Skip to content

R
raspberrypi-kernel

openeuler / raspberrypi-kernel

通知 13
Star 1
Fork 0
R
raspberrypi-kernel
切换分支/标签
  1. 01 4月, 2013 1 次提交
    • A
      perf tools: Add support for weight v7 (modified) · 05484298
      由 Andi Kleen 提交于 
      perf record has a new option -W that enables weightened sampling.

Add sorting support in top/report for the average weight per sample and the
total weight sum. This allows to both compare relative cost per event
and the total cost over the measurement period.

Add the necessary glue to perf report, record and the library.

v2: Merge with new hist refactoring.
v3: Fix manpage. Remove value check.
Rename global_weight to weight and weight to local_weight.
v4: Readd sort keys to manpage
v5: Move weight to end
v6: Move weight to template
v7: Rename weight key.

Original patch from Andi modified by Stephane Eranian <eranian@google.com>
to include ONLY the weight supporting code and apply to pristine 3.8.0-rc4.
Signed-off-by: NAndi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1359040242-8269-6-git-send-email-eranian@google.com
[ committer note: changed to cope with fc5871ed and the hists_link perf test entry ]
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      05484298
  3. 07 2月, 2013 1 次提交
  5. 25 1月, 2013 3 次提交
  7. 09 12月, 2012 4 次提交
  9. 09 11月, 2012 3 次提交
    • A
      perf diff: Use hists__link when not pairing just with baseline · bfaef4b4
      由 Arnaldo Carvalho de Melo 提交于 
      Previously there were blind spots because we were not looking at symbols
that didn't ocurred in the latest run:

  # perf record usleep 1
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.018 MB perf.data (~801 samples) ]
  # perf record usleep 1
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.018 MB perf.data (~801 samples) ]

Before:

  # perf diff
  # Event 'cycles'
  #
  # Baseline    Delta      Shared Object                         Symbol
  # ........  .......  .................  .............................
  #
              +10.38%  [kernel.kallsyms]  [k] get_empty_filp
               +9.51%  [kernel.kallsyms]  [k] update_sd_lb_stats
               +9.41%  libpopt.so.0.0.0   [.] _init
               +9.29%  [kernel.kallsyms]  [k] vma_interval_tree_insert
       9.05%   +0.12%  [kernel.kallsyms]  [k] do_sys_open
               +9.14%  [kernel.kallsyms]  [k] kfree
               +8.98%  [kernel.kallsyms]  [k] free_pages_and_swap_cache
               +8.78%  [kernel.kallsyms]  [k] unmap_page_range
       9.36%   -0.90%  [kernel.kallsyms]  [k] zap_pte_range
       7.60%   +0.09%  [kernel.kallsyms]  [k] find_next_bit
               +4.37%  [kernel.kallsyms]  [k] place_entity
               +3.38%  [kernel.kallsyms]  [k] __do_page_fault
               +0.80%  [kernel.kallsyms]  [k] native_apic_mem_write
       0.21%   +0.43%  [kernel.kallsyms]  [k] native_write_msr_safe
  #

So 9.05 + 9.36 + 7.60 + 0.21 != 100%

Now using the recently introduced hists__link we can see the whole
picture:

  # perf diff
  # Event 'cycles'
  #
  # Baseline    Delta      Shared Object                         Symbol
  # ........  .......  .................  .............................
  #
       8.44%   -8.44%  [kernel.kallsyms]  [k] _raw_spin_lock
       9.05%   -9.05%  [kernel.kallsyms]  [k] sha_transform
      10.55%  -10.55%  [kernel.kallsyms]  [k] __d_lookup_rcu
              +10.38%  [kernel.kallsyms]  [k] get_empty_filp
      17.70%  -17.70%  [kernel.kallsyms]  [k] kmem_cache_free
               +9.51%  [kernel.kallsyms]  [k] update_sd_lb_stats
               +9.41%  libpopt.so.0.0.0   [.] _init
               +9.29%  [kernel.kallsyms]  [k] vma_interval_tree_insert
       9.05%   +0.12%  [kernel.kallsyms]  [k] do_sys_open
               +9.14%  [kernel.kallsyms]  [k] kfree
               +8.98%  [kernel.kallsyms]  [k] free_pages_and_swap_cache
               +8.78%  [kernel.kallsyms]  [k] unmap_page_range
       9.36%   -0.90%  [kernel.kallsyms]  [k] zap_pte_range
       7.60%   +0.09%  [kernel.kallsyms]  [k] find_next_bit
               +4.37%  [kernel.kallsyms]  [k] place_entity
               +3.38%  [kernel.kallsyms]  [k] __do_page_fault
       4.01%   -4.01%  [kernel.kallsyms]  [k] handle_pte_fault
       9.27%   -9.27%  [kernel.kallsyms]  [k] find_get_page
       0.78%   -0.78%  [kernel.kallsyms]  [k] rcu_irq_enter
       0.57%   -0.57%  [kernel.kallsyms]  [k] finish_task_switch
       4.25%   -4.25%  [kernel.kallsyms]  [k] run_timer_softirq
               +0.80%  [kernel.kallsyms]  [k] native_apic_mem_write
       0.21%   +0.43%  [kernel.kallsyms]  [k] native_write_msr_safe
       9.16%   -9.16%  ld-2.12.so         [.] close
  #

