mirror of
https://github.com/VictoriaMetrics/VictoriaMetrics.git
synced 2026-07-01 14:44:35 +03:00
Compare commits
97 Commits
get-series
...
VMSelectCo
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
f6f2b8b025 | ||
|
|
8e5ca7e9b0 | ||
|
|
119ba0fb5b | ||
|
|
c82127b6d4 | ||
|
|
06bc808ddc | ||
|
|
a6927c46be | ||
|
|
15a4c31e87 | ||
|
|
54f9cd6edd | ||
|
|
2e16874e95 | ||
|
|
81d330f297 | ||
|
|
3278ddd170 | ||
|
|
cc790c2ea1 | ||
|
|
950f38fd6a | ||
|
|
ab9db9152f | ||
|
|
5b89f52c72 | ||
|
|
3608ab5b4c | ||
|
|
5ee1fa70c1 | ||
|
|
1b0e843e8f | ||
|
|
679646a3b3 | ||
|
|
bb3c038e2f | ||
|
|
8f32b6648f | ||
|
|
df5f11623f | ||
|
|
6c8a41f5ed | ||
|
|
e749a6ce8d | ||
|
|
615176ad55 | ||
|
|
3aec167f00 | ||
|
|
6f633e5654 | ||
|
|
50a827256a | ||
|
|
e30e8be1f4 | ||
|
|
24ac567a9f | ||
|
|
dce8193c16 | ||
|
|
e196479fb2 | ||
|
|
1c774564a2 | ||
|
|
e1c554d4a6 | ||
|
|
3419328f1c | ||
|
|
e841e45877 | ||
|
|
d53d8849e7 | ||
|
|
d3641394d9 | ||
|
|
53a8f4bd47 | ||
|
|
2b256952c9 | ||
|
|
12086e75de | ||
|
|
d426575622 | ||
|
|
a76b1ce0e3 | ||
|
|
5f49fb7f31 | ||
|
|
80d1104fca | ||
|
|
ae59c2624c | ||
|
|
4661f69d9f | ||
|
|
4d9901fbf4 | ||
|
|
9356c2111a | ||
|
|
45f0b87150 | ||
|
|
8480f6b43e | ||
|
|
61668f0672 | ||
|
|
d1ebbf573c | ||
|
|
16422b2d14 | ||
|
|
0f1ca87611 | ||
|
|
0dd2b2cee6 | ||
|
|
7caec5fcb4 | ||
|
|
612f8ac8d6 | ||
|
|
6aa31a09d7 | ||
|
|
b6e6a50e29 | ||
|
|
a6d48b6af3 | ||
|
|
dc4cf5631b | ||
|
|
005f133146 | ||
|
|
35fc595e6f | ||
|
|
710c920d60 | ||
|
|
0ceeb14076 | ||
|
|
adc29732f9 | ||
|
|
41ffe23b18 | ||
|
|
6229a8fe7d | ||
|
|
b58c73ac90 | ||
|
|
77efbb2e36 | ||
|
|
e388e41430 | ||
|
|
ed795a8443 | ||
|
|
94e5955b1f | ||
|
|
5b31a047a5 | ||
|
|
17c3fb5656 | ||
|
|
30133ec182 | ||
|
|
8b27a36fb5 | ||
|
|
f33cd8a937 | ||
|
|
615e49c983 | ||
|
|
eb1b4c6df4 | ||
|
|
ca71127158 | ||
|
|
1df805e23b | ||
|
|
dfc459eb38 | ||
|
|
83ef694e9c | ||
|
|
f6830298dc | ||
|
|
f16bcb1355 | ||
|
|
22802101e0 | ||
|
|
00420e16f9 | ||
|
|
6c3c548ddb | ||
|
|
d52de359d5 | ||
|
|
892f4aced2 | ||
|
|
05903c8acd | ||
|
|
a9fae230ae | ||
|
|
19fac13418 | ||
|
|
3a6054f8a2 | ||
|
|
6653f6a5e7 |
2
.github/workflows/build.yml
vendored
2
.github/workflows/build.yml
vendored
@@ -66,6 +66,8 @@ jobs:
|
||||
steps:
|
||||
- name: Code checkout
|
||||
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
with:
|
||||
persist-credentials: false
|
||||
|
||||
- name: Setup Go
|
||||
id: go
|
||||
|
||||
1
.github/workflows/changelog-linter.yml
vendored
1
.github/workflows/changelog-linter.yml
vendored
@@ -17,6 +17,7 @@ jobs:
|
||||
with:
|
||||
# needed for proper diff
|
||||
fetch-depth: 0
|
||||
persist-credentials: false
|
||||
|
||||
- name: 'Validate that changelog changes are under ## tip'
|
||||
run: |
|
||||
|
||||
1
.github/workflows/check-commit-signed.yml
vendored
1
.github/workflows/check-commit-signed.yml
vendored
@@ -15,6 +15,7 @@ jobs:
|
||||
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
with:
|
||||
fetch-depth: 0 # we need full history for commit verification
|
||||
persist-credentials: false
|
||||
|
||||
- name: Check commit signatures
|
||||
run: |
|
||||
|
||||
2
.github/workflows/check-licenses.yml
vendored
2
.github/workflows/check-licenses.yml
vendored
@@ -18,6 +18,8 @@ jobs:
|
||||
steps:
|
||||
- name: Code checkout
|
||||
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
with:
|
||||
persist-credentials: false
|
||||
|
||||
- name: Setup Go
|
||||
id: go
|
||||
|
||||
2
.github/workflows/codeql-analysis-go.yml
vendored
2
.github/workflows/codeql-analysis-go.yml
vendored
@@ -32,6 +32,8 @@ jobs:
|
||||
steps:
|
||||
- name: Checkout repository
|
||||
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
with:
|
||||
persist-credentials: false
|
||||
|
||||
- name: Set up Go
|
||||
id: go
|
||||
|
||||
2
.github/workflows/docs.yaml
vendored
2
.github/workflows/docs.yaml
vendored
@@ -21,6 +21,7 @@ jobs:
|
||||
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
with:
|
||||
path: __vm
|
||||
persist-credentials: false
|
||||
|
||||
- name: Checkout private code
|
||||
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
@@ -28,6 +29,7 @@ jobs:
|
||||
repository: VictoriaMetrics/vmdocs
|
||||
token: ${{ secrets.VM_BOT_GH_TOKEN }}
|
||||
path: __vm-docs
|
||||
persist-credentials: true
|
||||
|
||||
- name: Import GPG key
|
||||
uses: crazy-max/ghaction-import-gpg@2dc316deee8e90f13e1a351ab510b4d5bc0c82cd # v7.0.0
|
||||
|
||||
6
.github/workflows/test.yml
vendored
6
.github/workflows/test.yml
vendored
@@ -35,6 +35,8 @@ jobs:
|
||||
steps:
|
||||
- name: Code checkout
|
||||
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
with:
|
||||
persist-credentials: false
|
||||
|
||||
- name: Setup Go
|
||||
id: go
|
||||
@@ -78,6 +80,8 @@ jobs:
|
||||
steps:
|
||||
- name: Code checkout
|
||||
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
with:
|
||||
persist-credentials: false
|
||||
|
||||
- name: Setup Go
|
||||
id: go
|
||||
@@ -103,6 +107,8 @@ jobs:
|
||||
steps:
|
||||
- name: Code checkout
|
||||
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
with:
|
||||
persist-credentials: false
|
||||
|
||||
- name: Setup Go
|
||||
id: go
|
||||
|
||||
2
.github/workflows/vmui.yml
vendored
2
.github/workflows/vmui.yml
vendored
@@ -33,6 +33,8 @@ jobs:
|
||||
steps:
|
||||
- name: Code checkout
|
||||
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
with:
|
||||
persist-credentials: false
|
||||
|
||||
- name: Cache node_modules
|
||||
id: cache
|
||||
|
||||
@@ -1,9 +1,18 @@
|
||||
version: "2"
|
||||
linters:
|
||||
enable:
|
||||
- errorlint
|
||||
settings:
|
||||
errcheck:
|
||||
exclude-functions:
|
||||
- (net/http.ResponseWriter).Write
|
||||
errorlint:
|
||||
errorf: true
|
||||
# Do not enable `comparison` and `asserts`: they produce false positives,
|
||||
# since many call sites intentionally compare sentinel errors directly (e.g. err == io.EOF)
|
||||
# when the producer is documented to return them unwrapped. See https://github.com/VictoriaMetrics/VictoriaLogs/pull/1490
|
||||
comparison: false
|
||||
asserts: false
|
||||
exclusions:
|
||||
generated: lax
|
||||
presets:
|
||||
|
||||
@@ -35,6 +35,9 @@ 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)
|
||||
|
||||
@@ -102,3 +105,17 @@ 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
|
||||
}
|
||||
|
||||
@@ -187,7 +187,7 @@ func newHTTPClient(argIdx int, remoteWriteURL, sanitizedURL string, fq *persiste
|
||||
return c
|
||||
}
|
||||
|
||||
func (c *client) init(argIdx, concurrency int, sanitizedURL string) {
|
||||
func (c *client) init(argIdx 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)
|
||||
@@ -204,11 +204,20 @@ func (c *client) init(argIdx, concurrency 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))
|
||||
metrics.GetOrCreateGauge(fmt.Sprintf(`vmagent_remotewrite_queues{url=%q}`, c.sanitizedURL), func() float64 {
|
||||
return float64(concurrency)
|
||||
})
|
||||
for range concurrency {
|
||||
c.wg.Go(c.runWorker)
|
||||
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)
|
||||
})
|
||||
}
|
||||
logger.Infof("initialized client for -remoteWrite.url=%q", c.sanitizedURL)
|
||||
}
|
||||
@@ -302,12 +311,12 @@ func getAWSAPIConfig(argIdx int) (*awsapi.Config, error) {
|
||||
return cfg, nil
|
||||
}
|
||||
|
||||
func (c *client) runWorker() {
|
||||
func (c *client) runWorker(readBlock func(dst []byte) ([]byte, bool)) {
|
||||
var ok bool
|
||||
var block []byte
|
||||
ch := make(chan bool, 1)
|
||||
for {
|
||||
block, ok = c.fq.MustReadBlock(block[:0])
|
||||
block, ok = readBlock(block[:0])
|
||||
if !ok {
|
||||
return
|
||||
}
|
||||
|
||||
@@ -209,13 +209,12 @@ 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)
|
||||
neededBufLen := len(src.MetricFamilyName) + len(src.Help) + len(src.Unit)
|
||||
bufLen := len(wr.metadatabuf)
|
||||
wr.metadatabuf = slicesutil.SetLength(wr.metadatabuf, bufLen+neededBufLen)
|
||||
buf := wr.metadatabuf[:bufLen]
|
||||
@@ -230,6 +229,11 @@ 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
|
||||
}
|
||||
|
||||
|
||||
@@ -12,19 +12,18 @@ import (
|
||||
"sync/atomic"
|
||||
"time"
|
||||
|
||||
"github.com/cespare/xxhash/v2"
|
||||
|
||||
"github.com/VictoriaMetrics/metrics"
|
||||
"github.com/cespare/xxhash/v2"
|
||||
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/bloomfilter"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/cgroup"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/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"
|
||||
@@ -66,6 +65,9 @@ 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 "+
|
||||
@@ -103,6 +105,9 @@ 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. "+
|
||||
"Please see https://docs.victoriametrics.com/victoriametrics/vmagent/#monitoring-data-exchange")
|
||||
)
|
||||
|
||||
var (
|
||||
@@ -159,8 +164,8 @@ func InitSecretFlags() {
|
||||
}
|
||||
|
||||
var (
|
||||
shardByURLLabelsMap map[string]struct{}
|
||||
shardByURLIgnoreLabelsMap map[string]struct{}
|
||||
shardByURLLabelsFilter []string
|
||||
shardByURLIgnoreLabelsFilter []string
|
||||
)
|
||||
|
||||
// Init initializes remotewrite.
|
||||
@@ -207,8 +212,8 @@ 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")
|
||||
}
|
||||
shardByURLLabelsMap = newMapFromStrings(*shardByURLLabels)
|
||||
shardByURLIgnoreLabelsMap = newMapFromStrings(*shardByURLIgnoreLabels)
|
||||
shardByURLLabelsFilter = slices.Clone(*shardByURLLabels)
|
||||
shardByURLIgnoreLabelsFilter = slices.Clone(*shardByURLIgnoreLabels)
|
||||
|
||||
initLabelsGlobal()
|
||||
|
||||
@@ -304,6 +309,10 @@ 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 {
|
||||
@@ -695,18 +704,18 @@ func shardAmountRemoteWriteCtx(tssBlock []prompb.TimeSeries, shards [][]prompb.T
|
||||
|
||||
for _, ts := range tssBlock {
|
||||
hashLabels := ts.Labels
|
||||
if len(shardByURLLabelsMap) > 0 {
|
||||
if len(shardByURLLabelsFilter) > 0 {
|
||||
hashLabels = tmpLabels.Labels[:0]
|
||||
for _, label := range ts.Labels {
|
||||
if _, ok := shardByURLLabelsMap[label.Name]; ok {
|
||||
if slices.Contains(shardByURLLabelsFilter, label.Name) {
|
||||
hashLabels = append(hashLabels, label)
|
||||
}
|
||||
}
|
||||
tmpLabels.Labels = hashLabels
|
||||
} else if len(shardByURLIgnoreLabelsMap) > 0 {
|
||||
} else if len(shardByURLIgnoreLabelsFilter) > 0 {
|
||||
hashLabels = tmpLabels.Labels[:0]
|
||||
for _, label := range ts.Labels {
|
||||
if _, ok := shardByURLIgnoreLabelsMap[label.Name]; !ok {
|
||||
if !slices.Contains(shardByURLIgnoreLabelsFilter, label.Name) {
|
||||
hashLabels = append(hashLabels, label)
|
||||
}
|
||||
}
|
||||
@@ -807,34 +816,26 @@ 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 {
|
||||
bb := labelsHashBufPool.Get()
|
||||
b := bb.B[:0]
|
||||
var d xxhash.Digest
|
||||
d.Reset()
|
||||
for _, label := range labels {
|
||||
b = append(b, label.Name...)
|
||||
b = append(b, label.Value...)
|
||||
_, _ = d.WriteString(label.Name)
|
||||
_, _ = d.WriteString(label.Value)
|
||||
}
|
||||
h := xxhash.Sum64(b)
|
||||
bb.B = b
|
||||
labelsHashBufPool.Put(bb)
|
||||
return h
|
||||
return d.Sum64()
|
||||
}
|
||||
|
||||
func getLabelsHash(labels []prompb.Label) uint64 {
|
||||
bb := labelsHashBufPool.Get()
|
||||
b := bb.B[:0]
|
||||
var d xxhash.Digest
|
||||
d.Reset()
|
||||
for _, label := range labels {
|
||||
b = append(b, label.Name...)
|
||||
b = append(b, '=')
|
||||
b = append(b, label.Value...)
|
||||
_, _ = d.WriteString(label.Name)
|
||||
_, _ = d.WriteString("=")
|
||||
_, _ = d.WriteString(label.Value)
|
||||
}
|
||||
h := xxhash.Sum64(b)
|
||||
bb.B = b
|
||||
labelsHashBufPool.Put(bb)
|
||||
return h
|
||||
return d.Sum64()
|
||||
}
|
||||
|
||||
var labelsHashBufPool bytesutil.ByteBufferPool
|
||||
|
||||
func logSkippedSeries(labels []prompb.Label, flagName string, flagValue int) {
|
||||
select {
|
||||
case <-logSkippedSeriesTicker.C:
|
||||
@@ -859,6 +860,7 @@ type remoteWriteCtx struct {
|
||||
|
||||
sas atomic.Pointer[streamaggr.Aggregators]
|
||||
deduplicator *streamaggr.Deduplicator
|
||||
mdxFilter *mdx.Filter
|
||||
|
||||
streamAggrKeepInput bool
|
||||
streamAggrDropInput bool
|
||||
@@ -873,6 +875,7 @@ type remoteWriteCtx struct {
|
||||
|
||||
rowsPushedAfterRelabel *metrics.Counter
|
||||
rowsDroppedByRelabel *metrics.Counter
|
||||
mdxRowsPreserved *metrics.Counter
|
||||
|
||||
pushFailures *metrics.Counter
|
||||
metadataDroppedOnPushFailure *metrics.Counter
|
||||
@@ -906,7 +909,8 @@ func newRemoteWriteCtx(argIdx int, remoteWriteURL *url.URL, sanitizedURL string)
|
||||
}
|
||||
|
||||
isPQDisabled := disableOnDiskQueue.GetOptionalArg(argIdx)
|
||||
queuesSize := queues.GetOptionalArg(argIdx)
|
||||
inmemoryQueueSize := inmemoryQueues.GetOptionalArg(argIdx)
|
||||
queuesSize := queues.GetOptionalArg(argIdx) + inmemoryQueueSize
|
||||
if queuesSize > maxQueues {
|
||||
queuesSize = maxQueues
|
||||
} else if queuesSize <= 0 {
|
||||
@@ -923,7 +927,13 @@ func newRemoteWriteCtx(argIdx int, remoteWriteURL *url.URL, sanitizedURL string)
|
||||
if maxInmemoryBlocks < 2 {
|
||||
maxInmemoryBlocks = 2
|
||||
}
|
||||
fq := persistentqueue.MustOpenFastQueue(queuePath, sanitizedURL, maxInmemoryBlocks, maxPendingBytes, isPQDisabled)
|
||||
fqOpts := persistentqueue.OpenFastQueueOpts{
|
||||
MaxInmemoryBlocks: maxInmemoryBlocks,
|
||||
MaxPendingBytes: maxPendingBytes,
|
||||
IsPQDisabled: isPQDisabled,
|
||||
PrioritizeInmemoryData: inmemoryQueueSize > 0,
|
||||
}
|
||||
fq := persistentqueue.MustOpenFastQueueWithOpts(queuePath, sanitizedURL, fqOpts)
|
||||
_ = metrics.GetOrCreateGauge(fmt.Sprintf(`vmagent_remotewrite_pending_data_bytes{path=%q, url=%q}`, queuePath, sanitizedURL), func() float64 {
|
||||
return float64(fq.GetPendingBytes())
|
||||
})
|
||||
@@ -936,6 +946,9 @@ 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 {
|
||||
@@ -944,7 +957,7 @@ 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, queuesSize, sanitizedURL)
|
||||
c.init(argIdx, sanitizedURL)
|
||||
|
||||
// Initialize pss
|
||||
sf := significantFigures.GetOptionalArg(argIdx)
|
||||
@@ -959,7 +972,6 @@ 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,
|
||||
@@ -976,6 +988,16 @@ func newRemoteWriteCtx(argIdx int, remoteWriteURL *url.URL, sanitizedURL string)
|
||||
}
|
||||
rwctx.initStreamAggrConfig()
|
||||
|
||||
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
|
||||
}
|
||||
|
||||
@@ -989,6 +1011,11 @@ 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()
|
||||
@@ -1004,6 +1031,7 @@ func (rwctx *remoteWriteCtx) MustStop() {
|
||||
|
||||
rwctx.rowsPushedAfterRelabel = nil
|
||||
rwctx.rowsDroppedByRelabel = nil
|
||||
|
||||
}
|
||||
|
||||
// TryPushTimeSeries sends tss series to the configured remote write endpoint
|
||||
@@ -1011,16 +1039,41 @@ 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 rctx == nil {
|
||||
return
|
||||
if v != nil {
|
||||
*v = prompb.ResetTimeSeries(tss)
|
||||
tssPool.Put(v)
|
||||
}
|
||||
if rctx != nil {
|
||||
putRelabelCtx(rctx)
|
||||
}
|
||||
if mctx != nil {
|
||||
mdx.PutContext(mctx)
|
||||
}
|
||||
*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]
|
||||
@@ -1030,8 +1083,7 @@ func (rwctx *remoteWriteCtx) TryPushTimeSeries(tss []prompb.TimeSeries, forceDro
|
||||
// from affecting time series for other remoteWrite.url configs.
|
||||
// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/467
|
||||
// and https://github.com/VictoriaMetrics/VictoriaMetrics/issues/599
|
||||
v = tssPool.Get().(*[]prompb.TimeSeries)
|
||||
tss = append(*v, tss...)
|
||||
copyTimeSeriesIfNeeded()
|
||||
rowsCountBeforeRelabel := getRowsCount(tss)
|
||||
tss = rctx.applyRelabeling(tss, pcs)
|
||||
rowsCountAfterRelabel := getRowsCount(tss)
|
||||
@@ -1049,8 +1101,7 @@ func (rwctx *remoteWriteCtx) TryPushTimeSeries(tss []prompb.TimeSeries, forceDro
|
||||
if rctx == nil {
|
||||
rctx = getRelabelCtx()
|
||||
// Make a copy of tss before dropping aggregated series
|
||||
v = tssPool.Get().(*[]prompb.TimeSeries)
|
||||
tss = append(*v, tss...)
|
||||
copyTimeSeriesIfNeeded()
|
||||
}
|
||||
tss = dropAggregatedSeries(tss, matchIdxs.B, rwctx.streamAggrDropInput)
|
||||
} else if rwctx.streamAggrDropInput {
|
||||
@@ -1058,8 +1109,7 @@ func (rwctx *remoteWriteCtx) TryPushTimeSeries(tss []prompb.TimeSeries, forceDro
|
||||
if rctx == nil {
|
||||
rctx = getRelabelCtx()
|
||||
// Make a copy of tss before dropping aggregated series
|
||||
v = tssPool.Get().(*[]prompb.TimeSeries)
|
||||
tss = append(*v, tss...)
|
||||
copyTimeSeriesIfNeeded()
|
||||
}
|
||||
tss = dropUnaggregatedSeries(tss, matchIdxs.B)
|
||||
}
|
||||
@@ -1178,15 +1228,6 @@ 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 {
|
||||
|
||||
@@ -145,10 +145,10 @@ func TestRuleValidate(t *testing.T) {
|
||||
}
|
||||
|
||||
func TestGroupValidate_Failure(t *testing.T) {
|
||||
f := func(group *Group, validateExpressions bool, errStrExpected string) {
|
||||
f := func(data []byte, validateExpressions bool, errStrExpected string) {
|
||||
t.Helper()
|
||||
|
||||
err := group.Validate(nil, validateExpressions)
|
||||
_, err := parse(map[string][]byte{"test.yaml": data}, nil, validateExpressions)
|
||||
if err == nil {
|
||||
t.Fatalf("expecting non-nil error")
|
||||
}
|
||||
@@ -158,275 +158,238 @@ func TestGroupValidate_Failure(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
f(&Group{}, false, "group name must be set")
|
||||
f([]byte(`
|
||||
groups:
|
||||
- name: ""
|
||||
`), false, "group name must be set")
|
||||
|
||||
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: 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: "negative interval",
|
||||
Interval: promutil.NewDuration(-1),
|
||||
}, false, "interval shouldn't be lower than 0")
|
||||
f([]byte(`
|
||||
groups:
|
||||
- name: negative interval
|
||||
interval: -1ms
|
||||
`), false, "interval shouldn't be lower than 0")
|
||||
|
||||
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 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: too big negative eval_offset
|
||||
interval: 1m
|
||||
eval_offset: -2m
|
||||
`), false, "eval_offset should be smaller than interval")
|
||||
|
||||
limit := -1
|
||||
f(&Group{
|
||||
Name: "wrong limit",
|
||||
Limit: &limit,
|
||||
}, false, "invalid limit")
|
||||
f([]byte(`
|
||||
groups:
|
||||
- name: wrong limit
|
||||
limit: -1
|
||||
`), false, "invalid limit")
|
||||
|
||||
f(&Group{
|
||||
Name: "wrong concurrency",
|
||||
Concurrency: -1,
|
||||
}, false, "invalid concurrency")
|
||||
f([]byte(`
|
||||
groups:
|
||||
- name: wrong concurrency
|
||||
concurrency: -1
|
||||
`), false, "invalid concurrency")
|
||||
|
||||
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
|
||||
- alert: alert
|
||||
expr: up == 1
|
||||
`), 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:
|
||||
- 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{
|
||||
{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
|
||||
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{
|
||||
{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")
|
||||
f([]byte(`
|
||||
groups:
|
||||
- name: test thanos
|
||||
type: thanos
|
||||
rules:
|
||||
- alert: alert
|
||||
expr: up == 1
|
||||
labels:
|
||||
description: "{{ value|query }}"
|
||||
`), true, "unknown datasource type")
|
||||
|
||||
// validate expressions
|
||||
f(&Group{
|
||||
Name: "test prometheus expr",
|
||||
Type: NewPrometheusType(),
|
||||
Rules: []Rule{
|
||||
{
|
||||
Record: "record",
|
||||
Expr: "up | 0",
|
||||
},
|
||||
},
|
||||
}, true, "bad MetricsQL expr")
|
||||
f([]byte(`
|
||||
groups:
|
||||
- name: test prometheus expr
|
||||
type: prometheus
|
||||
rules:
|
||||
- record: record
|
||||
expr: "up | 0"
|
||||
`), true, "bad MetricsQL 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 graphite expr
|
||||
type: graphite
|
||||
rules:
|
||||
- alert: alert
|
||||
expr: up == 1
|
||||
labels:
|
||||
description: some-description
|
||||
`), true, "bad GraphiteQL 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
|
||||
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: "_time: 1m | stats by (path, _time: 1m) 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 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 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 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 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 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")
|
||||
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")
|
||||
}
|
||||
|
||||
func TestGroupValidate_Success(t *testing.T) {
|
||||
f := func(group *Group, validateAnnotations, validateExpressions bool) {
|
||||
f := func(data []byte, validateAnnotations, validateExpressions bool) {
|
||||
t.Helper()
|
||||
|
||||
var validateTplFn ValidateTplFn
|
||||
if validateAnnotations {
|
||||
validateTplFn = notifier.ValidateTemplates
|
||||
}
|
||||
err := group.Validate(validateTplFn, validateExpressions)
|
||||
_, err := parse(map[string][]byte{"test.yaml": data}, validateTplFn, validateExpressions)
|
||||
if err != nil {
|
||||
t.Fatalf("unexpected error: %s", err)
|
||||
}
|
||||
}
|
||||
|
||||
f(&Group{
|
||||
Name: "test",
|
||||
Rules: []Rule{
|
||||
{
|
||||
Record: "record",
|
||||
Expr: "up | 0",
|
||||
},
|
||||
},
|
||||
}, false, false)
|
||||
f([]byte(`
|
||||
groups:
|
||||
- name: test
|
||||
rules:
|
||||
- record: record
|
||||
expr: "up | 0"
|
||||
`), false, false)
|
||||
|
||||
f(&Group{
|
||||
Name: "test",
|
||||
Rules: []Rule{
|
||||
{
|
||||
Alert: "alert",
|
||||
Expr: "up == 1",
|
||||
Labels: map[string]string{
|
||||
"summary": "{{ value|query }}",
|
||||
},
|
||||
},
|
||||
},
|
||||
}, false, false)
|
||||
f([]byte(`
|
||||
groups:
|
||||
- name: test
|
||||
rules:
|
||||
- alert: alert
|
||||
expr: up == 1
|
||||
labels:
|
||||
summary: "{{ value|query }}"
|
||||
`), false, false)
|
||||
|
||||
// validate annotations
|
||||
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)
|
||||
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)
|
||||
|
||||
// validate expressions
|
||||
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)
|
||||
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)
|
||||
}
|
||||
|
||||
func TestHashRule_NotEqual(t *testing.T) {
|
||||
|
||||
@@ -315,6 +315,11 @@ func configReload(ctx context.Context, m *manager, groupsCfg []config.Group, sig
|
||||
|
||||
parseFn := config.Parse
|
||||
for {
|
||||
select {
|
||||
case <-ctx.Done():
|
||||
return
|
||||
default:
|
||||
}
|
||||
select {
|
||||
case <-ctx.Done():
|
||||
return
|
||||
|
||||
@@ -457,12 +457,10 @@ 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) {
|
||||
|
||||
@@ -840,6 +840,11 @@ func authConfigReloader(sighupCh <-chan os.Signal) {
|
||||
}
|
||||
|
||||
for {
|
||||
select {
|
||||
case <-stopCh:
|
||||
return
|
||||
default:
|
||||
}
|
||||
select {
|
||||
case <-stopCh:
|
||||
return
|
||||
@@ -906,7 +911,8 @@ func reloadAuthConfigData(data []byte) (bool, error) {
|
||||
return false, fmt.Errorf("failed to parse auth config: %w", err)
|
||||
}
|
||||
|
||||
jui, oidcDP, err := parseJWTUsers(ac)
|
||||
oidcDP := &oidcDiscovererPool{}
|
||||
jui, err := parseJWTUsers(ac, oidcDP)
|
||||
if err != nil {
|
||||
return false, fmt.Errorf("failed to parse JWT users from auth config: %w", err)
|
||||
}
|
||||
|
||||
@@ -140,6 +140,18 @@ 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.
|
||||
|
||||
@@ -65,6 +65,8 @@ 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
|
||||
@@ -72,9 +74,8 @@ type JWTConfig struct {
|
||||
verifierPool atomic.Pointer[jwt.VerifierPool]
|
||||
}
|
||||
|
||||
func parseJWTUsers(ac *AuthConfig) ([]*UserInfo, *oidcDiscovererPool, error) {
|
||||
func parseJWTUsers(ac *AuthConfig, oidcDP *oidcDiscovererPool) ([]*UserInfo, error) {
|
||||
jui := make([]*UserInfo, 0, len(ac.Users))
|
||||
oidcDP := &oidcDiscovererPool{}
|
||||
|
||||
uniqClaims := make(map[string]*UserInfo)
|
||||
var sortedClaims []string
|
||||
@@ -85,10 +86,10 @@ func parseJWTUsers(ac *AuthConfig) ([]*UserInfo, *oidcDiscovererPool, error) {
|
||||
}
|
||||
|
||||
if ui.AuthToken != "" || ui.BearerToken != "" || ui.Username != "" || ui.Password != "" {
|
||||
return nil, nil, fmt.Errorf("auth_token, bearer_token, username and password cannot be specified if jwt is set")
|
||||
return 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, nil, fmt.Errorf("jwt must contain at least a single public key, public_key_files, oidc or have skip_verify=true")
|
||||
return 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]
|
||||
@@ -97,7 +98,7 @@ func parseJWTUsers(ac *AuthConfig) ([]*UserInfo, *oidcDiscovererPool, error) {
|
||||
sortedClaims = append(sortedClaims, fmt.Sprintf("%s=%s", ck, cv))
|
||||
pc, err := jwt.NewClaim(ck, cv)
|
||||
if err != nil {
|
||||
return nil, nil, fmt.Errorf("incorrect match claim, key=%q, value regex=%q: %w", ck, cv, err)
|
||||
return nil, fmt.Errorf("incorrect match claim, key=%q, value regex=%q: %w", ck, cv, err)
|
||||
}
|
||||
parsedClaims = append(parsedClaims, pc)
|
||||
}
|
||||
@@ -106,7 +107,7 @@ func parseJWTUsers(ac *AuthConfig) ([]*UserInfo, *oidcDiscovererPool, error) {
|
||||
claimsString = strings.Join(sortedClaims, ",")
|
||||
|
||||
if oldUI, ok := uniqClaims[claimsString]; ok {
|
||||
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)
|
||||
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)
|
||||
}
|
||||
uniqClaims[claimsString] = &ui
|
||||
if len(jwtToken.PublicKeys) > 0 || len(jwtToken.PublicKeyFiles) > 0 {
|
||||
@@ -115,7 +116,7 @@ func parseJWTUsers(ac *AuthConfig) ([]*UserInfo, *oidcDiscovererPool, error) {
|
||||
for i := range jwtToken.PublicKeys {
|
||||
k, err := jwt.ParseKey([]byte(jwtToken.PublicKeys[i]))
|
||||
if err != nil {
|
||||
return nil, nil, err
|
||||
return nil, err
|
||||
}
|
||||
keys = append(keys, k)
|
||||
}
|
||||
@@ -123,52 +124,52 @@ func parseJWTUsers(ac *AuthConfig) ([]*UserInfo, *oidcDiscovererPool, error) {
|
||||
for _, filePath := range jwtToken.PublicKeyFiles {
|
||||
keyData, err := os.ReadFile(filePath)
|
||||
if err != nil {
|
||||
return nil, nil, fmt.Errorf("cannot read public key from file %q: %w", filePath, err)
|
||||
return nil, fmt.Errorf("cannot read public key from file %q: %w", filePath, err)
|
||||
}
|
||||
k, err := jwt.ParseKey(keyData)
|
||||
if err != nil {
|
||||
return nil, nil, fmt.Errorf("cannot parse public key from file %q: %w", filePath, err)
|
||||
return 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, nil, err
|
||||
return nil, err
|
||||
}
|
||||
|
||||
jwtToken.verifierPool.Store(vp)
|
||||
}
|
||||
if jwtToken.OIDC != nil {
|
||||
if len(jwtToken.PublicKeys) > 0 || len(jwtToken.PublicKeyFiles) > 0 || jwtToken.SkipVerify {
|
||||
return nil, nil, fmt.Errorf("jwt with oidc cannot contain public keys or have skip_verify=true")
|
||||
return nil, fmt.Errorf("jwt with oidc cannot contain public keys or have skip_verify=true")
|
||||
}
|
||||
|
||||
if jwtToken.OIDC.Issuer == "" {
|
||||
return nil, nil, fmt.Errorf("oidc issuer cannot be empty")
|
||||
return nil, fmt.Errorf("oidc issuer cannot be empty")
|
||||
}
|
||||
isserURL, err := url.Parse(jwtToken.OIDC.Issuer)
|
||||
if err != nil {
|
||||
return nil, nil, fmt.Errorf("oidc issuer %q must be a valid URL", jwtToken.OIDC.Issuer)
|
||||
return nil, fmt.Errorf("oidc issuer %q must be a valid URL", jwtToken.OIDC.Issuer)
|
||||
}
|
||||
if isserURL.Scheme != "https" && isserURL.Scheme != "http" {
|
||||
return nil, nil, fmt.Errorf("oidc issuer %q must have http or https scheme", jwtToken.OIDC.Issuer)
|
||||
return 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, nil, err
|
||||
return nil, err
|
||||
}
|
||||
|
||||
if err := ui.initURLs(); err != nil {
|
||||
return nil, nil, err
|
||||
return nil, err
|
||||
}
|
||||
|
||||
metricLabels, err := ui.getMetricLabels()
|
||||
if err != nil {
|
||||
return nil, nil, fmt.Errorf("cannot parse metric_labels: %w", err)
|
||||
return 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)
|
||||
@@ -187,7 +188,7 @@ func parseJWTUsers(ac *AuthConfig) ([]*UserInfo, *oidcDiscovererPool, error) {
|
||||
|
||||
rt, err := newRoundTripper(ui.TLSCAFile, ui.TLSCertFile, ui.TLSKeyFile, ui.TLSServerName, ui.TLSInsecureSkipVerify)
|
||||
if err != nil {
|
||||
return nil, nil, fmt.Errorf("cannot initialize HTTP RoundTripper: %w", err)
|
||||
return nil, fmt.Errorf("cannot initialize HTTP RoundTripper: %w", err)
|
||||
}
|
||||
ui.rt = rt
|
||||
|
||||
@@ -200,7 +201,7 @@ func parseJWTUsers(ac *AuthConfig) ([]*UserInfo, *oidcDiscovererPool, error) {
|
||||
return len(jui[i].JWT.MatchClaims) > len(jui[j].JWT.MatchClaims)
|
||||
})
|
||||
|
||||
return jui, oidcDP, nil
|
||||
return jui, nil
|
||||
}
|
||||
|
||||
var tokenPool sync.Pool
|
||||
@@ -433,7 +434,6 @@ 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() {
|
||||
@@ -488,7 +488,6 @@ func hasAnyPlaceholders(u *url.URL) bool {
|
||||
return true
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
@@ -39,16 +39,14 @@ XOtclIk1uhc03oL9nOQ=
|
||||
}
|
||||
return
|
||||
}
|
||||
users, oidcDP, err := parseJWTUsers(ac)
|
||||
oidcDP := &oidcDiscovererPool{}
|
||||
users, err := parseJWTUsers(ac, oidcDP)
|
||||
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
|
||||
@@ -326,7 +324,8 @@ XOtclIk1uhc03oL9nOQ=
|
||||
t.Fatalf("unexpected error: %s", err)
|
||||
}
|
||||
|
||||
jui, oidcDP, err := parseJWTUsers(ac)
|
||||
oidcDP := &oidcDiscovererPool{}
|
||||
jui, err := parseJWTUsers(ac, oidcDP)
|
||||
if err != nil {
|
||||
t.Fatalf("unexpected error: %s", err)
|
||||
}
|
||||
|
||||
@@ -6,6 +6,7 @@ import (
|
||||
"flag"
|
||||
"fmt"
|
||||
"io"
|
||||
"math/rand/v2"
|
||||
"net"
|
||||
"net/http"
|
||||
"net/textproto"
|
||||
@@ -31,6 +32,7 @@ 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 (
|
||||
@@ -190,6 +192,10 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
|
||||
if tkn == nil {
|
||||
logger.Panicf("BUG: unexpected nil jwt token for user %q", ui.name())
|
||||
}
|
||||
if !tkn.HasVMAccessClaim() && ui.JWT.DefaultVMAccessClaim == nil {
|
||||
http.Error(w, "Unauthorized", http.StatusUnauthorized)
|
||||
return true
|
||||
}
|
||||
defer putToken(tkn)
|
||||
processUserRequest(w, r, ui, tkn)
|
||||
return true
|
||||
@@ -202,6 +208,7 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
|
||||
}
|
||||
|
||||
invalidAuthTokenRequests.Inc()
|
||||
slowdownUnauthorizedResponse(r)
|
||||
if *logInvalidAuthTokens {
|
||||
err := fmt.Errorf("cannot authorize request with auth tokens %q", ats)
|
||||
err = &httpserver.ErrorWithStatusCode{
|
||||
@@ -424,8 +431,12 @@ 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, tkn.VMAccess())
|
||||
targetURL, hc = replaceJWTPlaceholders(bu, hc, vmac)
|
||||
}
|
||||
if isDefault {
|
||||
// Don't change path and add request_path query param for default route.
