNano() / 1e6}},
},
},
})
@@ -497,41 +488,41 @@ func TestAlertingRule_Exec(t *testing.T) {
0: {{labels: []string{"name", "foo", "a1", "b1", "a2", "b2", "a3", "b3"}, alert: &notifier.Alert{State: notifier.StatePending}}},
1: {{labels: []string{"name", "foo", "a1", "b1", "a2", "b2", "a3", "b3"}, alert: &notifier.Alert{State: notifier.StatePending}}},
2: {},
}, map[int][]prompb.TimeSeries{
}, map[int][]prompbmarshal.TimeSeries{
0: {
{
Labels: []prompb.Label{{Name: "__name__", Value: alertMetricName}, {Name: "a1", Value: "b1"}, {Name: "a2", Value: "b2"}, {Name: "a3", Value: "b3"}, {Name: "alertname", Value: "for-pending=>empty"}, {Name: "alertstate", Value: "pending"}, {Name: "name", Value: "foo"}},
Samples: []prompb.Sample{{Value: 1, Timestamp: ts.UnixNano() / 1e6}},
Labels: []prompbmarshal.Label{{Name: "__name__", Value: alertMetricName}, {Name: "a1", Value: "b1"}, {Name: "a2", Value: "b2"}, {Name: "a3", Value: "b3"}, {Name: "alertname", Value: "for-pending=>empty"}, {Name: "alertstate", Value: "pending"}, {Name: "name", Value: "foo"}},
Samples: []prompbmarshal.Sample{{Value: 1, Timestamp: ts.UnixNano() / 1e6}},
},
{
Labels: []prompb.Label{{Name: "__name__", Value: alertForStateMetricName}, {Name: "a1", Value: "b1"}, {Name: "a2", Value: "b2"}, {Name: "a3", Value: "b3"}, {Name: "alertname", Value: "for-pending=>empty"}, {Name: "name", Value: "foo"}},
Samples: []prompb.Sample{{Value: float64(ts.Unix()), Timestamp: ts.UnixNano() / 1e6}},
Labels: []prompbmarshal.Label{{Name: "__name__", Value: alertForStateMetricName}, {Name: "a1", Value: "b1"}, {Name: "a2", Value: "b2"}, {Name: "a3", Value: "b3"}, {Name: "alertname", Value: "for-pending=>empty"}, {Name: "name", Value: "foo"}},
Samples: []prompbmarshal.Sample{{Value: float64(ts.Unix()), Timestamp: ts.UnixNano() / 1e6}},
},
},
1: {
{
Labels: []prompb.Label{{Name: "__name__", Value: alertMetricName}, {Name: "a1", Value: "b1"}, {Name: "a2", Value: "b2"}, {Name: "a3", Value: "b3"}, {Name: "alertname", Value: "for-pending=>empty"}, {Name: "alertstate", Value: "pending"}, {Name: "name", Value: "foo"}},
Samples: []prompb.Sample{{Value: 1, Timestamp: ts.Add(defaultStep).UnixNano() / 1e6}},
Labels: []prompbmarshal.Label{{Name: "__name__", Value: alertMetricName}, {Name: "a1", Value: "b1"}, {Name: "a2", Value: "b2"}, {Name: "a3", Value: "b3"}, {Name: "alertname", Value: "for-pending=>empty"}, {Name: "alertstate", Value: "pending"}, {Name: "name", Value: "foo"}},
Samples: []prompbmarshal.Sample{{Value: 1, Timestamp: ts.Add(defaultStep).UnixNano() / 1e6}},
},
{
Labels: []prompb.Label{{Name: "__name__", Value: alertForStateMetricName}, {Name: "a1", Value: "b1"}, {Name: "a2", Value: "b2"}, {Name: "a3", Value: "b3"}, {Name: "alertname", Value: "for-pending=>empty"}, {Name: "name", Value: "foo"}},
Samples: []prompb.Sample{{Value: float64(ts.Unix()), Timestamp: ts.Add(defaultStep).UnixNano() / 1e6}},
Labels: []prompbmarshal.Label{{Name: "__name__", Value: alertForStateMetricName}, {Name: "a1", Value: "b1"}, {Name: "a2", Value: "b2"}, {Name: "a3", Value: "b3"}, {Name: "alertname", Value: "for-pending=>empty"}, {Name: "name", Value: "foo"}},
Samples: []prompbmarshal.Sample{{Value: float64(ts.Unix()), Timestamp: ts.Add(defaultStep).UnixNano() / 1e6}},
},
},
// stale time series for `pending -> inactive`
2: {
{
Labels: []prompb.Label{{Name: "__name__", Value: alertMetricName}, {Name: "a1", Value: "b1"}, {Name: "a2", Value: "b2"}, {Name: "a3", Value: "b3"}, {Name: "alertname", Value: "for-pending=>empty"}, {Name: "alertstate", Value: "pending"}, {Name: "name", Value: "foo"}},
Samples: []prompb.Sample{{Value: decimal.StaleNaN, Timestamp: ts.Add(2*defaultStep).UnixNano() / 1e6}},
