The open and composable observability and data visualization platform. Visualize metrics, logs, and traces from multiple sources like Prometheus, Loki, Elasticsearch, InfluxDB, Postgres and many more.
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
grafana/pkg/services/ngalert/models/instance.go

88 lines
2.4 KiB

package models
import (
"fmt"
"time"
)
// AlertInstance represents a single alert instance.
type AlertInstance struct {
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
3 years ago
AlertInstanceKey `xorm:"extends"`
Labels InstanceLabels
CurrentState InstanceStateType
CurrentReason string
CurrentStateSince time.Time
CurrentStateEnd time.Time
LastEvalTime time.Time
}
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
3 years ago
type AlertInstanceKey struct {
RuleOrgID int64 `xorm:"rule_org_id"`
RuleUID string `xorm:"rule_uid"`
LabelsHash string
}
// InstanceStateType is an enum for instance states.
type InstanceStateType string
const (
// InstanceStateFiring is for a firing alert.
InstanceStateFiring InstanceStateType = "Alerting"
// InstanceStateNormal is for a normal alert.
InstanceStateNormal InstanceStateType = "Normal"
// InstanceStatePending is for an alert that is firing but has not met the duration
InstanceStatePending InstanceStateType = "Pending"
// InstanceStateNoData is for an alert with no data.
InstanceStateNoData InstanceStateType = "NoData"
// InstanceStateError is for a erroring alert.
InstanceStateError InstanceStateType = "Error"
)
// IsValid checks that the value of InstanceStateType is a valid
// string.
func (i InstanceStateType) IsValid() bool {
return i == InstanceStateFiring ||
i == InstanceStateNormal ||
i == InstanceStateNoData ||
i == InstanceStatePending ||
i == InstanceStateError
}
// GetAlertInstanceQuery is the query for retrieving/deleting an alert definition by ID.
// nolint:unused
type GetAlertInstanceQuery struct {
RuleOrgID int64
RuleUID string
Labels InstanceLabels
Result *AlertInstance
}
// ListAlertInstancesQuery is the query list alert Instances.
type ListAlertInstancesQuery struct {
RuleOrgID int64 `json:"-"`
RuleUID string
State InstanceStateType
StateReason string
Result []*AlertInstance
}
// ValidateAlertInstance validates that the alert instance contains an alert rule id,
// and state.
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
3 years ago
func ValidateAlertInstance(alertInstance AlertInstance) error {
if alertInstance.RuleOrgID == 0 {
return fmt.Errorf("alert instance is invalid due to missing alert rule organisation")
}
if alertInstance.RuleUID == "" {
return fmt.Errorf("alert instance is invalid due to missing alert rule uid")
}
if !alertInstance.CurrentState.IsValid() {
return fmt.Errorf("alert instance is invalid because the state '%v' is invalid", alertInstance.CurrentState)
}
return nil
}