From 065e31a536a59badf20b1d430e169161942cccbc Mon Sep 17 00:00:00 2001 From: igneum-labs <337424239+igneum-labs@users.noreply.github.com> Date: Wed, 7 Oct 2026 18:33:47 +0000 Subject: [PATCH] in-house-pass.md: the SIGSTOP yield retired; sweeps at nice 10 on cores 8 to 95 under the build-server lane's rule Co-Authored-By: Claude Fable 5.1 --- docs/plans/cryptanalysis/in-house-pass.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/plans/cryptanalysis/in-house-pass.md b/docs/plans/cryptanalysis/in-house-pass.md index 89b141c6c..1b02ff24a 100644 --- a/docs/plans/cryptanalysis/in-house-pass.md +++ b/docs/plans/cryptanalysis/in-house-pass.md @@ -84,7 +84,7 @@ Standing rule from the project lead through main (7 October 2026, 19:1x BST), bi | Rule | What it means for a lane | |---|---| | Every idle core on both boxes | A lane runs on build-1 and build-2 together, on every idle core, at nice 10, no core band; release builds and the class v5 suites keep priority. the project lead's read at 19:4x BST: build-1 at 11 percent, build-2 at 56; his word is both near max, so CPU-bound sweeps go to build-1 explicitly (`--box 1`) and both boxes stay above 80 percent until the queue is empty; the build-server lane raises the lease pool to about 88 cores per box | -| Yield to builds | The capacity layer's pattern (`infra/build-server`, the yield-to-builds workload): the run polls `/srv/builds/_locks` every 5 s, SIGSTOPs its own process group while any `build-` or `measure` lock is held, SIGCONT when clear Box rule from the build-server lane (19:4x BST): every bounded run through `tools/build-remote.sh` takes the last 88 of 96 cores at nice 10 with `-j 88` (the first 8 cores reserved for release builds, the seed and the observer); the router spills to the other box when the preferred box has no free slot or a 1-minute load above 80; a pinned measurement leases its exact cores with `/srv/builds/_bin/lease cores --label "..." --owner adv- -- ` (no measure flock); every adversarial worktree merges the mirror's master at `04c4d9bc` or later | +| Yield to builds | RETIRED at 19:3x BST (adv-accept's exception: a build slot is held nearly continuously on both boxes, so the SIGSTOP yield of the capacity layer kept every sweep in state T and "both boxes above 80 percent" was unreachable). In its place the build-server lane's rule (19:4x BST): every bounded run at nice 10 on cores 8 to 95 only (`taskset -c 8-95`; cores 0 to 7 reserved for release builds, the seed and the observer), `-j 88` through `tools/build-remote.sh`, the router spilling to the other box at no free slot or a 1-minute load above 80, a pinned measurement leasing its exact cores with `/srv/builds/_bin/lease cores --label "..." --owner adv- -- ` (no measure flock), every adversarial worktree merged to the mirror's master at `04c4d9bc` or later; each lane notes the change and its time in its report | | Back to back | Question `n + 1`'s sweep starts the minute question `n`'s ends; no waiting for a human to read; each result row lands in the report and is pushed as it lands | | No lane idle | Every planned sweep is a self-contained executable in `/srv/builds/_adv//queue/NN--.sh` on build-2 (binary path, args, log path, pid file); a lane claims a file before running it with `mkdir /srv/builds/_adv//claims/` (atomic); a lane whose own queue is empty claims the next unclaimed file of any sibling on its target, runs it, and names the owner in its report The held lanes' sweeps are in the queue as DEFINITION ONLY files (`90-` to `92-adv-cache-3-*`, `90-` to `92-adv-accept-3-*`, 19:3x BST): an idle lane claims one, implements it in its own crate, runs it and reports it, naming the owner | | Pods | Second resort after the boxes' idle cores. The fleet's rules (the fleet lane, 18:26Z): no CPU-only pod type exists; every pod is a RunPod GPU pod (secure, or a 3090 or 4090 community; Vast unreliable tonight), image nvidia/cuda 12.8.1 on Ubuntu 24.04, 40 GB disk, vCPUs with the card (4 to 16), rented by `oneshot.py rent