Labels: []prompbmarshal.Label{{Name: "__name__", Value: alertMetricName}, {Name: "a1", Value: "b1"}, {Name: "a2", Value: "b2"}, {Name: "a3", Value: "b3"}, {Name: "alertname", Value: "for-pending=>empty"}, {Name: "alertstate", Value: "pending"}, {Name: "name", Value: "foo"}},
Samples: []prompbmarshal.Sample{{Value: decimal.StaleNaN, Timestamp: ts.Add(2*defaultStep).UnixNano() / 1e6}},
},
{
Labels: []prompb.Label{{Name: "__name__", Value: alertForStateMetricName}, {Name: "a1", Value: "b1"}, {Name: "a2", Value: "b2"}, {Name: "a3", Value: "b3"}, {Name: "alertname", Value: "for-pending=>empty"}, {Name: "name", Value: "foo"}},
Samples: []prompb.Sample{{Value: decimal.StaleNaN, Timestamp: ts.Add(2*defaultStep).UnixNano() / 1e6}},
Labels: []prompbmarshal.Label{{Name: "__name__", Value: alertForStateMetricName}, {Name: "a1", Value: "b1"}, {Name: "a2", Value: "b2"}, {Name: "a3", Value: "b3"}, {Name: "alertname", Value: "for-pending=>empty"}, {Name: "name", Value: "foo"}},
Samples: []prompbmarshal.Sample{{Value: decimal.StaleNaN, Timestamp: ts.Add(2*defaultStep).UnixNano() / 1e6}},
},
},
})
f(newTestAlertingRuleWithCustomFields("for-pending=>firing=>inactive=>pending=>firing", defaultStep, 0, 0, map[string]string{"activeAt": "{{ $activeAt.UnixMilli }}"}), [][]datasource.Metric{
f(newTestAlertingRule("for-pending=>firing=>inactive=>pending=>firing", defaultStep), [][]datasource.Metric{
{metricWithLabels(t, "name", "foo")},
{metricWithLabels(t, "name", "foo")},
// empty step to set alert inactive
@@ -539,11 +530,11 @@ 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, Annotations: map[string]string{"activeAt": strconv.FormatInt(ts.UnixMilli(), 10)}}}},
1: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateFiring, Annotations: map[string]string{"activeAt": strconv.FormatInt(ts.UnixMilli(), 10)}}}},
2: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateInactive, Annotations: map[string]string{"activeAt": strconv.FormatInt(ts.UnixMilli(), 10)}}}},
3: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StatePending, Annotations: map[string]string{"activeAt": strconv.FormatInt(ts.Add(defaultStep*3).UnixMilli(), 10)}}}},
4: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateFiring, Annotations: map[string]string{"activeAt": strconv.FormatInt(ts.Add(defaultStep*3).UnixMilli(), 10)}}}},
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}}},
}, nil)
f(newTestAlertingRuleWithCustomFields("for-pending=>firing=>keepfiring=>firing", defaultStep, 0, defaultStep, nil), [][]datasource.Metric{
@@ -597,7 +588,7 @@ func TestAlertingRuleExecRange(t *testing.T) {
if err != nil {
t.Fatalf("unexpected error: %s", err)
}
var expTS []prompb.TimeSeries
var expTS []prompbmarshal.TimeSeries
var j int
for _, series := range data {
for _, timestamp := range series.Timestamps {
@@ -737,7 +728,7 @@ func TestAlertingRuleExecRange(t *testing.T) {
{Values: []float64{1, 1, 1}, Timestamps: []int64{1, 3, 5}},
{
Values: []float64{1, 1}, Timestamps: []int64{1, 5},
Labels: []prompb.Label{{Name: "foo", Value: "bar"}},
Labels: []prompbmarshal.Label{{Name: "foo", Value: "bar"}},
},
}, []*notifier.Alert{
{State: notifier.StatePending, ActiveAt: time.Unix(1, 0)},
@@ -785,7 +776,7 @@ func TestAlertingRuleExecRange(t *testing.T) {
{Values: []float64{1, 1}, Timestamps: []int64{1, 100}},
{
Values: []float64{1, 1}, Timestamps: []int64{1, 5},
Labels: []prompb.Label{{Name: "foo", Value: "bar"}},
Labels: []prompbmarshal.Label{{Name: "foo", Value: "bar"}},
},
}, []*notifier.Alert{
{
@@ -827,9 +818,12 @@ func TestGroup_Restore(t *testing.T) {
