From 1f91f22b5f0c93be6c65983834fcea8ccebc6594 Mon Sep 17 00:00:00 2001 From: Nikolay Date: Tue, 10 Oct 2023 13:44:02 +0200 Subject: [PATCH] app/vmselect: reduce lock contention for heavy aggregation requests (#5119) reduce lock contention for heavy aggregation requests previously lock contetion may happen on machine with big number of CPU due to enabled string interning. sync.Map was a choke point for all aggregation requests. Now instead of interning, new string is created. It may increase CPU and memory usage for some cases. https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5087 --- app/vmselect/promql/aggr.go | 3 +-- app/vmselect/promql/aggr_incremental.go | 3 +-- app/vmselect/promql/binary_op.go | 6 ++---- app/vmselect/promql/eval.go | 7 +++---- app/vmselect/promql/exec.go | 3 +-- app/vmselect/promql/rollup_result_cache.go | 5 ++--- app/vmselect/promql/transform.go | 8 ++++---- docs/CHANGELOG.md | 2 ++ 8 files changed, 16 insertions(+), 21 deletions(-) diff --git a/app/vmselect/promql/aggr.go b/app/vmselect/promql/aggr.go index 3ba78615a..c3310ee22 100644 --- a/app/vmselect/promql/aggr.go +++ b/app/vmselect/promql/aggr.go @@ -8,7 +8,6 @@ import ( "strconv" "strings" - "github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil" "github.com/VictoriaMetrics/VictoriaMetrics/lib/logger" "github.com/VictoriaMetrics/VictoriaMetrics/lib/storage" "github.com/VictoriaMetrics/metrics" @@ -130,7 +129,7 @@ func aggrPrepareSeries(argOrig []*timeseries, modifier *metricsql.ModifierExpr, for i, ts := range arg { removeGroupTags(&ts.MetricName, modifier) bb.B = marshalMetricNameSorted(bb.B[:0], &ts.MetricName) - k := bytesutil.InternBytes(bb.B) + k := string(bb.B) if keepOriginal { ts = argOrig[i] } diff --git a/app/vmselect/promql/aggr_incremental.go b/app/vmselect/promql/aggr_incremental.go index f3d5bd416..c87ba7bb3 100644 --- a/app/vmselect/promql/aggr_incremental.go +++ b/app/vmselect/promql/aggr_incremental.go @@ -6,7 +6,6 @@ import ( "unsafe" "github.com/VictoriaMetrics/VictoriaMetrics/app/vmselect/netstorage" - "github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil" "github.com/VictoriaMetrics/metricsql" ) @@ -105,7 +104,7 @@ func (iafc *incrementalAggrFuncContext) updateTimeseries(tsOrig *timeseries, wor removeGroupTags(&ts.MetricName, &iafc.ae.Modifier) bb := bbPool.Get() bb.B = marshalMetricNameSorted(bb.B[:0], &ts.MetricName) - k := bytesutil.InternBytes(bb.B) + k := string(bb.B) iac := m[k] if iac == nil { if iafc.ae.Limit > 0 && len(m) >= iafc.ae.Limit { diff --git a/app/vmselect/promql/binary_op.go b/app/vmselect/promql/binary_op.go index 3c354946a..d02082556 100644 --- a/app/vmselect/promql/binary_op.go +++ b/app/vmselect/promql/binary_op.go @@ -5,7 +5,6 @@ import ( "math" "strings" - "github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil" "github.com/VictoriaMetrics/VictoriaMetrics/lib/logger" "github.com/VictoriaMetrics/VictoriaMetrics/lib/storage" "github.com/VictoriaMetrics/metricsql" @@ -261,8 +260,7 @@ func groupJoin(singleTimeseriesSide string, be *metricsql.BinaryOpExpr, rvsLeft, bb.B = marshalMetricTagsSorted(bb.B[:0], &tsCopy.MetricName) pair, ok := m[string(bb.B)] if !ok { - k := bytesutil.InternBytes(bb.B) - m[k] = &tsPair{ + m[string(bb.B)] = &tsPair{ left: &tsCopy, right: tsRight, } @@ -524,7 +522,7 @@ func createTimeseriesMapByTagSet(be *metricsql.BinaryOpExpr, left, right []*time logger.Panicf("BUG: unexpected binary op modifier %q", groupOp) } bb.B = marshalMetricTagsSorted(bb.B[:0], mn) - k := bytesutil.InternBytes(bb.B) + k := string(bb.B) m[k] = append(m[k], ts) } storage.PutMetricName(mn) diff --git a/app/vmselect/promql/eval.go b/app/vmselect/promql/eval.go index a9a85f624..b7593f963 100644 --- a/app/vmselect/promql/eval.go +++ b/app/vmselect/promql/eval.go @@ -548,8 +548,8 @@ func getCommonLabelFilters(tss []*timeseries) []metricsql.LabelFilter { for _, tag := range ts.MetricName.Tags { vc, ok := m[string(tag.Key)] if !ok { - k := bytesutil.InternBytes(tag.Key) - v := bytesutil.InternBytes(tag.Value) + k := string(tag.Key) + v := string(tag.Value) m[k] = &valuesCounter{ values: map[string]struct{}{ v: {}, @@ -566,8 +566,7 @@ func getCommonLabelFilters(tss []*timeseries) []metricsql.LabelFilter { } vc.count++ if _, ok := vc.values[string(tag.Value)]; !ok { - v := bytesutil.InternBytes(tag.Value) - vc.values[v] = struct{}{} + vc.values[string(tag.Value)] = struct{}{} } } } diff --git a/app/vmselect/promql/exec.go b/app/vmselect/promql/exec.go index ab14cb14c..02ea1ce6c 100644 --- a/app/vmselect/promql/exec.go +++ b/app/vmselect/promql/exec.go @@ -12,7 +12,6 @@ import ( "github.com/VictoriaMetrics/VictoriaMetrics/app/vmselect/netstorage" "github.com/VictoriaMetrics/VictoriaMetrics/app/vmselect/querystats" - "github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil" "github.com/VictoriaMetrics/VictoriaMetrics/lib/decimal" "github.com/VictoriaMetrics/VictoriaMetrics/lib/querytracer" "github.com/VictoriaMetrics/VictoriaMetrics/lib/storage" @@ -128,7 +127,7 @@ func timeseriesToResult(tss []*timeseries, maySort bool) ([]netstorage.Result, e bb := bbPool.Get() for i, ts := range tss { bb.B = marshalMetricNameSorted(bb.B[:0], &ts.MetricName) - k := bytesutil.InternBytes(bb.B) + k := string(bb.B) if _, ok := m[k]; ok { return nil, fmt.Errorf(`duplicate output timeseries: %s`, stringMetricName(&ts.MetricName)) } diff --git a/app/vmselect/promql/rollup_result_cache.go b/app/vmselect/promql/rollup_result_cache.go index 376867db0..b5ecaf147 100644 --- a/app/vmselect/promql/rollup_result_cache.go +++ b/app/vmselect/promql/rollup_result_cache.go @@ -486,8 +486,7 @@ func mergeTimeseries(a, b []*timeseries, bStart int64, ec *EvalConfig) []*timese defer bbPool.Put(bb) for _, ts := range a { bb.B = marshalMetricNameSorted(bb.B[:0], &ts.MetricName) - k := bytesutil.InternBytes(bb.B) - m[k] = ts + m[string(bb.B)] = ts } rvs := make([]*timeseries, 0, len(a)) @@ -499,7 +498,7 @@ func mergeTimeseries(a, b []*timeseries, bStart int64, ec *EvalConfig) []*timese tmp.MetricName.MoveFrom(&tsB.MetricName) bb.B = marshalMetricNameSorted(bb.B[:0], &tmp.MetricName) - k := bytesutil.InternBytes(bb.B) + k := string(bb.B) tsA := m[k] if tsA == nil { tStart := ec.Start diff --git a/app/vmselect/promql/transform.go b/app/vmselect/promql/transform.go index d61acf08b..25ff45fbe 100644 --- a/app/vmselect/promql/transform.go +++ b/app/vmselect/promql/transform.go @@ -420,7 +420,7 @@ func transformBucketsLimit(tfa *transformFuncArg) ([]*timeseries, error) { mn.CopyFrom(&ts.MetricName) mn.RemoveTag("le") b = marshalMetricNameSorted(b[:0], &mn) - k := bytesutil.InternBytes(b) + k := bytesutil.ToUnsafeString(b) m[k] = append(m[k], x{ le: le, ts: ts, @@ -523,7 +523,7 @@ func vmrangeBucketsToLE(tss []*timeseries) []*timeseries { ts.MetricName.RemoveTag("le") ts.MetricName.RemoveTag("vmrange") bb.B = marshalMetricNameSorted(bb.B[:0], &ts.MetricName) - k := bytesutil.InternBytes(bb.B) + k := string(bb.B) m[k] = append(m[k], x{ startStr: startStr, endStr: endStr, @@ -1023,7 +1023,7 @@ func groupLeTimeseries(tss []*timeseries) map[string][]leTimeseries { ts.MetricName.ResetMetricGroup() ts.MetricName.RemoveTag("le") bb.B = marshalMetricTagsSorted(bb.B[:0], &ts.MetricName) - k := bytesutil.InternBytes(bb.B) + k := string(bb.B) m[k] = append(m[k], leTimeseries{ le: le, ts: ts, @@ -1657,7 +1657,7 @@ func transformUnion(tfa *transformFuncArg) ([]*timeseries, error) { for _, arg := range args { for _, ts := range arg { bb.B = marshalMetricNameSorted(bb.B[:0], &ts.MetricName) - k := bytesutil.InternBytes(bb.B) + k := string(bb.B) if m[k] { continue } diff --git a/docs/CHANGELOG.md b/docs/CHANGELOG.md index 6d998adbb..b07737344 100644 --- a/docs/CHANGELOG.md +++ b/docs/CHANGELOG.md @@ -40,6 +40,8 @@ The sandbox cluster installation is running under the constant load generated by * BUGFIX: [vmalert](https://docs.victoriametrics.com/vmalert.html): strip sensitive information such as auth headers or passwords from datasource, remote-read, remote-write or notifier URLs in log messages or UI. This behavior is by default and is controlled via `-datasource.showURL`, `-remoteRead.showURL`, `remoteWrite.showURL` or `-notifier.showURL` cmd-line flags. See [this issue](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5044). +* BUGFIX: [vmselect](https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html): improve performance and memory usage during query processing on machines with big number of CPU cores. See [this issue](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5087) for details. + ## [v1.94.0](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.94.0) Released at 2023-10-02