Files
usenet-indexer/app/services/planner.ts
T
Daan MeijerandClaude Opus 5.5 31493a98be
Test and deploy / test (push) Successful in 22s
Test and deploy / deploy (push) Skipped
Rebuild: merger rounds with one neighbour query, a cursor and a time budget; planning skips failing groups
The neighbour check was three queries per file (~2,000 files/minute); now
one per round of 20k files, with a cursor so waiting files don't take
every round's places, and rounds until nothing is left or 30 s. On the
dev backlog (old-style fragments): ~18k files/minute in the 30 s budget;
at full throughput the new fragment rule leaves ~1,200 files/minute.
A group that fails GROUP (gone from the server) no longer stops planning
the others; edge:bench's groups are inactive.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-09 02:25:45 +02:00

73 lines
2.9 KiB
TypeScript

import db from '@adonisjs/lucid/services/db'
import logger from '@adonisjs/core/services/logger'
import coordinatorConfig from '#config/coordinator'
import NntpPool from '#services/nntp_pool'
/**
* The indexed groups and their ranges (REBUILD.md, group list, coordinator).
* New groups get priorities after the existing ones (owner rule). A group's
* span from GROUP is cut into ranges of RANGE_ARTICLES; a range's priority is
* its position in its group's history (0 oldest … 1000 newest), so all groups
* start with their oldest era. Planning again only adds ranges for new articles.
*/
class Planner {
async addGroups(names: string[]): Promise<number> {
let added = 0
for (const name of names) {
const { rows } = await db.rawQuery(
`INSERT INTO groups (name, priority) SELECT ?, coalesce(max(priority), 0) + 1 FROM groups ON CONFLICT (name) DO NOTHING RETURNING id`,
[name]
)
added += rows.length
}
return added
}
/** The `top` groups matching `pattern` by article span, largest first (LIST ACTIVE). */
async largestGroups(pattern: string, top: number): Promise<string[]> {
const groups = await NntpPool.use((client) => client.listActive(pattern))
return groups
.filter((g) => g.high > g.low)
.sort((a, b) => b.high - b.low - (a.high - a.low))
.slice(0, top)
.map((g) => g.name)
}
async planGroup(group: { id: number; name: string }): Promise<number> {
const info = await NntpPool.use((client) => client.group(group.name))
const size = coordinatorConfig.rangeArticles
const last = await db.from('ranges').where('group_id', group.id).max('end_id as end').first()
const from = Math.max(info.low, Number(last?.end ?? 0) + 1)
const span = Math.max(1, info.high - info.low)
const rows = []
for (let start = from; start <= info.high; start += size) {
rows.push({
group_id: group.id,
start_id: start,
end_id: Math.min(start + size - 1, info.high),
next_id: start,
priority: Math.floor((1000 * (start - info.low)) / span),
})
}
for (let i = 0; i < rows.length; i += 2000) await db.table('ranges').multiInsert(rows.slice(i, i + 2000))
await db.from('groups').where('id', group.id).update({ low: info.low, high: info.high, planned_at: new Date() })
return rows.length
}
async planAll(): Promise<{ groups: number; ranges: number }> {
const groups = await db.from('groups').where('active', true).orderBy('priority').select('id', 'name')
let ranges = 0
for (const group of groups) {
// One group failing (e.g. gone from the server) doesn't stop the others.
try {
ranges += await this.planGroup({ id: Number(group.id), name: group.name })
} catch (error: any) {
logger.warn(`Planning ${group.name}: ${error.message}`)
}
}
return { groups: groups.length, ranges }
}
}
export default new Planner()