fg := NewGroup(config.Group{Name: "TestRestore", Rules: rules}, fqr, time.Second, nil)
fg.Init()
wg := sync.WaitGroup{}
wg.Go(func() {
fg.Start(context.Background(), nil, fqr)
})
wg.Add(1)
go func() {
nts := func() []notifier.Notifier { return []notifier.Notifier{&notifier.FakeNotifier{}} }
fg.Start(context.Background(), nts, nil, fqr)
wg.Done()
}()
fg.Close()
wg.Wait()
@@ -1359,7 +1353,7 @@ func newTestAlertingRuleWithCustomFields(name string, waitFor, evalInterval, kee
func TestAlertingRule_ToLabels(t *testing.T) {
metric := datasource.Metric{
Labels: []prompb.Label{
Labels: []prompbmarshal.Label{
{Name: "instance", Value: "0.0.0.0:8800"},
{Name: "group", Value: "vmalert"},
{Name: "alertname", Value: "ConfigurationReloadFailure"},
@@ -1370,10 +1364,8 @@ func TestAlertingRule_ToLabels(t *testing.T) {
ar := &AlertingRule{
Labels: map[string]string{
"instance": "override", // this should override instance with new value
"group": "vmalert", // this shouldn't have effect since value in metric is equal
"invalid_label": "{{ .Values.mustRuntimeFail }}",
"empty_label": "", // this should be dropped
"instance": "override", // this should override instance with new value
"group": "vmalert", // this shouldn't have effect since value in metric is equal
},
Expr: "sum(vmalert_alerting_rules_error) by(instance, group, alertname) > 0",
Name: "AlertingRulesError",
@@ -1381,11 +1373,10 @@ func TestAlertingRule_ToLabels(t *testing.T) {
}
expectedOriginLabels := map[string]string{
"instance": "0.0.0.0:8800",
"group": "vmalert",
"alertname": "ConfigurationReloadFailure",
"alertgroup": "vmalert",
"invalid_label": `error evaluating template: template: :1:268: executing "" at <.Values.mustRuntimeFail>: can't evaluate field Values in type notifier.tplData`,
"instance": "0.0.0.0:8800",
"group": "vmalert",
"alertname": "ConfigurationReloadFailure",
"alertgroup": "vmalert",
}
expectedProcessedLabels := map[string]string{
@@ -1395,12 +1386,11 @@ func TestAlertingRule_ToLabels(t *testing.T) {
"exported_alertname": "ConfigurationReloadFailure",
"group": "vmalert",
"alertgroup": "vmalert",
"invalid_label": `error evaluating template: template: :1:268: executing "" at <.Values.mustRuntimeFail>: can't evaluate field Values in type notifier.tplData`,
}
ls, err := ar.toLabels(metric, nil)
if err == nil || !strings.Contains(err.Error(), "error evaluating template") {
t.Fatalf("unexpected error %q", err.Error())
if err != nil {
t.Fatalf("unexpected error: %s", err)
}
if !reflect.DeepEqual(ls.origin, expectedOriginLabels) {
@@ -1431,142 +1421,3 @@ func TestAlertingRuleExec_Partial(t *testing.T) {
t.Fatalf("unexpected error: %s", err)
}
}
func TestAlertingRule_QueryTemplateInLabels(t *testing.T) {
fq := &datasource.FakeQuerier{}
fakeGroup := Group{
Name: "TestQueryTemplateInLabels",
}
ar := &AlertingRule{
Name: "test_alert",
Labels: map[string]string{
"suppress_for_mass_alert": `{{ if (printf "ALERTS{alertname='SomeAlert', alertstate='firing', device='%s'} == 1" $labels.device | query) }}true{{ else }}false{{ end }}`,
},
Annotations: map[string]string{
"summary": "Test alert with query template in labels",
},
alerts: make(map[uint64]*notifier.Alert),
}
ar.GroupID = fakeGroup.GetID()
ar.q = fq
ar.state = &ruleState{
entries: make([]StateEntry, 10),
}
// Add a metric that should trigger the alert
fq.Add(metricWithValueAndLabels(t, 1, "device", "sda1"))
ts := time.Now()
_, err := ar.exec(context.TODO(), ts, 0)
if err != nil {
t.Fatalf("unexpected error with query template in labels: %s", err)
}
// Verify that the alert was created and the query template was executed
if len(ar.alerts) != 1 {
