Lease lanes for the tail, a mixed lease order, coordinator:status, the edge end to end
A group now has two lease lanes (migration 6600): `history` works the ranges the bounds hand out, `tail` the tail planner's, each with its own holder, window, snapshot and takeover redo, so a thread on the tail never wades through a group's history and a held group's tail isn't stuck behind it. The edge puts `--tail-threads` (EDGE_TAIL_THREADS, 1 of 2+ by default) of its threads on the tail lane; the group routes take `?lane=`. The lease order within a lane alternates the group with the most planned articles and the longest unheld one. The takeover redo puts back only the lane's ranges the window did after the snapshot, and a group whose last range is held by a holder gone quiet can be taken over. `coordinator:status` prints the catalog's room, the ranges by band, the last hour's rates, the held groups with their snapshots and the phase-2 backlogs. `tests/e2e` runs the real edge-node binary against the node API: the corpus-fill race, a failed stream and the restart that restores the snapshot, a restart without the snapshot file, a takeover (STREAM_CHUNK_WAIT_MINUTES is a setting now). CI builds the binary before the tests. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
This commit is contained in:
1 parent
db96642a72
commit
680751e26a
21 files changed
+1362
-180
No files matched your search
@@ -0,0 +1,149 @@
|
||||
import { spawn } from 'node:child_process'
|
||||
import { access } from 'node:fs/promises'
|
||||
import { resolve } from 'node:path'
|
||||
import { deflateSync } from 'node:zlib'
|
||||
import env from '#start/env'
|
||||
|
||||
export const GROUP = 'alt.binaries.e2e'
|
||||
|
||||
/** The edge worker binary: EDGE_NODE_BIN, else the release or debug build under edge/target. */
|
||||
export async function edgeBinary(): Promise<string> {
|
||||
const candidates = [
|
||||
process.env.EDGE_NODE_BIN,
|
||||
'edge/target/release/edge-node',
|
||||
'edge/target/debug/edge-node',
|
||||
]
|
||||
.filter((c): c is string => !!c)
|
||||
.map((c) => resolve(c))
|
||||
for (const path of candidates) {
|
||||
try {
|
||||
await access(path)
|
||||
return path
|
||||
} catch {}
|
||||
}
|
||||
throw new Error(
|
||||
`No edge-node binary (looked at ${candidates.join(', ')}): build it with "cargo build --release --manifest-path edge/Cargo.toml --bin edge-node", or set EDGE_NODE_BIN`
|
||||
)
|
||||
}
|
||||
|
||||
/** The test server's address for the worker (tests/bootstrap.ts starts it on HOST:PORT). */
|
||||
export function coordinatorUrl(): string {
|
||||
const host = env.get('HOST', 'localhost')
|
||||
return `http://${host === '0.0.0.0' ? '127.0.0.1' : host}:${env.get('PORT', 3333)}`
|
||||
}
|
||||
|
||||
export interface EdgeRun {
|
||||
exit: Promise<{ code: number | null; signal: string | null }>
|
||||
lines: string[]
|
||||
kill: () => void
|
||||
}
|
||||
|
||||
/**
|
||||
* The real edge worker against the test server: one thread on the history lane, one group, a batch per chunk
|
||||
* (100 articles in these tests), a snapshot after every range.
|
||||
*/
|
||||
export async function startEdge(token: string, args: string[] = []): Promise<EdgeRun> {
|
||||
const bin = await edgeBinary()
|
||||
// The test server first (tests/bootstrap.ts starts it for this suite): a worker that can't connect retries for
|
||||
// minutes before it says so.