|
||||
@@ -881,3 +892,20 @@ 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)
|
||||
}
|
||||
|
||||
@@ -739,6 +739,12 @@ 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{
|
||||
@@ -779,6 +785,26 @@ statusCode=401
|
||||
Unauthorized`
|
||||
f(simpleCfgStr, request, responseExpected)
|
||||
|
||||
// token without vm_access claim is accepted when it
|
||||
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)
|
||||
|
||||
@@ -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.md).
|
||||
vmctl docs can be edited at [docs/vmctl.md](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/docs/victoriametrics/vmctl/vmctl.md).
|
||||
|
||||
@@ -131,16 +131,13 @@ func (ac *authContext) initFromBasicAuthConfig(ba *BasicAuthConfig) error {
|
||||
if ba.Username == "" {
|
||||
return fmt.Errorf("missing `username` in `basic_auth` section")
|
||||
}
|
||||
if ba.Password != "" {
|
||||
ac.getAuthHeader = func() string {
|
||||
// See https://en.wikipedia.org/wiki/Basic_access_authentication
|
||||
token := ba.Username + ":" + ba.Password
|
||||
token64 := base64.StdEncoding.EncodeToString([]byte(token))
|
||||
return "Basic " + token64
|
||||
}
|
||||
ac.authDigest = fmt.Sprintf("basic(username=%q, password=%q)", ba.Username, ba.Password)
|
||||
return nil
|
||||
ac.getAuthHeader = func() string {
|
||||
// See https://en.wikipedia.org/wiki/Basic_access_authentication
|
||||
token := ba.Username + ":" + ba.Password
|
||||
token64 := base64.StdEncoding.EncodeToString([]byte(token))
|
||||
return "Basic " + token64
|
||||
}
|
||||
ac.authDigest = fmt.Sprintf("basic(username=%q, password=%q)", ba.Username, ba.Password)
|
||||
return nil
|
||||
}
|
||||
|
||||
|
||||
@@ -69,6 +69,8 @@ const (
|
||||
vmAddr = "vm-addr"
|
||||
vmUser = "vm-user"
|
||||
vmPassword = "vm-password"
|
||||
vmHeaders = "vm-headers"
|
||||
vmBearerToken = "vm-bearer-token"
|
||||
vmAccountID = "vm-account-id"
|
||||
vmConcurrency = "vm-concurrency"
|
||||
vmCompress = "vm-compress"
|
||||
@@ -112,6 +114,16 @@ var (
|
||||
Usage: "VictoriaMetrics password for basic auth",
|
||||
EnvVars: []string{"VM_PASSWORD"},
|
||||
},
|
||||
&cli.StringFlag{
|
||||
Name: vmHeaders,
|
||||
Usage: "Optional HTTP headers to send with each request to the corresponding destination address. \n" +
|
||||
"For example, --vm-headers='My-Auth:foobar' would send 'My-Auth: foobar' HTTP header with every request to the corresponding destination address. \n" +
|
||||
"Multiple headers must be delimited by '^^': --vm-headers='header1:value1^^header2:value2'",
|
||||
},
|
||||
&cli.StringFlag{
|
||||
Name: vmBearerToken,
|
||||
Usage: "Optional bearer auth token to use for the corresponding --vm-addr",
|
||||
},
|
||||
&cli.StringFlag{
|
||||
Name: vmAccountID,
|
||||
Usage: "AccountID is an arbitrary 32-bit integer identifying namespace for data ingestion (aka tenant). \n" +
|
||||
|
||||
@@ -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 filed %q", cr.field)
|
||||
return nil, nil, fmt.Errorf("response doesn't contain field %q", cr.field)
|
||||
}
|
||||
values := make([]float64, len(fieldValues))
|
||||
for i, fv := range fieldValues {
|
||||
|
||||
@@ -457,7 +457,7 @@ func main() {
|
||||
auth.WithBearer(c.String(vmNativeDstBearerToken)),
|
||||
auth.WithHeaders(c.String(vmNativeDstHeaders)))
|
||||
if err != nil {
|
||||
return fmt.Errorf("error initialize auth config for destination: %s", dstAddr)
|
||||
return fmt.Errorf("error initialize auth config for destination: %s: %w", dstAddr, err)
|
||||
}
|
||||
|
||||
// create TLS config
|
||||
@@ -563,11 +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) {
|
||||
@@ -596,11 +596,18 @@ func initConfigVM(c *cli.Context) (vm.Config, error) {
|
||||
return vm.Config{}, fmt.Errorf("failed to create backoff object: %w", err)
|
||||
}
|
||||
|
||||
authCfg, err := auth.Generate(
|
||||
auth.WithBasicAuth(c.String(vmUser), c.String(vmPassword)),
|
||||
auth.WithBearer(c.String(vmBearerToken)),
|
||||
auth.WithHeaders(c.String(vmHeaders)))
|
||||
if err != nil {
|
||||
return vm.Config{}, fmt.Errorf("error initialize auth config for destination: %s: %w", addr, err)
|
||||
}
|
||||
|
||||
return vm.Config{
|
||||
Addr: addr,
|
||||
Transport: tr,
|
||||
User: c.String(vmUser),
|
||||
Password: c.String(vmPassword),
|
||||
AuthCfg: authCfg,
|
||||
Concurrency: uint8(c.Int(vmConcurrency)),
|
||||
Compress: c.Bool(vmCompress),
|
||||
AccountID: c.String(vmAccountID),
|
||||
|
||||
@@ -74,9 +74,9 @@ func wrapErr(vmErr *vm.ImportError, verbose bool) error {
|
||||
verboseMsg = "(enable `--verbose` output to get more details)"
|
||||
}
|
||||
if vmErr.Err == nil {
|
||||
return fmt.Errorf("%s\n\tLatest delivered batch for timestamps range %d - %d %s\n%s",
|
||||
return fmt.Errorf("%w\n\tLatest delivered batch for timestamps range %d - %d %s\n%s",
|
||||
vmErr.Err, minTS, maxTS, verboseMsg, errTS)
|
||||
}
|
||||
return fmt.Errorf("%s\n\tImporting batch failed for timestamps range %d - %d %s\n%s",
|
||||
return fmt.Errorf("%w\n\tImporting batch failed for timestamps range %d - %d %s\n%s",
|
||||
vmErr.Err, minTS, maxTS, verboseMsg, errTS)
|
||||
}
|
||||
|
||||
@@ -12,6 +12,7 @@ import (
|
||||
"sync"
|
||||
"time"
|
||||
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/auth"
|
||||
"github.com/VictoriaMetrics/metrics"
|
||||
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/backoff"
|
||||
@@ -27,6 +28,8 @@ type Config struct {
|
||||
// --httpListenAddr value for single node version
|
||||
// --httpListenAddr value of vmselect component for cluster version
|
||||
Addr string
|
||||
|
||||
AuthCfg *auth.Config
|
||||
// Transport allows specifying custom http.Transport
|
||||
Transport *http.Transport
|
||||
// Concurrency defines number of worker
|
||||
@@ -40,10 +43,6 @@ type Config struct {
|
||||
// BatchSize defines how many samples
|
||||
// importer collects before sending the import request
|
||||
BatchSize int
|
||||
// User name for basic auth
|
||||
User string
|
||||
// Password for basic auth
|
||||
Password string
|
||||
// SignificantFigures defines the number of significant figures to leave
|
||||
// in metric values before importing.
|
||||
// Zero value saves all the significant decimal places
|
||||
@@ -65,11 +64,10 @@ type Config struct {
|
||||
// see https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#how-to-import-time-series-data
|
||||
type Importer struct {
|
||||
addr string
|
||||
authCfg *auth.Config
|
||||
client *http.Client
|
||||
importPath string
|
||||
compress bool
|
||||
user string
|
||||
password string
|
||||
|
||||
close chan struct{}
|
||||
input chan *TimeSeries
|
||||
@@ -148,8 +146,7 @@ func NewImporter(ctx context.Context, cfg Config) (*Importer, error) {
|
||||
client: client,
|
||||
importPath: importPath,
|
||||
compress: cfg.Compress,
|
||||
user: cfg.User,
|
||||
password: cfg.Password,
|
||||
authCfg: cfg.AuthCfg,
|
||||
rl: limiter.NewLimiter(cfg.RateLimit),
|
||||
close: make(chan struct{}),
|
||||
input: make(chan *TimeSeries, cfg.Concurrency*4),
|
||||
@@ -304,8 +301,8 @@ func (im *Importer) Ping() error {
|
||||
if err != nil {
|
||||
return fmt.Errorf("cannot create request to %q: %w", im.addr, err)
|
||||
}
|
||||
if im.user != "" {
|
||||
req.SetBasicAuth(im.user, im.password)
|
||||
if im.authCfg != nil {
|
||||
im.authCfg.SetHeaders(req, true)
|
||||
}
|
||||
resp, err := im.client.Do(req)
|
||||
if err != nil {
|
||||
@@ -334,8 +331,8 @@ func (im *Importer) Import(tsBatch []*TimeSeries) error {
|
||||
im.importRequestsErrorsTotal.Inc()
|
||||
return fmt.Errorf("cannot create request to %q: %w", im.addr, err)
|
||||
}
|
||||
if im.user != "" {
|
||||
req.SetBasicAuth(im.user, im.password)
|
||||
if im.authCfg != nil {
|
||||
im.authCfg.SetHeaders(req, true)
|
||||
}
|
||||
if im.compress {
|
||||
req.Header.Set("Content-Encoding", "gzip")
|
||||
|
||||
@@ -405,7 +405,16 @@ func buildMatchWithFilter(filter string, metricName string) (string, error) {
|
||||
if len(tf.Key) == 0 {
|
||||
continue
|
||||
}
|
||||
a = append(a, tf.String())
|
||||
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, nameFilter)
|
||||
filters = append(filters, strings.Join(a, ","))
|
||||
|
||||
@@ -6,8 +6,6 @@ import (
|
||||
"flag"
|
||||
"fmt"
|
||||
"net/http"
|
||||
nethttputil "net/http/httputil"
|
||||
"net/url"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
@@ -29,6 +27,7 @@ import (
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promscrape"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/querytracer"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/timerpool"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/vmalertproxy"
|
||||
)
|
||||
|
||||
var (
|
||||
@@ -38,7 +37,10 @@ var (
|
||||
resetCacheAuthKey = flagutil.NewPassword("search.resetCacheAuthKey", "Optional authKey for resetting rollup cache via /internal/resetRollupResultCache call. It could be passed via authKey query arg. It overrides -httpAuth.*")
|
||||
logSlowQueryDuration = flag.Duration("search.logSlowQueryDuration", 5*time.Second, "Log queries with execution time exceeding this value. Zero disables slow query logging. "+
|
||||
"See also -search.logQueryMemoryUsage")
|
||||
vmalertProxyURL = flag.String("vmalert.proxyURL", "", "Optional URL for proxying requests to vmalert. For example, if -vmalert.proxyURL=http://vmalert:8880 , then alerting API requests such as /api/v1/rules from Grafana will be proxied to http://vmalert:8880/api/v1/rules")
|
||||
|
||||
vmalertProxyURL = flag.String("vmalert.proxyURL", "", "Optional URL for proxying requests to vmalert. For example, if -vmalert.proxyURL=http://vmalert:8880 , "+
|
||||
"then alerting API requests such as /api/v1/rules from Grafana will be proxied to http://vmalert:8880/api/v1/rules . "+
|
||||
"See https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#vmalert")
|
||||
)
|
||||
|
||||
var slowQueries = metrics.NewCounter(`vm_slow_queries_total`)
|
||||
@@ -55,8 +57,8 @@ func Init(vmselectMaxConcurrentRequests int, vmselectMaxQueueDuration time.Durat
|
||||
concurrencyLimitCh = make(chan struct{}, maxConcurrentRequests)
|
||||
|
||||
initVMUIConfig()
|
||||
initVMAlertProxy()
|
||||
|
||||
vmalertproxy.Init(*vmalertProxyURL)
|
||||
flagutil.RegisterSecretFlag("vmalert.proxyURL")
|
||||
}
|
||||
|
||||
@@ -514,10 +516,11 @@ func handleStaticAndSimpleRequests(w http.ResponseWriter, r *http.Request, path
|
||||
if len(*vmalertProxyURL) == 0 {
|
||||
w.WriteHeader(http.StatusBadRequest)
|
||||
w.Header().Set("Content-Type", "application/json")
|
||||
fmt.Fprintf(w, "%s", `{"status":"error","msg":"for accessing vmalert flag '-vmalert.proxyURL' must be configured"}`)
|
||||
fmt.Fprintf(w, "%s", `{"status":"error","msg":"the '-vmalert.proxyURL' command-line must be configured; `+
|
||||
`see https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#vmalert"}`)
|
||||
return true
|
||||
}
|
||||
proxyVMAlertRequests(w, r, path)
|
||||
vmalertproxy.HandleRequest(w, r, path)
|
||||
return true
|
||||
}
|
||||
|
||||
@@ -555,7 +558,7 @@ func handleStaticAndSimpleRequests(w http.ResponseWriter, r *http.Request, path
|
||||
case "/api/v1/rules", "/rules":
|
||||
rulesRequests.Inc()
|
||||
if len(*vmalertProxyURL) > 0 {
|
||||
proxyVMAlertRequests(w, r, path)
|
||||
vmalertproxy.HandleRequest(w, r, path)
|
||||
return true
|
||||
}
|
||||
// Return dumb placeholder for https://prometheus.io/docs/prometheus/latest/querying/api/#rules
|
||||
@@ -565,7 +568,7 @@ func handleStaticAndSimpleRequests(w http.ResponseWriter, r *http.Request, path
|
||||
case "/api/v1/alerts", "/alerts":
|
||||
alertsRequests.Inc()
|
||||
if len(*vmalertProxyURL) > 0 {
|
||||
proxyVMAlertRequests(w, r, path)
|
||||
vmalertproxy.HandleRequest(w, r, path)
|
||||
return true
|
||||
}
|
||||
// Return dumb placeholder for https://prometheus.io/docs/prometheus/latest/querying/api/#alerts
|
||||
@@ -575,7 +578,7 @@ func handleStaticAndSimpleRequests(w http.ResponseWriter, r *http.Request, path
|
||||
case "/api/v1/notifiers", "/notifiers":
|
||||
notifiersRequests.Inc()
|
||||
if len(*vmalertProxyURL) > 0 {
|
||||
proxyVMAlertRequests(w, r, path)
|
||||
vmalertproxy.HandleRequest(w, r, path)
|
||||
return true
|
||||
}
|
||||
w.Header().Set("Content-Type", "application/json")
|
||||
@@ -722,48 +725,7 @@ var (
|
||||
metricNamesStatsResetErrors = metrics.NewCounter(`vm_http_request_errors_total{path="/api/v1/admin/status/metric_names_stats/reset"}`)
|
||||
)
|
||||
|
||||
func proxyVMAlertRequests(w http.ResponseWriter, r *http.Request, path string) {
|
||||
defer func() {
|
||||
err := recover()
|
||||
if err == nil || err == http.ErrAbortHandler {
|
||||
// Suppress http.ErrAbortHandler panic.
|
||||
// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1353
|
||||
return
|
||||
}
|
||||
// Forward other panics to the caller.
|
||||
panic(err)
|
||||
}()
|
||||
req := r.Clone(r.Context())
|
||||
req.URL.Path = strings.TrimPrefix(path, "prometheus")
|
||||
req.Host = vmalertProxyHost
|
||||
|
||||
if strings.HasPrefix(r.Header.Get(`User-Agent`), `Grafana`) {
|
||||
// Grafana currently supports only Prometheus-style alerts. If other alert types
|
||||
// (e.g. logs or traces) are returned, it may fail with "Error loading alerts".
|
||||
//
|
||||
// Grafana queries the vmalert API directly, bypassing the VictoriaMetrics datasource,
|
||||
// so query params (such as datasource_type) cannot be enforced on the Grafana side.
|
||||
//
|
||||
// To ensure compatibility, we detect Grafana requests via the User-Agent and enforce
|
||||
// `datasource_type=prometheus`.
|
||||
//
|
||||
// See:
|
||||
// - https://github.com/VictoriaMetrics/victoriametrics-datasource/issues/329#issuecomment-3847585443
|
||||
// - https://github.com/VictoriaMetrics/victoriametrics-datasource/issues/59
|
||||
q := req.URL.Query()
|
||||
q.Set("datasource_type", "prometheus")
|
||||
req.URL.RawQuery = q.Encode()
|
||||
req.RequestURI = ""
|
||||
}
|
||||
|
||||
vmalertProxy.ServeHTTP(w, req)
|
||||
}
|
||||
|
||||
var (
|
||||
vmalertProxyHost string
|
||||
vmalertProxy *nethttputil.ReverseProxy
|
||||
vmuiConfig string
|
||||
)
|
||||
var vmuiConfig string
|
||||
|
||||
func initVMUIConfig() {
|
||||
var cfg struct {
|
||||
@@ -795,16 +757,3 @@ func initVMUIConfig() {
|
||||
}
|
||||
vmuiConfig = string(data)
|
||||
}
|
||||
|
||||
// initVMAlertProxy must be called after flag.Parse(), since it uses command-line flags.
|
||||
func initVMAlertProxy() {
|
||||
if len(*vmalertProxyURL) == 0 {
|
||||
return
|
||||
}
|
||||
proxyURL, err := url.Parse(*vmalertProxyURL)
|
||||
if err != nil {
|
||||
logger.Fatalf("cannot parse -vmalert.proxyURL=%q: %s", *vmalertProxyURL, err)
|
||||
}
|
||||
vmalertProxyHost = proxyURL.Host
|
||||
vmalertProxy = nethttputil.NewSingleHostReverseProxy(proxyURL)
|
||||
}
|
||||
|
||||
@@ -15,7 +15,7 @@ See https://prometheus.io/docs/prometheus/latest/querying/api/#querying-metric-m
|
||||
currentItem := 0
|
||||
%}
|
||||
{% for _, row := range result %}
|
||||
"{%s string(row.MetricFamilyName) %}": [
|
||||
{%q= string(row.MetricFamilyName) %}: [
|
||||
{
|
||||
"type": {%q= row.Type.String() %},
|
||||
{% if len(row.Unit) > 0 -%}
|
||||
|
||||
@@ -35,12 +35,10 @@ 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.E().S(string(row.MetricFamilyName))
|
||||
qw422016.N().Q(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
|
||||
|
||||
@@ -28,6 +28,7 @@ import (
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/fasttime"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/httputil"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/netutil"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/querytracer"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/storage"
|
||||
@@ -525,6 +526,7 @@ func DeleteHandler(startTime time.Time, r *http.Request) error {
|
||||
if deletedCount > 0 {
|
||||
promql.ResetRollupResultCache()
|
||||
}
|
||||
logger.Infof("/api/v1/admin/tsdb/delete_series has been called for %q. Deleted %d series.", sq.FiltersString(), deletedCount)
|
||||
return nil
|
||||
}
|
||||
|
||||
@@ -954,6 +956,7 @@ func queryRangeHandler(qt *querytracer.Tracer, startTime time.Time, w http.Respo
|
||||
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
|
||||
@@ -975,18 +978,19 @@ 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,
|
||||
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,
|
||||
OptimizeRepeatedBinaryOpSubexprs: optimizeRepeatedBinaryOpSubexprs,
|
||||
LookbackDelta: lookbackDelta,
|
||||
RoundDigits: getRoundDigits(r),
|
||||
EnforcedTagFilterss: etfs,
|
||||
CacheTagFilters: etfs,
|
||||
GetRequestURI: func() string {
|
||||
return httpserver.GetRequestURI(r)
|
||||
},
|
||||
|
||||
@@ -132,6 +132,9 @@ 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
|
||||
|
||||
@@ -171,6 +174,7 @@ 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
|
||||
@@ -467,7 +471,8 @@ func isAggrFuncWithoutGrouping(e metricsql.Expr) bool {
|
||||
}
|
||||
|
||||
func execBinaryOpArgs(qt *querytracer.Tracer, ec *EvalConfig, exprFirst, exprSecond metricsql.Expr, be *metricsql.BinaryOpExpr) ([]*timeseries, []*timeseries, error) {
|
||||
if !canPushdownCommonFilters(be) {
|
||||
canPushdown := canPushdownCommonFilters(be)
|
||||
if !canPushdown && !shouldOptimizeRepeatedBinaryOpSubexprs(ec, exprFirst, exprSecond) {
|
||||
// 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
|
||||
@@ -500,6 +505,25 @@ func execBinaryOpArgs(qt *querytracer.Tracer, ec *EvalConfig, exprFirst, exprSec
|
||||
}
|
||||
return tssFirst, tssSecond, nil
|
||||
}
|
||||
if !canPushdown {
|
||||
qt = qt.NewChild("execute left and right sides of %q sequentially because repeated cacheable subexpression was found", be.Op)
|
||||
defer qt.Done()
|
||||
|
||||
qtFirst := qt.NewChild("expr1")
|
||||
tssFirst, err := evalExpr(qtFirst, ec, exprFirst)
|
||||
qtFirst.Done()
|
||||
if err != nil {
|
||||
return nil, nil, err
|
||||
}
|
||||
|
||||
qtSecond := qt.NewChild("expr2")
|
||||
tssSecond, err := evalExpr(qtSecond, ec, exprSecond)
|
||||
qtSecond.Done()
|
||||
if err != nil {
|
||||
return nil, nil, err
|
||||
}
|
||||
return tssFirst, tssSecond, nil
|
||||
}
|
||||
|
||||
// Execute binary operation in the following way:
|
||||
//
|
||||
@@ -544,6 +568,78 @@ func execBinaryOpArgs(qt *querytracer.Tracer, ec *EvalConfig, exprFirst, exprSec
|
||||
return tssFirst, tssSecond, nil
|
||||
}
|
||||
|
||||
func shouldOptimizeRepeatedBinaryOpSubexprs(ec *EvalConfig, exprFirst, exprSecond metricsql.Expr) bool {
|
||||
if !ec.OptimizeRepeatedBinaryOpSubexprs {
|
||||
return false
|
||||
}
|
||||
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
|
||||
}
|
||||
|
||||
func getCommonLabelFilters(tss []*timeseries) []metricsql.LabelFilter {
|
||||
if len(tss) == 0 {
|
||||
return nil
|
||||
@@ -1591,6 +1687,10 @@ func assertInstantValues(tss []*timeseries) {
|
||||
|
||||
var memoryIntensiveQueries = metrics.NewCounter(`vm_memory_intensive_queries_total`)
|
||||
|
||||
var _ = metrics.NewGauge(`vm_max_memory_per_query`, func() float64 {
|
||||
return float64(maxMemoryPerQuery.N)
|
||||
})
|
||||
|
||||
func evalRollupFuncWithMetricExpr(qt *querytracer.Tracer, ec *EvalConfig, funcName string, rf rollupFunc,
|
||||
expr metricsql.Expr, me *metricsql.MetricExpr, iafc *incrementalAggrFuncContext, windowExpr *metricsql.DurationExpr,
|
||||
) ([]*timeseries, error) {
|
||||
|
||||
@@ -170,3 +170,87 @@ 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)
|
||||
}
|
||||
|
||||
File diff suppressed because one or more lines are too long
197
app/vmselect/vmui/assets/index-CusQvJzs.js
Normal file
197
app/vmselect/vmui/assets/index-CusQvJzs.js
Normal file
File diff suppressed because one or more lines are too long
@@ -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)=>()=>(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};
|
||||
1
app/vmselect/vmui/assets/rolldown-runtime-Cyuzqnbw.js
Normal file
1
app/vmselect/vmui/assets/rolldown-runtime-Cyuzqnbw.js
Normal 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),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};
|
||||
78
app/vmselect/vmui/assets/vendor-B83wxFqK.js
Normal file
78
app/vmselect/vmui/assets/vendor-B83wxFqK.js
Normal file
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
@@ -37,9 +37,9 @@
|
||||
<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-CoGukb-x.js"></script>
|
||||
<link rel="modulepreload" crossorigin href="./assets/rolldown-runtime-COnpUsM8.js">
|
||||
<link rel="modulepreload" crossorigin href="./assets/vendor-C8Kwp93_.js">
|
||||
<script type="module" crossorigin src="./assets/index-CusQvJzs.js"></script>
|
||||
<link rel="modulepreload" crossorigin href="./assets/rolldown-runtime-Cyuzqnbw.js">
|
||||
<link rel="modulepreload" crossorigin href="./assets/vendor-B83wxFqK.js">
|
||||
<link rel="stylesheet" crossorigin href="./assets/vendor-CnsZ1jie.css">
|
||||
<link rel="stylesheet" crossorigin href="./assets/index-BBUnmLOr.css">
|
||||
</head>
|
||||
|
||||
@@ -10,8 +10,6 @@ import (
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/VictoriaMetrics/metrics"
|
||||
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/fasttime"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/fs"
|
||||
@@ -23,6 +21,7 @@ import (
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/stringsutil"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/vminsertapi"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/vmselectapi"
|
||||
"github.com/VictoriaMetrics/metrics"
|
||||
)
|
||||
|
||||
var (
|
||||
@@ -153,7 +152,7 @@ func Init(vmselectMaxConcurrentRequests int, resetCacheIfNeeded func(mrs []stora
|
||||
LogNewSeries: *logNewSeries,
|
||||
}
|
||||
strg := storage.MustOpenStorage(*storageDataPath, opts)
|
||||
vmStorage = newVMStorageSingleNode(strg, vmselectMaxConcurrentRequests, resetCacheIfNeeded)
|
||||
vmStorage = newVMStorage(strg, vmselectMaxConcurrentRequests, resetCacheIfNeeded)
|
||||
|
||||
var m storage.Metrics
|
||||
strg.UpdateMetrics(&m)
|
||||
@@ -175,15 +174,15 @@ func Init(vmselectMaxConcurrentRequests int, resetCacheIfNeeded func(mrs []stora
|
||||
GetSearch = vmStorage.GetSearch
|
||||
PutSearch = vmStorage.PutSearch
|
||||
RequestHandler = vmStorage.requestHandler
|
||||
DebugFlush = vmStorage.vms.s.DebugFlush
|
||||
DebugFlush = vmStorage.s.DebugFlush
|
||||
}
|
||||
|
||||
var storageMetrics *metrics.Set
|
||||
|
||||
var (
|
||||
// vmStorageSingleNode is an instance of vmstorage used by vminsert and
|
||||
// vmStorage is an instance of vmstorage used by vminsert and
|
||||
// vmselect for writing and reading data.
|
||||
vmStorage *VMStorageSingleNode
|
||||
vmStorage *VMStorage
|
||||
VMInsertAPI vminsertapi.API
|
||||
VMSelectAPI vmselectapi.API
|
||||
GetSearch func(qt *querytracer.Tracer, sq *storage.SearchQuery, deadline uint64) (*storage.Search, int, error)
|
||||
@@ -209,15 +208,12 @@ func Stop() {
|
||||
logger.Infof("the vmstorage has been stopped")
|
||||
}
|
||||
|
||||
func (vmssn *VMStorageSingleNode) requestHandler(w http.ResponseWriter, r *http.Request) bool {
|
||||
vmssn.wg.Add(1)
|
||||
defer vmssn.wg.Done()
|
||||
return vmssn.vms.requestHandler(w, r)
|
||||
}
|
||||
|
||||
// requestHandler is a storage request handler.
|
||||
// TODO(@rtm0): Move to a separate file, request_handler.go
|
||||
func (vms *VMStorage) requestHandler(w http.ResponseWriter, r *http.Request) bool {
|
||||
vms.wg.Add(1)
|
||||
defer vms.wg.Done()
|
||||
|
||||
path := r.URL.Path
|
||||
if path == "/internal/force_merge" {
|
||||
if !httpserver.CheckAuthFlag(w, r, forceMergeAuthKey) {
|
||||
@@ -361,15 +357,11 @@ var (
|
||||
snapshotsDeleteAllErrorsTotal = metrics.NewCounter(`vm_http_request_errors_total{path="/snapshot/delete_all"}`)
|
||||
)
|
||||
|
||||
// TODO(@rtm0): Move to metrics.go.
|
||||
func (vmssn *VMStorageSingleNode) writeStorageMetrics(w io.Writer) {
|
||||
vmssn.wg.Add(1)
|
||||
defer vmssn.wg.Done()
|
||||
vmssn.vms.writeStorageMetrics(w)
|
||||
}
|
||||
|
||||
// TODO(@rtm0): Move to metrics.go.
|
||||
func (vms *VMStorage) writeStorageMetrics(w io.Writer) {
|
||||
vms.wg.Add(1)
|
||||
defer vms.wg.Done()
|
||||
|
||||
strg := vms.s
|
||||
var m storage.Metrics
|
||||
strg.UpdateMetrics(&m)
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
package vmstorage
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"flag"
|
||||
"fmt"
|
||||
"sync"
|
||||
@@ -14,6 +15,7 @@ import (
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/storage"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/storage/metricnamestats"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/storage/metricsmetadata"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/syncwg"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/timeutil"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/vmselectapi"
|
||||
)
|
||||
@@ -34,7 +36,7 @@ var (
|
||||
// newVMStorage creates a new instance of of VMStorage.
|
||||
//
|
||||
// The created VMStorage instance takes ownership of s.
|
||||
func newVMStorage(s *storage.Storage, vmselectMaxConcurrentRequests int) *VMStorage {
|
||||
func newVMStorage(s *storage.Storage, vmselectMaxConcurrentRequests int, resetCacheIfNeeded func(mrs []storage.MetricRow)) *VMStorage {
|
||||
if err := encoding.CheckPrecisionBits(uint8(*precisionBits)); err != nil {
|
||||
logger.Fatalf("invalid -precisionBits=%d: %s", *precisionBits, err)
|
||||
}
|
||||
@@ -49,6 +51,8 @@ func newVMStorage(s *storage.Storage, vmselectMaxConcurrentRequests int) *VMStor
|
||||
maxUniqueTimeseries: *maxUniqueTimeseries,
|
||||
maxUniqueTimeSeriesCalculated: maxUniqueTimeseriesCalculated,
|
||||
staleSnapshotsRemoverCh: make(chan struct{}),
|
||||
wg: syncwg.WaitGroup{},
|
||||
resetCacheIfNeeded: resetCacheIfNeeded,
|
||||
}
|
||||
vms.initStaleSnapshotsRemover()
|
||||
return vms
|
||||
@@ -78,6 +82,17 @@ type VMStorage struct {
|
||||
maxUniqueTimeSeriesCalculated int
|
||||
staleSnapshotsRemoverCh chan struct{}
|
||||
staleSnapshotsRemoverWG sync.WaitGroup
|
||||
|
||||
// wg is used to wrap every storage call into wg.Add(1) ... wg.Done()
|
||||
// for proper graceful shutdown when Stop is called.
|
||||
//
|
||||
// Use syncwg instead of sync, since Add is called from concurrent
|
||||
// goroutines.
|
||||
wg syncwg.WaitGroup
|
||||
|
||||
// resetCacheIfNeeded is a callback for automatic resetting of response
|
||||
// cache if needed.
