Top all-time · #15517
My Octopress Blog
Personal blog · joemario.github.io/blogsystemsprogramming
My Octopress Blog is a personal blog at joemario.github.io about systems and programming. Since 2016, 5 different Hacker News readers have linked it 5 times, most often “C2C – False Sharing Detection in Linux Perf”. The last post was in 2016, but the archive is still widely read.
Too few sampled comments (2) to say how often HN recommends it.?
Why HN links it
Blog on Linux performance analysis, including perf c2c for finding cache-line contention and false sharing. HN commenters link its perf c2c post as background on that tool.
Summarised by Claude from a sample of 2 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Do you run your application in a NUMA environment? Is it multi-threaded? Is it multi-process with shared memory? If so, is your performance impacted …
Most-linked posts?
- C2C – False Sharing Detection in Linux Perf5 people · 5 mentions · first linked 2016-10-22
What Hacker News says?
Another related tool I found interesting: perf c2c This will let us find the false sharing cost (cache contention etc). https://joemario.github.io/blog/2016/09/01/c2c-blog/
Comment linking /blog/2016/09/01/c2c-blog/
on “CPU Utilization is Wrong”Submitted C2C – False Sharing Detection in Linux Perf as a story · 3 points
HN discussionc2c stands for cache-2-cache. perf-c2c allows you to measure cacheline contention - see https://man7.org/linux/man-pages/man1/perf-c2c.1.html and https://joemario.github.io/blog/2016/09/01/c2c-blog/ .
Comment linking /blog/2016/09/01/c2c-blog/
on “A single line of code made a 24-core server slower than a laptop”Submitted C2C – False Sharing Detection Using Linux Perf as a story · 2 points
HN discussionSubmitted C2C – False Sharing Detection in Linux Perf as a story · 2 points
HN discussion