Skip to content

Commit

Permalink
[9.0] [OBX-UX-MGTM][ALERTING] Add the reason message to the rules rec…
Browse files Browse the repository at this point in the history 
…overy context (#211411) (#212896)

# Backport

This will backport the following commits from `main` to `9.0`:
- [[OBX-UX-MGTM][ALERTING] Add the reason message to the rules recovery
context (#211411)](#211411)

<!--- Backport version: 9.6.6 -->

### Questions ?
Please refer to the [Backport tool
documentation](https://github.com/sorenlouv/backport)

<!--BACKPORT [{"author":{"name":"Faisal
Kanout","email":"faisal.kanout@elastic.co"},"sourceCommit":{"committedDate":"2025-03-03T12:04:52Z","message":"[OBX-UX-MGTM][ALERTING]
Add the reason message to the rules recovery context (#211411)\n\n##
Summary\n\nIt fixes #184803 by:\n\n### Adding the reason message to
recovery context variables in the\nfollowing rules:\n- Inventory
Threshold\n- Metric threshold\n- Custom threshold\n- Log
threshold\n\n### Enabling recovery context and handling the recovery
alert context\nfor APM (except Anomaly)\n- Latency threshold\n- Error
count\n- Failed transaction
rate","sha":"9a6b4ecda3c0f1db49f8f93cd6968b4e2f2055d7","branchLabelMapping":{"^v9.1.0$":"main","^v8.19.0$":"8.x","^v(\\d+).(\\d+).\\d+$":"$1.$2"}},"sourcePullRequest":{"labels":["release_note:enhancement","Feature:Alerting","backport:prev-minor","Team:obs-ux-infra_services","Team:obs-ux-management","v9.1.0"],"title":"[OBX-UX-MGTM][ALERTING]
Add the reason message to the rules recovery
context","number":211411,"url":"https://github.com/elastic/kibana/pull/211411","mergeCommit":{"message":"[OBX-UX-MGTM][ALERTING]
Add the reason message to the rules recovery context (#211411)\n\n##
Summary\n\nIt fixes #184803 by:\n\n### Adding the reason message to
recovery context variables in the\nfollowing rules:\n- Inventory
Threshold\n- Metric threshold\n- Custom threshold\n- Log
threshold\n\n### Enabling recovery context and handling the recovery
alert context\nfor APM (except Anomaly)\n- Latency threshold\n- Error
count\n- Failed transaction
rate","sha":"9a6b4ecda3c0f1db49f8f93cd6968b4e2f2055d7"}},"sourceBranch":"main","suggestedTargetBranches":[],"targetPullRequestStates":[{"branch":"main","label":"v9.1.0","branchLabelMappingKey":"^v9.1.0$","isSourceBranch":true,"state":"MERGED","url":"https://github.com/elastic/kibana/pull/211411","number":211411,"mergeCommit":{"message":"[OBX-UX-MGTM][ALERTING]
Add the reason message to the rules recovery context (#211411)\n\n##
Summary\n\nIt fixes #184803 by:\n\n### Adding the reason message to
recovery context variables in the\nfollowing rules:\n- Inventory
Threshold\n- Metric threshold\n- Custom threshold\n- Log
threshold\n\n### Enabling recovery context and handling the recovery
alert context\nfor APM (except Anomaly)\n- Latency threshold\n- Error
count\n- Failed transaction
rate","sha":"9a6b4ecda3c0f1db49f8f93cd6968b4e2f2055d7"}}]}] BACKPORT-->