|
||||
resetCacheIfNeeded func(mrs []storage.MetricRow)
|
||||
}
|
||||
|
||||
func (vms *VMStorage) initStaleSnapshotsRemover() {
|
||||
@@ -103,6 +118,7 @@ func (vms *VMStorage) initStaleSnapshotsRemover() {
|
||||
func (vms *VMStorage) Stop() {
|
||||
close(vms.staleSnapshotsRemoverCh)
|
||||
vms.staleSnapshotsRemoverWG.Wait()
|
||||
vms.wg.WaitAndBlock()
|
||||
vms.s.MustClose()
|
||||
}
|
||||
|
||||
@@ -111,6 +127,14 @@ func (vms *VMStorage) Stop() {
|
||||
// The caller should limit the number of concurrent calls to WriteRows() in
|
||||
// order to limit memory usage.
|
||||
func (vms *VMStorage) WriteRows(rows []storage.MetricRow) error {
|
||||
vms.wg.Add(1)
|
||||
defer vms.wg.Done()
|
||||
|
||||
if vms.s.IsReadOnly() {
|
||||
return errReadOnly
|
||||
}
|
||||
vms.resetCacheIfNeeded(rows)
|
||||
|
||||
vms.s.AddRows(rows, uint8(*precisionBits))
|
||||
return nil
|
||||
}
|
||||
@@ -120,26 +144,41 @@ func (vms *VMStorage) WriteRows(rows []storage.MetricRow) error {
|
||||
// The caller should limit the number of concurrent calls to WriteMetadata() in
|
||||
// order to limit memory usage.
|
||||
func (vms *VMStorage) WriteMetadata(rows []metricsmetadata.Row) error {
|
||||
vms.wg.Add(1)
|
||||
defer vms.wg.Done()
|
||||
|
||||
if vms.s.IsReadOnly() {
|
||||
return errReadOnly
|
||||
}
|
||||
vms.s.AddMetadataRows(rows)
|
||||
return nil
|
||||
}
|
||||
|
||||
var errReadOnly = errors.New("the storage is in read-only mode; check -storage.minFreeDiskSpaceBytes command-line flag value")
|
||||
|
||||
// IsReadOnly returns true is the storage is in read-only mode.
|
||||
func (vms *VMStorage) IsReadOnly() bool {
|
||||
vms.wg.Add(1)
|
||||
defer vms.wg.Done()
|
||||
return vms.s.IsReadOnly()
|
||||
}
|
||||
|
||||
func (vms *VMStorage) InitSearch(qt *querytracer.Tracer, sq *storage.SearchQuery, deadline uint64) (vmselectapi.BlockIterator, error) {
|
||||
vms.wg.Add(1)
|
||||
|
||||
tr := sq.GetTimeRange()
|
||||
maxMetrics := vms.getMaxMetrics(sq.MaxMetrics)
|
||||
tfss, err := vms.setupTfss(qt, sq, tr, maxMetrics, deadline)
|
||||
if err != nil {
|
||||
vms.wg.Done()
|
||||
return nil, err
|
||||
}
|
||||
if len(tfss) == 0 {
|
||||
vms.wg.Done()
|
||||
return nil, fmt.Errorf("missing tag filters")
|
||||
}
|
||||
bi := getBlockIterator()
|
||||
bi.wgDone = vms.wg.Done
|
||||
bi.sr.Init(qt, vms.s, tfss, tr, maxMetrics, deadline)
|
||||
if err := bi.sr.Error(); err != nil {
|
||||
bi.MustClose()
|
||||
@@ -161,8 +200,9 @@ func (vms *VMStorage) getMaxMetrics(searchQueryLimit int) int {
|
||||
|
||||
// blockIterator implements vmselectapi.BlockIterator
|
||||
type blockIterator struct {
|
||||
sr storage.Search
|
||||
mb storage.MetricBlock
|
||||
sr storage.Search
|
||||
mb storage.MetricBlock
|
||||
wgDone func()
|
||||
}
|
||||
|
||||
var blockIteratorsPool sync.Pool
|
||||
@@ -171,6 +211,8 @@ func (bi *blockIterator) MustClose() {
|
||||
bi.sr.MustClose()
|
||||
bi.mb.MetricName = nil
|
||||
bi.mb.Block.Reset()
|
||||
bi.wgDone()
|
||||
bi.wgDone = nil
|
||||
blockIteratorsPool.Put(bi)
|
||||
}
|
||||
|
||||
@@ -197,8 +239,63 @@ func (bi *blockIterator) Error() error {
|
||||
return bi.sr.Error()
|
||||
}
|
||||
|
||||
// GetSearch sets up an instance of storage search and returns it to the caller
|
||||
// along with the max series count that the search can return.
|
||||
//
|
||||
// This method is not part of the vmselectapi.API and must only be used by
|
||||
// vmsingle HTTP handlers.
|
||||
//
|
||||
// Callers of this method must call PutSearch() once the search instance is not
|
||||
// needed anymore.
|
||||
func (vms *VMStorage) GetSearch(qt *querytracer.Tracer, sq *storage.SearchQuery, deadline uint64) (*storage.Search, int, error) {
|
||||
vms.wg.Add(1)
|
||||
|
||||
tr := sq.GetTimeRange()
|
||||
maxMetrics := vms.getMaxMetrics(sq.MaxMetrics)
|
||||
tfss, err := vms.setupTfss(qt, sq, tr, maxMetrics, deadline)
|
||||
if err != nil {
|
||||
vms.wg.Done()
|
||||
return nil, 0, err
|
||||
}
|
||||
|
||||
sr := getSearch()
|
||||
maxSeriesCount := sr.Init(qt, vms.s, tfss, tr, sq.MaxMetrics, deadline)
|
||||
return sr, maxSeriesCount, nil
|
||||
}
|
||||
|
||||
// PutSearch resets the search once it is not needed anymore and puts it aside
|
||||
// for future reuse.
|
||||
//
|
||||
// This method is not part of the vmselectapi.API and must only be used by
|
||||
// vmsingle HTTP handlers.
|
||||
//
|
||||
// The method must only be used on search instances that have been created with
|
||||
// GetSearch().
|
||||
func (vms *VMStorage) PutSearch(sr *storage.Search) {
|
||||
putSearch(sr)
|
||||
vms.wg.Done()
|
||||
}
|
||||
|
||||
func getSearch() *storage.Search {
|
||||
v := ssPool.Get()
|
||||
if v == nil {
|
||||
return &storage.Search{}
|
||||
}
|
||||
return v.(*storage.Search)
|
||||
}
|
||||
|
||||
func putSearch(sr *storage.Search) {
|
||||
sr.MustClose()
|
||||
ssPool.Put(sr)
|
||||
}
|
||||
|
||||
var ssPool sync.Pool
|
||||
|
||||
// SearchMetricNames returns metric names for the given tfss on the given tr.
|
||||
func (vms *VMStorage) SearchMetricNames(qt *querytracer.Tracer, sq *storage.SearchQuery, deadline uint64) ([]string, error) {
|
||||
vms.wg.Add(1)
|
||||
defer vms.wg.Done()
|
||||
|
||||
tr := sq.GetTimeRange()
|
||||
maxMetrics := sq.MaxMetrics
|
||||
if maxMetrics <= 0 {
|
||||
@@ -219,6 +316,9 @@ func (vms *VMStorage) SearchMetricNames(qt *querytracer.Tracer, sq *storage.Sear
|
||||
// SearchLabelValues searches for label values for the given labelName, tfss and
|
||||
// tr.
|
||||
func (vms *VMStorage) LabelValues(qt *querytracer.Tracer, sq *storage.SearchQuery, labelName string, maxLabelValues int, deadline uint64) ([]string, error) {
|
||||
vms.wg.Add(1)
|
||||
defer vms.wg.Done()
|
||||
|
||||
tr := sq.GetTimeRange()
|
||||
if maxLabelValues <= 0 || maxLabelValues > *maxTagValues {
|
||||
maxLabelValues = *maxTagValues
|
||||
@@ -244,6 +344,9 @@ func (vms *VMStorage) LabelValues(qt *querytracer.Tracer, sq *storage.SearchQuer
|
||||
// similar APIs.
|
||||
func (vms *VMStorage) TagValueSuffixes(qt *querytracer.Tracer, _, _ uint32, tr storage.TimeRange, tagKey, tagValuePrefix string, delimiter byte,
|
||||
maxSuffixes int, deadline uint64) ([]string, error) {
|
||||
vms.wg.Add(1)
|
||||
defer vms.wg.Done()
|
||||
|
||||
if maxSuffixes <= 0 || maxSuffixes > *maxTagValueSuffixesPerSearch {
|
||||
maxSuffixes = *maxTagValueSuffixesPerSearch
|
||||
}
|
||||
@@ -260,6 +363,9 @@ func (vms *VMStorage) TagValueSuffixes(qt *querytracer.Tracer, _, _ uint32, tr s
|
||||
|
||||
// SearchLabelNames searches for tag keys matching the given tfss on tr.
|
||||
func (vms *VMStorage) LabelNames(qt *querytracer.Tracer, sq *storage.SearchQuery, maxLabelNames int, deadline uint64) ([]string, error) {
|
||||
vms.wg.Add(1)
|
||||
defer vms.wg.Done()
|
||||
|
||||
tr := sq.GetTimeRange()
|
||||
if maxLabelNames <= 0 || maxLabelNames > *maxTagKeys {
|
||||
maxLabelNames = *maxTagKeys
|
||||
@@ -278,6 +384,8 @@ func (vms *VMStorage) LabelNames(qt *querytracer.Tracer, sq *storage.SearchQuery
|
||||
}
|
||||
|
||||
func (vms *VMStorage) SeriesCount(_ *querytracer.Tracer, _, _ uint32, deadline uint64) (uint64, error) {
|
||||
vms.wg.Add(1)
|
||||
defer vms.wg.Done()
|
||||
return vms.s.GetSeriesCount(deadline)
|
||||
}
|
||||
|
||||
@@ -287,6 +395,9 @@ func (vms *VMStorage) Tenants(_ *querytracer.Tracer, _ storage.TimeRange, _ uint
|
||||
|
||||
// GetTSDBStatus returns TSDB status for given filters on the given date.
|
||||
func (vms *VMStorage) TSDBStatus(qt *querytracer.Tracer, sq *storage.SearchQuery, focusLabel string, topN int, deadline uint64) (*storage.TSDBStatus, error) {
|
||||
vms.wg.Add(1)
|
||||
defer vms.wg.Done()
|
||||
|
||||
tr := sq.GetTimeRange()
|
||||
maxMetrics := sq.MaxMetrics
|
||||
if maxMetrics <= 0 {
|
||||
@@ -306,6 +417,9 @@ func (vms *VMStorage) TSDBStatus(qt *querytracer.Tracer, sq *storage.SearchQuery
|
||||
//
|
||||
// Returns the number of deleted series.
|
||||
func (vms *VMStorage) DeleteSeries(qt *querytracer.Tracer, sq *storage.SearchQuery, deadline uint64) (int, error) {
|
||||
vms.wg.Add(1)
|
||||
defer vms.wg.Done()
|
||||
|
||||
tr := sq.GetTimeRange()
|
||||
maxMetrics := sq.MaxMetrics
|
||||
if maxMetrics <= 0 {
|
||||
@@ -324,17 +438,26 @@ func (vms *VMStorage) DeleteSeries(qt *querytracer.Tracer, sq *storage.SearchQue
|
||||
}
|
||||
|
||||
func (vms *VMStorage) RegisterMetricNames(qt *querytracer.Tracer, mrs []storage.MetricRow, _ uint64) error {
|
||||
vms.wg.Add(1)
|
||||
defer vms.wg.Done()
|
||||
|
||||
vms.s.RegisterMetricNames(qt, mrs)
|
||||
return nil
|
||||
}
|
||||
|
||||
// GetMetricNamesUsageStats returns metric name usage stats.
|
||||
func (vms *VMStorage) GetMetricNamesUsageStats(qt *querytracer.Tracer, _ *storage.TenantToken, limit, le int, matchPattern string, _ uint64) (metricnamestats.StatsResult, error) {
|
||||
vms.wg.Add(1)
|
||||
defer vms.wg.Done()
|
||||
|
||||
return vms.s.GetMetricNamesStats(qt, limit, le, matchPattern), nil
|
||||
}
|
||||
|
||||
// ResetMetricNamesStats resets state for metric names usage tracker
|
||||
func (vms *VMStorage) ResetMetricNamesUsageStats(qt *querytracer.Tracer, _ uint64) error {
|
||||
vms.wg.Add(1)
|
||||
defer vms.wg.Done()
|
||||
|
||||
vms.s.ResetMetricNamesStats(qt)
|
||||
return nil
|
||||
}
|
||||
@@ -371,6 +494,8 @@ func (vms *VMStorage) setupTfss(qt *querytracer.Tracer, sq *storage.SearchQuery,
|
||||
}
|
||||
|
||||
func (vms *VMStorage) GetMetadataRecords(qt *querytracer.Tracer, _ *storage.TenantToken, limit int, metricName string, _ uint64) ([]*metricsmetadata.Row, error) {
|
||||
vms.wg.Add(1)
|
||||
defer vms.wg.Done()
|
||||
return vms.s.GetMetadataRows(qt, limit, metricName), nil
|
||||
}
|
||||
|
||||
|
||||
@@ -1,213 +0,0 @@
|
||||
package vmstorage
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"fmt"
|
||||
"sync"
|
||||
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/querytracer"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/storage"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/storage/metricnamestats"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/storage/metricsmetadata"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/syncwg"
|
||||
"github.com/VictoriaMetrics/VictoriaMetrics/lib/vmselectapi"
|
||||
)
|
||||
|
||||
// newVMStorageSingleNode creates a new instance of of VMStorage for vmsingle.
|
||||
func newVMStorageSingleNode(s *storage.Storage, maxConcurrentRequests int, resetCacheIfNeeded func(mrs []storage.MetricRow)) *VMStorageSingleNode {
|
||||
vms := newVMStorage(s, maxConcurrentRequests)
|
||||
return &VMStorageSingleNode{
|
||||
vms: vms,
|
||||
wg: syncwg.WaitGroup{},
|
||||
resetCacheIfNeeded: resetCacheIfNeeded,
|
||||
}
|
||||
}
|
||||
|
||||
type VMStorageSingleNode struct {
|
||||
vms *VMStorage
|
||||
|
||||
// wg is used to wrap every storage call into wg.Add(1) ... wg.Done()
|
||||
// for proper graceful shutdown when Stop is called.
|
||||
//
|
||||
// Use syncwg instead of sync, since Add is called from concurrent
|
||||
// goroutines.
|
||||
wg syncwg.WaitGroup
|
||||
|
||||
// resetCacheIfNeeded is a callback for automatic resetting of response
|
||||
// cache if needed.
|
||||
resetCacheIfNeeded func(mrs []storage.MetricRow)
|
||||
}
|
||||
|
||||
func (vmssn *VMStorageSingleNode) Stop() {
|
||||
vmssn.wg.WaitAndBlock()
|
||||
vmssn.vms.Stop()
|
||||
}
|
||||
|
||||
// WriteRows writes metric rows to the storage.
|
||||
//
|
||||
// Returns an error if the storage is in read-only mode.
|
||||
//
|
||||
// The caller should limit the number of concurrent calls to WriteRows() in
|
||||
// order to limit memory usage.
|
||||
func (vmssn *VMStorageSingleNode) WriteRows(rows []storage.MetricRow) error {
|
||||
vmssn.wg.Add(1)
|
||||
defer vmssn.wg.Done()
|
||||
|
||||
if vmssn.vms.IsReadOnly() {
|
||||
return errReadOnly
|
||||
}
|
||||
vmssn.resetCacheIfNeeded(rows)
|
||||
return vmssn.vms.WriteRows(rows)
|
||||
}
|
||||
|
||||
// WriteMetadata writes metrics metadata to storage.
|
||||
//
|
||||
// Returns an error if the storage is in read-only mode.
|
||||
//
|
||||
// The caller should limit the number of concurrent calls to WriteMetadata() in
|
||||
// order to limit memory usage.
|
||||
func (vmssn *VMStorageSingleNode) WriteMetadata(rows []metricsmetadata.Row) error {
|
||||
vmssn.wg.Add(1)
|
||||
defer vmssn.wg.Done()
|
||||
|
||||
if vmssn.vms.IsReadOnly() {
|
||||
return errReadOnly
|
||||
}
|
||||
return vmssn.vms.WriteMetadata(rows)
|
||||
}
|
||||
|
||||
var errReadOnly = errors.New("the storage is in read-only mode; check -storage.minFreeDiskSpaceBytes command-line flag value")
|
||||
|
||||
func (vmssn *VMStorageSingleNode) IsReadOnly() bool {
|
||||
vmssn.wg.Add(1)
|
||||
defer vmssn.wg.Done()
|
||||
return vmssn.vms.IsReadOnly()
|
||||
}
|
||||
|
||||
func (vmssn *VMStorageSingleNode) InitSearch(qt *querytracer.Tracer, sq *storage.SearchQuery, deadline uint64) (vmselectapi.BlockIterator, error) {
|
||||
return nil, fmt.Errorf("not implemented in vmsingle")
|
||||
}
|
||||
|
||||
// GetSearch sets up an instance of storage search and returns it to the caller
|
||||
// along with the max series count that the search can return.
|
||||
//
|
||||
// This method is not part of the vmselectapi.API and must only be used by
|
||||
// vmsingle HTTP handlers.
|
||||
//
|
||||
// Callers of this method must call PutSearch() once the search instance is not
|
||||
// needed anymore.
|
||||
func (vmssn *VMStorageSingleNode) GetSearch(qt *querytracer.Tracer, sq *storage.SearchQuery, deadline uint64) (*storage.Search, int, error) {
|
||||
vmssn.wg.Add(1)
|
||||
|
||||
tr := sq.GetTimeRange()
|
||||
maxMetrics := vmssn.vms.getMaxMetrics(sq.MaxMetrics)
|
||||
tfss, err := vmssn.vms.setupTfss(qt, sq, tr, maxMetrics, deadline)
|
||||
if err != nil {
|
||||
vmssn.wg.Done()
|
||||
return nil, 0, err
|
||||
}
|
||||
|
||||
sr := getSearch()
|
||||
maxSeriesCount := sr.Init(qt, vmssn.vms.s, tfss, tr, sq.MaxMetrics, deadline)
|
||||
return sr, maxSeriesCount, nil
|
||||
}
|
||||
|
||||
// PutSearch resets the search once it is not needed anymore and puts it aside
|
||||
// for future reuse.
|
||||
//
|
||||
// This method is not part of the vmselectapi.API and must only be used by
|
||||
// vmsingle HTTP handlers.
|
||||
//
|
||||
// The method must only be used on search instances that have been created with
|
||||
// GetSearch().
|
||||
func (vmssn *VMStorageSingleNode) PutSearch(sr *storage.Search) {
|
||||
putSearch(sr)
|
||||
vmssn.wg.Done()
|
||||
}
|
||||
|
||||
func getSearch() *storage.Search {
|
||||
v := ssPool.Get()
|
||||
if v == nil {
|
||||
return &storage.Search{}
|
||||
}
|
||||
return v.(*storage.Search)
|
||||
}
|
||||
|
||||
func putSearch(sr *storage.Search) {
|
||||
sr.MustClose()
|
||||
ssPool.Put(sr)
|
||||
}
|
||||
|
||||
var ssPool sync.Pool
|
||||
|
||||
func (vmssn *VMStorageSingleNode) SearchMetricNames(qt *querytracer.Tracer, sq *storage.SearchQuery, deadline uint64) ([]string, error) {
|
||||
vmssn.wg.Add(1)
|
||||
defer vmssn.wg.Done()
|
||||
return vmssn.vms.SearchMetricNames(qt, sq, deadline)
|
||||
}
|
||||
|
||||
func (vmssn *VMStorageSingleNode) LabelValues(qt *querytracer.Tracer, sq *storage.SearchQuery, labelName string, maxLabelValues int, deadline uint64) ([]string, error) {
|
||||
vmssn.wg.Add(1)
|
||||
defer vmssn.wg.Done()
|
||||
return vmssn.vms.LabelValues(qt, sq, labelName, maxLabelValues, deadline)
|
||||
}
|
||||
|
||||
func (vmssn *VMStorageSingleNode) TagValueSuffixes(qt *querytracer.Tracer, accountID, projectID uint32, tr storage.TimeRange, tagKey, tagValuePrefix string, delimiter byte, maxSuffixes int, deadline uint64) ([]string, error) {
|
||||
vmssn.wg.Add(1)
|
||||
defer vmssn.wg.Done()
|
||||
return vmssn.vms.TagValueSuffixes(qt, accountID, projectID, tr, tagKey, tagValuePrefix, delimiter, maxSuffixes, deadline)
|
||||
}
|
||||
|
||||
func (vmssn *VMStorageSingleNode) LabelNames(qt *querytracer.Tracer, sq *storage.SearchQuery, maxLabelNames int, deadline uint64) ([]string, error) {
|
||||
vmssn.wg.Add(1)
|
||||
defer vmssn.wg.Done()
|
||||
return vmssn.vms.LabelNames(qt, sq, maxLabelNames, deadline)
|
||||
}
|
||||
|
||||
func (vmssn *VMStorageSingleNode) SeriesCount(qt *querytracer.Tracer, accountID, projectID uint32, deadline uint64) (uint64, error) {
|
||||
vmssn.wg.Add(1)
|
||||
defer vmssn.wg.Done()
|
||||
return vmssn.vms.SeriesCount(qt, accountID, projectID, deadline)
|
||||
}
|
||||
|
||||
func (vmssn *VMStorageSingleNode) Tenants(qt *querytracer.Tracer, tr storage.TimeRange, deadline uint64) ([]string, error) {
|
||||
vmssn.wg.Add(1)
|
||||
defer vmssn.wg.Done()
|
||||
return vmssn.vms.Tenants(qt, tr, deadline)
|
||||
}
|
||||
|
||||
func (vmssn *VMStorageSingleNode) TSDBStatus(qt *querytracer.Tracer, sq *storage.SearchQuery, focusLabel string, topN int, deadline uint64) (*storage.TSDBStatus, error) {
|
||||
vmssn.wg.Add(1)
|
||||
defer vmssn.wg.Done()
|
||||
return vmssn.vms.TSDBStatus(qt, sq, focusLabel, topN, deadline)
|
||||
}
|
||||
|
||||
func (vmssn *VMStorageSingleNode) DeleteSeries(qt *querytracer.Tracer, sq *storage.SearchQuery, deadline uint64) (int, error) {
|
||||
vmssn.wg.Add(1)
|
||||
defer vmssn.wg.Done()
|
||||
return vmssn.vms.DeleteSeries(qt, sq, deadline)
|
||||
}
|
||||
|
||||
func (vmssn *VMStorageSingleNode) RegisterMetricNames(qt *querytracer.Tracer, mrs []storage.MetricRow, deadline uint64) error {
|
||||
vmssn.wg.Add(1)
|
||||
defer vmssn.wg.Done()
|
||||
return vmssn.vms.RegisterMetricNames(qt, mrs, deadline)
|
||||
}
|
||||
|
||||
func (vmssn *VMStorageSingleNode) GetMetricNamesUsageStats(qt *querytracer.Tracer, tt *storage.TenantToken, limit, le int, matchPattern string, deadline uint64) (metricnamestats.StatsResult, error) {
|
||||
vmssn.wg.Add(1)
|
||||
defer vmssn.wg.Done()
|
||||
return vmssn.vms.GetMetricNamesUsageStats(qt, tt, limit, le, matchPattern, deadline)
|
||||
}
|
||||
|
||||
func (vmssn *VMStorageSingleNode) ResetMetricNamesUsageStats(qt *querytracer.Tracer, deadline uint64) error {
|
||||
vmssn.wg.Add(1)
|
||||
defer vmssn.wg.Done()
|
||||
return vmssn.vms.ResetMetricNamesUsageStats(qt, deadline)
|
||||
}
|
||||
|
||||
func (vmssn *VMStorageSingleNode) GetMetadataRecords(qt *querytracer.Tracer, tt *storage.TenantToken, limit int, metricName string, deadline uint64) ([]*metricsmetadata.Row, error) {
|
||||
vmssn.wg.Add(1)
|
||||
defer vmssn.wg.Done()
|
||||
return vmssn.vms.GetMetadataRecords(qt, tt, limit, metricName, deadline)
|
||||
}
|
||||
@@ -48,7 +48,7 @@ func TestGetMaxMetrics(t *testing.T) {
|
||||
t.Helper()
|
||||
*maxUniqueTimeseries = storageMaxUniqueTimeseries
|
||||
s := storage.MustOpenStorage(t.Name(), storage.OpenOptions{})
|
||||
vms := newVMStorage(s, maxConcurrentRequests)
|
||||
vms := newVMStorage(s, maxConcurrentRequests, func(mrs []storage.MetricRow) {})
|
||||
defer vms.Stop()
|
||||
maxMetrics := vms.getMaxMetrics(searchQueryLimit)
|
||||
if maxMetrics != expect {
|
||||
|
||||
@@ -6,7 +6,7 @@ COPY web/ /build/
|
||||
RUN GOOS=linux GOARCH=amd64 CGO_ENABLED=0 go build -o web-amd64 github.com/VictoriMetrics/vmui/ && \
|
||||
GOOS=windows GOARCH=amd64 CGO_ENABLED=0 go build -o web-windows github.com/VictoriMetrics/vmui/
|
||||
|
||||
FROM alpine:3.23.4
|
||||
FROM alpine:3.24.1
|
||||
USER root
|
||||
|
||||
COPY --from=build-web-stage /build/web-amd64 /app/web
|
||||
|
||||
@@ -5,7 +5,7 @@ import uPlot from "uplot";
|
||||
import Button from "../../Main/Button/Button";
|
||||
import { CloseIcon, DragIcon } from "../../Main/Icons";
|
||||
import { SeriesItemStatsFormatted } from "../../../types";
|
||||
import { STATS_ORDER } from "../../../constants/graph";
|
||||
import { STATS_ORDER_TOOLTIP } from "../../../constants/graph";
|
||||
|
||||
export interface ChartTooltipProps {
|
||||
u?: uPlot;
|
||||
@@ -164,7 +164,7 @@ const ChartTooltip: FC<ChartTooltipProps> = ({
|
||||
</div>
|
||||
{statsFormatted && (
|
||||
<table className="vm-chart-tooltip-stats">
|
||||
{STATS_ORDER.map((key, i) => (
|
||||
{STATS_ORDER_TOOLTIP.map((key, i) => (
|
||||
<div
|
||||
className="vm-chart-tooltip-stats-row"
|
||||
key={i}
|
||||
|
||||
@@ -61,7 +61,7 @@ const LegendConfigs: FC<Props> = ({ data, isCompact }) => {
|
||||
label: "Hide Statistics",
|
||||
value: hideStats,
|
||||
onChange: onChangeStats,
|
||||
info: "If enabled, hides the display of min, median, and max values.",
|
||||
info: "If enabled, hides the display of min, median, max, and last values.",
|
||||
}
|
||||
];
|
||||
|
||||
|
||||
@@ -5,7 +5,7 @@ import "./style.scss";
|
||||
import classNames from "classnames";
|
||||
import { getFreeFields } from "./helpers";
|
||||
import useCopyToClipboard from "../../../../../hooks/useCopyToClipboard";
|
||||
import { STATS_ORDER } from "../../../../../constants/graph";
|
||||
import { STATS_ORDER_LEGEND } from "../../../../../constants/graph";
|
||||
import { useShowStats } from "../hooks/useShowStats";
|
||||
import { useLegendFormat } from "../hooks/useLegendFormat";
|
||||
import { getLabelAlias } from "../../../../../utils/metric";
|
||||
@@ -80,7 +80,7 @@ const LegendItem: FC<LegendItemProps> = ({ legend, onChange, duplicateFields })
|
||||
</div>
|
||||
{!hideStats && showStats && (
|
||||
<div className="vm-legend-item-stats">
|
||||
{STATS_ORDER.map((key, i) => (
|
||||
{STATS_ORDER_LEGEND.map((key, i) => (
|
||||
<div
|
||||
className="vm-legend-item-stats-row"
|
||||
key={i}
|
||||
|
||||
@@ -4,11 +4,11 @@ import "./style.scss";
|
||||
import { LegendItemType } from "../../../../../types";
|
||||
import { MouseEvent } from "react";
|
||||
import classNames from "classnames";
|
||||
import { STATS_ORDER } from "../../../../../constants/graph";
|
||||
import { STATS_ORDER_LEGEND } from "../../../../../constants/graph";
|
||||
import { useShowStats } from "../hooks/useShowStats";
|
||||
import { getValueByPath } from "../../../../../utils/object";
|
||||
|
||||
const statsColumns = STATS_ORDER.map(k => ({
|
||||
const statsColumns = STATS_ORDER_LEGEND.map(k => ({
|
||||
key: `statsFormatted.${k}`,
|
||||
title: k
|
||||
}));
|
||||
|
||||
@@ -26,4 +26,5 @@ export const GRAPH_SIZES: GraphSize[] = [
|
||||
},
|
||||
];
|
||||
|
||||
export const STATS_ORDER: (keyof SeriesItemStatsFormatted)[] = ["min", "median", "max"];
|
||||
export const STATS_ORDER_LEGEND: (keyof SeriesItemStatsFormatted)[] = ["min", "median", "max", "last"];
|
||||
export const STATS_ORDER_TOOLTIP: (keyof SeriesItemStatsFormatted)[] = ["min", "median", "max"];
|
||||
|
||||
@@ -4,6 +4,7 @@ export interface SeriesItemStatsFormatted {
|
||||
min: string,
|
||||
max: string,
|
||||
median: string,
|
||||
last: string,
|
||||
}
|
||||
|
||||
export interface SeriesItem extends Series {
|
||||
|
||||
@@ -53,6 +53,7 @@ const getSeriesStatistics = (d: MetricResult) => {
|
||||
min: formatPrettyNumber(min, min, max),
|
||||
max: formatPrettyNumber(max, min, max),
|
||||
median: formatPrettyNumber(median, min, max),
|
||||
last: formatPrettyNumber(values.at(-1), min, max),
|
||||
},
|
||||
};
|
||||
};
|
||||
|
||||
@@ -4,7 +4,7 @@ The `apptest` package contains the integration tests for the VictoriaMetrics
|
||||
applications (such as vmstorage, vminsert, and vmselect).
|
||||
|
||||
An integration test aims at verifying the behavior of an application as a whole,
|
||||
as apposed to a unit test that verifies the behavior of a building block of an
|
||||
as opposed to a unit test that verifies the behavior of a building block of an
|
||||
application.
|
||||
|
||||
To achieve that an integration test starts an application in a separate process
|
||||
@@ -19,10 +19,10 @@ work together as a system.
|
||||
The package provides a collection of helpers to start applications and make
|
||||
queries to them:
|
||||
|
||||
- `app.go` - contains the generic code for staring an application and should
|
||||
- `app.go` - contains the generic code for starting an application and should
|
||||
not be used by integration tests directly.
|
||||
- `{vmstorage,vminsert,etc}.go` - build on top of `app.go` and provide the
|
||||
code for staring a specific application.
|
||||
code for starting a specific application.
|
||||
- `client.go` - provides helper functions for sending HTTP requests to
|
||||
applications.
|
||||
|
||||
@@ -36,7 +36,7 @@ the application binary files to be built and put into the `bin` directory. The
|
||||
build rule used for running integration tests, `make apptest`,
|
||||
accounts for that, it builds all application binaries before running the tests.
|
||||
But if you want to run the tests without `make`, i.e. by executing
|
||||
`go test ./app/apptest`, you will need to build the binaries first (for example,
|
||||
`go test ./apptest/tests`, you will need to build the binaries first (for example,
|
||||
by executing `make all`).
|
||||
|
||||
Not all binaries can be built from `master` branch, cluster binaries can be built
|
||||
|
||||
@@ -156,14 +156,14 @@ func readAllAndClose(t *testing.T, responseBody io.ReadCloser) string {
|
||||
//
|
||||
// This type is expected to be embedded by the apps that serve metrics.
