Brendan Gregg

Announcing my next book: Systems Performance: Enterprise and the Cloud, 2nd Edition (2020) brendangregg.com/blog/2020-07-1…

Huge news for Doctor Who fans: DMP 1 & 3 found! bbc.com/news/articles/…

excited to work with Brendan, have been a big fan of his work for many years!

New blog post: Why I joined OpenAI brendangregg.com/blog/2026-02-0…

New post: Leaving Intel brendangregg.com/blog/2025-12-0…

new post: When to Hire a Computer Performance Engineering Team (2025) part 1 of 2 brendangregg.com/blog/2025-08-0…

Had a great time at #srenext Tokyo

@cperciva I guess I'm lucky; I've also been sick & WFH-ok many times, 10 in 9 years is just "days off sick."

@brendangregg You've had 10 sick days in the past 9 years? Let me guess, you don't have a toddler...

new blog post: 3 Years of Extremely Remote Work brendangregg.com/blog/2025-05-2…

New blog post: Doom GPU Flame Graphs, a fun demo of AI/GPU Flame Graphs and FlameScope, now open source brendangregg.com/blog/2025-05-0…

My website is back online brendangregg.com after migrating to a different provider (and https works again)

My website is online as http at brendangregg.com, but I just broke the https links, sorry. If you delete the "s" then the links should still work.

AI Flame Graphs: Showing what's actually running on the HW and how we got there. Uses Intel EU stall profiling and eBPF. brendangregg.com/blog/2024-10-2…

WSJ covering the eBPF "super revolutionary technology" wsj.com/articles/how-t…

@msherman1970 I mean that it might seem that we've accomplished nothing if we move a crash from one body of software (a security agent) to another (eBPF code). It's a point people make as well: "oh, but eBPF has had panics too." Yes it has, but it's still an overall improvement.

@brendangregg What do you mean by “substituting a vendor’s bug for its own” in this sentence, “This doesn't mean that eBPF has solved nothing, substituting a vendor's bug for its own” ? thanks!

New post: No More Blue Fridays: How eBPF is already being adopted to prevent kernel crashes brendangregg.com/blog/2024-07-2…

@senolcolaks Thanks, I was wondering why it wasn't already on my list then saw it's provided by the systemd package, so maybe I've never had to add it

@brendangregg Once again precious tools. But nowadays everything is in cgroups & containers. I would add systemd-cgtop to the list.

New blog post: Linux crisis tools brendangregg.com/blog/2024-03-2…

@CarlMastrangelo Yes by "perf trace" and the bpf tracers, which use ring buffers. Current strace is dangerous for production use (ok as a last resort) brendangregg.com/blog/2014-05-1…

@brendangregg Is strace already covered by another tool on the list?

@indygreg Some have switched already (golang) others have options. It'd be nice for it to be default, but it's less of a problem than the OS, because (A) profiling becomes obviously broken and developers go hunting for the fix, and (B) easier to add runtime options than OS changes.

@brendangregg Are you aware of any efforts to move programming language packaging ecosystems (Python, Java, etc) to compile with frame pointers by default? My fear is that even if the distros give us frame pointers, GCC/Clang won’t. And language ecosystems will be stuck in the past.

New blog post: The Return of the Frame Pointers (Fedora, Ubuntu) brendangregg.com/blog/2024-03-1…

@iiirogers Your post was super helpful, thanks! #comment-828647" target="_blank" rel="nofollow noopener">pagure.io/fesco/issue/28…

@brendangregg Thanks for the thanks, I don't think I did anything 🙂 It may be interesting to mention the apx extensions and their impact. If we need to recompile for APX could we have some more callee save registers?