Skip to content

L
linux
Switch branch/tag
  1. 06 Jun, 2018 7 commits
    • Jiri Olsa's avatar
      perf tools: Fix pmu events parsing rule · ceac7b79
      Jiri Olsa authored 
      Currently all the event parsing fails end up
in the event_pmu rule, and display misleading
help like:

  $ perf stat -e inst kill
  event syntax error: 'inst'
                       \___ Cannot find PMU `inst'. Missing kernel support?
  ...

The reason is that the event_pmu is too strong
and match also single string. Changing it to
force the '/' separators to be part of the rule,
and getting the proper error now:

  $ perf stat -e inst kill
  event syntax error: 'inst'
                       \___ parser error
  Run 'perf list' for a list of valid events
  ...
Suggested-by: default avatarAdrian Hunter <adrian.hunter@intel.com>
Signed-off-by: default avatarJiri Olsa <jolsa@kernel.org>
Tested-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180605121416.31645-1-jolsa@kernel.orgSigned-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      ceac7b79
    • Jiri Olsa's avatar
      perf stat: Display user and system time · 0ce2da14
      Jiri Olsa authored 
      Adding the support to read rusage data once the workload is finished and
display the system/user time values:

  $ perf stat --null perf bench sched pipe
  ...

   Performance counter stats for 'perf bench sched pipe':

       5.342599256 seconds time elapsed

       2.544434000 seconds user
       4.549691000 seconds sys

It works only in non -r mode and only for workload target.

So as of now, for workload targets, we display 3 types of timings. The
time we meassure in perf stat from enable to disable+period:

       5.342599256 seconds time elapsed

The time spent in user and system lands, displayed only for workload
session/target:

       2.544434000 seconds user
       4.549691000 seconds sys

Those times are the very same displayed by 'time' tool.  They are
returned by wait4 call via the getrusage struct interface.

Committer notes:

Had to rename some variables to avoid this on older systems such as
centos:6:

  builtin-stat.c: In function 'print_footer':
  builtin-stat.c:1831: warning: declaration of 'stime' shadows a global declaration
  /usr/include/time.h:297: warning: shadowed declaration is here

Committer testing:

  # perf stat --null time perf bench sched pipe
  # Running 'sched/pipe' benchmark:
  # Executed 1000000 pipe operations between two processes

       Total time: 5.526 [sec]

         5.526534 usecs/op
           180945 ops/sec
  1.00user 6.25system 0:05.52elapsed 131%CPU (0avgtext+0avgdata 8056maxresident)k
  0inputs+0outputs (0major+606minor)pagefaults 0swaps

   Performance counter stats for 'time perf bench sched pipe':

         5.530978744 seconds time elapsed

         1.004037000 seconds user
         6.259937000 seconds sys

  #
Suggested-by: default avatarIngo Molnar <mingo@kernel.org>
Signed-off-by: default avatarJiri Olsa <jolsa@kernel.org>
Tested-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180605121313.31337-1-jolsa@kernel.orgSigned-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      0ce2da14
    • Alexey Budankov's avatar
      perf record: Enable arbitrary event names thru name= modifier · f92da712
      Alexey Budankov authored 
      Enable complex event names containing [.:=,] symbols to be encoded into Perf
trace using name= modifier e.g. like this:

  perf record -e cpu/name=\'OFFCORE_RESPONSE:request=DEMAND_RFO:response=L3_HIT.SNOOP_HITM\',\
		  period=0x3567e0,event=0x3c,cmask=0x1/Duk ./futex

Below is how it looks like in the report output. Please note explicit escaped
quoting at cmdline string in the header so that thestring can be directly reused
for another collection in shell:

perf report --header

  # ========
  ...
  # cmdline : /root/abudanko/kernel/tip/tools/perf/perf record -v -e cpu/name=\'OFFCORE_RESPONSE:request=DEMAND_RFO:response=L3_HIT.SNOOP_HITM\',period=0x3567e0,event=0x3c,cmask=0x1/Duk ./futex
  # event : name = OFFCORE_RESPONSE:request=DEMAND_RFO:response=L3_HIT.SNOOP_HITM, , type = 4, size = 112, config = 0x100003c, { sample_period, sample_freq } = 3500000, sample_type = IP|TID|TIME, disabled = 1, inh
  ...
  # ========
  #
  #
  # Total Lost Samples: 0
  #
  # Samples: 24K of event 'OFFCORE_RESPONSE:request=DEMAND_RFO:response=L3_HIT.SNOOP_HITM'
  # Event count (approx.): 86492000000
  #
  # Overhead  Command  Shared Object     Symbol
  # ........  .......  ................  ..............................................
  #
      14.75%  futex    [kernel.vmlinux]  [k] __entry_trampoline_start
...

