TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Cachy: Out of tree Linux scheduler improving CPU cache usage

38 点作者 karma_daemon超过 4 年前

3 条评论

rurban超过 4 年前
His previous attempt on the same policy was <a href="https:&#x2F;&#x2F;github.com&#x2F;hamadmarri&#x2F;popcorn" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;hamadmarri&#x2F;popcorn</a><p>This new one looks simpler and a bit better.
gravypod超过 4 年前
It would be interesting to see how this scales with cores&#x2F;threads. Current gen CPUs have ~128 threads per socket and you can find hardware that is quad socket. I&#x27;ve seen some systems with &lt;512 concurrent processes running. In those use cases would this patch have the effect of pinning each process to a single thread (ignoring io&#x2F;other sleep states)? Would the performance benefits of this patch scale super-linearly against thread count?
评论 #24261050 未加载
LinuxBender超过 4 年前
Very nice! I hope this is considered for merge into the kernel as an optional scheduler.