Claude 39e81c1eb5 docs(geode): correct OK ordering/durability assumptions in ingestion plan ...

OK frames carry the event id, so clients pair replies by id rather
than by arrival order. NIP-01 also treats OK true as "accepted," not
"fsynced." That removes two constraints the plan was carrying:

- no per-connection FIFO requirement on OKs
- no need to delay OKs until after batch fsync

Tier 1 can fan OKs out as soon as the per-row INSERT returns inside
the open transaction, hiding the group-commit fsync entirely from
publisher latency. Tier 2 drops the order-preserving commit log and
just sends OKs straight to outQueue. The pipelined benchmark now
checks one-OK-per-event-id rather than ordering.

2026-05-07 21:35:49 +00:00

..

plans

docs(geode): correct OK ordering/durability assumptions in ingestion plan

2026-05-07 21:35:49 +00:00

src

audit(geode): drop dead firstSeenNs + clarify heap-vs-RSS in LoadBenchmark

2026-05-07 20:50:10 +00:00

build.gradle.kts

refactor(geode): test fixtures + collectUntilEose helper, move to testFixtures sourceSet

2026-05-07 13:42:20 +00:00

config.example.toml

perf(geode): adaptive outQueue + CIO pool sizing for 10k+ connections

2026-05-07 20:12:50 +00:00