[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <YW7gsEDXBw1jk65o@kernel.org>
Date: Tue, 19 Oct 2021 12:13:52 -0300
From: Arnaldo Carvalho de Melo <acme@...nel.org>
To: Ian Rogers <irogers@...gle.com>
Cc: Andi Kleen <ak@...ux.intel.com>, Jiri Olsa <jolsa@...hat.com>,
Jin Yao <yao.jin@...ux.intel.com>,
Namhyung Kim <namhyung@...nel.org>,
John Garry <john.garry@...wei.com>,
Kajol Jain <kjain@...ux.ibm.com>,
"Paul A . Clarke" <pc@...ibm.com>,
Riccardo Mancini <rickyman7@...il.com>,
Kan Liang <kan.liang@...ux.intel.com>,
Peter Zijlstra <peterz@...radead.org>,
Ingo Molnar <mingo@...hat.com>,
Mark Rutland <mark.rutland@....com>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
Kees Cook <keescook@...omium.org>,
Sami Tolvanen <samitolvanen@...gle.com>,
Nick Desaulniers <ndesaulniers@...gle.com>,
Andrew Morton <akpm@...ux-foundation.org>,
Jacob Keller <jacob.e.keller@...el.com>,
Zhen Lei <thunder.leizhen@...wei.com>,
ToastC <mrtoastcheng@...il.com>,
Joakim Zhang <qiangqing.zhang@....com>,
Felix Fietkau <nbd@....name>,
Jiapeng Chong <jiapeng.chong@...ux.alibaba.com>,
Song Liu <songliubraving@...com>, Fabian Hemmer <copy@...y.sh>,
Alexander Antonov <alexander.antonov@...ux.intel.com>,
Nicholas Fraser <nfraser@...eweavers.com>,
Adrian Hunter <adrian.hunter@...el.com>,
Denys Zagorui <dzagorui@...co.com>,
Wan Jiabing <wanjiabing@...o.com>,
Thomas Richter <tmricht@...ux.ibm.com>,
Sumanth Korikkar <sumanthk@...ux.ibm.com>,
Heiko Carstens <hca@...ux.ibm.com>,
Changbin Du <changbin.du@...el.com>,
linux-kernel@...r.kernel.org, linux-perf-users@...r.kernel.org,
Andrew Kilroy <andrew.kilroy@....com>,
Stephane Eranian <eranian@...gle.com>
Subject: Re: [PATCH v2 21/21] perf metric: Allow modifiers on metrics.
Em Tue, Oct 19, 2021 at 12:06:17PM -0300, Arnaldo Carvalho de Melo escreveu:
> Em Fri, Oct 15, 2021 at 10:21:32AM -0700, Ian Rogers escreveu:
> > By allowing modifiers on metrics we can, for example, gather the
> > same metric for kernel and user mode. On a SkylakeX with
> > TopDownL1 this gives:
> >
> > $ perf stat -M TopDownL1:u,TopDownL1:k -a sleep 2
> >
> > Performance counter stats for 'system wide':
>
> Hi Ian, can you please take a look on this? this is on my perf/core
> branch.
I processed the first version of this series, reviewed by Andi, can you
please submit the diff from one to the other?
- Arnaldo
> - Arnaldo
>
> [root@...e ~]# perf test -vv "for cgroups"
> 70: Event expansion for cgroups :
> --- start ---
> test child forked, pid 992568
> Using CPUID AuthenticAMD-25-21-0
> libpfm was not enabled
> metric expr 1 / IPC for CPI
> parsing metric: 1 / IPC
> metric expr instructions / cycles for IPC
> parsing metric: instructions / cycles
> found event instructions
> found event cycles
> Parsing metric events '{instructions/metric-id=instructions/,cycles/metric-id=cycles/}:W'
> copying metric event for cgroup 'A': instructions (idx=0)
> copying metric event for cgroup 'B': instructions (idx=0)
> copying metric event for cgroup 'C': instructions (idx=0)
> free(): double free detected in tcache 2
> test child interrupted
> ---- end ----
> Event expansion for cgroups: FAILED!
> [root@...e ~]#
>
> ⬢[acme@...lbox perf]$ git bisect bad
> c067335fcbfc67c36663dabdb9ccaa96badf9359 is the first bad commit
> commit c067335fcbfc67c36663dabdb9ccaa96badf9359
> Author: Ian Rogers <irogers@...gle.com>
> Date: Thu Oct 7 09:56:47 2021 -0700
>
> perf metric: Allow modifiers on metrics.
>
> By allowing modifiers on metrics we can, for example, gather the
> same metric for kernel and user mode. On a SkylakeX with
> TopDownL1 this gives:
>
--
- Arnaldo
Powered by blists - more mailing lists