|
||||
type metricsClient struct {
|
||||
metricsCli *Client
|
||||
url string
|
||||
cli *Client
|
||||
url string
|
||||
}
|
||||
|
||||
func newMetricsClient(cli *Client, addr string) *metricsClient {
|
||||
return &metricsClient{
|
||||
metricsCli: cli,
|
||||
url: fmt.Sprintf("http://%s/metrics", addr),
|
||||
cli: cli,
|
||||
url: fmt.Sprintf("http://%s/metrics", addr),
|
||||
}
|
||||
}
|
||||
|
||||
@@ -179,7 +179,7 @@ func (c *metricsClient) GetIntMetric(t *testing.T, metricName string) int {
|
||||
func (c *metricsClient) GetMetric(t *testing.T, metricName string) float64 {
|
||||
t.Helper()
|
||||
|
||||
metrics, statusCode := c.metricsCli.Get(t, c.url, nil)
|
||||
metrics, statusCode := c.cli.Get(t, c.url, nil)
|
||||
if statusCode != http.StatusOK {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusOK)
|
||||
}
|
||||
@@ -205,7 +205,7 @@ func (c *metricsClient) GetMetricsByPrefix(t *testing.T, prefix string) []float6
|
||||
|
||||
values := []float64{}
|
||||
|
||||
metrics, statusCode := c.metricsCli.Get(t, c.url, nil)
|
||||
metrics, statusCode := c.cli.Get(t, c.url, nil)
|
||||
if statusCode != http.StatusOK {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusOK)
|
||||
}
|
||||
@@ -234,7 +234,7 @@ func (c *metricsClient) GetMetricsByRegexp(t *testing.T, re *regexp.Regexp) []fl
|
||||
|
||||
values := []float64{}
|
||||
|
||||
metrics, statusCode := c.metricsCli.Get(t, c.url, nil)
|
||||
metrics, statusCode := c.cli.Get(t, c.url, nil)
|
||||
if statusCode != http.StatusOK {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusOK)
|
||||
}
|
||||
@@ -270,7 +270,7 @@ func (c *metricsClient) rpcRowsSentTotal(t *testing.T) int {
|
||||
}
|
||||
|
||||
type vmselectClient struct {
|
||||
vmselectCli *Client
|
||||
cli *Client
|
||||
url func(op, path string, opts QueryOpts) string
|
||||
metricNamesStatsResetURL string
|
||||
tenantsURL string
|
||||
@@ -287,7 +287,7 @@ func (c *vmselectClient) PrometheusAPIV1Export(t *testing.T, query string, opts
|
||||
values := opts.asURLValues()
|
||||
values.Add("match[]", query)
|
||||
values.Add("format", "promapi")
|
||||
res, _ := c.vmselectCli.PostForm(t, url, values, opts.Headers)
|
||||
res, _ := c.cli.PostForm(t, url, values, opts.Headers)
|
||||
return NewPrometheusAPIV1QueryResponse(t, res)
|
||||
}
|
||||
|
||||
@@ -302,7 +302,7 @@ func (c *vmselectClient) PrometheusAPIV1ExportNative(t *testing.T, query string,
|
||||
values := opts.asURLValues()
|
||||
values.Add("match[]", query)
|
||||
values.Add("format", "promapi")
|
||||
res, _ := c.vmselectCli.PostForm(t, url, values, opts.Headers)
|
||||
res, _ := c.cli.PostForm(t, url, values, opts.Headers)
|
||||
return []byte(res)
|
||||
}
|
||||
|
||||
@@ -315,7 +315,7 @@ func (c *vmselectClient) PrometheusAPIV1Query(t *testing.T, query string, opts Q
|
||||
url := c.url("select", "prometheus/api/v1/query", opts)
|
||||
values := opts.asURLValues()
|
||||
values.Add("query", query)
|
||||
res, _ := c.vmselectCli.PostForm(t, url, values, opts.Headers)
|
||||
res, _ := c.cli.PostForm(t, url, values, opts.Headers)
|
||||
return NewPrometheusAPIV1QueryResponse(t, res)
|
||||
}
|
||||
|
||||
@@ -329,7 +329,7 @@ func (c *vmselectClient) PrometheusAPIV1QueryRange(t *testing.T, query string, o
|
||||
url := c.url("select", "prometheus/api/v1/query_range", opts)
|
||||
values := opts.asURLValues()
|
||||
values.Add("query", query)
|
||||
res, _ := c.vmselectCli.PostForm(t, url, values, opts.Headers)
|
||||
res, _ := c.cli.PostForm(t, url, values, opts.Headers)
|
||||
return NewPrometheusAPIV1QueryResponse(t, res)
|
||||
}
|
||||
|
||||
@@ -342,7 +342,7 @@ func (c *vmselectClient) PrometheusAPIV1Series(t *testing.T, matchQuery string,
|
||||
url := c.url("select", "prometheus/api/v1/series", opts)
|
||||
values := opts.asURLValues()
|
||||
values.Add("match[]", matchQuery)
|
||||
res, _ := c.vmselectCli.PostForm(t, url, values, opts.Headers)
|
||||
res, _ := c.cli.PostForm(t, url, values, opts.Headers)
|
||||
return NewPrometheusAPIV1SeriesResponse(t, res)
|
||||
}
|
||||
|
||||
@@ -354,7 +354,7 @@ func (c *vmselectClient) PrometheusAPIV1SeriesCount(t *testing.T, opts QueryOpts
|
||||
t.Helper()
|
||||
url := c.url("select", "prometheus/api/v1/series/count", opts)
|
||||
values := opts.asURLValues()
|
||||
res, _ := c.vmselectCli.PostForm(t, url, values, opts.Headers)
|
||||
res, _ := c.cli.PostForm(t, url, values, opts.Headers)
|
||||
return NewPrometheusAPIV1SeriesCountResponse(t, res)
|
||||
}
|
||||
|
||||
@@ -367,7 +367,7 @@ func (c *vmselectClient) PrometheusAPIV1Labels(t *testing.T, matchQuery string,
|
||||
url := c.url("select", "prometheus/api/v1/labels", opts)
|
||||
values := opts.asURLValues()
|
||||
values.Add("match[]", matchQuery)
|
||||
res, _ := c.vmselectCli.PostForm(t, url, values, opts.Headers)
|
||||
res, _ := c.cli.PostForm(t, url, values, opts.Headers)
|
||||
return NewPrometheusAPIV1LabelsResponse(t, res)
|
||||
}
|
||||
|
||||
@@ -382,7 +382,7 @@ func (c *vmselectClient) PrometheusAPIV1LabelValues(t *testing.T, labelName, mat
|
||||
url := c.url("select", path, opts)
|
||||
values := opts.asURLValues()
|
||||
values.Add("match[]", matchQuery)
|
||||
res, _ := c.vmselectCli.PostForm(t, url, values, opts.Headers)
|
||||
res, _ := c.cli.PostForm(t, url, values, opts.Headers)
|
||||
return NewPrometheusAPIV1LabelValuesResponse(t, res)
|
||||
}
|
||||
|
||||
@@ -394,7 +394,7 @@ func (c *vmselectClient) PrometheusAPIV1Metadata(t *testing.T, metric string, li
|
||||
values := opts.asURLValues()
|
||||
values.Add("metric", metric)
|
||||
values.Add("limit", strconv.Itoa(limit))
|
||||
res, _ := c.vmselectCli.PostForm(t, url, values, opts.Headers)
|
||||
res, _ := c.cli.PostForm(t, url, values, opts.Headers)
|
||||
return NewPrometheusAPIV1Metadata(t, res)
|
||||
}
|
||||
|
||||
@@ -408,7 +408,7 @@ func (c *vmselectClient) PrometheusAPIV1AdminTSDBDeleteSeries(t *testing.T, matc
|
||||
url := c.url("delete", "prometheus/api/v1/admin/tsdb/delete_series", opts)
|
||||
values := opts.asURLValues()
|
||||
values.Add("match[]", matchQuery)
|
||||
res, statusCode := c.vmselectCli.PostForm(t, url, values, opts.Headers)
|
||||
res, statusCode := c.cli.PostForm(t, url, values, opts.Headers)
|
||||
if statusCode != http.StatusNoContent {
|
||||
t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusNoContent, res)
|
||||
}
|
||||
@@ -426,7 +426,7 @@ func (c *vmselectClient) PrometheusAPIV1StatusMetricNamesStats(t *testing.T, lim
|
||||
values.Add("limit", limit)
|
||||
values.Add("le", le)
|
||||
values.Add("match_pattern", matchPattern)
|
||||
res, statusCode := c.vmselectCli.PostForm(t, url, values, opts.Headers)
|
||||
res, statusCode := c.cli.PostForm(t, url, values, opts.Headers)
|
||||
if statusCode != http.StatusOK {
|
||||
t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusOK, res)
|
||||
}
|
||||
@@ -455,7 +455,7 @@ func (c *vmselectClient) PrometheusAPIV1StatusTSDB(t *testing.T, matchQuery stri
|
||||
addNonEmpty("match[]", matchQuery)
|
||||
addNonEmpty("topN", topN)
|
||||
addNonEmpty("date", date)
|
||||
res, statusCode := c.vmselectCli.PostForm(t, url, values, opts.Headers)
|
||||
res, statusCode := c.cli.PostForm(t, url, values, opts.Headers)
|
||||
if statusCode != http.StatusOK {
|
||||
t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusOK, res)
|
||||
}
|
||||
@@ -476,7 +476,7 @@ func (c *vmselectClient) GraphiteMetricsIndex(t *testing.T, opts QueryOpts) Grap
|
||||
t.Helper()
|
||||
|
||||
url := c.url("select", "graphite/metrics/index.json", opts)
|
||||
res, statusCode := c.vmselectCli.Get(t, url, opts.Headers)
|
||||
res, statusCode := c.cli.Get(t, url, opts.Headers)
|
||||
if statusCode != http.StatusOK {
|
||||
t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusOK, res)
|
||||
}
|
||||
@@ -499,7 +499,7 @@ func (c *vmselectClient) GraphiteMetricsFind(t *testing.T, query string, opts Qu
|
||||
url := c.url("select", "graphite/metrics/find", opts)
|
||||
values := opts.asURLValues()
|
||||
values.Add("query", query)
|
||||
resText, statusCode := c.vmselectCli.PostForm(t, url, values, opts.Headers)
|
||||
resText, statusCode := c.cli.PostForm(t, url, values, opts.Headers)
|
||||
if statusCode != http.StatusOK {
|
||||
t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusOK, resText)
|
||||
}
|
||||
@@ -522,7 +522,7 @@ func (c *vmselectClient) GraphiteMetricsExpand(t *testing.T, query string, opts
|
||||
url := c.url("select", "graphite/metrics/expand", opts)
|
||||
values := opts.asURLValues()
|
||||
values.Add("query", query)
|
||||
resText, statusCode := c.vmselectCli.PostForm(t, url, values, opts.Headers)
|
||||
resText, statusCode := c.cli.PostForm(t, url, values, opts.Headers)
|
||||
if statusCode != http.StatusOK {
|
||||
t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusOK, resText)
|
||||
}
|
||||
@@ -546,7 +546,7 @@ func (c *vmselectClient) GraphiteRender(t *testing.T, target string, opts QueryO
|
||||
values := opts.asURLValues()
|
||||
values.Add("format", "json")
|
||||
values.Add("target", target)
|
||||
resText, statusCode := c.vmselectCli.PostForm(t, url, values, opts.Headers)
|
||||
resText, statusCode := c.cli.PostForm(t, url, values, opts.Headers)
|
||||
if statusCode != http.StatusOK {
|
||||
t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusOK, resText)
|
||||
}
|
||||
@@ -567,7 +567,7 @@ func (c *vmselectClient) GraphiteTagsTagSeries(t *testing.T, record string, opts
|
||||
url := c.url("select", "graphite/tags/tagSeries", opts)
|
||||
values := opts.asURLValues()
|
||||
values.Add("path", record)
|
||||
_, statusCode := c.vmselectCli.PostForm(t, url, values, opts.Headers)
|
||||
_, statusCode := c.cli.PostForm(t, url, values, opts.Headers)
|
||||
if got, want := statusCode, http.StatusNotImplemented; got != want {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", got, want)
|
||||
}
|
||||
@@ -584,7 +584,7 @@ func (c *vmselectClient) GraphiteTagsTagMultiSeries(t *testing.T, records []stri
|
||||
for _, rec := range records {
|
||||
values.Add("path", rec)
|
||||
}
|
||||
_, statusCode := c.vmselectCli.PostForm(t, url, values, opts.Headers)
|
||||
_, statusCode := c.cli.PostForm(t, url, values, opts.Headers)
|
||||
if got, want := statusCode, http.StatusNotImplemented; got != want {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", got, want)
|
||||
}
|
||||
@@ -598,7 +598,7 @@ func (c *vmselectClient) GraphiteTagsTagMultiSeries(t *testing.T, records []stri
|
||||
func (c *vmselectClient) PrometheusAPIV1AdminStatusMetricNamesStatsReset(t *testing.T, opts QueryOpts) {
|
||||
t.Helper()
|
||||
values := opts.asURLValues()
|
||||
res, statusCode := c.vmselectCli.PostForm(t, c.metricNamesStatsResetURL, values, opts.Headers)
|
||||
res, statusCode := c.cli.PostForm(t, c.metricNamesStatsResetURL, values, opts.Headers)
|
||||
if statusCode != http.StatusNoContent {
|
||||
t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusNoContent, res)
|
||||
}
|
||||
@@ -608,7 +608,7 @@ func (c *vmselectClient) PrometheusAPIV1AdminStatusMetricNamesStatsReset(t *test
|
||||
// /admin/tenants endpoint.
|
||||
func (c *vmselectClient) APIV1AdminTenants(t *testing.T, opts QueryOpts) *AdminTenantsResponse {
|
||||
t.Helper()
|
||||
res, statusCode := c.vmselectCli.Get(t, c.tenantsURL, opts.Headers)
|
||||
res, statusCode := c.cli.Get(t, c.tenantsURL, opts.Headers)
|
||||
if statusCode != http.StatusOK {
|
||||
t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusOK, res)
|
||||
}
|
||||
@@ -622,7 +622,7 @@ func (c *vmselectClient) APIV1AdminTenants(t *testing.T, opts QueryOpts) *AdminT
|
||||
}
|
||||
|
||||
type vminsertClient struct {
|
||||
vminsertCli *Client
|
||||
cli *Client
|
||||
url func(op, path string, opts QueryOpts) string
|
||||
openTSDBURL func(op, path string, opts QueryOpts) string
|
||||
graphiteListenAddr string
|
||||
@@ -647,7 +647,7 @@ func (c *vminsertClient) PrometheusAPIV1ImportCSV(t *testing.T, records []string
|
||||
headers := opts.getHeaders()
|
||||
headers.Set("Content-Type", "text/plain")
|
||||
c.sendBlocking(t, len(records), func() {
|
||||
_, statusCode := c.vminsertCli.Post(t, url, data, headers)
|
||||
_, statusCode := c.cli.Post(t, url, data, headers)
|
||||
if statusCode != http.StatusNoContent {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
|
||||
}
|
||||
@@ -671,7 +671,7 @@ func (c *vminsertClient) PrometheusAPIV1ImportNative(t *testing.T, data []byte,
|
||||
headers := opts.getHeaders()
|
||||
headers.Set("Content-Type", "text/plain")
|
||||
c.sendBlocking(t, 1, func() {
|
||||
_, statusCode := c.vminsertCli.Post(t, url, data, headers)
|
||||
_, statusCode := c.cli.Post(t, url, data, headers)
|
||||
if statusCode != http.StatusNoContent {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
|
||||
}
|
||||
@@ -693,7 +693,7 @@ func (c *vminsertClient) PrometheusAPIV1Write(t *testing.T, wr prompb.WriteReque
|
||||
headers := opts.getHeaders()
|
||||
headers.Set("Content-Type", "application/x-protobuf")
|
||||
c.sendBlocking(t, recordsCount, func() {
|
||||
_, statusCode := c.vminsertCli.Post(t, url, data, headers)
|
||||
_, statusCode := c.cli.Post(t, url, data, headers)
|
||||
if statusCode != http.StatusNoContent {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
|
||||
}
|
||||
@@ -745,7 +745,7 @@ func (c *vminsertClient) PrometheusAPIV1ImportPrometheus(t *testing.T, records [
|
||||
headers := opts.getHeaders()
|
||||
headers.Set("Content-Type", "text/plain")
|
||||
c.sendBlocking(t, recordsCount, func() {
|
||||
_, statusCode := c.vminsertCli.Post(t, url, data, headers)
|
||||
_, statusCode := c.cli.Post(t, url, data, headers)
|
||||
if statusCode != http.StatusNoContent {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
|
||||
}
|
||||
@@ -771,7 +771,7 @@ func (c *vminsertClient) InfluxWrite(t *testing.T, records []string, opts QueryO
|
||||
headers.Set("Content-Type", "text/plain")
|
||||
c.sendBlocking(t, len(records), func() {
|
||||
t.Helper()
|
||||
_, statusCode := c.vminsertCli.Post(t, url, data, headers)
|
||||
_, statusCode := c.cli.Post(t, url, data, headers)
|
||||
if statusCode != http.StatusNoContent {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
|
||||
}
|
||||
@@ -805,7 +805,7 @@ func (c *vminsertClient) OpentelemetryV1Metrics(t *testing.T, md otlppb.MetricsD
|
||||
headers := opts.getHeaders()
|
||||
headers.Set("Content-Type", "application/x-protobuf")
|
||||
c.sendBlocking(t, recordsCount, func() {
|
||||
_, statusCode := c.vminsertCli.Post(t, url, data, headers)
|
||||
_, statusCode := c.cli.Post(t, url, data, headers)
|
||||
if statusCode != http.StatusOK {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusOK)
|
||||
}
|
||||
@@ -830,7 +830,7 @@ func (c *vminsertClient) OpenTSDBAPIPut(t *testing.T, records []string, opts Que
|
||||
headers := opts.getHeaders()
|
||||
headers.Set("Content-Type", "application/json")
|
||||
c.sendBlocking(t, len(records), func() {
|
||||
_, statusCode := c.vminsertCli.Post(t, url, data, headers)
|
||||
_, statusCode := c.cli.Post(t, url, data, headers)
|
||||
if statusCode != http.StatusNoContent {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
|
||||
}
|
||||
@@ -853,7 +853,7 @@ func (c *vminsertClient) ZabbixConnectorHistory(t *testing.T, records []string,
|
||||
headers := opts.getHeaders()
|
||||
headers.Set("Content-Type", "application/json")
|
||||
c.sendBlocking(t, len(records), func() {
|
||||
_, statusCode := c.vminsertCli.Post(t, url, data, headers)
|
||||
_, statusCode := c.cli.Post(t, url, data, headers)
|
||||
if statusCode != http.StatusOK {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusOK)
|
||||
}
|
||||
@@ -867,11 +867,11 @@ func (c *vminsertClient) ZabbixConnectorHistory(t *testing.T, records []string,
|
||||
// See https://docs.victoriametrics.com/victoriametrics/integrations/graphite/#ingesting
|
||||
func (c *vminsertClient) GraphiteWrite(t *testing.T, records []string, _ QueryOpts) {
|
||||
t.Helper()
|
||||
c.vminsertCli.Write(t, c.graphiteListenAddr, records)
|
||||
c.cli.Write(t, c.graphiteListenAddr, records)
|
||||
}
|
||||
|
||||
type vmstorageClient struct {
|
||||
vmstorageCli *Client
|
||||
cli *Client
|
||||
httpListenAddr string
|
||||
}
|
||||
|
||||
@@ -881,7 +881,7 @@ func (c *vmstorageClient) ForceFlush(t *testing.T) {
|
||||
t.Helper()
|
||||
|
||||
url := fmt.Sprintf("http://%s/internal/force_flush", c.httpListenAddr)
|
||||
_, statusCode := c.vmstorageCli.Get(t, url, nil)
|
||||
_, statusCode := c.cli.Get(t, url, nil)
|
||||
if statusCode != http.StatusOK {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusOK)
|
||||
}
|
||||
@@ -892,7 +892,7 @@ func (c *vmstorageClient) ForceMerge(t *testing.T) {
|
||||
t.Helper()
|
||||
|
||||
url := fmt.Sprintf("http://%s/internal/force_merge", c.httpListenAddr)
|
||||
_, statusCode := c.vmstorageCli.Get(t, url, nil)
|
||||
_, statusCode := c.cli.Get(t, url, nil)
|
||||
if statusCode != http.StatusOK {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusOK)
|
||||
}
|
||||
@@ -905,7 +905,7 @@ func (c *vmstorageClient) ForceMerge(t *testing.T) {
|
||||
func (c *vmstorageClient) SnapshotCreate(t *testing.T) *SnapshotCreateResponse {
|
||||
t.Helper()
|
||||
|
||||
data, statusCode := c.vmstorageCli.Post(t, c.SnapshotCreateURL(), nil, nil)
|
||||
data, statusCode := c.cli.Post(t, c.SnapshotCreateURL(), nil, nil)
|
||||
if got, want := statusCode, http.StatusOK; got != want {
|
||||
t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", got, want, data)
|
||||
}
|
||||
@@ -931,7 +931,7 @@ func (c *vmstorageClient) APIV1AdminTSDBSnapshot(t *testing.T) *APIV1AdminTSDBSn
|
||||
t.Helper()
|
||||
|
||||
url := fmt.Sprintf("http://%s/api/v1/admin/tsdb/snapshot", c.httpListenAddr)
|
||||
data, statusCode := c.vmstorageCli.Post(t, url, nil, nil)
|
||||
data, statusCode := c.cli.Post(t, url, nil, nil)
|
||||
if got, want := statusCode, http.StatusOK; got != want {
|
||||
t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", got, want, data)
|
||||
}
|
||||
@@ -952,7 +952,7 @@ func (c *vmstorageClient) SnapshotList(t *testing.T) *SnapshotListResponse {
|
||||
t.Helper()
|
||||
|
||||
url := fmt.Sprintf("http://%s/snapshot/list", c.httpListenAddr)
|
||||
data, statusCode := c.vmstorageCli.Get(t, url, nil)
|
||||
data, statusCode := c.cli.Get(t, url, nil)
|
||||
if got, want := statusCode, http.StatusOK; got != want {
|
||||
t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", got, want, data)
|
||||
}
|
||||
@@ -973,7 +973,7 @@ func (c *vmstorageClient) SnapshotDelete(t *testing.T, snapshotName string) *Sna
|
||||
t.Helper()
|
||||
|
||||
url := fmt.Sprintf("http://%s/snapshot/delete?snapshot=%s", c.httpListenAddr, snapshotName)
|
||||
data, statusCode := c.vmstorageCli.Delete(t, url)
|
||||
data, statusCode := c.cli.Delete(t, url)
|
||||
wantStatusCodes := map[int]bool{
|
||||
http.StatusOK: true,
|
||||
http.StatusInternalServerError: true,
|
||||
@@ -998,7 +998,7 @@ func (c *vmstorageClient) SnapshotDeleteAll(t *testing.T) *SnapshotDeleteAllResp
|
||||
t.Helper()
|
||||
|
||||
url := fmt.Sprintf("http://%s/snapshot/delete_all", c.httpListenAddr)
|
||||
data, statusCode := c.vmstorageCli.Post(t, url, nil, nil)
|
||||
data, statusCode := c.cli.Post(t, url, nil, nil)
|
||||
if got, want := statusCode, http.StatusOK; got != want {
|
||||
t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", got, want, data)
|
||||
}
|
||||
|
||||
@@ -45,11 +45,13 @@ func TestSingleMetricsMetadata(t *testing.T) {
|
||||
{Labels: []prompb.Label{{Name: "__name__", Value: "metric_name_4"}}, Samples: []prompb.Sample{{Value: 40, Timestamp: ingestTimestamp}}},
|
||||
{Labels: []prompb.Label{{Name: "__name__", Value: "metric_name_5"}}, Samples: []prompb.Sample{{Value: 40, Timestamp: ingestTimestamp}}},
|
||||
{Labels: []prompb.Label{{Name: "__name__", Value: "metric_name_6"}}, Samples: []prompb.Sample{{Value: 40, Timestamp: ingestTimestamp}}},
|
||||
{Labels: []prompb.Label{{Name: "__name__", Value: `metric_name_7_!@"_suffix`}}, Samples: []prompb.Sample{{Value: 40, Timestamp: ingestTimestamp}}},
|
||||
},
|
||||
Metadata: []prompb.MetricMetadata{
|
||||
{MetricFamilyName: "metric_name_4", Help: "some help message", Type: prompb.MetricTypeSummary},
|
||||
{MetricFamilyName: "metric_name_5", Help: "some help message", Type: prompb.MetricTypeSummary},
|
||||
{MetricFamilyName: "metric_name_6", Help: "some help message", Type: prompb.MetricTypeStateset},
|
||||
{MetricFamilyName: `metric_name_7_!@"_suffix`, Help: "some help message", Type: prompb.MetricTypeStateset},
|
||||
},
|
||||
}
|
||||
|
||||
@@ -59,12 +61,13 @@ func TestSingleMetricsMetadata(t *testing.T) {
|
||||
expected := &apptest.PrometheusAPIV1Metadata{
|
||||
Status: "success",
|
||||
Data: map[string][]apptest.MetadataEntry{
|
||||
"metric_name_1": {{Help: "some help message", Type: "gauge"}},
|
||||
"metric_name_2": {{Help: "some help message", Type: "counter"}},
|
||||
"metric_name_3": {{Help: "some help message", Type: "gauge"}},
|
||||
"metric_name_4": {{Help: "some help message", Type: "summary"}},
|
||||
"metric_name_5": {{Help: "some help message", Type: "summary"}},
|
||||
"metric_name_6": {{Help: "some help message", Type: "stateset"}},
|
||||
"metric_name_1": {{Help: "some help message", Type: "gauge"}},
|
||||
"metric_name_2": {{Help: "some help message", Type: "counter"}},
|
||||
"metric_name_3": {{Help: "some help message", Type: "gauge"}},
|
||||
"metric_name_4": {{Help: "some help message", Type: "summary"}},
|
||||
"metric_name_5": {{Help: "some help message", Type: "summary"}},
|
||||
"metric_name_6": {{Help: "some help message", Type: "stateset"}},
|
||||
`metric_name_7_!@"_suffix`: {{Help: "some help message", Type: "stateset"}},
|
||||
},
|
||||
}
|
||||
gotStats := sut.PrometheusAPIV1Metadata(t, "", 0, apptest.QueryOpts{})
|
||||
@@ -154,11 +157,13 @@ func TestClusterMetricsMetadata(t *testing.T) {
|
||||
{Labels: []prompb.Label{{Name: "__name__", Value: "metric_name_4"}}, Samples: []prompb.Sample{{Value: 40, Timestamp: ingestTimestamp}}},
|
||||
{Labels: []prompb.Label{{Name: "__name__", Value: "metric_name_5"}}, Samples: []prompb.Sample{{Value: 40, Timestamp: ingestTimestamp}}},
|
||||
{Labels: []prompb.Label{{Name: "__name__", Value: "metric_name_6"}}, Samples: []prompb.Sample{{Value: 40, Timestamp: ingestTimestamp}}},
|
||||
{Labels: []prompb.Label{{Name: "__name__", Value: `metric_name_7_!@"_suffix`}}, Samples: []prompb.Sample{{Value: 40, Timestamp: ingestTimestamp}}},
|
||||
},
|
||||
Metadata: []prompb.MetricMetadata{
|
||||
{MetricFamilyName: "metric_name_4", Help: "some help message", Type: prompb.MetricTypeSummary},
|
||||
{MetricFamilyName: "metric_name_5", Help: "some help message", Type: prompb.MetricTypeSummary},
|
||||
{MetricFamilyName: "metric_name_6", Help: "some help message", Type: prompb.MetricTypeStateset},
|
||||
{MetricFamilyName: `metric_name_7_!@"_suffix`, Help: "some help message", Type: prompb.MetricTypeStateset},
|
||||
},
|
||||
}
|
||||
|
||||
@@ -171,12 +176,13 @@ func TestClusterMetricsMetadata(t *testing.T) {
|
||||
expected := &apptest.PrometheusAPIV1Metadata{
|
||||
Status: "success",
|
||||
Data: map[string][]apptest.MetadataEntry{
|
||||
"metric_name_1": {{Help: "some help message", Type: "gauge"}},
|
||||
"metric_name_2": {{Help: "some help message", Type: "counter"}},
|
||||
"metric_name_3": {{Help: "some help message", Type: "gauge"}},
|
||||
"metric_name_4": {{Help: "some help message", Type: "summary"}},
|
||||
"metric_name_5": {{Help: "some help message", Type: "summary"}},
|
||||
"metric_name_6": {{Help: "some help message", Type: "stateset"}},
|
||||
"metric_name_1": {{Help: "some help message", Type: "gauge"}},
|
||||
"metric_name_2": {{Help: "some help message", Type: "counter"}},
|
||||
"metric_name_3": {{Help: "some help message", Type: "gauge"}},
|
||||
"metric_name_4": {{Help: "some help message", Type: "summary"}},
|
||||
"metric_name_5": {{Help: "some help message", Type: "summary"}},
|
||||
"metric_name_6": {{Help: "some help message", Type: "stateset"}},
|
||||
`metric_name_7_!@"_suffix`: {{Help: "some help message", Type: "stateset"}},
|
||||
},
|
||||
}
|
||||
gotStats := vmselect.PrometheusAPIV1Metadata(t, "", 0, apptest.QueryOpts{Tenant: tenantID})
|
||||
|
||||
@@ -8,6 +8,7 @@ import (
|
||||
"net/http/httptest"
|
||||
"strings"
|
||||
"sync"
|
||||
"sync/atomic"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
@@ -332,13 +333,11 @@ func TestSingleVMAgentDropOnOverload(t *testing.T) {
|
||||
vmagent.APIV1ImportPrometheusNoWaitFlush(t, []string{
|
||||
"foo_bar 1 1652169600000", // 2022-05-10T08:00:00Z
|
||||
}, apptest.QueryOpts{})
|
||||
|
||||
waitFor(
|
||||
func() bool {
|
||||
return vmagent.RemoteWriteRequests(t, url1) == 1 && vmagent.RemoteWriteRequests(t, url2) == 1
|
||||
},
|
||||
)
|
||||
|
||||
// Send 2 more requests, the first RW endpoint should receive everything, the second should add them to the queue
|
||||
// since worker is busy with the first request.
|
||||
for i := range 2 {
|
||||
@@ -641,3 +640,116 @@ func TestSingleVMAgentMultitenancy(t *testing.T) {
|
||||
t.Fatalf("expected vmagent_tenant_inserted_rows_total to have value 1 for accountID=5, projectID=0")
|
||||
}
|
||||
}
|
||||
|
||||
func TestSingleVMAgentPriorizeRecentData(t *testing.T) {
|
||||
tc := apptest.NewTestCase(t)
|
||||
defer tc.Stop()
|
||||
|
||||
remoteWriteSrv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
w.WriteHeader(http.StatusNoContent)
|
||||
}))
|
||||
defer remoteWriteSrv.Close()
|
||||
|
||||
var mustRW2ReturnError atomic.Bool
|
||||
mustRW2ReturnError.Store(true)
|
||||
|
||||
remoteWriteSrv2 := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
if mustRW2ReturnError.Load() {
|
||||
w.WriteHeader(http.StatusServiceUnavailable)
|
||||
return
|
||||
}
|
||||
w.WriteHeader(http.StatusNoContent)
|
||||
}))
|
||||
defer remoteWriteSrv2.Close()
|
||||
|
||||
vmagent := tc.MustStartDefaultRWVmagent("vmagent", []string{
|
||||
fmt.Sprintf(`-remoteWrite.url=%s/api/v1/write`, remoteWriteSrv.URL),
|
||||
fmt.Sprintf(`-remoteWrite.url=%s/api/v1/write`, remoteWriteSrv2.URL),
|
||||
"-remoteWrite.disableOnDiskQueue=true",
|
||||
// use only 1 worker to get a full queue faster
|
||||
"-remoteWrite.queues=1",
|
||||
"-remoteWrite.flushInterval=1ms",
|
||||
"-remoteWrite.inmemoryQueues=1",
|
||||
// fastqueue size is roughly memory.Allowed() / len(urls) / *maxRowsPerBlock / 100
|
||||
// Use very large maxRowsPerBlock to get fastqueue of minimal length(2).
|
||||
// See initRemoteWriteCtxs function in remotewrite.go for details.
|
||||
"-remoteWrite.maxRowsPerBlock=1000000000",
|
||||
"-remoteWrite.tmpDataPath=" + tc.Dir() + "/vmagent",
|
||||
|
||||
// Delay retry logic to avoid race conditions with waitFor assertions.
|
||||
// It improves the test stability on resource-constrained runners.
|
||||
"-remoteWrite.retryMinInterval=3s",
|
||||
"-remoteWrite.retryMaxTime=3s",
|
||||
})
|
||||
|
||||
const (
|
||||
retries = 20
|
||||
period = 200 * time.Millisecond
|
||||
)
|
||||
|
||||
waitFor := func(f func() bool) {
|
||||
t.Helper()
|
||||
for range retries {
|
||||
if f() {
|
||||
return
|
||||
}
|
||||
time.Sleep(period)
|
||||
}
|
||||
t.Fatalf("timed out waiting for retry #%d", retries)
|
||||
}
|
||||
|
||||
// Real remote write URLs are hidden in metrics
|
||||
url1 := "1:secret-url"
|
||||
url2 := "2:secret-url"
|
||||
|
||||
// Wait until first request got flushed to remote write server
|
||||
vmagent.APIV1ImportPrometheusNoWaitFlush(t, []string{
|
||||
"foo_bar 1 1652169600000", // 2022-05-10T08:00:00Z
|
||||
}, apptest.QueryOpts{})
|
||||
waitFor(
|
||||
func() bool {
|
||||
return vmagent.RemoteWriteRequests(t, url1) == 1 && vmagent.RemoteWriteRequests(t, url2) == 1
|
||||
},
|
||||
)
|
||||
// Wait until second request got flushed to remote write server
|
||||
// since there are 2 independent queues (general and in-memory) with minimal capacity of 1
|
||||
vmagent.APIV1ImportPrometheusNoWaitFlush(t, []string{
|
||||
"foo_bar 1 1652169600000", // 2022-05-10T08:00:00Z
|
||||
}, apptest.QueryOpts{})
|
||||
waitFor(
|
||||
func() bool {
|
||||
return vmagent.RemoteWriteRequests(t, url1) == 2 && vmagent.RemoteWriteRequests(t, url2) == 2
|
||||
},
|
||||
)
|
||||
// Send 2 more requests, the first RW endpoint should receive everything, the second should add them to the queue
|
||||
// since worker is busy with the first request.
|
||||
for i := range 2 {
|
||||
vmagent.APIV1ImportPrometheusNoWaitFlush(t, []string{
|
||||
"foo_bar 1 1652169600000", // 2022-05-10T08:00:00Z
|
||||
}, apptest.QueryOpts{})
|
||||
|
||||
waitFor(
|
||||
func() bool {
|
||||
return vmagent.RemoteWriteRequests(t, url1) == 3+i && vmagent.RemoteWritePendingInmemoryBlocks(t, url2) == 1+i
|
||||
},
|
||||
)
|
||||
}
|
||||
|
||||
// Send one more request.