t.Fatalf("expected 1 alert, got %d", len(ar.alerts))
}
alert := ar.GetAlerts()[0]
suppressLabel, exists := alert.Labels["suppress_for_mass_alert"]
if !exists {
t.Fatalf("expected 'suppress_for_mass_alert' label to exist")
}
// The query template should have been executed (even if it returns false due to mock data)
if suppressLabel != "true" && suppressLabel != "false" {
t.Fatalf("expected 'suppress_for_mass_alert' label to be 'true' or 'false', got '%s'", suppressLabel)
}
}
// TestAlertingRule_ActiveAtPreservedInAnnotations ensures that the fix for
// https://github.com/VictoriaMetrics/VictoriaMetrics/issues/9543 is preserved
// while allowing query templates in labels (https://github.com/VictoriaMetrics/VictoriaMetrics/issues/9783)
func TestAlertingRule_ActiveAtPreservedInAnnotations(t *testing.T) {
// wrap into synctest because of time manipulations
synctest.Test(t, func(t *testing.T) {
fq := &datasource.FakeQuerier{}
ar := &AlertingRule{
Name: "TestActiveAtPreservation",
Labels: map[string]string{
"test_query_in_label": `{{ "static_value" }}`,
},
Annotations: map[string]string{
"description": "Alert active since {{ $activeAt }}",
},
alerts: make(map[uint64]*notifier.Alert),
q: fq,
state: &ruleState{
entries: make([]StateEntry, 10),
},
}
// Mock query result - return empty result to make suppress_for_mass_alert = false
// (no need to add anything to fq for empty result)
// Add a metric that should trigger the alert
fq.Add(metricWithValueAndLabels(t, 1, "instance", "server1"))
// First execution - creates new alert
ts1 := time.Now()
_, err := ar.exec(context.TODO(), ts1, 0)
if err != nil {
t.Fatalf("unexpected error on first exec: %s", err)
}
if len(ar.alerts) != 1 {
t.Fatalf("expected 1 alert, got %d", len(ar.alerts))
}
firstAlert := ar.GetAlerts()[0]
// Verify first execution: activeAt should be ts1 and annotation should reflect it
if !firstAlert.ActiveAt.Equal(ts1) {
t.Fatalf("expected activeAt to be %v, got %v", ts1, firstAlert.ActiveAt)
}
// Extract time from annotation (format will be like "Alert active since 2025-09-30 08:55:13.638551611 -0400 EDT m=+0.002928464")
expectedTimeStr := ts1.Format("2006-01-02 15:04:05")
if !strings.Contains(firstAlert.Annotations["description"], expectedTimeStr) {
t.Fatalf("first exec annotation should contain time %s, got: %s", expectedTimeStr, firstAlert.Annotations["description"])
}
// Second execution - should preserve activeAt in annotation
// Ensure different timestamp with different seconds
// sleep is non-blocking thanks to synctest
time.Sleep(2 * time.Second)
ts2 := time.Now()
_, err = ar.exec(context.TODO(), ts2, 0)
if err != nil {
t.Fatalf("unexpected error on second exec: %s", err)
}
// Get the alert again (should be the same alert)
if len(ar.alerts) != 1 {
t.Fatalf("expected 1 alert, got %d", len(ar.alerts))
}
secondAlert := ar.GetAlerts()[0]
// Critical test: activeAt should still be ts1, not ts2
if !secondAlert.ActiveAt.Equal(ts1) {
t.Fatalf("activeAt should be preserved as %v, but got %v", ts1, secondAlert.ActiveAt)
}
// Critical test: annotation should still contain ts1 time, not ts2
if !strings.Contains(secondAlert.Annotations["description"], expectedTimeStr) {
t.Fatalf("second exec annotation should still contain original time %s, got: %s", expectedTimeStr, secondAlert.Annotations["description"])
}
// Additional verification: annotation should NOT contain ts2 time
ts2TimeStr := ts2.Format("2006-01-02 15:04:05")
if strings.Contains(secondAlert.Annotations["description"], ts2TimeStr) {
t.Fatalf("annotation should NOT contain new eval time %s, got: %s", ts2TimeStr, secondAlert.Annotations["description"])
}
