The par2 prune's cursor is (created_at to the microsecond, set_id): 20k sets of one flush share a created_at

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

app/services/par2_pruner.ts

@@ -26,6 +26,9 @@ export interface PruneRound {
  * par2 reposted, whose probe writes the rows again; without rows its merge finds no files and the count check holds.
  */
 export class Par2Pruner {
+  /** Sets per batch (BATCH; smaller in the tests). */
+  constructor(private batch = BATCH) {}
+
   /**
    * Batches until done or `budgetMs` is spent (the cursor is saved per batch, the next round goes on from it): run
    * from the merger's loop, a first round over two days of sets held the merges back for hours (LOG.md 2026-10-17 (72)).
@@ -33,14 +36,18 @@ export class Par2Pruner {
   async round(budgetMs = Infinity): Promise<PruneRound> {
     const deadline = Date.now() + budgetMs
     const round: PruneRound = { complete: 0, judged: 0, rows: 0 }
-    const saved = await db.from('worker_cursors').where('name', CURSOR).first()
+    // (created_at to the microsecond, set_id): one prober flush gives thousands of sets the same created_at, and a
-    let since: Date = saved ? new Date(saved.at) : new Date(0)
+    // timestamp read back to the millisecond took the same batch again every round (LOG.md 2026-10-17 (73)).
+    const { rows: cursors } = await db.rawQuery(`SELECT at::text AS at, key FROM worker_cursors WHERE name = ?`, [CURSOR])
+    let since: string = cursors[0]?.at ?? '1970-01-01 00:00:00+00'
+    let sinceKey: string = cursors[0]?.key ?? ''
     const until = new Date(Date.now() - SETTLED_MS)
     for (;;) {
       const { rows: sets } = await db.rawQuery(
-        `SELECT set_id, max(created_at) AS at FROM par2_sets GROUP BY set_id
+        `SELECT set_id, max(created_at)::text AS at FROM par2_sets GROUP BY set_id
-         HAVING max(created_at) > ? AND max(created_at) <= ? ORDER BY 2 LIMIT ?`,
+         HAVING (max(created_at), set_id::text) > (?::timestamptz, ?::text) AND max(created_at) <= ?
-        [since, until, BATCH]
+         ORDER BY max(created_at), set_id LIMIT ?`,
+        [since, sinceKey, until, this.batch]
       )
       if (sets.length === 0) break
       const ids = sets.map((s: { set_id: string }) => s.set_id)
@@ -56,11 +63,12 @@ export class Par2Pruner {
       round.complete += done.length
       round.rows += await this.drop(done.map((s: { set_id: string }) => s.set_id))
       since = sets.at(-1).at
+      sinceKey = sets.at(-1).set_id
       await db.rawQuery(
-        `INSERT INTO worker_cursors (name, at) VALUES (?, ?) ON CONFLICT (name) DO UPDATE SET at = excluded.at`,
+        `INSERT INTO worker_cursors (name, at, key) VALUES (?, ?::timestamptz, ?) ON CONFLICT (name) DO UPDATE SET at = excluded.at, key = excluded.key`,
-        [CURSOR, since]
+        [CURSOR, since, sinceKey]
       )
-      if (sets.length < BATCH || Date.now() > deadline) break
+      if (sets.length < this.batch || Date.now() > deadline) break
     }
     if (Date.now() > deadline) return round
     // Judged: no cursor (verdicts come and go); only sets with rows left.

database/migrations/1770000004300_worker_cursors_key.ts

@@ -0,0 +1,16 @@
+import { BaseSchema } from '@adonisjs/lucid/schema'
+
+/**
+ * worker_cursors.key: a tie-breaker after `at`. The par2 pruner's cursor was a timestamp alone, read back to the
+ * millisecond: 20,000 sets of one prober flush share created_at 2026-10-15 14:38:39.883984, and every round took the
+ * same batch again (LOG.md 2026-10-17 (73)). Now (at to the microsecond, set_id).
+ */
+export default class extends BaseSchema {
+  async up() {
+    this.schema.raw(`ALTER TABLE worker_cursors ADD COLUMN IF NOT EXISTS key text`)
+  }
+
+  async down() {
+    this.schema.raw(`ALTER TABLE worker_cursors DROP COLUMN IF EXISTS key`)
+  }
+}

tests/functional/par2_pruner.spec.ts

@@ -68,4 +68,26 @@ test.group('Par2Pruner', (group) => {
     // Again: the cursor is past them, nothing more.
     assert.deepEqual(await new Par2Pruner().round(), { complete: 0, judged: 0, rows: 0 })
   })
+
+  test('more sets of one created_at than a batch holds: each batch goes on past the last one', async ({ assert }) => {
+    // One prober flush gives thousands of sets the same created_at (to the microsecond).
+    const flush = new Date('2026-10-15T14:38:39.883Z')
+    let candidate = 7000
+    for (const letter of ['p', 'q', 'r']) {
+      const key = `pr${letter}`.padEnd(40, '0')
+      const [row] = await db.table('releases').insert({ release_key: key, identity_key: key, name: key, source: 'stem', groups: '[]', group_id: 1, files: 1, readable: false }).returning('id')
+      const id = Number(row.id)
+      const setId = letter.repeat(32)
+      const h = `${letter}0`.padEnd(32, '0')
+      await db.table('par2_files').insert({ set_id: setId, file_id: h, hash16k: h, length: 1000, name: 'f.rar' })
+      candidate++
+      await db.table('probe_candidates').insert({ id: candidate, release_id: id, kind: 'lone', message_id: `<${candidate}@x>`, file: 'x', status: 'done' })
+      await db.table('file_hashes').insert({ candidate_id: candidate, release_id: id, hash16k: h, size: 1000 })
+      await db.rawQuery(`INSERT INTO par2_sets (set_id, release_id, files, created_at) VALUES (?, ?, 1, ?::timestamptz + interval '984 microseconds')`, [setId, id, flush])
+    }
+    const round = await new Par2Pruner(1).round()
+    assert.equal(round.complete, 3)
+    assert.equal((await db.from('par2_files').whereIn('set_id', ['p'.repeat(32), 'q'.repeat(32), 'r'.repeat(32)]).count('* as n'))[0].n, '0')
+    assert.equal((await db.from('worker_cursors').where('name', 'par2-prune').firstOrFail()).key, 'r'.repeat(32))
+  })
 })