|
||||
vmagent.APIV1ImportPrometheusNoWaitFlush(t, []string{
|
||||
"foo_bar 1 1652169600000", // 2022-05-10T08:00:00Z
|
||||
}, apptest.QueryOpts{})
|
||||
|
||||
waitFor(
|
||||
func() bool {
|
||||
return vmagent.RemoteWriteRequests(t, url1) == 5 && vmagent.RemoteWriteSamplesDropped(t, url2) > 0
|
||||
},
|
||||
)
|
||||
mustRW2ReturnError.Store(false)
|
||||
// ensure that inmemory data correctly flushed to the remote write
|
||||
waitFor(
|
||||
func() bool {
|
||||
return vmagent.RemoteWritePendingInmemoryBlocks(t, url2) == 0
|
||||
},
|
||||
)
|
||||
}
|
||||
|
||||
@@ -77,7 +77,7 @@ type vminsertRuntimeValues struct {
|
||||
func newVminsert(app *app, cli *Client, rt vminsertRuntimeValues) *Vminsert {
|
||||
metricsClient := newMetricsClient(cli, rt.httpListenAddr)
|
||||
vminsertClient := &vminsertClient{
|
||||
vminsertCli: cli,
|
||||
cli: cli,
|
||||
url: func(op, path string, opts QueryOpts) string {
|
||||
return getClusterPath(rt.httpListenAddr, op, path, opts)
|
||||
},
|
||||
|
||||
@@ -48,7 +48,7 @@ func newVmselect(app *app, cli *Client, rt vmselectRuntimeValues) *Vmselect {
|
||||
app: app,
|
||||
metricsClient: newMetricsClient(cli, rt.httpListenAddr),
|
||||
vmselectClient: &vmselectClient{
|
||||
vmselectCli: cli,
|
||||
cli: cli,
|
||||
url: func(op, path string, opts QueryOpts) string {
|
||||
return getClusterPath(rt.httpListenAddr, op, path, opts)
|
||||
},
|
||||
|
||||
@@ -58,11 +58,11 @@ func newVmsingle(app *app, cli *Client, rt vmsingleRuntimeValues) *Vmsingle {
|
||||
app: app,
|
||||
metricsClient: newMetricsClient(cli, rt.httpListenAddr),
|
||||
vmstorageClient: &vmstorageClient{
|
||||
vmstorageCli: cli,
|
||||
cli: cli,
|
||||
httpListenAddr: rt.httpListenAddr,
|
||||
},
|
||||
vmselectClient: &vmselectClient{
|
||||
vmselectCli: cli,
|
||||
cli: cli,
|
||||
url: func(op, path string, opts QueryOpts) string {
|
||||
return fmt.Sprintf("http://%s/%s", rt.httpListenAddr, path)
|
||||
},
|
||||
@@ -70,7 +70,7 @@ func newVmsingle(app *app, cli *Client, rt vmsingleRuntimeValues) *Vmsingle {
|
||||
tenantsURL: "vmsingle-does-not-serve-tenants",
|
||||
},
|
||||
vminsertClient: &vminsertClient{
|
||||
vminsertCli: cli,
|
||||
cli: cli,
|
||||
url: func(_, path string, _ QueryOpts) string {
|
||||
return fmt.Sprintf("http://%s/%s", rt.httpListenAddr, path)
|
||||
},
|
||||
|
||||
@@ -63,7 +63,7 @@ func newVmstorage(app *app, cli *Client, rt vmstorageRuntimeValues) *Vmstorage {
|
||||
app: app,
|
||||
metricsClient: newMetricsClient(cli, rt.httpListenAddr),
|
||||
vmstorageClient: &vmstorageClient{
|
||||
vmstorageCli: cli,
|
||||
cli: cli,
|
||||
httpListenAddr: rt.httpListenAddr,
|
||||
},
|
||||
storageDataPath: rt.storageDataPath,
|
||||
|
||||
@@ -2083,7 +2083,7 @@
|
||||
"type": "prometheus",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"description": "Shows memory pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\n**Lower is better.**\n\nPressure is measured as amount of time within 1sec time window the process was:\n- waiting: at least one thread was blocked on memory.\n- stalled: every thread was blocked on memory (severe pressure).\n\nElevated memory pressure can slowdown the process performance by utilizing more disk IO. Consider increasing amount of available RAM limit or decreasing the load on the process.\n\nSeу major page faults rate panel in Troubleshooting section if this metric continued to be high.",
|
||||
"description": "Shows memory pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\n**Lower is better.**\n\nPressure is measured as amount of time within 1sec time window the process was:\n- waiting: at least one thread was blocked on memory.\n- stalled: every thread was blocked on memory (severe pressure).\n\nElevated memory pressure can slowdown the process performance by utilizing more disk IO. Consider increasing amount of available RAM limit or decreasing the load on the process.\n\nSee major page faults rate panel in Troubleshooting section if this metric continued to be high.",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
|
||||
@@ -2388,7 +2388,7 @@
|
||||
"type": "prometheus",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"description": "Shows memory pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\n**Lower is better.**\n\nPressure is measured as amount of time within 1sec time window the process was:\n- waiting: at least one thread was blocked on memory.\n- stalled: every thread was blocked on memory (severe pressure).\n\nElevated memory pressure can slowdown the process performance by utilizing more disk IO. Consider increasing amount of available RAM limit or decreasing the load on the process.\n\nSeу major page faults rate panel in Troubleshooting section if this metric continued to be high.",
|
||||
"description": "Shows memory pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\n**Lower is better.**\n\nPressure is measured as amount of time within 1sec time window the process was:\n- waiting: at least one thread was blocked on memory.\n- stalled: every thread was blocked on memory (severe pressure).\n\nElevated memory pressure can slowdown the process performance by utilizing more disk IO. Consider increasing amount of available RAM limit or decreasing the load on the process.\n\nSee major page faults rate panel in Troubleshooting section if this metric continued to be high.",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
|
||||
@@ -2084,7 +2084,7 @@
|
||||
"type": "victoriametrics-metrics-datasource",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"description": "Shows memory pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\n**Lower is better.**\n\nPressure is measured as amount of time within 1sec time window the process was:\n- waiting: at least one thread was blocked on memory.\n- stalled: every thread was blocked on memory (severe pressure).\n\nElevated memory pressure can slowdown the process performance by utilizing more disk IO. Consider increasing amount of available RAM limit or decreasing the load on the process.\n\nSeу major page faults rate panel in Troubleshooting section if this metric continued to be high.",
|
||||
"description": "Shows memory pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\n**Lower is better.**\n\nPressure is measured as amount of time within 1sec time window the process was:\n- waiting: at least one thread was blocked on memory.\n- stalled: every thread was blocked on memory (severe pressure).\n\nElevated memory pressure can slowdown the process performance by utilizing more disk IO. Consider increasing amount of available RAM limit or decreasing the load on the process.\n\nSee major page faults rate panel in Troubleshooting section if this metric continued to be high.",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
|
||||
@@ -2389,7 +2389,7 @@
|
||||
"type": "victoriametrics-metrics-datasource",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"description": "Shows memory pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\n**Lower is better.**\n\nPressure is measured as amount of time within 1sec time window the process was:\n- waiting: at least one thread was blocked on memory.\n- stalled: every thread was blocked on memory (severe pressure).\n\nElevated memory pressure can slowdown the process performance by utilizing more disk IO. Consider increasing amount of available RAM limit or decreasing the load on the process.\n\nSeу major page faults rate panel in Troubleshooting section if this metric continued to be high.",
|
||||
"description": "Shows memory pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\n**Lower is better.**\n\nPressure is measured as amount of time within 1sec time window the process was:\n- waiting: at least one thread was blocked on memory.\n- stalled: every thread was blocked on memory (severe pressure).\n\nElevated memory pressure can slowdown the process performance by utilizing more disk IO. Consider increasing amount of available RAM limit or decreasing the load on the process.\n\nSee major page faults rate panel in Troubleshooting section if this metric continued to be high.",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
|
||||
@@ -2165,7 +2165,7 @@
|
||||
"type": "victoriametrics-metrics-datasource",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"description": "Shows memory pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\n**Lower is better.**\n\nPressure is measured as amount of time within 1sec time window the process was:\n- waiting: at least one thread was blocked on memory.\n- stalled: every thread was blocked on memory (severe pressure).\n\nElevated memory pressure can slowdown the process performance by utilizing more disk IO. Consider increasing amount of available RAM limit or decreasing the load on the process.\n\nSeу major page faults rate panel in Troubleshooting section if this metric continued to be high.",
|
||||
"description": "Shows memory pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\n**Lower is better.**\n\nPressure is measured as amount of time within 1sec time window the process was:\n- waiting: at least one thread was blocked on memory.\n- stalled: every thread was blocked on memory (severe pressure).\n\nElevated memory pressure can slowdown the process performance by utilizing more disk IO. Consider increasing amount of available RAM limit or decreasing the load on the process.\n\nSee major page faults rate panel in Troubleshooting section if this metric continued to be high.",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
@@ -6201,7 +6201,7 @@
|
||||
"type": "victoriametrics-metrics-datasource",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"description": "The rate of ignored samples during aggregation. \nStream aggregation will drop samples with NaN values, or samples with too old timestamps. See https://docs.victoriametrics.com/victoriametrics/stream-aggregation/#ignoring-old-samples ",
|
||||
"description": "The rate of dropped samples during aggregation. \nStream aggregation will drop samples with NaN values, too old timestamps or samples identified as duplicates during deduplication. See https://docs.victoriametrics.com/victoriametrics/stream-aggregation/#ignoring-old-samples ",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
@@ -6282,14 +6282,14 @@
|
||||
"uid": "$ds"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"expr": "sum(rate(vm_streamaggr_ignored_samples_total{job=~\"$job\",instance=~\"$instance\", url=~\"$url\"}[$__rate_interval]) > 0) without (instance, pod)",
|
||||
"expr": "sum(rate({__name__=~\"vm_streamaggr_ignored_samples_total|vm_streamaggr_dedup_dropped_samples_total\", job=~\"$job\",instance=~\"$instance\", url=~\"$url\"}[$__rate_interval]) > 0) without (instance, pod)",
|
||||
"instant": false,
|
||||
"legendFormat": "__auto",
|
||||
"range": true,
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Ignored samples ($instance)",
|
||||
"title": "Dropped samples ($instance)",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
|
||||
@@ -1840,7 +1840,7 @@
|
||||
"type": "victoriametrics-metrics-datasource",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"description": "Shows memory pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\n**Lower is better.**\n\nPressure is measured as amount of time within 1sec time window the process was:\n- waiting: at least one thread was blocked on memory.\n- stalled: every thread was blocked on memory (severe pressure).\n\nElevated memory pressure can slowdown the process performance by utilizing more disk IO. Consider increasing amount of available RAM limit or decreasing the load on the process.\n\nSeу major page faults rate panel in Troubleshooting section if this metric continued to be high.",
|
||||
"description": "Shows memory pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\n**Lower is better.**\n\nPressure is measured as amount of time within 1sec time window the process was:\n- waiting: at least one thread was blocked on memory.\n- stalled: every thread was blocked on memory (severe pressure).\n\nElevated memory pressure can slowdown the process performance by utilizing more disk IO. Consider increasing amount of available RAM limit or decreasing the load on the process.\n\nSee major page faults rate panel in Troubleshooting section if this metric continued to be high.",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
|
||||
@@ -2164,7 +2164,7 @@
|
||||
"type": "prometheus",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"description": "Shows memory pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\n**Lower is better.**\n\nPressure is measured as amount of time within 1sec time window the process was:\n- waiting: at least one thread was blocked on memory.\n- stalled: every thread was blocked on memory (severe pressure).\n\nElevated memory pressure can slowdown the process performance by utilizing more disk IO. Consider increasing amount of available RAM limit or decreasing the load on the process.\n\nSeу major page faults rate panel in Troubleshooting section if this metric continued to be high.",
|
||||
"description": "Shows memory pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\n**Lower is better.**\n\nPressure is measured as amount of time within 1sec time window the process was:\n- waiting: at least one thread was blocked on memory.\n- stalled: every thread was blocked on memory (severe pressure).\n\nElevated memory pressure can slowdown the process performance by utilizing more disk IO. Consider increasing amount of available RAM limit or decreasing the load on the process.\n\nSee major page faults rate panel in Troubleshooting section if this metric continued to be high.",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
@@ -6200,7 +6200,7 @@
|
||||
"type": "prometheus",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"description": "The rate of ignored samples during aggregation. \nStream aggregation will drop samples with NaN values, or samples with too old timestamps. See https://docs.victoriametrics.com/victoriametrics/stream-aggregation/#ignoring-old-samples ",
|
||||
"description": "The rate of dropped samples during aggregation. \nStream aggregation will drop samples with NaN values, too old timestamps or samples identified as duplicates during deduplication. See https://docs.victoriametrics.com/victoriametrics/stream-aggregation/#ignoring-old-samples ",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
@@ -6281,14 +6281,14 @@
|
||||
"uid": "$ds"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"expr": "sum(rate(vm_streamaggr_ignored_samples_total{job=~\"$job\",instance=~\"$instance\", url=~\"$url\"}[$__rate_interval]) > 0) without (instance, pod)",
|
||||
"expr": "sum(rate({__name__=~\"vm_streamaggr_ignored_samples_total|vm_streamaggr_dedup_dropped_samples_total\", job=~\"$job\",instance=~\"$instance\", url=~\"$url\"}[$__rate_interval]) > 0) without (instance, pod)",
|
||||
"instant": false,
|
||||
"legendFormat": "__auto",
|
||||
"range": true,
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Ignored samples ($instance)",
|
||||
"title": "Dropped samples ($instance)",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
|
||||
@@ -1839,7 +1839,7 @@
|
||||
"type": "prometheus",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"description": "Shows memory pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\n**Lower is better.**\n\nPressure is measured as amount of time within 1sec time window the process was:\n- waiting: at least one thread was blocked on memory.\n- stalled: every thread was blocked on memory (severe pressure).\n\nElevated memory pressure can slowdown the process performance by utilizing more disk IO. Consider increasing amount of available RAM limit or decreasing the load on the process.\n\nSeу major page faults rate panel in Troubleshooting section if this metric continued to be high.",
|
||||
"description": "Shows memory pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\n**Lower is better.**\n\nPressure is measured as amount of time within 1sec time window the process was:\n- waiting: at least one thread was blocked on memory.\n- stalled: every thread was blocked on memory (severe pressure).\n\nElevated memory pressure can slowdown the process performance by utilizing more disk IO. Consider increasing amount of available RAM limit or decreasing the load on the process.\n\nSee major page faults rate panel in Troubleshooting section if this metric continued to be high.",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
|
||||
@@ -3,9 +3,9 @@
|
||||
DOCKER_REGISTRIES ?= docker.io quay.io
|
||||
DOCKER_NAMESPACE ?= victoriametrics
|
||||
|
||||
ROOT_IMAGE ?= alpine:3.23.4
|
||||
ROOT_IMAGE ?= alpine:3.24.1
|
||||
ROOT_IMAGE_SCRATCH ?= scratch
|
||||
CERTS_IMAGE := alpine:3.23.4
|
||||
CERTS_IMAGE := alpine:3.24.1
|
||||
|
||||
GO_BUILDER_IMAGE := golang:1.26.4
|
||||
|
||||
|
||||
@@ -3,7 +3,7 @@ services:
|
||||
# It scrapes targets defined in --promscrape.config
|
||||
# And forward them to --remoteWrite.url
|
||||
vmagent:
|
||||
image: victoriametrics/vmagent:v1.145.0
|
||||
image: victoriametrics/vmagent:v1.146.0
|
||||
depends_on:
|
||||
- "vmauth"
|
||||
ports:
|
||||
@@ -42,14 +42,14 @@ services:
|
||||
# vmstorage shards. Each shard receives 1/N of all metrics sent to vminserts,
|
||||
# where N is number of vmstorages (2 in this case).
|
||||
vmstorage-1:
|
||||
image: victoriametrics/vmstorage:v1.145.0-cluster
|
||||
image: victoriametrics/vmstorage:v1.146.0-cluster
|
||||
volumes:
|
||||
- strgdata-1:/storage
|
||||
command:
|
||||
- "--storageDataPath=/storage"
|
||||
restart: always
|
||||
vmstorage-2:
|
||||
image: victoriametrics/vmstorage:v1.145.0-cluster
|
||||
image: victoriametrics/vmstorage:v1.146.0-cluster
|
||||
volumes:
|
||||
- strgdata-2:/storage
|
||||
command:
|
||||
@@ -59,7 +59,7 @@ services:
|
||||
# vminsert is ingestion frontend. It receives metrics pushed by vmagent,
|
||||
# pre-process them and distributes across configured vmstorage shards.
|
||||
vminsert-1:
|
||||
image: victoriametrics/vminsert:v1.145.0-cluster
|
||||
image: victoriametrics/vminsert:v1.146.0-cluster
|
||||
depends_on:
|
||||
- "vmstorage-1"
|
||||
- "vmstorage-2"
|
||||
@@ -68,7 +68,7 @@ services:
|
||||
- "--storageNode=vmstorage-2:8400"
|
||||
restart: always
|
||||
vminsert-2:
|
||||
image: victoriametrics/vminsert:v1.145.0-cluster
|
||||
image: victoriametrics/vminsert:v1.146.0-cluster
|
||||
depends_on:
|
||||
- "vmstorage-1"
|
||||
- "vmstorage-2"
|
||||
@@ -80,7 +80,7 @@ services:
|
||||
# vmselect is a query fronted. It serves read queries in MetricsQL or PromQL.
|
||||
# vmselect collects results from configured `--storageNode` shards.
|
||||
vmselect-1:
|
||||
image: victoriametrics/vmselect:v1.145.0-cluster
|
||||
image: victoriametrics/vmselect:v1.146.0-cluster
|
||||
depends_on:
|
||||
- "vmstorage-1"
|
||||
- "vmstorage-2"
|
||||
@@ -90,7 +90,7 @@ services:
|
||||
- "--vmalert.proxyURL=http://vmalert:8880"
|
||||
restart: always
|
||||
vmselect-2:
|
||||
image: victoriametrics/vmselect:v1.145.0-cluster
|
||||
image: victoriametrics/vmselect:v1.146.0-cluster
|
||||
depends_on:
|
||||
- "vmstorage-1"
|
||||
- "vmstorage-2"
|
||||
@@ -105,7 +105,7 @@ services:
|
||||
# read requests from Grafana, vmui, vmalert among vmselects.
|
||||
# It can be used as an authentication proxy.
|
||||
vmauth:
|
||||
image: victoriametrics/vmauth:v1.145.0
|
||||
image: victoriametrics/vmauth:v1.146.0
|
||||
depends_on:
|
||||
- "vmselect-1"
|
||||
- "vmselect-2"
|
||||
@@ -119,7 +119,7 @@ services:
|
||||
|
||||
# vmalert executes alerting and recording rules
|
||||
vmalert:
|
||||
image: victoriametrics/vmalert:v1.145.0
|
||||
image: victoriametrics/vmalert:v1.146.0
|
||||
depends_on:
|
||||
- "vmauth"
|
||||
ports:
|
||||
|
||||
@@ -3,7 +3,7 @@ services:
|
||||
# It scrapes targets defined in --promscrape.config
|
||||
# And forward them to --remoteWrite.url
|
||||
vmagent:
|
||||
image: victoriametrics/vmagent:v1.145.0
|
||||
image: victoriametrics/vmagent:v1.146.0
|
||||
depends_on:
|
||||
- "victoriametrics"
|
||||
ports:
|
||||
@@ -18,7 +18,7 @@ services:
|
||||
# VictoriaMetrics instance, a single process responsible for
|
||||
# storing metrics and serve read requests.
|
||||
victoriametrics:
|
||||
image: victoriametrics/victoria-metrics:v1.145.0
|
||||
image: victoriametrics/victoria-metrics:v1.146.0
|
||||
ports:
|
||||
- 8428:8428
|
||||
- 8089:8089
|
||||
@@ -59,7 +59,7 @@ services:
|
||||
|
||||
# vmalert executes alerting and recording rules
|
||||
vmalert:
|
||||
image: victoriametrics/vmalert:v1.145.0
|
||||
image: victoriametrics/vmalert:v1.146.0
|
||||
depends_on:
|
||||
- "victoriametrics"
|
||||
- "alertmanager"
|
||||
|
||||
@@ -223,4 +223,16 @@ groups:
|
||||
Unexpected TSID misses for \"{{ $labels.job }}\" ({{ $labels.instance }}) for the last 15 minutes.
|
||||
If this happens after unclean shutdown of VictoriaMetrics process (via \"kill -9\", OOM or power off),
|
||||
then this is OK - the alert must go away in a few minutes after the restart.
|
||||
Otherwise this may point to the corruption of index data.
|
||||
Otherwise this may point to the corruption of index data.
|
||||
|
||||
- alert: VMSelectConcurrentQueriesExceedMemoryLimit
|
||||
expr: (vm_max_memory_per_query * on(job, instance) vm_concurrent_select_capacity) > on(job, instance) vm_available_memory_bytes
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "vmselect ({{ $labels.instance }}) concurrent query memory may exceed pod limit"
|
||||
description: "Current concurrent queries ({{ $value | humanize1024 }} combined max memory) exceed
|
||||
the available memory on instance {{ $labels.instance }}.
|
||||
This may result in OOM kills. Consider reducing -maxConcurrentRequests,
|
||||
lowering -maxMemoryPerQuery, or scaling up pod memory limits."
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
services:
|
||||
vmagent:
|
||||
image: victoriametrics/vmagent:v1.145.0
|
||||
image: victoriametrics/vmagent:v1.146.0
|
||||
depends_on:
|
||||
- "victoriametrics"
|
||||
ports:
|
||||
@@ -14,7 +14,7 @@ services:
|
||||
restart: always
|
||||
|
||||
victoriametrics:
|
||||
image: victoriametrics/victoria-metrics:v1.145.0
|
||||
image: victoriametrics/victoria-metrics:v1.146.0
|
||||
ports:
|
||||
- 8428:8428
|
||||
volumes:
|
||||
@@ -40,7 +40,7 @@ services:
|
||||
restart: always
|
||||
|
||||
vmalert:
|
||||
image: victoriametrics/vmalert:v1.145.0
|
||||
image: victoriametrics/vmalert:v1.146.0
|
||||
depends_on:
|
||||
- "victoriametrics"
|
||||
ports:
|
||||
@@ -59,7 +59,7 @@ services:
|
||||
- '--external.alert.source=explore?orgId=1&left=["now-1h","now","VictoriaMetrics",{"expr": },{"mode":"Metrics"},{"ui":[true,true,true,"none"]}]'
|
||||
restart: always
|
||||
vmanomaly:
|
||||
image: victoriametrics/vmanomaly:v1.29.4
|
||||
image: victoriametrics/vmanomaly:v1.29.7
|
||||
depends_on:
|
||||
- "victoriametrics"
|
||||
ports:
|
||||
|
||||
@@ -43,7 +43,7 @@
|
||||
"content": "If you don't observe any data initially, please wait a few minutes for it to appear. \n\nUpon the first running the guide (if there is not enough node_exporter monitoring data collected in your system), you may notice a significant number of false positive anomalies found. The predictions will become more accurate with at least two weeks' (full `fit_window`) worth of data provided to vmanomaly.\n\nEach row displays information for a distinct mode. The query used for anomaly detection is `sum(rate(node_cpu_seconds_total[5m])) by (mode, instance, job)`.\n",
|
||||
"mode": "markdown"
|
||||
},
|
||||
"pluginVersion": "10.2.1",
|
||||
"pluginVersion": "12.2.0",
|
||||
"title": "Overview",
|
||||
"type": "text"
|
||||
},
|
||||
|
||||
@@ -32,6 +32,17 @@ docs-image:
|
||||
--platform $(DOCKER_PLATFORM) \
|
||||
vmdocs
|
||||
|
||||
docs-check-links: docs-image
|
||||
rm -rf vmdocs/public
|
||||
docker run \
|
||||
--rm \
|
||||
--platform $(DOCKER_PLATFORM) \
|
||||
-v ./vmdocs:/opt/docs \
|
||||
$(shell for d in ./docs/*/; do printf ' -v %s:/opt/docs/content/%s' "$${d}" "$$(basename $${d})"; done) \
|
||||
--entrypoint /bin/sh \
|
||||
vmdocs-docker-package \
|
||||
-c "yarn install && hugo --minify && yarn run check-links"
|
||||
|
||||
docs-debug: docs docs-image
|
||||
docker run \
|
||||
--rm \
|
||||
|
||||
@@ -14,6 +14,39 @@ aliases:
|
||||
---
|
||||
Please find the changelog for VictoriaMetrics Anomaly Detection below.
|
||||
|
||||
## v1.29.7
|
||||
Released: 2026-06-25
|
||||
|
||||
- UI: updated [vmanomaly UI](https://docs.victoriametrics.com/anomaly-detection/ui/) from [v1.7.1](https://docs.victoriametrics.com/anomaly-detection/ui/#v171) to [v1.7.2](https://docs.victoriametrics.com/anomaly-detection/ui/#v172), see respective [release notes](https://docs.victoriametrics.com/anomaly-detection/ui/#v172) for details. Notable mentions include `api/v1/server/model` endpoint for accessing production models config and queries from UI, manually or through [AI assistant](https://docs.victoriametrics.com/anomaly-detection/ui/#ai-assistance).
|
||||
|
||||
- IMPROVEMENT: Increased high-cardinality inference scaling by optionally scattering periodic infer jobs to reduce contention on shared resources (e.g. datasource, CPU, RAM) when `settings.n_workers > 1` and `scheduler.infer_every` is smaller than the total time to fetch and process all queries. This is controlled by new `scatter_infer_jobs` boolean argument of [Periodic Scheduler](https://docs.victoriametrics.com/anomaly-detection/components/scheduler/#parameters-1) (default: `false`).
|
||||
|
||||
- IMPROVEMENT: Optimized internal batching for reader post-fetch series processing, exposing reader processing queue depth (`vmanomaly_reader_processing_tasks_queued` [metric](https://docs.victoriametrics.com/anomaly-detection/components/monitoring/#reader-behaviour-metrics)), and clarifying inference skip logs after data fetch timeouts. See `series_processing_batch_size` argument of [VmReader](https://docs.victoriametrics.com/anomaly-detection/components/reader/#vm-reader) and [VLogsReader](https://docs.victoriametrics.com/anomaly-detection/components/reader/#victorialogs-reader) for details.
|
||||
|
||||
- IMPROVEMENT: Refined `VmReader` and `VLogsReader` logging after datasource request failures by suppressing the follow-up generic "No data" or "No unseen data" warning for failed fetches. Failed requests now keep the original datasource error while empty successful responses still emit the no-data warning.
|
||||
|
||||
## v1.29.6
|
||||
Released: 2026-06-17
|
||||
|
||||
- BUGFIX: Fixed `VLogsReader` startup and query execution when `tenant_id` is omitted or provided in short account-only form such as `"0"`. Omitted or empty tenant IDs are treated as single-node/no-tenant mode, and account-only tenant IDs are expanded to `accountID:0` before adding VictoriaLogs `AccountID`/`ProjectID` params or VM tenant labels.
|
||||
|
||||
- BUGFIX: Hardened [`OnlineMADModel`](https://docs.victoriametrics.com/anomaly-detection/components/models/#online-mad) anomaly scoring for perfectly constant time series (all values identical). The model now keeps a small deterministic prediction interval when the learned MAD is zero, so values deviating from an unknown constant baseline can produce `anomaly_score > 1` (previously, all anomaly scores were `0`).
|
||||
|
||||
## v1.29.5
|
||||
Released: 2026-06-11
|
||||
|
||||
- UI: Updated [vmanomaly UI](https://docs.victoriametrics.com/anomaly-detection/ui/) from [v1.7.0](https://docs.victoriametrics.com/anomaly-detection/ui/#v170) to [v1.7.1](https://docs.victoriametrics.com/anomaly-detection/ui/#v171), see respective [release notes](https://docs.victoriametrics.com/anomaly-detection/ui/#v171) for details.
|
||||
|
||||
- IMPROVEMENT: Redesigned [hot reload](https://docs.victoriametrics.com/anomaly-detection/components/#hot-reload) config change detection to content-based polling with configurable `-configCheckInterval`, improving reliability for Kubernetes ConfigMap symlink rotations and other filesystems where event delivery can be inconsistent.
|
||||
|
||||
- IMPROVEMENT: Refined config validation errors for broken or invalid config sections, so startup and reload failures point to the affected section more clearly (e.g. YAML indentation typos).
|
||||
|
||||
- IMPROVEMENT: Tightened config validation for [`PeriodicScheduler`](https://docs.victoriametrics.com/anomaly-detection/components/scheduler/#periodic-scheduler) `infer_every` and [`IsolationForestModel`](https://docs.victoriametrics.com/anomaly-detection/components/models/#isolation-forest-multivariate) `contamination`, including clearer handling of missing scheduler intervals, numeric contamination strings, and invalid non-finite values.
|
||||
|
||||
- BUGFIX: Fixed a multiprocessing startup issue with `settings.n_workers > 1` that could leave scheduled data fetch or successive inference jobs stuck and repeatedly skipped by internal scheduler.
|
||||
|
||||
- BUGFIX: Bounded [`VmReader`](https://docs.victoriametrics.com/anomaly-detection/components/reader/#vm-reader) and [`VLogsReader`](https://docs.victoriametrics.com/anomaly-detection/components/reader/#victorialogs-reader) data fetch and post-fetch processing waits so stalled datasource reads or multiprocessing dataframe creation no longer keep [`PeriodicScheduler`](https://docs.victoriametrics.com/anomaly-detection/components/scheduler/#periodic-scheduler) `data_fetch` jobs running indefinitely. Previously, such stuck jobs could keep internal scheduler's `max_instances=1` slot per (scheduler, query) pair occupied, causing future data fetch, fit, or infer runs to be skipped until vmanomaly was restarted. The config validator now also warns when the configured reader timeout budget can exceed the connected scheduler interval.
|
||||
|
||||
## v1.29.4
|
||||
Released: 2026-05-15
|
||||
|
||||
|
||||
@@ -423,7 +423,7 @@ services:
|
||||
# ...
|
||||
vmanomaly:
|
||||
container_name: vmanomaly
|
||||
image: victoriametrics/vmanomaly:v1.29.4
|
||||
image: victoriametrics/vmanomaly:v1.29.7
|
||||
# ...
|
||||
restart: always
|
||||
volumes:
|
||||
@@ -641,7 +641,7 @@ options:
|
||||
Here’s an example of using the config splitter to divide configurations based on the `extra_filters` argument from the reader section:
|
||||
|
||||
```sh
|
||||
docker pull victoriametrics/vmanomaly:v1.29.4 && docker image tag victoriametrics/vmanomaly:v1.29.4 vmanomaly
|
||||
docker pull victoriametrics/vmanomaly:v1.29.7 && docker image tag victoriametrics/vmanomaly:v1.29.7 vmanomaly
|
||||
```
|
||||
|
||||
```sh
|
||||
|
||||
@@ -45,8 +45,7 @@ There are 2 types of compatibility to consider when migrating in stateful mode:
|
||||
|
||||
| Group start | Group end | Compatibility | Notes |
|
||||
|---------|--------- |------------|-------|
|
||||
| [v1.29.3](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1293) | Latest* | Fully Compatible | Just a placeholder for new releases |
|
||||
| [v1.29.1](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1291) | [v1.29.3](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1293) | Fully Compatible | - |
|
||||
| [v1.29.1](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1291) | [v1.29.7](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1297) | Fully Compatible | - |
|
||||
| [v1.28.7](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1287) | [v1.29.0](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1290) | Partially compatible* | Dumped models of class [prophet](https://docs.victoriametrics.com/anomaly-detection/components/models/#prophet) and [seasonal quantile](https://docs.victoriametrics.com/anomaly-detection/components/models/#online-seasonal-quantile) have problems with loading to [v1.29.0](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1290) due to dropped `pytz` library. **Upgrading directly from v1.28.7 to [v1.29.1](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1291) with a fix is suggested** |
|
||||
| [v1.26.0](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1262) | [v1.28.7](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1287) | Fully Compatible | [v1.28.0](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1280) introduced [rolling](https://docs.victoriametrics.com/anomaly-detection/components/models/#rolling-models) model class drop in favor of [online](https://docs.victoriametrics.com/anomaly-detection/components/models/#online-models) models (`rolling_quantile` and `std` models), however, it does not impact compatibility, as artifacts were not produced by default for rolling models. Also, offline `mad` and `zscore` models are redirecting to their respective online counterparts since [v1.28.4](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1284). |
|
||||
| [v1.25.3](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1253) | [v1.26.0](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1270) | Partially Compatible* | [v1.25.3](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1253) introduced `forecast_at` argument for base [univariate](https://docs.victoriametrics.com/anomaly-detection/components/models/#univariate-models) and `Prophet` [models](https://docs.victoriametrics.com/anomaly-detection/components/models/#prophet), however, itself remains backward-reversible from newer states like [v1.26.2](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1262), [v1.27.0](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1270). (All models except `isolation_forest_multivariate` class will be dropped) |
|
||||
|
||||
@@ -37,29 +37,39 @@ The `vmanomaly` service supports a set of command-line arguments to configure it
|
||||
> Single-dashed command-line argument {{% available_from "v1.23.3" anomaly %}} format can be used, e.g. `-license.forceOffline` in addition to `--license.forceOffline`. This aligns better with other VictoriaMetrics ecosystem components. Mixing the two styles is also supported, e.g. `-license.forceOffline --loggerLevel INFO`.
|
||||
|
||||
```shellhelp
|
||||
usage: vmanomaly.py [-h] [--license STRING | --licenseFile PATH] [--license.forceOffline] [--loggerLevel {DEBUG,WARNING,FATAL,ERROR,INFO}] [--watch] [--dryRun] [--outputSpec PATH] config [config ...]
|
||||
usage: vmanomaly.py [-h] [--license STRING | --licenseFile PATH] [--license.forceOffline] [--loggerLevel {DEBUG,INFO,WARNING,ERROR,FATAL}] [--watch] [-configCheckInterval DURATION] [--dryRun] [--outputSpec PATH] config [config ...]
|
||||
|
||||
VictoriaMetrics Anomaly Detection Service
|
||||
|
||||
positional arguments:
|
||||
config YAML config file(s) or directories containing YAML files. Multiple files will recursively merge each other values so multiple configs can be combined. If a directory is provided,
|
||||
all `.yaml` files inside will be merged, without recursion. Default: vmanomaly.yaml is expected in the current directory.
|
||||
config YAML config file(s) or directories containing YAML files. Multiple files will recursively merge each other
|
||||
values so multiple configs can be combined. If a directory is provided, all `.yaml` files inside will be
|
||||
merged, without recursion. Default: vmanomaly.yaml is expected in the current directory.
|
||||
|
||||
options:
|
||||
-h Show this help message and exit
|
||||
--license STRING License key for VictoriaMetrics Enterprise. See https://victoriametrics.com/products/enterprise/trial/ to obtain a trial license.
|
||||
--licenseFile PATH Path to file with license key for VictoriaMetrics Enterprise. See https://victoriametrics.com/products/enterprise/trial/ to obtain a trial license.
|
||||
--license STRING License key for VictoriaMetrics Enterprise. See https://victoriametrics.com/products/enterprise/trial/ to
|
||||
obtain a trial license.
|
||||
--licenseFile PATH Path to file with license key for VictoriaMetrics Enterprise. See
|
||||
https://victoriametrics.com/products/enterprise/trial/ to obtain a trial license.
|
||||
--license.forceOffline
|
||||
Whether to force offline verification for VictoriaMetrics Enterprise license key, which has been passed either via -license or via -licenseFile command-line flag. The issued
|
||||
license key must support offline verification feature. Contact info@victoriametrics.com if you need offline license verification.
|
||||
--loggerLevel {DEBUG,WARNING,FATAL,ERROR,INFO}
|
||||
Minimum level to log. Possible values: DEBUG, INFO, WARNING, ERROR, FATAL.
|
||||
--watch Watch config files for changes and trigger hot reloads. Watches the specified config file or directory for modifications, deletions, or additions. Upon detecting changes,
|
||||
triggers config reload. If new config validation fails, continues with previous valid config and state.
|
||||
--dryRun Validate only: parse + merge all YAML(s) and run schema checks, then exit. Does not require a license to run. Does not expose metrics, or launch vmanomaly service(s).
|
||||
Whether to force offline verification for VictoriaMetrics Enterprise license key, which has been passed either
|
||||
via -license or via -licenseFile command-line flag. The issued license key must support offline verification
|
||||
feature. Contact info@victoriametrics.com if you need offline license verification.
