pending:classes without table scans; an index for the prober's startup reset
Test and deploy / test (push) Successful in 2m55s
Test and deploy / deploy (push) Successful in 25m6s

The first run scanned the 58M-row pending table on the HDD once per
6-hour window and starved the prober and the batch store. Now one scan
classes the finished rows and seeds the record, and the waiting rows go
by windows of created_at through their index. The prober's start puts a
previous run's claims back with a status scan of the same table, 20+
minutes after every deploy: a partial index on the taken rows (migration
6900) makes it instant.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
This commit is contained in:
Daan MeijerandClaude Fable 5.1 committed 2026-11-02 13:33:48 +01:00
1 parent 3612bf3e43
commit 4d46db291e
2 files changed
+58 -30

No files matched your search

+38 -30
View File
@@ -6,9 +6,10 @@ import { describeClass } from '#lib/release/index'
/**
* The pending ladder's classes (LOG.md (130)) on the rows from before them: `klass` (the SQL pending_class) and
* `target_bytes` (the first target's bytes, when its candidates carry them) set in windows of created_at; the
* finished rows among them (named, exhausted, naming) seed each class's record, which gets its verdict (dropped) as
* the ladder gives it; then pending_classes' `waiting` counted afresh from the rows. --report shows the record.
* `target_bytes` (the first target's bytes, when its candidates carry them). The finished rows (named, exhausted,
* naming) in one scan, seeding each class's record, which gets its verdict (dropped) as the ladder gives it; the
* waiting rows in windows of created_at by their index (a scan per window starved the prober on the HDD); then
* pending_classes' `waiting` counted afresh from the claim's index. --report shows the record.
*/
export default class PendingClasses extends BaseCommand {
static commandName = 'pending:classes'
@@ -25,45 +26,52 @@ export default class PendingClasses extends BaseCommand {
async run() {
if (this.report) return this.showReport()
const hours = this.hours ?? 6
const { rows: span } = await db.rawQuery(
`SELECT min(created_at) AS lo, max(created_at) AS hi FROM pending_releases WHERE klass = 0`
const started = Date.now()
// The finished rows (named, exhausted, naming; 6.5M on 2026-11-02) in one pass: a scan of the table, no index
// reaches them by status; they seed each class's record.
const { rows: seeded } = await db.rawQuery(
`WITH classed AS (
UPDATE pending_releases SET klass = pending_class(name, bytes, partial),
target_bytes = (SELECT min((c->>'bytes')::bigint) FROM jsonb_array_elements(candidates) c WHERE c->>'bytes' IS NOT NULL)
WHERE klass = 0 AND status IN (1, 3, 4)
RETURNING tool, group_id, klass, status),
upserted AS (
INSERT INTO pending_classes (tool, group_id, klass, probed, named)
SELECT tool, group_id, klass, count(*), count(*) FILTER (WHERE status IN (1, 4)) FROM classed GROUP BY 1, 2, 3
ON CONFLICT (tool, group_id, klass) DO UPDATE SET probed = pending_classes.probed + excluded.probed, named = pending_classes.named + excluded.named
RETURNING 1)
SELECT (SELECT count(*) FROM classed) AS classed, (SELECT count(*) FROM upserted) AS classes`
)
if (!span[0].lo) {
this.logger.info('No rows without a class.')
} else {
this.logger.info(
`Finished rows: ${seeded[0].classed} classed into ${seeded[0].classes} classes (${Math.round((Date.now() - started) / 1000)} s).`
)
const { pendingMinProbes, pendingMaxNamed } = coordinatorConfig.probe
await db.rawQuery(
`UPDATE pending_classes SET dropped = true WHERE NOT dropped AND probed >= ?::int AND named::float <= probed * ?::float`,
[pendingMinProbes, pendingMaxNamed]
)
// The waiting rows by windows of created_at (pending_releases_waiting_idx reaches them).
const { rows: span } = await db.rawQuery(
`SELECT (SELECT min(created_at) FROM pending_releases WHERE status = 0) AS lo, (SELECT max(created_at) FROM pending_releases WHERE status = 0) AS hi`
)
if (span[0].lo) {
let from = new Date(span[0].lo)
const hi = new Date(span[0].hi)
let classed = 0
const started = Date.now()
while (from <= hi) {
const to = new Date(from.getTime() + hours * 3600_000)
// Rows of the window classed; the finished ones among them (named, exhausted, naming) seed the record.
const { rows } = await db.rawQuery(
`WITH classed AS (
UPDATE pending_releases SET klass = pending_class(name, bytes, partial),
target_bytes = (SELECT min((c->>'bytes')::bigint) FROM jsonb_array_elements(candidates) c WHERE c->>'bytes' IS NOT NULL)
WHERE klass = 0 AND created_at >= ? AND created_at < ?
RETURNING tool, group_id, klass, status),
seeded AS (
INSERT INTO pending_classes (tool, group_id, klass, probed, named)
SELECT tool, group_id, klass, count(*), count(*) FILTER (WHERE status IN (1, 4)) FROM classed WHERE status IN (1, 3, 4) GROUP BY 1, 2, 3
ON CONFLICT (tool, group_id, klass) DO UPDATE SET probed = pending_classes.probed + excluded.probed, named = pending_classes.named + excluded.named
RETURNING 1)
SELECT (SELECT count(*) FROM classed) AS classed, (SELECT count(*) FROM seeded) AS seeded`,
const result = await db.rawQuery(
`UPDATE pending_releases SET klass = pending_class(name, bytes, partial),
target_bytes = (SELECT min((c->>'bytes')::bigint) FROM jsonb_array_elements(candidates) c WHERE c->>'bytes' IS NOT NULL)
WHERE status = 0 AND created_at >= ? AND created_at < ? AND klass = 0`,
[from.toISOString(), to.toISOString()]
)
classed += Number(rows[0].classed)
classed += result.rowCount ?? 0
from = to
this.logger.info(
`Up to ${to.toISOString().slice(0, 16)}: ${classed} rows classed (${Math.round((Date.now() - started) / 1000)} s).`
`Waiting rows up to ${to.toISOString().slice(0, 16)}: ${classed} classed (${Math.round((Date.now() - started) / 1000)} s).`
)
}
// The record's verdicts on the seeded classes.
const { pendingMinProbes, pendingMaxNamed } = coordinatorConfig.probe
await db.rawQuery(
`UPDATE pending_classes SET dropped = true WHERE NOT dropped AND probed >= ?::int AND named::float <= probed * ?::float`,
[pendingMinProbes, pendingMaxNamed]
)
}
// The waiting counts from the rows themselves (the claim, the discard and the batch store keep them from here).
await db.rawQuery(`
@@ -0,0 +1,20 @@
import { BaseSchema } from '@adonisjs/lucid/schema'
/**
* The prober's start puts a previous run's claims back (PendingLadder.release: status 9 → 0), which scanned the
* 58M-row pending table on the HDD for 20+ minutes after every deploy (LOG.md (130)): a partial index on the few
* taken rows makes it instant.
*/
export default class extends BaseSchema {
static disableTransactions = true
async up() {
this.schema.raw(
`CREATE INDEX CONCURRENTLY IF NOT EXISTS pending_releases_taken_idx ON pending_releases (release_key) WHERE status = 9`
)
}
async down() {
this.schema.raw(`DROP INDEX CONCURRENTLY IF EXISTS pending_releases_taken_idx`)
}
}