At the Southern California Linux Expo earlier this year (SCaLE 11x) I presented a talk on Linux Performance Analysis and Tools. It’s a great conference, and I was happy to be back.
My talk provided an overview of over twenty performance tools, and I described the problems they solve. At the end of the talk, I summarized some methodologies for using these tools, so that you know when to reach for what.
The video is on youtube:
The slides are available on slideshare and as a PDF:
These are also linked on the Joyent blog post about my talk, by Deirdré Straughan who filmed it and then spread the word afterwards.
I’ve used pretty much everything for solving performance issues, including advanced tools like perf, DTrace, and SystemTap, and I was able to explain their role and how they fit together (see slide 16 in particular). It was pretty dense: you can treat this as a 60 minute crash course into Linux performance analysis and tools.
The talk referenced my earlier posts on the USE Method Linux Performance Checklist, and Linux Kernel Flame Graphs.