Investigation of Machine-specific Frame Latency Issues (PresentData)
维护者通常 2 天内回复
还没有人认领这个 Issue。
评估
- 难度
- 4/5
- 预计耗时
- 3-5 天
- 新手友好度
- 25/100
- Issue 类型
- 缺陷
- 描述清晰度
- 需要澄清
- 活跃度
- 停滞
- 技术栈
- cpp
- 领域
- performance
调研方向
Start by capturing an ETL trace on a misbehaving system while confirming the frame-metric drops, then investigate the PresentData state machinery mentioned in the issue. Compare event sequences and test whether playback reproduces the dynamic query behavior. Done means narrowing down the cause; the issue also identifies automated test cases as a future safeguard.
由索引模型根据 Issue 内容生成。
描述
As first reported in #590, on certain machines we see frequent drops to zero on all frame data metrics in the overlay (telemetry unaffected). This has been tentatively traced back and linked to PresentData. The ETW events themselves come in with low latency, but the frames fail to be completed and output in a timely fashion by the PresentData state machinery.
pmlog.txt
pmlog-mid.txt
pmsvc-log-260305-164320.txt
Possible scenarios:
- Event sequences on some platforms differ in a way that trips up the state tracking
- Expected events were changed or removed
- Drivers or components are emitting essential events very late (seems unlikely)
First steps: capture ETL on misbehaving system concurrent with confirming behavior during capture period. If this can reproduce the dynamic query behavior on playback, it would confirm several theories and narrow down possible causes. Such ETL could then be used for system-agnostic analysis and for automated test cases to guard against such issues in the future.
- 主要语言
- C++
- 星标
- 2.6k
- 派生
- 201
- 平均合并
- 2 天 21 小时
- 30 天内合并 PR
- 16
环境准备
这个项目没有提供开发容器、Dockerfile 或贡献指南,环境需要你自己搭建:先看它的 README,通用步骤见我们的新手贡献指南。
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。
GameTechDev/PresentMon 的其他 Issue
-
难度 2/5 1-3 小时 新手友好度 75/100
GameTechDev/PresentMon#745 ·
维护者通常 2 天内回复
-
难度 1/5 1 小时以内 新手友好度 80/100
GameTechDev/PresentMon#684 · 1 条评论 ·
维护者通常 2 天内回复
-
难度 4/5 3-5 天 新手友好度 45/100
GameTechDev/PresentMon#743 ·
维护者通常 2 天内回复
-
Runtime-generated FSR/AFMF presents may suppress simulation intervals and report 0 Simulation FPS未关闭
难度 4/5 3-5 天 新手友好度 45/100
GameTechDev/PresentMon#742 ·
维护者通常 2 天内回复
-
Reduce nonpaged memory reserved by the PresentMon ETW session at startup可能已有人在做 @markgalvan-intel 于 3 天前认领。 未关闭PresentData
GameTechDev/PresentMon#740 · 已指派 1 人 ·
维护者通常 2 天内回复
查看 GameTechDev/PresentMon 的全部 Issue
相似的 Issue
-
area/build-framework kind/enhancement priority/low
难度 2/5 1-3 小时 新手友好度 77/100
yugabyte/yugabyte-db#38826 ·
维护者通常 1 天内回复
-
bug compositor:other void
难度 2/5 1-3 小时 新手友好度 62/100
noctalia-dev/noctalia#5451 ·
维护者通常 1 天内回复
-
难度 1/5 1 小时以内 新手友好度 91/100
维护者通常 1 天内回复
-
难度 2/5 1-3 小时 新手友好度 64/100
维护者通常 1 天内回复
-
难度 2/5 1-3 小时 新手友好度 69/100
maplibre/maplibre-native#5072 ·
维护者通常 1 天内回复