mirror of
https://github.com/VictoriaMetrics/VictoriaMetrics.git
synced 2025-01-20 15:29:24 +01:00
28a9e92b5e
- Reduce memory usage by up to 5x when de-duplicating samples across big number of time series. - Reduce memory usage by up to 5x when aggregating across big number of output time series. - Add lib/promutils.LabelsCompressor, which is going to be used by other VictoriaMetrics components for reducing memory usage for marshaled []prompbmarshal.Label. - Add `dedup_interval` option at aggregation config, which allows setting individual deduplication intervals per each aggregation. - Add `keep_metric_names` option at aggregation config, which allows keeping the original metric names in the output samples. - Add `unique_samples` output, which counts the number of unique sample values. - Add `increase_prometheus` and `total_prometheus` outputs, which ignore the first sample per each newly encountered time series. - Use 64-bit hashes instead of marshaled labels as map keys when calculating `count_series` output. This makes obsolete https://github.com/VictoriaMetrics/VictoriaMetrics/pull/5579 - Expose various metrics, which may help debugging stream aggregation: - vm_streamaggr_dedup_state_size_bytes - the size of data structures responsible for deduplication - vm_streamaggr_dedup_state_items_count - the number of items in the deduplication data structures - vm_streamaggr_labels_compressor_size_bytes - the size of labels compressor data structures - vm_streamaggr_labels_compressor_items_count - the number of entries in the labels compressor - vm_streamaggr_flush_duration_seconds - a histogram, which shows the duration of stream aggregation flushes - vm_streamaggr_dedup_flush_duration_seconds - a histogram, which shows the duration of deduplication flushes - vm_streamaggr_flush_timeouts_total - counter for timed out stream aggregation flushes, which took longer than the configured interval - vm_streamaggr_dedup_flush_timeouts_total - counter for timed out deduplication flushes, which took longer than the configured dedup_interval - Actualize docs/stream-aggregation.md The memory usage reduction increases CPU usage during stream aggregation by up to 30%. This commit is based on https://github.com/VictoriaMetrics/VictoriaMetrics/pull/5850 Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5898
49 lines
1016 B
Go
49 lines
1016 B
Go
package streamaggr
|
|
|
|
import (
|
|
"fmt"
|
|
"sync/atomic"
|
|
"testing"
|
|
)
|
|
|
|
func BenchmarkDedupAggr(b *testing.B) {
|
|
for _, samplesPerPush := range []int{1, 10, 100, 1_000, 10_000, 100_000} {
|
|
b.Run(fmt.Sprintf("samplesPerPush_%d", samplesPerPush), func(b *testing.B) {
|
|
benchmarkDedupAggr(b, samplesPerPush)
|
|
})
|
|
}
|
|
}
|
|
|
|
func benchmarkDedupAggr(b *testing.B, samplesPerPush int) {
|
|
flushSamples := func(samples []pushSample) {
|
|
Sink.Add(uint64(len(samples)))
|
|
}
|
|
|
|
const loops = 2
|
|
benchSamples := newBenchSamples(samplesPerPush)
|
|
da := newDedupAggr()
|
|
|
|
b.ReportAllocs()
|
|
b.SetBytes(int64(samplesPerPush * loops))
|
|
b.RunParallel(func(pb *testing.PB) {
|
|
for pb.Next() {
|
|
for i := 0; i < loops; i++ {
|
|
da.pushSamples(benchSamples)
|
|
}
|
|
da.flush(flushSamples)
|
|
}
|
|
})
|
|
}
|
|
|
|
func newBenchSamples(count int) []pushSample {
|
|
samples := make([]pushSample, count)
|
|
for i := range samples {
|
|
sample := &samples[i]
|
|
sample.key = fmt.Sprintf("key_%d", i)
|
|
sample.value = float64(i)
|
|
}
|
|
return samples
|
|
}
|
|
|
|
var Sink atomic.Uint64
|