Skip to content

K
Kernel

openeuler / Kernel
1 年多 前同步成功

通知 8
Star 0
Fork 0
K
Kernel
切换分支/标签
  1. 07 1月, 2016 1 次提交
  3. 11 12月, 2015 1 次提交
  5. 10 12月, 2015 1 次提交
  7. 28 11月, 2015 1 次提交
    • N
      perf hists: Do not skip elided fields when processing samples · e72655d9
      由 Namhyung Kim 提交于 
      If user gives a filter, perf marks the corresponding column elided and
omits the output.  But it should process and aggregates samples using
the field, otherwise samples will be aggregated as if the column was not
there resulted in incorrect output.

For example, I'd like to set a filter on native_write_msr_safe.  The
original overhead of the function is negligible.

  $ perf report | grep native_write_msr_safe
      0.00%  swapper  [kernel.vmlinux]  native_write_msr_safe
      0.00%  perf     [kernel.vmlinux]  native_write_msr_safe

However adding -S option gives different output.

  $ perf report -S native_write_msr_safe --percentage absolute | \
  > grep -e swapper -e perf
     51.47%  swapper  [kernel.vmlinux]
      4.14%  perf     [kernel.vmlinux]

Since it aggregated samples using comm and dso only.  In fact, the above
values are same when it sorts with -s comm,dso.

  $ perf report -s comm,dso | grep -e swapper -e perf
     51.47%  swapper  [kernel.vmlinux]
      4.14%  perf     [kernel.vmlinux]

This resulted in TUI failure with -ERANGE since it tries to increase
sample hit count for annotation with wrong symbols due to incorrect
aggregation.

This patch fixes it not to skip elided fields when comparing samples in
order to insert them to the hists.

Commiter note:

After the patch, with a different workloads:

  # perf report --show-total-period -S native_write_msr_safe --stdio
  #
  # symbol: native_write_msr_safe
  #
  # Samples: 455  of event 'cycles:pp'
  # Event count (approx.): 134787489
  #
  # Overhead Period Command         Shared Object
  # ........ ...... ............... ................
  #
       0.22% 293081 qemu-system-x86 [vmlinux]
       0.19% 255914 swapper         [vmlinux]
       0.00%   2054 Timer           [vmlinux]
       0.00%   1021 firefox         [vmlinux]
       0.00%      2 perf            [vmlinux]

  # perf report --show-total-period | grep native_write_msr_safe
  Failed to open /tmp/perf-14838.map, continuing without symbols
       0.22% 293081 qemu-system-x86 [vmlinux]  [k] native_write_msr_safe
       0.19% 255914 swapper         [vmlinux]  [k] native_write_msr_safe
       0.00%   2054 Timer           [vmlinux]  [k] native_write_msr_safe
       0.00%   1021 firefox         [vmlinux]  [k] native_write_msr_safe
       0.00%      2 perf            [vmlinux]  [k] native_write_msr_safe
  #
Reported-by: NIngo Molnar <mingo@kernel.org>
Signed-off-by: NNamhyung Kim <namhyung@kernel.org>
Tested-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1448645559-31167-2-git-send-email-namhyung@kernel.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      e72655d9
  9. 06 10月, 2015 1 次提交
  11. 01 10月, 2015 1 次提交
  13. 29 9月, 2015 1 次提交
  15. 15 9月, 2015 1 次提交
  17. 14 9月, 2015 4 次提交
  19. 13 8月, 2015 2 次提交
    • K
      perf report: Show call graph from reference events · 9e207ddf
      由 Kan Liang 提交于 
      Introduce --show-ref-call-graph for perf report to print reference
callgraph for no callgraph event.

Here is an example.

 perf report --show-ref-call-graph --stdio

 # To display the perf.data header info, please use
 --header/--header-only options.
 #
 #
 # Total Lost Samples: 0
 #
 # Samples: 5  of event 'cpu/cpu-cycles,call-graph=fp/'
 # Event count (approx.): 144985
 #
 # Children      Self  Command  Shared Object     Symbol
 # ........  ........  .......  ................  ........................................
 #
    72.30%     0.00%  sleep    [kernel.vmlinux]  [k] entry_SYSCALL_64_fastpath
              |
              ---entry_SYSCALL_64_fastpath
                 |
                 |--22.62%-- __GI___libc_nanosleep
                  --77.38%-- [...]

