[BUG] grpc server job selection algorithm can starve clients when multiple clients continuously submit
维护者通常 1 天内回复
还没有人认领这个 Issue。
评估
调研方向
The issue describes job scheduling in the gRPC server but names no source files or tests. Start by locating the server’s slot selection and job dispatch code, then inspect its scheduling tests. Done when waiting jobs are served fairly under continuous submissions and the legacy REST FIFO behavior remains unaffected.
由索引模型根据 Issue 内容生成。
描述
Workaround (26.10 proxy and direct gRPC in 26.08+). The server runs jobs by scanning slots from slot 0, not in arrival order. A client that submits again as soon as its job finishes can take the lowest free slot and run ahead of jobs already waiting. Those waiting jobs can stay queued while other clients complete many times.
Keep at most one job in flight per worker. Use a single submitter, or a shared lock or FIFO in your
application, and submit the next job only after the current result is retrieved. With one worker,
extra jobs sitting in the server queue do not add throughput.
A one-shot batch of at most 100 jobs is fine if nothing else is submitted until that batch finishes
. The server rejects anything beyond 100 in flight with Job queue full (HTTP 500 through the proxy,
RESOURCE_EXHAUSTED on gRPC).
The legacy REST server is unaffected: it dispatches from a FIFO.
- 主要语言
- Cuda
- 星标
- 1.1k
- 派生
- 255
- 平均合并
- 1 天 22 小时
- 30 天内合并 PR
- 102
环境准备
- 没有 Dockerfile 或 Docker Compose 文件
- 有 Pull Request 模板
- 阅读贡献指南
从这里开始
- 先读完整个 Issue，再读项目的贡献指南。
- 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
- Fork 仓库，在一个分支上完成修改。
- 提交 Pull Request，并在描述里引用这个 Issue 编号。
NVIDIA/cuopt 的其他 Issue
-
[BUG] Constraint validation reports CSR offset count as the number of rows可能已有人在做 @0z5a 于 3 天前认领。 未关闭
难度 2/5 1-3 小时 新手友好度 78/100
维护者通常 1 天内回复
-
ci: pr-test-summary job shows red when the GitHub API returns persistent 5xx errors可能已有人在做 @0z5a 于 3 天前认领。 未关闭
难度 2/5 1-3 小时 新手友好度 72/100
维护者通常 1 天内回复
-
难度 1/5 1 小时以内 新手友好度 82/100
维护者通常 1 天内回复
-
bug mip
难度 4/5 1-2 天 新手友好度 53/100
维护者通常 1 天内回复
-
[BUG] Dataset downloader reports success and replaces data after a failed download可能已有人在做 @0z5a 于 3 天前认领。 未关闭
难度 3/5 1-2 天 新手友好度 75/100
维护者通常 1 天内回复
相似的 Issue
-
难度 2/5 1-3 小时 新手友好度 73/100
维护者通常 4 天内回复
-
bug
难度 2/5 1-3 小时 新手友好度 83/100
-
难度 2/5 1-3 小时 新手友好度 84/100
NVIDIA/auto-ontology#463 ·
维护者通常 1 天内回复
-
难度 2/5 1-3 小时 新手友好度 82/100
RustCrypto/utils#1597 ·
维护者通常 1 天内回复
-
/shutdown/ready can fail to return an HTTP response when readiness takes longer than the server write timeout可能已有人在做 @floriankoch 今天认领。 未关闭triage
难度 2/5 1-3 小时 新手友好度 76/100
envoyproxy/gateway#10562 ·
维护者通常 1 天内回复