Messages in this thread | | | Date | Fri, 14 Mar 2014 17:12:06 +0100 | From | Jiri Olsa <> | Subject | Re: [PATCH V2] perf: Speed up thread map generation |
| |
On Fri, Mar 14, 2014 at 10:43:44AM -0400, Don Zickus wrote: > When trying to capture perf data on a system running spejbb2013, > perf hung for about 15 minutes. This is because it took that > long to gather about 10,000 thread maps and process them. > > I don't think a user wants to wait that long. > > Instead, recognize that thread maps are roughly equivalent to > pid maps and just quickly copy those instead. > > To do this, I synthesize 'fork' events, this eventually calls > thread__fork() and copies the maps over. > > The overhead goes from 15 minutes down to about a few seconds. > > Signed-off-by: Don Zickus <dzickus@redhat.com> > -- > V2: based on Jiri's comments, moved malloc up a level > and made sure the memory was freed
Acked-by: Jiri Olsa <jolsa@redhat.com>
thanks, jirka
| |