-
-
Notifications
You must be signed in to change notification settings - Fork 713
Use redis worker for run heartbeats and alerts #1669
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Merged
Merged
Changes from all commits
Commits
Show all changes
6 commits
Select commit
Hold shift + click to select a range
56d69f9
Move the task run heartbeats to RedisWorker
ericallam ac71200
Move alerts to redis worker, improving redis worker
ericallam f3cd6cb
Fix typecheck errors
ericallam b902ab1
Use single threaded tests for redis worker
ericallam 630ba39
Enable/disable the redis workers independently
ericallam a2ca3ee
Remove preview release from PR checks
ericallam File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,93 @@ | ||
| import { Worker as RedisWorker } from "@internal/redis-worker"; | ||
| import { Logger } from "@trigger.dev/core/logger"; | ||
| import { z } from "zod"; | ||
| import { env } from "~/env.server"; | ||
| import { logger } from "~/services/logger.server"; | ||
| import { singleton } from "~/utils/singleton"; | ||
| import { DeliverAlertService } from "./services/alerts/deliverAlert.server"; | ||
| import { PerformDeploymentAlertsService } from "./services/alerts/performDeploymentAlerts.server"; | ||
| import { PerformTaskRunAlertsService } from "./services/alerts/performTaskRunAlerts.server"; | ||
|
|
||
| function initializeWorker() { | ||
| const redisOptions = { | ||
| keyPrefix: "common:worker:", | ||
| host: env.COMMON_WORKER_REDIS_HOST, | ||
| port: env.COMMON_WORKER_REDIS_PORT, | ||
| username: env.COMMON_WORKER_REDIS_USERNAME, | ||
| password: env.COMMON_WORKER_REDIS_PASSWORD, | ||
| enableAutoPipelining: true, | ||
| ...(env.COMMON_WORKER_REDIS_TLS_DISABLED === "true" ? {} : { tls: {} }), | ||
| }; | ||
|
|
||
| logger.debug(`👨🏭 Initializing common worker at host ${env.COMMON_WORKER_REDIS_HOST}`); | ||
|
|
||
| const worker = new RedisWorker({ | ||
| name: "common-worker", | ||
| redisOptions, | ||
| catalog: { | ||
| "v3.performTaskRunAlerts": { | ||
| schema: z.object({ | ||
| runId: z.string(), | ||
| }), | ||
| visibilityTimeoutMs: 60_000, | ||
| retry: { | ||
| maxAttempts: 3, | ||
| }, | ||
| }, | ||
| "v3.performDeploymentAlerts": { | ||
| schema: z.object({ | ||
| deploymentId: z.string(), | ||
| }), | ||
| visibilityTimeoutMs: 60_000, | ||
| retry: { | ||
| maxAttempts: 3, | ||
| }, | ||
| }, | ||
| "v3.deliverAlert": { | ||
| schema: z.object({ | ||
| alertId: z.string(), | ||
| }), | ||
| visibilityTimeoutMs: 60_000, | ||
| retry: { | ||
| maxAttempts: 3, | ||
| }, | ||
| }, | ||
| }, | ||
| concurrency: { | ||
| workers: env.COMMON_WORKER_CONCURRENCY_WORKERS, | ||
| tasksPerWorker: env.COMMON_WORKER_CONCURRENCY_TASKS_PER_WORKER, | ||
| limit: env.COMMON_WORKER_CONCURRENCY_LIMIT, | ||
| }, | ||
| pollIntervalMs: env.COMMON_WORKER_POLL_INTERVAL, | ||
| immediatePollIntervalMs: env.COMMON_WORKER_IMMEDIATE_POLL_INTERVAL, | ||
| logger: new Logger("CommonWorker", "debug"), | ||
| jobs: { | ||
| "v3.deliverAlert": async ({ payload }) => { | ||