// Verify query template in labels still works (this would fail if query templates were broken)
if firstAlert.Labels["test_query_in_label"] != "static_value" {
t.Fatalf("expected test_query_in_label=static_value, got %s", firstAlert.Labels["test_query_in_label"])
}
})
}

View File

@@ -2,6 +2,7 @@ package rule
import (
"context"
"encoding/json"
"errors"
"flag"
"fmt"
@@ -18,15 +19,12 @@ import (
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/remotewrite"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/vmalertutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
)
var (
ruleResultsLimit = flag.Int("rule.resultsLimit", 0, "Limits the number of alerts or recording results a single rule can produce. "+
"Can be overridden by the limit option under group if specified. "+
"If exceeded, the rule will be marked with an error and all its results will be discarded. "+
"0 means no limit.")
ruleUpdateEntriesLimit = flag.Int("rule.updateEntriesLimit", 20, "Defines the max number of rule's state updates stored in-memory. "+
"Rule's updates are available on rule's Details page and are used for debugging purposes. The number of stored updates can be overridden per rule via update_entries_limit param.")
resendDelay = flag.Duration("rule.resendDelay", 0, "MiniMum amount of time to wait before resending an alert to notifier.")
@@ -38,8 +36,6 @@ var (
disableAlertGroupLabel = flag.Bool("disableAlertgroupLabel", false, "Whether to disable adding group's Name as label to generated alerts and time series.")
remoteReadLookBack = flag.Duration("remoteRead.lookback", time.Hour, "Lookback defines how far to look into past for alerts timeseries. "+
"For example, if lookback=1h then range from now() to now()-1h will be scanned.")
maxStartDelay = flag.Duration("group.maxStartDelay", 5*time.Minute, "Defines the max delay before starting the group evaluation. Group's start is artificially delayed for random duration on interval"+
" [0..min(--group.maxStartDelay, group.interval)]. This helps smoothing out the load on the configured datasource, so evaluations aren't executed too close to each other.")
)
// Group is an entity for grouping rules
@@ -116,6 +112,7 @@ func NewGroup(cfg config.Group, qb datasource.QuerierBuilder, defaultInterval ti
Name: cfg.Name,
File: cfg.File,
Interval: cfg.Interval.Duration(),
Limit: cfg.Limit,
Concurrency: cfg.Concurrency,
checksum: cfg.Checksum,
Params: cfg.Params,
@@ -132,11 +129,6 @@ func NewGroup(cfg config.Group, qb datasource.QuerierBuilder, defaultInterval ti
if g.Interval == 0 {
g.Interval = defaultInterval
}
if cfg.Limit != nil {
g.Limit = *cfg.Limit
} else {
g.Limit = *ruleResultsLimit
}
if g.Concurrency < 1 {
g.Concurrency = 1
}
@@ -297,7 +289,7 @@ func (g *Group) InterruptEval() {
}
}
// Close stops the group and its rules, unregisters group metrics
// Close stops the group and it's rules, unregisters group metrics
func (g *Group) Close() {
if g.doneCh == nil {
return
@@ -306,6 +298,10 @@ func (g *Group) Close() {
g.InterruptEval()
<-g.finishedCh
g.closeGroupMetrics()
}
func (g *Group) closeGroupMetrics() {
metrics.UnregisterSet(g.metrics.set, true)
}
@@ -331,13 +327,13 @@ func (g *Group) Init() {
}
// Start starts group's evaluation
func (g *Group) Start(ctx context.Context, rw remotewrite.RWClient, rr datasource.QuerierBuilder) {
func (g *Group) Start(ctx context.Context, nts func() []notifier.Notifier, rw remotewrite.RWClient, rr datasource.QuerierBuilder) {
defer func() { close(g.finishedCh) }()
evalTS := time.Now()
// sleep random duration to spread group rules evaluation
// over maxStartDelay to reduce the load on datasource.
