Scheduler and worker loops survive a database restart
index-scheduler's loop ended when Postgres restarted (the active-groups query was outside its try), leaving live indexing stopped for ~3 hours while the process stayed up. Each step's error is now caught and retried next round; worker:spots and worker:deferred wait 30 s and claim again. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
1 parent
61192690a7
commit
e3e3ecc93d
3 files changed
+60
-41
No files matched your search
@@ -31,23 +31,29 @@ export default class DeferredWorker extends BaseCommand {
|
||||
let done = 0
|
||||
try {
|
||||
while (!Shutdown.requested && (!this.limit || done < this.limit)) {
|
||||
const batch = await DeferredService.claim(Math.min(concurrency * 4, this.limit ? this.limit - done : Infinity))
|
||||
if (batch.length === 0) {
|
||||
if (this.limit) break
|
||||
await Shutdown.sleep(IDLE_MS)
|
||||
continue
|
||||
try {
|
||||
const batch = await DeferredService.claim(Math.min(concurrency * 4, this.limit ? this.limit - done : Infinity))
|
||||
if (batch.length === 0) {
|
||||
if (this.limit) break
|
||||
await Shutdown.sleep(IDLE_MS)
|
||||
continue
|
||||
}
|
||||
let next = 0
|
||||
await Promise.all(
|
||||
Array.from({ length: concurrency }, async () => {
|
||||
while (next < batch.length) {
|
||||
const status = await DeferredService.process(batch[next++])
|
||||
counts[status] = (counts[status] ?? 0) + 1
|
||||
}
|
||||
})
|
||||
)
|
||||
done += batch.length
|
||||
this.logger.info(`${done} deferred files processed: ${Object.entries(counts).map(([k, v]) => `${v} ${k}`).join(', ')}.`)
|
||||
} catch (err: any) {
|
||||
// E.g. Postgres restarting: wait and claim again, instead of ending the loop (LOG.md 2026-10-07 (3)).
|
||||
this.logger.error(`Round failed, retrying in 30 s: ${err.message}`)
|
||||
await Shutdown.sleep(30_000)
|
||||
}
|
||||
let next = 0
|
||||
await Promise.all(
|
||||
Array.from({ length: concurrency }, async () => {
|
||||
while (next < batch.length) {
|
||||
const status = await DeferredService.process(batch[next++])
|
||||
counts[status] = (counts[status] ?? 0) + 1
|
||||
}
|
||||
})
|
||||
)
|
||||
done += batch.length
|
||||
this.logger.info(`${done} deferred files processed: ${Object.entries(counts).map(([k, v]) => `${v} ${k}`).join(', ')}.`)
|
||||
}
|
||||
} finally {
|
||||
await NntpService.shutdown()
|
||||
|
||||
Reference in new issue
Block a user