Co-authored-by: Faisal Kanout <faisal.kanout@elastic.co>
  • Loading branch information
@kibanamachine @fkanout
kibanamachine and fkanout authored Mar 3, 2025
1 parent 9953d52 commit 2fc95c6
Show file tree
Hide file tree
Showing 20 changed files with 572 additions and 11 deletions.
4 changes: 4 additions & 0 deletions x-pack/solutions/observability/plugins/apm/common/rules/apm_rule_types.ts
View file
Original file line number Diff line number Diff line change
Expand Up @@ -307,3 +307,7 @@ export const ANOMALY_DETECTOR_SELECTOR_OPTIONS = [
// Client side registrations:
// x-pack/solutions/observability/plugins/apm/public/components/alerting/<alert>/index.tsx
// x-pack/solutions/observability/plugins/apm/public/components/alerting/register_apm_alerts

export interface AdditionalContext {
[x: string]: any;
}
8 changes: 4 additions & 4 deletions x-pack/solutions/observability/plugins/apm/common/rules/default_action_message.ts
View file
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,7 @@ export const errorCountMessage = i18n.translate(
export const errorCountRecoveryMessage = i18n.translate(
'xpack.apm.alertTypes.errorCount.defaultRecoveryMessage',
{
defaultMessage: `'{{context.reason}}'
defaultMessage: `Recovered: '{{context.reason}}'
'{{rule.name}}' has recovered.
Expand Down Expand Up @@ -61,7 +61,7 @@ export const transactionDurationMessage = i18n.translate(
export const transactionDurationRecoveryMessage = i18n.translate(
'xpack.apm.alertTypes.transactionDuration.defaultRecoveryMessage',
{
defaultMessage: `'{{context.reason}}'
defaultMessage: `Recovered: '{{context.reason}}'
'{{rule.name}}' has recovered.
Expand Down Expand Up @@ -97,7 +97,7 @@ export const transactionErrorRateMessage = i18n.translate(
export const transactionErrorRateRecoveryMessage = i18n.translate(
'xpack.apm.alertTypes.transactionErrorRate.defaultRecoveryMessage',
{
defaultMessage: `'{{context.reason}}'
defaultMessage: `Recovered: '{{context.reason}}'
'{{rule.name}}' has recovered.
Expand Down Expand Up @@ -132,7 +132,7 @@ export const anomalyMessage = i18n.translate(
export const anomalyRecoveryMessage = i18n.translate(
'xpack.apm.alertTypes.transactionDurationAnomaly.defaultRecoveryMessage',
{
defaultMessage: `'{{context.reason}}'
defaultMessage: `Recovered: '{{context.reason}}'
'{{rule.name}}' has recovered.
Expand Down
6 changes: 6 additions & 0 deletions ...bservability/plugins/apm/public/components/alerting/rule_types/register_apm_rule_types.ts
View file
Original file line number Diff line number Diff line change
Expand Up @@ -13,8 +13,11 @@ import { getAlertUrlErrorCount, getAlertUrlTransaction } from '../../../../commo
import {
anomalyMessage,
errorCountMessage,
errorCountRecoveryMessage,
transactionDurationMessage,
transactionDurationRecoveryMessage,
transactionErrorRateMessage,
transactionErrorRateRecoveryMessage,
} from '../../../../common/rules/default_action_message';
import type { AlertParams } from './anomaly_rule_type';

Expand Down Expand Up @@ -49,6 +52,7 @@ export function registerApmRuleTypes(observabilityRuleTypeRegistry: Observabilit
}),
requiresAppContext: false,
defaultActionMessage: errorCountMessage,
defaultRecoveryMessage: errorCountRecoveryMessage,
priority: 80,
});

Expand Down Expand Up @@ -80,6 +84,7 @@ export function registerApmRuleTypes(observabilityRuleTypeRegistry: Observabilit
alertDetailsAppSection: lazy(() => import('../ui_components/alert_details_app_section')),
requiresAppContext: false,
defaultActionMessage: transactionDurationMessage,
defaultRecoveryMessage: transactionDurationRecoveryMessage,
priority: 60,
});

Expand Down Expand Up @@ -108,6 +113,7 @@ export function registerApmRuleTypes(observabilityRuleTypeRegistry: Observabilit
}),
requiresAppContext: false,
defaultActionMessage: transactionErrorRateMessage,
defaultRecoveryMessage: transactionErrorRateRecoveryMessage,
priority: 70,
});

