Posting-time windows into the corpus: ranges:dates, ranges:capture
ranges:dates samples each active group's posting dates from the news server (group_dates) and estimates every range's date (ranges.est_date). ranges:capture --from --to marks a window's ranges of every group for the corpus. The corpus fill takes capture ranges in priority order, done ones too, and remembers complete ones (ranges.stored_at). Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
This commit is contained in:
1 parent
0469fcd975
commit
137e931e9e
8 files changed
+683
-40
No files matched your search
+47
-9
@@ -41,7 +41,12 @@ class Leases {
|
||||
AND l.heartbeat_at >= now() - make_interval(secs => ?)) < ${MAX_LEASES_PER_GROUP}
|
||||
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, coordinatorConfig.leaseTtlSeconds]
|
||||
[
|
||||
nodeId,
|
||||
rules.version,
|
||||
coordinatorConfig.leaseTtlSeconds,
|
||||
coordinatorConfig.leaseTtlSeconds,
|
||||
]
|
||||
)
|
||||
let { rows } = await take(true)
|
||||
if (rows.length === 0) ({ rows } = await take(false))
|
||||
@@ -49,7 +54,16 @@ class Leases {
|
||||
if (!row) return null
|
||||
await db.from('nodes').where('id', nodeId).update({ last_seen_at: new Date() })
|
||||
const group = await db.from('groups').where('id', row.group_id).select('name').firstOrFail()
|
||||
return { range: { id: Number(row.id), group: group.name, start: Number(row.start_id), end: Number(row.end_id), next: Number(row.next_id) }, rules }
|
||||
return {
|
||||
range: {
|
||||
id: Number(row.id),
|
||||
group: group.name,
|
||||
start: Number(row.start_id),
|
||||
end: Number(row.end_id),
|
||||
next: Number(row.next_id),
|
||||
},
|
||||
rules,
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -70,7 +84,8 @@ class Leases {
|
||||
|
||||
async leased(rangeId: number, nodeId: number) {
|
||||
const range = await db.from('ranges').where('id', rangeId).first()
|
||||
if (!range || range.status !== 'leased' || Number(range.node_id) !== nodeId) throw new LeaseLost(`Range ${rangeId} is not leased to this node`)
|
||||
if (!range || range.status !== 'leased' || Number(range.node_id) !== nodeId)
|
||||
throw new LeaseLost(`Range ${rangeId} is not leased to this node`)
|
||||
return range
|
||||
}
|
||||
|
||||
@@ -83,8 +98,14 @@ class Leases {
|
||||
/** The worker reached the range's end: done, and its spooled chunks go. */
|
||||
async finish(rangeId: number, nodeId: number) {
|
||||
const range = await this.leased(rangeId, nodeId)
|
||||
if (Number(range.next_id) <= Number(range.end_id)) throw new LeaseLost(`Range ${rangeId} is at ${range.next_id}, not past its end ${range.end_id}`)
|
||||
await db.from('ranges').where('id', rangeId).update({ status: 'done', done_at: new Date(), heartbeat_at: new Date() })
|
||||
if (Number(range.next_id) <= Number(range.end_id))
|
||||
throw new LeaseLost(
|
||||
`Range ${rangeId} is at ${range.next_id}, not past its end ${range.end_id}`
|
||||
)
|
||||
await db
|
||||
.from('ranges')
|
||||
.where('id', rangeId)
|
||||
.update({ status: 'done', done_at: new Date(), heartbeat_at: new Date() })
|
||||
await Spool.remove(rangeId)
|
||||
}
|
||||
|
||||
@@ -95,12 +116,19 @@ class Leases {
|
||||
*/
|
||||
async corrupt(rangeId: number, nodeId: number, from: number) {
|
||||
const range = await this.leased(rangeId, nodeId)
|
||||
const span = Spool.chunksOf({ start: Number(range.start_id), end: Number(range.end_id) }).find((s) => s.from === from)
|
||||
const span = Spool.chunksOf({ start: Number(range.start_id), end: Number(range.end_id) }).find(
|
||||
(s) => s.from === from
|
||||
)
|
||||
if (span) {
|
||||
await Spool.removeChunk(rangeId, span)
|
||||
if (range.capture) {
|
||||
const group = await db.from('groups').where('id', range.group_id).select('name').first()
|
||||
await Corpus.removeChunk({ group: group.name, start: Number(range.start_id), end: Number(range.end_id) }, span)
|
||||
await Corpus.removeChunk(
|
||||
{ group: group.name, start: Number(range.start_id), end: Number(range.end_id) },
|
||||
span
|
||||
)
|
||||
// Not complete in the corpus any more: the corpus fill fetches the chunk again.
|
||||
await db.from('ranges').where('id', rangeId).update({ stored_at: null })
|
||||
}
|
||||
}
|
||||
const plain: number[] = (range.plain_chunks ?? []).map(Number)
|
||||
@@ -108,11 +136,21 @@ class Leases {
|
||||
// refreshed yet) and spooled again (range 161820, LOG.md 2026-10-11), so a second try plain first.
|
||||
if (plain.filter((p) => p === from).length >= 2) {
|
||||
// Fetched plain (deflated here) and still not inflating: not the server's compression; set aside.
|
||||
await db.from('ranges').where('id', rangeId).update({ status: 'failed', node_id: null, error: `chunk ${from} doesn't inflate, also fetched plain` })
|
||||
await db
|
||||
.from('ranges')
|
||||
.where('id', rangeId)
|
||||
.update({
|
||||
status: 'failed',
|
||||
node_id: null,
|
||||
error: `chunk ${from} doesn't inflate, also fetched plain`,
|
||||
})
|
||||
return
|
||||
}
|
||||
// The server's compressed reply is cut short (the same bytes every time): fetched plain next time.
|
||||
await db.rawQuery(`UPDATE ranges SET status = 'planned', node_id = NULL, plain_chunks = array_append(plain_chunks, ?::bigint) WHERE id = ?`, [from, rangeId])
|
||||
await db.rawQuery(
|
||||
`UPDATE ranges SET status = 'planned', node_id = NULL, plain_chunks = array_append(plain_chunks, ?::bigint) WHERE id = ?`,
|
||||
[from, rangeId]
|
||||
)
|
||||
}
|
||||
|
||||
/** A stopping worker gives its range back; the next one resumes it. */
|
||||
|
||||
Reference in new issue
Block a user