VictoriaMetrics/lib/storage/index_db_timing_test.go
Aliaksandr Valialkin 67beb8c856
lib/storage: follow-up after 2ce02a7fe6
- Document the change at docs/CHANGELOG.md
- Clarify comments for non-trivial code touched by the commit
- Improve the logic behind maybeCreateIndexes():
  - Correctly create per-day indexes if the indexdb rotation is performed during
    the first hour or the last hour of the day by UTC.
    Previously there was a possibility of missing index entries on that day.
  - Increase the duration for creating new indexes in the current indexdb for up to 22 hours
    after indexdb rotation. This should reduce the increased resource usage
    after indexdb rotation.
    It is safe to postpone index creation for the current day until the last hour
    of the current day after indexdb rotation by UTC, since the corresponding (date, ...)
    entries exist in the previous indexdb.
- Search for TSID by (date, MetricName) in both the current and the previous indexdb.
  Previously the search was performed only in the current indexdb. This could lead
  to excess creation of per-day indexes for the current day just after indexdb rotation.
- Search for (date, metricID) entries in both the current and the previous indexdb.
  Previously the search was performed only in the current indexdb. This could lead
  to excess creation of per-day indexes for the current day just after indexdb rotation.
2023-05-16 23:31:59 -07:00

356 lines
10 KiB
Go

package storage
import (
"fmt"
"os"
"regexp"
"strconv"
"sync/atomic"
"testing"
"time"
)
func BenchmarkRegexpFilterMatch(b *testing.B) {
b.ReportAllocs()
b.RunParallel(func(pb *testing.PB) {
re := regexp.MustCompile(`.*foo-bar-baz.*`)
b := []byte("fdsffd foo-bar-baz assd fdsfad dasf dsa")
for pb.Next() {
if !re.Match(b) {
panic("BUG: regexp must match!")
}
b[0]++
}
})
}
func BenchmarkRegexpFilterMismatch(b *testing.B) {
b.ReportAllocs()
b.RunParallel(func(pb *testing.PB) {
re := regexp.MustCompile(`.*foo-bar-baz.*`)
b := []byte("fdsffd foo-bar sfddsf assd nmn,mfdsdsakj")
for pb.Next() {
if re.Match(b) {
panic("BUG: regexp mustn't match!")
}
b[0]++
}
})
}
func BenchmarkIndexDBAddTSIDs(b *testing.B) {
const recordsPerLoop = 1e3
s := newTestStorage()
defer stopTestStorage(s)
dbName := nextIndexDBTableName()
var isReadOnly uint32
db := mustOpenIndexDB(dbName, s, 0, &isReadOnly)
defer func() {
db.MustClose()
if err := os.RemoveAll(dbName); err != nil {
b.Fatalf("cannot remove indexDB: %s", err)
}
}()
var goroutineID uint32
b.ReportAllocs()
b.SetBytes(recordsPerLoop)
b.ResetTimer()
b.RunParallel(func(pb *testing.PB) {
var mn MetricName
var genTSID generationTSID
mn.AccountID = atomic.AddUint32(&goroutineID, 1)
// The most common tags.
mn.Tags = []Tag{
{
Key: []byte("job"),
},
{
Key: []byte("instance"),
},
}
startOffset := 0
for pb.Next() {
benchmarkIndexDBAddTSIDs(db, &genTSID, &mn, startOffset, recordsPerLoop)
startOffset += recordsPerLoop
}
})
b.StopTimer()
}
func benchmarkIndexDBAddTSIDs(db *indexDB, genTSID *generationTSID, mn *MetricName, startOffset, recordsPerLoop int) {
var metricName []byte
var metricNameRaw []byte
is := db.getIndexSearch(0, 0, noDeadline)
defer db.putIndexSearch(is)
for i := 0; i < recordsPerLoop; i++ {
mn.MetricGroup = strconv.AppendUint(mn.MetricGroup[:0], uint64(i+startOffset), 10)
for j := range mn.Tags {
mn.Tags[j].Value = strconv.AppendUint(mn.Tags[j].Value[:0], uint64(i*j), 16)
}
mn.sortTags()
metricName = mn.Marshal(metricName[:0])
metricNameRaw = mn.marshalRaw(metricNameRaw[:0])
if err := is.GetOrCreateTSIDByName(genTSID, metricName, metricNameRaw, 0); err != nil {
panic(fmt.Errorf("cannot insert record: %w", err))
}
}
}
func BenchmarkHeadPostingForMatchers(b *testing.B) {
// This benchmark is equivalent to https://github.com/prometheus/prometheus/blob/23c0299d85bfeb5d9b59e994861553a25ca578e5/tsdb/head_bench_test.go#L52
// See https://www.robustperception.io/evaluating-performance-and-correctness for more details.