// over time in order to reduce load on datasource.
if !SkipRandSleepOnGroupStart {
sleepBeforeStart := g.delayBeforeStart(evalTS, *maxStartDelay)
sleepBeforeStart := delayBeforeStart(evalTS, g.GetID(), g.Interval, g.EvalOffset)
g.infof("will start in %v", sleepBeforeStart)
sleepTimer := time.NewTimer(sleepBeforeStart)
@@ -369,6 +365,7 @@ func (g *Group) Start(ctx context.Context, rw remotewrite.RWClient, rr datasourc
e := &executor{
Rw: rw,
Notifiers: nts,
notifierHeaders: g.NotifierHeaders,
}
@@ -475,31 +472,32 @@ func (g *Group) UpdateWith(newGroup *Group) {
g.updateCh <- newGroup
}
// delayBeforeStart returns duration for delaying the evaluation start
// based on given ts and Group settings. The delay can't exceed maxDelay.
// maxDelay is ignored if g.EvalOffset != nil.
//
// Delaying is important to smooth out the load on the datasource when all groups start at the same time.
// delayBeforeStart calculates delay based on Group ID, so all groups will start at different moments of time.
func (g *Group) delayBeforeStart(ts time.Time, maxDelay time.Duration) time.Duration {
if g.EvalOffset != nil {
// if offset is specified, ignore the maxDelay and return a duration aligned with offset
currentOffsetPoint := ts.Truncate(g.Interval).Add(*g.EvalOffset)
// DeepCopy returns a deep copy of group
func (g *Group) DeepCopy() *Group {
g.mu.RLock()
data, _ := json.Marshal(g)
g.mu.RUnlock()
newG := Group{}
_ = json.Unmarshal(data, &newG)
newG.Rules = g.Rules
newG.id = g.id
return &newG
}
// if offset is specified, delayBeforeStart returns a duration to help aligning timestamp with offset;
// otherwise, it returns a random duration between [0..interval] based on group key.
func delayBeforeStart(ts time.Time, key uint64, interval time.Duration, offset *time.Duration) time.Duration {
if offset != nil {
currentOffsetPoint := ts.Truncate(interval).Add(*offset)
if currentOffsetPoint.Before(ts) {
// wait until the next offset point
return currentOffsetPoint.Add(g.Interval).Sub(ts)
return currentOffsetPoint.Add(interval).Sub(ts)
}
return currentOffsetPoint.Sub(ts)
}
// otherwise, return a random duration between [0..min(interval, maxDelay)] based on group ID
interval := g.Interval
if interval > maxDelay {
// artificially limit interval, so groups with big intervals could start sooner.