......

 # Samples: 6  of event 'cpu/instructions,call-graph=no/', show reference callgraph
 # Event count (approx.): 172780
 #
 # Children      Self  Command  Shared Object     Symbol
 # ........  ........  .......  ................  ........................................
 #
    73.16%     0.00%  sleep    [kernel.vmlinux]  [k] entry_SYSCALL_64_fastpath
              |
              ---entry_SYSCALL_64_fastpath
                 |
                 |--31.44%-- __GI___libc_nanosleep
                  --68.56%-- [...]
Signed-off-by: NKan Liang <kan.liang@intel.com>
Tested-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/1439289050-40510-3-git-send-email-kan.liang@intel.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      9e207ddf
    • K
      perf callchain: Allow disabling call graphs per event · f9db0d0f
      由 Kan Liang 提交于 
      This patch introduce "call-graph=no" to disable per-event callgraph.

Here is an example.

  perf record -e 'cpu/cpu-cycles,call-graph=fp/,cpu/instructions,call-graph=no/' sleep 1

  perf report --stdio

  # To display the perf.data header info, please use
  --header/--header-only options.
  #
  #
  # Total Lost Samples: 0
  #
  # Samples: 6  of event 'cpu/cpu-cycles,call-graph=fp/'
  # Event count (approx.): 774218
  #
  # Children      Self  Command  Shared Object     Symbol
  # ........  ........  .......  ................  ........................................
  #
    61.94%     0.00%  sleep    [kernel.vmlinux]  [k] entry_SYSCALL_64_fastpath
              |
              ---entry_SYSCALL_64_fastpath
                 |
                 |--97.30%-- __brk
                 |
                  --2.70%-- mmap64
                            _dl_check_map_versions
                            _dl_check_all_versions

    61.94%     0.00%  sleep    [kernel.vmlinux]  [k] perf_event_mmap
              |
              ---perf_event_mmap
                 |
                 |--97.30%-- do_brk
                 |          sys_brk
                 |          entry_SYSCALL_64_fastpath
                 |          __brk
                 |
                  --2.70%-- mmap_region
                            do_mmap_pgoff
                            vm_mmap_pgoff
                            sys_mmap_pgoff
                            sys_mmap
                            entry_SYSCALL_64_fastpath
                            mmap64
                            _dl_check_map_versions
                            _dl_check_all_versions
  ......

  # Samples: 6  of event 'cpu/instructions,call-graph=no/'
  # Event count (approx.): 359692
  #
  # Children      Self  Command  Shared Object     Symbol
  # ........  ........  .......  ................  .................................
  #
     89.03%     0.00%  sleep    [unknown]         [.] 0xffff6598ffff6598
     89.03%     0.00%  sleep    ld-2.17.so        [.] _dl_resolve_conflicts
     89.03%     0.00%  sleep    [kernel.vmlinux]  [k] page_fault
Signed-off-by: NKan Liang <kan.liang@intel.com>
Tested-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/1439289050-40510-2-git-send-email-kan.liang@intel.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      f9db0d0f
  21. 11 8月, 2015 3 次提交
    • A
      perf report: Add support for srcfile sort key · 31191a85
      由 Andi Kleen 提交于 
      In some cases it's useful to characterize samples by file. This is
useful to get a higher level categorization, for example to map cost to
subsystems.

Add a srcfile sort key to perf report. It builds on top of the existing
srcline support.

Commiter notes:

E.g.:

  # perf record -F 10000 usleep 1
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.016 MB perf.data (13 samples) ]
  [root@zoo ~]# perf report -s srcfile --stdio
  # Total Lost Samples: 0
  #
  # Samples: 13  of event 'cycles'
  # Event count (approx.): 869878
  #
  # Overhead  Source File
  # ........  ...........
      60.99%  .
      20.62%  paravirt.h
      14.23%  rmap.c
       4.04%  signal.c
       0.11%  msr.h

  #

The first line is collecting all the files for which srcfiles couldn't somehow
get resolved to:

  # perf report -s srcfile,dso --stdio
  # Total Lost Samples: 0
  #
  # Samples: 13  of event 'cycles'
  # Event count (approx.): 869878
  #
  # Overhead  Source File  Shared Object
  # ........  ...........  ................
      40.97%  .            ld-2.20.so
      20.62%  paravirt.h   [kernel.vmlinux]
      20.02%  .            libc-2.20.so
      14.23%  rmap.c       [kernel.vmlinux]
       4.04%  signal.c     [kernel.vmlinux]
       0.11%  msr.h        [kernel.vmlinux]

  #

XXX: Investigate why that is not resolving on Fedora 21, Andi says he hasn't
     seen this on Fedora 22.
Signed-off-by: NAndi Kleen <ak@linux.intel.com>
Tested-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/1438988064-21834-1-git-send-email-andi@firstfloor.org
[ Added column length update, from 0e65bdb3f90f ('perf hists: Update the column width for the "srcline" sort key') ]
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      31191a85
    • A
      perf hists: Update the column width for the "srcline" sort key · e8e6d37e
      由 Arnaldo Carvalho de Melo 提交于 
      When we introduce a new sort key, we need to update the
hists__calc_col_len() function accordingly, otherwise the width
will be limited to strlen(header).

We can't update it when obtaining a line value for a column (for
instance, in sort__srcline_cmp()), because we reset it all when doing a
resort (see hists__output_recalc_col_len()), so we need to, from what is
in the hist_entry fields, set each of the column widths.

Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Fixes: 409a8be6 ("perf tools: Add sort by src line/number")
Link: http://lkml.kernel.org/n/tip-jgbe0yx8v1gs89cslr93pvz2@git.kernel.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      e8e6d37e
    • A
      perf hists: hist_entry__cmp() may use he_tmp.hists, initialize it · 5cef8976
      由 Arnaldo Carvalho de Melo 提交于 
      The iter_add_next_cumulative_entry() function calls hist_entry__cmp(),
which may want to access the hists where this hist_entry is stored,
initialize it to let that happen and avoid segfaults.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-iqg98sfn4fvwcxp0pdvqauie@git.kernel.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      5cef8976
  23. 07 8月, 2015 2 次提交
  25. 16 6月, 2015 1 次提交
  27. 27 5月, 2015 2 次提交
  29. 06 5月, 2015 1 次提交
  31. 18 3月, 2015 1 次提交
  33. 12 3月, 2015 1 次提交
    • H
      perf hists browser: Fix UI bug after zoom into thread/dso/symbol · a8cd1f43
      由 He Kuang 提交于 
      When zoom into thread/dso/symbol, the fold/unfold stat is cleared in
hists__filter_by_thread/dso/symbol(), but h->nr_rows is not cleared. So
if we toggle fold stat on the unfold entires, nr_entries got a wrong
value.

This bug can be reproduced as follows:

$ perf record -g -e syscalls:sys_enter_open ls
$ perf report

    Children      Self  Command  Shared Object            Symbol
  ================================================================
  +   50.00%     0.00%  ls       ld64.so  [.]  _dl_get_ready_to_run
  -   50.00%     0.00%  ls       ld64.so  [.]  _dl_load_shared_library
      _dl_load_shared_library <= [Zoom into thread/dso]
      _dl_get_ready_to_run
      _start
  ...

In the new thread hists, all entries reset to fold, if we unfold the
same entry as we previously unfolded, nr_entries got wrong value, and we
can't move down cursor to bottom row.

                                                         Thread: ls
    Children      Self  Command  Shared Object            Symbol
  ================================================================
  +   50.00%     0.00%  ls       ld64.so  [.]  _dl_get_ready_to_run
  -   50.00%     0.00%  ls       ld64.so  [.]  _dl_load_shared_library
      _dl_load_shared_library
      _dl_get_ready_to_run <= [cursor may stop here, can't move down]
      _start
  ...

This patch clear h->nr_rows to fix this bug.
Signed-off-by: NHe Kuang <hekuang@huawei.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1426077363-855-2-git-send-email-hekuang@huawei.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      a8cd1f43
  35. 03 3月, 2015 1 次提交
    • A
      perf tools: Reference count struct thread · f3b623b8
      由 Arnaldo Carvalho de Melo 提交于 
      We need to do that to stop accumulating entries in the dead_threads
linked list, i.e. we were keeping references to threads in struct hists
that continue to exist even after a thread exited and was removed from
the machine threads rbtree.