|
||||
--loggerLevel {DEBUG,INFO,WARNING,ERROR,FATAL}
|
||||
Minimum level to log. Possible values: {'DEBUG', 'INFO', 'WARNING', 'ERROR', 'FATAL'}.
|
||||
--watch Watch config files for changes and trigger hot reloads. Watches the specified config file or directory for
|
||||
modifications, deletions, or additions. Upon detecting changes, triggers config reload. If new config
|
||||
validation fails, continues with previous valid config and state.
|
||||
-configCheckInterval DURATION
|
||||
Interval for checking watched config files for content changes. Default: 30s.
|
||||
--dryRun Validate only: parse + merge all YAML(s) and run schema checks, then exit. Does not require a license to run.
|
||||
Does not expose metrics, or launch vmanomaly service(s).
|
||||
--outputSpec PATH Target location of .yaml output spec.
|
||||
```
|
||||
|
||||
{{% available_from "v1.29.5" anomaly %}} When `--watch` is enabled, config changes are detected by fixed-interval content polling instead of filesystem event delivery. The polling frequency is controlled by `-configCheckInterval` (default: `30s`). The same option can also be passed as `--configCheckInterval`, `--config.check.interval`, `--config-check-interval`, `--config_check_interval`, or in key-value form such as `configCheckInterval=30s`.
|
||||
|
||||
You can specify these options when running `vmanomaly` to fine-tune logging levels or handle licensing configurations, as per your requirements.
|
||||
|
||||
### Licensing
|
||||
@@ -122,7 +132,7 @@ Below are the steps to get `vmanomaly` up and running inside a Docker container:
|
||||
1. Pull Docker image:
|
||||
|
||||
```sh
|
||||
docker pull victoriametrics/vmanomaly:v1.29.4
|
||||
docker pull victoriametrics/vmanomaly:v1.29.7
|
||||
```
|
||||
|
||||
2. Create the license file with your license key.
|
||||
@@ -142,7 +152,7 @@ docker run -it \
|
||||
-v ./license:/license \
|
||||
-v ./config.yaml:/config.yaml \
|
||||
-p 8490:8490 \
|
||||
victoriametrics/vmanomaly:v1.29.4 \
|
||||
victoriametrics/vmanomaly:v1.29.7 \
|
||||
/config.yaml \
|
||||
--licenseFile=/license \
|
||||
--loggerLevel=INFO \
|
||||
@@ -159,7 +169,7 @@ docker run -it \
|
||||
-e VMANOMALY_DATA_DUMPS_DIR=/tmp/vmanomaly/data \
|
||||
-e VMANOMALY_MODEL_DUMPS_DIR=/tmp/vmanomaly/models \
|
||||
-p 8490:8490 \
|
||||
victoriametrics/vmanomaly:v1.29.4 \
|
||||
victoriametrics/vmanomaly:v1.29.7 \
|
||||
/config.yaml \
|
||||
--licenseFile=/license \
|
||||
--loggerLevel=INFO \
|
||||
@@ -172,7 +182,7 @@ services:
|
||||
# ...
|
||||
vmanomaly:
|
||||
container_name: vmanomaly
|
||||
image: victoriametrics/vmanomaly:v1.29.4
|
||||
image: victoriametrics/vmanomaly:v1.29.7
|
||||
# ...
|
||||
restart: always
|
||||
volumes:
|
||||
@@ -257,6 +267,7 @@ schedulers:
|
||||
# https://docs.victoriametrics.com/anomaly-detection/components/scheduler/#periodic-scheduler
|
||||
class: 'periodic'
|
||||
infer_every: '5m'
|
||||
scatter_infer_jobs: true
|
||||
fit_every: '1d'
|
||||
fit_window: '4w'
|
||||
|
||||
@@ -288,6 +299,7 @@ reader:
|
||||
datasource_url: "https://play.victoriametrics.com/" # [YOUR_DATASOURCE_URL]
|
||||
tenant_id: '0:0'
|
||||
sampling_period: "5m"
|
||||
series_processing_batch_size: 8 # number of time series to process together while preparing data for fit or infer stages
|
||||
queries:
|
||||
# define your queries with MetricsQL - https://docs.victoriametrics.com/victoriametrics/metricsql/
|
||||
cpu_user:
|
||||
@@ -403,11 +415,13 @@ For optimal service behavior, consider the following tweaks when configuring `vm
|
||||
- Configure the **inference frequency** in the [scheduler](https://docs.victoriametrics.com/anomaly-detection/components/scheduler/) section of the configuration file.
|
||||
- Ensure that `infer_every` aligns with your **minimum required alerting frequency**.
|
||||
- For example, if receiving **alerts every 15 minutes** is sufficient (when `anomaly_score > 1`), set `infer_every` to match `reader.sampling_period` or override it per query via `reader.queries.query_xxx.step` for an optimal setup.
|
||||
- Set `scheduler.scatter_infer_jobs` {{% available_from "v1.29.7" anomaly %}} [arg](https://docs.victoriametrics.com/anomaly-detection/components/scheduler/#parameters-1) to `true` to allow for equal distribution of inference jobs across `infer_every` intervals, which can further enhance parallel processing efficiency and reduce resource contention when `reader.queries` contains a large number of queries.
|
||||
|
||||
**Reader**:
|
||||
- Setup the datasource to read data from in the [reader](https://docs.victoriametrics.com/anomaly-detection/components/reader/) section. Include tenant ID if using a [cluster version of VictoriaMetrics](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/) (`multitenant` value {{% available_from "v1.16.2" anomaly %}} can be also used here).
|
||||
- Define queries for input data using [MetricsQL](https://docs.victoriametrics.com/victoriametrics/metricsql/) under `reader.queries` section. Note, it's possible to override reader-level arguments at query level for increased flexibility, e.g. specifying per-query [timezone](https://docs.victoriametrics.com/anomaly-detection/faq/#handling-timezones) or [sampling period](https://docs.victoriametrics.com/anomaly-detection/components/reader/#config-parameters).
|
||||
- For longer `fit_window` intervals in scheduler, consider splitting queries into smaller time ranges to avoid excessive memory usage, timeouts and hitting server-side constraints, so they can be queried separately and reconstructed on `vmanomaly` side. Please refer to this [example](https://docs.victoriametrics.com/anomaly-detection/faq/#handling-large-queries-in-vmanomaly) for more details.
|
||||
- Set `reader.series_processing_batch_size` {{% available_from "v1.29.7" anomaly %}} [arg](https://docs.victoriametrics.com/anomaly-detection/components/reader/#config-parameters) to a reasonable value (4-16, default is 8) to balance between memory usage and processing speed when preparing data for fit or infer stages.
|
||||
|
||||
> If applicable - consider [`VLogsReader`](https://docs.victoriametrics.com/anomaly-detection/components/reader/#victorialogs-reader) {{% available_from "v1.26.0" anomaly %}} to perform anomaly detection on **log-derived metrics**. This is particularly useful for scenarios where log data needs to be analyzed for unusual patterns or behaviors, such as error rates or request latencies.
|
||||
|
||||
|
||||
@@ -315,7 +315,7 @@ docker run -it --rm \
|
||||
-e VMANOMALY_MCP_SERVER_URL=http://mcp-vmanomaly:8081/mcp \
|
||||
-p 8080:8080 \
|
||||
-p 8490:8490 \
|
||||
victoriametrics/vmanomaly:v1.29.4 \
|
||||
victoriametrics/vmanomaly:v1.29.7 \
|
||||
vmanomaly_config.yaml
|
||||
```
|
||||
|
||||
@@ -640,6 +640,32 @@ If the **results** look good and the **model configuration should be deployed in
|
||||
|
||||
## Changelog
|
||||
|
||||
### v1.7.2
|
||||
Released: 2026-06-25
|
||||
|
||||
vmanomaly version: [v1.29.7](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1297)
|
||||
|
||||
- FEATURE: Added controls for selecting server-configured scheduled models (drop-down inside [model wizard](#model-panel)) and browsing scheduled queries from the running vmanomaly instance ("Queries" button, "scheduled queries" tab).
|
||||
|
||||
- IMPROVEMENT: Surfaced datasource fetch failures from ad-hoc VMUI raw queries as query-level errors instead of returning a successful empty result that triggers a generic "No match" warning. Now the user can see the actual error message from the datasource (e.g. "unauthorized", "not found", etc.) and take appropriate action.
|
||||
|
||||
- BUGFIX: Fixed [UI/query-server](#settings-panel) handling of VictoriaMetrics datasource URLs that already include `/select/multitenant/prometheus`. Such URLs are now recognized as cluster datasource URLs, preserving the multitenant path when proxying VMUI requests and allowing `server.use_reader_connection_settings` to reuse [configured reader credentials for authenticated datasources](#authentication).
|
||||
|
||||
- BUGFIX: Fixed [settings](#settings-panel) inputs for server and datasource URLs so editing, deleting, or pasting text is no longer immediately reverted to the previous value before applying changes.
|
||||
|
||||
- BUGFIX: Fixed [model wizard](#model-panel) settings for [`IsolationForestModel`](https://docs.victoriametrics.com/anomaly-detection/components/models/#isolation-forest-multivariate) `contamination`, allowing decimal float values such as `0.1` or `0,1` to be typed or pasted without being collapsed to `0`, while preserving the `"auto"` value.
|
||||
|
||||
### v1.7.1
|
||||
Released: 2026-06-11
|
||||
|
||||
vmanomaly version: [v1.29.5](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1295)
|
||||
|
||||
- FEATURE: Added bulk Apply/Decline actions for [Copilot](#ai-assistance) chat suggestions.
|
||||
|
||||
- BUGFIX: Fixed modal windows closing when the mouse is released outside the window during text selection.
|
||||
|
||||
- BUGFIX: Fixed tooltip hover behavior so tooltips do not disappear while the cursor moves into the hover content.
|
||||
|
||||
### v1.7.0
|
||||
Released: 2026-05-15
|
||||
|
||||
|
||||
@@ -49,6 +49,7 @@ schedulers:
|
||||
periodic_online: # alias
|
||||
class: 'periodic' # scheduler class
|
||||
infer_every: "30s" # how often to produce anomaly scores for new data
|
||||
scatter_infer_jobs: true # distribute infer jobs evenly across the infer interval to reduce synchronized bursts
|
||||
fit_every: "365d" # how often to re-fit the models, for online models used effectively once, then they are updated with new data and won't require re-fit
|
||||
fit_window: "3d" # how much historical data to use for fit stage
|
||||
start_from: "00:00" # start from specified time, i.e. 00:00 given timezone and do daily fits as `fit_every` is 1 day
|
||||
@@ -56,6 +57,7 @@ schedulers:
|
||||
periodic_offline_1w:
|
||||
class: 'periodic'
|
||||
infer_every: "15m"
|
||||
scatter_infer_jobs: true
|
||||
fit_every: "24h"
|
||||
fit_window: "14d"
|
||||
# if no start_from is specified, jobs will start immediately after service starts
|
||||
@@ -135,6 +137,7 @@ server:
|
||||
port: 8490
|
||||
path_prefix: '/vmanomaly' # optional path prefix for all HTTP routes
|
||||
max_concurrent_tasks: 4 # maximum number of concurrent anomaly detection tasks processed by backend
|
||||
use_reader_connection_settings: True # if True, use reader's datasource_url and credentials for UI requests to datasource
|
||||
uvicorn_config: # optional Uvicorn server configuration
|
||||
log_level: 'warning'
|
||||
```
|
||||
@@ -143,11 +146,14 @@ server:
|
||||
|
||||
> This feature is better used in conjunction with [stateful service](https://docs.victoriametrics.com/anomaly-detection/components/settings/#state-restoration) to preserve the state of the models and schedulers between restarts and reuse what can be reused, thus avoiding unnecessary re-training of models, re-initialization of schedulers and re-reading of data.
|
||||
|
||||
{{% available_from "v1.25.0" anomaly %}} Service supports hot reload of configuration files, which allows for automatic reloading of configurations on config files change filesystem events without the need of explicit service restart. This can be enabled via the `--watch` [CLI argument](https://docs.victoriametrics.com/anomaly-detection/quickstart/#command-line-arguments). `vmanomaly_config_reload_enabled` flag in [self-monitoring metrics](https://docs.victoriametrics.com/anomaly-detection/components/monitoring/#startup-metrics) will be set to 1 (if enabled) or 0 (if disabled).
|
||||
{{% available_from "v1.25.0" anomaly %}} Service supports hot reload of configuration files, which allows for automatic reloading of configurations on config files change without the need of explicit service restart. This can be enabled via the `--watch` [CLI argument](https://docs.victoriametrics.com/anomaly-detection/quickstart/#command-line-arguments). `vmanomaly_config_reload_enabled` flag in [self-monitoring metrics](https://docs.victoriametrics.com/anomaly-detection/components/monitoring/#startup-metrics) will be set to 1 (if enabled) or 0 (if disabled).
|
||||
|
||||
> [!NOTE]
|
||||
> {{% deprecated_from "v1.29.5" anomaly %}} File system event-based hot reload has been deprecated in favor of content-based polling with configurable `-configCheckInterval` due to reliability issues with Kubernetes ConfigMap symlink rotations and other filesystems where event delivery can be inconsistent. If you were using file system event-based hot reload, please switch to content-based polling by enabling `--watch` flag and configuring `-configCheckInterval` as needed.
|
||||
|
||||
### How it works
|
||||
|
||||
It works by watching for file system events, such as modifications, creations, or deletions of `.yml|.yaml` files in the specified directories. When a change is detected, the service will attempt to reload the configuration files, rebuild the [global config](https://docs.victoriametrics.com/anomaly-detection/scaling-vmanomaly/#global-configuration) and reinitialize the components. If the reload is successful, the `vmanomaly_config_reloads_total` metric will be incremented for `status="success"` label, otherwise it will be incremented with `status="failure"` label and a respective error message on config validation failure(s) will be logged.
|
||||
It works by checking watched `.yml|.yaml` file contents in the specified files or directories on the configured interval `-configCheckInterval` (default is `30s`) {{% available_from "v1.29.5" anomaly %}}. When a content change is detected, the service will attempt to reload the configuration files after the existing debounce window, rebuild the [global config](https://docs.victoriametrics.com/anomaly-detection/scaling-vmanomaly/#global-configuration) and reinitialize the components. If the reload is successful, the `vmanomaly_config_reloads_total` metric will be incremented for `status="success"` label, otherwise it will be incremented with `status="failure"` label and a respective error message on config validation failure(s) will be logged.
|
||||
|
||||
> If the reload fails, the service will log an error message indicating the reason for the failure, and the **previous configuration will remain active until a successful reload occurs** to preserve the service's stability. This means that if there are errors in the new configuration, the service will continue to operate with the last valid configuration until the issues are resolved.
|
||||
|
||||
|
||||
@@ -449,9 +449,9 @@ models:
|
||||
|
||||
> The `decay` argument works only in combination with [online models](#online-models) like [`ZScoreOnlineModel`](#online-z-score) or [`OnlineQuantileModel`](#online-seasonal-quantile).
|
||||
|
||||
The `decay` {{% available_from "v1.23.0" anomaly %}} argument is used to control the (exponential) **decay factor** for online models, which determines how quickly the model adapts to new data. It is a float value between `0.0` and `1.0`, where:
|
||||
- `1.0` means no decay (the model treats all data equally, without giving more weight to recent data). This is the default value for backward compatibility.
|
||||
- Less than `1.0` means that the model will give more weight to recent data, effectively "forgetting" older data over time.
|
||||
The `decay` {{% available_from "v1.23.0" anomaly %}} argument is used to control the (exponential) **decay factor** for online models, which determines how quickly the model adapts to new data. It is a positive float value from `(0.0, 1.0]` interval, where:
|
||||
- Value `1.0` means no decay (the model treats all data points equally, without giving more weight to recent ones). This is the default value for backward compatibility.
|
||||
- Values less than `1.0` mean that the model will give more weight to recent data, effectively "forgetting" older data over time.
|
||||
|
||||
Roughly speaking, for the recent N datapoints model processes `decay` = `d` means that these datapoints will contribute to the model as [1 - d^X] percent of total importance, for example decay of
|
||||
- `0.99` means that 100 recent datapoints will contribute as [1 - 0.99^100] = 63.23% of total importance
|
||||
@@ -998,7 +998,7 @@ Here we use Isolation Forest implementation from `scikit-learn` [library](https:
|
||||
|
||||
* `class` (string) - model class name `"model.isolation_forest.IsolationForestMultivariateModel"` (or `isolation_forest_multivariate` with class alias support {{% available_from "v1.13.0" anomaly %}})
|
||||
|
||||
* `contamination` (float or string, optional) - The amount of contamination of the data set, i.e. the proportion of outliers in the data set. Used when fitting to define the threshold on the scores of the samples. Default value - "auto". Should be either `"auto"` or be in the range (0.0, 0.5].
|
||||
* `contamination` (float or string, optional) - The amount of contamination of the data set, i.e. the proportion of outliers in the data set. Used when fitting to define the threshold on the scores of the samples. Default value - "auto". Should be either `"auto"` or be in the range (0.0, 0.5]. {{% available_from "v1.29.5" anomaly %}} Numeric strings, such as `"0.01"`, are accepted, while invalid non-finite values, such as `nan`, `inf`, and `-inf`, are rejected during config validation.
|
||||
|
||||
* `seasonal_features` (list of string) - List of seasonality to encode through [cyclical encoding](https://towardsdatascience.com/cyclical-features-encoding-its-about-time-ce23581845ca), i.e. `dow` (day of week). **Introduced in [1.12.0](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1120)**.
|
||||
- Empty by default for backward compatibility.
|
||||
@@ -1265,7 +1265,7 @@ monitoring:
|
||||
Let's pull the docker image for `vmanomaly`:
|
||||
|
||||
```sh
|
||||
docker pull victoriametrics/vmanomaly:v1.29.4
|
||||
docker pull victoriametrics/vmanomaly:v1.29.7
|
||||
```
|
||||
|
||||
Now we can run the docker container putting as volumes both config and model file:
|
||||
@@ -1279,7 +1279,7 @@ docker run -it \
|
||||
-v $(PWD)/license:/license \
|
||||
-v $(PWD)/custom_model.py:/vmanomaly/model/custom.py \
|
||||
-v $(PWD)/custom.yaml:/config.yaml \
|
||||
victoriametrics/vmanomaly:v1.29.4 /config.yaml \
|
||||
victoriametrics/vmanomaly:v1.29.7 /config.yaml \
|
||||
--licenseFile=/license
|
||||
--watch
|
||||
```
|
||||
|
||||
@@ -458,6 +458,21 @@ Label names [description](#labelnames)
|
||||
<td>The total number of datapoints received from VictoriaMetrics for the `query_key` query within the specified scheduler `scheduler_alias`, in the `vmanomaly` service running in `preset` mode.</td>
|
||||
<td>
|
||||
|
||||
`url`, `query_key`, `scheduler_alias`, `preset`
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>
|
||||
|
||||
<span style="white-space: nowrap;">`vmanomaly_reader_processing_tasks_queued`</span>
|
||||
</td>
|
||||
<td>
|
||||
|
||||
`Gauge`
|
||||
</td>
|
||||
<td>The total number of queued processing tasks {{% available_from "v1.29.7" anomaly %}} (timeseries batches of size `series_processing_batch_size`) for the `query_key` query within the specified scheduler `scheduler_alias`, in the `vmanomaly` service running in `preset` mode. If continuously >0, it may lead to skipped infer runs due to resource contention and timeouts.</td>
|
||||
<td>
|
||||
|
||||
`url`, `query_key`, `scheduler_alias`, `preset`
|
||||
</td>
|
||||
</tr>
|
||||
|
||||
@@ -421,7 +421,20 @@ Optional argument{{% available_from "v1.18.1" anomaly %}} allows defining **vali
|
||||
`60s`
|
||||
</td>
|
||||
<td>
|
||||
Optional argument{{% available_from "v1.25.3" anomaly %}} allows specifying a time offset for all queries in `queries`. Defaults to `0s` (0) if not set and can be overridden on a [per-query basis](#per-query-parameters).
|
||||
Optional argument {{% available_from "v1.25.3" anomaly %}}, allows specifying a time offset for all queries in `queries`. Defaults to `0s` (0) if not set and can be overridden on a [per-query basis](#per-query-parameters).
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>
|
||||
|
||||
<span style="white-space: nowrap;">`series_processing_batch_size`</span>
|
||||
</td>
|
||||
<td>
|
||||
|
||||
`8`
|
||||
</td>
|
||||
<td>
|
||||
Optional argument {{% available_from "v1.29.7" anomaly %}}, allows specifying the number of time series to process together while preparing data for fit or infer stages. Defaults to `8`. Suggested values are 4-16 for high-cardinality queries.
|
||||
</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
@@ -450,6 +463,7 @@ reader:
|
||||
sampling_period: '1m'
|
||||
query_from_last_seen_timestamp: True # false by default
|
||||
latency_offset: '1ms'
|
||||
series_processing_batch_size: 8
|
||||
```
|
||||
|
||||
### MetricsQL Playground
|
||||
@@ -879,6 +893,19 @@ If a path to a CA bundle file (like `ca.crt`), it will verify the certificate us
|
||||
(Optional) Password for authentication. If set, it will be used to authenticate the request.
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>
|
||||
|
||||
<span style="white-space: nowrap;">`series_processing_batch_size`</span>
|
||||
</td>
|
||||
<td>
|
||||
|
||||
`8`
|
||||
</td>
|
||||
<td>
|
||||
Optional argument {{% available_from "v1.29.7" anomaly %}}, allows specifying the number of time series to process together while preparing data for fit or infer stages. Defaults to `8`. Suggested values are 4-16 for high-cardinality queries.
|
||||
</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
||||
@@ -897,6 +924,7 @@ reader:
|
||||
# tenant_id: '0:0' # for cluster version only
|
||||
sampling_period: '1m'
|
||||
max_points_per_query: 10000
|
||||
series_processing_batch_size: 8
|
||||
data_range: [0, 'inf'] # reader-level
|
||||
offset: '0s' # reader-level
|
||||
timeout: '30s'
|
||||
|
||||
@@ -74,40 +74,7 @@ options={`"scheduler.periodic.PeriodicScheduler"`, `"scheduler.oneoff.OneoffSche
|
||||
|
||||
### Parameters
|
||||
|
||||
For periodic scheduler parameters are defined as differences in times, expressed in difference units, e.g. days, hours, minutes, seconds.
|
||||
|
||||
Examples: `"50s"`, `"4m"`, `"3h"`, `"2d"`, `"1w"`.
|
||||
|
||||
<table class="params">
|
||||
<thead>
|
||||
<tr>
|
||||
<th></th>
|
||||
<th>Time granularity</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td>s</td>
|
||||
<td>seconds</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>m</td>
|
||||
<td>minutes</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>h</td>
|
||||
<td>hours</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>d</td>
|
||||
<td>days</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>w</td>
|
||||
<td>weeks</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
For periodic scheduler parameters are defined as differences in times, expressed in difference units, e.g. days, hours, minutes, seconds. Time granularity is defined by the last characters of a string. Examples: `"50s"` (seconds), `"4m"` (minutes), `"3h"` (hours), `"2d"` (days), `"1w"` (weeks).
|
||||
|
||||
<table class="params">
|
||||
<thead>
|
||||
@@ -188,6 +155,21 @@ Specifies when to initiate the first `fit_every` call. Accepts either an ISO 860
|
||||
Defines the local timezone for the `start_from` parameter, if specified. Defaults to `UTC` if no timezone is provided.
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>
|
||||
|
||||
<span style="white-space: nowrap;">`scatter_infer_jobs`{{% available_from "v1.29.7" anomaly %}}</span>
|
||||
</td>
|
||||
<td>bool, <span style="white-space: nowrap;">Optional</span></td>
|
||||
<td>
|
||||
|
||||
`true` or `false`
|
||||
</td>
|
||||
<td>
|
||||
|
||||
If `true`, distribute infer jobs and their dependent data-fetch jobs evenly across the infer interval. This reduces synchronized read and inference bursts for high-scale configurations. Defaults to `false`. Useful when `settings.n_workers > 1`, `reader.queries` cardinality is high, and `scheduler.infer_every` is small.
|
||||
</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
||||
@@ -200,6 +182,7 @@ schedulers:
|
||||
# (or class: "scheduler.periodic.PeriodicScheduler" for versions before v1.13.0, without class alias support)
|
||||
fit_window: "14d"
|
||||
infer_every: "1m"
|
||||
scatter_infer_jobs: true # Distribute infer jobs evenly across the infer interval to reduce synchronized bursts.
|
||||
fit_every: "1h"
|
||||
start_from: "20:00" # If launched before 20:00 (local Kyiv time), the first run starts today at 20:00. Otherwise, it starts tomorrow at 20:00.
|
||||
tz: "Europe/Kyiv" # Defaults to 'UTC' if not specified.
|
||||
|
||||
@@ -10,12 +10,12 @@ sitemap:
|
||||
|
||||
- To use *vmanomaly*, part of the enterprise package, a license key is required. Obtain your key [here](https://victoriametrics.com/products/enterprise/trial/) for this tutorial or for enterprise use.
|
||||
- In the tutorial, we'll be using the following VictoriaMetrics components:
|
||||
- [VictoriaMetrics Single-Node](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/) (v1.137.0)
|
||||
- [vmalert](https://docs.victoriametrics.com/victoriametrics/vmalert/) (v1.137.0)
|
||||
- [vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/) (v1.137.0)
|
||||
- [Grafana](https://grafana.com/) (v.10.2.1)
|
||||
- [VictoriaMetrics Single-Node](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/) (v1.146.0)
|
||||
- [vmalert](https://docs.victoriametrics.com/victoriametrics/vmalert/) (v1.146.0)
|
||||
- [vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/) (v1.146.0)
|
||||
- [Grafana](https://grafana.com/) (v12.2.0)
|
||||
- [Docker](https://docs.docker.com/get-docker/) and [Docker Compose](https://docs.docker.com/compose/)
|
||||
- [Node exporter](https://github.com/prometheus/node_exporter#node-exporter) (v1.7.0) and [Alertmanager](https://prometheus.io/docs/alerting/latest/alertmanager/) (v0.27.0)
|
||||
- [Node exporter](https://github.com/prometheus/node_exporter#node-exporter) (v1.9.1) and [Alertmanager](https://prometheus.io/docs/alerting/latest/alertmanager/) (v0.28.1)
|
||||
|
||||

|
||||
|
||||
@@ -323,7 +323,7 @@ Let's wrap it all up together into the `docker-compose.yml` file.
|
||||
services:
|
||||
vmagent:
|
||||
container_name: vmagent
|
||||
image: victoriametrics/vmagent:v1.137.0
|
||||
image: victoriametrics/vmagent:v1.146.0
|
||||
depends_on:
|
||||
- "victoriametrics"
|
||||
ports:
|
||||
@@ -340,7 +340,7 @@ services:
|
||||
|
||||
victoriametrics:
|
||||
container_name: victoriametrics
|
||||
image: victoriametrics/victoria-metrics:v1.137.0
|
||||
image: victoriametrics/victoria-metrics:v1.146.0
|
||||
ports:
|
||||
- 8428:8428
|
||||
volumes:
|
||||
@@ -356,7 +356,7 @@ services:
|
||||
|
||||
grafana:
|
||||
container_name: grafana
|
||||
image: grafana/grafana-oss:10.2.1
|
||||
image: grafana/grafana:12.2.0
|
||||
depends_on:
|
||||
- "victoriametrics"
|
||||
ports:
|
||||
@@ -373,7 +373,7 @@ services:
|
||||
|
||||
vmalert:
|
||||
container_name: vmalert
|
||||
image: victoriametrics/vmalert:v1.137.0
|
||||
image: victoriametrics/vmalert:v1.146.0
|
||||
depends_on:
|
||||
- "victoriametrics"
|
||||
ports:
|
||||
@@ -395,7 +395,7 @@ services:
|
||||
restart: always
|
||||
vmanomaly:
|
||||
container_name: vmanomaly
|
||||
image: victoriametrics/vmanomaly:v1.29.4
|
||||
image: victoriametrics/vmanomaly:v1.29.7
|
||||
depends_on:
|
||||
- "victoriametrics"
|
||||
ports:
|
||||
@@ -412,7 +412,7 @@ services:
|
||||
- "--licenseFile=/license"
|
||||
alertmanager:
|
||||
container_name: alertmanager
|
||||
image: prom/alertmanager:v0.27.0
|
||||
image: prom/alertmanager:v0.28.1
|
||||
volumes:
|
||||
- ./alertmanager.yml:/config/alertmanager.yml
|
||||
command:
|
||||
@@ -424,7 +424,7 @@ services:
|
||||
restart: always
|
||||
|
||||
node-exporter:
|
||||
image: quay.io/prometheus/node-exporter:v1.7.0
|
||||
image: quay.io/prometheus/node-exporter:v1.9.1
|
||||
container_name: node-exporter
|
||||
ports:
|
||||
- 9100:9100
|
||||
|
||||
@@ -240,23 +240,23 @@ vmagent will write data into VictoriaMetrics single-node and cluster (with tenan
|
||||
# compose.yaml
|
||||
services:
|
||||
vmsingle:
|
||||
image: victoriametrics/victoria-metrics:v1.145.0
|
||||
image: victoriametrics/victoria-metrics:v1.146.0
|
||||
|
||||
vmstorage:
|
||||
image: victoriametrics/vmstorage:v1.145.0-cluster
|
||||
image: victoriametrics/vmstorage:v1.146.0-cluster
|
||||
|
||||
vminsert:
|
||||
image: victoriametrics/vminsert:v1.145.0-cluster
|
||||
image: victoriametrics/vminsert:v1.146.0-cluster
|
||||
command:
|
||||
- -storageNode=vmstorage:8400
|
||||
|
||||
vmselect:
|
||||
image: victoriametrics/vmselect:v1.145.0-cluster
|
||||
image: victoriametrics/vmselect:v1.146.0-cluster
|
||||
command:
|
||||
- -storageNode=vmstorage:8401
|
||||
|
||||
vmagent:
|
||||
image: victoriametrics/vmagent:v1.145.0
|
||||
image: victoriametrics/vmagent:v1.146.0
|
||||
volumes:
|
||||
- ./scrape.yaml:/etc/vmagent/config.yaml
|
||||
command:
|
||||
@@ -308,7 +308,7 @@ Now add the vmauth service to `compose.yaml`:
|
||||
# compose.yaml
|
||||
services:
|
||||
vmauth:
|
||||
image: docker.io/victoriametrics/vmauth:v1.145.0
|
||||
image: docker.io/victoriametrics/vmauth:v1.146.0
|
||||
ports:
|
||||
- 8427:8427
|
||||
volumes:
|
||||
|
||||
@@ -6,45 +6,348 @@ build:
|
||||
sitemap:
|
||||
disable: true
|
||||
---
|
||||
**Objective**
|
||||
|
||||
Setup Victoria Metrics Cluster with support of multiple retention periods within one installation.
|
||||
> [VictoriaMetrics Enterprise](https://docs.victoriametrics.com/victoriametrics/enterprise/) supports specifying multiple retentions for distinct sets of time series and tenants. If you are an Enterprise user, [configure multiple retentions directly through retention filters](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/#retention-filters) instead of following this guide.
|
||||
|
||||
**Enterprise Solution**
|
||||
This guide explains how to set up multiple retentions using an [open-source VictoriaMetrics Cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/).
|
||||
|
||||
[VictoriaMetrics Enterprise](https://docs.victoriametrics.com/victoriametrics/enterprise/) supports specifying multiple retentions
|
||||
for distinct sets of time series and [tenants](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/#multitenancy)
|
||||
via [retention filters](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/#retention-filters).
|
||||
## Overview
|
||||
|
||||
**Open Source Solution**
|
||||
VictoriaMetrics retains metrics by default for **1 month**. You can change data retention with the [`-retentionPeriod` command-line flag](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#retention), but this value applies to **all time series stored** on a given `vmstorage` node and cannot be customized per tenant or per metric in the open source version.
|
||||
|
||||
Community version of VictoriaMetrics supports only one retention period per `vmstorage` node via [-retentionPeriod](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#retention) command-line flag.
|
||||
The core idea of this guide is to run **separate logic groups of storages** (or even clusters) with individual `-retentionPeriod` settings, while still providing a single unified write and read path via vmagent and vmselect.
|
||||
|
||||
A multi-retention setup can be implemented by dividing a [victoriametrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/) into logical groups with different retentions.
|
||||
## Multi-Retention Architecture
|
||||
|
||||
Example:
|
||||
Setup should handle 3 different retention groups 3months, 1year and 3 years.
|
||||
Solution contains 3 groups of vmstorages + vminserts and one group of vmselects. Routing is done by [vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/)
|
||||
by [splitting data streams](https://docs.victoriametrics.com/victoriametrics/vmagent/#splitting-data-streams-among-multiple-systems).
|
||||
The [-retentionPeriod](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#retention) sets how long to keep the metrics.
|
||||
To support multiple retentions with the open source version of VictoriaMetrics cluster, you can split the cluster into several logical groups of storage nodes. Each group is configured with a different `-retentionPeriod` and receives only the data that must follow that retention.
|
||||
|
||||
The diagram below shows a proposed solution
|
||||
Each storage group is connected to a separate vminsert, while a shared vmselect layer queries across all storage groups so that dashboards and alerts continue to see a single unified VictoriaMetrics backend.
|
||||
|
||||

|
||||
|
||||
**Implementation Details**
|
||||
In the example used throughout this guide, the cluster is divided into three groups:
|
||||
|
||||
1. Groups of vminserts A know about only vmstorages A and this is explicitly specified via `-storageNode` [configuration](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/#cluster-setup).
|
||||
1. Groups of vminserts B know about only vmstorages B and this is explicitly specified via `-storageNode` [configuration](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/#cluster-setup).
|
||||
1. Groups of vminserts C know about only vmstorages C and this is explicitly specified via `-storageNode` [configuration](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/#cluster-setup).
|
||||
1. vmselect reads data from all vmstorage nodes via `-storageNode` [configuration](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/#cluster-setup)
|
||||
with [deduplication](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/#deduplication) setting equal to vmagent's scrape interval or minimum interval between collected samples.
|
||||
1. vmagent routes incoming metrics to the given set of `vminsert` nodes using relabeling rules specified at `-remoteWrite.urlRelabelConfig` [configuration](https://docs.victoriametrics.com/victoriametrics/relabeling/).
|
||||
- Group A: 3-month retention.
|
||||
- Group B: 1-year retention.
|
||||
- Group C: 3-year retention.