Expand Down
109 changes: 109 additions & 0 deletions ...ns/apm/server/routes/alerts/rule_types/error_count/register_error_count_rule_type.test.ts
View file
Original file line number Diff line number Diff line change
Expand Up @@ -1025,4 +1025,113 @@ describe('Error count alert', () => {
},
});
});
it('sends recovered alerts with their context', async () => {
const { services, dependencies, executor } = createRuleTypeMocks();

registerErrorCountRuleType(dependencies);

const params = {
threshold: 2,
windowSize: 5,
windowUnit: 'm',
};

services.scopedClusterClient.asCurrentUser.search.mockResponse({
hits: {
hits: [],
total: {
relation: 'eq',
value: 1,
},
},
aggregations: {
error_counts: {
buckets: [],
},
},
took: 0,
timed_out: false,
_shards: {
failed: 0,
skipped: 0,
successful: 1,
total: 1,
},
});
services.alertsClient.getRecoveredAlerts.mockReturnValue([
{
alert: {
getId: jest.fn().mockReturnValue('test-id'),
getUuid: jest.fn().mockReturnValue('test-uuid'),
scheduledExecutionOptions: undefined,
meta: [],
state: [],
context: {},
id: 'synthtrace-high-cardinality-0_Synthtrace: many_errors',
alertAsData: undefined,
},
hit: {
'processor.event': 'error',
'kibana.alert.evaluation.value': 60568922,
'kibana.alert.evaluation.threshold': 24999998,
'kibana.alert.reason':
'Error count is 60568922 in the last 5 days for service: synthtrace-high-cardinality-0, env: Synthtrace: many_errors. Alert when > 24999998.',
'agent.name': 'java',
'service.environment': 'Synthtrace: many_errors',
'service.name': 'synthtrace-high-cardinality-0',
'kibana.alert.rule.category': 'Error count threshold',
'kibana.alert.rule.consumer': 'alerts',
'kibana.alert.rule.execution.uuid': '8ecb0754-1220-4b6b-b95d-87b3594e925a',
'kibana.alert.rule.name': 'Error count threshold rule',
'kibana.alert.rule.parameters': [],
'kibana.alert.rule.producer': 'apm',
'kibana.alert.rule.revision': 8,
'kibana.alert.rule.rule_type_id': 'apm.error_rate',
'kibana.alert.rule.tags': [],
'kibana.alert.rule.uuid': '63028cf5-c059-4a6b-b375-fd9007233223',
'kibana.space_ids': [],
'@timestamp': '2025-02-20T12:11:51.960Z',
'event.action': 'active',
'event.kind': 'signal',
'kibana.alert.rule.execution.timestamp': '2025-02-20T12:11:51.960Z',
'kibana.alert.action_group': 'threshold_met',
'kibana.alert.flapping': true,
'kibana.alert.flapping_history': [],
'kibana.alert.instance.id': 'synthtrace-high-cardinality-0_Synthtrace: many_errors',
'kibana.alert.maintenance_window_ids': [],
'kibana.alert.consecutive_matches': 2,
'kibana.alert.status': 'active',
'kibana.alert.uuid': '81617b97-02d2-413a-9f64-77161de80df4',
'kibana.alert.workflow_status': 'open',
'kibana.alert.duration.us': 12012000,
'kibana.alert.start': '2025-02-20T12:11:39.948Z',
'kibana.alert.time_range': [],
'kibana.version': '9.1.0',
tags: [],
'kibana.alert.previous_action_group': 'threshold_met',
},
},
]);

await executor({ params });

expect(services.alertsClient.setAlertData).toHaveBeenCalledTimes(1);

