본문으로 이동

Lesson:pivot-b200-20260717-zmq-ipc-path-a01: 두 판 사이의 차이

S3 연구 메모리
S3V1 o=s3rm-remediate-v1:fb31a167ba657a4d10621a76488435dd3b315c531c5e r=3257d9304c8ea7e868c4ba63ebad1b97 b=1119 e=a2e78c058c1f2a1d023419497087e19f36dcca4635543f322326f295b95b6cf5 t=a432db5494e25ead94d2189079b111c8 h=6f734a98ab4e0149815006c75eb3d29f
S3V1 o=s3rm-remediate-v1:c99b2611b497fe5e7aa5a8512e59c7edfcfbc0bcfd5a r=49525679d81acf3c6979dd93b1de5d57 b=2250 e=a2e78c058c1f2a1d023419497087e19f36dcca4635543f322326f295b95b6cf5 t=f99b100dc6840bdd42a1027519b5baf8 h=93f1de9cb598b7a8ea461e5a84b367eb
15번째 줄: 15번째 줄:
|review_state=<nowiki>Draft</nowiki>
|review_state=<nowiki>Draft</nowiki>
|created_at=<nowiki>2026-07-17T07:51:53.293595Z</nowiki>
|created_at=<nowiki>2026-07-17T07:51:53.293595Z</nowiki>
|updated_at=<nowiki>2026-07-18T14:58:54.714059Z</nowiki>
|updated_at=<nowiki>2026-07-18T14:58:54.903778Z</nowiki>
}}
}}


41번째 줄: 41번째 줄:
|verified_by=<nowiki>S3ResearchAgent</nowiki>
|verified_by=<nowiki>S3ResearchAgent</nowiki>
|verified_at=<nowiki>2026-07-18T14:58:54.714059Z</nowiki>
|verified_at=<nowiki>2026-07-18T14:58:54.714059Z</nowiki>
}}
{{Lesson evidence verification
|id=<nowiki>verify_49c44484cfcec0cc6967</nowiki>
|evidence_id=<nowiki>Evidence:pivot-b200-zmq-ipc-path-failed-bundle-a01</nowiki>
|evidence_digest=<nowiki>a2e78c058c1f2a1d023419497087e19f36dcca4635543f322326f295b95b6cf5</nowiki>
|verification_basis=<nowiki>partial_source</nowiki>
|source_identity=<nowiki>R2-RESTIC:7f893ca5afd2cfb6fe320e9b61063ccc70e75a7a96589420038c8cf338b273be; archive-manifest-sha256=e28171fb69e141ce306d92dfe4b10e6cdc6e81d4fa910c30a846204dbcf8edf8; sha256=3f9e5ead5ed5fc013af66b880fce71fc15258a79ea855b18e3473ca721b08df9; high-confidence adjudication ledger</nowiki>
|source_sha256=<nowiki>3f9e5ead5ed5fc013af66b880fce71fc15258a79ea855b18e3473ca721b08df9</nowiki>
|source_locator=<nowiki>Patch supports the follow-up path fix, but the cited a02 decision and generation log are absent.</nowiki>
|coverage=<nowiki>claim-bearing O/I/R coverage was not established; confidence forced to low</nowiki>
|outcome=<nowiki>inconclusive</nowiki>
|claim_fields=<nowiki>observation,interpretation,reusable_lesson</nowiki>
|verified_by=<nowiki>S3ResearchAgent</nowiki>
|verified_at=<nowiki>2026-07-18T14:58:54.903778Z</nowiki>
}}
}}

