Compare commits

..

3 Commits

Author SHA1 Message Date
Max Kotliar
12e0b8a184 prompt 2026-06-16 22:56:04 +03:00
Max Kotliar
914f72e062 test code 2026-06-16 22:44:47 +03:00
Max Kotliar
35b7bd90fd sso poc 2026-06-16 22:37:52 +03:00
1141 changed files with 18322 additions and 87881 deletions

0
.codex Normal file
View File

View File

@@ -65,7 +65,7 @@ jobs:
arch: amd64
steps:
- name: Code checkout
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
with:
persist-credentials: false
@@ -73,19 +73,11 @@ jobs:
id: go
uses: actions/setup-go@4a3601121dd01d1626a1e23e37211e3254c1c06c # v6.4.0
with:
cache: false
cache-dependency-path: |
go.sum
Makefile
app/**/Makefile
go-version-file: 'go.mod'
- name: Cache Go build artifacts
uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
with:
path: |
~/.cache/go-build
~/go/pkg/mod
key: go-build-${{ matrix.os }}-${{ matrix.arch }}-${{ hashFiles('go.sum', 'Makefile') }}
restore-keys: |
go-build-${{ matrix.os }}-${{ matrix.arch }}-
- run: go version
- name: Build victoria-metrics for ${{ matrix.os }}-${{ matrix.arch }}

View File

@@ -13,7 +13,7 @@ jobs:
contents: read
runs-on: 'ubuntu-latest'
steps:
- uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
with:
# needed for proper diff
fetch-depth: 0

View File

@@ -12,7 +12,7 @@ jobs:
runs-on: ubuntu-latest
steps:
- name: Checkout code
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
with:
fetch-depth: 0 # we need full history for commit verification
persist-credentials: false

View File

@@ -17,7 +17,7 @@ jobs:
runs-on: ubuntu-latest
steps:
- name: Code checkout
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
with:
persist-credentials: false

View File

@@ -31,7 +31,7 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
with:
persist-credentials: false
@@ -54,14 +54,14 @@ jobs:
restore-keys: go-artifacts-${{ runner.os }}-codeql-analyze-${{ steps.go.outputs.go-version }}-
- name: Initialize CodeQL
uses: github/codeql-action/init@54f647b7e1bb85c95cddabcd46b0c578ec92bc1a # v4.36.3
uses: github/codeql-action/init@e46ed2cbd01164d986452f91f178727624ae40d7 # v4.35.3
with:
languages: go
- name: Autobuild
uses: github/codeql-action/autobuild@54f647b7e1bb85c95cddabcd46b0c578ec92bc1a # v4.36.3
uses: github/codeql-action/autobuild@e46ed2cbd01164d986452f91f178727624ae40d7 # v4.35.3
- name: Perform CodeQL Analysis
uses: github/codeql-action/analyze@54f647b7e1bb85c95cddabcd46b0c578ec92bc1a # v4.36.3
uses: github/codeql-action/analyze@e46ed2cbd01164d986452f91f178727624ae40d7 # v4.35.3
with:
category: 'language:go'

View File

@@ -18,13 +18,13 @@ jobs:
runs-on: ubuntu-latest
steps:
- name: Code checkout
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
with:
path: __vm
persist-credentials: false
- name: Checkout private code
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
with:
repository: VictoriaMetrics/vmdocs
token: ${{ secrets.VM_BOT_GH_TOKEN }}

View File

@@ -34,7 +34,7 @@ jobs:
runs-on: 'vm-runner'
steps:
- name: Code checkout
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
with:
persist-credentials: false
@@ -79,7 +79,7 @@ jobs:
steps:
- name: Code checkout
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
with:
persist-credentials: false
@@ -106,7 +106,7 @@ jobs:
steps:
- name: Code checkout
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
with:
persist-credentials: false

View File

@@ -26,11 +26,13 @@ jobs:
vmui-checks:
name: VMUI Checks (lint, test, typecheck)
permissions:
checks: write
contents: read
pull-requests: read
runs-on: ubuntu-latest
steps:
- name: Code checkout
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
with:
persist-credentials: false
@@ -68,6 +70,12 @@ jobs:
env:
VMUI_SKIP_INSTALL: true
- name: Annotate Code Linting Results
uses: ataylorme/eslint-annotate-action@d57a1193d4c59cbfbf3f86c271f42612f9dbd9e9 # 3.0.0
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 }}"

View File

@@ -23,4 +23,3 @@ linters:
text: 'SA(4003|1019|5011):'
paths:
- ^app/vmui/
- app/vmui/packages/vmui/node_modules/

View File

@@ -447,7 +447,7 @@ vet:
go vet ./app/...
go vet ./apptest/...
check-all: fmt vet golangci-lint
check-all: fmt vet golangci-lint govulncheck
clean-checkers: remove-golangci-lint remove-govulncheck
@@ -471,9 +471,8 @@ test-full-386:
apptest:
$(MAKE) victoria-metrics-race vmagent-race vmalert-race vmauth-race vmctl-race vmbackup-race vmrestore-race
go test ./apptest/... -skip="^Test(Cluster|Mixed|Legacy).*"
go test ./apptest/... -skip="^Test(Cluster|Legacy).*"
# App tests for legacy indexDB
apptest-legacy: victoria-metrics-race vmbackup-race vmrestore-race
OS=$$(uname | tr '[:upper:]' '[:lower:]'); \
ARCH=$$(uname -m | tr '[:upper:]' '[:lower:]' | sed 's/x86_64/amd64/'); \
@@ -490,22 +489,6 @@ apptest-legacy: victoria-metrics-race vmbackup-race vmrestore-race
VMSTORAGE_V1_132_0_PATH=$${DIR}/vmstorage-prod \
go test ./apptest/tests -run="^TestLegacySingle.*"
# App tests for mixed setups where vmsingle and vmcluster coexist.
apptest-mixed: victoria-metrics-race
OS=$$(uname | tr '[:upper:]' '[:lower:]'); \
ARCH=$$(uname -m | tr '[:upper:]' '[:lower:]' | sed 's/x86_64/amd64/'); \
VERSION=v1.147.0; \
VMSINGLE=victoria-metrics-$${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 $${DIR} \
); \
VMSELECT_PATH=$${DIR}/vmselect-prod \
go test ./apptest/tests -run="^TestMixed.*"
benchmark:
go test -run=NO_TESTS -bench=. ./lib/...
go test -run=NO_TESTS -bench=. ./app/...

View File

@@ -2,6 +2,7 @@
[![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)](https://hub.docker.com/u/victoriametrics)
[![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)
[![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)
[![Join Slack](https://img.shields.io/badge/Join%20Slack-4A154B?logo=slack)](https://slack.victoriametrics.com)
@@ -41,8 +42,8 @@ VictoriaMetrics is optimized for timeseries data, even when old time series are
* **Ideal for big data**: Works well with large amounts of time series data from APM, Kubernetes, IoT sensors, connected cars, industrial telemetry, financial data and various [Enterprise workloads](https://docs.victoriametrics.com/victoriametrics/enterprise/).
* **Query language**: Supports both PromQL and the more performant MetricsQL.
* **Easy to setup**: No dependencies, single [small binary](https://medium.com/@valyala/stripping-dependency-bloat-in-victoriametrics-docker-image-983fb5912b0d), configuration through command-line flags, but the default is also fine-tuned; backup and restore with [instant snapshots](https://medium.com/@valyala/how-victoriametrics-makes-instant-snapshots-for-multi-terabyte-time-series-data-e1f3fb0e0282).
* **Global query view**: Multiple Prometheus instances or any other data sources may ingest data into VictoriaMetrics and be queried via a single query.
* **Various Protocols**: Support metric scraping, ingestion and backfilling in various protocols.
* **Global query view**: Multiple Prometheus instances or any other data sources may ingest data into VictoriaMetrics and queried via a single query.
* **Various Protocols**: Support metric scraping, ingestion and backfilling in various protocol.
* [Prometheus exporters](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#how-to-scrape-prometheus-exporters-such-as-node-exporter), [Prometheus remote write API](https://docs.victoriametrics.com/victoriametrics/integrations/prometheus/), [Prometheus exposition format](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#how-to-import-data-in-prometheus-exposition-format).
* [InfluxDB line protocol](https://docs.victoriametrics.com/victoriametrics/integrations/influxdb/) over HTTP, TCP and UDP.
* [Graphite plaintext protocol](https://docs.victoriametrics.com/victoriametrics/integrations/graphite/#ingesting) with [tags](https://graphite.readthedocs.io/en/latest/tags.html#carbon).
@@ -78,7 +79,7 @@ We strictly apply security measures in everything we do. VictoriaMetrics has ach
Some good benchmarks VictoriaMetrics achieved:
* **Minimal memory footprint**: handling millions of unique timeseries with [10x less RAM](https://medium.com/@valyala/insert-benchmarks-with-inch-influxdb-vs-victoriametrics-e31a41ae2893) than InfluxDB, up to [7x less RAM](https://valyala.medium.com/prometheus-vs-victoriametrics-benchmark-on-node-exporter-metrics-4ca29c75590f) than Prometheus, Thanos or Cortex.
* **Highly scalable and performant** for [data ingestion](https://medium.com/@valyala/high-cardinality-tsdb-benchmarks-victoriametrics-vs-timescaledb-vs-influxdb-13e6ee64dd6b) and [querying](https://medium.com/@valyala/when-size-matters-benchmarking-victoriametrics-vs-timescale-and-influxdb-6035811952d4), [20x outperforms](https://medium.com/@valyala/insert-benchmarks-with-inch-influxdb-vs-victoriametrics-e31a41ae2893) InfluxDB and TimescaleDB.
* **Highly scalable and performance** for [data ingestion](https://medium.com/@valyala/high-cardinality-tsdb-benchmarks-victoriametrics-vs-timescaledb-vs-influxdb-13e6ee64dd6b) and [querying](https://medium.com/@valyala/when-size-matters-benchmarking-victoriametrics-vs-timescale-and-influxdb-6035811952d4), [20x outperforms](https://medium.com/@valyala/insert-benchmarks-with-inch-influxdb-vs-victoriametrics-e31a41ae2893) InfluxDB and TimescaleDB.
* **High data compression**: [70x more data points](https://medium.com/@valyala/when-size-matters-benchmarking-victoriametrics-vs-timescale-and-influxdb-6035811952d4) may be stored into limited storage than TimescaleDB, [7x less storage](https://valyala.medium.com/prometheus-vs-victoriametrics-benchmark-on-node-exporter-metrics-4ca29c75590f) space is required than Prometheus, Thanos or Cortex.
* **Reducing storage costs**: [10x more effective](https://docs.victoriametrics.com/victoriametrics/casestudies/#grammarly) than Graphite according to the Grammarly case study.
* **A single-node VictoriaMetrics** can replace medium-sized clusters built with competing solutions such as Thanos, M3DB, Cortex, InfluxDB or TimescaleDB. See [VictoriaMetrics vs Thanos](https://medium.com/@valyala/comparing-thanos-to-victoriametrics-cluster-b193bea1683), [Measuring vertical scalability](https://medium.com/@valyala/measuring-vertical-scalability-for-time-series-databases-in-google-cloud-92550d78d8ae), [Remote write storage wars - PromCon 2019](https://promcon.io/2019-munich/talks/remote-write-storage-wars/).
@@ -86,7 +87,7 @@ Some good benchmarks VictoriaMetrics achieved:
## Community and contributions
Feel free to ask any questions regarding VictoriaMetrics:
Feel free asking any questions regarding VictoriaMetrics:
* [Slack Inviter](https://slack.victoriametrics.com/) and [Slack channel](https://victoriametrics.slack.com/)
* [X (Twitter)](https://x.com/VictoriaMetrics/)

View File

@@ -22,7 +22,6 @@ import (
"github.com/VictoriaMetrics/VictoriaMetrics/lib/procutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promscrape"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/pushmetrics"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/querytracer/push"
)
var (
@@ -64,7 +63,6 @@ func main() {
flag.CommandLine.SetOutput(os.Stdout)
flag.Usage = usage
envflag.Parse()
initSecretFlags()
buildinfo.Init()
logger.Init()
@@ -91,7 +89,7 @@ func main() {
}
logger.Infof("starting VictoriaMetrics at %q...", listenAddrs)
startTime := time.Now()
vmstorage.Init(*vmselectMaxConcurrentRequests, *vmselectMaxQueueDuration, promql.ResetRollupResultCacheIfNeeded)
vmstorage.Init(*vmselectMaxConcurrentRequests, promql.ResetRollupResultCacheIfNeeded)
vmselect.Init(*vmselectMaxConcurrentRequests, *vmselectMaxQueueDuration)
vminsertcommon.StartIngestionRateLimiter(*maxIngestionRate)
vminsert.Init()
@@ -104,10 +102,8 @@ func main() {
logger.Infof("started VictoriaMetrics in %.3f seconds", time.Since(startTime).Seconds())
pushmetrics.Init()
push.Init()
sig := procutil.WaitForSigterm()
logger.Infof("received signal %s", sig)
push.Stop()
pushmetrics.Stop()
stopSelfScraper()
@@ -174,9 +170,3 @@ See the docs at https://docs.victoriametrics.com/victoriametrics/
`
flagutil.Usage(s)
}
// initSecretFlags manages the secret flags for this app and must be called after flag parsing and before logger init.
func initSecretFlags() {
pushmetrics.InitSecretFlags()
vmselect.InitSecretFlags()
}

View File

@@ -51,7 +51,7 @@ func InsertHandlerForHTTP(at *auth.Token, req *http.Request) error {
}
q := req.URL.Query()
precision := q.Get("precision")
// Read db tag from https://docs.influxdata.com/influxdb/v1/api/write/#operation/PostWrite
// Read db tag from https://docs.influxdata.com/influxdb/v1.7/tools/api/#write-http-endpoint
db := q.Get("db")
encoding := req.Header.Get("Content-Encoding")
isStreamMode := req.Header.Get("Stream-Mode") == "1"

View File

@@ -84,7 +84,7 @@ var (
maxLabelNameLen = flag.Int("maxLabelNameLen", 0, "The maximum length of label names in the accepted time series. Series with longer label name are ignored. In this case the vm_rows_ignored_total{reason=\"too_long_label_name\"} metric at /metrics page is incremented")
maxLabelValueLen = flag.Int("maxLabelValueLen", 0, "The maximum length of label values in the accepted time series. Series with longer label value are ignored. In this case the vm_rows_ignored_total{reason=\"too_long_label_value\"} metric at /metrics page is incremented")
enableMultitenancyViaHeaders = flag.Bool("enableMultitenancyViaHeaders", true, "Enables multitenancy via HTTP headers. "+
enableMultitenancyViaHeaders = flag.Bool("enableMultitenancyViaHeaders", false, "Enables multitenancy via HTTP headers. "+
"See https://docs.victoriametrics.com/victoriametrics/vmagent/#multitenancy")
)
@@ -115,7 +115,7 @@ func main() {
flag.CommandLine.SetOutput(os.Stdout)
flag.Usage = usage
envflag.Parse()
initSecretFlags()
remotewrite.InitSecretFlags()
buildinfo.Init()
logger.Init()
opentelemetry.Init()
@@ -462,9 +462,7 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
return true
case "/prometheus/metric-relabel-debug", "/metric-relabel-debug":
promscrapeMetricRelabelDebugRequests.Inc()
rwGlobalRelabelConfigs := remotewrite.GetRemoteWriteRelabelConfigString()
rwURLRelabelConfigss := remotewrite.GetURLRelabelConfigString()
promscrape.WriteMetricRelabelDebug(w, r, rwGlobalRelabelConfigs, rwURLRelabelConfigss)
promscrape.WriteMetricRelabelDebug(w, r)
return true
case "/prometheus/target-relabel-debug", "/target-relabel-debug":
promscrapeTargetRelabelDebugRequests.Inc()
@@ -843,9 +841,3 @@ See the docs at https://docs.victoriametrics.com/victoriametrics/vmagent/ .
`
flagutil.Usage(s)
}
// initSecretFlags manages the secret flags for this app and must be called after flag parsing and before logger init.
func initSecretFlags() {
remotewrite.InitSecretFlags()
pushmetrics.InitSecretFlags()
}

View File

@@ -63,7 +63,6 @@ func insertRows(at *auth.Token, tss []prompb.TimeSeries, mms []prompb.MetricMeta
rowsTotal := 0
tssDst := ctx.WriteRequest.Timeseries[:0]
mmsDst := ctx.WriteRequest.Metadata[:0]
labels := ctx.Labels[:0]
samples := ctx.Samples[:0]
for i := range tss {
@@ -83,19 +82,7 @@ func insertRows(at *auth.Token, tss []prompb.TimeSeries, mms []prompb.MetricMeta
var metadataTotal int
if prommetadata.IsEnabled() {
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: mm.AccountID,
ProjectID: mm.ProjectID,
})
}
ctx.WriteRequest.Metadata = mmsDst
ctx.WriteRequest.Metadata = mms
metadataTotal = len(mms)
}

View File

@@ -52,7 +52,6 @@ func setUp() {
func tearDown() {
protoparserutil.StopUnmarshalWorkers()
remotewrite.Stop()
srv.Close()
logger.ResetOutputForTest()
tmpDataDir := flag.Lookup("remoteWrite.tmpDataPath").Value.String()

View File

@@ -35,9 +35,6 @@ func InsertHandler(at *auth.Token, req *http.Request) error {
}
func insertRows(at *auth.Token, timeseries []prompb.TimeSeries, mms []prompb.MetricMetadata, extraLabels []prompb.Label) error {
if len(extraLabels) == 0 && !prommetadata.IsEnabled() && at == nil {
return insertRowsFast(at, timeseries)
}
ctx := common.GetPushCtx()
defer common.PutPushCtx(ctx)
@@ -105,17 +102,3 @@ func insertRows(at *auth.Token, timeseries []prompb.TimeSeries, mms []prompb.Met
rowsPerInsert.Update(float64(rowsTotal))
return nil
}
func insertRowsFast(at *auth.Token, timeseries []prompb.TimeSeries) error {
rowsTotal := 0
for i := range timeseries {
rowsTotal += len(timeseries[i].Samples)
}
wr := &prompb.WriteRequest{Timeseries: timeseries}
if !remotewrite.TryPush(at, wr) {
return remotewrite.ErrQueueFullHTTPRetry
}
rowsInserted.Add(rowsTotal)
rowsPerInsert.Update(float64(rowsTotal))
return nil
}

View File

@@ -151,23 +151,17 @@ func newHTTPClient(argIdx int, remoteWriteURL, sanitizedURL string, fq *persiste
}
tr.Proxy = http.ProxyURL(pu)
}
hc := &http.Client{
Transport: authCfg.NewRoundTripper(tr),
Timeout: sendTimeout.GetOptionalArg(argIdx),
}
rwURL, err := url.Parse(remoteWriteURL)
if err != nil {
logger.Fatalf("BUG: cannot parse already parsed -remoteWrite.url=%q: %s", remoteWriteURL, err)
}
hc.Transport, rwURL = httputil.NewLoadBalancerTransport(hc.Transport, rwURL)
retryMaxIntervalFlag := retryMaxTime
if retryMaxInterval.String() != "" {
retryMaxIntervalFlag = retryMaxInterval
}
c := &client{
sanitizedURL: sanitizedURL,
remoteWriteURL: rwURL.String(),
remoteWriteURL: remoteWriteURL,
authCfg: authCfg,
awsCfg: awsCfg,
fq: fq,
@@ -193,7 +187,7 @@ func newHTTPClient(argIdx int, remoteWriteURL, sanitizedURL string, fq *persiste
return c
}
func (c *client) init(argIdx int, sanitizedURL string) {
func (c *client) init(argIdx, concurrency int, sanitizedURL string) {
limitReached := metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_rate_limit_reached_total{url=%q}`, c.sanitizedURL))
if bytesPerSec := rateLimit.GetOptionalArg(argIdx); bytesPerSec > 0 {
logger.Infof("applying %d bytes per second rate limit for -remoteWrite.url=%q", bytesPerSec, sanitizedURL)
@@ -210,20 +204,11 @@ func (c *client) init(argIdx int, sanitizedURL string) {
c.packetsDropped = metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_packets_dropped_total{url=%q}`, c.sanitizedURL))
c.retriesCount = metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_retries_count_total{url=%q}`, c.sanitizedURL))
c.sendDuration = metrics.GetOrCreateFloatCounter(fmt.Sprintf(`vmagent_remotewrite_send_duration_seconds_total{url=%q}`, c.sanitizedURL))
workers := queues.GetOptionalArg(argIdx)
if workers <= 0 {
workers = 1
}
inmemoryWorkers := inmemoryQueues.GetOptionalArg(argIdx)
for range inmemoryWorkers {
c.wg.Go(func() {
c.runWorker(c.fq.MustReadInMemoryBlockBlocking)
})
}
for range workers {
c.wg.Go(func() {
c.runWorker(c.fq.MustReadBlock)
})
metrics.GetOrCreateGauge(fmt.Sprintf(`vmagent_remotewrite_queues{url=%q}`, c.sanitizedURL), func() float64 {
return float64(concurrency)
})
for range concurrency {
c.wg.Go(c.runWorker)
}
logger.Infof("initialized client for -remoteWrite.url=%q", c.sanitizedURL)
}
@@ -317,12 +302,12 @@ func getAWSAPIConfig(argIdx int) (*awsapi.Config, error) {
return cfg, nil
}
func (c *client) runWorker(readBlock func(dst []byte) ([]byte, bool)) {
func (c *client) runWorker() {
var ok bool
var block []byte
ch := make(chan bool, 1)
for {
block, ok = readBlock(block[:0])
block, ok = c.fq.MustReadBlock(block[:0])
if !ok {
return
}

View File

@@ -1,108 +0,0 @@
package remotewrite
import (
"crypto/sha256"
"encoding/hex"
"slices"
"strings"
"sync"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
)
type obfuscateLabelsCtx struct {
labels []prompb.Label
// buf holds allocations for cached results below
buf []byte
// cacheResults maps original label values to their SHA-256 hex digests,
// avoiding redundant hashing of repeated values within a single batch.
cacheResults map[string]string
}
func (olctx *obfuscateLabelsCtx) reset() {
promrelabel.CleanLabels(olctx.labels)
olctx.labels = olctx.labels[:0]
clear(olctx.cacheResults)
olctx.buf = olctx.buf[:0]
}
var obfuscateLabelsCtxPool = &sync.Pool{
New: func() any {
return &obfuscateLabelsCtx{
cacheResults: make(map[string]string),
}
},
}
func getObfuscateLabelsCtx() *obfuscateLabelsCtx {
return obfuscateLabelsCtxPool.Get().(*obfuscateLabelsCtx)
}
func putObfuscateLabelsCtx(ctx *obfuscateLabelsCtx) {
ctx.reset()
obfuscateLabelsCtxPool.Put(ctx)
}
func (olctx *obfuscateLabelsCtx) obfuscate(tss []prompb.TimeSeries, obfuscateLabels []string) []prompb.TimeSeries {
if len(obfuscateLabels) == 0 || len(tss) == 0 {
return tss
}
labels := olctx.labels
for i := range tss {
ts := &tss[i]
labelsLen := len(labels)
labels = append(labels, ts.Labels...)
found := false
for _, labelName := range obfuscateLabels {
tmp := promrelabel.GetLabelByName(labels[labelsLen:], labelName)
if tmp == nil {
continue
}
found = true
if obfuscatedValue, ok := olctx.cacheResults[tmp.Value]; ok {
// fast path: the obfuscated result was calculated before
tmp.Value = obfuscatedValue
continue
}
digest := sha256.Sum256(bytesutil.ToUnsafeBytes(tmp.Value))
buf := olctx.buf
bufLen := len(buf)
buf = hex.AppendEncode(buf, digest[:])
obfuscatedValue := bytesutil.ToUnsafeString(buf[bufLen:])
olctx.buf = buf
olctx.cacheResults[tmp.Value] = obfuscatedValue
tmp.Value = obfuscatedValue
}
if found {
ts.Labels = labels[labelsLen:]
} else {
labels = labels[:labelsLen]
}
}
olctx.labels = labels
return tss
}
func (rwctx *remoteWriteCtx) initObfuscateLabels() {
if len(*obfuscateLabels) == 0 {
return
}
idx := rwctx.idx
rwObfuscateLabels := obfuscateLabels.GetOptionalArg(idx)
rwObfuscateLabelsList := strings.Split(rwObfuscateLabels, "^^")
for _, label := range rwObfuscateLabelsList {
if label == "" {
continue
}
if !slices.Contains(rwctx.obfuscateLabels, label) {
rwctx.obfuscateLabels = append(rwctx.obfuscateLabels, label)
}
}
}

View File

@@ -1,186 +0,0 @@
package remotewrite
import (
"crypto/sha256"
"encoding/hex"
"reflect"
"testing"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/metrics"
)
func TestRemoteWriteObfuscateLabels(t *testing.T) {
f := func(obfuscateLabelList string, inputTss []prompb.TimeSeries, expectedTss []prompb.TimeSeries) {
t.Helper()
rwctx := &remoteWriteCtx{
idx: 0,
}
olctx := &obfuscateLabelsCtx{
cacheResults: make(map[string]string),
}
defer metrics.UnregisterAllMetrics()
originValue := *obfuscateLabels
defer func() {
*obfuscateLabels = originValue
}()
*obfuscateLabels = []string{obfuscateLabelList}
rwctx.initObfuscateLabels()
outputTss := olctx.obfuscate(inputTss, rwctx.obfuscateLabels)
if !reflect.DeepEqual(expectedTss, outputTss) {
t.Fatalf("unexpected samples;\ngot\n%v\nwant\n%v", outputTss, expectedTss)
}
}
sha256Result := func(str string) string {
sha256Result := sha256.Sum256([]byte(str))
return hex.EncodeToString(sha256Result[:])
}
// 1. obfuscation is not set.
f("",
[]prompb.TimeSeries{
{
Labels: []prompb.Label{
{Name: "ip", Value: "123"},
{Name: "instance", Value: "1234"},
},
Samples: []prompb.Sample{
{Value: 1, Timestamp: 0},
},
},
},
[]prompb.TimeSeries{
{
Labels: []prompb.Label{
{Name: "ip", Value: "123"},
{Name: "instance", Value: "1234"},
},
Samples: []prompb.Sample{
{Value: 1, Timestamp: 0},
},
},
},
)
// 1. obfuscation is set for another rwctx.
f(",ip",
[]prompb.TimeSeries{
{
Labels: []prompb.Label{
{Name: "ip", Value: "123"},
{Name: "instance", Value: "1234"},
},
Samples: []prompb.Sample{
{Value: 1, Timestamp: 0},
},
},
},
[]prompb.TimeSeries{
{
Labels: []prompb.Label{
{Name: "ip", Value: "123"},
{Name: "instance", Value: "1234"},
},
Samples: []prompb.Sample{
{Value: 1, Timestamp: 0},
},
},
},
)
// 2. obfuscate the value of "ip" label
f("ip",
[]prompb.TimeSeries{
{
Labels: []prompb.Label{
{Name: "ip", Value: "123"},
{Name: "instance", Value: "1234"},
},
Samples: []prompb.Sample{
{Value: 1, Timestamp: 0},
},
},
},
[]prompb.TimeSeries{
{
Labels: []prompb.Label{
{Name: "ip", Value: sha256Result("123")},
{Name: "instance", Value: "1234"},
},
Samples: []prompb.Sample{
{Value: 1, Timestamp: 0},
},
},
},
)
// 3. obfuscate the values of "ip" and "instance"
f("ip^^instance",
[]prompb.TimeSeries{
{
Labels: []prompb.Label{
{Name: "ip", Value: "123"},
{Name: "instance", Value: "1234"},
},
Samples: []prompb.Sample{
{Value: 1, Timestamp: 0},
},
},
{
Labels: []prompb.Label{
{Name: "job", Value: "123"},
},
Samples: []prompb.Sample{
{Value: 1, Timestamp: 0},
},
},
},
[]prompb.TimeSeries{
{
Labels: []prompb.Label{
{Name: "ip", Value: sha256Result("123")},
{Name: "instance", Value: sha256Result("1234")},
},
Samples: []prompb.Sample{
{Value: 1, Timestamp: 0},
},
},
{
Labels: []prompb.Label{
{Name: "job", Value: "123"},
},
Samples: []prompb.Sample{
{Value: 1, Timestamp: 0},
},
},
},
)
// 4. duplicate label names in config must produce single SHA-256, not double
f("ip^^ip",
[]prompb.TimeSeries{
{
Labels: []prompb.Label{
{Name: "ip", Value: "123"},
},
Samples: []prompb.Sample{
{Value: 1, Timestamp: 0},
},
},
},
[]prompb.TimeSeries{
{
Labels: []prompb.Label{
{Name: "ip", Value: sha256Result("123")},
},
Samples: []prompb.Sample{
{Value: 1, Timestamp: 0},
},
},
},
)
}

View File

@@ -1,94 +0,0 @@
package remotewrite
import (
"crypto/sha256"
"encoding/hex"
"reflect"
"testing"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/metrics"
)
func BenchmarkRemoteWriteObfuscateLabels(b *testing.B) {
originValue := *obfuscateLabels
defer func() {
*obfuscateLabels = originValue
}()
*obfuscateLabels = []string{"ip^^instance"}
sha256Result := func(str string) string {
sha256Result := sha256.Sum256([]byte(str))
return hex.EncodeToString(sha256Result[:])
}
expected := []prompb.TimeSeries{
{
Labels: []prompb.Label{
{Name: "ip", Value: sha256Result("123")},
{Name: "instance", Value: sha256Result("12345")},
{Name: "__name__", Value: "http_requests_total"},
},
Samples: []prompb.Sample{
{Value: 1, Timestamp: 0},
},
},
{
Labels: []prompb.Label{
{Name: "ip", Value: sha256Result("1236")},
{Name: "instance", Value: sha256Result("some-long-instante-string")},
{Name: "__name__", Value: "concurrent_requests"},
},
Samples: []prompb.Sample{
{Value: 1, Timestamp: 0},
},
},
}
defer metrics.UnregisterAllMetrics()
inputTss := []prompb.TimeSeries{
{
Labels: []prompb.Label{
{Name: "ip", Value: "123"},
{Name: "instance", Value: "12345"},
{Name: "__name__", Value: "http_requests_total"},
},
Samples: []prompb.Sample{
{Value: 1, Timestamp: 0},
},
},
{
Labels: []prompb.Label{
{Name: "ip", Value: "1236"},
{Name: "instance", Value: "some-long-instante-string"},
{Name: "__name__", Value: "concurrent_requests"},
},
Samples: []prompb.Sample{
{Value: 1, Timestamp: 0},
},
},
}
b.ResetTimer()
b.ReportAllocs()
b.RunParallel(func(pb *testing.PB) {
rwctx := &remoteWriteCtx{
idx: 0,
}
olctx := &obfuscateLabelsCtx{
cacheResults: make(map[string]string),
}
rwctx.initObfuscateLabels()
var localTss []prompb.TimeSeries
for pb.Next() {
// always make a shallow copy because obfuscate changes input
localTss = localTss[:0]
localTss = append(localTss, inputTss...)
olctx.reset()
outputTss := olctx.obfuscate(localTss, rwctx.obfuscateLabels)
if !reflect.DeepEqual(expected, outputTss) {
b.Fatalf("unexpected output: got: \n%v\n want: \n%v\n", outputTss, expected)
}
}
})
}

View File

@@ -209,12 +209,13 @@ func (wr *writeRequest) tryPushMetadata(mms []prompb.MetricMetadata) bool {
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
dst.AccountID = src.AccountID
dst.ProjectID = src.ProjectID
// Pre-allocate memory for all string fields.
neededBufLen := len(src.MetricFamilyName) + len(src.Help) + len(src.Unit)
neededBufLen := len(src.MetricFamilyName) + len(src.Help)
bufLen := len(wr.metadatabuf)
wr.metadatabuf = slicesutil.SetLength(wr.metadatabuf, bufLen+neededBufLen)
buf := wr.metadatabuf[:bufLen]
@@ -229,11 +230,6 @@ func (wr *writeRequest) copyMetadata(dst, src *prompb.MetricMetadata) {
buf = append(buf, src.Help...)
dst.Help = bytesutil.ToUnsafeString(buf[bufLen:])
// Copy Unit
bufLen = len(buf)
buf = append(buf, src.Unit...)
dst.Unit = bytesutil.ToUnsafeString(buf[bufLen:])
wr.metadatabuf = buf
}

View File

@@ -12,7 +12,6 @@ import (
"github.com/VictoriaMetrics/metrics"
"gopkg.in/yaml.v2"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/fasttime"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
@@ -83,16 +82,6 @@ func WriteRelabelConfigData(w io.Writer) {
_, _ = w.Write(*p)
}
// GetRemoteWriteRelabelConfigString returns -remoteWrite.relabelConfig contents in string
func GetRemoteWriteRelabelConfigString() string {
var bb bytesutil.ByteBuffer
WriteRelabelConfigData(&bb)
if bb.Len() == 0 {
return ""
}
return string(bb.B)
}
// WriteURLRelabelConfigData writes -remoteWrite.urlRelabelConfig contents to w
func WriteURLRelabelConfigData(w io.Writer) {
p := remoteWriteURLRelabelConfigData.Load()
@@ -119,24 +108,6 @@ func WriteURLRelabelConfigData(w io.Writer) {
_, _ = w.Write(d)
}
// GetURLRelabelConfigString returns -remoteWrite.urlRelabelConfig contents in []string
func GetURLRelabelConfigString() []string {
p := remoteWriteURLRelabelConfigData.Load()
if p == nil {
return nil
}
var ss []string
for i := range *remoteWriteURLs {
cfgData := (*p)[i]
var cfgDataBytes []byte
if cfgData != nil {
cfgDataBytes, _ = yaml.Marshal(cfgData)
}
ss = append(ss, string(cfgDataBytes))
}
return ss
}
func reloadRelabelConfigs() {
rcs := allRelabelConfigs.Load()
if !rcs.isSet() {

View File

@@ -12,18 +12,19 @@ import (
"sync/atomic"
"time"
"github.com/VictoriaMetrics/metrics"
"github.com/cespare/xxhash/v2"
"github.com/VictoriaMetrics/metrics"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/bloomfilter"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/cgroup"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/consistenthash"
"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/mdx"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/memory"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/persistentqueue"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/procutil"
@@ -65,9 +66,6 @@ var (
queues = flagutil.NewArrayInt("remoteWrite.queues", cgroup.AvailableCPUs()*2, "The number of concurrent queues to each -remoteWrite.url. Set more queues if default number of queues "+
"isn't enough for sending high volume of collected data to remote storage. "+
"Default value depends on the number of available CPU cores. It should work fine in most cases since it minimizes resource usage")
inmemoryQueues = flagutil.NewArrayInt("remoteWrite.inmemoryQueues", 0, "The number of additional workers per each -remoteWrite.url, which send only recently ingested data from the in-memory queue, "+
"while the file-based queue at -remoteWrite.tmpDataPath is drained by workers configured via -remoteWrite.queues. "+
"This reduces delivery lag for fresh samples when the file-based queue contains a backlog accumulated during remote storage outages.")
showRemoteWriteURL = flag.Bool("remoteWrite.showURL", false, "Whether to show -remoteWrite.url in the exported metrics. "+
"It is hidden by default, since it can contain sensitive info such as auth key")
maxPendingBytesPerURL = flagutil.NewArrayBytes("remoteWrite.maxDiskUsagePerURL", 0, "The maximum file-based buffer size in bytes at -remoteWrite.tmpDataPath "+
@@ -105,14 +103,6 @@ var (
"cannot be pushed into the configured -remoteWrite.url systems in a timely manner. See https://docs.victoriametrics.com/victoriametrics/vmagent/#disabling-on-disk-persistence")
disableMetadataPerURL = flagutil.NewArrayBool("remoteWrite.disableMetadata", "Whether to disable sending metadata to the corresponding -remoteWrite.url. "+
"By default, metadata sending is controlled by the global -enableMetadata flag")
enableMdx = flagutil.NewArrayBool("remoteWrite.mdx.enable", "Whether to only retain metrics from VictoriaMetrics services before sending them to the corresponding -remoteWrite.url. "+
"Can be combined with -remoteWrite.obfuscateLabels to hide sensitive label values in the forwarded metrics. "+
"Please see https://docs.victoriametrics.com/victoriametrics/vmagent/#monitoring-data-exchange")
obfuscateLabels = flagutil.NewArrayString("remoteWrite.obfuscateLabels", "List of label names whose values will be obfuscated before being sent to the corresponding -remoteWrite.url. "+
"Multiple label names should be separated by `^^`, e.g. \"job^^instance,ip\". "+
"Can be combined with -remoteWrite.mdx.enable to hide sensitive label values in VictoriaMetrics self-monitoring metrics. "+
"Please see https://docs.victoriametrics.com/victoriametrics/vmagent/#obfuscating-label-values")
)
var (
@@ -156,8 +146,7 @@ var maxQueues = cgroup.AvailableCPUs() * 16
const persistentQueueDirname = "persistent-queue"
// InitSecretFlags manages the secret flags for this pkg and must be called by app-level initSecretFlags.
// It should run before logger initialization and package Init() (if exists).
// InitSecretFlags must be called after flag.Parse and before any logging.
func InitSecretFlags() {
if !*showRemoteWriteURL {
// remoteWrite.url can contain authentication codes, so hide it at `/metrics` output.
@@ -170,8 +159,8 @@ func InitSecretFlags() {
}
var (
shardByURLLabelsFilter []string
shardByURLIgnoreLabelsFilter []string
shardByURLLabelsMap map[string]struct{}
shardByURLIgnoreLabelsMap map[string]struct{}
)
// Init initializes remotewrite.
@@ -218,8 +207,8 @@ func Init() {
logger.Fatalf("-remoteWrite.shardByURL.labels and -remoteWrite.shardByURL.ignoreLabels cannot be set simultaneously; " +
"see https://docs.victoriametrics.com/victoriametrics/vmagent/#sharding-among-remote-storages")
}
shardByURLLabelsFilter = slices.Clone(*shardByURLLabels)
shardByURLIgnoreLabelsFilter = slices.Clone(*shardByURLIgnoreLabels)
shardByURLLabelsMap = newMapFromStrings(*shardByURLLabels)
shardByURLIgnoreLabelsMap = newMapFromStrings(*shardByURLIgnoreLabels)
initLabelsGlobal()
@@ -246,8 +235,6 @@ func Init() {
dropDanglingQueues()
// Start config reloader.
configReloaderStopCh = make(chan struct{})
configReloaderWG = sync.WaitGroup{}
configReloaderWG.Go(func() {
for {
select {
@@ -317,10 +304,6 @@ func initRemoteWriteCtxs(urls []string) {
}
fs.RegisterPathFsMetrics(*tmpDataPath)
if slices.Contains(*enableMdx, true) && *shardByURL {
logger.Fatalf("-remoteWrite.mdx.enable and -remoteWrite.shardByURL cannot be set to true simultaneously.")
}
if *shardByURL {
consistentHashNodes := make([]string, 0, len(urls))
for i, url := range urls {
@@ -334,7 +317,7 @@ func initRemoteWriteCtxs(urls []string) {
}
var (
configReloaderStopCh chan struct{}
configReloaderStopCh = make(chan struct{})
configReloaderWG sync.WaitGroup
)
@@ -579,14 +562,6 @@ func tryPushMetadataToRemoteStorages(at *auth.Token, rwctxs []*remoteWriteCtx, m
mm.ProjectID = at.ProjectID
}
}
tmp := mms[:0]
for _, mm := range mms {
if timeserieslimits.IsMetricMetadataExceeding(&mm) {
continue
}
tmp = append(tmp, mm)
}
mms = tmp
// 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.
@@ -720,18 +695,18 @@ func shardAmountRemoteWriteCtx(tssBlock []prompb.TimeSeries, shards [][]prompb.T
for _, ts := range tssBlock {
hashLabels := ts.Labels
if len(shardByURLLabelsFilter) > 0 {
if len(shardByURLLabelsMap) > 0 {
hashLabels = tmpLabels.Labels[:0]
for _, label := range ts.Labels {
if slices.Contains(shardByURLLabelsFilter, label.Name) {
if _, ok := shardByURLLabelsMap[label.Name]; ok {
hashLabels = append(hashLabels, label)
}
}
tmpLabels.Labels = hashLabels
} else if len(shardByURLIgnoreLabelsFilter) > 0 {
} else if len(shardByURLIgnoreLabelsMap) > 0 {
hashLabels = tmpLabels.Labels[:0]
for _, label := range ts.Labels {
if !slices.Contains(shardByURLIgnoreLabelsFilter, label.Name) {
if _, ok := shardByURLIgnoreLabelsMap[label.Name]; !ok {
hashLabels = append(hashLabels, label)
}
}
@@ -832,26 +807,34 @@ var (
// it omits the '=' separator between label name and value for backward compatibility.
// Changing it would re-shard all series across remoteWrite targets.
func getLabelsHashForShard(labels []prompb.Label) uint64 {
var d xxhash.Digest
d.Reset()
bb := labelsHashBufPool.Get()
b := bb.B[:0]
for _, label := range labels {
_, _ = d.WriteString(label.Name)
_, _ = d.WriteString(label.Value)
b = append(b, label.Name...)
b = append(b, label.Value...)
}
return d.Sum64()
h := xxhash.Sum64(b)
bb.B = b
labelsHashBufPool.Put(bb)
return h
}
func getLabelsHash(labels []prompb.Label) uint64 {
var d xxhash.Digest
d.Reset()
bb := labelsHashBufPool.Get()
b := bb.B[:0]
for _, label := range labels {
_, _ = d.WriteString(label.Name)
_, _ = d.WriteString("=")
_, _ = d.WriteString(label.Value)
b = append(b, label.Name...)
b = append(b, '=')
b = append(b, label.Value...)
}
return d.Sum64()
h := xxhash.Sum64(b)
bb.B = b
labelsHashBufPool.Put(bb)
return h
}
var labelsHashBufPool bytesutil.ByteBufferPool
func logSkippedSeries(labels []prompb.Label, flagName string, flagValue int) {
select {
case <-logSkippedSeriesTicker.C:
@@ -876,7 +859,6 @@ type remoteWriteCtx struct {
sas atomic.Pointer[streamaggr.Aggregators]
deduplicator *streamaggr.Deduplicator
mdxFilter *mdx.Filter
streamAggrKeepInput bool
streamAggrDropInput bool
@@ -889,11 +871,8 @@ type remoteWriteCtx struct {
pss []*pendingSeries
pssNextIdx atomic.Uint64
obfuscateLabels []string
rowsPushedAfterRelabel *metrics.Counter
rowsDroppedByRelabel *metrics.Counter
mdxRowsPreserved *metrics.Counter
pushFailures *metrics.Counter
metadataDroppedOnPushFailure *metrics.Counter
@@ -927,8 +906,7 @@ func newRemoteWriteCtx(argIdx int, remoteWriteURL *url.URL, sanitizedURL string)
}
isPQDisabled := disableOnDiskQueue.GetOptionalArg(argIdx)
inmemoryQueueSize := inmemoryQueues.GetOptionalArg(argIdx)
queuesSize := queues.GetOptionalArg(argIdx) + inmemoryQueueSize
queuesSize := queues.GetOptionalArg(argIdx)
if queuesSize > maxQueues {
queuesSize = maxQueues
} else if queuesSize <= 0 {
@@ -945,13 +923,7 @@ func newRemoteWriteCtx(argIdx int, remoteWriteURL *url.URL, sanitizedURL string)
if maxInmemoryBlocks < 2 {
maxInmemoryBlocks = 2
}
fqOpts := persistentqueue.OpenFastQueueOpts{
MaxInmemoryBlocks: maxInmemoryBlocks,
MaxPendingBytes: maxPendingBytes,
IsPQDisabled: isPQDisabled,
PrioritizeInmemoryData: inmemoryQueueSize > 0,
}
fq := persistentqueue.MustOpenFastQueueWithOpts(queuePath, sanitizedURL, fqOpts)
fq := persistentqueue.MustOpenFastQueue(queuePath, sanitizedURL, maxInmemoryBlocks, maxPendingBytes, isPQDisabled)
_ = metrics.GetOrCreateGauge(fmt.Sprintf(`vmagent_remotewrite_pending_data_bytes{path=%q, url=%q}`, queuePath, sanitizedURL), func() float64 {
return float64(fq.GetPendingBytes())
})
@@ -964,9 +936,6 @@ func newRemoteWriteCtx(argIdx int, remoteWriteURL *url.URL, sanitizedURL string)
}
return 0
})
metrics.GetOrCreateGauge(fmt.Sprintf(`vmagent_remotewrite_queues{url=%q}`, sanitizedURL), func() float64 {
return float64(queuesSize)
})
var c *client
switch remoteWriteURL.Scheme {
@@ -975,7 +944,7 @@ func newRemoteWriteCtx(argIdx int, remoteWriteURL *url.URL, sanitizedURL string)
default:
logger.Fatalf("unsupported scheme: %s for remoteWriteURL: %s, want `http`, `https`", remoteWriteURL.Scheme, sanitizedURL)
}
c.init(argIdx, sanitizedURL)
c.init(argIdx, queuesSize, sanitizedURL)
// Initialize pss
sf := significantFigures.GetOptionalArg(argIdx)
@@ -990,6 +959,7 @@ func newRemoteWriteCtx(argIdx int, remoteWriteURL *url.URL, sanitizedURL string)
for i := range pss {
pss[i] = newPendingSeries(fq, &c.useVMProto, sf, rd)
}
rwctx := &remoteWriteCtx{
idx: argIdx,
fq: fq,
@@ -1005,17 +975,6 @@ func newRemoteWriteCtx(argIdx int, remoteWriteURL *url.URL, sanitizedURL string)
rowsDroppedOnPushFailure: metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_samples_dropped_total{path=%q,url=%q}`, queuePath, sanitizedURL)),
}
rwctx.initStreamAggrConfig()
rwctx.initObfuscateLabels()
if enableMdx.GetOptionalArg(argIdx) {
mdxFilter := mdx.NewFilter()
rwctx.mdxFilter = mdxFilter
rwctx.mdxRowsPreserved = metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_mdx_rows_preserved_total{path=%q,url=%q}`, queuePath, sanitizedURL))
_ = metrics.NewGauge(fmt.Sprintf(`vmagent_remotewrite_mdx_tracked_instances{path=%q,url=%q}`, queuePath, sanitizedURL), func() float64 {
return float64(mdxFilter.VMInstancesCount())
})
}
return rwctx
}
@@ -1030,11 +989,6 @@ func (rwctx *remoteWriteCtx) MustStop() {
rwctx.deduplicator.MustStop()
rwctx.deduplicator = nil
}
if rwctx.mdxFilter != nil {
rwctx.mdxFilter.MustStop()
rwctx.mdxFilter = nil
rwctx.mdxRowsPreserved = nil
}
for _, ps := range rwctx.pss {
ps.MustStop()
@@ -1050,7 +1004,6 @@ func (rwctx *remoteWriteCtx) MustStop() {
rwctx.rowsPushedAfterRelabel = nil
rwctx.rowsDroppedByRelabel = nil
}
// TryPushTimeSeries sends tss series to the configured remote write endpoint
@@ -1058,41 +1011,16 @@ func (rwctx *remoteWriteCtx) MustStop() {
// 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 {
var rctx *relabelCtx
var mctx *mdx.Ctx
var v *[]prompb.TimeSeries
defer func() {
if v != nil {
*v = prompb.ResetTimeSeries(tss)
tssPool.Put(v)
}
if rctx != nil {
putRelabelCtx(rctx)
}
if mctx != nil {
mdx.PutContext(mctx)
if rctx == nil {
return
}
*v = prompb.ResetTimeSeries(tss)
tssPool.Put(v)
putRelabelCtx(rctx)
}()
copyTimeSeriesIfNeeded := func() {
if v == nil {
v = tssPool.Get().(*[]prompb.TimeSeries)
tss = append(*v, tss...)
}
}
if rwctx.mdxFilter != nil {
mctx = mdx.GetContext()
// Make a copy of tss before applying relabeling in order to prevent
// from affecting time series for other remoteWrite.mdx configs.
copyTimeSeriesIfNeeded()
tss = rwctx.mdxFilter.Filter(mctx, tss)
if len(tss) == 0 {
return true
}
rowsCount := getRowsCount(tss)
rwctx.mdxRowsPreserved.Add(rowsCount)
}
// Apply relabeling
rcs := allRelabelConfigs.Load()
pcs := rcs.perURL[rwctx.idx]
@@ -1102,7 +1030,8 @@ 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
copyTimeSeriesIfNeeded()
v = tssPool.Get().(*[]prompb.TimeSeries)
tss = append(*v, tss...)
rowsCountBeforeRelabel := getRowsCount(tss)
tss = rctx.applyRelabeling(tss, pcs)
rowsCountAfterRelabel := getRowsCount(tss)
@@ -1120,7 +1049,8 @@ func (rwctx *remoteWriteCtx) TryPushTimeSeries(tss []prompb.TimeSeries, forceDro
if rctx == nil {
rctx = getRelabelCtx()
// Make a copy of tss before dropping aggregated series
copyTimeSeriesIfNeeded()
v = tssPool.Get().(*[]prompb.TimeSeries)
tss = append(*v, tss...)
}
tss = dropAggregatedSeries(tss, matchIdxs.B, rwctx.streamAggrDropInput)
} else if rwctx.streamAggrDropInput {
@@ -1128,7 +1058,8 @@ func (rwctx *remoteWriteCtx) TryPushTimeSeries(tss []prompb.TimeSeries, forceDro
if rctx == nil {
rctx = getRelabelCtx()
// Make a copy of tss before dropping aggregated series
copyTimeSeriesIfNeeded()
v = tssPool.Get().(*[]prompb.TimeSeries)
tss = append(*v, tss...)
}
tss = dropUnaggregatedSeries(tss, matchIdxs.B)
}
@@ -1209,41 +1140,24 @@ func (rwctx *remoteWriteCtx) tryPushMetadataInternal(mms []prompb.MetricMetadata
func (rwctx *remoteWriteCtx) tryPushTimeSeriesInternal(tss []prompb.TimeSeries) bool {
var rctx *relabelCtx
var v *[]prompb.TimeSeries
var olctx *obfuscateLabelsCtx
defer func() {
if v != nil {
*v = prompb.ResetTimeSeries(tss)
tssPool.Put(v)
}
if rctx != nil {
putRelabelCtx(rctx)
}
if olctx != nil {
putObfuscateLabelsCtx(olctx)
if rctx == nil {
return
}
*v = prompb.ResetTimeSeries(tss)
tssPool.Put(v)
putRelabelCtx(rctx)
}()
copyTimeSeriesIfNeeded := func() {
if v == nil {
v = tssPool.Get().(*[]prompb.TimeSeries)
tss = append(*v, tss...)
}
}
if len(labelsGlobal) > 0 {
// Make a copy of tss before adding extra labels to prevent
// from affecting time series for other remoteWrite.url configs.
rctx = getRelabelCtx()
copyTimeSeriesIfNeeded()
v = tssPool.Get().(*[]prompb.TimeSeries)
tss = append(*v, tss...)
rctx.appendExtraLabels(tss, labelsGlobal)
}
if len(rwctx.obfuscateLabels) != 0 {
copyTimeSeriesIfNeeded()
olctx = getObfuscateLabelsCtx()
tss = olctx.obfuscate(tss, rwctx.obfuscateLabels)
}
pss := rwctx.pss
idx := rwctx.pssNextIdx.Add(1) % uint64(len(pss))
@@ -1264,6 +1178,15 @@ func getRowsCount(tss []prompb.TimeSeries) int {
}
return rowsCount
}
func newMapFromStrings(a []string) map[string]struct{} {
m := make(map[string]struct{}, len(a))
for _, s := range a {
m[s] = struct{}{}
}
return m
}
func getMaxHourlySeries() int {
limit := *maxHourlySeries
if limit == -1 || limit > math.MaxInt32 {

View File

@@ -6,6 +6,7 @@ import (
"net/url"
"reflect"
"sort"
"time"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
@@ -93,3 +94,10 @@ Outer:
}
return
}
func durationToTime(pd *promutil.Duration) time.Time {
if pd == nil {
return time.Time{}
}
return time.UnixMilli(pd.Duration().Milliseconds())
}

View File

@@ -44,19 +44,12 @@ import (
var (
storagePath string
httpListenAddr string
// Insert series from 2000-01-01T00:00:00.
testStartTime = time.Date(2000, 1, 1, 0, 0, 0, 0, time.UTC)
// insert series from 1970-01-01T00:00:00
testStartTime = time.Unix(0, 0).UTC()
testLogLevel = "ERROR"
disableAlertgroupLabel bool
)
func durationToTime(pd *promutil.Duration) time.Time {
if pd == nil {
return testStartTime
}
return testStartTime.Add(pd.Duration())
}
const (
testStoragePath = "vmalert-unittest"
)
@@ -289,8 +282,7 @@ func processFlags() {
func setUp() {
const maxConcurrentRequests = 4
maxQueueDuration := 5 * time.Second
vmstorage.Init(maxConcurrentRequests, maxQueueDuration, promql.ResetRollupResultCacheIfNeeded)
vmstorage.Init(maxConcurrentRequests, promql.ResetRollupResultCacheIfNeeded)
ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
defer cancel()
readyCheckFunc := func() bool {

View File

@@ -145,10 +145,10 @@ func TestRuleValidate(t *testing.T) {
}
func TestGroupValidate_Failure(t *testing.T) {
f := func(data []byte, validateExpressions bool, errStrExpected string) {
f := func(group *Group, validateExpressions bool, errStrExpected string) {
t.Helper()
_, err := parse(map[string][]byte{"test.yaml": data}, nil, validateExpressions)
err := group.Validate(nil, validateExpressions)
if err == nil {
t.Fatalf("expecting non-nil error")
}
@@ -158,238 +158,275 @@ func TestGroupValidate_Failure(t *testing.T) {
}
}
f([]byte(`
groups:
- name: ""
`), false, "group name must be set")
f(&Group{}, false, "group name must be set")
f([]byte(`
groups:
- name: both record and alert are not set
rules:
- expr: "sum(up == 0 ) by (host)"
for: 10ms
- expr: "sumSeries(time('foo.bar',10))"
`), false, "invalid rule")
f(&Group{
Name: "both record and alert are not set",
Rules: []Rule{
{
Expr: "sum(up == 0 ) by (host)",
For: promutil.NewDuration(10 * time.Millisecond),
},
{
Expr: "sumSeries(time('foo.bar',10))",
},
},
}, false, "invalid rule")
f([]byte(`
groups:
- name: negative interval
interval: -1ms
`), false, "interval shouldn't be lower than 0")
f(&Group{
Name: "negative interval",
Interval: promutil.NewDuration(-1),
}, false, "interval shouldn't be lower than 0")
f([]byte(`
groups:
- name: too big eval_offset
interval: 1m
eval_offset: 2m
`), false, "eval_offset should be smaller than interval")
f(&Group{
Name: "too big eval_offset",
Interval: promutil.NewDuration(time.Minute),
EvalOffset: promutil.NewDuration(2 * time.Minute),
}, false, "eval_offset should be smaller than interval")
f([]byte(`
groups:
- name: too big negative eval_offset
interval: 1m
eval_offset: -2m
`), false, "eval_offset should be smaller than interval")
f(&Group{
Name: "too big negative eval_offset",
Interval: promutil.NewDuration(time.Minute),
EvalOffset: promutil.NewDuration(-2 * time.Minute),
}, false, "eval_offset should be smaller than interval")
f([]byte(`
groups:
- name: wrong limit
limit: -1
`), false, "invalid limit")
limit := -1
f(&Group{
Name: "wrong limit",
Limit: &limit,
}, false, "invalid limit")
f([]byte(`
groups:
- name: wrong concurrency
concurrency: -1
`), false, "invalid concurrency")
f(&Group{
Name: "wrong concurrency",
Concurrency: -1,
}, false, "invalid concurrency")
f([]byte(`
groups:
- name: test
rules:
- alert: alert
expr: up == 1
- alert: alert
expr: up == 1
`), false, "duplicate")
f(&Group{
Name: "test",
Rules: []Rule{
{
Alert: "alert",
Expr: "up == 1",
},
{
Alert: "alert",
Expr: "up == 1",
},
},
}, false, "duplicate")
f([]byte(`
groups:
- name: test
rules:
- alert: alert
expr: up == 1
labels:
summary: "{{ value|query }}"
- alert: alert
expr: up == 1
labels:
summary: "{{ value|query }}"
`), false, "duplicate")
f(&Group{
Name: "test",
Rules: []Rule{
{Alert: "alert", Expr: "up == 1", Labels: map[string]string{
"summary": "{{ value|query }}",
}},
{Alert: "alert", Expr: "up == 1", Labels: map[string]string{
"summary": "{{ value|query }}",
}},
},
}, false, "duplicate")
f([]byte(`
groups:
- name: test
rules:
- record: record
expr: up == 1
labels:
summary: "{{ value|query }}"
- record: record
expr: up == 1
labels:
summary: "{{ value|query }}"
`), false, "duplicate")
f(&Group{
Name: "test",
Rules: []Rule{
{Record: "record", Expr: "up == 1", Labels: map[string]string{
"summary": "{{ value|query }}",
}},
{Record: "record", Expr: "up == 1", Labels: map[string]string{
"summary": "{{ value|query }}",
}},
},
}, false, "duplicate")
f([]byte(`
groups:
- name: test thanos
type: thanos
rules:
- alert: alert
expr: up == 1
labels:
description: "{{ value|query }}"
`), true, "unknown datasource type")
f(&Group{
Name: "test",
Rules: []Rule{
{Alert: "alert", Expr: "up == 1", Labels: map[string]string{
"summary": "{{ value|query }}",
}},
{Alert: "alert", Expr: "up == 1", Labels: map[string]string{
"description": "{{ value|query }}",
}},
},
}, false, "duplicate")
f(&Group{
Name: "test",
Rules: []Rule{
{Record: "alert", Expr: "up == 1", Labels: map[string]string{
"summary": "{{ value|query }}",
}},
{Alert: "alert", Expr: "up == 1", Labels: map[string]string{
"summary": "{{ value|query }}",
}},
},
}, false, "duplicate")
f(&Group{
Name: "test thanos",
Type: NewRawType("thanos"),
Rules: []Rule{
{Alert: "alert", Expr: "up == 1", Labels: map[string]string{
"description": "{{ value|query }}",
}},
},
}, true, "unknown datasource type")
// validate expressions
f([]byte(`
groups:
- name: test prometheus expr
type: prometheus
rules:
- record: record
expr: "up | 0"
`), true, "bad MetricsQL expr")
f(&Group{
Name: "test prometheus expr",
Type: NewPrometheusType(),
Rules: []Rule{
{
Record: "record",
Expr: "up | 0",
},
},
}, true, "bad MetricsQL expr")
f([]byte(`
groups:
- name: test graphite expr
type: graphite
rules:
- alert: alert
expr: up == 1
labels:
description: some-description
`), true, "bad GraphiteQL expr")
f(&Group{
Name: "test graphite expr",
Type: NewGraphiteType(),
Rules: []Rule{
{Alert: "alert", Expr: "up == 1", Labels: map[string]string{
"description": "some-description",
}},
},
}, true, "bad GraphiteQL expr")
f([]byte(`
groups:
- name: test vlogs expr
type: vlogs
rules:
- alert: alert
expr: "stats count(*) as requests"
`), true, "bad LogsQL expr")
f(&Group{
Name: "test vlogs expr",
Type: NewVLogsType(),
Rules: []Rule{
{Alert: "alert", Expr: "stats count(*) as requests"},
},
}, true, "bad LogsQL expr")
f([]byte(`
groups:
- name: test vlogs expr multipart
type: vlogs
rules:
- alert: alert
expr: "_time: 1m | stats by (path, _time: 1m) count(*) as requests"
`), true, "bad LogsQL expr")
f(&Group{
Name: "test vlogs expr",
Type: NewVLogsType(),
Rules: []Rule{
{Alert: "alert", Expr: "_time: 1m | stats by (path, _time: 1m) count(*) as requests"},
},
}, true, "bad LogsQL expr")
f([]byte(`
groups:
- name: test graphite with prometheus expr
type: graphite
rules:
- record: r1
expr: "sumSeries(time('foo.bar',10))"
for: 10ms
- record: r2
expr: "sum(up == 0 ) by (host)"
`), true, "bad GraphiteQL expr")
f(&Group{
Name: "test graphite with prometheus expr",
Type: NewGraphiteType(),
Rules: []Rule{
{
Record: "r1",
ID: 1,
Expr: "sumSeries(time('foo.bar',10))",
For: promutil.NewDuration(10 * time.Millisecond),
},
{
Record: "r2",
ID: 2,
Expr: "sum(up == 0 ) by (host)",
},
},
}, true, "bad GraphiteQL expr")
f([]byte(`
groups:
- name: test vlogs with prometheus expr
type: vlogs
rules:
- record: r1
expr: "sum(up == 0 ) by (host)"
for: 10ms
`), true, "bad LogsQL expr")
f(&Group{
Name: "test vlogs with prometheus exp",
Type: NewVLogsType(),
Rules: []Rule{
{
Record: "r1",
Expr: "sum(up == 0 ) by (host)",
For: promutil.NewDuration(10 * time.Millisecond),
},
},
}, true, "bad LogsQL expr")
f([]byte(`
groups:
- name: test prometheus with vlogs expr
type: prometheus
rules:
- record: r1
expr: "* | stats by (path) count()"
for: 10ms
`), true, "bad MetricsQL expr")
f(&Group{
Name: "test prometheus with vlogs exp",
Type: NewPrometheusType(),
Rules: []Rule{
{
Record: "r1",
Expr: "* | stats by (path) count()",
For: promutil.NewDuration(10 * time.Millisecond),
},
},
}, true, "bad MetricsQL expr")
}
func TestGroupValidate_Success(t *testing.T) {
f := func(data []byte, validateAnnotations, validateExpressions bool) {
f := func(group *Group, validateAnnotations, validateExpressions bool) {
t.Helper()
var validateTplFn ValidateTplFn
if validateAnnotations {
validateTplFn = notifier.ValidateTemplates
}
_, err := parse(map[string][]byte{"test.yaml": data}, validateTplFn, validateExpressions)
err := group.Validate(validateTplFn, validateExpressions)
if err != nil {
t.Fatalf("unexpected error: %s", err)
}
}
f([]byte(`
groups:
- name: test
rules:
- record: record
expr: "up | 0"
`), false, false)
f(&Group{
Name: "test",
Rules: []Rule{
{
Record: "record",
Expr: "up | 0",
},
},
}, false, false)
f([]byte(`
groups:
- name: test
rules:
- alert: alert
expr: up == 1
labels:
summary: "{{ value|query }}"
`), false, false)
f(&Group{
Name: "test",
Rules: []Rule{
{
Alert: "alert",
Expr: "up == 1",
Labels: map[string]string{
"summary": "{{ value|query }}",
},
},
},
}, false, false)
// validate annotations
f([]byte(`
groups:
- name: test
rules:
- alert: alert
expr: up == 1
labels:
summary: "\n{{ with printf \"node_memory_MemTotal{job='node',instance='%s'}\" \"localhost\" | query }}\n {{ . | first | value | humanize1024 }}B\n{{ end }}"
`), true, false)
f(&Group{
Name: "test",
Rules: []Rule{
{
Alert: "alert",
Expr: "up == 1",
Labels: map[string]string{
"summary": `
{{ with printf "node_memory_MemTotal{job='node',instance='%s'}" "localhost" | query }}
{{ . | first | value | humanize1024 }}B
{{ end }}`,
},
},
},
}, true, false)
// validate expressions
f([]byte(`
groups:
- name: test prometheus
type: prometheus
rules:
- alert: alert
expr: up == 1
labels:
description: "{{ value|query }}"
`), false, true)
f([]byte(`
groups:
- name: test victorialogs
type: vlogs
rules:
- alert: alert
expr: " _time: 1m | stats count(*) as requests"
labels:
description: "{{ value|query }}"
`), false, true)
f(&Group{
Name: "test prometheus",
Type: NewPrometheusType(),
Rules: []Rule{
{Alert: "alert", Expr: "up == 1", Labels: map[string]string{
"description": "{{ value|query }}",
}},
},
}, false, true)
f(&Group{
Name: "test victorialogs",
Type: NewVLogsType(),
Rules: []Rule{
{Alert: "alert", Expr: " _time: 1m | stats count(*) as requests", Labels: map[string]string{
"description": "{{ value|query }}",
}},
},
}, false, true)
}
func TestHashRule_NotEqual(t *testing.T) {

View File

@@ -11,7 +11,6 @@ import (
"strings"
"time"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/netutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promauth"
@@ -268,11 +267,7 @@ func (c *Client) do(req *http.Request) (*http.Response, error) {
if resp.StatusCode != http.StatusOK {
body, _ := io.ReadAll(resp.Body)
_ = resp.Body.Close()
err = &httpserver.ErrorWithStatusCode{
StatusCode: resp.StatusCode,
Err: fmt.Errorf("unexpected response code %d for %s. Response body %s", resp.StatusCode, ru, body),
}
return nil, err
return nil, fmt.Errorf("unexpected response code %d for %s. Response body %s", resp.StatusCode, ru, body)
}
return resp, nil
}

View File

@@ -11,7 +11,6 @@ import (
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/vmalertutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/httputil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promauth"
)
@@ -60,8 +59,7 @@ var (
`Only valid for VictoriaMetrics as the datasource.`)
)
// InitSecretFlags manages the secret flags for this pkg and must be called by app-level initSecretFlags.
// It should run before logger initialization and package Init() (if exists).
// InitSecretFlags must be called after flag.Parse and before any logging
func InitSecretFlags() {
if !*showDatasourceURL {
flagutil.RegisterSecretFlag("datasource.url")
@@ -96,12 +94,6 @@ func Init(extraParams url.Values) (QuerierBuilder, error) {
tr.MaxIdleConns = tr.MaxIdleConnsPerHost
}
tr.IdleConnTimeout = *idleConnectionTimeout
hc := &http.Client{Transport: tr}
datasourceURL, err := url.Parse(*addr)
if err != nil {
logger.Fatalf("BUG: cannot parse already parsed -datasource.url=%q: %s", *addr, err)
}
hc.Transport, datasourceURL = httputil.NewLoadBalancerTransport(tr, datasourceURL)
if extraParams == nil {
extraParams = url.Values{}
@@ -128,9 +120,9 @@ func Init(extraParams url.Values) (QuerierBuilder, error) {
}
return &Client{
c: hc,
c: &http.Client{Transport: tr},
authCfg: authCfg,
datasourceURL: strings.TrimSuffix(datasourceURL.String(), "/"),
datasourceURL: strings.TrimSuffix(*addr, "/"),
appendTypePrefix: *appendTypePrefix,
queryStep: *queryStep,
extraParams: extraParams,

View File

@@ -88,7 +88,10 @@ func main() {
flag.CommandLine.SetOutput(os.Stdout)
flag.Usage = usage
envflag.Parse()
initSecretFlags()
remoteread.InitSecretFlags()
remotewrite.InitSecretFlags()
datasource.InitSecretFlags()
notifier.InitSecretFlags()
buildinfo.Init()
logger.Init()
@@ -435,12 +438,3 @@ func getLastConfigError() error {
defer lastConfigErrMu.RUnlock()
return lastConfigErr
}
// initSecretFlags manages the secret flags for this app and must be called after flag parsing and before logger init.
func initSecretFlags() {
remoteread.InitSecretFlags()
remotewrite.InitSecretFlags()
datasource.InitSecretFlags()
notifier.InitSecretFlags()
pushmetrics.InitSecretFlags()
}

View File

@@ -31,8 +31,6 @@ type Alert struct {
State AlertState
// Expr contains expression that was executed to generate the Alert
Expr string
// Interval contains the evaluation interval of the Alert's group
Interval time.Duration
// ActiveAt defines the moment of time when Alert has become active
ActiveAt time.Time
// Start defines the moment of time when Alert has become firing
@@ -86,7 +84,6 @@ type AlertTplData struct {
Labels map[string]string
Value float64
Expr string
Interval time.Duration
AlertID uint64
GroupID uint64
ActiveAt time.Time
@@ -99,7 +96,6 @@ var tplHeaders = []string{
"{{ $type := .Type }}",
"{{ $labels := .Labels }}",
"{{ $expr := .Expr }}",
"{{ $interval := .Interval }}",
"{{ $externalLabels := .ExternalLabels }}",
"{{ $externalURL := .ExternalURL }}",
"{{ $alertID := .AlertID }}",
@@ -119,7 +115,6 @@ func (a *Alert) ExecTemplate(q templates.QueryFn, labels, annotations map[string
Type: a.Type,
Labels: labels,
Expr: a.Expr,
Interval: a.Interval,
AlertID: a.ID,
GroupID: a.GroupID,
ActiveAt: a.ActiveAt,

View File

@@ -129,17 +129,6 @@ func TestAlertExecTemplate(t *testing.T) {
"exprEscapedHTML": "vm_rows{&quot;label&quot;=&quot;bar&quot;}&lt;0",
})
// interval-template
f(&Alert{
Interval: 10 * time.Second,
}, map[string]string{
"interval": "{{ .Interval }}",
"intervalVariable": "{{ $interval }}",
}, map[string]string{
"interval": "10s",
"intervalVariable": "10s",
})
// query
f(&Alert{
Expr: `vm_rows{"label"="bar"}>0`,

View File

@@ -189,8 +189,7 @@ func Init(extLabels map[string]string, extURL string) error {
return nil
}
// InitSecretFlags manages the secret flags for this pkg and must be called by app-level initSecretFlags.
// It should run before logger initialization and package Init() (if exists).
// InitSecretFlags must be called after flag.Parse and before any logging
func InitSecretFlags() {
if !*showNotifierURL {
flagutil.RegisterSecretFlag("notifier.url")

View File

@@ -4,14 +4,12 @@ import (
"flag"
"fmt"
"net/http"
"net/url"
"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/httputil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promauth"
)
@@ -56,8 +54,7 @@ var (
oauth2Scopes = flag.String("remoteRead.oauth2.scopes", "", "Optional OAuth2 scopes to use for -remoteRead.url. Scopes must be delimited by ';'.")
)
// InitSecretFlags manages the secret flags for this pkg and must be called by app-level initSecretFlags.
// It should run before logger initialization and package Init() (if exists).
// InitSecretFlags must be called after flag.Parse and before any logging
func InitSecretFlags() {
if !*showRemoteReadURL {
flagutil.RegisterSecretFlag("remoteRead.url")
@@ -79,13 +76,7 @@ func Init() (datasource.QuerierBuilder, error) {
return nil, fmt.Errorf("failed to create transport for -remoteRead.url=%q: %w", *addr, err)
}
tr.IdleConnTimeout = *idleConnectionTimeout
c := &http.Client{Transport: tr}
rrURL, err := url.Parse(*addr)
if err != nil {
logger.Fatalf("BUG: cannot parse already parsed -remoteRead.url=%q: %s", *addr, err)
}
c.Transport, rrURL = httputil.NewLoadBalancerTransport(tr, rrURL)
endpointParams, err := flagutil.ParseJSONMap(*oauth2EndpointParams)
if err != nil {
return nil, fmt.Errorf("cannot parse JSON for -remoteRead.oauth2.endpointParams=%s: %w", *oauth2EndpointParams, err)
@@ -98,5 +89,6 @@ func Init() (datasource.QuerierBuilder, error) {
if err != nil {
return nil, fmt.Errorf("failed to configure auth: %w", err)
}
return datasource.NewPrometheusClient(rrURL.String(), authCfg, false, c), nil
c := &http.Client{Transport: tr}
return datasource.NewPrometheusClient(*addr, authCfg, false, c), nil
}

View File

@@ -8,7 +8,6 @@ import (
"fmt"
"io"
"net/http"
"net/url"
"path"
"strings"
"sync"
@@ -112,18 +111,12 @@ func NewClient(ctx context.Context, cfg Config) (*Client, error) {
if cfg.Concurrency > 0 {
cc = cfg.Concurrency
}
hc := &http.Client{
Timeout: *sendTimeout,
Transport: cfg.Transport,
}
rwURL, err := url.Parse(cfg.Addr)
if err != nil {
logger.Fatalf("cannot parse already parsed -remoteWrite.url=%q: %s", cfg.Addr, err)
}
hc.Transport, rwURL = httputil.NewLoadBalancerTransport(hc.Transport, rwURL)
c := &Client{
c: hc,
addr: strings.TrimSuffix(rwURL.String(), "/"),
c: &http.Client{
Timeout: *sendTimeout,
Transport: cfg.Transport,
},
addr: strings.TrimSuffix(cfg.Addr, "/"),
authCfg: cfg.AuthCfg,
flushInterval: cfg.FlushInterval,
maxBatchSize: cfg.MaxBatchSize,
@@ -284,15 +277,7 @@ func (c *Client) flush(ctx context.Context, wr *prompb.WriteRequest) {
bb := writeRequestBufPool.Get()
bb.B = wr.MarshalProtobuf(bb.B[:0])
zb := compressBufPool.Get()
// A failed send may leave the http transport still reading zb.B in a separate goroutine
// even after send returns, so zb is returned to the pool only if no send attempt has failed.
// See https://pkg.go.dev/net/http#RoundTripper
sendFailed := false
defer func() {
if !sendFailed {
compressBufPool.Put(zb)
}
}()
defer compressBufPool.Put(zb)
if c.isVMRemoteWrite.Load() {
zb.B = zstd.CompressLevel(zb.B[:0], bb.B, 0)
} else {
@@ -311,13 +296,10 @@ func (c *Client) flush(ctx context.Context, wr *prompb.WriteRequest) {
L:
for {
err := c.send(ctx, zb.B)
if err != nil {
sendFailed = true
if errors.Is(err, io.EOF) || netutil.IsTrivialNetworkError(err) {
// Something in the middle between client and destination might be closing
// the connection. So we do a one more attempt in hope request will succeed.
err = c.send(ctx, zb.B)
}
if err != nil && (errors.Is(err, io.EOF) || netutil.IsTrivialNetworkError(err)) {
// Something in the middle between client and destination might be closing
// the connection. So we do a one more attempt in hope request will succeed.
err = c.send(ctx, zb.B)
}
if err == nil {
sentRows.Add(len(wr.Timeseries))

View File

@@ -36,13 +36,6 @@ func NewDebugClient() (*DebugClient, error) {
if err != nil {
return nil, fmt.Errorf("failed to create transport for -remoteWrite.url=%q: %w", *addr, err)
}
tr.IdleConnTimeout = *idleConnectionTimeout
// DebugClient sends every series in a separate request, so it needs more idle
// connections than the two http.DefaultTransport keeps per host.
tr.MaxIdleConnsPerHost = *maxIdleConnections
if tr.MaxIdleConns != 0 && tr.MaxIdleConns < tr.MaxIdleConnsPerHost {
tr.MaxIdleConns = tr.MaxIdleConnsPerHost
}
c := &DebugClient{
c: &http.Client{
Timeout: *sendTimeout,

View File

@@ -1,45 +0,0 @@
package remotewrite
import (
"net/http"
"testing"
)
// TestDebugClient_IdleConns makes sure DebugClient keeps enough idle connections
// to -remoteWrite.url. Every series is pushed in a separate request, so with the
// two idle connections per host of http.DefaultTransport most of the concurrent
// requests would open a new connection and leave a socket in TIME_WAIT state.
func TestDebugClient_IdleConns(t *testing.T) {
f := func(maxIdle int) {
t.Helper()
oldAddr, oldMaxIdle := *addr, *maxIdleConnections
*addr, *maxIdleConnections = "http://localhost:8428", maxIdle
defer func() {
*addr, *maxIdleConnections = oldAddr, oldMaxIdle
}()
client, err := NewDebugClient()
if err != nil {
t.Fatalf("failed to create debug client: %s", err)
}
tr, ok := client.c.Transport.(*http.Transport)
if !ok {
t.Fatalf("unexpected transport type %T", client.c.Transport)
}
if tr.MaxIdleConnsPerHost != maxIdle {
t.Fatalf("unexpected MaxIdleConnsPerHost; got %d; want %d", tr.MaxIdleConnsPerHost, maxIdle)
}
if tr.MaxIdleConns != 0 && tr.MaxIdleConns < maxIdle {
t.Fatalf("MaxIdleConns=%d is lower than MaxIdleConnsPerHost=%d", tr.MaxIdleConns, maxIdle)
}
if tr.IdleConnTimeout != *idleConnectionTimeout {
t.Fatalf("unexpected IdleConnTimeout; got %s; want %s", tr.IdleConnTimeout, *idleConnectionTimeout)
}
}
f(100)
// the number of idle connections must be raised together with the total limit
f(1000)
}

View File

@@ -34,7 +34,6 @@ var (
bearerTokenFile = flag.String("remoteWrite.bearerTokenFile", "", "Optional path to bearer token file to use for -remoteWrite.url.")
idleConnectionTimeout = flag.Duration("remoteWrite.idleConnTimeout", 50*time.Second, `Defines a duration for idle (keep-alive connections) to exist. Consider settings this value less to the value of "-http.idleConnTimeout". It must prevent possible "write: broken pipe" and "read: connection reset by peer" errors.`)
maxIdleConnections = flag.Int("remoteWrite.maxIdleConnections", 100, `Defines the number of idle (keep-alive connections) to -remoteWrite.url for the vmalert-tool debug writer, which sends every series in a separate request. Too low a value may result in a high number of sockets in TIME_WAIT state.`)
maxQueueSize = flag.Int("remoteWrite.maxQueueSize", defaultMaxQueueSize, "Defines the max number of pending datapoints to remote write endpoint")
maxBatchSize = flag.Int("remoteWrite.maxBatchSize", defaultMaxBatchSize, "Defines max number of timeseries to be flushed at once")
@@ -58,8 +57,7 @@ var (
oauth2Scopes = flag.String("remoteWrite.oauth2.scopes", "", "Optional OAuth2 scopes to use for -notifier.url. Scopes must be delimited by ';'.")
)
// InitSecretFlags manages the secret flags for this pkg and must be called by app-level initSecretFlags.
// It should run before logger initialization and package Init() (if exists).
// InitSecretFlags must be called after flag.Parse and before any logging
func InitSecretFlags() {
if !*showRemoteWriteURL {
flagutil.RegisterSecretFlag("remoteWrite.url")

View File

@@ -25,13 +25,11 @@ var (
replayMaxDatapoints = flag.Int("replay.maxDatapointsPerQuery", 1e3,
"Max number of data points expected in one request. It affects the max time range for every '/query_range' request during the replay. The higher the value, the less requests will be made during replay.")
replayRuleRetryAttempts = flag.Int("replay.ruleRetryAttempts", 5,
"Defines how many retries to make before giving up on rule if request for it returns a retriable error.")
"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.")
continueWithExecutionErr = flag.Bool("replay.continueWithExecutionErr", false, "Whether to continue replaying other rules if a rule execution fails with a 400 or 422 response code, "+
"which can happen due to an expression syntax error or a resource limit being hit.")
)
func replay(groupsCfg []config.Group, qb datasource.QuerierBuilder, rw remotewrite.RWClient) (totalRows, droppedRows int, err error) {
@@ -75,7 +73,7 @@ func replay(groupsCfg []config.Group, qb datasource.QuerierBuilder, rw remotewri
for _, cfg := range groupsCfg {
ng := rule.NewGroup(cfg, qb, *evaluationInterval, labels)
totalRows += ng.Replay(tFrom, tTo, rw, *replayMaxDatapoints, *replayRuleRetryAttempts, *replayRulesDelay, *disableProgressBar, *ruleEvaluationConcurrency, *continueWithExecutionErr)
totalRows += ng.Replay(tFrom, tTo, rw, *replayMaxDatapoints, *replayRuleRetryAttempts, *replayRulesDelay, *disableProgressBar, *ruleEvaluationConcurrency)
}
logger.Infof("replay evaluation finished, generated %d samples", totalRows)
if err := rw.Close(); err != nil {

View File

@@ -8,10 +8,8 @@ import (
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/config"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promutil"
"github.com/VictoriaMetrics/metricsql"
)
type fakeReplayQuerier struct {
@@ -34,14 +32,6 @@ func (fc *fakeRWClient) Close() error {
}
func (fr *fakeReplayQuerier) QueryRange(_ context.Context, q string, from, to time.Time) (res datasource.Result, err error) {
_, err = metricsql.Parse(q)
if err != nil {
return res, &httpserver.ErrorWithStatusCode{
StatusCode: 422,
Err: err,
}
}
key := fmt.Sprintf("%s+%s", from.Format("15:04:05"), to.Format("15:04:05"))
dps, ok := fr.registry[q]
if !ok {
@@ -285,28 +275,4 @@ func TestReplay(t *testing.T) {
},
},
}, 10)
// rule with wrong expression won't break the other rule with continueWithExecutionErr
continueWithExecutionErrOld := *continueWithExecutionErr
defer func() {
*continueWithExecutionErr = continueWithExecutionErrOld
}()
*continueWithExecutionErr = true
f("2021-01-01T12:00:00.000Z", "2021-01-01T12:02:30.000Z", 1, 1, time.Millisecond, []config.Group{
{Rules: []config.Rule{{Record: "foo", Expr: "sum(up)"}}},
{Rules: []config.Rule{{Record: "bar", Expr: "up ++"}}},
}, &fakeReplayQuerier{
registry: map[string]map[string][]datasource.Metric{
"sum(up)": {
"12:00:00+12:01:00": {
{
Timestamps: []int64{1, 2},
Values: []float64{1, 2},
},
},
"12:01:00+12:02:00": {},
"12:02:00+12:02:30": {},
},
},
}, 2)
}

View File

@@ -462,11 +462,7 @@ func (ar *AlertingRule) exec(ctx context.Context, ts time.Time, limit int) ([]pr
}
isPartial := isPartialResponse(res)
seriesFetched := 0
if res.SeriesFetched != nil {
seriesFetched = *res.SeriesFetched
}
ar.logDebugf(ts, nil, "query returned %d series (series_fetched: %d, elapsed: %s, isPartial: %t)", curState.Samples, seriesFetched, curState.Duration, isPartial)
ar.logDebugf(ts, nil, "query returned %d series (elapsed: %s, isPartial: %t)", curState.Samples, curState.Duration, isPartial)
qFn := func(query string) ([]datasource.Metric, error) {
res, _, err := ar.q.Query(ctx, query, ts)
return res.Data, err
@@ -534,7 +530,6 @@ func (ar *AlertingRule) exec(ctx context.Context, ts time.Time, limit int) ([]pr
ar.logDebugf(ts, a, "INACTIVE => PENDING")
}
a.Value = m.Values[0]
a.Interval = ar.EvalInterval
a.Annotations = annotations
a.KeepFiringSince = time.Time{}
continue
@@ -617,7 +612,6 @@ func (ar *AlertingRule) expandAnnotationTemplates(m datasource.Metric, qFn templ
Type: ar.Type.String(),
Labels: ls.origin,
Expr: ar.Expr,
Interval: ar.EvalInterval,
AlertID: hash(ls.processed),
GroupID: ar.GroupID,
ActiveAt: activeAt,
@@ -679,7 +673,6 @@ func (ar *AlertingRule) newAlert(m datasource.Metric, start time.Time, labels, a
Name: ar.Name,
Type: ar.Type.String(),
Expr: ar.Expr,
Interval: ar.EvalInterval,
For: ar.For,
ActiveAt: start,
Value: m.Values[0],

View File

@@ -662,7 +662,6 @@ func TestAlertingRuleExecRange(t *testing.T) {
GroupID: fakeGroup.GetID(),
Name: "for-pending",
Type: config.NewPrometheusType().String(),
Interval: time.Second,
Labels: map[string]string{"alertname": "for-pending"},
Annotations: map[string]string{},
State: notifier.StatePending,
@@ -683,7 +682,6 @@ func TestAlertingRuleExecRange(t *testing.T) {
GroupID: fakeGroup.GetID(),
Name: "for-firing",
Type: config.NewPrometheusType().String(),
Interval: 3 * time.Second,
Labels: map[string]string{"alertname": "for-firing"},
Annotations: map[string]string{},
State: notifier.StateFiring,
@@ -705,7 +703,6 @@ func TestAlertingRuleExecRange(t *testing.T) {
GroupID: fakeGroup.GetID(),
Name: "for-hold-pending",
Type: config.NewPrometheusType().String(),
Interval: time.Second,
Labels: map[string]string{"alertname": "for-hold-pending"},
Annotations: map[string]string{},
State: notifier.StatePending,
@@ -762,7 +759,6 @@ func TestAlertingRuleExecRange(t *testing.T) {
GroupID: fakeGroup.GetID(),
Name: "multi-series",
Type: config.NewPrometheusType().String(),
Interval: 3 * time.Second,
Labels: map[string]string{"alertname": "multi-series"},
Annotations: map[string]string{},
State: notifier.StateFiring,
@@ -775,7 +771,6 @@ func TestAlertingRuleExecRange(t *testing.T) {
GroupID: fakeGroup.GetID(),
Name: "multi-series",
Type: config.NewPrometheusType().String(),
Interval: 3 * time.Second,
Labels: map[string]string{"alertname": "multi-series", "foo": "bar"},
Annotations: map[string]string{},
State: notifier.StatePending,
@@ -1139,8 +1134,7 @@ func TestAlertingRule_Template(t *testing.T) {
fq.Add(metrics...)
fq.SetPartialResponse(isResponsePartial)
ts := time.Unix(3600, 0)
if _, err := rule.exec(context.TODO(), ts, 0); err != nil {
if _, err := rule.exec(context.TODO(), time.Now(), 0); err != nil {
t.Fatalf("unexpected error: %s", err)
}
for hash, expAlert := range alertsExpected {
@@ -1158,14 +1152,12 @@ func TestAlertingRule_Template(t *testing.T) {
}
f(&AlertingRule{
Name: "common",
EvalInterval: time.Hour,
Name: "common",
Labels: map[string]string{
"region": "east",
},
Annotations: map[string]string{
"summary": `{{ $labels.alertname }}: Too high connection number for "{{ $labels.instance }}"`,
"dashboard": `&from={{ ($activeAt.Add (parseDurationTime (printf "-%s" .Interval))).UnixMilli }}&to={{ $activeAt.UnixMilli }}`,
"summary": `{{ $labels.alertname }}: Too high connection number for "{{ $labels.instance }}"`,
},
alerts: make(map[uint64]*notifier.Alert),
}, []datasource.Metric{
@@ -1174,8 +1166,7 @@ func TestAlertingRule_Template(t *testing.T) {
}, false, map[uint64]*notifier.Alert{
hash(map[string]string{alertNameLabel: "common", "region": "east", "instance": "foo"}): {
Annotations: map[string]string{
"summary": `common: Too high connection number for "foo"`,
"dashboard": "&from=0&to=3600000",
"summary": `common: Too high connection number for "foo"`,
},
Labels: map[string]string{
alertNameLabel: "common",
@@ -1185,8 +1176,7 @@ func TestAlertingRule_Template(t *testing.T) {
},
hash(map[string]string{alertNameLabel: "common", "region": "east", "instance": "bar"}): {
Annotations: map[string]string{
"summary": `common: Too high connection number for "bar"`,
"dashboard": "&from=0&to=3600000",
"summary": `common: Too high connection number for "bar"`,
},
Labels: map[string]string{
alertNameLabel: "common",
@@ -1398,7 +1388,7 @@ func TestAlertingRule_ToLabels(t *testing.T) {
"alertname": "ConfigurationReloadFailure",
"alertgroup": "vmalert",
"pod": "vmalert-0",
"invalid_label": `error evaluating template: template: :1:326: executing "" at <.Values.mustRuntimeFail>: can't evaluate field Values in type notifier.tplData`,
"invalid_label": `error evaluating template: template: :1:298: executing "" at <.Values.mustRuntimeFail>: can't evaluate field Values in type notifier.tplData`,
}
expectedProcessedLabels := map[string]string{
@@ -1408,7 +1398,7 @@ func TestAlertingRule_ToLabels(t *testing.T) {
"exported_alertname": "ConfigurationReloadFailure",
"group": "vmalert",
"alertgroup": "vmalert",
"invalid_label": `error evaluating template: template: :1:326: executing "" at <.Values.mustRuntimeFail>: can't evaluate field Values in type notifier.tplData`,
"invalid_label": `error evaluating template: template: :1:298: executing "" at <.Values.mustRuntimeFail>: can't evaluate field Values in type notifier.tplData`,
}
ls, err := ar.toLabels(metric, nil)

View File

@@ -97,7 +97,6 @@ type groupMetrics struct {
iterationMissed *metrics.Counter
iterationReset *metrics.Counter
iterationInterval *metrics.Gauge
iterationLimit *metrics.Gauge
}
// merges group rule labels into result map
@@ -290,8 +289,6 @@ func (g *Group) updateWith(newGroup *Group) error {
g.Headers = newGroup.Headers
g.NotifierHeaders = newGroup.NotifierHeaders
g.Labels = newGroup.Labels
g.EvalDelay = newGroup.EvalDelay
g.evalAlignment = newGroup.evalAlignment
g.Limit = newGroup.Limit
g.checksum = newGroup.checksum
g.Rules = newRules
@@ -339,12 +336,6 @@ func (g *Group) Init() {
i := g.Interval.Seconds()
return i
})
g.metrics.iterationLimit = g.metrics.set.NewGauge(fmt.Sprintf(`vmalert_group_rule_results_limit{%s}`, labels), func() float64 {
g.mu.RLock()
limit := g.Limit
g.mu.RUnlock()
return float64(limit)
})
for i := range g.Rules {
g.Rules[i].registerMetrics(g.metrics.set)
}
@@ -375,7 +366,7 @@ func (g *Group) Start(ctx context.Context, rw remotewrite.RWClient, rr datasourc
g.mu.Lock()
err := g.updateWith(ng)
if err != nil {
logger.Errorf("group %q (file=%q): failed to update: %s", g.Name, g.File, err)
logger.Errorf("group %q: failed to update: %s", g.Name, err)
g.mu.Unlock()
continue
}
@@ -414,7 +405,7 @@ func (g *Group) Start(ctx context.Context, rw remotewrite.RWClient, rr datasourc
errs := e.execConcurrently(ctx, g.Rules, ts, g.Concurrency, resolveDuration, g.Limit)
for err := range errs {
if err != nil {
logger.Errorf("group %q (file=%q): %s", g.Name, g.File, err)
logger.Errorf("group %q: %s", g.Name, err)
}
}
g.metrics.iterationDuration.UpdateDuration(start)
@@ -443,17 +434,17 @@ func (g *Group) Start(ctx context.Context, rw remotewrite.RWClient, rr datasourc
if rr != nil {
err := g.restore(ctx, rr, realEvalTS, *remoteReadLookBack)
if err != nil {
logger.Errorf("error while restoring ruleState for group %q (file=%q): %s", g.Name, g.File, err)
logger.Errorf("error while restoring ruleState for group %q: %s", g.Name, err)
}
}
for {
select {
case <-ctx.Done():
logger.Infof("group %q (file=%q): context cancelled", g.Name, g.File)
logger.Infof("group %q: context cancelled", g.Name)
return
case <-g.doneCh:
logger.Infof("group %q (file=%q): received stop signal", g.Name, g.File)
logger.Infof("group %q: received stop signal", g.Name)
return
case ng := <-g.updateCh:
g.mu.Lock()
@@ -467,7 +458,7 @@ func (g *Group) Start(ctx context.Context, rw remotewrite.RWClient, rr datasourc
err := g.updateWith(ng)
if err != nil {
logger.Errorf("group %q (file=%q): failed to update: %s", g.Name, g.File, err)
logger.Errorf("group %q: failed to update: %s", g.Name, err)
g.mu.Unlock()
continue
}
@@ -545,12 +536,12 @@ func (g *Group) delayBeforeStart(ts time.Time, maxDelay time.Duration) time.Dura
func (g *Group) infof(format string, args ...any) {
msg := fmt.Sprintf(format, args...)
logger.Infof("group %q (file=%q; interval=%v; eval_offset=%v; concurrency=%d) %s",
g.Name, g.File, g.Interval, g.EvalOffset, g.Concurrency, msg)
logger.Infof("group %q %s; interval=%v; eval_offset=%v; concurrency=%d",
g.Name, msg, g.Interval, g.EvalOffset, g.Concurrency)
}
// Replay performs group replay
func (g *Group) Replay(start, end time.Time, rw remotewrite.RWClient, maxDataPoint, replayRuleRetryAttempts int, replayDelay time.Duration, disableProgressBar bool, ruleEvaluationConcurrency int, continueWithExecutionErr bool) int {
func (g *Group) Replay(start, end time.Time, rw remotewrite.RWClient, maxDataPoint, replayRuleRetryAttempts int, replayDelay time.Duration, disableProgressBar bool, ruleEvaluationConcurrency int) int {
var total int
step := g.Interval * time.Duration(maxDataPoint)
ri := rangeIterator{start: start, end: end, step: step}
@@ -578,7 +569,7 @@ func (g *Group) Replay(start, end time.Time, rw remotewrite.RWClient, maxDataPoi
if !disableProgressBar {
bar = pb.StartNew(iterations)
}
total += replayRuleRange(rule, ri, bar, rw, replayRuleRetryAttempts, ruleEvaluationConcurrency, continueWithExecutionErr)
total += replayRuleRange(rule, ri, bar, rw, replayRuleRetryAttempts, ruleEvaluationConcurrency)
if bar != nil {
bar.Finish()
}
@@ -600,7 +591,7 @@ func (g *Group) Replay(start, end time.Time, rw remotewrite.RWClient, maxDataPoi
rule := g.Rules[i]
sem <- struct{}{}
wg.Go(func() {
res <- replayRuleRange(rule, ri, bar, rw, replayRuleRetryAttempts, ruleEvaluationConcurrency, continueWithExecutionErr)
res <- replayRuleRange(rule, ri, bar, rw, replayRuleRetryAttempts, ruleEvaluationConcurrency)
<-sem
})
}
@@ -620,7 +611,7 @@ func (g *Group) Replay(start, end time.Time, rw remotewrite.RWClient, maxDataPoi
return total
}
func replayRuleRange(r Rule, ri rangeIterator, bar *pb.ProgressBar, rw remotewrite.RWClient, replayRuleRetryAttempts, ruleEvaluationConcurrency int, continueWithExecutionErr bool) int {
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
@@ -635,7 +626,7 @@ func replayRuleRange(r Rule, ri rangeIterator, bar *pb.ProgressBar, rw remotewri
start := ri.s
end := ri.e
wg.Go(func() {
n, err := replayRule(r, start, end, rw, replayRuleRetryAttempts, continueWithExecutionErr)
n, err := replayRule(r, start, end, rw, replayRuleRetryAttempts)
if err != nil {
logger.Fatalf("rule %q: %s", r, err)
}