| const service = new DeliverAlertService(); | ||
|
|
||
| return await service.call(payload.alertId); | ||
| }, | ||
| "v3.performDeploymentAlerts": async ({ payload }) => { | ||
| const service = new PerformDeploymentAlertsService(); | ||
|
|
||
| return await service.call(payload.deploymentId); | ||
| }, | ||
| "v3.performTaskRunAlerts": async ({ payload }) => { | ||
| const service = new PerformTaskRunAlertsService(); | ||
| return await service.call(payload.runId); | ||
| }, | ||
| }, | ||
| }); | ||
|
|
||
| if (env.COMMON_WORKER_ENABLED === "true") { | ||
| logger.debug( | ||
| `👨🏭 Starting common worker at host ${env.COMMON_WORKER_REDIS_HOST}, pollInterval = ${env.COMMON_WORKER_POLL_INTERVAL}, immediatePollInterval = ${env.COMMON_WORKER_IMMEDIATE_POLL_INTERVAL}, workers = ${env.COMMON_WORKER_CONCURRENCY_WORKERS}, tasksPerWorker = ${env.COMMON_WORKER_CONCURRENCY_TASKS_PER_WORKER}, concurrencyLimit = ${env.COMMON_WORKER_CONCURRENCY_LIMIT}` | ||
| ); | ||
|
|
||
| worker.start(); | ||
| } | ||
|
|
||
| return worker; | ||
| } | ||
|
|
||
| export const commonWorker = singleton("commonWorker", initializeWorker); |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,66 @@ | ||
| import { Worker as RedisWorker } from "@internal/redis-worker"; | ||
| import { Logger } from "@trigger.dev/core/logger"; | ||
| import { z } from "zod"; | ||
| import { env } from "~/env.server"; | ||
| import { logger } from "~/services/logger.server"; | ||
| import { singleton } from "~/utils/singleton"; | ||
| import { TaskRunHeartbeatFailedService } from "./taskRunHeartbeatFailed.server"; | ||
|
|
||
| function initializeWorker() { | ||
| const redisOptions = { | ||
| keyPrefix: "legacy-run-engine:worker:", | ||
| host: env.LEGACY_RUN_ENGINE_WORKER_REDIS_HOST, | ||
| port: env.LEGACY_RUN_ENGINE_WORKER_REDIS_PORT, | ||
| username: env.LEGACY_RUN_ENGINE_WORKER_REDIS_USERNAME, | ||
| password: env.LEGACY_RUN_ENGINE_WORKER_REDIS_PASSWORD, | ||
| enableAutoPipelining: true, | ||
| ...(env.LEGACY_RUN_ENGINE_WORKER_REDIS_TLS_DISABLED === "true" ? {} : { tls: {} }), | ||
| }; | ||
|
|
||
| logger.debug( | ||
| `👨🏭 Initializing legacy run engine worker at host ${env.LEGACY_RUN_ENGINE_WORKER_REDIS_HOST}` | ||
| ); | ||
|
|
||
| const worker = new RedisWorker({ | ||
| name: "legacy-run-engine-worker", | ||
| redisOptions, | ||
| catalog: { | ||
| runHeartbeat: { | ||
| schema: z.object({ | ||
| runId: z.string(), | ||
| }), | ||
| visibilityTimeoutMs: 60_000, | ||
| retry: { | ||
| maxAttempts: 3, | ||
| }, | ||
| }, | ||
| }, | ||
| concurrency: { | ||
| workers: env.LEGACY_RUN_ENGINE_WORKER_CONCURRENCY_WORKERS, | ||
| tasksPerWorker: env.LEGACY_RUN_ENGINE_WORKER_CONCURRENCY_TASKS_PER_WORKER, | ||
| limit: env.LEGACY_RUN_ENGINE_WORKER_CONCURRENCY_LIMIT, | ||
| }, | ||
| pollIntervalMs: env.LEGACY_RUN_ENGINE_WORKER_POLL_INTERVAL, | ||
| immediatePollIntervalMs: env.LEGACY_RUN_ENGINE_WORKER_IMMEDIATE_POLL_INTERVAL, | ||
| logger: new Logger("LegacyRunEngineWorker", "debug"), | ||
