Em Mon, Apr 25, 2016 at 05:49:38PM -0700, Brendan Gregg escreveu: > On Mon, Apr 25, 2016 at 5:47 PM, Arnaldo Carvalho de Melo > <[email protected]> wrote: > > Em Mon, Apr 25, 2016 at 05:44:00PM -0700, Alexei Starovoitov escreveu: > >> On Mon, Apr 25, 2016 at 09:29:28PM -0300, Arnaldo Carvalho de Melo wrote: > >> > Because we only allocate the callchain percpu data structures when > >> > there > >> > is a user, which allows for changing the max easily, its just a > >> > matter > >> > of having no callchain users at that point. > >> > > >> > Reported-and-Tested-by: Brendan Gregg <[email protected]> > >> > Acked-by: Alexei Starovoitov <[email protected]> > >> > >> yep :) > >> hopefully Brendan can give it another spin. > > > > Agreed, and I'm calling it a day anyway, Brendan, please consider > > retesting, thanks, > Will do, thanks! > Brendan
So, for completeness, further testing it to see how far it goes on a 8GB machine I got: [root@emilia ~]# echo 131100 > /proc/sys/kernel/perf_event_max_stack [root@emilia ~]# perf record -g ls Error: The sys_perf_event_open() syscall returned with 12 (Cannot allocate memory) for event (cycles). /bin/dmesg may provide additional information. No CONFIG_PERF_EVENTS=y kernel support configured? [root@emilia ~]# [root@emilia ~]# echo 131000 > /proc/sys/kernel/perf_event_max_stack [root@emilia ~]# perf record -g usleep [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data (9 samples) ] [root@emilia ~]# ls -la perf.data -rw-------. 1 root root 15736 Apr 26 13:33 perf.data [root@emilia ~]# - Arnaldo
