Messages in this thread | | | Date | Sat, 27 Sep 2008 13:18:01 -0400 (EDT) | From | Steven Rostedt <> | Subject | Re: [PATCH v5] Unified trace buffer |
| |
On Sat, 27 Sep 2008, Ingo Molnar wrote: > * Steven Rostedt <rostedt@goodmis.org> wrote: > > > Subject: [RFC PATCH 2/2 v3] ftrace: make work with new ring buffer > > > > Note: This patch is a proof of concept, and breaks a lot of > > functionality of ftrace. > > > > This patch simply makes ftrace work with the developmental ring > > buffer. > > ... to not have known bugs, so that we could try it in tip/ftrace and > make sure it works well in practice? > > it's a ton of changes already, it would be nice to get to some stable > known-working state and do delta patches from that point on, and keep > its 'works well' quality.
OK, the patch that I was using was against Linus's tree. I'll port it over to linux-tip on Monday and get it past the "proof of concept" stage. Actually, the verison I have on my desk works pretty well. The main issues to solve is that some other tracers and the self test stick their noses into the buffering system, which would need to be fixed.
There's also some bugs in the status numbers printed in the latency_trace header. But I have not hit any bugs with the buffering itself.
I'll clean all this up and send out a patch on Monday. My wife is mandating that I do not do anymore work over the weekend ;-)
-- Steve
| |