|
||||
|
||||
**Multi-Tenant Setup**
|
||||
Metrics are routed to the appropriate vminsert group by splitting data streams in vmagent, so each time series is sent to exactly one retention group instead of being replicated to all groups. See [Deploying vmagent](https://docs.victoriametrics.com/guides/guide-vmcluster-multiple-retention-setup/#step3) for an example of label‑based routing that implements this split. An optional [vmauth](https://docs.victoriametrics.com/guides/guide-vmcluster-multiple-retention-setup/#additional-enhancements) layer can be added on top to restrict access to specific sub‑clusters or tenants while still keeping a unified write and read path.
|
||||
|
||||
Every group of vmstorages can handle one tenant or multiple one. Different groups can have overlapping tenants. As vmselect reads from all vmstorage nodes, the data is aggregated on its level.
|
||||
## Implementing Multi-Retention on Kubernetes
|
||||
|
||||
**Additional Enhancements**
|
||||
In this section, we'll install and configure the components for a multi-retention deployment of the VictoriaMetrics cluster. See [Kubernetes monitoring with VictoriaMetrics Cluster](https://docs.victoriametrics.com/guides/k8s-monitoring-via-vm-cluster/) for details on running VictoriaMetrics in Kubernetes.
|
||||
|
||||
You can set up [vmauth](https://docs.victoriametrics.com/victoriametrics/vmauth/) for routing data to the given vminsert group depending on the needed retention.
|
||||
Run the following command to add the VictoriaMetrics Helm repository:
|
||||
|
||||
```shell
|
||||
helm repo add vm https://victoriametrics.github.io/helm-charts/
|
||||
helm repo update
|
||||
```
|
||||
|
||||
### Step 1: Deploying storage groups {#step1}
|
||||
|
||||
We'll create three storage groups. Each has a different retention period and disk size. Read [Understand Your Setup Size](https://docs.victoriametrics.com/guides/understand-your-setup-size/) to estimate how much space you will need for each group. The following table is shown as an example:
|
||||
|
||||
|
||||
| Group | Retention Period | Total disk size |
|
||||
|--------------|------------------|-----------------------|
|
||||
| `vmcluster-a` | 3 months (`3M`) | 80 Gi |
|
||||
| `vmcluster-b` | 1 year (`1Y`) | 300 Gi |
|
||||
| `vmcluster-c` | 3 years (`3Y`) | 900 Gi |
|
||||
|
||||
Create a Helm values file for Group A.
|
||||
|
||||
```shell
|
||||
cat <<EOF > vmcluster-a.yaml
|
||||
vmstorage:
|
||||
enabled: true
|
||||
replicaCount: 1
|
||||
persistence:
|
||||
size: 80Gi
|
||||
extraArgs:
|
||||
retentionPeriod: 3M
|
||||
podLabels:
|
||||
retention-group: a
|
||||
|
||||
vminsert:
|
||||
enabled: true
|
||||
podLabels:
|
||||
retention-group: a
|
||||
|
||||
vmselect:
|
||||
enabled: false
|
||||
EOF
|
||||
```
|
||||
|
||||
The values file above creates vminsert and vmstorage services while turning off vmselect, which we'll deploy separately. The `retentionPeriod` flag configures how long data is kept in this group.
|
||||
|
||||
Create the values files for Group B and Group C:
|
||||
|
||||
```shell
|
||||
cat <<EOF > vmcluster-b.yaml
|
||||
vmstorage:
|
||||
enabled: true
|
||||
replicaCount: 1
|
||||
persistence:
|
||||
size: 300Gi
|
||||
extraArgs:
|
||||
retentionPeriod: 1y
|
||||
podLabels:
|
||||
retention-group: b
|
||||
|
||||
vminsert:
|
||||
enabled: true
|
||||
podLabels:
|
||||
retention-group: b
|
||||
|
||||
vmselect:
|
||||
enabled: false
|
||||
EOF
|
||||
|
||||
|
||||
cat <<EOF > vmcluster-c.yaml
|
||||
vmstorage:
|
||||
enabled: true
|
||||
replicaCount: 1
|
||||
persistence:
|
||||
size: 900Gi
|
||||
extraArgs:
|
||||
retentionPeriod: 3y
|
||||
podLabels:
|
||||
retention-group: c
|
||||
|
||||
vminsert:
|
||||
enabled: true
|
||||
podLabels:
|
||||
retention-group: c
|
||||
|
||||
vmselect:
|
||||
enabled: false
|
||||
EOF
|
||||
```
|
||||
|
||||
Deploy the three storage groups with:
|
||||
|
||||
```shell
|
||||
helm upgrade --install vmcluster-a vm/victoria-metrics-cluster -f vmcluster-a.yaml
|
||||
helm upgrade --install vmcluster-b vm/victoria-metrics-cluster -f vmcluster-b.yaml
|
||||
helm upgrade --install vmcluster-c vm/victoria-metrics-cluster -f vmcluster-c.yaml
|
||||
|
||||
# Wait for all storage pods to be ready
|
||||
kubectl rollout status statefulset -l app.kubernetes.io/instance=vmcluster-a
|
||||
kubectl rollout status statefulset -l app.kubernetes.io/instance=vmcluster-b
|
||||
kubectl rollout status statefulset -l app.kubernetes.io/instance=vmcluster-c
|
||||
```
|
||||
|
||||
### Step 2: Deploying vmselect {#step2}
|
||||
|
||||
Next, we'll deploy a vmselect service to route queries to the storage groups.
|
||||
|
||||
Create a Helm values file with:
|
||||
|
||||
```shell
|
||||
cat <<EOF >vmselect.yaml
|
||||
vmstorage:
|
||||
enabled: false
|
||||
|
||||
vminsert:
|
||||
enabled: false
|
||||
|
||||
vmselect:
|
||||
enabled: true
|
||||
replicaCount: 1
|
||||
suppressStorageFQDNsRender: true
|
||||
extraArgs:
|
||||
# Each list item is a single -storageNode flag. In this example, there is
|
||||
# one vmstorage pod per retention group, so each entry contains a single host.
|
||||
# If you run multiple pods per group, list them as comma-separated hosts
|
||||
# in the same -storageNode value.
|
||||
#
|
||||
# The FQDN format is:
|
||||
# <pod>.<svc>.default.svc
|
||||
# where pod = <release>-victoria-metrics-cluster-vmstorage-<N>
|
||||
# and svc = <release>-victoria-metrics-cluster-vmstorage
|
||||
storageNode:
|
||||
- "vmcluster-a-victoria-metrics-cluster-vmstorage-0.vmcluster-a-victoria-metrics-cluster-vmstorage.default.svc:8401"
|
||||
- "vmcluster-b-victoria-metrics-cluster-vmstorage-0.vmcluster-b-victoria-metrics-cluster-vmstorage.default.svc:8401"
|
||||
- "vmcluster-c-victoria-metrics-cluster-vmstorage-0.vmcluster-c-victoria-metrics-cluster-vmstorage.default.svc:8401"
|
||||
EOF
|
||||
```
|
||||
|
||||
Let's break down the file above:
|
||||
|
||||
- Deploys vmselect as a separate Helm release.
|
||||
- Disables vminsert and vmstorage as these services were already deployed in Step 1.
|
||||
- `suppressStorageFQDNsRender: true` turns off automatic FQDN generation for storage nodes. By default, the Helm chart auto-generates `-storageNodes` flags, but since `vmstorage` has been disabled, we need to supply them manually in `extraArgs`.
|
||||
- In `extraArgs.storageNode:` we define the vmstorage endpoints for queries. On querying, vmselect merges results across all the specified vmstorages to provide a unified view of the data.
|
||||
|
||||
Deploy the `vmselect` release with:
|
||||
|
||||
```shell
|
||||
helm upgrade --install vmselect vm/victoria-metrics-cluster -f vmselect.yaml
|
||||
```
|
||||
|
||||
### Step 3: Deploying vmagent {#step3}
|
||||
|
||||
We'll use `vmagent` to route incoming metrics to the correct retention group. For example, we can use a `retention` label for mapping metrics to storage groups in the following way:
|
||||
|
||||
| `retention` label | Storage Group |
|
||||
|-------------------|--------------|
|
||||
| `"3mo"` | `vmcluster-a` |
|
||||
| `"1yr"` | `vmcluster-b` |
|
||||
| `"3yr"` | `vmcluster-c` |
|
||||
|
||||
|
||||
Create the values file for vmagent:
|
||||
|
||||
```shell
|
||||
cat <<EOF >vmagent.yaml
|
||||
service:
|
||||
enabled: true
|
||||
remoteWrite:
|
||||
# Group A: receives metrics with retention="3mo"
|
||||
- url: http://vmcluster-a-victoria-metrics-cluster-vminsert:8480/insert/0/prometheus/api/v1/write
|
||||
urlRelabelConfig:
|
||||
- if: '{retention="3mo"}'
|
||||
action: keep
|
||||
# Group B: receives metrics with retention="1yr"
|
||||
- url: http://vmcluster-b-victoria-metrics-cluster-vminsert:8480/insert/0/prometheus/api/v1/write
|
||||
urlRelabelConfig:
|
||||
- if: '{retention="1yr"}'
|
||||
action: keep
|
||||
# Group C: receives metrics with retention="3yr"
|
||||
- url: http://vmcluster-c-victoria-metrics-cluster-vminsert:8480/insert/0/prometheus/api/v1/write
|
||||
urlRelabelConfig:
|
||||
- if: '{retention="3yr"}'
|
||||
action: keep
|
||||
EOF
|
||||
```
|
||||
|
||||
> Metrics without a matching `retention` label are silently dropped by the `keep` rules. You must ensure that every metric is labeled, or use a different routing configuration.
|
||||
|
||||
Now deploy the vmagent release:
|
||||
|
||||
```shell
|
||||
helm upgrade --install vmagent vm/victoria-metrics-agent -f vmagent.yaml
|
||||
```
|
||||
|
||||
Wait for vmagent to become ready:
|
||||
|
||||
```shell
|
||||
kubectl rollout status deploy/vmagent-victoria-metrics-agent
|
||||
```
|
||||
|
||||
### Step 4: Verification
|
||||
|
||||
We can send test data to verify that the data is flowing to the correct storage group.
|
||||
|
||||
First, port-forward vmagent and vmselect:
|
||||
|
||||
```shell
|
||||
VMAGENT_SVC=$(kubectl get svc -l app.kubernetes.io/instance=vmagent -o jsonpath='{.items[0].metadata.name}')
|
||||
kubectl port-forward "svc/$VMAGENT_SVC" 8429 &
|
||||
|
||||
VMSELECT_SVC=$(kubectl get svc -l app.kubernetes.io/instance=vmselect -o jsonpath='{.items[0].metadata.name}')
|
||||
kubectl port-forward "svc/$VMSELECT_SVC" 8481 &
|
||||
```
|
||||
|
||||
Send test metrics directly to vmagent's HTTP endpoint to exercise all three retention labels:
|
||||
|
||||
```shell
|
||||
POD=$(kubectl get pod -l app.kubernetes.io/instance=vmagent -o jsonpath='{.items[0].metadata.name}')
|
||||
|
||||
for retention in 3mo 1yr 3yr; do
|
||||
kubectl exec "$POD" -- wget -qO- --post-data="test_routing{retention=\"${retention}\"} 1.0" \
|
||||
"http://127.0.0.1:8429/api/v1/import/prometheus"
|
||||
done
|
||||
```
|
||||
|
||||
Query the data back from vmselect (it may take around 30-60 seconds for new data to be available for queries):
|
||||
|
||||
```shell
|
||||
for retention in 3mo 1yr 3yr; do
|
||||
echo "-> retention=${retention}"
|
||||
curl -s "http://localhost:8481/select/0/prometheus/api/v1/query" \
|
||||
--data-urlencode "query=test_routing{retention=\"${retention}\"}"
|
||||
echo
|
||||
done
|
||||
```
|
||||
|
||||
You can also check that vmagent is forwarding data to all three groups:
|
||||
|
||||
```shell
|
||||
curl -s http://localhost:8429/metrics | grep vmagent_remotewrite_blocks_sent_total
|
||||
```
|
||||
|
||||
Each `url="N:secret-url"` corresponds to one `remoteWrite` entry (N=1 for Group A, N=2 for Group B, N=3 for Group C). Non-zero values confirm data is flowing.
|
||||
|
||||
## Alternative Routing by Existing Labels
|
||||
|
||||
The example setup above relies on a synthetic `retention` label to exist in every incoming metric.
|
||||
|
||||
If having a `retention` label in every metric isn't practical, you can, as an alternative, rely on existing labels to map data to the correct storage group.
|
||||
|
||||
The following example configures vmagent to route metrics based on the `environment` and `team` labels:
|
||||
|
||||
```yaml
|
||||
# vmagent.yaml
|
||||
remoteWrite:
|
||||
# send dev and staging data to Group A
|
||||
- url: "http://vmcluster-a-victoria-metrics-cluster-vminsert:8480/insert/0/prometheus/api/v1/write"
|
||||
urlRelabelConfig:
|
||||
- if: {environment=~"dev|staging"}
|
||||
action: keep
|
||||
# send prod data to Group B
|
||||
- url: "http://vmcluster-b-victoria-metrics-cluster-vminsert:8480/insert/0/prometheus/api/v1/write"
|
||||
urlRelabelConfig:
|
||||
- if: {environment=~"prod|production"}
|
||||
action: keep
|
||||
# send data from Infra and SRE teams to Group C
|
||||
- url: "http://vmcluster-c-victoria-metrics-cluster-vminsert:8480/insert/0/prometheus/api/v1/write"
|
||||
urlRelabelConfig:
|
||||
- if: {team=~"infra|sre"}
|
||||
action: keep
|
||||
```
|
||||
|
||||
> Metrics that do not match any of the `keep` rules are dropped in the configuration above.
|
||||
|
||||
## Additional Enhancements
|
||||
|
||||
You can set up [vmauth](https://docs.victoriametrics.com/victoriametrics/vmauth/) to route data to the specified vminsert group based on the required retention or to restrict which data different users can query.
|
||||
|
||||
The following [`-auth.config`](https://docs.victoriametrics.com/victoriametrics/vmauth/#quick-start) example exposes the same vmselect backend via vmauth with two users using basic auth:
|
||||
|
||||
- `admin`: can query **all** data across all retention groups.
|
||||
- `dev`: can query **only** time series that have `team="dev"` label, enforced via the `extra_label` query argument.
|
||||
|
||||
```yaml
|
||||
users:
|
||||
# User with access to all data across all retention groups
|
||||
- username: "admin"
|
||||
password: "foo"
|
||||
url_map:
|
||||
- src_paths:
|
||||
- "/api/v1/query"
|
||||
- "/api/v1/query_range"
|
||||
- "/api/v1/series"
|
||||
- "/api/v1/labels"
|
||||
- "/api/v1/label/.+/values"
|
||||
# vmselect service that aggregates all vmstorage groups
|
||||
url_prefix: "http://vmselect-victoria-metrics-cluster-vmselect:8481/select/0/prometheus"
|
||||
|
||||
# User restricted to Dev team data only
|
||||
- username: "dev"
|
||||
password: "bar"
|
||||
url_map:
|
||||
- src_paths:
|
||||
- "/api/v1/query"
|
||||
- "/api/v1/query_range"
|
||||
- "/api/v1/series"
|
||||
- "/api/v1/labels"
|
||||
- "/api/v1/label/.+/values"
|
||||
# Same vmselect backend, but enforce label filter at query time
|
||||
# by adding extra_label=team=dev to every proxied request
|
||||
url_prefix: "http://vmselect-victoria-metrics-cluster-vmselect:8481/select/0/prometheus/?extra_label=team=dev"
|
||||
```
|
||||
|
||||
This is useful for restricting access by team, environment, or tenant without changing the underlying storage topology.
|
||||
|
||||
@@ -155,15 +155,15 @@ These services will store and query the metrics scraped by vmagent.
|
||||
# compose.yaml
|
||||
services:
|
||||
vmstorage:
|
||||
image: victoriametrics/vmstorage:v1.145.0-cluster
|
||||
image: victoriametrics/vmstorage:v1.146.0-cluster
|
||||
|
||||
vminsert:
|
||||
image: victoriametrics/vminsert:v1.145.0-cluster
|
||||
image: victoriametrics/vminsert:v1.146.0-cluster
|
||||
command:
|
||||
- -storageNode=vmstorage:8400
|
||||
|
||||
vmselect:
|
||||
image: victoriametrics/vmselect:v1.145.0-cluster
|
||||
image: victoriametrics/vmselect:v1.146.0-cluster
|
||||
command:
|
||||
- -storageNode=vmstorage:8401
|
||||
ports:
|
||||
@@ -196,7 +196,7 @@ Add the vmauth service to `compose.yaml`:
|
||||
# compose.yaml
|
||||
services:
|
||||
vmauth:
|
||||
image: victoriametrics/vmauth:v1.145.0-enterprise
|
||||
image: victoriametrics/vmauth:v1.146.0-enterprise
|
||||
ports:
|
||||
- 8427:8427
|
||||
volumes:
|
||||
@@ -251,7 +251,7 @@ Add the vmagent service to `compose.yaml` with OAuth2 configuration:
|
||||
# compose.yaml
|
||||
services:
|
||||
vmagent:
|
||||
image: victoriametrics/vmagent:v1.145.0
|
||||
image: victoriametrics/vmagent:v1.146.0
|
||||
volumes:
|
||||
- ./scrape.yaml:/etc/vmagent/config.yaml
|
||||
command:
|
||||
|
||||
@@ -107,7 +107,7 @@ The final piece is the Docker Compose file. This ties all the services together
|
||||
# compose.yml
|
||||
services:
|
||||
victoriametrics:
|
||||
image: victoriametrics/victoria-metrics:v1.145.0
|
||||
image: victoriametrics/victoria-metrics:v1.146.0
|
||||
command:
|
||||
- "--storageDataPath=/victoria-metrics-data"
|
||||
- "--selfScrapeInterval=10s"
|
||||
@@ -128,7 +128,7 @@ services:
|
||||
- ./alertmanager.yml:/etc/alertmanager/alertmanager.yml:ro
|
||||
|
||||
vmalert:
|
||||
image: victoriametrics/vmalert:v1.145.0
|
||||
image: victoriametrics/vmalert:v1.146.0
|
||||
depends_on:
|
||||
- victoriametrics
|
||||
- alertmanager
|
||||
|
||||
@@ -19,6 +19,7 @@ See also [case studies](https://docs.victoriametrics.com/victoriametrics/casestu
|
||||
* [Datanami: Why Roblox Picked VictoriaMetrics for Observability Data Overhaul](https://www.hpcwire.com/bigdatawire/2023/05/30/why-roblox-picked-victoriametrics-for-observability-data-overhaul/)
|
||||
* [Cloudflare: Introducing notifications for HTTP Traffic Anomalies](https://blog.cloudflare.com/introducing-http-traffic-anomalies-notifications/)
|
||||
* [Grammarly: Better, Faster, Cheaper: How Grammarly Improved Monitoring by Over 10x with VictoriaMetrics](https://www.grammarly.com/blog/engineering/monitoring-with-victoriametrics/)
|
||||
* [Xata: How we rebuilt PostgreSQL branch metrics on VictoriaMetrics, per cell](https://xata.io/blog/how-we-rebuilt-postgresql-branch-metrics-on-victoriametrics-per-cell)
|
||||
* [CERN: CMS monitoring R&D: Real-time monitoring and alerts](https://indico.cern.ch/event/877333/contributions/3696707/attachments/1972189/3281133/CMS_mon_RD_for_opInt.pdf)
|
||||
* [CERN: The CMS monitoring infrastructure and applications](https://arxiv.org/pdf/2007.03630.pdf)
|
||||
* [Forbes: The (Almost) Infinitely Scalable Open Source Monitoring Dream](https://www.forbes.com/sites/adrianbridgwater/2022/08/16/the-almost-infinitely-scalable-open-source-monitoring-dream/)
|
||||
|
||||
@@ -28,7 +28,7 @@ If you like VictoriaMetrics and want to contribute, then it would be great:
|
||||
## Issues
|
||||
|
||||
When making a new issue, make sure to create no duplicates. Use GitHub search to find whether similar issues exist already.
|
||||
The new issue should be written in English and contain concise description of the problem and environment where it exists.
|
||||
The new issue should be written in English and contain a concise description of the problem and the environment where it exists.
|
||||
We'd very much prefer to have a specific use-case included in the description, since it could have workaround or alternative solutions.
|
||||
|
||||
When looking for an issue to contribute, always prefer working on [bugs](https://github.com/VictoriaMetrics/VictoriaMetrics/issues?q=is%3Aopen+is%3Aissue+label%3Abug)
|
||||
@@ -48,7 +48,7 @@ We use [labels](https://docs.github.com/en/issues/using-labels-and-milestones-to
|
||||
1. `need more info`, assigned to issues that require elaboration from the issue creator.
|
||||
For example, if we weren't able to reproduce the reported bug based on the ticket description then we ask additional
|
||||
questions which could help to reproduce the issue and add `need more info` label. This label helps other maintainers
|
||||
to understand that this issue wasn't forgotten but waits for the feedback from user.
|
||||
to understand that this issue wasn't forgotten but waits for the feedback from the user.
|
||||
1. `completed`, assigned to issues that required code changes and those changes were merged to upstream, but not released yet.
|
||||
Once a release is made, maintainers go through all labeled issues, leave a comment about the new release, and close the issue.
|
||||
1. `vmui`, assigned to issues related to [vmui](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#vmui) or [VictoriaLogs webui](https://docs.victoriametrics.com/victorialogs/querying/#web-ui)
|
||||
@@ -63,32 +63,46 @@ Pull requests requirements:
|
||||
1. Don't use `master` branch for making PRs, as it makes it impossible for reviewers to modify the changes.
|
||||
1. All commits need to be [signed](https://docs.github.com/en/authentication/managing-commit-signature-verification/signing-commits).
|
||||
1. Pull request title should be prefixed with `<dir>/<component>:` to show what component has been changed, i.e. `app/vmalert: fix...`.
|
||||
Pull request description should contain clear and concise description of what was done, why it is needed and for what purpose.
|
||||
Pull request description should contain a clear and concise description of what was done, why it is needed and for what purpose.
|
||||
Use clear language, so reviewers can quickly understand the change and its impact.
|
||||
1. A link to the issue(s) related to the change, if any. Use `Fixes [issue link]` if the PR resolves the issue, or `Related to [issue link]` for reference.
|
||||
1. Tests proving that the change is effective. Tests are expected for non-trivial new functionality or non-trivial modifications.
|
||||
Bug fixes must include tests unless a maintainer explicitly agrees otherwise.
|
||||
See [this style guide](https://itnext.io/f-tests-as-a-replacement-for-table-driven-tests-in-go-8814a8b19e9e) for tests.
|
||||
To run tests and code checks locally, execute commands `make test-full` and `make check-all`.
|
||||
See [this style guide](https://itnext.io/f-tests-as-a-replacement-for-table-driven-tests-in-go-8814a8b19e9e) for tests. See [this section](#testing) for how to run tests.
|
||||
1. Try to not extend the scope of the pull requests outside the issue, do not make unrelated changes.
|
||||
1. Update [docs](https://github.com/VictoriaMetrics/VictoriaMetrics/tree/master/docs) if needed. For example, adding a new flag or changing behavior of existing flags or features
|
||||
1. Update [docs](https://github.com/VictoriaMetrics/VictoriaMetrics/tree/master/docs) if needed. For example, adding a new flag or changing the behavior of existing flags or features
|
||||
requires reflecting these changes in the documentation. For new features add `{{%/* available_from "#" */%}}` shortcode to the documentation.
|
||||
It will be later automatically replaced with an actual release version.
|
||||
1. A line in the [changelog](https://docs.victoriametrics.com/victoriametrics/changelog/#tip) mentioning the change and related issue in a way
|
||||
that would be clear to other readers even if they don't have the full context.
|
||||
1. Avoid modifying code in the `/vendor` folder manually, even when the vendored package originates are from the VictoriaMetrics GitHub organization.
|
||||
1. Avoid modifying code in the `/vendor` folder manually, even when the vendored package originates from the VictoriaMetrics GitHub organization.
|
||||
For instance, VictoriaLogs vendors packages under the `/lib` folder from VictoriaMetrics, and VictoriaTraces vendors the `/lib/logstorage` package from VictoriaLogs.
|
||||
Submit a pull request to the upstream repository first. Afterward, a separate pull request can be opened to update the version of the vendored folder in downstream repository.
|
||||
Submit a pull request to the upstream repository first. Afterward, a separate pull request can be opened to update the version of the vendored folder in the downstream repository.
|
||||
* For common packages, the vendored package can be updated with this command: `go get <dependency>@vX.Y.Z`.
|
||||
* For VictoriaMetrics packages, use `go get <dependency>@canonical_commit_hash`.
|
||||
Finally, run `go mod tidy` and `go mod vendor` to update `go.mod`, `go.sum`, and `/vendor`.
|
||||
1. Ping reviewers who you think have the best expertise on the matter.
|
||||
|
||||
See good example of a [pull request](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6487).
|
||||
See a good example of a [pull request](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6487).
|
||||
|
||||
## AI policy
|
||||
|
||||
You are free to use any AI tools when working on a contribution, on code,
|
||||
documentation, issues, or anything else. You do not need to disclose whether or
|
||||
how you used them.
|
||||
|
||||
With or without the help of AI, you are responsible for the changes you submit.
|
||||
Take the effort to understand the code base and every change in your pull request,
|
||||
and clean up any AI slop before sending it. Do not use AI to automate your
|
||||
responses to maintainers.
|
||||
|
||||
We review contributions on their quality, regardless of how they were produced. A
|
||||
pull request or issue that looks like unreviewed AI output, with low-quality or
|
||||
broken changes, may be closed without a detailed review or triage.
|
||||
|
||||
## Merging Pull Request
|
||||
|
||||
The person who merges the Pull Request is responsible for satisfying requirements below:
|
||||
The person who merges the Pull Request is responsible for satisfying the requirements below:
|
||||
|
||||
1. Make sure that PR satisfies [Pull Request checklist](https://docs.victoriametrics.com/victoriametrics/contributing/#pull-request-checklist),
|
||||
it is approved by at least one reviewer, all CI checks are green.
|
||||
@@ -97,9 +111,9 @@ The person who merges the Pull Request is responsible for satisfying requirement
|
||||
1. If applicable, cherry-pick the change to [LTS release lines](https://docs.victoriametrics.com/victoriametrics/lts-releases/)
|
||||
and mention in the PR comment what was or wasn't cherry-picked.
|
||||
1. Update related issues with a meaningful message of what has changed and when it will be
|
||||
released. _This helps users to understand the change without reading PR._
|
||||
released. _This helps users to understand the change without reading the PR._
|
||||
1. Add label `completed` to related issues.
|
||||
1. Do not close related tickets until release is made. If ticket was auto-closed by GitHub or user - re-open it.
|
||||
1. Do not close related tickets until the release is made. If the ticket was auto-closed by GitHub or a user - re-open it.
|
||||
|
||||
## KISS principle
|
||||
|
||||
@@ -115,9 +129,9 @@ We are open to third-party pull requests provided they follow [KISS design princ
|
||||
- Minimize the number of moving parts in the distributed system.
|
||||
- Avoid automated decisions, which may hurt cluster availability, consistency, performance or debuggability.
|
||||
|
||||
Adhering to `KISS` principle, simplifies the resulting code and architecture so it can be reviewed, understood and debugged by a wider audience.
|
||||
Adhering to the `KISS` principle, simplifies the resulting code and architecture so it can be reviewed, understood and debugged by a wider audience.
|
||||
|
||||
Due to `KISS`, [cluster version of VictoriaMetrics](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/) has none of the following "features" popular in distributed computing world:
|
||||
Due to `KISS`, [cluster version of VictoriaMetrics](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/) has none of the following "features" popular in distributed computing:
|
||||
|
||||
- Fragile gossip protocols. See [failed attempt in Thanos](https://github.com/improbable-eng/thanos/blob/030bc345c12c446962225221795f4973848caab5/docs/proposals/completed/201809_gossip-removal.md).
|
||||
- Hard-to-understand-and-implement-properly [Paxos protocols](https://www.quora.com/In-distributed-systems-what-is-a-simple-explanation-of-the-Paxos-algorithm).
|
||||
@@ -126,3 +140,17 @@ Due to `KISS`, [cluster version of VictoriaMetrics](https://docs.victoriametrics
|
||||
- Automatic cluster resizing, which may cost you a lot of money if improperly configured.
|
||||
- Automatic discovering and addition of new nodes in the cluster, which may mix data between dev and prod clusters :)
|
||||
- Automatic leader election, which may result in split brain disaster on network errors.
|
||||
|
||||
## Testing
|
||||
|
||||
We recommend running the following sequence of checks and tests before submitting a pull request:
|
||||
```sh
|
||||
# run static checks
|
||||
make check-all
|
||||
|
||||
# run unit test
|
||||
make test-full
|
||||
|
||||
# run integration tests
|
||||
make apptest
|
||||
```
|
||||
@@ -61,9 +61,9 @@ Download the newest available [VictoriaMetrics release](https://docs.victoriamet
|
||||
from [DockerHub](https://hub.docker.com/r/victoriametrics/victoria-metrics) or [Quay](https://quay.io/repository/victoriametrics/victoria-metrics?tab=tags):
|
||||
|
||||
```sh
|
||||
docker pull victoriametrics/victoria-metrics:v1.145.0
|
||||
docker pull victoriametrics/victoria-metrics:v1.146.0
|
||||
docker run -it --rm -v `pwd`/victoria-metrics-data:/victoria-metrics-data -p 8428:8428 \
|
||||
victoriametrics/victoria-metrics:v1.145.0 --selfScrapeInterval=5s -storageDataPath=victoria-metrics-data
|
||||
victoriametrics/victoria-metrics:v1.146.0 --selfScrapeInterval=5s -storageDataPath=victoria-metrics-data
|
||||
```
|
||||
|
||||
_For Enterprise images, see [this link](https://docs.victoriametrics.com/victoriametrics/enterprise/#docker-images)._
|
||||
|
||||
@@ -245,7 +245,7 @@ The following steps must be performed during the upgrade / downgrade procedure:
|
||||
* Wait until the process stops. This can take a few seconds.
|
||||
* Start the upgraded VictoriaMetrics.
|
||||
|
||||
Prometheus doesn't drop data during VictoriaMetrics restart. See [this article](https://grafana.com/blog/2019/03/25/whats-new-in-prometheus-2.8-wal-based-remote-write/) for details. The same applies also to [vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/).
|
||||
Prometheus doesn't drop data during VictoriaMetrics restart. See [this article](https://grafana.com/blog/whats-new-in-prometheus-2-8-wal-based-remote-write/) for details. The same applies also to [vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/).
|
||||
|
||||
> If you'd prefer not to manage upgrades yourself, [VictoriaMetrics Cloud](https://console.victoriametrics.cloud/signUp?utm_source=website&utm_campaign=docs_vm_single_upgrade)
|
||||
> performs version upgrades automatically during maintenance windows with no action required on your part.
|
||||
@@ -417,7 +417,7 @@ VictoriaMetrics is configured via command-line flags, so it must be restarted wh
|
||||
* Wait until the process stops. This can take a few seconds.
|
||||
* Start VictoriaMetrics with the new command-line flags.
|
||||
|
||||
Prometheus doesn't drop data during VictoriaMetrics restart. See [this article](https://grafana.com/blog/2019/03/25/whats-new-in-prometheus-2.8-wal-based-remote-write/) for details. The same applies also to [vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/).
|
||||
Prometheus doesn't drop data during VictoriaMetrics restart. See [this article](https://grafana.com/blog/whats-new-in-prometheus-2-8-wal-based-remote-write/) for details. The same applies also to [vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/).
|
||||
|
||||
## How to scrape Prometheus exporters such as [node-exporter](https://github.com/prometheus/node_exporter)
|
||||
|
||||
@@ -478,6 +478,11 @@ and [/api/v1/query_range](https://docs.victoriametrics.com/victoriametrics/keyco
|
||||
to the given number of digits after the decimal point.
|
||||
For example, `/api/v1/query?query=avg_over_time(temperature[1h])&round_digits=2` would round response values to up to two digits after the decimal point.
|
||||
|
||||
VictoriaMetrics accepts `optimize_repeated_binary_op_subexprs=1` query arg for [/api/v1/query_range](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#range-query)
|
||||
handler. It allows `vmselect` to execute left and right sides of binary operators sequentially when they contain the same
|
||||
optimized aggregate rollup result expression, so the second side may reuse the rollup result cache populated by the first side.
|
||||
The optimization is disabled by default and applies only when rollup result cache can be used for the request.
|
||||
|
||||
VictoriaMetrics accepts `limit` query arg for [/api/v1/labels](https://docs.victoriametrics.com/victoriametrics/url-examples/#apiv1labels)
|
||||
and [`/api/v1/label/<labelName>/values`](https://docs.victoriametrics.com/victoriametrics/url-examples/#apiv1labelvalues) handlers for limiting the number of returned entries.
|
||||
For example, the query to `/api/v1/labels?limit=5` returns a sample of up to 5 unique labels, while ignoring the rest of labels.
|
||||
@@ -1712,64 +1717,63 @@ The following versions of VictoriaMetrics receive regular security fixes:
|
||||
| [LTS releases](https://docs.victoriametrics.com/victoriametrics/lts-releases/) | ✅ |
|
||||
| other releases | ❌ |
|
||||
|
||||
### Software Bill of Materials (SBOM)
|
||||
|
||||
Every VictoriaMetrics container{{% available_from "v1.137.0" %}} image published to
|
||||
[Docker Hub](https://hub.docker.com/u/victoriametrics) and [Quay.io](https://quay.io/organization/victoriametrics) include an [SPDX](https://spdx.dev/) SBOM attestation generated automatically by BuildKit during `docker buildx build`.
|
||||
|
||||
To inspect the SBOM for an image:
|
||||
|
||||
```sh
|
||||
docker buildx imagetools inspect \
|
||||
docker.io/victoriametrics/victoria-metrics:latest \
|
||||
--format "{{ json .SBOM }}"
|
||||
```
|
||||
|
||||
To scan an image using its SBOM attestation with [Trivy](https://github.com/aquasecurity/trivy):
|
||||
|
||||
```sh
|
||||
trivy image --sbom-sources oci \
|
||||
docker.io/victoriametrics/victoria-metrics:latest
|
||||
```
|
||||
|
||||
### Reporting a Vulnerability
|
||||
|
||||
Please report any security issues to <security@victoriametrics.com>
|
||||
|
||||
### CVE handling policy
|
||||
|
||||
**Source code:** Go dependencies are scanned by [govulncheck](https://pkg.go.dev/golang.org/x/vuln/cmd/govulncheck) in CI.