View File

@@ -78,12 +78,6 @@ func TestUpdateWith(t *testing.T) {
if g.Debug != expect.Debug {
t.Fatalf("expected to have debug %v; got %v", expect.Debug, g.Debug)
}
if !durationPtrEqual(g.EvalDelay, expect.EvalDelay) {
t.Fatalf("expected to have eval_delay %v; got %v", expect.EvalDelay, g.EvalDelay)
}
if !boolPtrEqual(g.evalAlignment, expect.evalAlignment) {
t.Fatalf("expected to have eval_alignment %v; got %v", expect.evalAlignment, g.evalAlignment)
}
}
// new rule
@@ -243,37 +237,6 @@ func TestUpdateWith(t *testing.T) {
{Alert: "foo1", Debug: &debug},
},
})
// update group evaluation settings
evalDelay := promutil.NewDuration(time.Minute)
evalAlignment := false
f(config.Group{
Rules: []config.Rule{{
Record: "foo",
Expr: "max(up)",
}},
}, config.Group{
EvalDelay: evalDelay,
EvalAlignment: &evalAlignment,
Rules: []config.Rule{{
Record: "foo",
Expr: "min(up)",
}},
})
}
func durationPtrEqual(a, b *time.Duration) bool {
if a == nil || b == nil {
return a == b
}
return *a == *b
}
func boolPtrEqual(a, b *bool) bool {
if a == nil || b == nil {
return a == b
}
return *a == *b
}
func TestUpdateDuringRandSleep(t *testing.T) {

View File

@@ -208,11 +208,7 @@ func (rr *RecordingRule) exec(ctx context.Context, ts time.Time, limit int) ([]p
return nil, curState.Err
}
seriesFetched := 0
if res.SeriesFetched != nil {
seriesFetched = *res.SeriesFetched
}
rr.logDebugf(ts, "query returned %d samples (series_fetched: %d, elapsed: %s, isPartial: %t)", curState.Samples, seriesFetched, curState.Duration, isPartialResponse(res))
rr.logDebugf(ts, "query returned %d samples (elapsed: %s, isPartial: %t)", curState.Samples, curState.Duration, isPartialResponse(res))
qMetrics := res.Data
numSeries := len(qMetrics)

View File

@@ -457,10 +457,12 @@ func TestSetIntervalAsTimeFilter(t *testing.T) {
f(`* | count()`, "vlogs", true)
f(`error OR _time:5m | count()`, "vlogs", true)
f(`(_time: 5m AND error) OR (_time: 5m AND warn) | count()`, "vlogs", true)
f(`* | error OR _time:5m | count()`, "vlogs", true)
f(`_time:5m | count()`, "vlogs", false)
f(`_time:2023-04-25T22:45:59Z | count()`, "vlogs", false)
f(`error AND _time:5m | count()`, "vlogs", false)
f(`* | error AND _time:5m | count()`, "vlogs", false)
}
func TestRecordingRuleExec_Partial(t *testing.T) {

View File

@@ -4,14 +4,12 @@ import (
"context"
"errors"
"fmt"
"net/http"
"sync"
"time"
"github.com/VictoriaMetrics/metrics"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/remotewrite"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
)
@@ -120,7 +118,7 @@ func (s *ruleState) add(e StateEntry) {
s.entries[s.cur] = e
}
func replayRule(r Rule, start, end time.Time, rw remotewrite.RWClient, replayRuleRetryAttempts int, continueWithExecutionErr bool) (int, error) {
func replayRule(r Rule, start, end time.Time, rw remotewrite.RWClient, replayRuleRetryAttempts int) (int, error) {
var err error
var tss []prompb.TimeSeries
for i := range replayRuleRetryAttempts {
@@ -128,22 +126,6 @@ func replayRule(r Rule, start, end time.Time, rw remotewrite.RWClient, replayRul
if err == nil {
break
}
// retry request if possible to tolerate temporary network or datasource unavailability issues
var esc *httpserver.ErrorWithStatusCode
if errors.As(err, &esc) {
statusCode := esc.StatusCode
// if the status code is 400 or 422, the query failed due to reasons such as an expression syntax error or a resource limit being hit,
// rather than datasource unavailability.
// Continue replaying but skip the problematic execution if continueWithExecutionErr is true, otherwise, return the error without retry.
if statusCode == http.StatusUnprocessableEntity || statusCode == http.StatusBadRequest {
if continueWithExecutionErr {
logger.Errorf("rule %q: %s", r, err)
return 0, nil
} else {
return 0, err
}
}
}
logger.Errorf("attempt %d to execute rule %q failed: %s", i+1, r, err)
time.Sleep(time.Second)
}

View File

@@ -75,13 +75,10 @@ type GroupAlerts struct {
// ApiRule represents a Rule for web view
// see https://github.com/prometheus/compliance/blob/main/alert_generator/specification.md#get-apiv1rules
type ApiRule struct {
// Rule state must be one of these under following scenarios:
// "pending": at least 1 alert in the rule in pending state and no other alert in firing state. (only for alerting rules)
// "firing": at least 1 alert in the rule in firing state. (only for alerting rules)
// "inactive": rule's last evaluation was successful but no alert in the rule in firing or pending state. (only for alerting rules)
// "unhealthy": rule's last evaluation was failed with error. (for both alerting and recording rules)
// "nomatch": rule's last evaluation was successful but no time series matched the rule's expression. (for both alerting and recording rules)
// "ok": the recording rule's last evaluation was successful. (only for recording rules)
// State must be one of these under following scenarios
// "pending": at least 1 alert in the rule in pending state and no other alert in firing ruleState.
// "firing": at least 1 alert in the rule in firing state.
// "inactive": no alert in the rule in firing or pending state.
State string `json:"state"`
Name string `json:"name"`
// Query represents Rule's `expression` field
@@ -240,7 +237,6 @@ func NewAlertAPI(ar *AlertingRule, a *notifier.Alert) *ApiAlert {
}
func (r *ApiRule) ExtendState() {
// if alerting rule already has alerts, then state is already set to either "pending" or "firing" and we don't need to change it
if len(r.Alerts) > 0 {
return
}

View File

@@ -115,7 +115,7 @@ func (rh *requestHandler) handler(w http.ResponseWriter, r *http.Request) bool {
}
WriteRule(w, r, rule)
return true
// used by old vmalert UI
// current used by old vmalert UI and Grafana Alerts
case "/vmalert/groups", "/rules":
rf, err := newRulesFilter(r)
if err != nil {
@@ -128,8 +128,6 @@ func (rh *requestHandler) handler(w http.ResponseWriter, r *http.Request) bool {
state = rf.states[0]
rf.states = rf.states[:1]
}
// enable extendedStates by default for vmalert UI
rf.extendedStates = true
lr := rh.groups(rf)
WriteListGroups(w, r, lr.Data.Groups, state)
return true
@@ -545,8 +543,6 @@ func (rh *requestHandler) groups(rf *rulesFilter) *listGroupsResponse {
if !groupFound && !strings.Contains(strings.ToLower(rule.Name), rf.search) {
continue
}
// extendedStates is used by the vmalert UI to extend the rule state with values such as "nomatch" and "unhealthy".
// those states are not supported by Grafana and not part of the Prometheus API spec yet
if rf.extendedStates {
rule.ExtendState()
}

View File

@@ -130,12 +130,9 @@
data-bs-target="#item-{%s g.ID %}"
>
<span class="d-flex gap-2">
{% if g.States["inactive"] > 0 %}<span class="badge bg-light text-success border border-success" title="None of the alert instances is in a pending or firing state">{%d g.States["inactive"] %} inactive</span> {% endif %}
{% if g.States["pending"] > 0 %}<span class="badge bg-warning text-dark" title="At least one alert instance is pending">{%d g.States["pending"] %} pending</span> {% endif %}
{% if g.States["firing"] > 0 %}<span class="badge bg-danger" title="At least one alert instance is firing">{%d g.States["firing"] %} firing</span> {% endif %}
{% if g.States["ok"] > 0 %}<span class="badge bg-success" title="Recording rule last evaluation succeeded">{%d g.States["ok"] %} ok</span>{% endif %}
{% if g.States["unhealthy"] > 0 %}<span class="badge bg-danger" title="Last evaluation failed with an error">{%d g.States["unhealthy"] %} unhealthy</span> {% endif %}
{% if g.States["nomatch"] > 0 %}<span class="badge bg-warning" title="Rule expression matched no time series">{%d g.States["nomatch"] %} nomatch</span> {% endif %}
{% if g.States["unhealthy"] > 0 %}<span class="badge bg-danger" title="Number of rules with status Error">{%d g.States["unhealthy"] %}</span> {% endif %}
{% if g.States["nomatch"] > 0 %}<span class="badge bg-warning" title="Number of rules with status NoMatch">{%d g.States["nomatch"] %}</span> {% endif %}
<span class="badge bg-success" title="Number of rules with status Ok">{%d g.States["ok"] %}</span>
</span>
</span>
</span>
@@ -172,7 +169,7 @@
<thead>
<tr>
<th scope="col" class="w-60">Rule</th>
<th scope="col" class="w-20" class="text-center" title="How many series were produced by the rule">Series Returned</th>
<th scope="col" class="w-20" class="text-center" title="How many series were produced by the rule">Series</th>
<th scope="col" class="w-20" class="text-center" title="How many seconds ago rule was executed">Updated</th>
</tr>
</thead>
@@ -191,21 +188,8 @@
{% else %}
<b>record:</b> {%s r.Name %}
{% endif %}
{% if r.State == "inactive" %}
<span><a class="badge bg-success">{%s r.State %}</a></span>
{% elseif r.State == "pending" %}
<span><a class="badge bg-warning">{%s r.State %}</a></span>
{% elseif r.State == "firing" %}
<span><a class="badge bg-danger">{%s r.State %}</a></span>
{% elseif r.State == "ok" %}
<span><a class="badge bg-success">{%s r.State %}</a></span>
{% elseif r.State == "unhealthy" %}
<span><a class="badge bg-danger">{%s r.State %}</a></span>
{% elseif r.State == "nomatch" %}
<span><a class="badge bg-warning">{%s r.State %}</a></span>
{% endif %}
{%= seriesFetchedWarn(prefix, &r) %}
|
{%= seriesFetchedWarn(prefix, &r) %}
<span><a target="_blank" href="{%s prefix+r.WebLink() %}">Details</a></span>
</div>
<div class="col-12">

File diff suppressed because it is too large Load Diff

View File

@@ -58,9 +58,12 @@ var (
type AuthConfig struct {
Users []UserInfo `yaml:"users,omitempty"`
UnauthorizedUser *UserInfo `yaml:"unauthorized_user,omitempty"`
SSO SSOConfig `yaml:"sso,omitempty"`
// ms holds all the metrics for the given AuthConfig
ms *metrics.Set
oidcDP *oidcDiscovererPool
}
// UserInfo is user information read from authConfigPath
@@ -118,10 +121,9 @@ type AccessLogFilters struct {
}
func (ui *UserInfo) logRequest(r *http.Request, userName string, statusCode int, duration time.Duration) {
if ui == nil || ui.AccessLog == nil {
if ui.AccessLog == nil {
return
}
filters := ui.AccessLog.Filters
if filters != nil && len(filters.SkipStatusCodes) > 0 {
if slices.Contains(filters.SkipStatusCodes, statusCode) {
@@ -135,17 +137,6 @@ func (ui *UserInfo) logRequest(r *http.Request, userName string, statusCode int,
r.Host, requestURI, statusCode, remoteAddr, r.UserAgent(), r.Referer(), duration.Milliseconds(), userName)
}
// hasAnyURLs reports whether ui has at least one backend URL route configured.
// It is used only for unauthorized_user config section, since other users
// must always have either URLPrefix or URLMaps set.
func (ui *UserInfo) hasAnyURLs() bool {
if ui == nil {
return false
}
return ui.URLPrefix != nil || len(ui.URLMaps) > 0 || ui.DefaultURL != nil
}
// HeadersConf represents config for request and response headers.
type HeadersConf struct {
RequestHeaders []*Header `yaml:"headers,omitempty"`
@@ -923,12 +914,25 @@ func reloadAuthConfigData(data []byte) (bool, error) {
return false, fmt.Errorf("failed to parse auth config: %w", err)
}
oidcDP := &oidcDiscovererPool{}
jui, err := parseJWTUsers(ac, oidcDP)
if err := validateSSOConfigs(ac.SSO); err != nil {
return false, fmt.Errorf("invalid SSO config: %w", err)
}
jui, oidcDP, err := parseJWTUsers(ac)
if err != nil {
return false, fmt.Errorf("failed to parse JWT users from auth config: %w", err)
}
ac.oidcDP = oidcDP
// Register SSO issuers with the OIDC discoverer pool so their discovery
// runs together with JWT users during startDiscovery below.
for _, cfg := range ac.SSO {
oidcDP.createOrAdd(cfg.OpenIDConnect.Issuer, nil)
}
oidcDP.startDiscovery()
jwtc := &jwtCache{
users: jui,
oidcDP: oidcDP,
@@ -995,11 +999,8 @@ func parseAuthConfig(data []byte) (*AuthConfig, error) {
if err := parseJWTPlaceholdersForUserInfo(ui, false); err != nil {
return nil, err
}
if ui.hasAnyURLs() {
if err := ui.initURLs(); err != nil {
return nil, err
}
if err := ui.initURLs(); err != nil {
return nil, err
}
metricLabels, err := ui.getMetricLabels()

View File

@@ -140,18 +140,6 @@ users:
- "ProjectID: {{.MetricsProjectID}}"
url_prefix: "http://vminsert:8480/insert/prometheus"
# JWT-based routing that relies solely on custom claims.
# The `vm_access` claim is missing, default value will be used.
# e.g. {"role": "admin"}.
- name: jwt-custom-claims
jwt:
skip_verify: true
vm_default_access_claim:
metrics_account_id: 1
match_claims:
role: admin
url_prefix: "http://vmselect-admin:8481/select/0/prometheus"
# Requests without Authorization header are proxied according to `unauthorized_user` section.
# Requests are proxied in round-robin fashion between `url_prefix` backends.
# The deny_partial_response query arg is added to all the proxied requests.

View File

@@ -65,8 +65,6 @@ type JWTConfig struct {
MatchClaims map[string]string `yaml:"match_claims,omitempty"`
parsedMatchClaims []*jwt.Claim
DefaultVMAccessClaim *jwt.VMAccessClaim `yaml:"default_vm_access_claim,omitempty"`
// verifierPool is used to verify JWT tokens.
// It is initialized from PublicKeys and/or PublicKeyFiles.
// In this case, it is initialized once at config reload and never updated until next reload
@@ -74,8 +72,9 @@ type JWTConfig struct {
verifierPool atomic.Pointer[jwt.VerifierPool]
}
func parseJWTUsers(ac *AuthConfig, oidcDP *oidcDiscovererPool) ([]*UserInfo, error) {
func parseJWTUsers(ac *AuthConfig) ([]*UserInfo, *oidcDiscovererPool, error) {
jui := make([]*UserInfo, 0, len(ac.Users))
oidcDP := &oidcDiscovererPool{}
uniqClaims := make(map[string]*UserInfo)
var sortedClaims []string
@@ -86,10 +85,10 @@ func parseJWTUsers(ac *AuthConfig, oidcDP *oidcDiscovererPool) ([]*UserInfo, err
}
if ui.AuthToken != "" || ui.BearerToken != "" || ui.Username != "" || ui.Password != "" {
return nil, fmt.Errorf("auth_token, bearer_token, username and password cannot be specified if jwt is set")
return nil, nil, fmt.Errorf("auth_token, bearer_token, username and password cannot be specified if jwt is set")
}
if len(jwtToken.PublicKeys) == 0 && len(jwtToken.PublicKeyFiles) == 0 && !jwtToken.SkipVerify && jwtToken.OIDC == nil {
return nil, fmt.Errorf("jwt must contain at least a single public key, public_key_files, oidc or have skip_verify=true")
return nil, nil, fmt.Errorf("jwt must contain at least a single public key, public_key_files, oidc or have skip_verify=true")
}
var claimsString string
sortedClaims = sortedClaims[:0]
@@ -98,7 +97,7 @@ func parseJWTUsers(ac *AuthConfig, oidcDP *oidcDiscovererPool) ([]*UserInfo, err
sortedClaims = append(sortedClaims, fmt.Sprintf("%s=%s", ck, cv))
pc, err := jwt.NewClaim(ck, cv)
if err != nil {
return nil, fmt.Errorf("incorrect match claim, key=%q, value regex=%q: %w", ck, cv, err)
return nil, nil, fmt.Errorf("incorrect match claim, key=%q, value regex=%q: %w", ck, cv, err)
}
parsedClaims = append(parsedClaims, pc)
}
@@ -107,7 +106,7 @@ func parseJWTUsers(ac *AuthConfig, oidcDP *oidcDiscovererPool) ([]*UserInfo, err
claimsString = strings.Join(sortedClaims, ",")
if oldUI, ok := uniqClaims[claimsString]; ok {
return nil, fmt.Errorf("duplicate match claims=%q found for name=%q at idx=%d; the previous one is set for name=%q", claimsString, ui.Name, idx, oldUI.Name)
return nil, nil, fmt.Errorf("duplicate match claims=%q found for name=%q at idx=%d; the previous one is set for name=%q", claimsString, ui.Name, idx, oldUI.Name)
}
uniqClaims[claimsString] = &ui
if len(jwtToken.PublicKeys) > 0 || len(jwtToken.PublicKeyFiles) > 0 {
@@ -116,7 +115,7 @@ func parseJWTUsers(ac *AuthConfig, oidcDP *oidcDiscovererPool) ([]*UserInfo, err
for i := range jwtToken.PublicKeys {
k, err := jwt.ParseKey([]byte(jwtToken.PublicKeys[i]))
if err != nil {
return nil, err
return nil, nil, err
}
keys = append(keys, k)
}
@@ -124,52 +123,52 @@ func parseJWTUsers(ac *AuthConfig, oidcDP *oidcDiscovererPool) ([]*UserInfo, err
for _, filePath := range jwtToken.PublicKeyFiles {
keyData, err := os.ReadFile(filePath)
if err != nil {
return nil, fmt.Errorf("cannot read public key from file %q: %w", filePath, err)
return nil, nil, fmt.Errorf("cannot read public key from file %q: %w", filePath, err)
}
k, err := jwt.ParseKey(keyData)
if err != nil {
return nil, fmt.Errorf("cannot parse public key from file %q: %w", filePath, err)
return nil, nil, fmt.Errorf("cannot parse public key from file %q: %w", filePath, err)
}
keys = append(keys, k)
}
vp, err := jwt.NewVerifierPool(keys)
if err != nil {
return nil, err
return nil, nil, err
}
jwtToken.verifierPool.Store(vp)
}
if jwtToken.OIDC != nil {
if len(jwtToken.PublicKeys) > 0 || len(jwtToken.PublicKeyFiles) > 0 || jwtToken.SkipVerify {
return nil, fmt.Errorf("jwt with oidc cannot contain public keys or have skip_verify=true")
return nil, nil, fmt.Errorf("jwt with oidc cannot contain public keys or have skip_verify=true")
}
if jwtToken.OIDC.Issuer == "" {
return nil, fmt.Errorf("oidc issuer cannot be empty")
return nil, nil, fmt.Errorf("oidc issuer cannot be empty")
}
isserURL, err := url.Parse(jwtToken.OIDC.Issuer)
if err != nil {
return nil, fmt.Errorf("oidc issuer %q must be a valid URL", jwtToken.OIDC.Issuer)
return nil, nil, fmt.Errorf("oidc issuer %q must be a valid URL", jwtToken.OIDC.Issuer)
}
if isserURL.Scheme != "https" && isserURL.Scheme != "http" {
return nil, fmt.Errorf("oidc issuer %q must have http or https scheme", jwtToken.OIDC.Issuer)
return nil, nil, fmt.Errorf("oidc issuer %q must have http or https scheme", jwtToken.OIDC.Issuer)
}
oidcDP.createOrAdd(ui.JWT.OIDC.Issuer, &ui.JWT.verifierPool)
}
if err := parseJWTPlaceholdersForUserInfo(&ui, true); err != nil {
return nil, err
return nil, nil, err
}
if err := ui.initURLs(); err != nil {
return nil, err
return nil, nil, err
}
metricLabels, err := ui.getMetricLabels()
if err != nil {
return nil, fmt.Errorf("cannot parse metric_labels: %w", err)
return nil, nil, fmt.Errorf("cannot parse metric_labels: %w", err)
}
ui.requests = ac.ms.GetOrCreateCounter(`vmauth_user_requests_total` + metricLabels)
ui.requestErrors = ac.ms.GetOrCreateCounter(`vmauth_user_request_errors_total` + metricLabels)
@@ -188,7 +187,7 @@ func parseJWTUsers(ac *AuthConfig, oidcDP *oidcDiscovererPool) ([]*UserInfo, err
rt, err := newRoundTripper(ui.TLSCAFile, ui.TLSCertFile, ui.TLSKeyFile, ui.TLSServerName, ui.TLSInsecureSkipVerify)
if err != nil {
return nil, fmt.Errorf("cannot initialize HTTP RoundTripper: %w", err)
return nil, nil, fmt.Errorf("cannot initialize HTTP RoundTripper: %w", err)
}
ui.rt = rt
@@ -201,7 +200,7 @@ func parseJWTUsers(ac *AuthConfig, oidcDP *oidcDiscovererPool) ([]*UserInfo, err
return len(jui[i].JWT.MatchClaims) > len(jui[j].JWT.MatchClaims)
})
return jui, nil
return jui, oidcDP, nil
}
var tokenPool sync.Pool
@@ -434,6 +433,7 @@ func validateJWTPlaceholdersForURL(up *URLPrefix, isAllowed bool) error {
}
if strings.Contains(p, placeholderPrefix) {
return fmt.Errorf("invalid placeholder found in URL request path: %q, supported values are: %s", bu.Path, strings.Join(allPlaceholders, ", "))
}
}
for param, values := range bu.Query() {
@@ -488,6 +488,7 @@ func hasAnyPlaceholders(u *url.URL) bool {
return true
}
}
}
return false
}

View File

@@ -39,14 +39,16 @@ XOtclIk1uhc03oL9nOQ=
}
return
}
oidcDP := &oidcDiscovererPool{}
users, err := parseJWTUsers(ac, oidcDP)
users, oidcDP, err := parseJWTUsers(ac)
if err == nil {
t.Fatalf("expecting non-nil error; got %v", users)
}
if expErr != err.Error() {
t.Fatalf("unexpected error; got\n%q\nwant \n%q", err.Error(), expErr)
}
if oidcDP != nil {
t.Fatalf("expecting nil oidcDP; got %v", oidcDP)
}
}
// unauthorized_user cannot be used with jwt
@@ -324,8 +326,7 @@ XOtclIk1uhc03oL9nOQ=
t.Fatalf("unexpected error: %s", err)
}
oidcDP := &oidcDiscovererPool{}
jui, err := parseJWTUsers(ac, oidcDP)
jui, oidcDP, err := parseJWTUsers(ac)
if err != nil {
t.Fatalf("unexpected error: %s", err)
}

View File

@@ -6,7 +6,7 @@ import (
"flag"
"fmt"
"io"
"math/rand/v2"
"log"
"net"
"net/http"
"net/textproto"
@@ -32,7 +32,6 @@ import (
"github.com/VictoriaMetrics/VictoriaMetrics/lib/procutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promauth"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/pushmetrics"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/timerpool"
)
var (
@@ -96,7 +95,6 @@ func main() {
flag.CommandLine.SetOutput(os.Stdout)
flag.Usage = usage
envflag.Parse()
initSecretFlags()
buildinfo.Init()
logger.Init()
@@ -172,16 +170,36 @@ func requestHandlerWithInternalRoutes(w http.ResponseWriter, r *http.Request) bo
}
func requestHandler(w http.ResponseWriter, r *http.Request) bool {
// Handle SSO callback before any auth checks.
if r.URL.Path == "/_vmauth/sso/callback" {
handleSSOCallback(w, r)
return true
}
ats := getAuthTokensFromRequest(r)
log.Println(51)
// Inject the SSO session cookie as a Bearer token so that the existing
// JWT pipeline can validate it and match it to a configured user.
if tok := ssoAuthTokenFromRequest(r); tok != "" {
log.Println(52, tok)
ats = append(ats, tok)
}
if len(ats) == 0 {
// Process requests for unauthorized users
ui := authConfig.Load().UnauthorizedUser
if ui.hasAnyURLs() {
if ui != nil {
processUserRequest(w, r, ui, nil)
return true
}
ui.logRequest(r, `unauthorized`, http.StatusUnauthorized, 0)
log.Println(1)
if cfg := ssoConfigForHost(r.Host); cfg != nil {
log.Println(2)
showSSOLoginPage(w, r, cfg)
return true
}
log.Println(3)
handleMissingAuthorizationError(w)
return true
}
@@ -195,23 +213,22 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
logger.Panicf("BUG: unexpected nil jwt token for user %q", ui.name())
}
defer putToken(tkn)
// Call processUserRequest only if the token contains the vm_access claim
// or a default claim is configured; otherwise fall through to unauthorized_user.
if tkn.HasVMAccessClaim() || ui.JWT.DefaultVMAccessClaim != nil {
processUserRequest(w, r, ui, tkn)
return true
}
processUserRequest(w, r, ui, tkn)
return true
}
uu := authConfig.Load().UnauthorizedUser
if uu.hasAnyURLs() {
if uu != nil {
processUserRequest(w, r, uu, nil)
return true
}
if cfg := ssoConfigForHost(r.Host); cfg != nil {
showSSOLoginPage(w, r, cfg)
return true
}
invalidAuthTokenRequests.Inc()
slowdownUnauthorizedResponse(r)
uu.logRequest(r, `unauthorized`, http.StatusUnauthorized, 0)
if *logInvalidAuthTokens {
err := fmt.Errorf("cannot authorize request with auth tokens %q", ats)
err = &httpserver.ErrorWithStatusCode{
@@ -387,7 +404,7 @@ func bufferRequestBody(ctx context.Context, r io.ReadCloser, userName string) (i
return nil, &httpserver.ErrorWithStatusCode{
Err: fmt.Errorf("reject request from the user %s because the request body couldn't be read in -maxQueueDuration=%s; read %d bytes in %s",
userName, *maxQueueDuration, len(buf), d.Truncate(time.Second)),
StatusCode: http.StatusRequestTimeout,
StatusCode: http.StatusBadRequest,
}
}
@@ -434,12 +451,8 @@ func processRequest(w http.ResponseWriter, r *http.Request, ui *UserInfo, tkn *j
}
targetURL := bu.url
if tkn != nil {
vmac := tkn.VMAccess()
if !tkn.HasVMAccessClaim() {
vmac = ui.JWT.DefaultVMAccessClaim
}
// for security reasons allow templating only for configured url values and headers
targetURL, hc = replaceJWTPlaceholders(bu, hc, vmac)
targetURL, hc = replaceJWTPlaceholders(bu, hc, tkn.VMAccess())
}
if isDefault {
// Don't change path and add request_path query param for default route.
@@ -895,25 +908,3 @@ func debugInfo(u *url.URL, r *http.Request) string {
fmt.Fprint(s, ")")
return s.String()
}
// slowdownUnauthorizedResponse adds a random delay in the [2..3] seconds range before returning an unauthorized response.
// This reduces the effectiveness of brute-force.
//
// Recommended by OWASP Top10:
// https://owasp.org/Top10/2025/A07_2025-Authentication_Failures
func slowdownUnauthorizedResponse(r *http.Request) {
d := 2*time.Second + time.Duration(rand.IntN(1000))*time.Millisecond
t := timerpool.Get(d)
select {
case <-t.C:
case <-r.Context().Done():
}
timerpool.Put(t)
}
// initSecretFlags manages the secret flags for this app and must be called after flag parsing and before logger init.
func initSecretFlags() {
pushmetrics.InitSecretFlags()
}

View File

@@ -1,54 +0,0 @@
//go:build synctest
package main
import (
"context"
"net/http"
"testing"
"testing/synctest"
"time"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
)
func TestBufferRequestBody_Timeout(t *testing.T) {
synctest.Test(t, func(t *testing.T) {
defaultMaxQueueDuration := *maxQueueDuration
defer func() {
*maxQueueDuration = defaultMaxQueueDuration
}()
*maxQueueDuration = 100 * time.Millisecond
ctx, cancel := context.WithTimeout(context.Background(), *maxQueueDuration)
defer cancel()
_, err := bufferRequestBody(ctx, &timeoutBody{delay: *maxQueueDuration + 100*time.Millisecond}, "foo")
if err == nil {
t.Fatalf("expecting non-nil error")
}
esc, ok := err.(*httpserver.ErrorWithStatusCode)
if !ok {
t.Fatalf("unexpected error type: %s", err)
}
if esc.StatusCode != http.StatusRequestTimeout {
t.Fatalf("read request body timeout meet unexpected status code; got %d; want %d", esc.StatusCode, http.StatusRequestTimeout)
}
})
}
type timeoutBody struct {
delay time.Duration
}
func (r *timeoutBody) Read(_ []byte) (int, error) {
time.Sleep(r.delay)
return 0, context.DeadlineExceeded
}
func (r *timeoutBody) Close() error {
return nil
}

View File

@@ -739,12 +739,6 @@ users:
"vm_access": map[string]any{},
}, false)
// token without vm_access claim, but with a custom claim usable for routing
roleToken := genToken(t, map[string]any{
"exp": time.Now().Add(10 * time.Minute).Unix(),
"role": "admin",
}, true)
fullToken := genToken(t, map[string]any{
"exp": time.Now().Add(10 * time.Minute).Unix(),
"vm_access": map[string]any{
@@ -785,45 +779,6 @@ statusCode=401
Unauthorized`
f(simpleCfgStr, request, responseExpected)
// token without vm_access claim should fall through to unauthorized_user
request = httptest.NewRequest(`GET`, "http://some-host.com/abc", nil)
request.Header.Set(`Authorization`, `Bearer `+noVMAccessClaimToken)
responseExpected = `
statusCode=200
path: /bar/abc
query:
headers:`
f(fmt.Sprintf(`
unauthorized_user:
url_prefix: {BACKEND}/bar
users:
- jwt:
public_keys:
- %q
match_claims:
role: admin
url_prefix: {BACKEND}/foo`, string(publicKeyPEM)), request, responseExpected)
// token without vm_access claim is accepted when default_vm_access_claim configured
request = httptest.NewRequest(`GET`, "http://some-host.com/abc", nil)
request.Header.Set(`Authorization`, `Bearer `+roleToken)
responseExpected = `
statusCode=200
path: /foo/abc
query:
headers:`
f(fmt.Sprintf(`
users:
- jwt:
public_keys:
- %q
default_vm_access_claim:
metrics_account_id: 10
metrics_project_id: 10
match_claims:
role: admin
url_prefix: {BACKEND}/foo`, string(publicKeyPEM)), request, responseExpected)
// expired token
request = httptest.NewRequest(`GET`, "http://some-host.com/abc", nil)
request.Header.Set(`Authorization`, `Bearer `+expiredToken)

