Messages in this thread | | | Date | Fri, 27 Mar 2015 16:07:01 -0700 | Subject | Re: [PATCH] perf, record: Add clockid parameter | From | Stephane Eranian <> |
| |
On Fri, Mar 27, 2015 at 1:15 PM, Arnaldo Carvalho de Melo <acme@redhat.com> wrote: > Em Fri, Mar 27, 2015 at 11:35:25AM -0600, David Ahern escreveu: >> On 3/27/15 11:20 AM, Peter Zijlstra wrote: >> >>This is a new feature which means use_clockid on older kernels will fail. So >> >>need to catch that and throw an error -- perhaps yet another probe function. > >> >How does that work? What do I grep to find an example? I figured if the >> >kernel didn't support the syscall will fail and we'll terminate >> >someplace. > >> Look at __perf_evsel__open(). In this case you probably do not want >> to fallback but tell the user the clock id option is not supported. >> The problem is deciphering the failure is due to the clock id versus >> all the other failure reasons. > > I.e. we're back to the sys_perf_event_open() error reporting suckz rockz > thing, this time with PeterZ trying to find a way to avoid getting back > to that discussion... /me runz... ;-P > Why not have the kernel advertise the perf capabilities (in procfs or sysfs) instead this guessing game with the return values?
| |