Now:

8.44 + 9.05 + 10.55 + 17.70 + 9.05 + 9.36 +
7.60 + 4.01 + 9.27 + 0.78 + 0.57 + 4.25 + 0.21 + 9.16 == 100%

Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-jeq55qdgby1745bs8r9sscdh@git.kernel.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      bfaef4b4
    • A
      perf diff: Move hists__match to the hists lib · 95529be4
      由 Arnaldo Carvalho de Melo 提交于 
      Its not 'diff' specific and will be useful for other use cases, like
bucketizing multiple events in a single session.

Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-o35urjgxfxxm70aw1wa81s4w@git.kernel.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      95529be4
    • A
      perf diff: Start moving to support matching more than two hists · b821c732
      由 Arnaldo Carvalho de Melo 提交于 
      We want to match more than two hists, so that we can match more than two
perf.data files and moreover, match hist_entries (buckets) in multiple
events in a group.

So the "baseline"/"leader" will instead of a ->pair pointer, use a
list_head, that will link to the pairs and hists__match use it.

Following that perf_evlist__link will link the hists in its evsel
groups.

Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-2kbmzepoi544ygj9godseqpv@git.kernel.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      b821c732
  11. 07 10月, 2012 1 次提交
    • A
      perf event: No need to create a thread when handling PERF_RECORD_EXIT · f62d3f0f
      由 Arnaldo Carvalho de Melo 提交于 
      When we were processing a PERF_RECORD_EXIT event we first used
machine__findnew_thread for both the thread exiting and for its parent,
only to use just the thread struct associated with the one exiting, and
to just delete it.

If it existed, i.e. not created at this very moment in
machine__findnew_thread, it will be moved to the machine->dead_threads
linked list, because we may have hist_entries pointing to it, but if it
was created just do be deleted, it will just sit there with no
references at all.

Use the new machine__find_thread() method so that if it is not there, we
don't create it.

As a bonus the parent thread will also not be created at this point.

Create process_fork() and process_exit() helpers to use this and make
the builtins use it instead of the generic process_task(), ditched by
this patch.

Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-z7n2y98ebjyrvmytaope4vdl@git.kernel.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      f62d3f0f
  13. 06 10月, 2012 7 次提交
  15. 05 10月, 2012 3 次提交
  17. 11 9月, 2012 1 次提交
    • I
      perf tools: Use __maybe_used for unused variables · 1d037ca1
      由 Irina Tirdea 提交于 
      perf defines both __used and __unused variables to use for marking
unused variables. The variable __used is defined to
__attribute__((__unused__)), which contradicts the kernel definition to
__attribute__((__used__)) for new gcc versions. On Android, __used is
also defined in system headers and this leads to warnings like: warning:
'__used__' attribute ignored

__unused is not defined in the kernel and is not a standard definition.
If __unused is included everywhere instead of __used, this leads to
conflicts with glibc headers, since glibc has a variables with this name
in its headers.

The best approach is to use __maybe_unused, the definition used in the
kernel for __attribute__((unused)). In this way there is only one
definition in perf sources (instead of 2 definitions that point to the
same thing: __used and __unused) and it works on both Linux and Android.
This patch simply replaces all instances of __used and __unused with
__maybe_unused.
Signed-off-by: NIrina Tirdea <irina.tirdea@intel.com>
Acked-by: NPekka Enberg <penberg@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com
[ committer note: fixed up conflict with a116e05d in builtin-sched.c ]
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      1d037ca1
  19. 09 9月, 2012 1 次提交
  21. 08 9月, 2012 1 次提交
    • J
      perf diff: Make diff command work with evsel hists · 863e451f
      由 Jiri Olsa 提交于 
      Putting 'perf diff' command back on track with the 'latest'
evsel hists changes. Each evsel has its own 'hists' object
gathering stats for the particular event.