expect(services.alertsClient.setAlertData).toHaveBeenCalledWith({
context: {
alertDetailsUrl: 'http://localhost:5601/eyr/app/observability/alerts/test-uuid',
environment: 'Synthtrace: many_errors',
errorGroupingKey: undefined,
interval: '5 mins',
reason:
'Error count is 60568922 in the last 5 days for service: synthtrace-high-cardinality-0, env: Synthtrace: many_errors. Alert when > 24999998.',
serviceName: 'synthtrace-high-cardinality-0',
threshold: 2,
triggerValue: 60568922,
viewInAppUrl:
'http://localhost:5601/eyr/app/apm/services/synthtrace-high-cardinality-0/errors?environment=Synthtrace%3A%20many_errors',
},
id: 'test-id',
});
});
});
49 changes: 49 additions & 0 deletions ...plugins/apm/server/routes/alerts/rule_types/error_count/register_error_count_rule_type.ts
View file
Original file line number Diff line number Diff line change
Expand Up @@ -43,6 +43,7 @@ import {
import type {
THRESHOLD_MET_GROUP,
ApmRuleParamsType,
AdditionalContext,
} from '../../../../../common/rules/apm_rule_types';
import {
APM_SERVER_FEATURE_ID,
Expand Down Expand Up @@ -105,6 +106,7 @@ export function registerErrorCountRuleType({
actionGroups: ruleTypeConfig.actionGroups,
defaultActionGroupId: ruleTypeConfig.defaultActionGroupId,
validate: { params: errorCountParamsSchema },
doesSetRecoveryContext: true,
schemas: {
params: {
type: 'config-schema',
Expand Down Expand Up @@ -271,6 +273,53 @@ export function registerErrorCountRuleType({
});
}
);
// Handle recovered alerts context
const recoveredAlerts = alertsClient.getRecoveredAlerts() ?? [];
for (const recoveredAlert of recoveredAlerts) {
const alertHits = recoveredAlert.hit as AdditionalContext;
const recoveredAlertId = recoveredAlert.alert.getId();
const alertUuid = recoveredAlert.alert.getUuid();
const alertDetailsUrl = getAlertDetailsUrl(basePath, spaceId, alertUuid);
const groupByFields: Record<string, string> = allGroupByFields.reduce(
(acc, sourceField: string) => {
if (alertHits?.[sourceField] !== undefined) {
acc[sourceField] = alertHits[sourceField];
}
return acc;
},
{} as Record<string, string>
);

const relativeViewInAppUrl = getAlertUrlErrorCount(
groupByFields[SERVICE_NAME],
getEnvironmentEsField(groupByFields[SERVICE_ENVIRONMENT])?.[SERVICE_ENVIRONMENT]
);
const viewInAppUrl = addSpaceIdToPath(
basePath.publicBaseUrl,
spaceId,
relativeViewInAppUrl
);
const groupByActionVariables = getGroupByActionVariables(groupByFields);
const recoveredContext = {
alertDetailsUrl,
interval: formatDurationFromTimeUnitChar(
ruleParams.windowSize,
ruleParams.windowUnit as TimeUnitChar
),
reason: alertHits?.[ALERT_REASON],
// When group by doesn't include error.grouping_key, the context.error.grouping_key action variable will contain value of the Error Grouping Key filter
errorGroupingKey: ruleParams.errorGroupingKey,
threshold: ruleParams.threshold,
triggerValue: alertHits?.[ALERT_EVALUATION_VALUE],
viewInAppUrl,
...groupByActionVariables,
};

alertsClient.setAlertData({
id: recoveredAlertId,
context: recoveredContext,
});
}

return { state: {} };
},
Expand Down
122 changes: 122 additions & 0 deletions ...es/alerts/rule_types/transaction_duration/register_transaction_duration_rule_type.test.ts
View file
Original file line number Diff line number Diff line change
Expand Up @@ -411,4 +411,126 @@ describe('registerTransactionDurationRuleType', () => {
},
});
});
it('sends recovered alert with their context', async () => {
const { services, dependencies, executor } = createRuleTypeMocks();

registerTransactionDurationRuleType(dependencies);

services.scopedClusterClient.asCurrentUser.search.mockResponse({
hits: {
hits: [],
total: {
relation: 'eq',
value: 0,
},
},
aggregations: {
series: {
buckets: [],
},
},
took: 0,
timed_out: false,
_shards: {
failed: 0,
skipped: 0,
successful: 1,
total: 1,
},
});