View File

@@ -44,7 +44,19 @@ func (dp *oidcDiscovererPool) createOrAdd(issuer string, vp *atomic.Pointer[jwt.
dp.ds[issuer] = ds
}
ds.vps = append(ds.vps, vp)
if vp != nil {
ds.vps = append(ds.vps, vp)
}
}
// openIDConfig returns the most recently discovered openidConfig for the given issuer,
// or nil if the issuer is not registered or discovery has not completed yet.
func (dp *oidcDiscovererPool) openIDConfig(issuer string) *openidConfig {
d := dp.ds[issuer]
if d == nil {
return nil
}
return d.cfg.Load()
}
func (dp *oidcDiscovererPool) startDiscovery() {
@@ -80,6 +92,7 @@ func (dp *oidcDiscovererPool) stopDiscovery() {
type oidcDiscoverer struct {
issuer string
vps []*atomic.Pointer[jwt.VerifierPool]
cfg atomic.Pointer[openidConfig]
}
func (d *oidcDiscoverer) run(ctx context.Context) {
@@ -117,21 +130,26 @@ func (d *oidcDiscoverer) refreshVerifierPools(ctx context.Context) error {
return fmt.Errorf("openid configuration issuer %q does not match expected issuer %q", cfg.Issuer, d.issuer)
}
verifierPool, err := fetchAndParseJWKs(ctx, cfg.JWKsURI)
if err != nil {
return err
}
d.cfg.Store(&cfg)
for _, vp := range d.vps {
vp.Store(verifierPool)
if len(d.vps) > 0 {
verifierPool, err := fetchAndParseJWKs(ctx, cfg.JWKsURI)
if err != nil {
return err
}
for _, vp := range d.vps {
vp.Store(verifierPool)
}
}
return nil
}
// See https://openid.net/specs/openid-connect-discovery-1_0.html#ProviderMetadata for details.
type openidConfig struct {
Issuer string `json:"issuer"`
JWKsURI string `json:"jwks_uri"`
Issuer string `json:"issuer"`
JWKsURI string `json:"jwks_uri"`
AuthorizationEndpoint string `json:"authorization_endpoint"`
TokenEndpoint string `json:"token_endpoint"`
}
var oidcHTTPClient = &http.Client{

320
app/vmauth/sso.go Normal file
View File

@@ -0,0 +1,320 @@
package main
import (
"context"
"crypto/hmac"
"crypto/rand"
"crypto/sha256"
"encoding/base64"
"encoding/json"
"fmt"
"html/template"
"io"
"log"
"net/http"
"net/url"
"strings"
"time"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
)
// SSOConfig maps hostname to its SSO configuration.
type SSOConfig map[string]*SSOHostConfig
// SSOHostConfig holds the SSO configuration for a single host.
type SSOHostConfig struct {
OpenIDConnect *OIDCConnectConfig `yaml:"openid_connect"`
}
// OIDCConnectConfig is the OpenID Connect configuration for SSO.
type OIDCConnectConfig struct {
Issuer string `yaml:"issuer"`
ClientID string `yaml:"client_id"`
ClientSecret string `yaml:"client_secret"`
// RedirectURL is optional. Defaults to https://{host}/_vmauth/sso/callback.
RedirectURL string `yaml:"redirect_url,omitempty"`
// Scopes defaults to ["openid"] when not set.
Scopes []string `yaml:"scopes,omitempty"`
// filled from OIDC discovery at init time
authEndpoint string
tokenEndpoint string
}
// validateSSOConfigs checks that all required fields are present in SSO configs.
func validateSSOConfigs(sso SSOConfig) error {
for host, cfg := range sso {
if cfg.OpenIDConnect == nil {
return fmt.Errorf("missing openid_connect config for sso host %q", host)
}
oidc := cfg.OpenIDConnect
if oidc.Issuer == "" {
return fmt.Errorf("missing issuer in openid_connect config for sso host %q", host)
}
if oidc.ClientID == "" {
return fmt.Errorf("missing client_id in openid_connect config for sso host %q", host)
}
if oidc.ClientSecret == "" {
return fmt.Errorf("missing client_secret in openid_connect config for sso host %q", host)
}
}
return nil
}
// ssoConfigForHost returns the SSO host config for the given request host, or nil.
func ssoConfigForHost(host string) *SSOHostConfig {
// Strip port, e.g. "foo.com:8427" -> "foo.com"
if i := strings.LastIndexByte(host, ':'); i >= 0 {
host = host[:i]
}
ac := authConfig.Load()
if ac == nil || ac.SSO == nil {
log.Println(21)
return nil
}
ssoh := ac.SSO[host]
if ssoh == nil || ssoh.OpenIDConnect == nil {
log.Println(22)
return nil
}
oidcCfg := ac.oidcDP.openIDConfig(ssoh.OpenIDConnect.Issuer)
if oidcCfg == nil {
log.Println(24)
return nil
}
ssoh.OpenIDConnect.authEndpoint = oidcCfg.AuthorizationEndpoint
ssoh.OpenIDConnect.tokenEndpoint = oidcCfg.TokenEndpoint
log.Println(25)
return ssoh
}
// ssoStatePayload is the CSRF state payload embedded in the OIDC state parameter.
type ssoStatePayload struct {
Nonce string `json:"n"`
OriginalURL string `json:"u"`
IssuedAt int64 `json:"t"`
}
const (
ssoStateTTL = 10 * time.Minute
ssoCookieName = "_vmauth_sso"
)
// buildSSOState builds a signed, self-contained state value safe to use across
// multiple vmauth instances behind a load balancer.
//
// Format: base64url(JSON(payload)) "." base64url(HMAC-SHA256(clientSecret, payload))
func buildSSOState(originalURL, clientSecret string) (string, error) {
nonce := make([]byte, 16)
if _, err := rand.Read(nonce); err != nil {
return "", fmt.Errorf("cannot generate nonce: %w", err)
}
p := ssoStatePayload{
Nonce: base64.RawURLEncoding.EncodeToString(nonce),
OriginalURL: originalURL,
IssuedAt: time.Now().Unix(),
}
payloadJSON, err := json.Marshal(p)
if err != nil {
return "", err
}
payloadEnc := base64.RawURLEncoding.EncodeToString(payloadJSON)
mac := hmac.New(sha256.New, []byte(clientSecret))
mac.Write([]byte(payloadEnc))
sig := base64.RawURLEncoding.EncodeToString(mac.Sum(nil))
return payloadEnc + "." + sig, nil
}
// verifySSOState verifies the state signature and expiry, returning the original URL.
func verifySSOState(state, clientSecret string) (string, error) {
dot := strings.LastIndexByte(state, '.')
if dot < 0 {
return "", fmt.Errorf("invalid state: missing separator")
}
payloadEnc := state[:dot]
sig := state[dot+1:]
mac := hmac.New(sha256.New, []byte(clientSecret))
mac.Write([]byte(payloadEnc))
expectedSig := base64.RawURLEncoding.EncodeToString(mac.Sum(nil))
if !hmac.Equal([]byte(sig), []byte(expectedSig)) {
return "", fmt.Errorf("invalid state signature")
}
payloadJSON, err := base64.RawURLEncoding.DecodeString(payloadEnc)
if err != nil {
return "", fmt.Errorf("cannot decode state payload: %w", err)
}
var p ssoStatePayload
if err := json.Unmarshal(payloadJSON, &p); err != nil {
return "", fmt.Errorf("cannot unmarshal state payload: %w", err)
}
if time.Since(time.Unix(p.IssuedAt, 0)) > ssoStateTTL {
return "", fmt.Errorf("state expired")
}
return p.OriginalURL, nil
}
var ssoLoginPageTmpl = template.Must(template.New("sso_login").Parse(`<!DOCTYPE html>
<html>
<head><meta charset="utf-8"><title>Login</title></head>
<body>
<p><a href="{{.}}">Login with SSO</a></p>
</body>
</html>`))
// showSSOLoginPage renders a minimal HTML page with a single "Login with SSO"
// button pointing directly to the OIDC provider's authorization endpoint.
func showSSOLoginPage(w http.ResponseWriter, r *http.Request, cfg *SSOHostConfig) {
oidc := cfg.OpenIDConnect
if oidc == nil || oidc.authEndpoint == "" {
http.Error(w, "SSO not properly configured for this host", http.StatusInternalServerError)
return
}
state, err := buildSSOState(r.RequestURI, oidc.ClientSecret)
if err != nil {
logger.Errorf("SSO: cannot build state: %s", err)
http.Error(w, "Internal Server Error", http.StatusInternalServerError)
return
}
redirectURL := ssoRedirectURL(r, oidc)
scopes := oidc.Scopes
if len(scopes) == 0 {
scopes = []string{"openid"}
}
params := url.Values{}
params.Set("response_type", "code")
params.Set("client_id", oidc.ClientID)
params.Set("redirect_uri", redirectURL)
params.Set("scope", strings.Join(scopes, " "))
params.Set("state", state)
authURL := oidc.authEndpoint + "?" + params.Encode()
w.Header().Set("Content-Type", "text/html; charset=utf-8")
w.WriteHeader(http.StatusOK)
if err := ssoLoginPageTmpl.Execute(w, authURL); err != nil {
logger.Errorf("SSO: cannot render login page: %s", err)
}
}
// handleSSOCallback handles the OIDC authorization code callback at /_vmauth/sso/callback.
func handleSSOCallback(w http.ResponseWriter, r *http.Request) {
cfg := ssoConfigForHost(r.Host)
if cfg == nil || cfg.OpenIDConnect == nil {
http.Error(w, "SSO not configured for this host", http.StatusBadRequest)
return
}
oidc := cfg.OpenIDConnect
q := r.URL.Query()
state := q.Get("state")
if state == "" {
http.Error(w, "missing state parameter", http.StatusBadRequest)
return
}
originalURL, err := verifySSOState(state, oidc.ClientSecret)
if err != nil {
logger.Warnf("SSO callback: invalid state from %s: %s", r.RemoteAddr, err)
http.Error(w, "invalid state", http.StatusBadRequest)
return
}
code := q.Get("code")
if code == "" {
http.Error(w, "missing code parameter", http.StatusBadRequest)
return
}
idToken, err := exchangeCodeForIDToken(r.Context(), oidc, code, ssoRedirectURL(r, oidc))
if err != nil {
logger.Warnf("SSO callback: token exchange failed: %s", err)
http.Error(w, "token exchange failed", http.StatusBadRequest)
return
}
http.SetCookie(w, &http.Cookie{
Name: ssoCookieName,
Value: idToken,
Path: "/",
HttpOnly: true,
Secure: r.TLS != nil,
SameSite: http.SameSiteLaxMode,
})
if originalURL == "" {
originalURL = "/"
}
http.Redirect(w, r, originalURL, http.StatusFound)
}
type tokenResponse struct {
IDToken string `json:"id_token"`
}
// exchangeCodeForIDToken exchanges the OIDC authorization code for an id_token.
func exchangeCodeForIDToken(ctx context.Context, oidc *OIDCConnectConfig, code, redirectURL string) (string, error) {
params := url.Values{}
params.Set("grant_type", "authorization_code")
params.Set("code", code)
params.Set("redirect_uri", redirectURL)
params.Set("client_id", oidc.ClientID)
params.Set("client_secret", oidc.ClientSecret)
req, err := http.NewRequestWithContext(ctx, http.MethodPost, oidc.tokenEndpoint, strings.NewReader(params.Encode()))
if err != nil {
return "", fmt.Errorf("cannot create token request: %w", err)
}
req.Header.Set("Content-Type", "application/x-www-form-urlencoded")
resp, err := oidcHTTPClient.Do(req)
if err != nil {
return "", fmt.Errorf("token request failed: %w", err)
}
defer resp.Body.Close()
body, err := io.ReadAll(resp.Body)
if err != nil {
return "", fmt.Errorf("cannot read token response: %w", err)
}
if resp.StatusCode != http.StatusOK {
return "", fmt.Errorf("token endpoint returned status %d: %s", resp.StatusCode, body)
}
var tr tokenResponse
if err := json.Unmarshal(body, &tr); err != nil {
return "", fmt.Errorf("cannot unmarshal token response: %w", err)
}
if tr.IDToken == "" {
return "", fmt.Errorf("token response missing id_token")
}
return tr.IDToken, nil
}
// ssoAuthTokenFromRequest extracts the SSO session cookie and returns it as
// a Bearer auth token string compatible with the existing JWT pipeline.
func ssoAuthTokenFromRequest(r *http.Request) string {
c, err := r.Cookie(ssoCookieName)
if err != nil || c.Value == "" {
return ""
}
return "http_auth:Bearer " + c.Value
}
// ssoRedirectURL returns the OIDC redirect URL for the current request.
func ssoRedirectURL(r *http.Request, oidc *OIDCConnectConfig) string {
if oidc.RedirectURL != "" {
return oidc.RedirectURL
}
scheme := "https"
if r.TLS == nil {
scheme = "http"
}
return scheme + "://" + r.Host + "/_vmauth/sso/callback"
}

View File

@@ -47,8 +47,9 @@ func main() {
// Write flags and help message to stdout, since it is easier to grep or pipe.
flag.CommandLine.SetOutput(os.Stdout)
flag.Usage = usage
flagutil.RegisterSecretFlag("snapshot.createURL")
flagutil.RegisterSecretFlag("snapshot.deleteURL")
envflag.Parse()
initSecretFlags()
buildinfo.Init()
logger.Init()
@@ -272,10 +273,3 @@ func newRemoteOriginFS(ctx context.Context) (common.RemoteFS, error) {
}
return fs, nil
}
// initSecretFlags manages the secret flags for this app and must be called after flag parsing and before logger init.
func initSecretFlags() {
flagutil.RegisterSecretFlag("snapshot.createURL")
flagutil.RegisterSecretFlag("snapshot.deleteURL")
pushmetrics.InitSecretFlags()
}

View File

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

View File

@@ -259,7 +259,7 @@ func (cr *ChunkedResponse) Next() ([]int64, []float64, error) {
fieldValues, ok := r.values[cr.field]
if !ok {
return nil, nil, fmt.Errorf("response doesn't contain field %q", cr.field)
return nil, nil, fmt.Errorf("response doesn't contain filed %q", cr.field)
}
values := make([]float64, len(fieldValues))
for i, fv := range fieldValues {

View File

@@ -47,7 +47,6 @@ func main() {
start := time.Now()
beforeFn := func(c *cli.Context) error {
flag.Parse()
initSecretFlags()
logger.Init()
isSilent = c.Bool(globalSilent)
if c.Bool(globalDisableProgressBar) {
@@ -564,11 +563,11 @@ func main() {
}()
err = app.Run(os.Args)
pushmetrics.StopAndPush()
if err != nil {
log.Fatalln(err)
}
log.Printf("Total time: %v", time.Since(start))
pushmetrics.StopAndPush()
}
func initConfigVM(c *cli.Context) (vm.Config, error) {
@@ -620,8 +619,3 @@ func initConfigVM(c *cli.Context) (vm.Config, error) {
Backoff: bf,
}, nil
}
// initSecretFlags manages the secret flags for this app and must be called after flag parsing and before logger init.
func initSecretFlags() {
pushmetrics.InitSecretFlags()
}

View File

@@ -8,14 +8,12 @@ import (
"io"
"net/http"
"net/url"
"strconv"
"strings"
"time"
"github.com/gogo/protobuf/proto"
"github.com/golang/snappy"
"github.com/prometheus/prometheus/config"
"github.com/prometheus/prometheus/model/histogram"
"github.com/prometheus/prometheus/prompb"
"github.com/prometheus/prometheus/storage/remote"
"github.com/prometheus/prometheus/tsdb/chunkenc"
@@ -236,29 +234,9 @@ func processResponse(body io.ReadCloser, callback StreamCallback) error {
// shouldn't be accounted as an error.
for _, res := range readResp.Results {
for _, ts := range res.Timeseries {
// A series contains either float samples or native histogram samples.
// Both fields are processed independently, since a series may switch
// from float to native histogram representation at some point in time,
// so the requested time range may contain samples of both types.
if len(ts.Samples) > 0 {
vmTs := convertSamples(ts.Samples, ts.Labels)
if err := callback(vmTs); err != nil {
return err
}
}
if len(ts.Histograms) > 0 {
hSamples := make([]histogramSample, 0, len(ts.Histograms))
for _, h := range ts.Histograms {
hSamples = append(hSamples, histogramSample{
timestamp: h.Timestamp,
fh: h.ToFloatHistogram(),
})
}
for _, vmTs := range convertHistograms(hSamples, ts.Labels) {
if err := callback(vmTs); err != nil {
return err
}
}
vmTs := convertSamples(ts.Samples, ts.Labels)
if err := callback(vmTs); err != nil {
return err
}
}
}
@@ -285,45 +263,17 @@ func processStreamResponse(body io.ReadCloser, callback StreamCallback) error {
for _, series := range res.ChunkedSeries {
samples := make([]prompb.Sample, 0)
var hSamples []histogramSample
for _, chunk := range series.Chunks {
switch chunk.Type {
case prompb.Chunk_XOR, prompb.Chunk_UNKNOWN:
// In proto3 the `type` field may be left unset (UNKNOWN) for XOR chunks.
// Prometheus remote.proto: "REQUIREMENT: when using proto3, this field
// MUST be set when using anything else than XOR". Senders before native
// histograms support (Prometheus < 2.40) do not set this field at all,
// so UNKNOWN chunks must be parsed as XOR ones.
s, err := parseSamples(chunk.Data)
if err != nil {
return err
}
samples = append(samples, s...)
case prompb.Chunk_HISTOGRAM, prompb.Chunk_FLOAT_HISTOGRAM:
hs, err := parseHistograms(chunk.Type, chunk.Data)
if err != nil {
return err
}
hSamples = append(hSamples, hs...)
default:
return fmt.Errorf("unsupported chunk encoding %q", chunk.Type)
s, err := parseSamples(chunk.Data)
if err != nil {
return err
}
samples = append(samples, s...)
}
// A series contains either XOR chunks or native histogram chunks.
// Both are processed independently, since a series may switch
// from float to native histogram representation at some point in time,
// so the requested time range may contain chunks of both types.
if len(samples) > 0 {
ts := convertSamples(samples, series.Labels)
if err := callback(ts); err != nil {
return err
}
}
for _, ts := range convertHistograms(hSamples, series.Labels) {
if err := callback(ts); err != nil {
return err
}
ts := convertSamples(samples, series.Labels)
if err := callback(ts); err != nil {
return err
}
}
}
@@ -362,151 +312,6 @@ func parseSamples(chunk []byte) ([]prompb.Sample, error) {
return samples, it.Err()
}
// histogramSample represents a single native histogram sample.
type histogramSample struct {
timestamp int64
fh *histogram.FloatHistogram
}
func parseHistograms(encoding prompb.Chunk_Encoding, chunk []byte) ([]histogramSample, error) {
var enc chunkenc.Encoding
switch encoding {
case prompb.Chunk_HISTOGRAM:
enc = chunkenc.EncHistogram
case prompb.Chunk_FLOAT_HISTOGRAM:
enc = chunkenc.EncFloatHistogram
default:
return nil, fmt.Errorf("unsupported histogram chunk encoding %q", encoding)
}
c, err := chunkenc.FromData(enc, chunk)
if err != nil {
return nil, fmt.Errorf("error read chunk: %w", err)
}
var hSamples []histogramSample
it := c.Iterator(nil)
for {
typ := it.Next()
if typ == chunkenc.ValNone {
break
}
switch typ {
case chunkenc.ValHistogram:
ts, h := it.AtHistogram(nil)
hSamples = append(hSamples, histogramSample{
timestamp: ts,
fh: h.ToFloat(nil),
})
case chunkenc.ValFloatHistogram:
ts, fh := it.AtFloatHistogram(nil)
hSamples = append(hSamples, histogramSample{
timestamp: ts,
fh: fh,
})
default:
// Skip unsupported values
continue
}
}
if err := it.Err(); err != nil {
return nil, fmt.Errorf("error iterate over chunks: %w", err)
}
return hSamples, nil
}
// convertHistograms converts native histogram samples into VictoriaMetrics histogram
// time series in the same way as VictoriaMetrics converts native histograms
// received via Prometheus remote write protocol: every native histogram sample
// is converted into `<name>_count` and `<name>_sum` series plus a set of
// `<name>_bucket` series with `vmrange` labels containing non-cumulative bucket counts.
// The only difference is that for native histograms with custom buckets (NHCB)
// bucket bounds are taken from the custom values, while the remote write protocol
// parser ignores custom values and estimates the bounds with the exponential formula.
// See https://prometheus.io/docs/specs/native_histograms/#data-model
func convertHistograms(hSamples []histogramSample, labels []prompb.Label) []*vm.TimeSeries {
if len(hSamples) == 0 {
return nil
}
labelPairs := make([]vm.LabelPair, 0, len(labels))
nameValue := ""
for _, label := range labels {
if label.Name == "__name__" {
nameValue = label.Value
continue
}
labelPairs = append(labelPairs, vm.LabelPair{Name: label.Name, Value: label.Value})
}
// the metric has no name, skip it in the same way as VictoriaMetrics does
// when it receives a native histogram without the metric name via remote write protocol.
if nameValue == "" {
return nil
}
countSeries := &vm.TimeSeries{
Name: nameValue + "_count",
LabelPairs: labelPairs,
}
sumSeries := &vm.TimeSeries{
Name: nameValue + "_sum",
LabelPairs: labelPairs,
}
bucketSeries := make(map[string]*vm.TimeSeries)
// vmranges preserves the order of bucketSeries creation
// in order to get deterministic results.
var vmranges []string
for _, hs := range hSamples {
fh := hs.fh
countSeries.Timestamps = append(countSeries.Timestamps, hs.timestamp)
countSeries.Values = append(countSeries.Values, fh.Count)
sumSeries.Timestamps = append(sumSeries.Timestamps, hs.timestamp)
sumSeries.Values = append(sumSeries.Values, fh.Sum)
it := fh.AllBucketIterator()
for it.Next() {
b := it.At()
if b.Count <= 0 {
continue
}
vmrange := formatVmrange(b.Lower, b.Upper)
s := bucketSeries[vmrange]
if s == nil {
bucketLabelPairs := make([]vm.LabelPair, len(labelPairs), len(labelPairs)+1)
copy(bucketLabelPairs, labelPairs)
bucketLabelPairs = append(bucketLabelPairs, vm.LabelPair{Name: "vmrange", Value: vmrange})
s = &vm.TimeSeries{
Name: nameValue + "_bucket",
LabelPairs: bucketLabelPairs,
}
bucketSeries[vmrange] = s
vmranges = append(vmranges, vmrange)
}
s.Timestamps = append(s.Timestamps, hs.timestamp)
s.Values = append(s.Values, b.Count)
}
}
tss := make([]*vm.TimeSeries, 0, 2+len(vmranges))
tss = append(tss, countSeries, sumSeries)
for _, vmrange := range vmranges {
tss = append(tss, bucketSeries[vmrange])
}
return tss
}
// formatVmrange formats the given bucket bounds into `vmrange` label value
// in the same way as VictoriaMetrics does for native histograms
// received via Prometheus remote write protocol.
func formatVmrange(lower, upper float64) string {
b := make([]byte, 0, 24)
b = strconv.AppendFloat(b, lower, 'e', 3, 64)
b = append(b, "..."...)
b = strconv.AppendFloat(b, upper, 'e', 3, 64)
return string(b)
}
type keyValue struct {
key string
value string

View File

@@ -1,334 +0,0 @@
package remoteread
import (
"bytes"
"io"
"reflect"
"testing"
"github.com/gogo/protobuf/proto"
"github.com/golang/snappy"
"github.com/prometheus/prometheus/model/histogram"
"github.com/prometheus/prometheus/prompb"
"github.com/prometheus/prometheus/storage/remote"
"github.com/prometheus/prometheus/tsdb/chunkenc"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/vm"
)
func testHistogram(mul int64) *histogram.Histogram {
return &histogram.Histogram{
Schema: 0,
Count: uint64(10 * mul),
Sum: 25.5 * float64(mul),
ZeroThreshold: 0.001,
ZeroCount: uint64(2 * mul),
PositiveSpans: []histogram.Span{{Offset: 0, Length: 2}},
PositiveBuckets: []int64{1 * mul, 2 * mul},
NegativeSpans: []histogram.Span{{Offset: 0, Length: 1}},
NegativeBuckets: []int64{4 * mul},
}
}
func TestConvertHistograms(t *testing.T) {
f := func(hSamples []histogramSample, labels []prompb.Label, expected []*vm.TimeSeries) {
t.Helper()
tss := convertHistograms(hSamples, labels)
if !reflect.DeepEqual(tss, expected) {
t.Fatalf("unexpected result\ngot:\n%v\nwant:\n%v", tss, expected)
}
}
// series without samples
f(nil, []prompb.Label{{Name: "__name__", Value: "foo"}}, nil)
// series without the metric name must be skipped
f([]histogramSample{
{timestamp: 1000, fh: testHistogram(1).ToFloat(nil)},
}, []prompb.Label{{Name: "job", Value: "bar"}}, nil)
// native histogram must be converted to _count, _sum and _bucket series
// in the same way as VictoriaMetrics does for Prometheus remote write protocol
labels := []prompb.Label{
{Name: "__name__", Value: "request_duration_seconds"},
{Name: "job", Value: "bar"},
}
jobLabel := []vm.LabelPair{{Name: "job", Value: "bar"}}
bucketLabels := func(vmrange string) []vm.LabelPair {
return []vm.LabelPair{
{Name: "job", Value: "bar"},
{Name: "vmrange", Value: vmrange},
}
}
f([]histogramSample{
{timestamp: 1000, fh: testHistogram(1).ToFloat(nil)},
{timestamp: 2000, fh: testHistogram(2).ToFloat(nil)},
}, labels, []*vm.TimeSeries{
{
Name: "request_duration_seconds_count",
LabelPairs: jobLabel,
Timestamps: []int64{1000, 2000},
Values: []float64{10, 20},
},
{
Name: "request_duration_seconds_sum",
LabelPairs: jobLabel,
Timestamps: []int64{1000, 2000},
Values: []float64{25.5, 51},
},
{
Name: "request_duration_seconds_bucket",
LabelPairs: bucketLabels("-1.000e+00...-5.000e-01"),
Timestamps: []int64{1000, 2000},
Values: []float64{4, 8},
},
{
Name: "request_duration_seconds_bucket",
LabelPairs: bucketLabels("-1.000e-03...1.000e-03"),
Timestamps: []int64{1000, 2000},
Values: []float64{2, 4},
},
{
Name: "request_duration_seconds_bucket",
LabelPairs: bucketLabels("5.000e-01...1.000e+00"),
Timestamps: []int64{1000, 2000},
Values: []float64{1, 2},
},
{
Name: "request_duration_seconds_bucket",
LabelPairs: bucketLabels("1.000e+00...2.000e+00"),
Timestamps: []int64{1000, 2000},
Values: []float64{3, 6},
},
})
}
func TestParseHistograms(t *testing.T) {
c := chunkenc.NewHistogramChunk()
app, err := c.Appender()
if err != nil {
t.Fatalf("cannot create chunk appender: %s", err)
}
if _, _, _, err := app.AppendHistogram(nil, 0, 1000, testHistogram(1), true); err != nil {
t.Fatalf("cannot append histogram: %s", err)
}
if _, _, _, err := app.AppendHistogram(nil, 0, 2000, testHistogram(2), true); err != nil {
t.Fatalf("cannot append histogram: %s", err)
}
hSamples, err := parseHistograms(prompb.Chunk_HISTOGRAM, c.Bytes())
if err != nil {
t.Fatalf("cannot parse histogram chunk: %s", err)
}
if len(hSamples) != 2 {
t.Fatalf("unexpected number of histogram samples; got %d; want 2", len(hSamples))
}
for i, expected := range []struct {
timestamp int64
count float64
sum float64
}{
{timestamp: 1000, count: 10, sum: 25.5},
{timestamp: 2000, count: 20, sum: 51},
} {
if hSamples[i].timestamp != expected.timestamp {
t.Fatalf("unexpected timestamp; got %d; want %d", hSamples[i].timestamp, expected.timestamp)
}
if hSamples[i].fh.Count != expected.count {
t.Fatalf("unexpected count; got %f; want %f", hSamples[i].fh.Count, expected.count)
}
if hSamples[i].fh.Sum != expected.sum {
t.Fatalf("unexpected sum; got %f; want %f", hSamples[i].fh.Sum, expected.sum)
}
}
// unsupported chunk encoding must return error
if _, err := parseHistograms(prompb.Chunk_XOR, c.Bytes()); err == nil {
t.Fatalf("expecting non-nil error for unsupported chunk encoding")
}
}
func TestProcessResponse(t *testing.T) {
readResp := &prompb.ReadResponse{
Results: []*prompb.QueryResult{
{
Timeseries: []*prompb.TimeSeries{
{
Labels: []prompb.Label{
{Name: "__name__", Value: "cpu_usage"},
{Name: "job", Value: "bar"},
},
Samples: []prompb.Sample{
{Timestamp: 1000, Value: 1.5},
},
},
{
Labels: []prompb.Label{
{Name: "__name__", Value: "request_duration_seconds"},
{Name: "job", Value: "bar"},
},
Histograms: []prompb.Histogram{
prompb.FromIntHistogram(1000, testHistogram(1)),
},
},
},
},
},
}
data, err := proto.Marshal(readResp)
if err != nil {
t.Fatalf("cannot marshal ReadResponse: %s", err)
}
compressed := snappy.Encode(nil, data)
var tss []*vm.TimeSeries
err = processResponse(io.NopCloser(bytes.NewReader(compressed)), func(ts *vm.TimeSeries) error {
tss = append(tss, ts)
return nil
})
if err != nil {
t.Fatalf("cannot process response: %s", err)
}
// 1 float series + _count + _sum + 4 buckets
if len(tss) != 7 {
t.Fatalf("unexpected number of time series; got %d; want 7", len(tss))
}
if tss[0].Name != "cpu_usage" || !reflect.DeepEqual(tss[0].Values, []float64{1.5}) {
t.Fatalf("unexpected float series: %v", tss[0])
}
if tss[1].Name != "request_duration_seconds_count" || !reflect.DeepEqual(tss[1].Values, []float64{10}) {
t.Fatalf("unexpected _count series: %v", tss[1])
}
if tss[2].Name != "request_duration_seconds_sum" || !reflect.DeepEqual(tss[2].Values, []float64{25.5}) {
t.Fatalf("unexpected _sum series: %v", tss[2])
}
for _, ts := range tss[3:] {
if ts.Name != "request_duration_seconds_bucket" {
t.Fatalf("unexpected bucket series name %q", ts.Name)
}
}
}
type nopFlusher struct{}
func (nopFlusher) Flush() {}
func TestProcessStreamResponse(t *testing.T) {
// build a histogram chunk
hc := chunkenc.NewHistogramChunk()
hApp, err := hc.Appender()
if err != nil {
t.Fatalf("cannot create histogram chunk appender: %s", err)
}
if _, _, _, err := hApp.AppendHistogram(nil, 0, 1000, testHistogram(1), true); err != nil {
t.Fatalf("cannot append histogram: %s", err)
}
// build a float chunk
xc := chunkenc.NewXORChunk()
xApp, err := xc.Appender()
if err != nil {
t.Fatalf("cannot create xor chunk appender: %s", err)
}
xApp.Append(0, 1000, 1.5)
res := &prompb.ChunkedReadResponse{
ChunkedSeries: []*prompb.ChunkedSeries{
{
Labels: []prompb.Label{
{Name: "__name__", Value: "request_duration_seconds"},
{Name: "job", Value: "bar"},
},
Chunks: []prompb.Chunk{
{Type: prompb.Chunk_HISTOGRAM, Data: hc.Bytes()},
},
},
{
Labels: []prompb.Label{
{Name: "__name__", Value: "cpu_usage"},
},
Chunks: []prompb.Chunk{
{Type: prompb.Chunk_XOR, Data: xc.Bytes()},
},
},
{
Labels: []prompb.Label{
{Name: "__name__", Value: "memory_usage"},
},
Chunks: []prompb.Chunk{
// the `type` field may be unset for XOR chunks,
// such chunks must be parsed as XOR ones
{Type: prompb.Chunk_UNKNOWN, Data: xc.Bytes()},
},
},
},
}
data, err := proto.Marshal(res)
if err != nil {
t.Fatalf("cannot marshal ChunkedReadResponse: %s", err)
}
var buf bytes.Buffer
cw := remote.NewChunkedWriter(&buf, nopFlusher{})
if _, err := cw.Write(data); err != nil {
t.Fatalf("cannot write chunked response: %s", err)
}
var tss []*vm.TimeSeries
err = processStreamResponse(io.NopCloser(&buf), func(ts *vm.TimeSeries) error {
tss = append(tss, ts)
return nil
})
if err != nil {
t.Fatalf("cannot process stream response: %s", err)
}
// _count + _sum + 4 buckets + 1 float series + 1 float series from UNKNOWN chunk
if len(tss) != 8 {
t.Fatalf("unexpected number of time series; got %d; want 8", len(tss))
}
if tss[0].Name != "request_duration_seconds_count" || !reflect.DeepEqual(tss[0].Values, []float64{10}) {
t.Fatalf("unexpected _count series: %v", tss[0])
}
if tss[1].Name != "request_duration_seconds_sum" || !reflect.DeepEqual(tss[1].Values, []float64{25.5}) {
t.Fatalf("unexpected _sum series: %v", tss[1])
}
for _, ts := range tss[2:6] {
if ts.Name != "request_duration_seconds_bucket" {
t.Fatalf("unexpected bucket series name %q", ts.Name)
}
}
if tss[6].Name != "cpu_usage" || !reflect.DeepEqual(tss[6].Values, []float64{1.5}) {
t.Fatalf("unexpected float series: %v", tss[6])
}
if tss[7].Name != "memory_usage" || !reflect.DeepEqual(tss[7].Values, []float64{1.5}) {
t.Fatalf("unexpected float series from UNKNOWN chunk: %v", tss[7])
}
}
func TestParseFloatHistograms(t *testing.T) {
c := chunkenc.NewFloatHistogramChunk()
app, err := c.Appender()
if err != nil {
t.Fatalf("cannot create chunk appender: %s", err)
}
fh := testHistogram(1).ToFloat(nil)
if _, _, _, err := app.AppendFloatHistogram(nil, 0, 1000, fh, true); err != nil {
t.Fatalf("cannot append float histogram: %s", err)
}
hSamples, err := parseHistograms(prompb.Chunk_FLOAT_HISTOGRAM, c.Bytes())
if err != nil {
t.Fatalf("cannot parse float histogram chunk: %s", err)
}
if len(hSamples) != 1 {
t.Fatalf("unexpected number of histogram samples; got %d; want 1", len(hSamples))
}
if hSamples[0].timestamp != 1000 {
t.Fatalf("unexpected timestamp; got %d; want 1000", hSamples[0].timestamp)
}
if hSamples[0].fh.Count != 10 {
t.Fatalf("unexpected count; got %f; want 10", hSamples[0].fh.Count)
}
}

