lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
Open Source and information security mailing list archives
| ||
|
Date: Tue, 2 Jun 2020 12:03:52 -0300 From: Arnaldo Carvalho de Melo <acme@...nel.org> To: Jiri Olsa <jolsa@...hat.com> Cc: Ian Rogers <irogers@...gle.com>, Jiri Olsa <jolsa@...nel.org>, Jin Yao <yao.jin@...ux.intel.com>, lkml <linux-kernel@...r.kernel.org>, Ingo Molnar <mingo@...nel.org>, Namhyung Kim <namhyung@...nel.org>, Alexander Shishkin <alexander.shishkin@...ux.intel.com>, Peter Zijlstra <a.p.zijlstra@...llo.nl>, Michael Petlan <mpetlan@...hat.com>, Stephane Eranian <eranian@...gle.com>, Andi Kleen <ak@...ux.intel.com> Subject: Re: [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@...enth ~]# 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@...enth ~]# > > > > 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@...enth ~]# 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@...enth ~]# > > > > 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@...enth ~]# 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@...enth ~]# Humm, in the presence of at least one group, any ungrouped events would have to be also separated, i.e.: [root@...enth ~]# 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@...enth ~]# wdyt? > > Also, this needs improvement: > > [root@...enth ~]# 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
Powered by blists - more mailing lists