services.alertsClient.getRecoveredAlerts.mockReturnValue([
{
alert: {
getId: jest.fn().mockReturnValue('test-id'),
getUuid: jest.fn().mockReturnValue('test-uuid'),
scheduledExecutionOptions: undefined,
meta: {},
state: {},
context: {},
id: 'synthtrace-high-cardinality-0_Synthtrace: many_errors_request',
alertAsData: undefined,
},
hit: {
'processor.event': 'transaction',
'kibana.alert.evaluation.value': 1000000,
'kibana.alert.evaluation.threshold': 149000,
'kibana.alert.reason':
'Avg. latency is 1,000 ms in the last 5 days for service: synthtrace-high-cardinality-0, env: Synthtrace: many_errors, type: request. Alert when > 149 ms.',
'agent.name': 'java',
labels: { custom_label: [] },
'service.environment': 'Synthtrace: many_errors',
'service.name': 'synthtrace-high-cardinality-0',
'transaction.type': 'request',
'kibana.alert.rule.category': 'Latency threshold',
'kibana.alert.rule.consumer': 'alerts',
'kibana.alert.rule.execution.uuid': '646b1ca4-5799-4b3f-b253-593941da2c2f',
'kibana.alert.rule.name': 'Latency threshold rule',
'kibana.alert.rule.parameters': {
aggregationType: 'avg',
threshold: 149,
windowSize: 5,
windowUnit: 'd',
environment: 'ENVIRONMENT_ALL',
},
'kibana.alert.rule.producer': 'apm',
'kibana.alert.rule.revision': 15,
'kibana.alert.rule.rule_type_id': 'apm.transaction_duration',
'kibana.alert.rule.tags': [],
'kibana.alert.rule.uuid': '9c4a8e4f-b55c-426c-b4cc-fd2c9cb8bf89',
'kibana.space_ids': ['default'],
'@timestamp': '2025-02-20T12:40:40.956Z',
'event.action': 'open',
'event.kind': 'signal',
'kibana.alert.rule.execution.timestamp': '2025-02-20T12:40:40.956Z',
'kibana.alert.action_group': 'threshold_met',
'kibana.alert.flapping': false,
'kibana.alert.flapping_history': [true],
'kibana.alert.instance.id':
'synthtrace-high-cardinality-0_Synthtrace: many_errors_request',
'kibana.alert.maintenance_window_ids': [],
'kibana.alert.consecutive_matches': 1,
'kibana.alert.status': 'active',
'kibana.alert.uuid': 'b60476e6-f4e3-47a1-ac1a-a53616411b66',
'kibana.alert.severity_improving': false,
'kibana.alert.workflow_status': 'open',
'kibana.alert.duration.us': 0,
'kibana.alert.start': '2025-02-20T12:40:40.956Z',
'kibana.alert.time_range': { gte: '2025-02-20T12:40:40.956Z' },
'kibana.version': '9.1.0',
tags: [],
},
},
]);
services.alertsClient.report.mockReturnValue({ uuid: 'test-uuid' });

const params = {
threshold: 3000,
windowSize: 5,
windowUnit: 'm',
transactionType: 'request',
serviceName: 'opbeans-java',
aggregationType: 'avg',
transactionName: 'GET /orders',
};
await executor({ params });
expect(services.alertsClient.setAlertData).toHaveBeenCalledTimes(1);
expect(services.alertsClient.setAlertData).toHaveBeenCalledWith({
context: {
alertDetailsUrl: 'http://localhost:5601/eyr/app/observability/alerts/test-uuid',
environment: 'Synthtrace: many_errors',
interval: '5 mins',
reason:
'Avg. latency is 1,000 ms in the last 5 days for service: synthtrace-high-cardinality-0, env: Synthtrace: many_errors, type: request. Alert when > 149 ms.',
serviceName: 'synthtrace-high-cardinality-0',
threshold: 3000,
transactionName: 'GET /orders',
transactionType: 'request',
triggerValue: '1,000 ms',
viewInAppUrl:
'http://localhost:5601/eyr/app/apm/services/synthtrace-high-cardinality-0?transactionType=request&environment=Synthtrace%3A%20many_errors',
},
id: 'test-id',
});
});
});
Loading

0 comments on commit 2fc95c6

Please sign in to comment.