View File

@@ -8,7 +8,6 @@ import (
"fmt"
"io"
"net/http"
"net/url"
"strings"
"sync"
"time"
@@ -112,7 +111,7 @@ func AddExtraLabelsToImportPath(path string, extraLabels []string) (string, erro
if strings.Contains(dst, "?") {
separator = "&"
}
dst += fmt.Sprintf("%sextra_label=%s", separator, url.QueryEscape(extraLabel))
dst += fmt.Sprintf("%sextra_label=%s", separator, extraLabel)
}
return dst, nil
}

View File

@@ -33,14 +33,11 @@ func TestAddExtraLabelsToImportPath_Success(t *testing.T) {
f("/api/v1/import", nil, "/api/v1/import")
// ok one extra label
f("/api/v1/import", []string{"instance=host-1"}, "/api/v1/import?extra_label=instance%3Dhost-1")
f("/api/v1/import", []string{"instance=host-1"}, "/api/v1/import?extra_label=instance=host-1")
// ok two extra labels
f("/api/v1/import", []string{"instance=host-2", "job=vmagent"}, "/api/v1/import?extra_label=instance%3Dhost-2&extra_label=job%3Dvmagent")
f("/api/v1/import", []string{"instance=host-2", "job=vmagent"}, "/api/v1/import?extra_label=instance=host-2&extra_label=job=vmagent")
// ok two extra with exist param
f("/api/v1/import?timeout=50", []string{"instance=host-2", "job=vmagent"}, "/api/v1/import?timeout=50&extra_label=instance%3Dhost-2&extra_label=job%3Dvmagent")
// ok special chars in label value
f("/api/v1/import", []string{"team=a&b"}, "/api/v1/import?extra_label=team%3Da%26b")
f("/api/v1/import?timeout=50", []string{"instance=host-2", "job=vmagent"}, "/api/v1/import?timeout=50&extra_label=instance=host-2&extra_label=job=vmagent")
}

View File

@@ -405,16 +405,7 @@ func buildMatchWithFilter(filter string, metricName string) (string, error) {
if len(tf.Key) == 0 {
continue
}
switch {
case tf.IsNegative && tf.IsRegexp:
a = append(a, fmt.Sprintf("%s!~%q", tf.Key, tf.Value))
case tf.IsNegative:
a = append(a, fmt.Sprintf("%s!=%q", tf.Key, tf.Value))
case tf.IsRegexp:
a = append(a, fmt.Sprintf("%s=~%q", tf.Key, tf.Value))
default:
a = append(a, fmt.Sprintf("%s=%q", tf.Key, tf.Value))
}
a = append(a, tf.String())
}
a = append(a, nameFilter)
filters = append(filters, strings.Join(a, ","))

View File

@@ -175,19 +175,13 @@ func (ctx *InsertCtx) WriteMetadata(mmpbs []prompb.MetricMetadata) error {
}
mms := ctx.mms
mms = slicesutil.SetLength(mms, len(mmpbs))
var cnt int
for _, mmpb := range mmpbs {
if timeserieslimits.IsMetricMetadataExceeding(&mmpb) {
continue
}
mm := &mms[cnt]
for idx, mmpb := range mmpbs {
mm := &mms[idx]
mm.MetricFamilyName = bytesutil.ToUnsafeBytes(mmpb.MetricFamilyName)
mm.Help = bytesutil.ToUnsafeBytes(mmpb.Help)
mm.Type = mmpb.Type
mm.Unit = bytesutil.ToUnsafeBytes(mmpb.Unit)
cnt++
}
mms = mms[:cnt]
ctx.mms = mms
err := vmstorage.VMInsertAPI.WriteMetadata(mms)
@@ -207,19 +201,14 @@ func (ctx *InsertCtx) WritePromMetadata(mmps []prometheus.Metadata) error {
}
mms := ctx.mms
mms = slicesutil.SetLength(mms, len(mmps))
var cnt int
for _, mmpb := range mmps {
mm := &mms[cnt]
if timeserieslimits.IsPrometheusMetadataExceeding(&mmpb) {
continue
}
for idx, mmpb := range mmps {
mm := &mms[idx]
mm.MetricFamilyName = bytesutil.ToUnsafeBytes(mmpb.Metric)
mm.Help = bytesutil.ToUnsafeBytes(mmpb.Help)
mm.Type = mmpb.Type
cnt++
}
mms = mms[:cnt]
ctx.mms = mms
err := vmstorage.VMInsertAPI.WriteMetadata(mms)
if err != nil {
return &httpserver.ErrorWithStatusCode{

View File

@@ -49,7 +49,7 @@ func InsertHandlerForHTTP(req *http.Request) error {
}
q := req.URL.Query()
precision := q.Get("precision")
// Read db tag from https://docs.influxdata.com/influxdb/v1/api/write/#operation/PostWrite
// Read db tag from https://docs.influxdata.com/influxdb/v1.7/tools/api/#write-http-endpoint
db := q.Get("db")
encoding := req.Header.Get("Content-Encoding")
isStreamMode := req.Header.Get("Stream-Mode") == "1"

View File

@@ -68,11 +68,9 @@ var (
"at -opentsdbHTTPListenAddr . See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt")
configAuthKey = flagutil.NewPassword("configAuthKey", "Authorization key for accessing /config page. It must be passed via authKey query arg. It overrides -httpAuth.*")
reloadAuthKey = flagutil.NewPassword("reloadAuthKey", "Auth key for /-/reload http endpoint. It must be passed via authKey query arg. It overrides httpAuth.* settings.")
maxLabelsPerTimeseries = flag.Int("maxLabelsPerTimeseries", 40, "The maximum number of labels per time series to be accepted. Series with superfluous labels are ignored. In this case the vm_rows_ignored_total{reason=\"too_many_labels\"} metric at /metrics page is incremented.")
maxLabelNameLen = flag.Int("maxLabelNameLen", 256, "The maximum length of label name in the accepted time series. Series with longer label name are ignored. In this case the vm_rows_ignored_total{reason=\"too_long_label_name\"} metric at /metrics page is incremented. "+
"Value must be in range 1..65535.")
maxLabelValueLen = flag.Int("maxLabelValueLen", 4*1024, "The maximum length of label values in the accepted time series. Series with longer label value are ignored. In this case the vm_rows_ignored_total{reason=\"too_long_label_value\"} metric at /metrics page is incremented. "+
"Value must be in range 1..65535.")
maxLabelsPerTimeseries = flag.Int("maxLabelsPerTimeseries", 40, "The maximum number of labels per time series to be accepted. Series with superfluous labels are ignored. In this case the vm_rows_ignored_total{reason=\"too_many_labels\"} metric at /metrics page is incremented")
maxLabelNameLen = flag.Int("maxLabelNameLen", 256, "The maximum length of label name in the accepted time series. Series with longer label name are ignored. In this case the vm_rows_ignored_total{reason=\"too_long_label_name\"} metric at /metrics page is incremented")
maxLabelValueLen = flag.Int("maxLabelValueLen", 4*1024, "The maximum length of label values in the accepted time series. Series with longer label value are ignored. In this case the vm_rows_ignored_total{reason=\"too_long_label_value\"} metric at /metrics page is incremented")
)
var (
@@ -108,7 +106,7 @@ func Init() {
promscrape.Init(func(_ *auth.Token, wr *prompb.WriteRequest) {
prompush.Push(wr)
})
timeserieslimits.MustInit(*maxLabelsPerTimeseries, *maxLabelNameLen, *maxLabelValueLen)
timeserieslimits.Init(*maxLabelsPerTimeseries, *maxLabelNameLen, *maxLabelValueLen)
}
// Stop stops vminsert.

View File

@@ -38,7 +38,6 @@ func main() {
flag.CommandLine.SetOutput(os.Stdout)
flag.Usage = usage
envflag.Parse()
initSecretFlags()
buildinfo.Init()
logger.Init()
@@ -113,8 +112,3 @@ func newSrcFS(ctx context.Context) (common.RemoteFS, error) {
}
return fs, nil
}
// initSecretFlags manages the secret flags for this app and must be called after flag parsing and before logger init.
func initSecretFlags() {
pushmetrics.InitSecretFlags()
}

View File

@@ -26,7 +26,6 @@ import (
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promscrape"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/querytracer"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/querytracer/push"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/timerpool"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/vmalertproxy"
)
@@ -60,12 +59,6 @@ func Init(vmselectMaxConcurrentRequests int, vmselectMaxQueueDuration time.Durat
initVMUIConfig()
vmalertproxy.Init(*vmalertProxyURL)
}
// InitSecretFlags manages the secret flags for this pkg and must be called by app-level initSecretFlags.
// It should run before logger initialization and package Init() (if exists).
func InitSecretFlags() {
flagutil.RegisterSecretFlag("vmalert.proxyURL")
}
@@ -118,15 +111,8 @@ func RequestHandler(w http.ResponseWriter, r *http.Request) bool {
// Handle non-trivial dynamic requests, which may take big amounts of time and resources.
startTime := time.Now()
defer requestDuration.UpdateDuration(startTime)
tracerEnabled := httputil.GetBool(r, "trace") || push.IsEnabled()
tracerEnabled := httputil.GetBool(r, "trace")
qt := querytracer.New(tracerEnabled, "%s", r.URL.Path)
if push.IsEnabled() {
defer func() {
if time.Since(startTime) >= push.MinTraceDuration() {
push.Push(qt)
}
}()
}
// Limit the number of concurrent queries.
select {
@@ -383,10 +369,6 @@ func RequestHandler(w http.ResponseWriter, r *http.Request) bool {
}
return true
case "/tags/delSeries":
if r.Method != "POST" {
http.Error(w, fmt.Sprintf("Only POST method is allowed. Got %s.", r.Method), http.StatusMethodNotAllowed)
return true
}
if !httpserver.CheckAuthFlag(w, r, deleteAuthKey) {
return true
}
@@ -406,10 +388,6 @@ func RequestHandler(w http.ResponseWriter, r *http.Request) bool {
}
return true
case "/api/v1/admin/tsdb/delete_series":
if r.Method != "POST" {
http.Error(w, fmt.Sprintf("Only POST method is allowed. Got %s.", r.Method), http.StatusMethodNotAllowed)
return true
}
if !httpserver.CheckAuthFlag(w, r, deleteAuthKey) {
return true
}
@@ -563,7 +541,7 @@ func handleStaticAndSimpleRequests(w http.ResponseWriter, r *http.Request, path
return true
case "/metric-relabel-debug":
promscrapeMetricRelabelDebugRequests.Inc()
promscrape.WriteMetricRelabelDebug(w, r, "", nil)
promscrape.WriteMetricRelabelDebug(w, r)
return true
case "/target-relabel-debug":
promscrapeTargetRelabelDebugRequests.Inc()

View File

@@ -15,7 +15,7 @@ See https://prometheus.io/docs/prometheus/latest/querying/api/#querying-metric-m
currentItem := 0
%}
{% for _, row := range result %}
{%q= string(row.MetricFamilyName) %}: [
"{%s string(row.MetricFamilyName) %}": [
{
"type": {%q= row.Type.String() %},
{% if len(row.Unit) > 0 -%}

View File

@@ -35,10 +35,12 @@ func StreamMetadataResponse(qw422016 *qt422016.Writer, result []*metricsmetadata
//line app/vmselect/prometheus/metadata_response.qtpl:17
for _, row := range result {
//line app/vmselect/prometheus/metadata_response.qtpl:17
qw422016.N().S(`"`)
//line app/vmselect/prometheus/metadata_response.qtpl:18
qw422016.N().Q(string(row.MetricFamilyName))
qw422016.E().S(string(row.MetricFamilyName))
//line app/vmselect/prometheus/metadata_response.qtpl:18
qw422016.N().S(`: [{"type":`)
qw422016.N().S(`": [{"type":`)
//line app/vmselect/prometheus/metadata_response.qtpl:20
qw422016.N().Q(row.Type.String())
//line app/vmselect/prometheus/metadata_response.qtpl:20

View File

@@ -516,7 +516,7 @@ func DeleteHandler(startTime time.Time, r *http.Request) error {
cp.deadline = searchutil.GetDeadlineForDelete(r, startTime)
if !cp.IsDefaultTimeRange() {
return fmt.Errorf("delete API does not support specific time ranges using start and end args, the series can only be deleted completely")
return fmt.Errorf("start=%d and end=%d args aren't supported. Remove these args from the query in order to delete all the matching metrics", cp.start, cp.end)
}
sq := storage.NewSearchQuery(cp.start, cp.end, cp.filterss, *maxDeleteSeries)
deletedCount, err := netstorage.DeleteSeries(nil, sq, cp.deadline)
@@ -540,11 +540,11 @@ func LabelValuesHandler(qt *querytracer.Tracer, startTime time.Time, labelName s
cp, err := getCommonParamsForLabelsAPI(r, startTime, false)
if err != nil {
return httpserver.InvalidParamError(err)
return err
}
limit, err := httputil.GetInt(r, "limit")
if err != nil {
return httpserver.InvalidParamError(err)
return err
}
sq := storage.NewSearchQuery(cp.start, cp.end, cp.filterss, *maxLabelsAPISeries)
@@ -584,7 +584,7 @@ func TSDBStatusHandler(qt *querytracer.Tracer, startTime time.Time, w http.Respo
cp, err := getCommonParams(r, startTime, false)
if err != nil {
return httpserver.InvalidParamError(err)
return err
}
cp.deadline = searchutil.GetDeadlineForStatusRequest(r, startTime)
@@ -596,7 +596,7 @@ func TSDBStatusHandler(qt *querytracer.Tracer, startTime time.Time, w http.Respo
} else {
t, err := time.Parse("2006-01-02", dateStr)
if err != nil {
return httpserver.InvalidParamError(fmt.Errorf("cannot parse `date` arg %q: %w", dateStr, err))
return fmt.Errorf("cannot parse `date` arg %q: %w", dateStr, err)
}
date = uint64(t.Unix()) / secsPerDay
}
@@ -607,7 +607,7 @@ func TSDBStatusHandler(qt *querytracer.Tracer, startTime time.Time, w http.Respo
if len(topNStr) > 0 {
n, err := strconv.Atoi(topNStr)
if err != nil {
return httpserver.InvalidParamError(fmt.Errorf("cannot parse `topN` arg %q: %w", topNStr, err))
return fmt.Errorf("cannot parse `topN` arg %q: %w", topNStr, err)
}
if n <= 0 {
n = 1
@@ -645,11 +645,11 @@ func LabelsHandler(qt *querytracer.Tracer, startTime time.Time, w http.ResponseW
cp, err := getCommonParamsForLabelsAPI(r, startTime, false)
if err != nil {
return httpserver.InvalidParamError(err)
return err
}
limit, err := httputil.GetInt(r, "limit")
if err != nil {
return httpserver.InvalidParamError(err)
return err
}
sq := storage.NewSearchQuery(cp.start, cp.end, cp.filterss, *maxLabelsAPISeries)
labels, err := netstorage.LabelNames(qt, sq, limit, cp.deadline)
@@ -671,9 +671,10 @@ func LabelsHandler(qt *querytracer.Tracer, startTime time.Time, w http.ResponseW
//
// See https://prometheus.io/docs/prometheus/latest/querying/api/#querying-metric-metadata
func MetadataHandler(qt *querytracer.Tracer, startTime time.Time, w http.ResponseWriter, r *http.Request) error {
limit, err := httputil.GetInt(r, "limit")
if err != nil {
return httpserver.InvalidParamError(err)
return err
}
if limit < 0 {
limit = 0
@@ -733,11 +734,11 @@ func SeriesHandler(qt *querytracer.Tracer, startTime time.Time, w http.ResponseW
// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/91
cp, err := getCommonParamsForLabelsAPI(r, startTime, true)
if err != nil {
return httpserver.InvalidParamError(err)
return err
}
limit, err := httputil.GetInt(r, "limit")
if err != nil {
return httpserver.InvalidParamError(err)
return err
}
sq := storage.NewSearchQuery(cp.start, cp.end, cp.filterss, *maxSeriesLimit)
@@ -771,19 +772,19 @@ func QueryHandler(qt *querytracer.Tracer, startTime time.Time, w http.ResponseWr
mayCache := !httputil.GetBool(r, "nocache")
query := r.FormValue("query")
if len(query) == 0 {
return httpserver.InvalidParamError(fmt.Errorf("missing `query` arg"))
return fmt.Errorf("missing `query` arg")
}
start, err := httputil.GetTime(r, "time", ct)
if err != nil {
return httpserver.InvalidParamError(err)
return err
}
lookbackDelta, err := getMaxLookback(r)
if err != nil {
return httpserver.InvalidParamError(err)
return err
}
step, err := httputil.GetDuration(r, "step", lookbackDelta)
if err != nil {
return httpserver.InvalidParamError(err)
return err
}
if step <= 0 {
step = defaultStep
@@ -791,16 +792,16 @@ func QueryHandler(qt *querytracer.Tracer, startTime time.Time, w http.ResponseWr
maxLen := searchutil.GetMaxQueryLen()
if len(query) > maxLen {
return httpserver.InvalidParamError(fmt.Errorf("too long query; got %d bytes; mustn't exceed `-search.maxQueryLen=%d` bytes", len(query), maxLen))
return fmt.Errorf("too long query; got %d bytes; mustn't exceed `-search.maxQueryLen=%d` bytes", len(query), maxLen)
}
etfs, err := searchutil.GetExtraTagFilters(r)
if err != nil {
return httpserver.InvalidParamError(err)
return err
}
if childQuery, windowExpr, offsetExpr := promql.IsMetricSelectorWithRollup(query); childQuery != "" {
window, err := windowExpr.NonNegativeDuration(step)
if err != nil {
return httpserver.InvalidParamError(fmt.Errorf("cannot parse lookbehind window in square brackets at %s: %w", query, err))
return fmt.Errorf("cannot parse lookbehind window in square brackets at %s: %w", query, err)
}
offset := offsetExpr.Duration(step)
start -= offset
@@ -814,7 +815,7 @@ func QueryHandler(qt *querytracer.Tracer, startTime time.Time, w http.ResponseWr
tagFilterss, err := getTagFilterssFromMatches([]string{childQuery})
if err != nil {
return httpserver.InvalidParamError(err)
return err
}
filterss := searchutil.JoinTagFilterss(tagFilterss, etfs)
@@ -830,25 +831,22 @@ func QueryHandler(qt *querytracer.Tracer, startTime time.Time, w http.ResponseWr
return nil
}
if childQuery, windowExpr, stepExpr, offsetExpr := promql.IsRollup(query); childQuery != "" {
if len(childQuery) > maxLen {
return httpserver.InvalidParamError(fmt.Errorf("too long query; got %d bytes; mustn't exceed `-search.maxQueryLen=%d` bytes", len(childQuery), maxLen))
}
newStep, err := stepExpr.NonNegativeDuration(step)
if err != nil {
return httpserver.InvalidParamError(fmt.Errorf("cannot parse step in square brackets at %s: %w", query, err))
return fmt.Errorf("cannot parse step in square brackets at %s: %w", query, err)
}
if newStep > 0 {
step = newStep
}
window, err := windowExpr.NonNegativeDuration(step)
if err != nil {
return httpserver.InvalidParamError(fmt.Errorf("cannot parse lookbehind window in square brackets at %s: %w", query, err))
return fmt.Errorf("cannot parse lookbehind window in square brackets at %s: %w", query, err)
}
offset := offsetExpr.Duration(step)
start -= offset
end := start
start = end - window
if err := queryRangeHandler(qt, startTime, w, childQuery, start, end, step, lookbackDelta, r, ct, etfs); err != nil {
if err := queryRangeHandler(qt, startTime, w, childQuery, start, end, step, r, ct, etfs); err != nil {
return fmt.Errorf("error when executing query=%q on the time range (start=%d, end=%d, step=%d): %w", childQuery, start, end, step, err)
}
return nil
@@ -856,7 +854,7 @@ func QueryHandler(qt *querytracer.Tracer, startTime time.Time, w http.ResponseWr
queryOffset, err := getLatencyOffsetMilliseconds(r)
if err != nil {
return httpserver.InvalidParamError(err)
return err
}
if !httputil.GetBool(r, "nocache") && ct-start < queryOffset && start-ct < queryOffset {
// Adjust start time only if `nocache` arg isn't set.
@@ -930,43 +928,44 @@ func QueryRangeHandler(qt *querytracer.Tracer, startTime time.Time, w http.Respo
ct := startTime.UnixNano() / 1e6
query := r.FormValue("query")
if len(query) == 0 {
return httpserver.InvalidParamError(fmt.Errorf("missing `query` arg"))
}
maxLen := searchutil.GetMaxQueryLen()
if len(query) > maxLen {
return httpserver.InvalidParamError(fmt.Errorf("too long query; got %d bytes; mustn't exceed `-search.maxQueryLen=%d` bytes", len(query), maxLen))
return fmt.Errorf("missing `query` arg")
}
start, err := httputil.GetTime(r, "start", ct-defaultStep)
if err != nil {
return httpserver.InvalidParamError(err)
return err
}
end, err := httputil.GetTime(r, "end", ct)
if err != nil {
return httpserver.InvalidParamError(err)
return err
}
step, err := httputil.GetDuration(r, "step", defaultStep)
if err != nil {
return httpserver.InvalidParamError(err)
return err
}
etfs, err := searchutil.GetExtraTagFilters(r)
if err != nil {
return httpserver.InvalidParamError(err)
return err
}
lookbackDelta, err := getMaxLookback(r)
if err != nil {
return httpserver.InvalidParamError(err)
}
if err := queryRangeHandler(qt, startTime, w, query, start, end, step, lookbackDelta, r, ct, etfs); err != nil {
if err := queryRangeHandler(qt, startTime, w, query, start, end, step, r, ct, etfs); err != nil {
return fmt.Errorf("error when executing query=%q on the time range (start=%d, end=%d, step=%d): %w", query, start, end, step, err)
}
return nil
}
func queryRangeHandler(qt *querytracer.Tracer, startTime time.Time, w http.ResponseWriter, query string,
start, end, step, lookbackDelta int64, r *http.Request, ct int64, etfs [][]storage.TagFilter) error {
start, end, step int64, r *http.Request, ct int64, etfs [][]storage.TagFilter) error {
deadline := searchutil.GetDeadlineForQuery(r, startTime)
mayCache := !httputil.GetBool(r, "nocache")
optimizeRepeatedBinaryOpSubexprs := httputil.GetBool(r, "optimize_repeated_binary_op_subexprs")
lookbackDelta, err := getMaxLookback(r)
if err != nil {
return err
}
// Validate input args.
maxLen := searchutil.GetMaxQueryLen()
if len(query) > maxLen {
return fmt.Errorf("too long query; got %d bytes; mustn't exceed `-search.maxQueryLen=%d` bytes", len(query), maxLen)
}
if start > end {
end = start + defaultStep
}
@@ -978,19 +977,18 @@ func queryRangeHandler(qt *querytracer.Tracer, startTime time.Time, w http.Respo
}
ec := &promql.EvalConfig{
Start: start,
End: end,
Step: step,
MaxPointsPerSeries: *maxPointsPerTimeseries,
MaxSeries: 0, // let vmstorage use maxUniqueTimeseries by default
QuotedRemoteAddr: httpserver.GetQuotedRemoteAddr(r),
Deadline: deadline,
MayCache: mayCache,
OptimizeRepeatedBinaryOpSubexprs: optimizeRepeatedBinaryOpSubexprs,
LookbackDelta: lookbackDelta,
RoundDigits: getRoundDigits(r),
EnforcedTagFilterss: etfs,
CacheTagFilters: etfs,
Start: start,
End: end,
Step: step,
MaxPointsPerSeries: *maxPointsPerTimeseries,
MaxSeries: 0, // let vmstorage use maxUniqueTimeseries by default
QuotedRemoteAddr: httpserver.GetQuotedRemoteAddr(r),
Deadline: deadline,
MayCache: mayCache,
LookbackDelta: lookbackDelta,
RoundDigits: getRoundDigits(r),
EnforcedTagFilterss: etfs,
CacheTagFilters: etfs,
GetRequestURI: func() string {
return httpserver.GetRequestURI(r)
},
@@ -1005,7 +1003,7 @@ func queryRangeHandler(qt *querytracer.Tracer, startTime time.Time, w http.Respo
if step < maxStepForPointsAdjustment.Milliseconds() {
queryOffset, err := getLatencyOffsetMilliseconds(r)
if err != nil {
return httpserver.InvalidParamError(err)
return err
}
if ct-queryOffset < end {
result = adjustLastPoints(result, ct-queryOffset, ct+step)
@@ -1156,13 +1154,13 @@ func QueryStatsHandler(w http.ResponseWriter, r *http.Request) error {
if len(topNStr) > 0 {
n, err := strconv.Atoi(topNStr)
if err != nil {
return httpserver.InvalidParamError(fmt.Errorf("cannot parse `topN` arg %q: %w", topNStr, err))
return fmt.Errorf("cannot parse `topN` arg %q: %w", topNStr, err)
}
topN = n
}
maxLifetimeMsecs, err := httputil.GetDuration(r, "maxLifetime", 10*60*1000)
if err != nil {
return httpserver.InvalidParamError(fmt.Errorf("cannot parse `maxLifetime` arg: %w", err))
return fmt.Errorf("cannot parse `maxLifetime` arg: %w", err)
}
maxLifetime := time.Duration(maxLifetimeMsecs) * time.Millisecond
w.Header().Set("Content-Type", "application/json")

