mirror of
https://github.com/VictoriaMetrics/VictoriaMetrics.git
synced 2024-12-16 00:41:24 +01:00
4fd2b6cd16
The previous implementation treated extra labels (global and rule labels) as separate label set to returned time series labels. Hence, time series always contained only original labels and alert ID was generated from sorted labels key-values. Extra labels didn't affect the generated ID and were applied on the following actions: - templating for Summary and Annotations; - persisting state via remote write; - restoring state via remote read. Such behaviour caused difficulties on restore procedure because extra labels had to be dropped before checking the alert ID, but that not always worked. Consider the case when expression returns the following time series `up{job="foo"}` and rule has extra label `job=bar`. This would mean that restored alert ID will be always different to the real time series because of collision. To solve the situation extra labels are now always applied beforehand and `vmalert` doesn't store original labels anymore. However, this could result into a new error situation. Consider the case when expression returns two time series `up{job="foo"}` and `up{job="baz"}`, while rule has extra label `job=bar`. In such case, applying extra labels will result into two identical time series and `vmalert` will return error: `result contains metrics with the same labelset after applying rule labels` https://github.com/VictoriaMetrics/VictoriaMetrics/issues/870
224 lines
4.9 KiB
Go
224 lines
4.9 KiB
Go
package main
|
|
|
|
import (
|
|
"context"
|
|
"sort"
|
|
"testing"
|
|
"time"
|
|
|
|
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/config"
|
|
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
|
|
)
|
|
|
|
func init() {
|
|
// Disable rand sleep on group start during tests in order to speed up test execution.
|
|
// Rand sleep is needed only in prod code.
|
|
skipRandSleepOnGroupStart = true
|
|
}
|
|
|
|
func TestUpdateWith(t *testing.T) {
|
|
testCases := []struct {
|
|
name string
|
|
currentRules []config.Rule
|
|
newRules []config.Rule
|
|
}{
|
|
{
|
|
"new rule",
|
|
nil,
|
|
[]config.Rule{{Alert: "bar"}},
|
|
},
|
|
{
|
|
"update alerting rule",
|
|
[]config.Rule{{
|
|
Alert: "foo",
|
|
Expr: "up > 0",
|
|
For: config.NewPromDuration(time.Second),
|
|
Labels: map[string]string{
|
|
"bar": "baz",
|
|
},
|
|
Annotations: map[string]string{
|
|
"summary": "{{ $value|humanize }}",
|
|
"description": "{{$labels}}",
|
|
},
|
|
}},
|
|
[]config.Rule{{
|
|
Alert: "foo",
|
|
Expr: "up > 10",
|
|
For: config.NewPromDuration(time.Second),
|
|
Labels: map[string]string{
|
|
"baz": "bar",
|
|
},
|
|
Annotations: map[string]string{
|
|
"summary": "none",
|
|
},
|
|
}},
|
|
},
|
|
{
|
|
"update recording rule",
|
|
[]config.Rule{{
|
|
Record: "foo",
|
|
Expr: "max(up)",
|
|
Labels: map[string]string{
|
|
"bar": "baz",
|
|
},
|
|
}},
|
|
[]config.Rule{{
|
|
Record: "foo",
|
|
Expr: "min(up)",
|
|
Labels: map[string]string{
|
|
"baz": "bar",
|
|
},
|
|
}},
|
|
},
|
|
{
|
|
"empty rule",
|
|
[]config.Rule{{Alert: "foo"}, {Record: "bar"}},
|
|
nil,
|
|
},
|
|
{
|
|
"multiple rules",
|
|
[]config.Rule{
|
|
{Alert: "bar"},
|
|
{Alert: "baz"},
|
|
{Alert: "foo"},
|
|
},
|
|
[]config.Rule{
|
|
{Alert: "baz"},
|
|
{Record: "foo"},
|
|
},
|
|
},
|
|
{
|
|
"replace rule",
|
|
[]config.Rule{{Alert: "foo1"}},
|
|
[]config.Rule{{Alert: "foo2"}},
|
|
},
|
|
{
|
|
"replace multiple rules",
|
|