| jobs: { | ||
| runHeartbeat: async ({ payload }) => { | ||
| const service = new TaskRunHeartbeatFailedService(); | ||
|
|
||
| await service.call(payload.runId); | ||
| }, | ||
| }, | ||
| }); | ||
|
|
||
| if (env.LEGACY_RUN_ENGINE_WORKER_ENABLED === "true") { | ||
| logger.debug( | ||
| `👨🏭 Starting legacy run engine worker at host ${env.LEGACY_RUN_ENGINE_WORKER_REDIS_HOST}, pollInterval = ${env.LEGACY_RUN_ENGINE_WORKER_POLL_INTERVAL}, immediatePollInterval = ${env.LEGACY_RUN_ENGINE_WORKER_IMMEDIATE_POLL_INTERVAL}, workers = ${env.LEGACY_RUN_ENGINE_WORKER_CONCURRENCY_WORKERS}, tasksPerWorker = ${env.LEGACY_RUN_ENGINE_WORKER_CONCURRENCY_TASKS_PER_WORKER}, concurrencyLimit = ${env.LEGACY_RUN_ENGINE_WORKER_CONCURRENCY_LIMIT}` | ||
| ); | ||
|
|
||
| worker.start(); | ||
| } | ||
|
|
||
| return worker; | ||
| } | ||
|
|
||
| export const legacyRunEngineWorker = singleton("legacyRunEngineWorker", initializeWorker); | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,12 +1,28 @@ | ||
| import { RequeueTaskRunService } from "../requeueTaskRun.server"; | ||
| import { legacyRunEngineWorker } from "../legacyRunEngineWorker.server"; | ||
| import { TaskRunHeartbeatFailedService } from "../taskRunHeartbeatFailed.server"; | ||
| import { VisibilityTimeoutStrategy } from "./types"; | ||
|
|
||
| export class V3VisibilityTimeout implements VisibilityTimeoutStrategy { | ||
| export class V3GraphileVisibilityTimeout implements VisibilityTimeoutStrategy { | ||
| async heartbeat(messageId: string, timeoutInMs: number): Promise<void> { | ||
| await RequeueTaskRunService.enqueue(messageId, new Date(Date.now() + timeoutInMs)); | ||
| await TaskRunHeartbeatFailedService.enqueue(messageId, new Date(Date.now() + timeoutInMs)); | ||
| } | ||
|
|
||
| async cancelHeartbeat(messageId: string): Promise<void> { | ||
| await RequeueTaskRunService.dequeue(messageId); | ||
| await TaskRunHeartbeatFailedService.dequeue(messageId); | ||
| } | ||
| } | ||
|
|
||
| export class V3LegacyRunEngineWorkerVisibilityTimeout implements VisibilityTimeoutStrategy { | ||
| async heartbeat(messageId: string, timeoutInMs: number): Promise<void> { | ||
| await legacyRunEngineWorker.enqueue({ | ||
| id: `heartbeat:${messageId}`, | ||
| job: "runHeartbeat", | ||
| payload: { runId: messageId }, | ||
| availableAt: new Date(Date.now() + timeoutInMs), | ||
| }); | ||
| } | ||
|
|
||
| async cancelHeartbeat(messageId: string): Promise<void> { | ||
| await legacyRunEngineWorker.ack(`heartbeat:${messageId}`); | ||
| } | ||
| } |
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
🛠️ Refactor suggestion
Add error handling for task failures.
The job handler should include proper error handling and logging.
runHeartbeat: async ({ payload }) => { + try { const service = new TaskRunHeartbeatFailedService(); await service.call(payload.runId); + } catch (error) { + logger.error("Failed to process run heartbeat", { + error, + runId: payload.runId, + }); + throw error; // Re-throw to trigger retry + } },📝 Committable suggestion