Rebuild: prefetching no longer waits for merging, nor stalls on finished ranges
The coordinator ran the prefetch tick in the same loop as the merger (up to 30 s a minute): its connections went idle once their targets were fetched, and the first leases after a start found nothing spooled. The prefetcher now ticks in a loop of its own. The prefetcher took the first planned ranges with nothing spooled, even ones with nothing left to fetch (next_id past the end): two such ranges (edge:bench's, set back to planned) kept it from fetching anything. It and the lease query now skip those, and edge:bench marks its range done. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
1 parent
2b4f673ddb
commit
bd1c846f27
4 files changed
+18
-4
No files matched your search
@@ -19,7 +19,7 @@ class Leases {
|
||||
`UPDATE ranges r SET status = 'leased', node_id = ?, leased_at = now(), heartbeat_at = now(), attempts = attempts + 1, rule_version = ?
|
||||
WHERE r.id = (
|
||||
SELECT id FROM ranges
|
||||
WHERE spooled_chunks > 0 AND (status = 'planned' OR (status = 'leased' AND heartbeat_at < now() - make_interval(secs => ?)))
|
||||
WHERE spooled_chunks > 0 AND next_id <= end_id AND (status = 'planned' OR (status = 'leased' AND heartbeat_at < now() - make_interval(secs => ?)))
|
||||
ORDER BY priority, id LIMIT 1 FOR UPDATE SKIP LOCKED)
|
||||
RETURNING r.id, r.group_id, r.start_id, r.end_id, r.next_id`,
|
||||
[nodeId, rules.version, coordinatorConfig.leaseTtlSeconds]
|
||||
|
||||
@@ -114,7 +114,7 @@ export class Prefetcher {
|
||||
const [{ ready }] = await db.from('ranges').where('status', 'planned').where('spooled_chunks', '>', 0).count('* as ready')
|
||||
const room = this.spoolBytes < coordinatorConfig.spool.maxBytes
|
||||
const fresh = room && Number(ready) < ahead
|
||||
? await rows(db.query()).where('r.status', 'planned').where('r.spooled_chunks', 0).orderBy([{ column: 'r.priority' }, { column: 'r.id' }]).limit(ahead - Number(ready))
|
||||
? await rows(db.query()).where('r.status', 'planned').where('r.spooled_chunks', 0).whereRaw('r.next_id <= r.end_id').orderBy([{ column: 'r.priority' }, { column: 'r.id' }]).limit(ahead - Number(ready))
|
||||
: []
|
||||
const targets: Target[] = []
|
||||
for (const row of [...leased, ...(room ? started : []), ...fresh]) {
|
||||
|
||||
@@ -34,9 +34,21 @@ export default class CoordinatorRun extends BaseCommand {
|
||||
prefetcher.stop()
|
||||
await done
|
||||
})
|
||||
this.logger.info('Coordinator started.')
|
||||
// Two loops: the prefetcher's ticks don't wait for merging or planning (a merge round
|
||||
// of up to MERGE_BUDGET_MS left the connections idle once their targets were fetched).
|
||||
const prefetching = (async () => {
|
||||
while (!stopping) {
|
||||
try {
|
||||
await prefetcher.tick()
|
||||
} catch (error: any) {
|
||||
this.logger.error(`Prefetch round failed: ${error.message}`)
|
||||
}
|
||||
await sleep(TICK_MS)
|
||||
}
|
||||
})()
|
||||
let plannedAt = 0
|
||||
let mergedAt = 0
|
||||
this.logger.info('Coordinator started.')
|
||||
while (!stopping) {
|
||||
try {
|
||||
if (Date.now() - plannedAt >= PLAN_EVERY_MS) {
|
||||
@@ -65,12 +77,12 @@ export default class CoordinatorRun extends BaseCommand {
|
||||
}
|
||||
if (totals.completed || totals.incomplete) this.logger.info(`Fragments: ${totals.completed} files completed, ${totals.incomplete} incomplete, ${totals.waiting} waiting.`)
|
||||
}
|
||||
await prefetcher.tick()
|
||||
} catch (error: any) {
|
||||
this.logger.error(`Coordinator round failed: ${error.message}`)
|
||||
}
|
||||
await sleep(TICK_MS)
|
||||
}
|
||||
await prefetching
|
||||
while (prefetcher.active > 0) await sleep(200)
|
||||
await NntpPool.close()
|
||||
stopped!()
|
||||
|
||||
@@ -163,6 +163,8 @@ export default class EdgeBench extends BaseCommand {
|
||||
peakDetail = `heap ${(m.heapUsed / 1e6).toFixed(0)}/${(m.heapTotal / 1e6).toFixed(0)} MB, external ${(m.external / 1e6).toFixed(0)} MB, array buffers ${(m.arrayBuffers / 1e6).toFixed(0)} MB`
|
||||
}
|
||||
}
|
||||
// Done, so nothing takes it for a range to work on (a leased one was set back to planned once).
|
||||
if (this.store) await db.from('ranges').where('id', rangeId).update({ status: 'done', done_at: new Date() })
|
||||
const cpu = process.cpuUsage(cpuStart)
|
||||
const cpuS = (cpu.user + cpu.system) / 1e6
|
||||
const total = t.inflate + t.parse + t.index
|
||||
|
||||
Reference in new issue
Block a user