linux.git/tools/perf/util/evlist.c, branch v5.5

perf stat: Use affinity for enabling/disabling events

2019-11-29T15:20:45+00:00

Restructure event enabling/disabling to use affinity, which
minimizes the number of IPIs needed.

Before on a large test case with 94 CPUs:

  % time     seconds  usecs/call     calls    errors syscall
  ------ ----------- ----------- --------- --------- ----------------
   54.65    1.899986          22     84812       660 ioctl

after:

   39.21    0.930451          10     84796       644 ioctl

Signed-off-by: Andi Kleen 
Acked-by: Jiri Olsa 
Link: http://lore.kernel.org/lkml/20191121001522.180827-13-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo

perf stat: Use affinity for opening events

2019-11-29T15:20:45+00:00

Restructure the event opening in perf stat to cycle through the events
by CPU after setting affinity to that CPU.

This eliminates IPI overhead in the perf API.

We have to loop through the CPU in the outter builtin-stat code instead
of leaving that to low level functions.

It has to change the weak group fallback strategy slightly.  Since we
cannot easily undo the opens for other CPUs move the weak group retry to
a separate loop.

Before with a large test case with 94 CPUs:

  % time     seconds  usecs/call     calls    errors syscall
  ------ ----------- ----------- --------- --------- ----------------
   42.75    4.050910          67     60046       110 perf_event_open

After:

   26.86    0.944396          16     58069       110 perf_event_open

(the number changes slightly because the weak group retries
work differently and the test case relies on weak groups)

Committer notes:

Added one of the hunks in a patch provided by Andi after I noticed that
the "event times" 'perf test' entry was segfaulting.

Signed-off-by: Andi Kleen 
Acked-by: Jiri Olsa 
Link: http://lore.kernel.org/lkml/20191121001522.180827-10-andi@firstfloor.org
Link: http://lore.kernel.org/lkml/20191127232657.GL84886@tassilo.jf.intel.com # Fix
Signed-off-by: Arnaldo Carvalho de Melo

perf stat: Use affinity for closing file descriptors

2019-11-29T15:20:45+00:00

Closing a perf fd can also trigger an IPI to the target CPU.

Use the same affinity technique as we use for reading/enabling events to
closing to optimize the CPU transitions.

Before on a large test case with 94 CPUs:

  % time     seconds  usecs/call     calls    errors syscall
  ------ ----------- ----------- --------- --------- ----------------
   32.56    3.085463          50     61483           close

  After:

   10.54    0.735704          11     61485           close

Signed-off-by: Andi Kleen 
Acked-by: Jiri Olsa 
Link: http://lore.kernel.org/lkml/20191121001522.180827-8-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo

perf evsel: Add iterator to iterate over events ordered by CPU

2019-11-29T15:20:45+00:00

Add some common code that is needed to iterate over all events
in CPU order. Used in followon patches

Signed-off-by: Andi Kleen 
Acked-by: Jiri Olsa 
Link: http://lore.kernel.org/lkml/20191121001522.180827-6-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo

libperf: Move mask setup to perf_evlist__mmap_ops()

2019-10-19T18:35:01+00:00

Move the mask setup to perf_evlist__mmap_ops(), because it's the same on
both perf and libperf path.

Signed-off-by: Jiri Olsa 
Cc: Alexander Shishkin 
Cc: Alexey Budankov 
Cc: Andi Kleen 
Cc: Jin Yao 
Cc: Michael Petlan 
Cc: Namhyung Kim 
Cc: Peter Zijlstra 
Cc: Stephane Eranian 
Link: http://lore.kernel.org/lkml/20191017105918.20873-4-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo

libperf: Move mmap allocation to perf_evlist__mmap_ops::get

2019-10-19T18:35:01+00:00

Move allocation of the mmap array into perf_evlist__mmap_ops::get, to
centralize the mmap allocation.

Also move nr_mmap setup to perf_evlist__mmap_ops so it's centralized and
shared by both perf and libperf mmap code.

Signed-off-by: Jiri Olsa 
Cc: Alexander Shishkin 
Cc: Alexey Budankov 
Cc: Andi Kleen 
Cc: Jin Yao 
Cc: Michael Petlan 
Cc: Namhyung Kim 
Cc: Peter Zijlstra 
Cc: Stephane Eranian 
Link: http://lore.kernel.org/lkml/20191017105918.20873-3-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo

libperf: Introduce perf_evlist__for_each_mmap()

2019-10-19T18:35:01+00:00

Add the perf_evlist__for_each_mmap() function and export it in the
perf/evlist.h header, so that the user can iterate through 'struct
perf_mmap' objects.

Add a internal perf_mmap__link() function to do the actual linking.

Signed-off-by: Jiri Olsa 
Cc: Alexander Shishkin 
Cc: Alexey Budankov 
Cc: Andi Kleen 
Cc: Jin Yao 
Cc: Michael Petlan 
Cc: Namhyung Kim 
Cc: Peter Zijlstra 
Cc: Stephane Eranian 
Link: http://lore.kernel.org/lkml/20191017105918.20873-2-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo

perf string: Export asprintf__tp_filter_pids()

2019-10-15T16:03:57+00:00

Will be used directly in 'perf trace' for setting up the command line
argv array to pass to cmd_record, as this was how 'perf trace record'
was implemented, following the model used in 'perf kvm record', 'perf
sched record', etc.

Cc: Adrian Hunter 
Cc: David Ahern 
Cc: Jiri Olsa 
Cc: Luis Cláudio Gonçalves 
Cc: Namhyung Kim 
Link: https://lkml.kernel.org/n/tip-w3cuwjs63lxf5zpryy3145uv@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo

perf evlist: Fix fix for freed id arrays

2019-10-15T11:36:22+00:00

In the earlier fix for the memory overrun of id arrays I managed to typo
the wrong event in the fix.

Of course we need to close the current event in the loop, not the
original failing event.

The same test case as in the original patch still passes.

Fixes: 7834fa948beb ("perf evlist: Fix access of freed id arrays")
Signed-off-by: Andi Kleen 
Cc: Jiri Olsa 
Link: http://lore.kernel.org/lkml/20191011182140.8353-2-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo

libperf: Adopt perf_evlist__filter_pollfd() from tools/perf

2019-10-10T15:58:45+00:00

Introduce the perf_evlist__filter_pollfd function and export it in the
perf/evlist.h header, so that libperf users can check if the descriptor
is still alive.

Signed-off-by: Jiri Olsa 
Cc: Alexander Shishkin 
Cc: Michael Petlan 
Cc: Namhyung Kim 
Cc: Peter Zijlstra 
Link: http://lore.kernel.org/lkml/20191007125344.14268-27-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo