Yesterday I noted some early performance regressions I’ve found on the Linux 6.19 kernel compared to Linux 6.18 LTS stable. Those initial benchmarks were on an AMD EPYC server. Since then I’ve seen many of the same workloads regressing similarly on an AMD Ryzen Threadripper workstation between Linux 6.18 and Linux 6.19 Git. Given the significant impact and AMD Threadripper processors always helping out to speed-up Linux kernel build times to make for a quicker and more manageable kernel bisecting experience, here is a look at some of the results for the Linux 6.19 performance regressions.
I was able to reproduce similar performance regressions using Linux 6.19 Git on a AMD Ryzen Threadripper PRO 9995WX workstation. The Threadripper PRO 9995WX is my favorite system for fast code compilation / bisecting thanks to its 96 Zen 5 cores boosting up to 5.4GHz and the 384MB L3 cache together making for very fast code compilation especially on large codebases such as the Linux kernel.
Thus with the speed of Threadripper it made the kernel bisecting experience more manageable in being less time consuming. (Although ultimately I am still running such in-depth testing at a loss given the unfortunate state of the web publishing / ad industry these days, rampant ad block use, and less than 0.5% of readers being Phoronix Premium subscribers.)
There are more performance regressions that I am still exploring on Linux 6.19 Git but for this article I decided to go through with the bisecting of the Stress-NG scheduler micro-benchmark and then the Nginx HTTPS web server given the prominence of that real-world workload. So here’s what I’ve found so far.