  perf stat -e cpu/name=\'CPU_CLK_UNHALTED.THREAD:cmask=0x1\',period=0x3567e0,event=0x3c,cmask=0x1/Duk ./futex

  10000000 process context switches in 16678890291ns (1667.9ns/ctxsw)

   Performance counter stats for './futex':

      88,095,770,571      CPU_CLK_UNHALTED.THREAD:cmask=0x1

        16.679542407 seconds time elapsed
Signed-off-by: default avatarAlexey Budankov <alexey.budankov@linux.intel.com>
Acked-by: default avatarAndi Kleen <ak@linux.intel.com>
Acked-by: default avatarJiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/c194b060-761d-0d50-3b21-bb4ed680002d@linux.intel.comSigned-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      f92da712
    • Adrian Hunter's avatar
      perf tools: Fix symbol and object code resolution for vdso32 and vdsox32 · aef4feac
      Adrian Hunter authored 
      Fix __kmod_path__parse() so that perf tools does not treat vdso32 and
vdsox32 as kernel modules and fail to find the object.
Signed-off-by: default avatarAdrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: stable@vger.kernel.org
Fixes: 1f121b03 ("perf tools: Deal with kernel module names in '[]' correctly")
Link: http://lkml.kernel.org/r/1528117014-30032-3-git-send-email-adrian.hunter@intel.comSigned-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      aef4feac
    • Adrian Hunter's avatar
      perf tests kmod-path: Add tests for vdso32 and vdsox32 · dcaeae4e
      Adrian Hunter authored 
      Add tests for vdso32 and vdsox32. This will cause the overall test to
fail because __kmod_path__parse() does not handle vdso32 or vdsox32.

Fixes: 1f121b03 ("perf tools: Deal with kernel module names in '[]' correctly")
Signed-off-by: default avatarAdrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1528117014-30032-2-git-send-email-adrian.hunter@intel.comSigned-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      dcaeae4e
    • Arnaldo Carvalho de Melo's avatar
      perf hists: Check if a hist_entry has callchains before using them · fabd37b8
      Arnaldo Carvalho de Melo authored 
      So far if we use 'perf record -g' this will make
symbol_conf.use_callchain 'true' and logic will assume that all events
have callchains enabled, but ever since we added the possibility of
setting up callchains for some events (e.g.: -e
cycles/call-graph=dwarf/) while not for others, we limit usage scenarios
by looking at that symbol_conf.use_callchain global boolean, we better
look at each event attributes.

On the road to that we need to look if a hist_entry has callchains, that
is, to go from hist_entry->hists to the evsel that contains it, to then
look at evsel->sample_type for PERF_SAMPLE_CALLCHAIN.

The next step is to add a symbol_conf.ignore_callchains global, to use
in the places where what we really want to know is if callchains should
be ignored, even if present.

Then -g will mean just to select a callchain mode to be applied to all
events not explicitely setting some other callchain mode, i.e. a default
callchain mode, and --no-call-graph will set
symbol_conf.ignore_callchains with that clear intention.

That too will at some point become a per evsel thing, that tools can set
for all or just a few of its evsels.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-0sas5cm4dsw2obn75g7ruz69@git.kernel.orgSigned-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      fabd37b8
    • Arnaldo Carvalho de Melo's avatar
      perf hists: Introduce hist_entry__has_callchain() method · 0b5d6ece
      Arnaldo Carvalho de Melo authored 
      We'll use this helper more frequently when reworking
symbol_conf.use_callchain logic, where knowing if a hist_entry has
callchains is the important bit, so make going from hist_entry to hists
to evsel easier, compact.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-p6gioxkzpkpz71dtt4wcs36o@git.kernel.orgSigned-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      0b5d6ece
  3. 05 Jun, 2018 3 commits
  5. 04 Jun, 2018 28 commits
  7. 03 Jun, 2018 2 commits
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7