While currently counts are accumulated for the whole session
regardless of the events diversification within compared
sessions.

The 'perf diff' command now outputs all matching events within
compared sessions (with event name specified). The per event
diff output stays the same.

  $ ./perf diff
  # Event 'cycles'
  #
  # Baseline  Delta          Shared Object                          Symbol
  # ........ ..........  .................  ..............................
  #
       0.00%    +15.14%  [kernel.kallsyms]  [k] __wake_up
       0.00%    +13.38%  [kernel.kallsyms]  [k] ext4fs_dirhash

... SNIP

       0.00%     +0.42%  [kernel.kallsyms]  [k] local_clock
       0.17%     -0.05%  [kernel.kallsyms]  [k] native_write_msr_safe

  # Event 'faults'
  #
  # Baseline  Delta          Shared Object                          Symbol
  # ........ ..........  .................  ..............................
  #
       0.00%    +79.12%  ld-2.15.so         [.] _dl_relocate_object
       0.00%    +11.62%  ld-2.15.so         [.] openaux
Signed-off-by: NJiri Olsa <jolsa@redhat.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1346946426-13496-2-git-send-email-jolsa@redhat.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      863e451f
  23. 23 3月, 2012 1 次提交
  25. 28 11月, 2011 3 次提交
  27. 07 10月, 2011 1 次提交
  29. 24 3月, 2011 1 次提交
    • A
      perf session: Pass evsel in event_ops->sample() · 9e69c210
      由 Arnaldo Carvalho de Melo 提交于 
      Resolving the sample->id to an evsel since the most advanced tools,
report and annotate, and the others will too when they evolve to
properly support multi-event perf.data files.

Good also because it does an extra validation, checking that the ID is
valid when present. When that is not the case, the overhead is just a
branch + function call (perf_evlist__id2evsel).

Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
LKML-Reference: <new-submission>
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      9e69c210
  31. 30 1月, 2011 2 次提交
  33. 22 12月, 2010 3 次提交
    • D
      perf symbols: Add symfs option for off-box analysis using specified tree · ec5761ea
      由 David Ahern 提交于 
      The symfs argument allows analysis of perf.data file using a locally accessible
filesystem tree with debug symbols - e.g., tree created during image builds,
sshfs mount, loop mounted KVM disk images, USB keys, initrds, etc. Anything
with an OS tree can be analyzed from anywhere without the need to populate a
local data store with build-ids.

Commiter notes:

o Fixed up symfs="/" variants handling.

o prefixed DSO__ORIG_GUEST_KMODULE case with symfs too, avoiding use of files
  outside the symfs directory.

LKML-Reference: <1291926427-28846-1-git-send-email-daahern@cisco.com>
Signed-off-by: NDavid Ahern <daahern@cisco.com>
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      ec5761ea
    • I
      perf record,report,annotate,diff: Process events in order · eac23d1c
      由 Ian Munsie 提交于 
      This patch changes perf report to ask for the ID info on all events be
default if recording from multiple CPUs.

Perf report, annotate and diff will now process the events in order if
the kernel is able to provide timestamps on all events. This ensures
that events such as COMM and MMAP which are necessary to correctly
interpret samples are processed prior to those samples so that they are
attributed correctly.

Before:
 # perf record ./cachetest
 # perf report

 # Events: 6K cycles
 #
 # Overhead  Command      Shared Object                           Symbol
 # ........  .......  .................  ...............................
 #
     74.11%    :3259  [unknown]          [k] 0x4a6c
      1.50%  cachetest  ld-2.11.2.so       [.] 0x1777c
      1.46%    :3259  [kernel.kallsyms]  [k] .perf_event_mmap_ctx
      1.25%    :3259  [kernel.kallsyms]  [k] restore
      0.74%    :3259  [kernel.kallsyms]  [k] ._raw_spin_lock
      0.71%    :3259  [kernel.kallsyms]  [k] .filemap_fault
      0.66%    :3259  [kernel.kallsyms]  [k] .memset
      0.54%  cachetest  [kernel.kallsyms]  [k] .sha_transform
      0.54%    :3259  [kernel.kallsyms]  [k] .copy_4K_page
      0.54%    :3259  [kernel.kallsyms]  [k] .find_get_page
      0.52%    :3259  [kernel.kallsyms]  [k] .trace_hardirqs_off
      0.50%    :3259  [kernel.kallsyms]  [k] .__do_fault
<SNIP>

