mirror of
https://github.com/elastic/kibana.git
synced 2025-06-27 18:51:07 -04:00
Fixes https://github.com/elastic/kibana/issues/151938 In this PR, I'm re-writing the Task Manager poller so it doesn't run concurrently when timeouts occur while also fixing the issue where polling requests would pile up when polling takes time. To support this, I've also made the following changes: - Removed the observable monitor and the `xpack.task_manager.max_poll_inactivity_cycles` setting - Make the task store `search` and `updateByQuery` functions have no retries. This prevents the request from retrying 5x whenever a timeout occurs, causing each call taking up to 2 1/2 minutes before Kibana sees the error (now down to 30s each). We have polling to manage retries in these situations. - Switch the task poller tests to use `sinon` for faking timers - Removing the `assertStillInSetup` checks on plugin setup. Felt like a maintenance burden that wasn't necessary to fix with my code changes. The main code changes are within these files (to review thoroughly so the polling cycle doesn't suddenly stop): - x-pack/plugins/task_manager/server/polling/task_poller.ts - x-pack/plugins/task_manager/server/polling_lifecycle.ts (easier to review if you disregard whitespace `?w=1`) ## To verify 1. Tasks run normally (create a rule or something that goes through task manager regularly). 2. When the update by query takes a while, the request is cancelled after 30s or the time manually configured. 4. When the search for claimed tasks query takes a while, the request is cancelled after 30s or the time manually configured. **Tips:** <details><summary>how to slowdown search for claimed task queries</summary> ``` diff --git a/x-pack/plugins/task_manager/server/queries/task_claiming.ts b/x-pack/plugins/task_manager/server/queries/task_claiming.ts index 07042650a37..2caefd63672 100644 --- a/x-pack/plugins/task_manager/server/queries/task_claiming.ts +++ b/x-pack/plugins/task_manager/server/queries/task_claiming.ts @@ -247,7 +247,7 @@ export class TaskClaiming { taskTypes, }); - const docs = tasksUpdated > 0 ? await this.sweepForClaimedTasks(taskTypes, size) : []; + const docs = await this.sweepForClaimedTasks(taskTypes, size); this.emitEvents(docs.map((doc) => asTaskClaimEvent(doc.id, asOk(doc)))); @@ -346,6 +346,13 @@ export class TaskClaiming { size, sort: SortByRunAtAndRetryAt, seq_no_primary_term: true, + aggs: { + delay: { + shard_delay: { + value: '40s', + }, + }, + }, }); return docs; ``` </details> <details><summary>how to slow down update by queries</summary> Not the cleanest way but you'll see occasional request timeouts from the updateByQuery calls. I had more luck creating rules running every 1s. ``` diff --git a/x-pack/plugins/task_manager/server/task_store.ts b/x-pack/plugins/task_manager/server/task_store.ts index a06ee7b918a..07aa81e5388 100644 --- a/x-pack/plugins/task_manager/server/task_store.ts +++ b/x-pack/plugins/task_manager/server/task_store.ts @@ -126,6 +126,7 @@ export class TaskStore { // Timeouts are retried and make requests timeout after (requestTimeout * (1 + maxRetries)) // The poller doesn't need retry logic because it will try again at the next polling cycle maxRetries: 0, + requestTimeout: 900, }); } @@ -458,6 +459,7 @@ export class TaskStore { ignore_unavailable: true, refresh: true, conflicts: 'proceed', + requests_per_second: 1, body: { ...opts, max_docs, ``` </details> --------- Co-authored-by: Kibana Machine <42973632+kibanamachine@users.noreply.github.com>
223 lines
7.1 KiB
TypeScript
223 lines
7.1 KiB
TypeScript
/*
|
|
* Copyright Elasticsearch B.V. and/or licensed to Elasticsearch B.V. under one
|
|
* or more contributor license agreements. Licensed under the Elastic License
|
|
* 2.0; you may not use this file except in compliance with the Elastic License
|
|
* 2.0.
|
|
*/
|
|
|
|
import { configSchema } from './config';
|
|
|
|
describe('config validation', () => {
|
|
test('task manager defaults', () => {
|
|
const config: Record<string, unknown> = {};
|
|
expect(configSchema.validate(config)).toMatchInlineSnapshot(`
|
|
Object {
|
|
"ephemeral_tasks": Object {
|
|
"enabled": false,
|
|
"request_capacity": 10,
|
|
},
|
|
"event_loop_delay": Object {
|
|
"monitor": true,
|
|
"warn_threshold": 5000,
|
|
},
|
|
"max_attempts": 3,
|
|
"max_workers": 10,
|
|
"monitored_aggregated_stats_refresh_rate": 60000,
|
|
"monitored_stats_health_verbose_log": Object {
|
|
"enabled": false,
|
|
"level": "debug",
|
|
"warn_delayed_task_start_in_seconds": 60,
|
|
},
|
|
"monitored_stats_required_freshness": 4000,
|
|
"monitored_stats_running_average_window": 50,
|
|
"monitored_task_execution_thresholds": Object {
|
|
"custom": Object {},
|
|
"default": Object {
|
|
"error_threshold": 90,
|
|
"warn_threshold": 80,
|
|
},
|
|
},
|
|
"poll_interval": 3000,
|
|
"request_capacity": 1000,
|
|
"unsafe": Object {
|
|
"exclude_task_types": Array [],
|
|
},
|
|
"version_conflict_threshold": 80,
|
|
"worker_utilization_running_average_window": 5,
|
|
}
|
|
`);
|
|
});
|
|
|
|
test('the required freshness of the monitored stats config must always be less-than-equal to the poll interval', () => {
|
|
const config: Record<string, unknown> = {
|
|
monitored_stats_required_freshness: 100,
|
|
};
|
|
expect(() => {
|
|
configSchema.validate(config);
|
|
}).toThrowErrorMatchingInlineSnapshot(
|
|
`"The specified monitored_stats_required_freshness (100) is invalid, as it is below the poll_interval (3000)"`
|
|
);
|
|
});
|
|
|
|
test('the default required freshness of the monitored stats is poll interval with a slight buffer', () => {
|
|
const config: Record<string, unknown> = {};
|
|
expect(configSchema.validate(config)).toMatchInlineSnapshot(`
|
|
Object {
|
|
"ephemeral_tasks": Object {
|
|
"enabled": false,
|
|
"request_capacity": 10,
|
|
},
|
|
"event_loop_delay": Object {
|
|
"monitor": true,
|
|
"warn_threshold": 5000,
|
|
},
|
|
"max_attempts": 3,
|
|
"max_workers": 10,
|
|
"monitored_aggregated_stats_refresh_rate": 60000,
|
|
"monitored_stats_health_verbose_log": Object {
|
|
"enabled": false,
|
|
"level": "debug",
|
|
"warn_delayed_task_start_in_seconds": 60,
|
|
},
|
|
"monitored_stats_required_freshness": 4000,
|
|
"monitored_stats_running_average_window": 50,
|
|
"monitored_task_execution_thresholds": Object {
|
|
"custom": Object {},
|
|
"default": Object {
|
|
"error_threshold": 90,
|
|
"warn_threshold": 80,
|
|
},
|
|
},
|
|
"poll_interval": 3000,
|
|
"request_capacity": 1000,
|
|
"unsafe": Object {
|
|
"exclude_task_types": Array [],
|
|
},
|
|
"version_conflict_threshold": 80,
|
|
"worker_utilization_running_average_window": 5,
|
|
}
|
|
`);
|
|
});
|
|
|
|
test('the custom monitored_task_execution_thresholds can be configured at task type', () => {
|
|
const config: Record<string, unknown> = {
|
|
monitored_task_execution_thresholds: {
|
|
custom: {
|
|
'alerting:always-fires': {
|
|
error_threshold: 50,
|
|
warn_threshold: 30,
|
|
},
|
|
},
|
|
},
|
|
};
|
|
expect(configSchema.validate(config)).toMatchInlineSnapshot(`
|
|
Object {
|
|
"ephemeral_tasks": Object {
|
|
"enabled": false,
|
|
"request_capacity": 10,
|
|
},
|
|
"event_loop_delay": Object {
|
|
"monitor": true,
|
|
"warn_threshold": 5000,
|
|
},
|
|
"max_attempts": 3,
|
|
"max_workers": 10,
|
|
"monitored_aggregated_stats_refresh_rate": 60000,
|
|
"monitored_stats_health_verbose_log": Object {
|
|
"enabled": false,
|
|
"level": "debug",
|
|
"warn_delayed_task_start_in_seconds": 60,
|
|
},
|
|
"monitored_stats_required_freshness": 4000,
|
|
"monitored_stats_running_average_window": 50,
|
|
"monitored_task_execution_thresholds": Object {
|
|
"custom": Object {
|
|
"alerting:always-fires": Object {
|
|
"error_threshold": 50,
|
|
"warn_threshold": 30,
|
|
},
|
|
},
|
|
"default": Object {
|
|
"error_threshold": 90,
|
|
"warn_threshold": 80,
|
|
},
|
|
},
|
|
"poll_interval": 3000,
|
|
"request_capacity": 1000,
|
|
"unsafe": Object {
|
|
"exclude_task_types": Array [],
|
|
},
|
|
"version_conflict_threshold": 80,
|
|
"worker_utilization_running_average_window": 5,
|
|
}
|
|
`);
|
|
});
|
|
|
|
test('the monitored_task_execution_thresholds ensures that the default warn_threshold is lt the default error_threshold', () => {
|
|
const config: Record<string, unknown> = {
|
|
monitored_task_execution_thresholds: {
|
|
default: {
|
|
warn_threshold: 80,
|
|
error_threshold: 70,
|
|
},
|
|
},
|
|
};
|
|
expect(() => {
|
|
configSchema.validate(config);
|
|
}).toThrowErrorMatchingInlineSnapshot(
|
|
`"[monitored_task_execution_thresholds.default]: warn_threshold (80) must be less than, or equal to, error_threshold (70)"`
|
|
);
|
|
});
|
|
|
|
test('the monitored_task_execution_thresholds allows the default warn_threshold to equal the default error_threshold', () => {
|
|
const config: Record<string, unknown> = {
|
|
monitored_task_execution_thresholds: {
|
|
default: {
|
|
warn_threshold: 70,
|
|
error_threshold: 70,
|
|
},
|
|
},
|
|
};
|
|
expect(() => {
|
|
configSchema.validate(config);
|
|
}).not.toThrowError();
|
|
});
|
|
|
|
test('the monitored_task_execution_thresholds ensures that the warn_threshold is lte error_threshold on custom thresholds', () => {
|
|
const config: Record<string, unknown> = {
|
|
monitored_task_execution_thresholds: {
|
|
custom: {
|
|
'alerting:always-fires': {
|
|
error_threshold: 80,
|
|
warn_threshold: 90,
|
|
},
|
|
},
|
|
},
|
|
};
|
|
expect(() => {
|
|
configSchema.validate(config);
|
|
}).toThrowErrorMatchingInlineSnapshot(
|
|
`"[monitored_task_execution_thresholds.custom.alerting:always-fires]: warn_threshold (90) must be less than, or equal to, error_threshold (80)"`
|
|
);
|
|
});
|
|
|
|
test('the monitored_task_execution_thresholds allows a custom error_threshold which is lower than the default warn_threshold', () => {
|
|
const config: Record<string, unknown> = {
|
|
monitored_task_execution_thresholds: {
|
|
default: {
|
|
warn_threshold: 80,
|
|
error_threshold: 90,
|
|
},
|
|
custom: {
|
|
'alerting:always-fires': {
|
|
error_threshold: 60,
|
|
warn_threshold: 50,
|
|
},
|
|
},
|
|
},
|
|
};
|
|
expect(() => {
|
|
configSchema.validate(config);
|
|
}).not.toThrowError();
|
|
});
|
|
});
|