From a2fdca08cf0e5b553bc46fe6811a835f4eea71db Mon Sep 17 00:00:00 2001 From: Claude Date: Fri, 10 Jul 2026 06:19:18 +0000 Subject: [PATCH] docs(graperank): record sub-cap rejection + cold hop-5 validation in plan Per-relay sub cap 32 made the hop-3 crawl 52% slower with slightly fewer lists (27 relays demoted us vs 5 at cap 16) - the Phase-B plateau is relay-side service rate, so 16 stays the default and AMY_RELAY_SUB_CAP remains an experiment hatch. Final validation: cold hop-5 completed in 85.4 min with 203,903 contact lists / 391,549 users / 626,599 events - the workload that never finished before this branch. Co-Authored-By: Claude Fable 5 Claude-Session: https://claude.ai/code/session_013zEYRGKF943RgLaHTViJaB --- quartz/plans/2026-07-10-graperank-connect-storm.md | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/quartz/plans/2026-07-10-graperank-connect-storm.md b/quartz/plans/2026-07-10-graperank-connect-storm.md index 32c09c10e6..04c9eceae3 100644 --- a/quartz/plans/2026-07-10-graperank-connect-storm.md +++ b/quartz/plans/2026-07-10-graperank-connect-storm.md @@ -95,6 +95,16 @@ noise between runs is normal — relays come and go). | + sharded-sweep dedup | 675s* | 18,801 | 168k | keep — round wall ↓ (301s vs 336s); total noise | | + overlap tail (no convergence park-wait, agg ∥ deletions) | 474s | 18,816 | 167k | **keep** | | + `--drain-concurrency 48` on top | **396s** | 18,816 | 167k | **keep → new default** | +| + per-relay sub cap 16→32 (`AMY_RELAY_SUB_CAP`) | 602s | 18,478 | 164k | **reject** — 27 relays demoted us + 7 rate-limited (vs 5+1 at 16); the Phase-B plateau is relay-side service rate, not client permits | + +Final validation — **cold hop-5, fresh store, winning stack** (the workload that +never completed pre-fixes): **85.4 min, 203,903 contact lists, 391,549 users +discovered, 626,599 events, 5,794 relays**. Per-hop list completeness: 90% +(hop 2), 71% (hop 3), 56% (hop 4). Remaining known lever for a future pass: +attempt>0 retries re-fan every user to the whole backbone inside per-batch +units, so the two retry rounds cost nearly as much as first passes at a +fraction of the yield — route retry backbone re-asks as round-wide chunked +per-relay units instead. \* total inflated by a slow round-3 network sample + the then-serial tail; the change's own effect (straggler-round Phase A 20s → 20ms) is visible directly.