s := newTestStorage()
defer stopTestStorage(s)
dbName := nextIndexDBTableName()
var isReadOnly uint32
db := mustOpenIndexDB(dbName, s, 0, &isReadOnly)
defer func() {
db.MustClose()
if err := os.RemoveAll(dbName); err != nil {
b.Fatalf("cannot remove indexDB: %s", err)
}
}()
// Fill the db with data as in https://github.com/prometheus/prometheus/blob/23c0299d85bfeb5d9b59e994861553a25ca578e5/tsdb/head_bench_test.go#L66
const accountID = 34327843
const projectID = 893433
var mn MetricName
var metricName []byte
var metricNameRaw []byte
var tsid TSID
is := db.getIndexSearch(0, 0, noDeadline)
defer db.putIndexSearch(is)
addSeries := func(kvs ...string) {
mn.Reset()
for i := 0; i < len(kvs); i += 2 {
mn.AddTag(kvs[i], kvs[i+1])
}
mn.sortTags()
mn.AccountID = accountID
mn.ProjectID = projectID
metricName = mn.Marshal(metricName[:0])
metricNameRaw = mn.marshalRaw(metricNameRaw[:0])
if err := is.createTSIDByMetricName(&tsid, metricName, metricNameRaw, 0); err != nil {
b.Fatalf("cannot insert record: %s", err)
}
}
for n := 0; n < 10; n++ {
ns := strconv.Itoa(n)
for i := 0; i < 100000; i++ {
ix := strconv.Itoa(i)
addSeries("i", ix, "n", ns, "j", "foo")
// Have some series that won't be matched, to properly test inverted matches.
addSeries("i", ix, "n", ns, "j", "bar")
addSeries("i", ix, "n", "0_"+ns, "j", "bar")
addSeries("i", ix, "n", "1_"+ns, "j", "bar")
addSeries("i", ix, "n", "2_"+ns, "j", "foo")
}
}
// Make sure all the items can be searched.
db.tb.DebugFlush()
b.ResetTimer()
benchSearch := func(b *testing.B, tfs *TagFilters, expectedMetricIDs int) {
is := db.getIndexSearch(tfs.accountID, tfs.projectID, noDeadline)
defer db.putIndexSearch(is)
tfss := []*TagFilters{tfs}
tr := TimeRange{
MinTimestamp: 0,
MaxTimestamp: timestampFromTime(time.Now()),
}
for i := 0; i < b.N; i++ {
metricIDs, err := is.searchMetricIDs(nil, tfss, tr, 2e9)
if err != nil {
b.Fatalf("unexpected error in searchMetricIDs: %s", err)
}
if len(metricIDs) != expectedMetricIDs {
b.Fatalf("unexpected metricIDs found; got %d; want %d", len(metricIDs), expectedMetricIDs)
}
}
}
addTagFilter := func(tfs *TagFilters, key, value string, isNegative, isRegexp bool) {
if err := tfs.Add([]byte(key), []byte(value), isNegative, isRegexp); err != nil {
b.Fatalf("cannot add tag filter %q=%q, isNegative=%v, isRegexp=%v", key, value, isNegative, isRegexp)
}
}
b.Run(`n="1"`, func(b *testing.B) {
tfs := NewTagFilters(accountID, projectID)
addTagFilter(tfs, "n", "1", false, false)
benchSearch(b, tfs, 2e5)
})
b.Run(`n="1",j="foo"`, func(b *testing.B) {
tfs := NewTagFilters(accountID, projectID)
addTagFilter(tfs, "n", "1", false, false)
addTagFilter(tfs, "j", "foo", false, false)
benchSearch(b, tfs, 1e5)
})
b.Run(`j="foo",n="1"`, func(b *testing.B) {
tfs := NewTagFilters(accountID, projectID)
addTagFilter(tfs, "j", "foo", false, false)
addTagFilter(tfs, "n", "1", false, false)
benchSearch(b, tfs, 1e5)
})
b.Run(`n="1",j!="foo"`, func(b *testing.B) {
tfs := NewTagFilters(accountID, projectID)
addTagFilter(tfs, "n", "1", false, false)
addTagFilter(tfs, "j", "foo", true, false)
benchSearch(b, tfs, 1e5)
})
b.Run(`i=~".*"`, func(b *testing.B) {
tfs := NewTagFilters(accountID, projectID)
addTagFilter(tfs, "i", ".*", false, true)
benchSearch(b, tfs, 0)
})
b.Run(`i=~".+"`, func(b *testing.B) {
tfs := NewTagFilters(accountID, projectID)
addTagFilter(tfs, "i", ".+", false, true)
benchSearch(b, tfs, 5e6)
})
b.Run(`i=~""`, func(b *testing.B) {
tfs := NewTagFilters(accountID, projectID)
addTagFilter(tfs, "i", "", false, true)
benchSearch(b, tfs, 0)
})
b.Run(`i!=""`, func(b *testing.B) {
tfs := NewTagFilters(accountID, projectID)
addTagFilter(tfs, "i", "", true, false)
benchSearch(b, tfs, 5e6)
})
b.Run(`n="1",i=~".*",j="foo"`, func(b *testing.B) {
tfs := NewTagFilters(accountID, projectID)
addTagFilter(tfs, "n", "1", false, false)