interval = maxDelay
}
var randSleep time.Duration
randSleep = time.Duration(float64(interval) * (float64(g.GetID()) / (1 << 64)))
randSleep = time.Duration(float64(interval) * (float64(key) / (1 << 64)))
sleepOffset := time.Duration(ts.UnixNano() % interval.Nanoseconds())
if randSleep < sleepOffset {
randSleep += interval
@@ -561,13 +559,15 @@ func (g *Group) Replay(start, end time.Time, rw remotewrite.RWClient, maxDataPoi
if !disableProgressBar {
bar = pb.StartNew(iterations * len(g.Rules))
}
for i := range g.Rules {
rule := g.Rules[i]
for _, r := range g.Rules {
sem <- struct{}{}
wg.Go(func() {
res <- replayRuleRange(rule, ri, bar, rw, replayRuleRetryAttempts, ruleEvaluationConcurrency)
wg.Add(1)
go func(r Rule, ri rangeIterator) {
// pass ri as a copy, so it can be modified within the replayRuleRange
res <- replayRuleRange(r, ri, bar, rw, replayRuleRetryAttempts, ruleEvaluationConcurrency)
<-sem
})
wg.Done()
}(r, ri)
}
wg.Wait()
@@ -587,20 +587,15 @@ func (g *Group) Replay(start, end time.Time, rw remotewrite.RWClient, maxDataPoi
func replayRuleRange(r Rule, ri rangeIterator, bar *pb.ProgressBar, rw remotewrite.RWClient, replayRuleRetryAttempts, ruleEvaluationConcurrency int) int {
fmt.Printf("> Rule %q (ID: %d)\n", r, r.ID())
// alerting rule with for>0 can't be replayed concurrently, since the status change might depend on the previous evaluation
// see https://github.com/VictoriaMetrics/VictoriaMetrics/commit/abcb21aa5ee918ba9a4e9cde495dba06e1e9564c
if r, ok := r.(*AlertingRule); ok && r.For > 0 {
ruleEvaluationConcurrency = 1
}
sem := make(chan struct{}, ruleEvaluationConcurrency)
wg := sync.WaitGroup{}
res := make(chan int, int(ri.end.Sub(ri.start)/ri.step)+1)
for ri.next() {
sem <- struct{}{}
start := ri.s
end := ri.e
wg.Go(func() {
n, err := replayRule(r, start, end, rw, replayRuleRetryAttempts)
wg.Add(1)
go func(s, e time.Time) {
n, err := replayRule(r, s, e, rw, replayRuleRetryAttempts)
if err != nil {
logger.Fatalf("rule %q: %s", r, err)
}
@@ -609,7 +604,8 @@ func replayRuleRange(r Rule, ri rangeIterator, bar *pb.ProgressBar, rw remotewri
}
res <- n
<-sem
})
wg.Done()
}(ri.s, ri.e)
}
wg.Wait()
close(res)
@@ -623,9 +619,10 @@ func replayRuleRange(r Rule, ri rangeIterator, bar *pb.ProgressBar, rw remotewri
}
// ExecOnce evaluates all the rules under group for once with given timestamp.
func (g *Group) ExecOnce(ctx context.Context, rw remotewrite.RWClient, evalTS time.Time) chan error {
func (g *Group) ExecOnce(ctx context.Context, nts func() []notifier.Notifier, rw remotewrite.RWClient, evalTS time.Time) chan error {
e := &executor{
Rw: rw,
Notifiers: nts,
notifierHeaders: g.NotifierHeaders,
}
if len(g.Rules) < 1 {
@@ -700,6 +697,7 @@ func (g *Group) getEvalDelay() time.Duration {
// executor contains group's notify and rw configs
type executor struct {
Notifiers func() []notifier.Notifier
notifierHeaders map[string]string
Rw remotewrite.RWClient
@@ -720,13 +718,14 @@ func (e *executor) execConcurrently(ctx context.Context, rules []Rule, ts time.T
sem := make(chan struct{}, concurrency)
go func() {
wg := sync.WaitGroup{}
for i := range rules {
rule := rules[i]
for _, r := range rules {
sem <- struct{}{}
wg.Go(func() {
res <- e.exec(ctx, rule, ts, resolveDuration, limit)
wg.Add(1)
go func(r Rule) {
res <- e.exec(ctx, r, ts, resolveDuration, limit)
<-sem
})
wg.Done()
}(r)
}
wg.Wait()
close(res)
@@ -756,7 +755,7 @@ func (e *executor) exec(ctx context.Context, r Rule, ts time.Time, resolveDurati
}
if e.Rw != nil {
pushToRW := func(tss []prompb.TimeSeries) error {