[]config.Rule{
|
|
{Alert: "foo1"},
|
|
{Record: "foo2"},
|
|
{Alert: "foo3"},
|
|
},
|
|
[]config.Rule{
|
|
{Alert: "foo3"},
|
|
{Alert: "foo4"},
|
|
{Record: "foo5"},
|
|
},
|
|
},
|
|
}
|
|
|
|
for _, tc := range testCases {
|
|
t.Run(tc.name, func(t *testing.T) {
|
|
g := &Group{Name: "test"}
|
|
for _, r := range tc.currentRules {
|
|
r.ID = config.HashRule(r)
|
|
g.Rules = append(g.Rules, g.newRule(r))
|
|
}
|
|
|
|
ng := &Group{Name: "test"}
|
|
for _, r := range tc.newRules {
|
|
r.ID = config.HashRule(r)
|
|
ng.Rules = append(ng.Rules, ng.newRule(r))
|
|
}
|
|
|
|
err := g.updateWith(ng)
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
|
|
if len(g.Rules) != len(tc.newRules) {
|
|
t.Fatalf("expected to have %d rules; got: %d",
|
|
len(g.Rules), len(tc.newRules))
|
|
}
|
|
sort.Slice(g.Rules, func(i, j int) bool {
|
|
return g.Rules[i].ID() < g.Rules[j].ID()
|
|
})
|
|
sort.Slice(ng.Rules, func(i, j int) bool {
|
|
return ng.Rules[i].ID() < ng.Rules[j].ID()
|
|
})
|
|
for i, r := range g.Rules {
|
|
got, want := r, ng.Rules[i]
|
|
if got.ID() != want.ID() {
|
|
t.Fatalf("expected to have rule %q; got %q", want, got)
|
|
}
|
|
if err := compareRules(t, got, want); err != nil {
|
|
t.Fatalf("comparsion error: %s", err)
|
|
}
|
|
}
|
|
})
|
|
}
|
|
}
|
|
|
|
func TestGroupStart(t *testing.T) {
|
|
// TODO: make parsing from string instead of file
|
|
groups, err := config.Parse([]string{"config/testdata/rules1-good.rules"}, true, true)
|
|
if err != nil {
|
|
t.Fatalf("failed to parse rules: %s", err)
|
|
}
|
|
const evalInterval = time.Millisecond
|
|
g := newGroup(groups[0], evalInterval, map[string]string{"cluster": "east-1"})
|
|
g.Concurrency = 2
|
|
|
|
fn := &fakeNotifier{}
|
|
fs := &fakeQuerier{}
|
|
|
|
const inst1, inst2, job = "foo", "bar", "baz"
|
|
m1 := metricWithLabels(t, "instance", inst1, "job", job)
|
|
m2 := metricWithLabels(t, "instance", inst2, "job", job)
|
|
|
|
r := g.Rules[0].(*AlertingRule)
|
|
alert1, err := r.newAlert(m1, time.Now())
|
|
if err != nil {
|
|
t.Fatalf("faield to create alert: %s", err)
|
|
}
|
|
alert1.State = notifier.StateFiring
|
|
// add external label
|
|
alert1.Labels["cluster"] = "east-1"
|
|
// add rule labels - see config/testdata/rules1-good.rules
|
|
alert1.Labels["label"] = "bar"
|
|
alert1.Labels["host"] = inst1
|
|
alert1.ID = hash(m1)
|
|
|
|
alert2, err := r.newAlert(m2, time.Now())
|
|
if err != nil {
|
|
t.Fatalf("faield to create alert: %s", err)
|
|
}
|
|
alert2.State = notifier.StateFiring
|
|
// add external label
|
|
alert2.Labels["cluster"] = "east-1"
|
|
// add rule labels - see config/testdata/rules1-good.rules
|
|
alert2.Labels["label"] = "bar"
|
|
alert2.Labels["host"] = inst2
|
|
alert2.ID = hash(m2)
|
|
|
|
finished := make(chan struct{})
|
|
fs.add(m1)
|
|
fs.add(m2)
|
|
go func() {
|
|
g.start(context.Background(), fs, []notifier.Notifier{fn}, nil)
|
|
close(finished)
|
|
}()
|
|
|
|
// wait for multiple evals
|
|
time.Sleep(20 * evalInterval)
|
|
|
|
gotAlerts := fn.getAlerts()
|
|
expectedAlerts := []notifier.Alert{*alert1, *alert2}
|
|
compareAlerts(t, expectedAlerts, gotAlerts)
|
|
|
|
// reset previous data
|
|
fs.reset()
|
|
// and set only one datapoint for response
|
|
fs.add(m1)
|
|
|
|
// wait for multiple evals
|
|
time.Sleep(20 * evalInterval)
|
|
|
|
gotAlerts = fn.getAlerts()
|
|
expectedAlerts = []notifier.Alert{*alert1}
|
|
compareAlerts(t, expectedAlerts, gotAlerts)
|
|
|
|
g.close()
|
|
<-finished
|
|
}
|