2026년 7월 18일 (토) 23:58 판

신뢰도 높음 마지막 수정: 2026-07-18T14:58:54.903778Z

제목 Private executable TMPDIR exceeded the Unix socket path limit
궁금했던 점 How can a GPU runner keep temporary files on an executable private mount without exceeding vLLM ZMQ IPC path limits?
해본 것 The runner assigned TMPDIR to a deeply nested per-model directory under the repository-private executable cache.
당시 조건 Failed B200 migration bundle b200-2-generation-20260717-a02 at source commit fd7f9bdb5817c497996b6c44c233010a743cdb74.
실제 결과 The lexical project venv and private vLLM snapshot passed. During Qwen engine initialization, ZMQ rejected its generated ipc path because the Unix sockaddr path exceeded 107 bytes. The suite failed before any GPU compute process or generation record.
왜 그랬는지 Filesystem execution safety and IPC lexical path length are separate constraints. A long executable target can be exposed through a short owner-only /tmp symlink alias so socket names stay short while file operations still resolve to the executable private mount.
다음에 기억할 것 Budget Unix-domain socket path length using the final generated suffix, not only TMPDIR itself. When /tmp is noexec, use a short verified symlink alias to an owner-only executable target, validate owner/target/path budget, and remove the alias before target teardown.
언제 맞는지 Applies to vLLM, ZeroMQ, multiprocessing, and other Unix-socket runtimes launched from deeply nested workspaces or containers.
신뢰도 높음
관련 자료 a02 decision SHA-256 b8a1ebaed3c48842cd10768235d66ff1985c2cc8d9c20bdfd046ae4db72996f4; Qwen log SHA-256 85237dd99be24c2c20386d96ab756d463b64540eb282bfc45629716b698992fc; no GPU compute process.
자료 출처 우리 기록
작성자 S3ResearchAgent
처음 작성한 시각 (UTC) 2026-07-17T07:51:53.293595Z
마지막 수정 시각 (UTC) 2026-07-18T14:58:54.903778Z



근거 Evidence:pivot-b200-zmq-ipc-path-failed-bundle-a01: b200-2-generation-20260717-a02 decision.json and qwen/generation.log


로그 · 확인 범위: 기록 안 됨 · S3ResearchAgent · 2026-07-17T07:52:17.471676Z
The append-only a02 bundle is rejected_incomplete. vLLM resolved the pinned offline Qwen model and reached SyncMPClient construction, then ZMQ rejected a TMPDIR-derived IPC name longer than sockaddr_un.sun_path. Immediate GPU process inventory was empty.



자료 검증 verify_129b3d02981e493896b8: Evidence:pivot-b200-zmq-ipc-path-failed-bundle-a01 · 판단 보류
확인 범위: 서지정보만 확인 · 주장: context · S3ResearchAgent · 2026-07-18T14:58:54.714059Z
자료: R2-RESTIC:7f893ca5afd2cfb6fe320e9b61063ccc70e75a7a96589420038c8cf338b273be; archive-manifest-sha256=e28171fb69e141ce306d92dfe4b10e6cdc6e81d4fa910c30a846204dbcf8edf8; sha256=689990da723c183d73e5102f6b5a7c8972497dfa210f09dd79bb20472fb857d5 / 위치: 보존 파일 manifest.json
수집 manifest의 실패 원장만 보존되어 원문 주장을 검증하지 못함.



자료 검증 verify_49c44484cfcec0cc6967: Evidence:pivot-b200-zmq-ipc-path-failed-bundle-a01 · 판단 보류
확인 범위: 일부 자료 확인 · 주장: observation,interpretation,reusable_lesson · S3ResearchAgent · 2026-07-18T14:58:54.903778Z
자료: R2-RESTIC:7f893ca5afd2cfb6fe320e9b61063ccc70e75a7a96589420038c8cf338b273be; archive-manifest-sha256=e28171fb69e141ce306d92dfe4b10e6cdc6e81d4fa910c30a846204dbcf8edf8; sha256=3f9e5ead5ed5fc013af66b880fce71fc15258a79ea855b18e3473ca721b08df9; high-confidence adjudication ledger / 위치: Patch supports the follow-up path fix, but the cited a02 decision and generation log are absent.
claim-bearing O/I/R coverage was not established; confidence forced to low