mirror of
https://github.com/prometheus/prometheus.git
synced 2024-09-20 07:47:31 -07:00
fc6737b7fb
tl;dr: This is not a fundamental solution to the indexing problem
(like tindex is) but it at least avoids utilizing the intersection
problem to the greatest possible amount.
In more detail:
Imagine the following query:
nicely:aggregating:rule{job="foo",env="prod"}
While it uses a nicely aggregating recording rule (which might have a
very low cardinality), Prometheus still intersects the low number of
fingerprints for `{__name__="nicely:aggregating:rule"}` with the many
thousands of fingerprints matching `{job="foo"}` and with the millions
of fingerprints matching `{env="prod"}`. This totally innocuous query
is dead slow if the Prometheus server has a lot of time series with
the `{env="prod"}` label. Ironically, if you make the query more
complicated, it becomes blazingly fast:
nicely:aggregating:rule{job=~"foo",env=~"prod"}
Why so? Because Prometheus only intersects with non-Equal matchers if
there are no Equal matchers. That's good in this case because it
retrieves the few fingerprints for
`{__name__="nicely:aggregating:rule"}` and then starts right ahead to
retrieve the metric for those FPs and checking individually if they
match the other matchers.
This change is generalizing the idea of when to stop intersecting FPs
and go into "retrieve metrics and check them individually against
remaining matchers" mode:
- First, sort all matchers by "expected cardinality". Matchers
matching the empty string are always worst (and never used for
intersections). Equal matchers are in general consider best, but by
using some crude heuristics, we declare some better than others
(instance labels or anything that looks like a recording rule).
- Then go through the matchers until we hit a threshold of remaining
FPs in the intersection. This threshold is higher if we are already
in the non-Equal matcher area as intersection is even more expensive
here.
- Once the threshold has been reached (or we have run out of matchers
that do not match the empty string), start with "retrieve metrics
and check them individually against remaining matchers".
A beefy server at SoundCloud was spending 67% of its CPU time in index
lookups (fingerprintsForLabelPairs), serving mostly a dashboard that
is exclusively built with recording rules. With this change, it spends
only 35% in fingerprintsForLabelPairs. The CPU usage dropped from 26
cores to 18 cores. The median latency for query_range dropped from 14s
to 50ms(!). As expected, higher percentile latency didn't improve that
much because the new approach is _occasionally_ running into the worst
case while the old one was _systematically_ doing so. The 99th
percentile latency is now about as high as the median before (14s)
while it was almost twice as high before (26s).
74 lines
2.4 KiB
Go
74 lines
2.4 KiB
Go
// Copyright 2014 The Prometheus Authors
|
|
// Licensed under the Apache License, Version 2.0 (the "License");
|
|
// you may not use this file except in compliance with the License.
|
|
// You may obtain a copy of the License at
|
|
//
|
|
// http://www.apache.org/licenses/LICENSE-2.0
|
|
//
|
|
// Unless required by applicable law or agreed to in writing, software
|
|
// distributed under the License is distributed on an "AS IS" BASIS,
|
|
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
// See the License for the specific language governing permissions and
|
|
// limitations under the License.
|
|
|
|
package metric
|
|
|
|
import (
|
|
"math/rand"
|
|
"reflect"
|
|
"sort"
|
|
"testing"
|
|
|
|
"github.com/prometheus/common/model"
|
|
)
|
|
|
|
func TestAnchoredMatcher(t *testing.T) {
|
|
m, err := NewLabelMatcher(RegexMatch, "", "foo|bar|baz")
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
|
|
if !m.Match("foo") {
|
|
t.Errorf("Expected match for %q but got none", "foo")
|
|
}
|
|
if m.Match("fooo") {
|
|
t.Errorf("Unexpected match for %q", "fooo")
|
|
}
|
|
}
|
|
|
|
func TestLabelMatchersSort(t *testing.T) {
|
|
// Line up Matchers in expected order:
|
|
want := LabelMatchers{
|
|
mustNewLabelMatcher(Equal, model.InstanceLabel, "not empty"),
|
|
mustNewLabelMatcher(Equal, model.MetricNameLabel, "a:recording:rule"),
|
|
mustNewLabelMatcher(Equal, model.MetricNameLabel, "up"),
|
|
mustNewLabelMatcher(Equal, "nothing_special but much longer", "not empty"),
|
|
mustNewLabelMatcher(Equal, "nothing_special", "not empty but longer"),
|
|
mustNewLabelMatcher(Equal, "nothing_special", "not empty"),
|
|
mustNewLabelMatcher(Equal, model.JobLabel, "not empty"),
|
|
mustNewLabelMatcher(Equal, model.BucketLabel, "not empty"),
|
|
mustNewLabelMatcher(RegexMatch, "irrelevant", "does not match empty string and is longer"),
|
|
mustNewLabelMatcher(RegexMatch, "irrelevant", "does not match empty string"),
|
|
mustNewLabelMatcher(RegexNoMatch, "irrelevant", "(matches empty string)?"),
|
|
mustNewLabelMatcher(RegexNoMatch, "irrelevant", "(matches empty string with a longer expression)?"),
|
|
mustNewLabelMatcher(NotEqual, "irrelevant", ""),
|
|
mustNewLabelMatcher(Equal, "irrelevant", ""),
|
|
}
|
|
got := make(LabelMatchers, len(want))
|
|
for i, j := range rand.Perm(len(want)) {
|
|
got[i] = want[j]
|
|
}
|
|
sort.Sort(got)
|
|
if !reflect.DeepEqual(want, got) {
|
|
t.Errorf("unexpected sorting of matchers, got %v, want %v", got, want)
|
|
}
|
|
}
|
|
|
|
func mustNewLabelMatcher(mt MatchType, name model.LabelName, val model.LabelValue) *LabelMatcher {
|
|
m, err := NewLabelMatcher(mt, name, val)
|
|
if err != nil {
|
|
panic(err)
|
|
}
|
|
return m
|
|
}
|