lkml.org 
[lkml]   [2011]   [May]   [29]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [GIT PULL 0/5] perf/urgent fixes

* Arnaldo Carvalho de Melo <acme@infradead.org> wrote:

> Em Sat, May 28, 2011 at 11:41:50AM +0200, Ingo Molnar escreveu:
> > The various variations of kptr_restrict now work fine AFAICS - will
> > send the fixes to Linus today.
> >
> > One (very) small issue i noticed, if the user only samples user-space
> > events then i still get the warning:
> >
> > aldebaran:~> perf record -e cycles:upp sleep 1
> > WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted,
> >
> > although perf does not record any kernel samples so kptr_restrict is
> > irrelevant in this case.
>
> I'll have that fixed too, oversight. We really should avoid
> confusing messages, and this one, as you mention, seems just noise
> as I still have to look again how vsyscall symbols get resolved,
> IIRC they need a kernel symtab, but then, if that is the case, the
> message should be changed accordingly.

Btw., if you touch that code, would you be interested in adding a
--user-events kind of option which would have the implicit effect of
adding :u to every event that is listed (or implied)? (and a
--kernel-events counterpart, for :k)

The reason is that right now there's no easy way to run say 'perf
stat -ddd' but measure userspace events only.

[ perf record --repeat would be nice as well :-) And a pony! ]

Thanks,

Ingo


\
 
 \ /
  Last update: 2011-05-29 16:33    [W:0.053 / U:0.472 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site