View File

@@ -164,21 +164,15 @@ func newBinaryOpFunc(bf func(left, right float64, isBool bool) float64) binaryOp
left := bfa.left
right := bfa.right
op := bfa.be.Op
isCmpOp := metricsql.IsBinaryOpCmp(op)
if !isCmpOp {
// Do not remove empty series for comparison operations, since NaN can be an
// explicitly present sample value. In particular, `value != NaN` is true.
// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/150.
switch true {
case metricsql.IsBinaryOpCmp(op):
// Do not remove empty series for comparison operations,
// since this may lead to missing result.
default:
left = removeEmptySeries(left)
right = removeEmptySeries(right)
}
if len(left) == 0 && len(right) == 0 {
return nil, nil
}
if len(left) == 0 && bfa.be.FillLeft == nil {
return nil, nil
}
if len(right) == 0 && bfa.be.FillRight == nil {
if len(left) == 0 || len(right) == 0 {
return nil, nil
}
left, right, dst, err := adjustBinaryOpTags(bfa.be, left, right)
@@ -189,16 +183,6 @@ func newBinaryOpFunc(bf func(left, right float64, isBool bool) float64) binaryOp
logger.Panicf("BUG: len(left) must match len(right) and len(dst); got %d vs %d vs %d", len(left), len(right), len(dst))
}
isBool := bfa.be.Bool
fillLeft := bfa.be.FillLeft
fillRight := bfa.be.FillRight
// A NaN produced by a vector comparison denotes a filtered-out sample rather
// than an explicitly present NaN value. Drop it when this result is used as
// the right-hand side of another comparison.
// Note that filtered-out samples surviving as NaN inside other wrappers such as
// transform functions or arithmetic operations aren't detected, since such NaN
// is indistinguishable from an explicitly present NaN value there.
// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10018.
dropNaNRight := isCmpOp && isVectorComparisonExpr(bfa.be.Right)
for i, tsLeft := range left {
leftValues := tsLeft.Values
rightValues := right[i].Values
@@ -209,24 +193,6 @@ func newBinaryOpFunc(bf func(left, right float64, isBool bool) float64) binaryOp
}
for j, a := range leftValues {
b := rightValues[j]
leftIsNaN := math.IsNaN(a)
rightIsNaN := math.IsNaN(b)
// Both sides are NaN.
if leftIsNaN && rightIsNaN {
dstValues[j] = bf(a, b, isBool)
continue
}
if dropNaNRight && rightIsNaN && fillRight == nil {
dstValues[j] = nan
continue
}
// Apply the fill value when either the left or right side is NaN, but not both.
if leftIsNaN && fillLeft != nil {
a = fillLeft.N
}
if rightIsNaN && fillRight != nil {
b = fillRight.N
}
dstValues[j] = bf(a, b, isBool)
}
}
@@ -236,38 +202,6 @@ func newBinaryOpFunc(bf func(left, right float64, isBool bool) float64) binaryOp
}
}
// isVectorComparisonExpr returns whether e is a comparison operation
// with at least one non-scalar operand.
func isVectorComparisonExpr(e metricsql.Expr) bool {
if re, ok := e.(*metricsql.RollupExpr); ok && re.Window == nil {
// Unwrap `(...) offset <d>` and `(...) @ <t>`, which do not change
// the shape of the result. Subqueries are left as is, since rollup
// functions skip NaN values on their own.
e = re.Expr
}
be, ok := e.(*metricsql.BinaryOpExpr)
if !ok || !metricsql.IsBinaryOpCmp(be.Op) {
return false
}
return !isScalarLikeExpr(be.Left) || !isScalarLikeExpr(be.Right)
}
// isScalarLikeExpr returns whether e always evaluates to a scalar value.
func isScalarLikeExpr(e metricsql.Expr) bool {
switch e := e.(type) {
case *metricsql.NumberExpr, *metricsql.DurationExpr:
return true
case *metricsql.BinaryOpExpr:
return isScalarLikeExpr(e.Left) && isScalarLikeExpr(e.Right)
case *metricsql.FuncExpr:
switch strings.ToLower(e.Name) {
case "now", "pi", "scalar", "start", "end", "step", "time", "timezone_offset":
return true
}
}
return false
}
func adjustBinaryOpTags(be *metricsql.BinaryOpExpr, left, right []*timeseries) ([]*timeseries, []*timeseries, []*timeseries, error) {
if len(be.GroupModifier.Op) == 0 && len(be.JoinModifier.Op) == 0 {
if isScalar(left) {
@@ -292,7 +226,7 @@ func adjustBinaryOpTags(be *metricsql.BinaryOpExpr, left, right []*timeseries) (
}
}
// Slow path: `vector op vector` or `a op {on|ignoring} {group_left|group_right} {fill|fill_left|fill_right} b`
// Slow path: `vector op vector` or `a op {on|ignoring} {group_left|group_right} b`
var rvsLeft, rvsRight []*timeseries
mLeft, mRight := createTimeseriesMapByTagSet(be, left, right)
joinOp := strings.ToLower(be.JoinModifier.Op)
@@ -305,27 +239,10 @@ func adjustBinaryOpTags(be *metricsql.BinaryOpExpr, left, right []*timeseries) (
// Add __name__ to groupTags if metric name must be preserved.
groupTags = append(groupTags[:len(groupTags):len(groupTags)], "__name__")
}
// Add missing keys from mRight to mLeft when fill_left()/fill() modifier is used
if be.FillLeft != nil {
for k := range mRight {
if _, ok := mLeft[k]; !ok {
mLeft[k] = nil
}
}
}
for k, tssLeft := range mLeft {
tssRight := mRight[k]
if len(tssLeft) == 0 {
if be.FillLeft == nil {
logger.Panicf("BUG: unexpected empty tssLeft for key %q when FillLeft is nil", k)
}
tssLeft = []*timeseries{newFillTimeseries(be, tssRight[0])}
}
if len(tssRight) == 0 {
if be.FillRight == nil {
continue
}
tssRight = []*timeseries{newFillTimeseries(be, tssLeft[0])}
continue
}
switch joinOp {
case "group_left":
@@ -370,28 +287,6 @@ func adjustBinaryOpTags(be *metricsql.BinaryOpExpr, left, right []*timeseries) (
return rvsLeft, rvsRight, dst, nil
}
// newFillTimeseries returns a time series filled with NaN values for the fill_left()/fill_right()/fill() modifiers.
// These NaN values will be replaced later with the fill value if needed.
func newFillTimeseries(be *metricsql.BinaryOpExpr, src *timeseries) *timeseries {
var ts timeseries
ts.CopyFromShallowTimestamps(src)
if !be.KeepMetricNames {
ts.MetricName.ResetMetricGroup()
}
groupTags := be.GroupModifier.Args
switch strings.ToLower(be.GroupModifier.Op) {
case "on":
ts.MetricName.RemoveTagsOn(groupTags)
default:
ts.MetricName.RemoveTagsIgnoring(groupTags)
}
values := ts.Values
for i := range values {
values[i] = math.NaN()
}
return &ts
}
func ensureSingleTimeseries(side string, be *metricsql.BinaryOpExpr, tss []*timeseries) error {
if len(tss) == 0 {
logger.Panicf("BUG: tss must contain at least one value")

View File

@@ -132,9 +132,6 @@ type EvalConfig struct {
// Whether the response can be cached.
MayCache bool
// Whether repeated cacheable binary op subexpressions can be optimized.
OptimizeRepeatedBinaryOpSubexprs bool
// LookbackDelta is analog to `-query.lookback-delta` from Prometheus.
LookbackDelta int64
@@ -174,7 +171,6 @@ func copyEvalConfig(src *EvalConfig) *EvalConfig {
ec.MaxPointsPerSeries = src.MaxPointsPerSeries
ec.Deadline = src.Deadline
ec.MayCache = src.MayCache
ec.OptimizeRepeatedBinaryOpSubexprs = src.OptimizeRepeatedBinaryOpSubexprs
ec.LookbackDelta = src.LookbackDelta
ec.RoundDigits = src.RoundDigits
ec.EnforcedTagFilterss = src.EnforcedTagFilterss
@@ -424,7 +420,18 @@ func evalBinaryOp(qt *querytracer.Tracer, ec *EvalConfig, be *metricsql.BinaryOp
if bf == nil {
return nil, fmt.Errorf(`unknown binary op %q`, be.Op)
}
tssLeft, tssRight, err := execBinaryOpArgs(qt, ec, be)
var err error
var tssLeft, tssRight []*timeseries
switch strings.ToLower(be.Op) {
case "and", "if":
// Fetch right-side series at first, since it usually contains
// lower number of time series for `and` and `if` operator.
// This should produce more specific label filters for the left side of the query.
// This, in turn, should reduce the time to select series for the left side of the query.
tssRight, tssLeft, err = execBinaryOpArgs(qt, ec, be.Right, be.Left, be)
default:
tssLeft, tssRight, err = execBinaryOpArgs(qt, ec, be.Left, be.Right, be)
}
if err != nil {
return nil, fmt.Errorf("cannot execute %q: %w", be.AppendString(nil), err)
}
@@ -440,29 +447,6 @@ func evalBinaryOp(qt *querytracer.Tracer, ec *EvalConfig, be *metricsql.BinaryOp
return rv, nil
}
// binaryOpEvalOrder might change the order of evaluation of the left and right sides of a binary operation,
// when there is chance to push down common label filters from exprFirst to exprSecond in the following executions.
func binaryOpEvalOrder(be *metricsql.BinaryOpExpr) (exprFirst, exprSecond metricsql.Expr) {
exprFirst, exprSecond = be.Left, be.Right
switch strings.ToLower(be.Op) {
case "and", "if":
// For `and` and `if`, fetch the right-side series first, since it usually contains
// fewer time series and yields more specific filters for the left side.
exprFirst, exprSecond = be.Right, be.Left
}
if be.FillLeft != nil && be.FillRight == nil {
// For `fill_left(<value>)`, the unmatched series can only come from the right side, so evaluate it first.
exprFirst, exprSecond = be.Right, be.Left
}
return exprFirst, exprSecond
}
// canPushdownCommonFilters decides if common label filters can be pushed down from one side of a binary operation to the other.
//
// Common filters cannot be pushed down when:
// - the operator is `or` or `default`;
// - either side is an aggregation function without explicit grouping;
// - fill(<value>) modifier is used.
func canPushdownCommonFilters(be *metricsql.BinaryOpExpr) bool {
switch strings.ToLower(be.Op) {
case "or", "default":
@@ -471,10 +455,6 @@ func canPushdownCommonFilters(be *metricsql.BinaryOpExpr) bool {
if isAggrFuncWithoutGrouping(be.Left) || isAggrFuncWithoutGrouping(be.Right) {
return false
}
// Filters cannot be propagated when fill(<value>) modifier is used.
if be.FillLeft != nil && be.FillRight != nil {
return false
}
return true
}
@@ -486,185 +466,82 @@ func isAggrFuncWithoutGrouping(e metricsql.Expr) bool {
return len(afe.Modifier.Args) == 0
}
func execBinaryOpArgs(qt *querytracer.Tracer, ec *EvalConfig, be *metricsql.BinaryOpExpr) ([]*timeseries, []*timeseries, error) {
exprFirst, exprSecond := binaryOpEvalOrder(be)
firstIsLeft := exprFirst == be.Left
sortResult := func(tssFirst, tssSecond []*timeseries) ([]*timeseries, []*timeseries, error) {
if firstIsLeft {
return tssFirst, tssSecond, nil
}
return tssSecond, tssFirst, nil
}
if canPushdownCommonFilters(be) {
// Execute binary operation in the following way:
//
// 1) execute the exprFirst
// 2) get common label filters for series returned at step 1
// 3) push down the found common label filters to exprSecond. This filters out unneeded series
// during exprSecond execution instead of spending compute resources on extracting and processing these series
// before they are dropped later when matching time series according to https://prometheus.io/docs/prometheus/latest/querying/operators/#vector-matching
// 4) execute the exprSecond with possible additional filters found at step 3
//
// Typical use cases:
// - Kubernetes-related: show pod creation time with the node name:
//
// kube_pod_created{namespace="prod"} * on (uid) group_left(node) kube_pod_info
//
// Without the optimization `kube_pod_info` would select and spend compute resources
// for more time series than needed. The selected time series would be dropped later
// when matching time series on the right and left sides of binary operand.
//
// - Generic alerting queries, which rely on `info` metrics.
// See https://grafana.com/blog/2021/08/04/how-to-use-promql-joins-for-more-effective-queries-of-prometheus-metrics-at-scale/
//
// - Queries, which get additional labels from `info` metrics.
// See https://www.robustperception.io/exposing-the-software-version-to-prometheus
tssFirst, err := evalExpr(qt, ec, exprFirst)
if err != nil {
return nil, nil, err
}
if len(tssFirst) == 0 && !strings.EqualFold(be.Op, "or") {
// Fast path: there is no sense in executing the exprSecond when exprFirst returns an empty result,
// since the "exprFirst op exprSecond" would return an empty result in any case.
// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3349
return nil, nil, nil
}
lfs := getCommonLabelFilters(tssFirst)
lfs = metricsql.TrimFiltersByGroupModifier(lfs, be)
exprSecond = metricsql.PushdownBinaryOpFilters(exprSecond, lfs)
tssSecond, err := evalExpr(qt, ec, exprSecond)
if err != nil {
return nil, nil, err
}
return sortResult(tssFirst, tssSecond)
}
// Execute exprFirst and exprSecond sequentially if there are cacheable repeated subexpressions
// in exprFirst and exprSecond.
// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10575
if shouldOptimizeRepeatedBinaryOpSubexprs(ec, exprFirst, exprSecond) {
qt = qt.NewChild("execute left and right sides of %q sequentially because repeated cacheable subexpression was found", be.Op)
func execBinaryOpArgs(qt *querytracer.Tracer, ec *EvalConfig, exprFirst, exprSecond metricsql.Expr, be *metricsql.BinaryOpExpr) ([]*timeseries, []*timeseries, error) {
if !canPushdownCommonFilters(be) {
// Execute exprFirst and exprSecond in parallel, since it is impossible to pushdown common filters
// from exprFirst to exprSecond.
// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/2886
qt = qt.NewChild("execute left and right sides of %q in parallel", be.Op)
defer qt.Done()
var wg sync.WaitGroup
var tssFirst []*timeseries
var errFirst error
qtFirst := qt.NewChild("expr1")
tssFirst, err := evalExpr(qtFirst, ec, exprFirst)
qtFirst.Done()
if err != nil {
return nil, nil, err
}
wg.Go(func() {
tssFirst, errFirst = evalExpr(qtFirst, ec, exprFirst)
qtFirst.Done()
})
var tssSecond []*timeseries
var errSecond error
qtSecond := qt.NewChild("expr2")
tssSecond, err := evalExpr(qtSecond, ec, exprSecond)
qtSecond.Done()
if err != nil {
return nil, nil, err
wg.Go(func() {
tssSecond, errSecond = evalExpr(qtSecond, ec, exprSecond)
qtSecond.Done()
})
wg.Wait()
if errFirst != nil {
return nil, nil, errFirst
}
if errSecond != nil {
return nil, nil, errSecond
}
return tssFirst, tssSecond, nil
}
// Execute exprFirst and exprSecond in parallel, since it is impossible to pushdown common filters
// from exprFirst to exprSecond.
// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/2886
qt = qt.NewChild("execute left and right sides of %q in parallel", be.Op)
defer qt.Done()
var wg sync.WaitGroup
var tssFirst []*timeseries
var errFirst error
qtFirst := qt.NewChild("expr1")
wg.Go(func() {
tssFirst, errFirst = evalExpr(qtFirst, ec, exprFirst)
qtFirst.Done()
})
var tssSecond []*timeseries
var errSecond error
qtSecond := qt.NewChild("expr2")
wg.Go(func() {
tssSecond, errSecond = evalExpr(qtSecond, ec, exprSecond)
qtSecond.Done()
})
wg.Wait()
if errFirst != nil {
return nil, nil, errFirst
// Execute binary operation in the following way:
//
// 1) execute the exprFirst
// 2) get common label filters for series returned at step 1
// 3) push down the found common label filters to exprSecond. This filters out unneeded series
// during exprSecond execution instead of spending compute resources on extracting and processing these series
// before they are dropped later when matching time series according to https://prometheus.io/docs/prometheus/latest/querying/operators/#vector-matching
// 4) execute the exprSecond with possible additional filters found at step 3
//
// Typical use cases:
// - Kubernetes-related: show pod creation time with the node name:
//
// kube_pod_created{namespace="prod"} * on (uid) group_left(node) kube_pod_info
//
// Without the optimization `kube_pod_info` would select and spend compute resources
// for more time series than needed. The selected time series would be dropped later
// when matching time series on the right and left sides of binary operand.
//
// - Generic alerting queries, which rely on `info` metrics.
// See https://grafana.com/blog/2021/08/04/how-to-use-promql-joins-for-more-effective-queries-of-prometheus-metrics-at-scale/
//
// - Queries, which get additional labels from `info` metrics.
// See https://www.robustperception.io/exposing-the-software-version-to-prometheus
tssFirst, err := evalExpr(qt, ec, exprFirst)
if err != nil {
return nil, nil, err
}
if errSecond != nil {
return nil, nil, errSecond
if len(tssFirst) == 0 && !strings.EqualFold(be.Op, "or") {
// Fast path: there is no sense in executing the exprSecond when exprFirst returns an empty result,
// since the "exprFirst op exprSecond" would return an empty result in any case.
// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3349
return nil, nil, nil
}
return sortResult(tssFirst, tssSecond)
}
func shouldOptimizeRepeatedBinaryOpSubexprs(ec *EvalConfig, exprFirst, exprSecond metricsql.Expr) bool {
if !ec.OptimizeRepeatedBinaryOpSubexprs {
return false
lfs := getCommonLabelFilters(tssFirst)
lfs = metricsql.TrimFiltersByGroupModifier(lfs, be)
exprSecond = metricsql.PushdownBinaryOpFilters(exprSecond, lfs)
tssSecond, err := evalExpr(qt, ec, exprSecond)
if err != nil {
return nil, nil, err
}
if ec.Start == ec.End {
return false
}
if !ec.mayCache() {
return false
}
candidatesFirst := make(map[string]struct{}, 1)
var b []byte
visitOptimizedAggrs(exprFirst, func(ae *metricsql.AggrFuncExpr) {
if hasUnseededVolatileFunc(ae) {
return
}
b = ae.AppendString(b[:0])
candidatesFirst[string(b)] = struct{}{}
})
if len(candidatesFirst) == 0 {
return false
}
repeated := false
visitOptimizedAggrs(exprSecond, func(ae *metricsql.AggrFuncExpr) {
if repeated {
return
}
b = ae.AppendString(b[:0])
_, repeated = candidatesFirst[string(b)]
})
return repeated
}
func visitOptimizedAggrs(e metricsql.Expr, f func(ae *metricsql.AggrFuncExpr)) {
metricsql.VisitAll(e, func(expr metricsql.Expr) {
ae, ok := expr.(*metricsql.AggrFuncExpr)
if !ok {
return
}
if getIncrementalAggrFuncCallbacks(ae.Name) == nil {
return
}
fe, _ := tryGetArgRollupFuncWithMetricExpr(ae)
if fe == nil {
return
}
f(ae)
})
}
func hasUnseededVolatileFunc(e metricsql.Expr) bool {
found := false
metricsql.VisitAll(e, func(expr metricsql.Expr) {
if found {
return
}
fe, ok := expr.(*metricsql.FuncExpr)
if !ok {
return
}
switch strings.ToLower(fe.Name) {
case "now":
found = true
case "rand", "rand_normal", "rand_exponential":
found = len(fe.Args) == 0
}
})
return found
return tssFirst, tssSecond, nil
}
func getCommonLabelFilters(tss []*timeseries) []metricsql.LabelFilter {

View File

@@ -170,87 +170,3 @@ func TestGetSumInstantValues(t *testing.T) {
[]*timeseries{ts("foo", 100, 1)},
)
}
func TestShouldOptimizeRepeatedBinaryOpSubexprsGate(t *testing.T) {
e, err := metricsql.Parse(`count(count(vm_requests_total) by (action,addr,cluster,endpoint)) by (action,addr,cluster) / count(count(vm_requests_total) by (action,addr,cluster,endpoint))`)
if err != nil {
t.Fatalf("unexpected error in metricsql.Parse(): %s", err)
}
be, ok := e.(*metricsql.BinaryOpExpr)
if !ok {
t.Fatalf("unexpected expr type; got %T; want *metricsql.BinaryOpExpr", e)
}
f := func(name string, ec *EvalConfig, resultExpected bool) {
t.Helper()
result := shouldOptimizeRepeatedBinaryOpSubexprs(ec, be.Left, be.Right)
if result != resultExpected {
t.Fatalf("unexpected result for %q; got %v; want %v", name, result, resultExpected)
}
}
f("disabled optimization", &EvalConfig{
Start: 1000,
End: 2000,
Step: 1000,
}, false)
f("disabled cache", &EvalConfig{
Start: 1000,
End: 2000,
Step: 1000,
OptimizeRepeatedBinaryOpSubexprs: true,
}, false)
f("instant query", &EvalConfig{
Start: 1000,
End: 1000,
Step: 1000,
MayCache: true,
OptimizeRepeatedBinaryOpSubexprs: true,
}, false)
f("repeated cacheable aggregate subexpression", &EvalConfig{
Start: 1000,
End: 2000,
Step: 1000,
MayCache: true,
OptimizeRepeatedBinaryOpSubexprs: true,
}, true)
f("unaligned range query", &EvalConfig{
Start: 1001,
End: 2000,
Step: 1000,
MayCache: true,
OptimizeRepeatedBinaryOpSubexprs: true,
}, false)
}
func TestShouldOptimizeRepeatedBinaryOpSubexprsExpressions(t *testing.T) {
f := func(name, q string, resultExpected bool) {
t.Helper()
e, err := metricsql.Parse(q)
if err != nil {
t.Fatalf("unexpected error in metricsql.Parse(%q) for %q: %s", q, name, err)
}
be, ok := e.(*metricsql.BinaryOpExpr)
if !ok {
t.Fatalf("unexpected expr type for %q; got %T; want *metricsql.BinaryOpExpr", name, e)
}
ec := &EvalConfig{Start: 1000, End: 2000, Step: 1000, MayCache: true, OptimizeRepeatedBinaryOpSubexprs: true}
result := shouldOptimizeRepeatedBinaryOpSubexprs(ec, be.Left, be.Right)
if result != resultExpected {
t.Fatalf("unexpected result for %q; got %v; want %v; query: %q", name, result, resultExpected, q)
}
}
f("original issue query", `count(count(vm_requests_total) by (action,addr,cluster,endpoint)) by (action,addr,cluster) / count(count(vm_requests_total) by (action,addr,cluster,endpoint))`, true)
f("right side contains repeated count aggregate", `count(foo) by (job) / (count(foo) by (job) + 1)`, true)
f("same sum aggregate", `sum(rate(foo[5m])) by (job) / sum(rate(foo[5m])) by (job)`, true)
f("same inner rollup but different aggregates", `sum(rate(foo[5m])) by (job) / count(rate(foo[5m])) by (job)`, false)
f("different count aggregates", `count(foo) by (job) / count(bar) by (job)`, false)
f("bare metric selector", `foo / foo`, false)
f("bare rollup function", `rate(a[5m]) / rate(a[5m])`, false)
f("now at modifier", `sum(rate(foo[5m] @ now())) by (job) / sum(rate(foo[5m] @ now())) by (job)`, false)
f("unseeded rand at modifier", `sum(rate(foo[5m] @ rand())) by (job) / sum(rate(foo[5m] @ rand())) by (job)`, false)
f("unseeded rand_normal at modifier", `sum(rate(foo[5m] @ rand_normal())) by (job) / sum(rate(foo[5m] @ rand_normal())) by (job)`, false)
f("unseeded rand_exponential at modifier", `sum(rate(foo[5m] @ rand_exponential())) by (job) / sum(rate(foo[5m] @ rand_exponential())) by (job)`, false)
f("seeded rand at modifier", `sum(rate(foo[5m] @ rand(1))) by (job) / sum(rate(foo[5m] @ rand(1))) by (job)`, true)
}

View File

@@ -11,7 +11,6 @@ import (
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmselect/netstorage"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmselect/querystats"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/decimal"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/querytracer"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/storage"
@@ -47,15 +46,15 @@ func Exec(qt *querytracer.Tracer, ec *EvalConfig, q string, isFirstPointOnly boo
e, err := parsePromQLWithCache(q)
if err != nil {
return nil, httpserver.InvalidParamError(err)
return nil, err
}
if *disableImplicitConversion || *logImplicitConversion {
isInvalid := metricsql.IsLikelyInvalid(e)
if isInvalid && *disableImplicitConversion {
// we don't add query=%q to err message as it will be added by the caller
return nil, httpserver.InvalidParamError(fmt.Errorf("query requires implicit conversion and is rejected according to -search.disableImplicitConversion command-line flag. " +
"See https://docs.victoriametrics.com/victoriametrics/metricsql/#implicit-query-conversions for details"))
return nil, fmt.Errorf("query requires implicit conversion and is rejected according to -search.disableImplicitConversion command-line flag. " +
"See https://docs.victoriametrics.com/victoriametrics/metricsql/#implicit-query-conversions for details")
}
if isInvalid && *logImplicitConversion {
logger.Warnf("query=%q requires implicit conversion, see https://docs.victoriametrics.com/victoriametrics/metricsql/#implicit-query-conversions for details", e.AppendString(nil))