After:
 # perf report

 # Events: 6K cycles
 #
 # Overhead  Command      Shared Object                           Symbol
 # ........  .......  .................  ...............................
 #
     44.28%  cachetest  cachetest          [.] sumArrayNaive
     22.53%  cachetest  cachetest          [.] sumArrayOptimal
      6.59%  cachetest  ld-2.11.2.so       [.] 0x1777c
      2.13%  cachetest  [unknown]          [k] 0x340
      1.46%  cachetest  [kernel.kallsyms]  [k] .perf_event_mmap_ctx
      1.25%  cachetest  [kernel.kallsyms]  [k] restore
      0.74%  cachetest  [kernel.kallsyms]  [k] ._raw_spin_lock
      0.71%  cachetest  [kernel.kallsyms]  [k] .filemap_fault
      0.66%  cachetest  [kernel.kallsyms]  [k] .memset
      0.54%  cachetest  [kernel.kallsyms]  [k] .copy_4K_page
      0.54%  cachetest  [kernel.kallsyms]  [k] .find_get_page
      0.54%  cachetest  [kernel.kallsyms]  [k] .sha_transform
      0.52%  cachetest  [kernel.kallsyms]  [k] .trace_hardirqs_off
      0.50%  cachetest  [kernel.kallsyms]  [k] .__do_fault
<SNIP>

Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
LKML-Reference: <1291872833-839-1-git-send-email-imunsie@au1.ibm.com>
Signed-off-by: NIan Munsie <imunsie@au1.ibm.com>
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      eac23d1c
    • I
      perf session: Fallback to unordered processing if no sample_id_all · 21ef97f0
      由 Ian Munsie 提交于 
      If we are running the new perf on an old kernel without support for
sample_id_all, we should fall back to the old unordered processing of
events. If we didn't than we would *always* process events without
timestamps out of order, whether or not we hit a reordering race. In
other words, instead of there being a chance of not attributing samples
correctly, we would guarantee that samples would not be attributed.

While processing all events without timestamps before events with
timestamps may seem like an intuitive solution, it falls down as
PERF_RECORD_EXIT events would also be processed before any samples.
Even with a workaround for that case, samples before/after an exec would
not be attributed correctly.

This patch allows commands to indicate whether they need to fall back to
unordered processing, so that commands that do not care about timestamps
on every event will not be affected. If we do fallback, this will print
out a warning if report -D was invoked.

This patch adds the test in perf_session__new so that we only need to
test once per session. Commands that do not use an event_ops (such as
record and top) can simply pass NULL in it's place.
Acked-by: NThomas Gleixner <tglx@linutronix.de>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
LKML-Reference: <1291951882-sup-6069@au1.ibm.com>
Signed-off-by: NIan Munsie <imunsie@au1.ibm.com>
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      21ef97f0
  35. 05 12月, 2010 1 次提交
    • A
      perf session: Parse sample earlier · 640c03ce
      由 Arnaldo Carvalho de Melo 提交于 
      At perf_session__process_event, so that we reduce the number of lines in eache
tool sample processing routine that now receives a sample_data pointer already
parsed.

This will also be useful in the next patch, where we'll allow sample the
identity fields in MMAP, FORK, EXIT, etc, when it will be possible to see (cpu,
timestamp) just after before every event.

Also validate callchains in perf_session__process_event, i.e. as early as
possible, and keep a counter of the number of events discarded due to invalid
callchains, warning the user about it if it happens.

There is an assumption that was kept that all events have the same sample_type,
that will be dealt with in the future, when this preexisting limitation will be
removed.
Tested-by: NThomas Gleixner <tglx@linutronix.de>
Reviewed-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: NIan Munsie <imunsie@au1.ibm.com>
Acked-by: NThomas Gleixner <tglx@linutronix.de>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: Ian Munsie <imunsie@au1.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Stephane Eranian <eranian@google.com>
LKML-Reference: <1291318772-30880-4-git-send-email-acme@infradead.org>
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      640c03ce
  37. 02 12月, 2010 1 次提交
  39. 27 7月, 2010 1 次提交