Files
orca/cloud/apps/relay/src/database/postgres-lock-wait-sample.ts
T
Neil 46fa97a6b4 refactor(relay): group route, forwarding and connection owners (#38374)
* refactor(relay): group route, forwarding and connection owners

* refactor(relay): use explicit defining-owner type imports
2026-11-04 21:59:50 -08:00

49 lines
2.1 KiB
TypeScript

import type { RelayDatabase } from './database.js'
import type { DatabaseLockWaitSample } from '../observability/relay-observability.js'
// Use application_name (orca-relay/<role>/<cell>) to separate shared-user waiters. Follow blockers to root, keeping non-relay intermediates and bounding depth for cycles. First referenced relay table labels the wait. Shared 3-slot pool can queue/undercount samples when saturated; dedicated sampling avoids it.
const LOCK_WAIT_SAMPLE_SQL = `
WITH RECURSIVE waiting AS MATERIALIZED (
SELECT pid, application_name, query, (pg_blocking_pids(pid))[1] AS blocker
FROM pg_stat_activity
WHERE datname = current_database() AND wait_event_type = 'Lock'
), chain AS (
SELECT pid AS waiter, blocker AS pid, 1 AS depth FROM waiting
UNION ALL
SELECT chain.waiter, waiting.blocker, chain.depth + 1
FROM chain JOIN waiting ON waiting.pid = chain.pid
WHERE chain.depth < 8
), root AS (
SELECT DISTINCT ON (waiter) waiter, pid FROM chain ORDER BY waiter, depth DESC
)
SELECT split_part(w.application_name, '/', 2) AS waiter_role,
COALESCE(
substring(w.query FROM '\\m(relay_cells|relay_assignments)\\M'),
'other'
) AS waited_table,
split_part(holder.application_name, '/', 2) AS holder_role,
COUNT(*) AS waiters
FROM waiting w JOIN root ON root.waiter = w.pid
LEFT JOIN pg_stat_activity holder ON holder.pid = root.pid
WHERE w.application_name LIKE 'orca-relay/%'
GROUP BY 1, 2, 3`
const RELAY_ROLES = new Set(['director', 'cell', 'combined'])
export async function readPostgresLockWaitSample(
database: RelayDatabase
): Promise<DatabaseLockWaitSample> {
const rows = await database.query(LOCK_WAIT_SAMPLE_SQL)
return rows.map((row) => ({
waiterRole: relayRole(row['waiter_role']),
table: String(row['waited_table']),
holderRole: relayRole(row['holder_role']),
waiters: Number(row['waiters'])
}))
}
// Anything else (an operator session, a finished holder) stays one bounded key.
function relayRole(value: unknown): string {
return typeof value === 'string' && RELAY_ROLES.has(value) ? value : 'other'
}