addTagFilter(tfs, "i", ".*", false, true)
addTagFilter(tfs, "j", "foo", false, false)
benchSearch(b, tfs, 1e5)
})
b.Run(`n="1",i=~".*",i!="2",j="foo"`, func(b *testing.B) {
tfs := NewTagFilters(accountID, projectID)
addTagFilter(tfs, "n", "1", false, false)
addTagFilter(tfs, "i", ".*", false, true)
addTagFilter(tfs, "i", "2", true, false)
addTagFilter(tfs, "j", "foo", false, false)
benchSearch(b, tfs, 1e5-1)
})
b.Run(`n="1",i!=""`, func(b *testing.B) {
tfs := NewTagFilters(accountID, projectID)
addTagFilter(tfs, "n", "1", false, false)
addTagFilter(tfs, "i", "", true, false)
benchSearch(b, tfs, 2e5)
})
b.Run(`n="1",i!="",j="foo"`, func(b *testing.B) {
tfs := NewTagFilters(accountID, projectID)
addTagFilter(tfs, "n", "1", false, false)
addTagFilter(tfs, "i", "", true, false)
addTagFilter(tfs, "j", "foo", false, false)
benchSearch(b, tfs, 1e5)
})
b.Run(`n="1",i=~".+",j="foo"`, func(b *testing.B) {
tfs := NewTagFilters(accountID, projectID)
addTagFilter(tfs, "n", "1", false, false)
addTagFilter(tfs, "i", ".+", false, true)
addTagFilter(tfs, "j", "foo", false, false)
benchSearch(b, tfs, 1e5)
})
b.Run(`n="1",i=~"1.+",j="foo"`, func(b *testing.B) {
tfs := NewTagFilters(accountID, projectID)
addTagFilter(tfs, "n", "1", false, false)
addTagFilter(tfs, "i", "1.+", false, true)
addTagFilter(tfs, "j", "foo", false, false)
benchSearch(b, tfs, 11110)
})
b.Run(`n="1",i=~".+",i!="2",j="foo"`, func(b *testing.B) {
tfs := NewTagFilters(accountID, projectID)
addTagFilter(tfs, "n", "1", false, false)
addTagFilter(tfs, "i", ".+", false, true)
addTagFilter(tfs, "i", "2", true, false)
addTagFilter(tfs, "j", "foo", false, false)
benchSearch(b, tfs, 1e5-1)
})
b.Run(`n="1",i=~".+",i!~"2.*",j="foo"`, func(b *testing.B) {
tfs := NewTagFilters(accountID, projectID)
addTagFilter(tfs, "n", "1", false, false)
addTagFilter(tfs, "i", ".+", false, true)
addTagFilter(tfs, "i", "2.*", true, true)
addTagFilter(tfs, "j", "foo", false, false)
benchSearch(b, tfs, 88889)
})
}
func BenchmarkIndexDBGetTSIDs(b *testing.B) {
s := newTestStorage()
defer stopTestStorage(s)
dbName := nextIndexDBTableName()
var isReadOnly uint32
db := mustOpenIndexDB(dbName, s, 0, &isReadOnly)
defer func() {
db.MustClose()
if err := os.RemoveAll(dbName); err != nil {
b.Fatalf("cannot remove indexDB: %s", err)
}
}()
const recordsPerLoop = 1000
const accountsCount = 111
const projectsCount = 33333
const recordsCount = 1e5
// Fill the db with recordsCount records.
var mn MetricName
mn.MetricGroup = []byte("rps")
for i := 0; i < 2; i++ {
key := fmt.Sprintf("key_%d", i)
value := fmt.Sprintf("value_%d", i)
mn.AddTag(key, value)
}
var genTSID generationTSID
var metricName []byte
var metricNameRaw []byte
is := db.getIndexSearch(0, 0, noDeadline)
defer db.putIndexSearch(is)
for i := 0; i < recordsCount; i++ {
mn.AccountID = uint32(i % accountsCount)
mn.ProjectID = uint32(i % projectsCount)
mn.sortTags()
metricName = mn.Marshal(metricName[:0])
metricNameRaw = mn.marshalRaw(metricName[:0])
if err := is.GetOrCreateTSIDByName(&genTSID, metricName, metricNameRaw, 0); err != nil {
b.Fatalf("cannot insert record: %s", err)
}
}
b.SetBytes(recordsPerLoop)
b.ReportAllocs()
b.ResetTimer()
b.RunParallel(func(pb *testing.PB) {
var tsidLocal generationTSID
var metricNameLocal []byte
var metricNameLocalRaw []byte
mnLocal := mn
is := db.getIndexSearch(0, 0, noDeadline)
defer db.putIndexSearch(is)
for pb.Next() {
for i := 0; i < recordsPerLoop; i++ {
mnLocal.AccountID = uint32(i % accountsCount)
mnLocal.ProjectID = uint32(i % projectsCount)
mnLocal.sortTags()
metricNameLocal = mnLocal.Marshal(metricNameLocal[:0])
metricNameLocalRaw = mnLocal.marshalRaw(metricNameLocalRaw[:0])
if err := is.GetOrCreateTSIDByName(&tsidLocal, metricNameLocal, metricNameLocalRaw, 0); err != nil {
panic(fmt.Errorf("cannot obtain tsid: %w", err))
}
}
}
})
b.StopTimer()
}