View File

@@ -2994,136 +2994,6 @@ func TestExecSuccess(t *testing.T) {
resultExpected := []netstorage.Result{}
f(q, resultExpected)
})
t.Run(`compare_to_nan_left_vector_right_scalar`, func(t *testing.T) {
t.Parallel()
q := `label_set(time(), "foo", "bar") != NaN`
r := netstorage.Result{
MetricName: metricNameExpected,
Values: []float64{1000, 1200, 1400, 1600, 1800, 2000},
Timestamps: timestampsExpected,
}
r.MetricName.Tags = []storage.Tag{{
Key: []byte("foo"),
Value: []byte("bar"),
}}
resultExpected := []netstorage.Result{r}
f(q, resultExpected)
})
t.Run(`compare_to_non_nan_scalar_right`, func(t *testing.T) {
t.Parallel()
q := `label_set(time(), "foo", "bar") != 1200`
r := netstorage.Result{
MetricName: metricNameExpected,
Values: []float64{1000, nan, 1400, 1600, 1800, 2000},
Timestamps: timestampsExpected,
}
r.MetricName.Tags = []storage.Tag{{
Key: []byte("foo"),
Value: []byte("bar"),
}}
resultExpected := []netstorage.Result{r}
f(q, resultExpected)
})
t.Run(`compare_to_nan_vector_right`, func(t *testing.T) {
t.Parallel()
q := `label_set(time(), "foo", "bar") != label_set(NaN, "foo", "bar")`
r := netstorage.Result{
MetricName: metricNameExpected,
Values: []float64{1000, 1200, 1400, 1600, 1800, 2000},
Timestamps: timestampsExpected,
}
r.MetricName.Tags = []storage.Tag{{
Key: []byte("foo"),
Value: []byte("bar"),
}}
resultExpected := []netstorage.Result{r}
f(q, resultExpected)
})
t.Run(`compare_to_nan_scalar_comparison_right`, func(t *testing.T) {
t.Parallel()
q := `label_set(time(), "foo", "bar") != (1 > 2)`
r := netstorage.Result{
MetricName: metricNameExpected,
Values: []float64{1000, 1200, 1400, 1600, 1800, 2000},
Timestamps: timestampsExpected,
}
r.MetricName.Tags = []storage.Tag{{
Key: []byte("foo"),
Value: []byte("bar"),
}}
resultExpected := []netstorage.Result{r}
f(q, resultExpected)
})
t.Run(`compare_to_empty_vector_right`, func(t *testing.T) {
t.Parallel()
q := `label_set(time(), "foo", "bar") != (label_set(time(), "foo", "bar") > 100000)`
resultExpected := []netstorage.Result{}
f(q, resultExpected)
})
t.Run(`compare_to_empty_vector_right_offset`, func(t *testing.T) {
t.Parallel()
q := `label_set(time(), "foo", "bar") != ((label_set(time(), "foo", "bar") > 100000) offset 0s)`
resultExpected := []netstorage.Result{}
f(q, resultExpected)
})
t.Run(`compare_to_empty_vector_left`, func(t *testing.T) {
// A missing sample on the left side results in NaN for every comparison
// operation, so no special handling is needed there.
t.Parallel()
q := `(label_set(time(), "foo", "bar") > 100000) != label_set(time(), "foo", "bar")`
resultExpected := []netstorage.Result{}
f(q, resultExpected)
})
t.Run(`compare_to_empty_series_right_bool`, func(t *testing.T) {
t.Parallel()
q := `label_set(time(), "foo", "bar") == bool (label_set(time(), "foo", "bar") > 100000)`
resultExpected := []netstorage.Result{}
f(q, resultExpected)
})
t.Run(`compare_to_partially_empty_series_right`, func(t *testing.T) {
// Prometheus drops the timestamps filtered out by the comparison on the right.
// See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/11100#issuecomment-4933952390.
t.Parallel()
q := `label_set(time(), "foo", "bar") != (label_set(time(), "foo", "bar") * 2 > 2800)`
r := netstorage.Result{
MetricName: metricNameExpected,
Values: []float64{nan, nan, nan, 1600, 1800, 2000},
Timestamps: timestampsExpected,
}
r.MetricName.Tags = []storage.Tag{{
Key: []byte("foo"),
Value: []byte("bar"),
}}
resultExpected := []netstorage.Result{r}
f(q, resultExpected)
})
t.Run(`compare_to_empty_unlabeled_vector_right`, func(t *testing.T) {
t.Parallel()
q := `sum(label_set(time(), "foo", "bar")) != (sum(label_set(time(), "foo", "bar")) > 100000)`
resultExpected := []netstorage.Result{}
f(q, resultExpected)
})
t.Run(`compare_to_empty_series_right_with_fill_left`, func(t *testing.T) {
t.Parallel()
q := `label_set(time(), "foo", "bar") != fill_left(0) (label_set(time(), "foo", "bar") > 100000)`
resultExpected := []netstorage.Result{}
f(q, resultExpected)
})
t.Run(`compare_to_empty_series_right_with_fill_right`, func(t *testing.T) {
t.Parallel()
q := `label_set(time(), "foo", "bar") != fill_right(0) (label_set(time(), "foo", "bar") > 100000)`
r := netstorage.Result{
MetricName: metricNameExpected,
Values: []float64{1000, 1200, 1400, 1600, 1800, 2000},
Timestamps: timestampsExpected,
}
r.MetricName.Tags = []storage.Tag{{
Key: []byte("foo"),
Value: []byte("bar"),
}}
resultExpected := []netstorage.Result{r}
f(q, resultExpected)
})
t.Run(`-1 < 2`, func(t *testing.T) {
t.Parallel()
q := `-1 < 2`
@@ -4136,275 +4006,6 @@ func TestExecSuccess(t *testing.T) {
resultExpected := []netstorage.Result{r1, r2}
f(q, resultExpected)
})
t.Run(`vector + vector fill()`, func(t *testing.T) {
t.Parallel()
q := `sort_by_label((
label_set(1, "foo", "common")
or label_set(2, "foo", "left_only")
) + fill(0) (
label_set(3, "foo", "common")
or label_set(4, "foo", "right_only")
), "foo")`
r1 := netstorage.Result{
MetricName: metricNameExpected,
Values: []float64{4, 4, 4, 4, 4, 4},
Timestamps: timestampsExpected,
}
r1.MetricName.Tags = []storage.Tag{{
Key: []byte("foo"),
Value: []byte("common"),
}}
r2 := netstorage.Result{
MetricName: metricNameExpected,
Values: []float64{2, 2, 2, 2, 2, 2},
Timestamps: timestampsExpected,
}
r2.MetricName.Tags = []storage.Tag{{
Key: []byte("foo"),
Value: []byte("left_only"),
}}
r3 := netstorage.Result{
MetricName: metricNameExpected,
Values: []float64{4, 4, 4, 4, 4, 4},
Timestamps: timestampsExpected,
}
r3.MetricName.Tags = []storage.Tag{{
Key: []byte("foo"),
Value: []byte("right_only"),
}}
resultExpected := []netstorage.Result{r1, r2, r3}
f(q, resultExpected)
})
t.Run(`vector + vector fill() both sides NaN case`, func(t *testing.T) {
t.Parallel()
q := `(
label_set(time() <= 1200, "foo", "common")
) + fill(10) (
label_set(time() >= 1600, "foo", "common")
)`
r := netstorage.Result{
MetricName: metricNameExpected,
Values: []float64{1010, 1210, nan, 1610, 1810, 2010},
Timestamps: timestampsExpected,
}
r.MetricName.Tags = []storage.Tag{{
Key: []byte("foo"),
Value: []byte("common"),
}}
resultExpected := []netstorage.Result{r}
f(q, resultExpected)
})
t.Run(`vector + vector fill_left() fill_right()`, func(t *testing.T) {
t.Parallel()
q := `sort_by_label((
label_set(1, "foo", "common")
or label_set(2, "foo", "left_only")
) + fill_left(10) fill_right(20) (
label_set(3, "foo", "common")
or label_set(4, "foo", "right_only")
), "foo")`
r1 := netstorage.Result{
MetricName: metricNameExpected,
Values: []float64{4, 4, 4, 4, 4, 4},
Timestamps: timestampsExpected,
}
r1.MetricName.Tags = []storage.Tag{{
Key: []byte("foo"),
Value: []byte("common"),
}}
r2 := netstorage.Result{
MetricName: metricNameExpected,
Values: []float64{22, 22, 22, 22, 22, 22},
Timestamps: timestampsExpected,
}
r2.MetricName.Tags = []storage.Tag{{
Key: []byte("foo"),
Value: []byte("left_only"),
}}
r3 := netstorage.Result{
MetricName: metricNameExpected,
Values: []float64{14, 14, 14, 14, 14, 14},
Timestamps: timestampsExpected,
}
r3.MetricName.Tags = []storage.Tag{{
Key: []byte("foo"),
Value: []byte("right_only"),
}}
resultExpected := []netstorage.Result{r1, r2, r3}
f(q, resultExpected)
})
t.Run(`vector + vector fill_right() only`, func(t *testing.T) {
t.Parallel()
q := `sort_by_label((
label_set(1, "foo", "common")
or label_set(2, "foo", "left_only")
) + fill_right(20) (
label_set(3, "foo", "common")
or label_set(4, "foo", "right_only")
), "foo")`
r1 := netstorage.Result{
MetricName: metricNameExpected,
Values: []float64{4, 4, 4, 4, 4, 4},
Timestamps: timestampsExpected,
}
r1.MetricName.Tags = []storage.Tag{{
Key: []byte("foo"),
Value: []byte("common"),
}}
r2 := netstorage.Result{
MetricName: metricNameExpected,
Values: []float64{22, 22, 22, 22, 22, 22},
Timestamps: timestampsExpected,
}
r2.MetricName.Tags = []storage.Tag{{
Key: []byte("foo"),
Value: []byte("left_only"),
}}
resultExpected := []netstorage.Result{r1, r2}
f(q, resultExpected)
})
t.Run(`vector + vector on() fill()`, func(t *testing.T) {
t.Parallel()
q := `sort_by_label((
label_set(1, "foo", "common", "extra", "l")
or label_set(2, "foo", "left_only", "extra", "l")
) + on(foo) fill(0) (
label_set(3, "foo", "common", "extra", "r")
or label_set(4, "foo", "right_only", "extra", "r")
), "foo")`
r1 := netstorage.Result{
MetricName: metricNameExpected,
Values: []float64{4, 4, 4, 4, 4, 4},
Timestamps: timestampsExpected,
}
r1.MetricName.Tags = []storage.Tag{{
Key: []byte("foo"),
Value: []byte("common"),
}}
r2 := netstorage.Result{
MetricName: metricNameExpected,
Values: []float64{2, 2, 2, 2, 2, 2},
Timestamps: timestampsExpected,
}
r2.MetricName.Tags = []storage.Tag{{
Key: []byte("foo"),
Value: []byte("left_only"),
}}
r3 := netstorage.Result{
MetricName: metricNameExpected,
Values: []float64{4, 4, 4, 4, 4, 4},
Timestamps: timestampsExpected,
}
r3.MetricName.Tags = []storage.Tag{{
Key: []byte("foo"),
Value: []byte("right_only"),
}}
resultExpected := []netstorage.Result{r1, r2, r3}
f(q, resultExpected)
})
t.Run(`vector + vector on() group_left() fill_right()`, func(t *testing.T) {
t.Parallel()
q := `sort_by_label((
label_set(1, "method", "get", "code", "500")
or label_set(2, "method", "get", "code", "404")
or label_set(3, "method", "put", "code", "501")
) + on(method) group_left() fill_right(0) (
label_set(10, "method", "get")
), "method", "code")`
r1 := netstorage.Result{
MetricName: metricNameExpected,
Values: []float64{12, 12, 12, 12, 12, 12},
Timestamps: timestampsExpected,
}
r1.MetricName.Tags = []storage.Tag{
{
Key: []byte("code"),
Value: []byte("404"),
},
{
Key: []byte("method"),
Value: []byte("get"),
},
}
r2 := netstorage.Result{
MetricName: metricNameExpected,
Values: []float64{11, 11, 11, 11, 11, 11},
Timestamps: timestampsExpected,
}
r2.MetricName.Tags = []storage.Tag{
{
Key: []byte("code"),
Value: []byte("500"),
},
{
Key: []byte("method"),
Value: []byte("get"),
},
}
r3 := netstorage.Result{
MetricName: metricNameExpected,
Values: []float64{3, 3, 3, 3, 3, 3},
Timestamps: timestampsExpected,
}
r3.MetricName.Tags = []storage.Tag{
{
Key: []byte("code"),
Value: []byte("501"),
},
{
Key: []byte("method"),
Value: []byte("put"),
},
}
resultExpected := []netstorage.Result{r1, r2, r3}
f(q, resultExpected)
})
t.Run(`vector / vector ignoring() fill()`, func(t *testing.T) {
t.Parallel()
q := `sort_by_label((
label_set(6, "method", "get", "code", "500")
or label_set(1, "method", "put", "code", "500")
) / ignoring(code) fill(0) (
label_set(12, "method", "get")
or label_set(5, "method", "post")
or label_set(10, "method", "put")
), "method")`
r1 := netstorage.Result{
MetricName: metricNameExpected,
Values: []float64{0.5, 0.5, 0.5, 0.5, 0.5, 0.5},
Timestamps: timestampsExpected,
}
r1.MetricName.Tags = []storage.Tag{
{
Key: []byte("method"),
Value: []byte("get"),
},
}
r2 := netstorage.Result{
MetricName: metricNameExpected,
Values: []float64{0, 0, 0, 0, 0, 0},
Timestamps: timestampsExpected,
}
r2.MetricName.Tags = []storage.Tag{
{
Key: []byte("method"),
Value: []byte("post"),
},
}
r3 := netstorage.Result{
MetricName: metricNameExpected,
Values: []float64{0.1, 0.1, 0.1, 0.1, 0.1, 0.1},
Timestamps: timestampsExpected,
}
r3.MetricName.Tags = []storage.Tag{
{
Key: []byte("method"),
Value: []byte("put"),
},
}
resultExpected := []netstorage.Result{r1, r2, r3}
f(q, resultExpected)
})
t.Run(`histogram_quantile(scalar)`, func(t *testing.T) {
t.Parallel()
q := `histogram_quantile(0.6, time())`
@@ -5232,137 +4833,13 @@ func TestExecSuccess(t *testing.T) {
resultExpected := []netstorage.Result{}
f(q, resultExpected)
})
// buckets that are consecutively empty at left and right ends will not be preserved.
t.Run(`buckets_limit(trim_zero_preserve_empty_when_limit_not_reached)`, func(t *testing.T) {
t.Run(`buckets_limit(zero)`, func(t *testing.T) {
t.Parallel()
q := `sort(buckets_limit(3, (
alias(label_set(36, "le", "+Inf"), "metric"),
alias(label_set(36, "le", "25"), "metric"),
alias(label_set(36, "le", "21"), "metric"),
alias(label_set(36, "le", "19"), "metric"),
alias(label_set(36, "le", "18"), "metric"),
alias(label_set(36, "le", "17"), "metric"),
alias(label_set(36, "le", "16"), "metric"),
alias(label_set(27, "le", "12"), "metric"),
alias(label_set(14, "le", "9"), "metric"),
alias(label_set(0, "le", "6"), "metric"),
alias(label_set(0, "le", "1"), "metric"),
)))`
r1 := netstorage.Result{
MetricName: metricNameExpected,
Values: []float64{14, 14, 14, 14, 14, 14},
Timestamps: timestampsExpected,
}
r1.MetricName.MetricGroup = []byte("metric")
r1.MetricName.Tags = []storage.Tag{
{
Key: []byte("le"),
Value: []byte("9"),
},
}
r2 := netstorage.Result{
MetricName: metricNameExpected,
Values: []float64{27, 27, 27, 27, 27, 27},
Timestamps: timestampsExpected,
}
r2.MetricName.MetricGroup = []byte("metric")
r2.MetricName.Tags = []storage.Tag{
{
Key: []byte("le"),
Value: []byte("12"),
},
}
r3 := netstorage.Result{
MetricName: metricNameExpected,
Values: []float64{36, 36, 36, 36, 36, 36},
Timestamps: timestampsExpected,
}
r3.MetricName.MetricGroup = []byte("metric")
r3.MetricName.Tags = []storage.Tag{
{
Key: []byte("le"),
Value: []byte("16"),
},
}
resultExpected := []netstorage.Result{r1, r2, r3}
f(q, resultExpected)
})
// the number of non-empty bucket doesn't reach the given "limit", so some empty buckets will be preserved, and left buckets are preferred to be kept.
t.Run(`buckets_limit(trim_zero)`, func(t *testing.T) {
t.Parallel()
q := `sort(buckets_limit(5, (
alias(label_set(36, "le", "18"), "metric"),
alias(label_set(36, "le", "17"), "metric"),
alias(label_set(36, "le", "16"), "metric"),
alias(label_set(27, "le", "12"), "metric"),
alias(label_set(14, "le", "9"), "metric"),
alias(label_set(0, "le", "6"), "metric"),
alias(label_set(0, "le", "1"), "metric"),
)))`
r1 := netstorage.Result{
MetricName: metricNameExpected,
Values: []float64{0, 0, 0, 0, 0, 0},
Timestamps: timestampsExpected,
}
r1.MetricName.MetricGroup = []byte("metric")
r1.MetricName.Tags = []storage.Tag{
{
Key: []byte("le"),
Value: []byte("1"),
},
}
r2 := netstorage.Result{
MetricName: metricNameExpected,
Values: []float64{0, 0, 0, 0, 0, 0},
Timestamps: timestampsExpected,
}
r2.MetricName.MetricGroup = []byte("metric")
r2.MetricName.Tags = []storage.Tag{
{
Key: []byte("le"),
Value: []byte("6"),
},
}
r3 := netstorage.Result{
MetricName: metricNameExpected,
Values: []float64{14, 14, 14, 14, 14, 14},
Timestamps: timestampsExpected,
}
r3.MetricName.MetricGroup = []byte("metric")
r3.MetricName.Tags = []storage.Tag{
{
Key: []byte("le"),
Value: []byte("9"),
},
}
r4 := netstorage.Result{
MetricName: metricNameExpected,
Values: []float64{27, 27, 27, 27, 27, 27},
Timestamps: timestampsExpected,
}
r4.MetricName.MetricGroup = []byte("metric")
r4.MetricName.Tags = []storage.Tag{
{
Key: []byte("le"),
Value: []byte("12"),
},
}
r5 := netstorage.Result{
MetricName: metricNameExpected,
Values: []float64{36, 36, 36, 36, 36, 36},
Timestamps: timestampsExpected,
}
r5.MetricName.MetricGroup = []byte("metric")
r5.MetricName.Tags = []storage.Tag{
{
Key: []byte("le"),
Value: []byte("16"),
},
}
resultExpected := []netstorage.Result{r1, r2, r3, r4, r5}
q := `buckets_limit(0, (
alias(label_set(100, "le", "inf", "x", "y"), "metric"),
alias(label_set(50, "le", "120", "x", "y"), "metric"),
))`
resultExpected := []netstorage.Result{}
f(q, resultExpected)
})
t.Run(`buckets_limit(unused)`, func(t *testing.T) {
@@ -6751,6 +6228,50 @@ func TestExecSuccess(t *testing.T) {
resultExpected := []netstorage.Result{r1, r2, r3, r4, r5, r6, r7}
f(q, resultExpected)
})
t.Run(`sum(histogram_over_time) by (vmrange)`, func(t *testing.T) {
t.Parallel()
q := `sort_by_label(
buckets_limit(
3,
sum(histogram_over_time(alias(label_set(rand(0)*1.3+1.1, "foo", "bar"), "xxx")[200s:5s])) by (vmrange)
), "le"
)`
r1 := netstorage.Result{
MetricName: metricNameExpected,
Values: []float64{40, 40, 40, 40, 40, 40},
Timestamps: timestampsExpected,
}
r1.MetricName.Tags = []storage.Tag{
{
Key: []byte("le"),
Value: []byte("+Inf"),
},
}
r2 := netstorage.Result{
MetricName: metricNameExpected,
Values: []float64{0, 0, 0, 0, 0, 0},
Timestamps: timestampsExpected,
}
r2.MetricName.Tags = []storage.Tag{
{
Key: []byte("le"),
Value: []byte("1.000e+00"),
},
}
r3 := netstorage.Result{
MetricName: metricNameExpected,
Values: []float64{40, 40, 40, 40, 40, 40},
Timestamps: timestampsExpected,
}
r3.MetricName.Tags = []storage.Tag{
{
Key: []byte("le"),
Value: []byte("2.448e+00"),
},
}
resultExpected := []netstorage.Result{r1, r2, r3}
f(q, resultExpected)
})
t.Run(`sum(histogram_over_time)`, func(t *testing.T) {
t.Parallel()
q := `sum(histogram_over_time(alias(label_set(rand(0)*1.3+1.1, "foo", "bar"), "xxx")[200s:5s]))`

View File

@@ -1055,7 +1055,7 @@ func newRollupHoltWinters(args []any) (rollupFunc, error) {
return nan
}
// See https://en.wikipedia.org/wiki/Exponential_smoothing#Double_exponential_smoothing_%28Holt_linear%29 .
// See https://en.wikipedia.org/wiki/Exponential_smoothing#Double_exponential_smoothing .
// TODO: determine whether this shit really works.
s0 := rfa.prevValue
if math.IsNaN(s0) {

View File

@@ -2,7 +2,6 @@ package promql
import (
"fmt"
"math"
"sort"
"strconv"
"sync"
@@ -289,9 +288,6 @@ func marshalMetricTagsSorted(dst []byte, mn *storage.MetricName) []byte {
}
func marshalBytesFast(dst []byte, s []byte) []byte {
if len(s) > math.MaxUint16 {
logger.Panicf("BUG: s len %d cannot exceed %d", len(s), math.MaxUint16)
}
dst = encoding.MarshalUint16(dst, uint16(len(s)))
dst = append(dst, s...)
return dst

View File

@@ -2,7 +2,6 @@ package promql
import (
"bytes"
"errors"
"fmt"
"math"
"math/rand"
@@ -394,7 +393,7 @@ func transformBucketsLimit(tfa *transformFuncArg) ([]*timeseries, error) {
return nil, err
}
if limit <= 0 {
return nil, fmt.Errorf("limit must be greater than 0; got %d", limit)
return nil, nil
}
if limit < 3 {
// Preserve the first and the last bucket for better accuracy for min and max values.
@@ -462,23 +461,6 @@ func transformBucketsLimit(tfa *transformFuncArg) ([]*timeseries, error) {
prevValue = value
}
}
// Remove buckets that are consecutively empty at left and right ends to obtain more accurate max and min values.
// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10417.
epsilon := 1e-9
isEmptyBucket := func(hits float64) bool {
return !math.IsNaN(hits) && math.Abs(hits) < epsilon
}
l := 0
r := len(leGroup) - 1
for r-l+1 > limit && isEmptyBucket(leGroup[r].hits) {
r--
}
for r-l+1 > limit && isEmptyBucket(leGroup[l].hits) {
l++
}
leGroup = leGroup[l : r+1]
for len(leGroup) > limit {
// Preserve the first and the last bucket for better accuracy for min and max values
xxMinIdx := 1
@@ -1139,29 +1121,29 @@ func groupLeTimeseries(tss []*timeseries) map[string][]leTimeseries {
func fixBrokenBuckets(i int, xss []leTimeseries) {
// Buckets are already sorted by le, so their values must be in ascending order,
// since the upper bucket includes all the lower buckets.
// If the upper bucket has lower value than the current bucket,
// then the upper bucket must be substituted with the current bucket value.
// since the next bucket includes all the previous buckets.
// If the next bucket has lower value than the current bucket,
// then the next bucket must be substituted with the current bucket value.
// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/4580#issuecomment-2186659102
if len(xss) < 2 {
return
}
vPrev := xss[0].ts.Values[i]
vNext := xss[0].ts.Values[i]
// Set the lowest bucket to 0 if its value is NaN, so it can be properly
// compared with upper buckets in the loop below.
if math.IsNaN(vPrev) {
vPrev = 0
xss[0].ts.Values[i] = vPrev
if math.IsNaN(vNext) {
vNext = 0
xss[0].ts.Values[i] = vNext
}
// Substitute upper bucket values with lower bucket values if the upper values are NaN
// or are smaller than the lower bucket values.
// or are bigger than the lower bucket values.
for j := 1; j < len(xss); j++ {
v := xss[j].ts.Values[i]
if math.IsNaN(v) || vPrev > v {
xss[j].ts.Values[i] = vPrev
if math.IsNaN(v) || vNext > v {
xss[j].ts.Values[i] = vNext
} else {
vPrev = v
vNext = v
}
}
}
@@ -2567,11 +2549,6 @@ func isDecimalChar(ch byte) bool {
func mustParseNum(s string) float64 {
f, err := strconv.ParseFloat(s, 64)
if err != nil {
if errors.Is(err, strconv.ErrRange) {
// The number is too large to fit into float64; ParseFloat returns ±Inf in this case.
// Use ±Inf for sorting purposes — it is semantically correct.
return f
}
logger.Panicf("BUG: unexpected error when parsing the number %q: %s", s, err)
}
return f

View File

@@ -385,12 +385,4 @@ func TestNumericLess(t *testing.T) {
f("12.9", "12.56", false)
f("12.56", "12.9", true)
f("12.9", "12.9", false)
// 309-digit numbers - must not panic (regression test for GHSA-9g98-8jgr-x2vv)
big := strings.Repeat("9", 309)
f(big, "1", false)
f("1", big, true)
f(big, big, false)
f("-"+big, big, true)
f(big, "-"+big, false)
}

View File

@@ -91,9 +91,9 @@ The list of MetricsQL features on top of PromQL:
Labels from the `on()` list aren't copied.
* [Aggregate functions](#aggregate-functions) accept arbitrary number of args.
For example, `avg(q1, q2, q3)` would return the average values for every point across time series returned by `q1`, `q2` and `q3`.
* [@ modifier](https://prometheus.io/docs/prometheus/latest/querying/basics/#-modifier) can be put anywhere in the query.
* [@ modifier](https://prometheus.io/docs/prometheus/latest/querying/basics/#modifier) can be put anywhere in the query.
For example, `sum(foo) @ end()` calculates `sum(foo)` at the `end` timestamp of the selected time range `[start ... end]`.
* Arbitrary subexpression can be used as [@ modifier](https://prometheus.io/docs/prometheus/latest/querying/basics/#-modifier).
* Arbitrary subexpression can be used as [@ modifier](https://prometheus.io/docs/prometheus/latest/querying/basics/#modifier).
For example, `foo @ (end() - 1h)` calculates `foo` at the `end - 1 hour` timestamp on the selected time range `[start ... end]`.
* [offset](https://prometheus.io/docs/prometheus/latest/querying/basics/#offset-modifier), lookbehind window in square brackets
and `step` value for [subquery](#subqueries) may refer to the current step aka `$__interval` value from Grafana with `[Ni]` syntax.
@@ -482,7 +482,7 @@ See also [hoeffding_bound_lower](#hoeffding_bound_lower).
#### holt_winters
`holt_winters(series_selector[d], sf, tf)` is a [rollup function](#rollup-functions), which calculates Holt-Winters value
(aka [double exponential smoothing](https://en.wikipedia.org/wiki/Exponential_smoothing#Double_exponential_smoothing_%28Holt_linear%29)) for [raw samples](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#raw-samples)
(aka [double exponential smoothing](https://en.wikipedia.org/wiki/Exponential_smoothing#Double_exponential_smoothing)) for [raw samples](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#raw-samples)
over the given lookbehind window `d` using the given smoothing factor `sf` and the given trend factor `tf`.
Both `sf` and `tf` must be in the range `[0...1]`.
@@ -1154,7 +1154,7 @@ See also [asin](#asin) and [cos](#cos).
#### acosh
`acosh(q)` is a [transform function](#transform-functions), which returns
[inverse hyperbolic cosine](https://en.wikipedia.org/wiki/Inverse_hyperbolic_functions#Definitions_in_terms_of_logarithms) for every point of every time series returned by `q`.
[inverse hyperbolic cosine](https://en.wikipedia.org/wiki/Inverse_hyperbolic_functions#Inverse_hyperbolic_cosine) for every point of every time series returned by `q`.
Metric names are stripped from the resulting series. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
@@ -1176,7 +1176,7 @@ See also [acos](#acos) and [sin](#sin).
#### asinh
`asinh(q)` is a [transform function](#transform-functions), which returns
[inverse hyperbolic sine](https://en.wikipedia.org/wiki/Inverse_hyperbolic_functions#Definitions_in_terms_of_logarithms) for every point of every time series returned by `q`.
[inverse hyperbolic sine](https://en.wikipedia.org/wiki/Inverse_hyperbolic_functions#Inverse_hyperbolic_sine) for every point of every time series returned by `q`.
Metric names are stripped from the resulting series. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
@@ -1198,7 +1198,7 @@ See also [tan](#tan).
#### atanh
`atanh(q)` is a [transform function](#transform-functions), which returns
[inverse hyperbolic tangent](https://en.wikipedia.org/wiki/Inverse_hyperbolic_functions#Definitions_in_terms_of_logarithms) for every point of every time series returned by `q`.
[inverse hyperbolic tangent](https://en.wikipedia.org/wiki/Inverse_hyperbolic_functions#Inverse_hyperbolic_tangent) for every point of every time series returned by `q`.
Metric names are stripped from the resulting series. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
@@ -1229,7 +1229,8 @@ Metric names are stripped from the resulting series. Add [keep_metric_names](#ke
`buckets_limit(limit, buckets)` is a [transform function](#transform-functions), which limits the number
of [histogram buckets](https://valyala.medium.com/improving-histogram-usability-for-prometheus-and-grafana-bc7e5df0e350) to the given `limit`.
The given `limit` should be greater than `0`. If it is less than `3`, it will be automatically raised to `3` to preserve the first and last buckets for better accuracy of min and max values.
The result will preserve the first and the last bucket to improve accuracy for min and max values.
So, if the `limit` is greater than 0 and less than 3, the function will still return 3 buckets: the first bucket, the last bucket, and a selected bucket.
See also [prometheus_buckets](#prometheus_buckets) and [histogram_quantile](#histogram_quantile).

View File

@@ -1,5 +0,0 @@
<svg width="48" height="48" fill="#020202" xmlns="http://www.w3.org/2000/svg">
<path d="M24.5475 0C10.3246.0265251 1.11379 3.06365 4.40623 6.10077c0 0 12.32997 11.23333 16.58217 14.84083.8131.6896 2.1728 1.1936 3.5191 1.2201h.1199c1.3463-.0265 2.706-.5305 3.5191-1.2201 4.2522-3.5942 16.5422-14.84083 16.5422-14.84083C48.0478 3.06365 38.8636.0265251 24.6674 0"/>
<path d="M28.1579 27.0159c-.8131.6896-2.1728 1.1936-3.5191 1.2201h-.12c-1.3463-.0265-2.7059-.5305-3.519-1.2201-2.9725-2.5067-13.35639-11.87-17.26201-15.3979v5.4112c0 .5968.22661 1.3793.6265 1.7506C7.00358 21.1936 17.2675 30.5437 20.9731 33.6737c.8132.6896 2.1728 1.1936 3.5191 1.2201h.12c1.3463-.0265 2.7059-.5305 3.519-1.2201 3.679-3.13 13.9429-12.4536 16.6089-14.8939.4132-.3713.6265-1.1538.6265-1.7506V11.618c-3.9323 3.5411-14.3162 12.931-17.2354 15.3979h.0267Z"/>
<path d="M28.1579 39.748c-.8131.6897-2.1728 1.1937-3.5191 1.2202h-.12c-1.3463-.0265-2.7059-.5305-3.519-1.2202-2.9725-2.4933-13.35639-11.8567-17.26201-15.3978v5.4111c0 .5969.22661 1.3793.6265 1.7507C7.00358 33.9258 17.2675 43.2759 20.9731 46.4058c.8132.6897 2.1728 1.1937 3.5191 1.2202h.12c1.3463-.0265 2.7059-.5305 3.519-1.2202 3.679-3.1299 13.9429-12.4535 16.6089-14.8938.4132-.3714.6265-1.1538.6265-1.7507v-5.4111c-3.9323 3.5411-14.3162 12.931-17.2354 15.3978h.0267Z"/>
</svg>

Before

Width:  |  Height:  |  Size: 1.3 KiB

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

View File

@@ -1 +0,0 @@
var e=Object.create,t=Object.defineProperty,n=Object.getOwnPropertyDescriptor,r=Object.getOwnPropertyNames,i=Object.getPrototypeOf,a=Object.prototype.hasOwnProperty,o=(e,t,n)=>()=>{if(n)throw n[0];try{return e&&(t=e(e=0)),t}catch(e){throw n=[e],e}},s=(e,t)=>()=>(t||(e((t={exports:{}}).exports,t),e=null),t.exports),c=(e,n)=>{let r={};for(var i in e)t(r,i,{get:e[i],enumerable:!0});return n||t(r,Symbol.toStringTag,{value:`Module`}),r},l=(e,i,o,s)=>{if(i&&typeof i==`object`||typeof i==`function`)for(var c=r(i),l=0,u=c.length,d;l<u;l++)d=c[l],!a.call(e,d)&&d!==o&&t(e,d,{get:(e=>i[e]).bind(null,d),enumerable:!(s=n(i,d))||s.enumerable});return e},u=(n,r,a)=>(a=n==null?{}:e(i(n)),l(r||!n||!n.__esModule?t(a,`default`,{value:n,enumerable:!0}):a,n)),d=e=>a.call(e,`module.exports`)?e[`module.exports`]:l(t({},`__esModule`,{value:!0}),e);export{u as a,d as i,o as n,c as r,s as t};

View File

@@ -0,0 +1 @@
var e=Object.create,t=Object.defineProperty,n=Object.getOwnPropertyDescriptor,r=Object.getOwnPropertyNames,i=Object.getPrototypeOf,a=Object.prototype.hasOwnProperty,o=(e,t)=>()=>(e&&(t=e(e=0)),t),s=(e,t)=>()=>(t||e((t={exports:{}}).exports,t),t.exports),c=(e,n)=>{let r={};for(var i in e)t(r,i,{get:e[i],enumerable:!0});return n||t(r,Symbol.toStringTag,{value:`Module`}),r},l=(e,i,o,s)=>{if(i&&typeof i==`object`||typeof i==`function`)for(var c=r(i),l=0,u=c.length,d;l<u;l++)d=c[l],!a.call(e,d)&&d!==o&&t(e,d,{get:(e=>i[e]).bind(null,d),enumerable:!(s=n(i,d))||s.enumerable});return e},u=(n,r,a)=>(a=n==null?{}:e(i(n)),l(r||!n||!n.__esModule?t(a,`default`,{value:n,enumerable:!0}):a,n)),d=e=>a.call(e,`module.exports`)?e[`module.exports`]:l(t({},`__esModule`,{value:!0}),e);export{u as a,d as i,o as n,c as r,s as t};

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

View File

@@ -0,0 +1 @@
<svg width="48" height="48" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M24.5475 0C10.3246.0265251 1.11379 3.06365 4.40623 6.10077c0 0 12.32997 11.23333 16.58217 14.84083.8131.6896 2.1728 1.1936 3.5191 1.2201h.1199c1.3463-.0265 2.706-.5305 3.5191-1.2201 4.2522-3.5942 16.5422-14.84083 16.5422-14.84083C48.0478 3.06365 38.8636.0265251 24.6674 0" fill="#020202"/><path d="M28.1579 27.0159c-.8131.6896-2.1728 1.1936-3.5191 1.2201h-.12c-1.3463-.0265-2.7059-.5305-3.519-1.2201-2.9725-2.5067-13.35639-11.87-17.26201-15.3979v5.4112c0 .5968.22661 1.3793.6265 1.7506C7.00358 21.1936 17.2675 30.5437 20.9731 33.6737c.8132.6896 2.1728 1.1936 3.5191 1.2201h.12c1.3463-.0265 2.7059-.5305 3.519-1.2201 3.679-3.13 13.9429-12.4536 16.6089-14.8939.4132-.3713.6265-1.1538.6265-1.7506V11.618c-3.9323 3.5411-14.3162 12.931-17.2354 15.3979h.0267Z" fill="#020202"/><path d="M28.1579 39.748c-.8131.6897-2.1728 1.1937-3.5191 1.2202h-.12c-1.3463-.0265-2.7059-.5305-3.519-1.2202-2.9725-2.4933-13.35639-11.8567-17.26201-15.3978v5.4111c0 .5969.22661 1.3793.6265 1.7507C7.00358 33.9258 17.2675 43.2759 20.9731 46.4058c.8132.6897 2.1728 1.1937 3.5191 1.2202h.12c1.3463-.0265 2.7059-.5305 3.519-1.2202 3.679-3.1299 13.9429-12.4535 16.6089-14.8938.4132-.3714.6265-1.1538.6265-1.7507v-5.4111c-3.9323 3.5411-14.3162 12.931-17.2354 15.3978h.0267Z" fill="#020202"/></svg>

After

Width:  |  Height:  |  Size: 1.3 KiB

View File

@@ -2,9 +2,9 @@
<html lang="en">
<head>
<meta charset="utf-8"/>
<link id="favicon" rel="icon" href="./assets/favicon.svg" />
<link rel="apple-touch-icon" href="./assets/favicon.svg" />
<link id="mask-icon" rel="mask-icon" href="./assets/favicon.svg" color="#000000">
<link rel="icon" href="./favicon.svg"/>
<link rel="apple-touch-icon" href="./favicon.svg"/>
<link rel="mask-icon" href="./favicon.svg" color="#000000">
<meta name="robots" content="noindex">
<meta name="viewport" content="width=device-width, initial-scale=1, maximum-scale=5"/>
@@ -37,11 +37,11 @@
<meta property="og:title" content="UI for VictoriaMetrics">
<meta property="og:url" content="https://victoriametrics.com/">
<meta property="og:description" content="Explore and troubleshoot your VictoriaMetrics data">
<script type="module" crossorigin src="./assets/index-BiDX4bB6.js"></script>
<link rel="modulepreload" crossorigin href="./assets/rolldown-runtime-CNC7AqOf.js">
<link rel="modulepreload" crossorigin href="./assets/vendor-DwJYpOdw.js">
<script type="module" crossorigin src="./assets/index-CoGukb-x.js"></script>
<link rel="modulepreload" crossorigin href="./assets/rolldown-runtime-COnpUsM8.js">
<link rel="modulepreload" crossorigin href="./assets/vendor-C8Kwp93_.js">
<link rel="stylesheet" crossorigin href="./assets/vendor-CnsZ1jie.css">
<link rel="stylesheet" crossorigin href="./assets/index-CymA7XYg.css">
<link rel="stylesheet" crossorigin href="./assets/index-BBUnmLOr.css">
</head>
<body>
<noscript>You need to enable JavaScript to run this app.</noscript>

View File

@@ -3,7 +3,7 @@
"name": "vmui",
"icons": [
{
"src": "./assets/favicon.svg",
"src": "favicon.svg",
"sizes": "any",
"type": "image/svg+xml"
}

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