diff --git a/app/vmselect/netstorage/tmp_blocks_file.go b/app/vmselect/netstorage/tmp_blocks_file.go index f6b39c284..f3f6a9a70 100644 --- a/app/vmselect/netstorage/tmp_blocks_file.go +++ b/app/vmselect/netstorage/tmp_blocks_file.go @@ -7,6 +7,7 @@ import ( "sync" "github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil" + "github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil" "github.com/VictoriaMetrics/VictoriaMetrics/lib/fs" "github.com/VictoriaMetrics/VictoriaMetrics/lib/logger" "github.com/VictoriaMetrics/VictoriaMetrics/lib/memory" @@ -14,6 +15,10 @@ import ( "github.com/VictoriaMetrics/metrics" ) +var tmpBufSize = flagutil.NewBytes("search.inmemoryBufSizeBytes", 0, "Size for in-memory data blocks used during processing search requests. "+ + "By default, the size is automatically calculated based on available memory. "+ + "Adjust this flag value if you observe that vm_tmp_blocks_max_inmemory_file_size_bytes metric constantly shows much higher values than vm_tmp_blocks_inmemory_file_size_bytes. See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6851") + // InitTmpBlocksDir initializes directory to store temporary search results. // // It stores data in system-defined temporary directory if tmpDirPath is empty. @@ -29,6 +34,9 @@ func InitTmpBlocksDir(tmpDirPath string) { var tmpBlocksDir string func maxInmemoryTmpBlocksFile() int { + if tmpBufSize.IntN() > 0 { + return tmpBufSize.IntN() + } mem := memory.Allowed() maxLen := mem / 1024 if maxLen < 64*1024 { @@ -40,9 +48,12 @@ func maxInmemoryTmpBlocksFile() int { return maxLen } -var _ = metrics.NewGauge(`vm_tmp_blocks_max_inmemory_file_size_bytes`, func() float64 { - return float64(maxInmemoryTmpBlocksFile()) -}) +var ( + _ = metrics.NewGauge(`vm_tmp_blocks_max_inmemory_file_size_bytes`, func() float64 { + return float64(maxInmemoryTmpBlocksFile()) + }) + tmpBufSizeSummary = metrics.NewSummary(`vm_tmp_blocks_inmemory_file_size_bytes`) +) type tmpBlocksFile struct { buf []byte @@ -65,6 +76,8 @@ func getTmpBlocksFile() *tmpBlocksFile { func putTmpBlocksFile(tbf *tmpBlocksFile) { tbf.MustClose() + bufLen := tbf.Len() + tmpBufSizeSummary.Update(float64(bufLen)) tbf.buf = tbf.buf[:0] tbf.f = nil tbf.r = nil diff --git a/docs/Cluster-VictoriaMetrics.md b/docs/Cluster-VictoriaMetrics.md index ea47ef628..e2c60c06b 100644 --- a/docs/Cluster-VictoriaMetrics.md +++ b/docs/Cluster-VictoriaMetrics.md @@ -1582,6 +1582,9 @@ Below is the output for `/path/to/vmselect -help`: Whether to fix lookback interval to 'step' query arg value. If set to true, the query model becomes closer to InfluxDB data model. If set to true, then -search.maxLookback and -search.maxStalenessInterval are ignored -search.skipSlowReplicas Whether to skip -replicationFactor - 1 slowest vmstorage nodes during querying. Enabling this setting may improve query speed, but it could also lead to incomplete results if some queried data has less than -replicationFactor copies at vmstorage nodes. Consider enabling this setting only if all the queried data contains -replicationFactor copies in the cluster + -search.inmemoryBufSizeBytes size + Size for in-memory data blocks used during processing search requests. By default, the size is automatically calculated based on available memory. Adjust this flag value if you observe that vm_tmp_blocks_max_inmemory_file_size_bytes metric constantly shows much higher values than vm_tmp_blocks_inmemory_file_size_bytes. See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6851 + Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB (default 0) -search.treatDotsAsIsInRegexps Whether to treat dots as is in regexp label filters used in queries. For example, foo{bar=~"a.b.c"} will be automatically converted to foo{bar=~"a\\.b\\.c"}, i.e. all the dots in regexp filters will be automatically escaped in order to match only dot char instead of matching any char. Dots in ".+", ".*" and ".{n}" regexps aren't escaped. This option is DEPRECATED in favor of {__graphite__="a.*.c"} syntax for selecting metrics matching the given Graphite metrics filter -selectNode array diff --git a/docs/changelog/CHANGELOG.md b/docs/changelog/CHANGELOG.md index e3333b4f4..c237595fd 100644 --- a/docs/changelog/CHANGELOG.md +++ b/docs/changelog/CHANGELOG.md @@ -35,6 +35,7 @@ The value of `instance` label for those scrape targets will be changed from `