|
||||
const probe = await fetch(`${coordinatorUrl()}/api/v1/node/lease`, { method: 'POST' }).catch(
|
||||
(e) => e as Error
|
||||
)
|
||||
if (probe instanceof Error || probe.status !== 401)
|
||||
throw new Error(
|
||||
`The test server doesn't answer at ${coordinatorUrl()}: ${probe instanceof Error ? probe.message : `HTTP ${probe.status}`}`
|
||||
)
|
||||
const child = spawn(
|
||||
bin,
|
||||
[
|
||||
'--threads',
|
||||
'1',
|
||||
'--tail-threads',
|
||||
'0',
|
||||
'--groups',
|
||||
'1',
|
||||
'--batch-articles',
|
||||
'100',
|
||||
'--snapshot-minutes',
|
||||
'0',
|
||||
...args,
|
||||
],
|
||||
{
|
||||
env: { ...process.env, COORDINATOR_URL: coordinatorUrl(), NODE_TOKEN: token },
|
||||
stdio: ['ignore', 'pipe', 'pipe'],
|
||||
}
|
||||
)
|
||||
const lines: string[] = []
|
||||
let rest = ''
|
||||
const collect = (chunk: Buffer) => {
|
||||
rest += chunk.toString('utf8')
|
||||
const parts = rest.split('\n')
|
||||
rest = parts.pop() ?? ''
|
||||
lines.push(...parts)
|
||||
}
|
||||
child.stdout.on('data', collect)
|
||||
child.stderr.on('data', collect)
|
||||
const exit = new Promise<{ code: number | null; signal: string | null }>((done) => {
|
||||
child.on('exit', (code, signal) => {
|
||||
if (rest) lines.push(rest)
|
||||
done({ code, signal })
|
||||
})
|
||||
})
|
||||
return { exit, lines, kill: () => child.kill('SIGKILL') }
|
||||
}
|
||||
|
||||
/** Runs the worker to its end (at most `timeoutMs`), its log lines and exit code. */
|
||||
export async function runEdge(token: string, args: string[] = [], timeoutMs = 60_000) {
|
||||
const run = await startEdge(token, args)
|
||||
const timer = setTimeout(() => run.kill(), timeoutMs)
|
||||
const result = await run.exit
|
||||
clearTimeout(timer)
|
||||
return { ...result, lines: run.lines }
|
||||
}
|
||||
|
||||
/** Polls `condition` every 100 ms until it holds or `timeoutMs` passed (then throws). */
|
||||
export async function waitFor(what: string, condition: () => Promise<boolean>, timeoutMs = 30_000) {
|
||||
const until = Date.now() + timeoutMs
|
||||
while (Date.now() < until) {
|
||||
if (await condition()) return
|
||||
await new Promise((r) => setTimeout(r, 100))
|
||||
}
|
||||
throw new Error(`Timed out waiting for ${what}`)
|
||||
}
|
||||
|
||||
const BASE_MS = Date.UTC(2026, 9, 5, 10)
|
||||
|
||||
/** A file name without digits (a number sequence would make an album of a poster's files): letters from `k`. */
|
||||
export function nameOf(k: number): string {
|
||||
let s = ''
|
||||
let n = k
|
||||
do {
|
||||
s = String.fromCharCode(97 + (n % 26)) + s
|
||||
n = Math.floor(n / 26)
|
||||
} while (n > 0)
|
||||
return `Set.${s}.mkv`
|
||||
}
|
||||
|
||||
/**
|
||||
* The overview lines of articles `from`..`to`, one an hour from 2026-10-05: article 1 is a one-part file, and from 2
|
||||
* on each even article is part 1 of a two-part file whose part 2 is the next (odd) article — so a file spans every
|
||||
* chunk boundary at an even `to` (100 and 101, 200 and 201: the window has to carry it). Dates an hour apart make
|
||||
* the posting frontier move a day every 24 articles, so the window closes on files as it goes.
|
||||
*/
|
||||
export function overviewLines(from: number, to: number): string[] {
|
||||
const lines: string[] = []
|
||||
for (let n = from; n <= to; n++) {
|
||||
const date = new Date(BASE_MS + n * 3600_000).toUTCString().replace(' GMT', ' +0000')
|
||||
const [name, part] =
|
||||
n === 1 ? [nameOf(1), '(1/1)'] : n % 2 === 0 ? [nameOf(n), '(1/2)'] : [nameOf(n - 1), '(2/2)']
|
||||
lines.push(
|
||||
`${n}\t"${name}" yEnc ${part}\tposter <p@x>\t${date}\t<a${n}@e2e>\t\t700000\t5000\tXref: news.example ${GROUP}:${n}`
|
||||
)
|
||||
}
|
||||
return lines
|
||||
}
|
||||
|
||||
/** One XOVER chunk as the news server sends it (deflated). */
|
||||
export function overviewChunk(from: number, to: number): Buffer {
|
||||
return deflateSync(Buffer.from(overviewLines(from, to).join('\r\n') + '\r\n'))
|
||||
}
|
||||
Reference in new issue
Block a user