app/vmselect/prometheus: improve performance for /api/v1/labels and /api/v1/label/<labelName>/values on time ranges exceeding one day when match[] query arg is set

This commit is contained in:
Aliaksandr Valialkin 2020-11-16 13:45:50 +02:00
parent e969346e3e
commit 852aed62f7
2 changed files with 66 additions and 37 deletions

View file

@ -662,12 +662,28 @@ func labelValuesWithMatches(at *auth.Token, denyPartialResponse bool, labelName
MaxTimestamp: end,
TagFilterss: tagFilterss,
}
rss, isPartial, err := netstorage.ProcessSearchQuery(at, denyPartialResponse, sq, false, deadline)
m := make(map[string]struct{})
isPartial := false
if end-start > 24*3600*1000 {
// It is cheaper to call SearchMetricNames on time ranges exceeding a day.
mns, isPartialResponse, err := netstorage.SearchMetricNames(at, denyPartialResponse, sq, deadline)
if err != nil {
return nil, false, fmt.Errorf("cannot fetch time series for %q: %w", sq, err)
}
isPartial = isPartialResponse
for _, mn := range mns {
labelValue := mn.GetTagValue(labelName)
if len(labelValue) == 0 {
continue
}
m[string(labelValue)] = struct{}{}
}
} else {
rss, isPartialResponse, err := netstorage.ProcessSearchQuery(at, denyPartialResponse, sq, false, deadline)
if err != nil {
return nil, false, fmt.Errorf("cannot fetch data for %q: %w", sq, err)
}
m := make(map[string]struct{})
isPartial = isPartialResponse
var mLock sync.Mutex
err = rss.RunParallel(func(rs *netstorage.Result, workerID uint) error {
labelValue := rs.MetricName.GetTagValue(labelName)
@ -682,7 +698,7 @@ func labelValuesWithMatches(at *auth.Token, denyPartialResponse bool, labelName
if err != nil {
return nil, false, fmt.Errorf("error when data fetching: %w", err)
}
}
labelValues := make([]string, 0, len(m))
for labelValue := range m {
labelValues = append(labelValues, labelValue)
@ -856,19 +872,31 @@ func labelsWithMatches(at *auth.Token, denyPartialResponse bool, matches []strin
MaxTimestamp: end,
TagFilterss: tagFilterss,
}
rss, isPartial, err := netstorage.ProcessSearchQuery(at, denyPartialResponse, sq, false, deadline)
m := make(map[string]struct{})
isPartial := false
if end-start > 24*3600*1000 {
// It is cheaper to call SearchMetricNames on time ranges exceeding a day.
mns, isPartialResponse, err := netstorage.SearchMetricNames(at, denyPartialResponse, sq, deadline)
if err != nil {
return nil, false, fmt.Errorf("cannot fetch time series for %q: %w", sq, err)
}
isPartial = isPartialResponse
for _, mn := range mns {
for _, tag := range mn.Tags {
m[string(tag.Key)] = struct{}{}
}
}
} else {
rss, isPartialResponse, err := netstorage.ProcessSearchQuery(at, denyPartialResponse, sq, false, deadline)
if err != nil {
return nil, false, fmt.Errorf("cannot fetch data for %q: %w", sq, err)
}
m := make(map[string]struct{})
isPartial = isPartialResponse
var mLock sync.Mutex
err = rss.RunParallel(func(rs *netstorage.Result, workerID uint) error {
mLock.Lock()
tags := rs.MetricName.Tags
for i := range tags {
t := &tags[i]
m[string(t.Key)] = struct{}{}
for _, tag := range rs.MetricName.Tags {
m[string(tag.Key)] = struct{}{}
}
m["__name__"] = struct{}{}
mLock.Unlock()
@ -877,6 +905,7 @@ func labelsWithMatches(at *auth.Token, denyPartialResponse bool, matches []strin
if err != nil {
return nil, false, fmt.Errorf("error when data fetching: %w", err)
}
}
labels := make([]string, 0, len(m))
for label := range m {

View file

@ -7,7 +7,7 @@
* FEATURE: vmselect: add `"isPartial":{true|false}` field in JSON output for `/api/v1/*` functions
from [Prometheus querying API](https://prometheus.io/docs/prometheus/latest/querying/api/). `"isPartial":true` is set if the response contains partial data
because of a part of `vmstorage` nodes were unavailable during query processing.
* FEATURE: improve performance for `/api/v1/series` on time ranges exceeding one day.
* FEATURE: improve performance for `/api/v1/series`, `/api/v1/labels` and `/api/v1/label/<labelName>/values` on time ranges exceeding one day.
* FEATURE: vmagent: reduce memory usage when service discovery detects big number of scrape targets and the set of discovered targets changes over time.
See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/825
* FEATURE: vmagent: add `-promscrape.dropOriginalLabels` command-line option, which can be used for reducing memory usage when scraping big number of targets.