perf: index routing snapshots and quota usage

This commit is contained in:
kami
2026-07-30 15:36:23 +04:00
parent e8fadfc998
commit fbb13c89d2
8 changed files with 577 additions and 63 deletions
+11 -5
View File
@@ -64,11 +64,17 @@ released agent, or reject a valid completion.
## P2 — performance
- Cache/parallelise health probes; schedule from one task/worker snapshot.
Current routing repeatedly scans tasks and probes candidates per queued task.
- Index active leases and quota windows. Do not scan the whole event log per
availability check or rewrite the full task snapshot after every event.
- Add 1k/10k-task benchmarks with assignment and append p95 budgets.
- **Closed 2026-07-30.** Each scheduling pass takes one atomic task/lease
snapshot, batches cached (TTL) reachability probes concurrently, and
evaluates candidate availability once. It no longer probes candidates or
scans active tasks once per queued task.
- **Closed 2026-07-30.** Active leases and per-harness, time-ordered quota
receipts are projection indexes. Availability uses indexed rolling-window
sums rather than decoding the event log; the task snapshot is a one-time
disposable compatibility cache rather than a full rewrite on every append.
- **Closed 2026-07-30.** `BenchmarkAssignPending{1K,10K}` and
`BenchmarkAppend{1K,10K}` report and enforce p95 budgets, with durable
fsync cost included in their respective paths.
## Delivery order