On Thu, 24 Jan 2008, Daniel Walker wrote: > > On Thu, 2008-01-24 at 15:36 -0500, Steven Rostedt wrote: > > Hi all, > > > > I'm about to gut the RT latency tracer with the version I'm pushing > > upstream. This will be some of the changes: > > > > Do you have all the functionality of the prior tracer ? Specifically the > histogram support .. I can vouch for the fact that it's getting used.. I > would prefer you don't gut the current tracer unless you have the same > level of functionality .. OK, I didn't even know the histogram worked. Which histogram did you use? all both? I'll try to implement it for upstream then, and port that over to -rt. Whenever there's a push to get part of the -rt kernel upstream, we replace what is in RT for what goes mainline. I'm trying hard to keep the same functionality, but the way it works changes a bit so we gain some more functionality while losing a bit of others. One thing is that we always trace all CPUS (except for preempt/irqs off max). Another is that we don't print traces on oops (yet). Although I did scalvage the PREEMPT_TRACE to print that. Let me know if you use all the histograms and I'll see if I can get them in tomorrow. -- Steve - To unsubscribe from this list: send the line "unsubscribe linux-rt-users" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
