lkml.org 
[lkml]   [2020]   [Jun]   [2]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCHv3] perf stat: Ensure group is defined on top of the same cpu mask
Em Tue, Jun 02, 2020 at 04:05:08PM +0200, Jiri Olsa escreveu:
> On Tue, Jun 02, 2020 at 10:42:56AM -0300, Arnaldo Carvalho de Melo wrote:
> > Em Tue, Jun 02, 2020 at 12:17:36PM +0200, Jiri Olsa escreveu:
> > > Jin Yao reported the issue (and posted first versions of this change)
> > > with groups being defined over events with different cpu mask.
> >
> > > This causes assert aborts in get_group_fd, like:
> >
> > > # perf stat -M "C2_Pkg_Residency" -a -- sleep 1
> > > perf: util/evsel.c:1464: get_group_fd: Assertion `!(fd == -1)' failed.
> > > Aborted
> >
> > > All the events in the group have to be defined over the same
> > > cpus so the group_fd can be found for every leader/member pair.
> >
> > > Adding check to ensure this condition is met and removing the
> > > group (with warning) if we detect mixed cpus, like:
> >
> > > $ sudo perf stat -e '{power/energy-cores/,cycles},{instructions,power/energy-cores/}'
> > > WARNING: event cpu maps do not match, disabling group:
> > > anon group { power/energy-cores/, cycles }
> > > anon group { instructions, power/energy-cores/ }
> >
> > So it doesn't disable the 'group', it disables the 'grouping' of those
> > events, right? I.e. reading the WARNING, I thought that it would count
> > nothing, since it lists both groups as being disabled, but when I tested
> > I noticed that:
> >
> > [root@seventh ~]# perf stat -e '{power/energy-cores/,cycles},{instructions,power/energy-cores/}'
> > WARNING: grouped events cpus do not match, disabling group:
> > anon group { power/energy-cores/, cycles }
> > anon group { instructions, power/energy-cores/ }
> > ^C
> > Performance counter stats for 'system wide':
> >
> > 12.62 Joules power/energy-cores/
> > 106,920,637 cycles
> > 80,228,899 instructions # 0.75 insn per cycle
> > 12.62 Joules power/energy-cores/
> >
> > 14.514476987 seconds time elapsed
> >
> >
> > [root@seventh ~]#
> >
> > I.e. it counted the events, ungrouped, or am I missing something?
>
> right, it disables 'grouping', events are scheduled/counted individualy

Ok, I applied this already, we can fix this in the next cycle.

> this way we will not hit the issue when looking for group_fd FD
> and there's not any, because of different cpu maps

> > If I do:

> > [root@seventh ~]# perf stat -e '{power/energy-cores/,power/energy-ram/},{instructions,cycles}' -a sleep 2

> > Performance counter stats for 'system wide':

> > 1.73 Joules power/energy-cores/
> > 0.92 Joules power/energy-ram/
> > 12,191,658 instructions # 0.67 insn per cycles/
> > 18,275,233 cycles

> > 2.001272492 seconds time elapsed

> > [root@seventh ~]#
> >
> > It works, grouped. One observation, shouldn't we somehow show in the
> > output that the first two were indeed grouped, ditto for the second two?

> yea, we don't display groups in output.. also there's no number
> for the group, it's still separate events numbers in output
> grouping is only used when creating events

perhaps if we just add a blank line to separate groups? I.e. the above
would be:

[root@seventh ~]# perf stat -e '{power/energy-cores/,power/energy-ram/},{instructions,cycles}' -a sleep 2

Performance counter stats for 'system wide':

1.73 Joules power/energy-cores/
0.92 Joules power/energy-ram/

12,191,658 instructions # 0.67 insn per cycle
18,275,233 cycles

2.001272492 seconds time elapsed

[root@seventh ~]#

Humm, in the presence of at least one group, any ungrouped events would
have to be also separated, i.e.:

[root@seventh ~]# perf stat -e '{power/energy-cores/,power/energy-ram/},instructions,cycles' -a sleep 2

Performance counter stats for 'system wide':

1.73 Joules power/energy-cores/
0.92 Joules power/energy-ram/

12,191,658 instructions # 0.67 insn per cycle

18,275,233 cycles

2.001272492 seconds time elapsed

[root@seventh ~]#

wdyt?

> > Also, this needs improvement:

> > [root@seventh ~]# perf stat -e '{power/energy-cores/,power/energy-ram/},{instructions,cycles}' sleep 2
> > Error:
> > The sys_perf_event_open() syscall returned with 22 (Invalid argument) for event (power/energy-cores/).
> > /bin/dmesg | grep -i perf may provide additional information.

> yes, power events don't work with events without cpu being defined,
> which is what we do for 'workload' session.. we should either check
> for that and display some sensible error for power events

> or perhaps check if we could monitor like perf record does with creating
> events for task and every cpu in the system

- Arnaldo

\
 
 \ /
  Last update: 2020-06-02 17:05    [W:0.058 / U:0.540 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site