|
||||
All vulnerabilities must be fixed before the next scheduled release and backported to [LTS releases](https://docs.victoriametrics.com/victoriametrics/lts-releases/).
|
||||
|
||||
**Docker images:** CVE findings in the [Alpine](https://security.alpinelinux.org/) base image pose minimal risk since VictoriaMetrics binaries are statically compiled with no OS dependencies.
|
||||
When detected, only the Alpine base tag is updated.
|
||||
Releases proceed as planned even if upstream fixes are not yet available.
|
||||
For maximum security, hardened [scratch](https://hub.docker.com/_/scratch)-based images are also provided.
|
||||
All images are continuously scanned by Docker Hub and verified before release using [grype](https://github.com/anchore/grype).
|
||||
|
||||
### General security recommendations:
|
||||
|
||||
* All the VictoriaMetrics components must run in protected private networks without direct access from untrusted networks such as Internet.
|
||||
* All VictoriaMetrics components must run in protected private networks without direct access from untrusted networks such as the Internet.
|
||||
The exception is [vmauth](https://docs.victoriametrics.com/victoriametrics/vmauth/) and [vmgateway](https://docs.victoriametrics.com/victoriametrics/vmgateway/),
|
||||
which are intended for serving public requests and performing authorization with [TLS termination](https://en.wikipedia.org/wiki/TLS_termination_proxy).
|
||||
* All the requests from untrusted networks to VictoriaMetrics components must go through auth proxy such as [vmauth](https://docs.victoriametrics.com/victoriametrics/vmauth/)
|
||||
* All the requests from untrusted networks to VictoriaMetrics components must go through an auth proxy, such as [vmauth](https://docs.victoriametrics.com/victoriametrics/vmauth/)
|
||||
or [vmgateway](https://docs.victoriametrics.com/victoriametrics/vmgateway/). The proxy must be set up with proper authentication and authorization.
|
||||
* Prefer using lists of allowed API endpoints, while disallowing access to other endpoints when configuring [vmauth](https://docs.victoriametrics.com/victoriametrics/vmauth/)
|
||||
in front of VictoriaMetrics components.
|
||||
* Set reasonable [`Strict-Transport-Security`](https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Strict-Transport-Security) header value to all the components to mitigate [MitM attacks](https://en.wikipedia.org/wiki/Man-in-the-middle_attack), for example: `max-age=31536000; includeSubDomains`. See `-http.header.hsts` flag.
|
||||
* Set a reasonable [`Strict-Transport-Security`](https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Strict-Transport-Security) header value on all the components to mitigate [MitM attacks](https://en.wikipedia.org/wiki/Man-in-the-middle_attack), for example: `max-age=31536000; includeSubDomains`. See `-http.header.hsts` flag.
|
||||
* Set reasonable [`Content-Security-Policy`](https://developer.mozilla.org/en-US/docs/Web/HTTP/CSP) header value to mitigate [XSS attacks](https://en.wikipedia.org/wiki/Cross-site_scripting). See `-http.header.csp` flag.
|
||||
* Set reasonable [`X-Frame-Options`](https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/X-Frame-Options) header value to mitigate [clickjacking attacks](https://en.wikipedia.org/wiki/Clickjacking), for example `DENY`. See `-http.header.frameOptions` flag.
|
||||
|
||||
VictoriaMetrics provides the following security-related command-line flags:
|
||||
The following security-related command-line flags are available for all components with HTTP API:
|
||||
|
||||
* `-tls`, `-tlsCertFile` and `-tlsKeyFile` for switching from HTTP to HTTPS at `-httpListenAddr` (TCP port 8428 is listened by default).
|
||||
* `-tls`, `-tlsCertFile` and `-tlsKeyFile` for switching from HTTP to HTTPS at `-httpListenAddr`.
|
||||
[Enterprise version of VictoriaMetrics](https://docs.victoriametrics.com/victoriametrics/enterprise/) supports automatic issuing of TLS certificates.
|
||||
See [these docs](#automatic-issuing-of-tls-certificates).
|
||||
* `-mtls` and `-mtlsCAFile` for enabling [mTLS](https://en.wikipedia.org/wiki/Mutual_authentication) for requests to `-httpListenAddr`. See [these docs](#mtls-protection).
|
||||
* `-httpAuth.username` and `-httpAuth.password` for protecting all the HTTP endpoints
|
||||
with [HTTP Basic Authentication](https://en.wikipedia.org/wiki/Basic_access_authentication).
|
||||
* `-http.header.hsts`, `-http.header.csp`, and `-http.header.frameOptions` for serving `Strict-Transport-Security`, `Content-Security-Policy`
|
||||
and `X-Frame-Options` HTTP response headers.
|
||||
|
||||
### Protecting service endpoints
|
||||
|
||||
All VictoriaMetrics components expose internal metrics in Prometheus exposition format at the `/metrics` page for [#Monitoring](https://docs.victoriametrics.com/victoriametrics/#monitoring).
|
||||
Consider limiting access to the `/metrics` page to trusted networks only.
|
||||
|
||||
The following service endpoints may require protection:
|
||||
|
||||
* `-deleteAuthKey` for protecting the `/api/v1/admin/tsdb/delete_series` endpoint. See [how to delete time series](#how-to-delete-time-series).
|
||||
* `-snapshotAuthKey` for protecting the `/snapshot*` endpoints. See [how to work with snapshots](#how-to-work-with-snapshots).
|
||||
* `-forceFlushAuthKey` for protecting the `/internal/force_flush` endpoint. See [force flush docs](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#forced-flush).
|
||||
* `-forceMergeAuthKey` for protecting the `/internal/force_merge` endpoint. See [force merge docs](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#forced-merge).
|
||||
* `-search.resetCacheAuthKey` for protecting the `/internal/resetRollupResultCache` endpoint. See [backfilling](#backfilling) for more details.
|
||||
* `-reloadAuthKey` for protecting the `/-/reload` endpoint, which is used for force reloading of [`-promscrape.config`](#how-to-scrape-prometheus-exporters-such-as-node-exporter).
|
||||
* `-reloadAuthKey` for protecting the `/-/reload` endpoint, which is used to force reload the [`-promscrape.config`](#how-to-scrape-prometheus-exporters-such-as-node-exporter).
|
||||
* `-configAuthKey` for protecting the `/config` endpoint, since it may contain sensitive information such as passwords.
|
||||
* `-flagsAuthKey` for protecting the `/flags` endpoint.
|
||||
* `-pprofAuthKey` for protecting the `/debug/pprof/*` endpoints, which can be used for [profiling](#profiling).
|
||||
* `-metricNamesStatsResetAuthKey` for protecting the `/api/v1/admin/status/metric_names_stats/reset` endpoint, used for [Metric Names Tracker](#track-ingested-metrics-usage).
|
||||
* `-denyQueryTracing` for disallowing [query tracing](#query-tracing).
|
||||
* `-http.header.hsts`, `-http.header.csp`, and `-http.header.frameOptions` for serving `Strict-Transport-Security`, `Content-Security-Policy`
|
||||
and `X-Frame-Options` HTTP response headers.
|
||||
|
||||
Explicitly set internal network interface for TCP and UDP ports for data ingestion with Graphite and OpenTSDB formats.
|
||||
For example, substitute `-graphiteListenAddr=:2003` with `-graphiteListenAddr=<internal_iface_ip>:2003`. This protects from unexpected requests from untrusted network interfaces.
|
||||
@@ -1777,17 +1781,6 @@ For example, substitute `-graphiteListenAddr=:2003` with `-graphiteListenAddr=<i
|
||||
See also [security recommendation for VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/#security)
|
||||
and [the general security page at VictoriaMetrics website](https://victoriametrics.com/security/).
|
||||
|
||||
### CVE handling policy
|
||||
|
||||
**Source code:** Go dependencies are scanned by [govulncheck](https://pkg.go.dev/golang.org/x/vuln/cmd/govulncheck) in CI.
|
||||
All vulnerabilities must be fixed before next scheduled release and backported to [LTS releases](https://docs.victoriametrics.com/victoriametrics/lts-releases/).
|
||||
|
||||
**Docker images:** CVE findings in [Alpine](https://security.alpinelinux.org/) base image pose minimal risk since VictoriaMetrics binaries are statically compiled with no OS dependencies.
|
||||
When detected, only the Alpine base tag is updated.
|
||||
Releases proceed as planned even if upstream fixes are not yet available.
|
||||
For maximum security, hardened [scratch](https://hub.docker.com/_/scratch)-based images are also provided.
|
||||
All images are continuously scanned by Docker Hub and verified before release using [grype](https://github.com/anchore/grype).
|
||||
|
||||
### mTLS protection
|
||||
|
||||
By default `VictoriaMetrics` accepts http requests at `8428` port (this port can be changed via `-httpListenAddr` command-line flags).
|
||||
@@ -1817,19 +1810,39 @@ This functionality can be evaluated for free according to [these docs](https://d
|
||||
|
||||
See also [security recommendations](#security).
|
||||
|
||||
### Software Bill of Materials (SBOM)
|
||||
|
||||
Every VictoriaMetrics container{{% available_from "v1.137.0" %}} image published to
|
||||
[Docker Hub](https://hub.docker.com/u/victoriametrics) and [Quay.io](https://quay.io/organization/victoriametrics) include an [SPDX](https://spdx.dev/) SBOM attestation generated automatically by BuildKit during `docker buildx build`.
|
||||
|
||||
To inspect the SBOM for an image:
|
||||
|
||||
```sh
|
||||
docker buildx imagetools inspect \
|
||||
docker.io/victoriametrics/victoria-metrics:latest \
|
||||
--format "{{ json .SBOM }}"
|
||||
```
|
||||
|
||||
To scan an image using its SBOM attestation with [Trivy](https://github.com/aquasecurity/trivy):
|
||||
|
||||
```sh
|
||||
trivy image --sbom-sources oci \
|
||||
docker.io/victoriametrics/victoria-metrics:latest
|
||||
```
|
||||
|
||||
## Tuning
|
||||
|
||||
* No need in tuning for VictoriaMetrics - it uses reasonable defaults for command-line flags,
|
||||
* No need to tune for VictoriaMetrics - it uses reasonable defaults for command-line flags,
|
||||
which are automatically adjusted for the available CPU and RAM resources.
|
||||
* No need in tuning for Operating System - VictoriaMetrics is optimized for default OS settings.
|
||||
* No need to tune for Operating System - VictoriaMetrics is optimized for default OS settings.
|
||||
The only option is increasing the limit on [the number of open files in the OS](https://medium.com/@muhammadtriwibowo/set-permanently-ulimit-n-open-files-in-ubuntu-4d61064429a).
|
||||
The recommendation is not specific for VictoriaMetrics only but also for any service which handles many HTTP connections and stores data on disk.
|
||||
* VictoriaMetrics is a write-heavy application and its performance depends on disk performance. So be careful with other
|
||||
The recommendation is not specific to VictoriaMetrics only, but also for any service that handles many HTTP connections and stores data on disk.
|
||||
* VictoriaMetrics is a write-heavy application, and its performance depends on disk performance. So be careful with other
|
||||
applications or utilities (like [fstrim](https://manpages.ubuntu.com/manpages/lunar/en/man8/fstrim.8.html))
|
||||
which could [exhaust disk resources](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1521).
|
||||
* The recommended filesystem is `ext4`, the recommended persistent storage is [persistent HDD-based disk on GCP](https://cloud.google.com/compute/docs/disks/#pdspecs),
|
||||
since it is protected from hardware failures via internal replication and it can be [resized on the fly](https://cloud.google.com/compute/docs/disks/add-persistent-disk#resize_pd).
|
||||
If you plan to store more than 1TB of data on `ext4` partition, then the following options are recommended to pass to `mkfs.ext4`:
|
||||
since it is protected from hardware failures via internal replication, and it can be [resized on the fly](https://cloud.google.com/compute/docs/disks/add-persistent-disk#resize_pd).
|
||||
If you plan to store more than 1TB of data on an `ext4` partition, then the following options are recommended to pass to `mkfs.ext4`:
|
||||
|
||||
```sh
|
||||
mkfs.ext4 ... -O 64bit,huge_file,extent -T huge
|
||||
|
||||
@@ -26,7 +26,48 @@ See also [LTS releases](https://docs.victoriametrics.com/victoriametrics/lts-rel
|
||||
|
||||
## tip
|
||||
|
||||
* BUGFIX: [stream aggregation](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/): fix issue with producing aggregated samples with identical timestamps between flushes. See PR [#10808](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/10808) for details.
|
||||
* SECURITY: upgrade base docker image (Alpine) from 3.23.4 to 3.24.1. See [Alpine 3.24.1 release notes](https://www.alpinelinux.org/posts/Alpine-3.24.1-released.html).
|
||||
|
||||
* FEATURE: `vmselect` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): expose `vm_max_memory_per_query` metric reflecting the `-search.maxMemoryPerQuery` limit. Create `VMSelectConcurrentQueriesExceedMemoryLimit` alert to warn when OOMs are possible due to misconfiguration of `-search.maxMemoryPerQuery` and max concurrent queries.
|
||||
|
||||
* FEATURE: [vmauth](https://docs.victoriametrics.com/victoriametrics/vmauth/): add `default_vm_access_claim` field into `jwt` section of auth config. It could be used at [JWT claim placeholders](https://docs.victoriametrics.com/victoriametrics/vmauth/#jwt-claim-based-request-templating), if `JWT` token doesn't have `vm_access` claim. See [#11054](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/11054).
|
||||
* FEATURE: [vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/): reduces CPU usage by 10% at [sharding among remote storages](https://docs.victoriametrics.com/victoriametrics/vmagent/#sharding-among-remote-storages). See [#11113](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/11113). Thanks to @bennf for contribution.
|
||||
* FEATURE: [vmsingle](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/) and `vmselect` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): add `optimize_repeated_binary_op_subexprs=1` query arg to [/api/v1/query_range](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#range-query) for executing binary operator sides sequentially when they share the same optimized aggregate rollup result expression. This allows the second side to reuse rollup result cache populated by the first side. See [#10575](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10575).
|
||||
* FEATURE: [vmauth](https://docs.victoriametrics.com/victoriametrics/vmauth/): prevent possible password brute-force attacks with an artificial 2-3 second delay as recommended by [OWASP](https://owasp.org/Top10/2025/A07_2025-Authentication_Failures). See [#11180](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/11180).
|
||||
|
||||
* BUGFIX: all VictoriaMetrics components: cancel in-flight HTTP requests shortly before `-http.maxGracefulShutdownDuration` elapses during graceful shutdown, so they can drain and the shutdown completes cleanly within that window instead of timing out and exiting via `logger.Fatalf` -> `os.Exit`. This prevents skipping the storage flush and losing in-memory data when long-lived requests are in flight (such as VictoriaLogs live tailing). See [#1502](https://github.com/VictoriaMetrics/VictoriaLogs/issues/1502).
|
||||
* BUGFIX: `vminsert` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): fixes unexpected rare rerouting. See [#11162](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/11162).
|
||||
* BUGFIX: `vmselect` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): propagate cache reset operation to `selectNode` when `/internal/resetRollupResultCache` is called. Previously, the propagation only happened when the `delete_series` API was called. See [#11112](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/11112).
|
||||
* BUGFIX: [stream aggregation](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/): fix possible unexpected increases in `rate_avg` and `rate_sum` if an out-of-order sample is ingested after the previous flush. See [#11140](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/11140).
|
||||
|
||||
## [v1.146.0](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.146.0)
|
||||
|
||||
Released at 2026-06-22
|
||||
|
||||
* FEATURE: all VictoriaMetrics components: add `-http.header.disableServerHostname` command-line flag for disabling the `X-Server-Hostname` HTTP response header. See [#11067](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/11067). Thanks to @zasdaym for contribution.
|
||||
* FEATURE: [stream aggregation](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/): expose `vm_streamaggr_dedup_dropped_samples_total` to allow tracking dropped old samples during [deduplication](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/#deduplication).
|
||||
* FEATURE: [stream aggregation](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/): use the aggregation rule interval as the default [staleness_interval](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/#staleness) instead of `2*interval`, to reduce spikes when there are gaps between received samples. See [#11102](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/11102).
|
||||
* FEATURE: [stream aggregation](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/): add new aggregation output [sum_samples_total](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#sum_samples_total) for summing input delta values into a cumulative counter. See issues [#11002](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/11002) and [#4843](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/4843).
|
||||
* FEATURE: [vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/): add a new flag `-remoteWrite.inmemoryQueues` to prioritize recently ingested data over historical data stored at file-based [persistent queue](https://docs.victoriametrics.com/victoriametrics/vmagent/#on-disk-persistence-and-data-processing-order). See [#8833](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/8833)
|
||||
* FEATURE: [vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/): add `-promscrape.cluster.shardByLabels` command-line flag for selecting target labels used for sharding scrape targets among `vmagent` instances in cluster mode. See [#11044](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/11044).
|
||||
* FEATURE: [vmctl](https://docs.victoriametrics.com/victoriametrics/vmctl/): add `-vm-headers` and `-vm-bearer-token` flags for authenticating requests to the VictoriaMetrics import destination. The flags are available in `opentsdb`, `influx`, `remote-read`, `prometheus`, `mimir`, and `thanos` vmctl sub-commands. See [#8897](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/8897).
|
||||
* FEATURE: [vmsingle](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/) and `vmselect` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): log calls to [/api/v1/admin/tsdb/delete_series](https://docs.victoriametrics.com/victoriametrics/url-examples/#apiv1admintsdbdelete_series) API handler. This should help to identify events of metrics deletion from the database. See [#11104](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/11104).
|
||||
* FEATURE: [vmui](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#vmui): add the `last` value to graph legend statistics. See [#10759](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/10759).
|
||||
* FEATURE: [vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/): add support for [Monitoring Data eXchange (MDX)](https://docs.victoriametrics.com/victoriametrics/vmagent/#monitoring-data-exchange): the ability to route only metrics from VictoriaMetrics services to a specific `-remoteWrite.url`. MDX is useful for building monitoring-of-monitoring where one remote storage should receive the full metric stream and another should receive only VictoriaMetrics metrics. Enable per destination with `-remoteWrite.mdx.enable=true`. See [#10600](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10600).
|
||||
|
||||
* BUGFIX: [enterprise](https://docs.victoriametrics.com/enterprise/) [vmsingle](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/) and `vmstorage` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): properly expose metric `vm_retention_filters_partitions_scheduled_rows`. See [#11138](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/11138)
|
||||
* BUGFIX: [stream aggregation](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/): fix issue with producing aggregated samples with identical timestamps between flushes. See [#10808](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/10808).
|
||||
* BUGFIX: [vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/): fix potential corruption of remote-write metadata `Unit` values. See [#11120](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/11120). Thanks for @fxrlv for the contribution.
|
||||
* BUGFIX: [vmalert](https://docs.victoriametrics.com/victoriametrics/vmalert/),[vmauth](https://docs.victoriametrics.com/victoriametrics/vmauth/),[vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/) and [vmsingle](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/): fix rare unbounded shutdown delay when config reload takes longer than `-configCheckInterval`. See [#11107](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/11107). Thanks to @PleasingFungus for contribution.
|
||||
* BUGFIX: [vmctl](https://docs.victoriametrics.com/victoriametrics/vmctl/): push metrics to configured `-pushmetrics.url` on shutdown when migration fails. Previously, metrics were not pushed if vmctl exited with an error. See [#11081](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/11081). Thanks to @zasdaym for contribution.
|
||||
* BUGFIX: [vmrestore](https://docs.victoriametrics.com/victoriametrics/vmrestore/): disallow restoring parts outside the configured `-storageDataPath` directory. See [710c920d](https://github.com/VictoriaMetrics/VictoriaMetrics/commit/710c920d6083327042a309e449fae4383617d817).
|
||||
* BUGFIX: `vmselect` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): correctly apply long tenant filters. Previously, such filters could be truncated, causing tenants to be matched incorrectly. See [#11096](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/11096). Thanks for @fxrlv for the contribution.
|
||||
* BUGFIX: `vmselect` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): fix corrupted metrics metadata when a response contains multiple rows. See [#11115](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/11115). Thanks for @fxrlv for the contribution.
|
||||
* BUGFIX: [vmbackup](https://docs.victoriametrics.com/vmbackup/), [vmbackupmanager](https://docs.victoriametrics.com/victoriametrics/vmbackupmanager/): do not fail backup list if directory is absent while using `fs://` destination to align with other protocols. See [6c3c548](https://github.com/VictoriaMetrics/VictoriaMetrics/commit/6c3c548ddb0385b749e731f52276f130e2a4e4a8)
|
||||
* BUGFIX: `vmselect` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): don't cache empty responses for tenant IDs discovery during [multitenant queries](https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html#multitenant-reads). This problem was visible during integration tests when multitenant queries were executed before the first ingestion happened. See [#10982](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/10982)
|
||||
* BUGFIX: [vmsingle](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/) and `vmselect` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): properly escape `metricFamilyName` at metrics metadata response. See [#11129](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/11129). Thanks for @fxrlv for the contribution.
|
||||
* BUGFIX: [vmsingle](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/) and `vmstorage` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): prevent more cases of panic during directory deletion on `NFS`-based mounts. See [#11060](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/11060).
|
||||
|
||||
|
||||
## [v1.145.0](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.145.0)
|
||||
|
||||
@@ -266,6 +307,25 @@ It enables back `Discovered targets` debug UI by default.
|
||||
* BUGFIX: `vmstorage` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): properly apply `extra_filters[]` filter when querying `vm_account_id` or `vm_project_id` labels via [multitenant](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/#multitenancy) request for `/api/v1/label/…/values` API. Before, `extra_filters` was ignored. See [#10503](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/10503).
|
||||
* BUGFIX: [vmsingle](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/) and `vmselect` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): revert the use of rollup result cache for [instant queries](https://docs.victoriametrics.com/keyConcepts.html#instant-query) that contain [`rate`](https://docs.victoriametrics.com/MetricsQL.html#rate) function with a lookbehind window larger than `-search.minWindowForInstantRollupOptimization`. The cache usage was removed since [v1.132.0](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.132.0). See [#10098](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10098#issuecomment-3895011084) for more details.
|
||||
|
||||
## [v1.136.12](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.136.12)
|
||||
|
||||
Released at 2026-06-19
|
||||
|
||||
**v1.136.x is a line of [LTS releases](https://docs.victoriametrics.com/victoriametrics/lts-releases/). It contains important up-to-date bugfixes for [VictoriaMetrics enterprise](https://docs.victoriametrics.com/victoriametrics/enterprise/).
|
||||
All these fixes are also included in [the latest community release](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/latest).
|
||||
The v1.136.x line will be supported for at least 12 months since [v1.136.0](https://docs.victoriametrics.com/victoriametrics/changelog/#v11360) release**
|
||||
|
||||
* BUGFIX: [stream aggregation](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/): fix issue with producing aggregated samples with identical timestamps between flushes. See [#10808](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/10808).
|
||||
* BUGFIX: [vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/): fix potential corruption of remote-write metadata `Unit` values. See [#11120](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/11120). Thanks for @fxrlv for the contribution.
|
||||
* BUGFIX: [vmalert](https://docs.victoriametrics.com/victoriametrics/vmalert/),[vmauth](https://docs.victoriametrics.com/victoriametrics/vmauth/),[vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/) and [vmsingle](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/): fix rare unbounded shutdown delay when config reload takes longer than `-configCheckInterval`. See [#11107](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/11107). Thanks to @PleasingFungus for contribution.
|
||||
* BUGFIX: [vmbackup](https://docs.victoriametrics.com/vmbackup/), [vmbackupmanager](https://docs.victoriametrics.com/victoriametrics/vmbackupmanager/): do not fail backup list if directory is absent while using `fs://` destination to align with other protocols. See [6c3c548d](https://github.com/VictoriaMetrics/VictoriaMetrics/commit/6c3c548ddb0385b749e731f52276f130e2a4e4a8)
|
||||
* BUGFIX: [vmctl](https://docs.victoriametrics.com/victoriametrics/vmctl/): push metrics to configured `-pushmetrics.url` on shutdown when migration fails. Previously, metrics were not pushed if vmctl exited with an error. See [#11081](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/11081). Thanks to @zasdaym for contribution.
|
||||
* BUGFIX: [vmrestore](https://docs.victoriametrics.com/victoriametrics/vmrestore/): disallow restoring parts outside the configured `-storageDataPath` directory. See [710c920d](https://github.com/VictoriaMetrics/VictoriaMetrics/commit/710c920d6083327042a309e449fae4383617d817).
|
||||
* BUGFIX: `vmselect` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): fix corrupted metrics metadata when a response contains multiple rows. See [#11115](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/11115). Thanks for @fxrlv for the contribution.
|
||||
* BUGFIX: [vmsingle](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/) and `vmselect` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): properly escape `metricFamilyName` at metrics metadata response. See [#11129](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/11129). Thanks for @fxrlv for the contribution.
|
||||
* BUGFIX: `vmselect` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): correctly apply long tenant filters. Previously, such filters could be truncated, causing tenants to be matched incorrectly. See [#11096](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/11096). Thanks for @fxrlv for the contribution.
|
||||
* BUGFIX: [vmsingle](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/) and `vmstorage` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): prevent more cases of panic during directory deletion on `NFS`-based mounts. See [#11060](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/11060).
|
||||
|
||||
## [v1.136.11](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.136.11)
|
||||
|
||||
Released at 2026-06-05
|
||||
@@ -627,6 +687,20 @@ See changes [here](https://docs.victoriametrics.com/victoriametrics/changelog/ch
|
||||
|
||||
See changes [here](https://docs.victoriametrics.com/victoriametrics/changelog/changelog_2025/#v11230)
|
||||
|
||||
## [v1.122.25](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.122.25)
|
||||
|
||||
Released at 2026-06-19
|
||||
|
||||
**v1.122.x is a line of [LTS releases](https://docs.victoriametrics.com/victoriametrics/lts-releases/). It contains important up-to-date bugfixes for [VictoriaMetrics enterprise](https://docs.victoriametrics.com/victoriametrics/enterprise/).
|
||||
All these fixes are also included in [the latest community release](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/latest).
|
||||
The v1.122.x line will be supported for at least 12 months since [v1.122.0](https://docs.victoriametrics.com/victoriametrics/changelog/#v11220) release**
|
||||
|
||||
* BUGFIX: [stream aggregation](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/): fix issue with producing aggregated samples with identical timestamps between flushes. See [#10808](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/10808).
|
||||
* BUGFIX: [vmalert](https://docs.victoriametrics.com/victoriametrics/vmalert/),[vmauth](https://docs.victoriametrics.com/victoriametrics/vmauth/),[vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/) and [vmsingle](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/): fix rare unbounded shutdown delay when config reload takes longer than `-configCheckInterval`. See [#11107](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/11107). Thanks to @PleasingFungus for contribution.
|
||||
* BUGFIX: `vmselect` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): fix corrupted metrics metadata when a response contains multiple rows. See [#11115](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/11115). Thanks for @fxrlv for the contribution.
|
||||
* BUGFIX: [vmbackup](https://docs.victoriametrics.com/vmbackup/), [vmbackupmanager](https://docs.victoriametrics.com/victoriametrics/vmbackupmanager/): do not fail backup list if directory is absent while using `fs://` destination to align with other protocols. See [6c3c548d](https://github.com/VictoriaMetrics/VictoriaMetrics/commit/6c3c548ddb0385b749e731f52276f130e2a4e4a8)
|
||||
* BUGFIX: [vmrestore](https://docs.victoriametrics.com/victoriametrics/vmrestore/): disallow restoring parts outside the configured `-storageDataPath` directory. See [710c920d](https://github.com/VictoriaMetrics/VictoriaMetrics/commit/710c920d6083327042a309e449fae4383617d817).
|
||||
|
||||
## [v1.122.24](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.122.24)
|
||||
|
||||
Released at 2026-06-05
|
||||
|
||||
@@ -121,7 +121,7 @@ It is allowed to run Enterprise components in [cases listed here](https://docs.v
|
||||
Binary releases of Enterprise components are available at [the releases page for VictoriaMetrics](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/latest),
|
||||
[the releases page for VictoriaLogs](https://github.com/VictoriaMetrics/VictoriaLogs/releases/latest)
|
||||
and [the releases page for VictoriaTraces](https://github.com/VictoriaMetrics/VictoriaTraces/releases/latest).
|
||||
Enterprise binaries and packages have `enterprise` suffix in their names. For example, `victoria-metrics-linux-amd64-v1.145.0-enterprise.tar.gz`.
|
||||
Enterprise binaries and packages have `enterprise` suffix in their names. For example, `victoria-metrics-linux-amd64-v1.146.0-enterprise.tar.gz`.
|
||||
|
||||
In order to run binary release of Enterprise component, please download the `*-enterprise.tar.gz` archive for your OS and architecture
|
||||
from the corresponding releases page and unpack it. Then run the unpacked binary.
|
||||
@@ -139,8 +139,8 @@ For example, the following command runs VictoriaMetrics Enterprise binary with t
|
||||
obtained at [this page](https://victoriametrics.com/products/enterprise/trial/):
|
||||
|
||||
```sh
|
||||
wget https://github.com/VictoriaMetrics/VictoriaMetrics/releases/download/v1.145.0/victoria-metrics-linux-amd64-v1.145.0-enterprise.tar.gz
|
||||
tar -xzf victoria-metrics-linux-amd64-v1.145.0-enterprise.tar.gz
|
||||
wget https://github.com/VictoriaMetrics/VictoriaMetrics/releases/download/v1.146.0/victoria-metrics-linux-amd64-v1.146.0-enterprise.tar.gz
|
||||
tar -xzf victoria-metrics-linux-amd64-v1.146.0-enterprise.tar.gz
|
||||
./victoria-metrics-prod -license=BASE64_ENCODED_LICENSE_KEY
|
||||
```
|
||||
|
||||
@@ -155,7 +155,7 @@ Alternatively, VictoriaMetrics Enterprise license can be stored in the file and
|
||||
It is allowed to run Enterprise components in [cases listed here](https://docs.victoriametrics.com/victoriametrics/enterprise/#valid-cases-for-victoriametrics-enterprise).
|
||||
|
||||
Docker images for Enterprise components are available at [VictoriaMetrics Docker Hub](https://hub.docker.com/u/victoriametrics) and [VictoriaMetrics Quay](https://quay.io/organization/victoriametrics).
|
||||
Enterprise docker images have `enterprise` suffix in their names. For example, `victoriametrics/victoria-metrics:v1.145.0-enterprise`.
|
||||
Enterprise docker images have `enterprise` suffix in their names. For example, `victoriametrics/victoria-metrics:v1.146.0-enterprise`.
|
||||
|
||||
In order to run Docker image of VictoriaMetrics Enterprise component, it is required to provide the license key via the command-line
|
||||
flag as described in the [binary-releases](https://docs.victoriametrics.com/victoriametrics/enterprise/#binary-releases) section.
|
||||
@@ -165,13 +165,13 @@ Enterprise license key can be obtained at [this page](https://victoriametrics.co
|
||||
For example, the following command runs VictoriaMetrics Enterprise Docker image with the specified license key:
|
||||
|
||||
```sh
|
||||
docker run --name=victoria-metrics victoriametrics/victoria-metrics:v1.145.0-enterprise -license=BASE64_ENCODED_LICENSE_KEY
|
||||
docker run --name=victoria-metrics victoriametrics/victoria-metrics:v1.146.0-enterprise -license=BASE64_ENCODED_LICENSE_KEY
|
||||
```
|
||||
|
||||
Alternatively, the license code can be stored in the file and then referred via `-licenseFile` command-line flag:
|
||||
|
||||
```sh
|
||||
docker run --name=victoria-metrics -v /vm-license:/vm-license victoriametrics/victoria-metrics:v1.145.0-enterprise -licenseFile=/path/to/vm-license
|
||||
docker run --name=victoria-metrics -v /vm-license:/vm-license victoriametrics/victoria-metrics:v1.146.0-enterprise -licenseFile=/path/to/vm-license
|
||||
```
|
||||
|
||||
Example docker-compose configuration:
|
||||
@@ -181,7 +181,7 @@ version: "3.5"
|
||||
services:
|
||||
victoriametrics:
|
||||
container_name: victoriametrics
|
||||
image: victoriametrics/victoria-metrics:v1.145.0
|
||||
image: victoriametrics/victoria-metrics:v1.146.0
|
||||
ports:
|
||||
- 8428:8428
|
||||
volumes:
|
||||
@@ -213,7 +213,7 @@ is used to provide the license key in plain-text:
|
||||
```yaml
|
||||
server:
|
||||
image:
|
||||
tag: v1.145.0-enterprise
|
||||
tag: v1.146.0-enterprise
|
||||
|
||||
license:
|
||||
key: {BASE64_ENCODED_LICENSE_KEY}
|
||||
@@ -224,7 +224,7 @@ In order to provide the license key via existing secret, the following values fi
|
||||
```yaml
|
||||
server:
|
||||
image:
|
||||
tag: v1.145.0-enterprise
|
||||
tag: v1.146.0-enterprise
|
||||
|
||||
license:
|
||||
secret:
|
||||
@@ -274,7 +274,7 @@ spec:
|
||||
license:
|
||||
key: {BASE64_ENCODED_LICENSE_KEY}
|
||||
image:
|
||||
tag: v1.145.0-enterprise
|
||||
tag: v1.146.0-enterprise
|
||||
```
|
||||
|
||||
In order to provide the license key via an existing secret, the following custom resource is used:
|
||||
@@ -291,7 +291,7 @@ spec:
|
||||
name: vm-license
|
||||
key: license
|
||||
image:
|
||||
tag: v1.145.0-enterprise
|
||||
tag: v1.146.0-enterprise
|
||||
```
|
||||
|
||||
Example secret with license key:
|
||||
@@ -342,7 +342,7 @@ Builds are available for amd64 and arm64 architectures.
|
||||
|
||||
Example archive:
|
||||
|
||||
`victoria-metrics-linux-amd64-v1.145.0-enterprise.tar.gz`
|
||||
`victoria-metrics-linux-amd64-v1.146.0-enterprise.tar.gz`
|
||||
|
||||
Includes:
|
||||
|
||||
@@ -351,7 +351,7 @@ Includes:
|
||||
|
||||
Example Docker image:
|
||||
|
||||
`victoriametrics/victoria-metrics:v1.145.0-enterprise-fips` – uses the FIPS-compatible binary and based on `scratch` image.
|
||||
`victoriametrics/victoria-metrics:v1.146.0-enterprise-fips` – uses the FIPS-compatible binary and based on `scratch` image.
|
||||
|
||||
## What Happens to Licensed Components When a License Expires
|
||||
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user