pushToRW := func(tss []prompbmarshal.TimeSeries) error {
var lastErr error
for _, ts := range tss {
if err := e.Rw.Push(ts); err != nil {
@@ -780,6 +779,17 @@ func (e *executor) exec(ctx context.Context, r Rule, ts time.Time, resolveDurati
return nil
}
errGr := notifier.Send(ctx, alerts, e.notifierHeaders)
wg := sync.WaitGroup{}
errGr := new(vmalertutil.ErrGroup)
for _, nt := range e.Notifiers() {
wg.Add(1)
go func(nt notifier.Notifier) {
if err := nt.Send(ctx, alerts, e.notifierHeaders); err != nil {
errGr.Add(fmt.Errorf("rule %q: failed to send alerts to addr %q: %w", r, nt.Addr(), err))
}
wg.Done()
}(nt)
}
wg.Wait()
return errGr.Err()
}

View File

@@ -262,7 +262,7 @@ func TestUpdateDuringRandSleep(t *testing.T) {
updateCh: make(chan *Group),
}
g.Init()
go g.Start(context.Background(), nil, nil)
go g.Start(context.Background(), nil, nil, nil)
rule1 := AlertingRule{
Name: "jobDown",
@@ -346,8 +346,7 @@ func TestGroupStart(t *testing.T) {
}
fs := &datasource.FakeQuerier{}
fn, cleanup := notifier.InitFakeNotifier()
defer cleanup()
fn := &notifier.FakeNotifier{}
const evalInterval = time.Millisecond
g := NewGroup(groups[0], fs, evalInterval, map[string]string{"cluster": "east-1"})
@@ -396,7 +395,7 @@ func TestGroupStart(t *testing.T) {
fs.Add(m2)
g.Init()
go func() {
g.Start(context.Background(), nil, fs)
g.Start(context.Background(), func() []notifier.Notifier { return []notifier.Notifier{fn} }, nil, fs)
close(finished)
}()
@@ -473,10 +472,15 @@ func TestFaultyNotifier(t *testing.T) {
r := newTestAlertingRule("instant", 0)
r.q = fq
fn, cleanup := notifier.InitFakeNotifier()
defer cleanup()
e := &executor{}
fn := &notifier.FakeNotifier{}
e := &executor{
Notifiers: func() []notifier.Notifier {
return []notifier.Notifier{
&notifier.FaultyNotifier{},
fn,
}
},
}
delay := 5 * time.Second
ctx, cancel := context.WithTimeout(context.Background(), delay)
defer cancel()
@@ -549,7 +553,7 @@ func TestCloseWithEvalInterruption(t *testing.T) {
g := NewGroup(groups[0], fq, evalInterval, nil)
g.Init()
go g.Start(context.Background(), nil, nil)
go g.Start(context.Background(), nil, nil, nil)
time.Sleep(evalInterval * 20)
@@ -567,10 +571,9 @@ func TestCloseWithEvalInterruption(t *testing.T) {
func TestGroupStartDelay(t *testing.T) {
g := &Group{}
g.id = uint64(math.MaxUint64 / 10)
// interval of 5min and key generate a static delay of 30s
g.Interval = time.Minute * 5
maxDelay := time.Minute * 5
key := uint64(math.MaxUint64 / 10)
f := func(atS, expS string) {
t.Helper()
@@ -582,7 +585,7 @@ func TestGroupStartDelay(t *testing.T) {
if err != nil {
t.Fatal(err)
}
delay := g.delayBeforeStart(at, maxDelay)
delay := delayBeforeStart(at, key, g.Interval, g.EvalOffset)
gotStart := at.Add(delay)
if expTS != gotStart {
t.Fatalf("expected to get %v; got %v instead", expTS, gotStart)
@@ -603,15 +606,6 @@ func TestGroupStartDelay(t *testing.T) {
f("2023-01-01T00:01:00.000+00:00", "2023-01-01T00:03:00.000+00:00")
f("2023-01-01T00:03:30.000+00:00", "2023-01-01T00:08:00.000+00:00")
f("2023-01-01T00:08:00.000+00:00", "2023-01-01T00:08:00.000+00:00")
maxDelay = time.Minute * 1
g.EvalOffset = nil
// test group with maxDelay, and offset disabled
f("2023-01-01T00:00:00.000+00:00", "2023-01-01T00:00:06.000+00:00")
f("2023-01-01T00:00:01.000+00:00", "2023-01-01T00:00:06.000+00:00")
f("2023-01-01T00:00:06.100+00:00", "2023-01-01T00:01:06.000+00:00")
f("2023-01-01T00:00:11.000+00:00", "2023-01-01T00:01:06.000+00:00")
}
func TestGetPrometheusReqTimestamp(t *testing.T) {

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