Alerting: Write and Delete multiple alert instances. (#54072)

Prior to this change, all alert instance writes and deletes happened
individually, in their own database transaction. This change batches up
writes or deletes for a given rule's evaluation loop into a single
transaction before applying it.

Before:
```
goos: darwin
goarch: arm64
pkg: github.com/grafana/grafana/pkg/services/ngalert/store
BenchmarkAlertInstanceOperations-8           398           2991381 ns/op         1133537 B/op      27703 allocs/op
--- BENCH: BenchmarkAlertInstanceOperations-8
    util.go:127: alert definition: {orgID: 1, UID: FovKXiRVzm} with title: "an alert definition FTvFXmRVkz" interval: 60 created
    util.go:127: alert definition: {orgID: 1, UID: foDFXmRVkm} with title: "an alert definition fovFXmRVkz" interval: 60 created
    util.go:127: alert definition: {orgID: 1, UID: VQvFuigVkm} with title: "an alert definition VwDKXmR4kz" interval: 60 created
PASS
ok      github.com/grafana/grafana/pkg/services/ngalert/store   1.619s
```

After:
```
goos: darwin
goarch: arm64
pkg: github.com/grafana/grafana/pkg/services/ngalert/store
BenchmarkAlertInstanceOperations-8          1440            816484 ns/op          352297 B/op       6529 allocs/op
--- BENCH: BenchmarkAlertInstanceOperations-8
    util.go:127: alert definition: {orgID: 1, UID: 302r_igVzm} with title: "an alert definition q0h9lmR4zz" interval: 60 created
    util.go:127: alert definition: {orgID: 1, UID: 71hrlmR4km} with title: "an alert definition nJ29_mR4zz" interval: 60 created
    util.go:127: alert definition: {orgID: 1, UID: Cahr_mR4zm} with title: "an alert definition ja2rlmg4zz" interval: 60 created
PASS
ok      github.com/grafana/grafana/pkg/services/ngalert/store   1.383s
```

So we cut time by about 75% and memory allocations by about 60% when
storing and deleting 100 instances.

This change also updates some of our tests so that they run successfully against postgreSQL - we were using random Int64s, but postgres integers, which our tables use, max out at 2^31-1
This commit is contained in:
Joe Blubaugh
2022-09-02 11:17:20 +08:00
committed by GitHub
parent d706320d0a
commit 5e4fd94413
15 changed files with 559 additions and 210 deletions

View File

@@ -2022,10 +2022,10 @@ func TestProcessEvalResults(t *testing.T) {
require.NotEmpty(t, states)
savedStates := make(map[string]models.SaveAlertInstanceCommand)
savedStates := make(map[string]models.AlertInstance)
for _, op := range instanceStore.RecordedOps {
switch q := op.(type) {
case models.SaveAlertInstanceCommand:
case models.AlertInstance:
cacheId, err := q.Labels.StringKey()
require.NoError(t, err)
savedStates[cacheId] = q
@@ -2058,28 +2058,39 @@ func TestStaleResultsHandler(t *testing.T) {
const mainOrgID int64 = 1
rule := tests.CreateTestAlertRule(t, ctx, dbstore, int64(interval.Seconds()), mainOrgID)
lastEval := evaluationTime.Add(-2 * interval)
saveCmd1 := &models.SaveAlertInstanceCommand{
RuleOrgID: rule.OrgID,
RuleUID: rule.UID,
Labels: models.InstanceLabels{"test1": "testValue1"},
State: models.InstanceStateNormal,
LastEvalTime: lastEval,
CurrentStateSince: lastEval,
CurrentStateEnd: lastEval.Add(3 * interval),
labels1 := models.InstanceLabels{"test1": "testValue1"}
_, hash1, _ := labels1.StringAndHash()
labels2 := models.InstanceLabels{"test2": "testValue2"}
_, hash2, _ := labels2.StringAndHash()
instances := []models.AlertInstance{
{
AlertInstanceKey: models.AlertInstanceKey{
RuleOrgID: rule.OrgID,
RuleUID: rule.UID,
LabelsHash: hash1,
},
CurrentState: models.InstanceStateNormal,
Labels: labels1,
LastEvalTime: lastEval,
CurrentStateSince: lastEval,
CurrentStateEnd: lastEval.Add(3 * interval),
},
{
AlertInstanceKey: models.AlertInstanceKey{
RuleOrgID: rule.OrgID,
RuleUID: rule.UID,
LabelsHash: hash2,
},
CurrentState: models.InstanceStateFiring,
Labels: labels2,
LastEvalTime: lastEval,
CurrentStateSince: lastEval,
CurrentStateEnd: lastEval.Add(3 * interval),
},
}
_ = dbstore.SaveAlertInstance(ctx, saveCmd1)
saveCmd2 := &models.SaveAlertInstanceCommand{
RuleOrgID: rule.OrgID,
RuleUID: rule.UID,
Labels: models.InstanceLabels{"test2": "testValue2"},
State: models.InstanceStateFiring,
LastEvalTime: lastEval,
CurrentStateSince: lastEval,
CurrentStateEnd: lastEval.Add(3 * interval),
}
_ = dbstore.SaveAlertInstance(ctx, saveCmd2)
_ = dbstore.SaveAlertInstances(ctx, instances...)
testCases := []struct {
desc string