We still keep the dead_threads list, but just for debugging, allowing us
to iterate at any given point over the threads that still are referenced
by things like struct hist_entry.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-3ejvfyed0r7ue61dkurzjux4@git.kernel.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      f3b623b8
  37. 22 1月, 2015 4 次提交
  39. 08 1月, 2015 1 次提交
  41. 23 12月, 2014 2 次提交
  43. 15 10月, 2014 1 次提交
    • A
      perf tools: Remove hists from evsel · a635fc51
      由 Arnaldo Carvalho de Melo 提交于 
      Now tools that deals want to have an hists per evsel need to call
hists__init() before creating any evsels, which can be as early as when
parsing the command line, so do it before calling parse_options().

The current tools using hists/hist_entries are report, top and annotate,
change them to request per evsel hists.

This is in preparation for making evsels usable by 3rd party tools, that
not necessarily live in perf's source code repository.
Acked-by: NBorislav Petkov <bp@suse.de>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jean Pihet <jean.pihet@linaro.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
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-usjx2la743f10ippj7p1b20x@git.kernel.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      a635fc51
  45. 14 10月, 2014 1 次提交
    • A
      perf session: Remove last reference to hists struct · 2a1731fb
      由 Arnaldo Carvalho de Melo 提交于 
      Now perf_session doesn't require that the evsels in its evlist are hists
containing ones.

Tools that are hists based and want to do per evsel events_stats
updates, if at some point this turns into a necessity, should do it in
the tool specific code, keeping the session class hists agnostic.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jean Pihet <jean.pihet@linaro.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
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-cli1bgwpo82mdikuhy3djsuy@git.kernel.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      2a1731fb
  47. 10 10月, 2014 1 次提交
    • A
      perf evsel: Add hists helper · 4ea062ed
      由 Arnaldo Carvalho de Melo 提交于 
      Not all tools need a hists instance per perf_evsel, so lets pave the way
to remove evsel->hists while leaving a way to access the hists from a
specially allocated evsel, one that comes with space at the end where
lives the evsel.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jean Pihet <jean.pihet@linaro.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
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-qlktkhe31w4mgtbd84035sr2@git.kernel.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      4ea062ed
  49. 03 10月, 2014 1 次提交
    • J
      perf callchain: Move callchain_param to util object in to fix python test · 23aadb1f
      由 Jiri Olsa 提交于 
      In following commit we changed the location of callchains data:

  72a128aa
  perf tools: Move callchain config from record_opts to callchain_param

Now all callchains stuff stays in callchain_param struct, which adds its
dependency for evsel.c object and breaks python perf.so usage
(unresolved callchain_param).

Moving callchain_param into callchain.c and adding it into
python-ext-sources unleash just another dependency hell, so I ended up
adding callchain_param into util.c for now.
Signed-off-by: NJiri Olsa <jolsa@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Milian Wolff <mail@milianw.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1412179229-19466-2-git-send-email-jolsa@kernel.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      23aadb1f
  51. 14 8月, 2014 1 次提交
  53. 09 6月, 2014 2 次提交
    • D
      perf tools: Add dcacheline sort · 9b32ba71
      由 Don Zickus 提交于 
      In perf's 'mem-mode', one can get access to a whole bunch of details specific to a
particular sample instruction.  A bunch of those details relate to the data
address.

One interesting thing you can do with data addresses is to convert them into a unique
cacheline they belong too.  Organizing these data cachelines into similar groups and sorting
them can reveal cache contention.

This patch creates an alogorithm based on various sample details that can help group
entries together into data cachelines and allows 'perf report' to sort on it.

The algorithm relies on having proper mmap2 support in the kernel to help determine
if the memory map the data address belongs to is private to a pid or globally shared.

The alogortithm is as follows:

o group cpumodes together
o group entries with discovered maps together
o sort on major, minor, inode and inode generation numbers
o if userspace anon, then sort on pid
o sort on cachelines based on data addresses

The 'dcacheline' sort option in 'perf report' only works in 'mem-mode'.

Sample output:

 #
 # Samples: 206  of event 'cpu/mem-loads/pp'
 # Total weight : 2534
 # Sort order   : dcacheline,pid
 #
 # Overhead       Samples                                                          Data Cacheline       Command:  Pid
 # ........  ............  ......................................................................  ..................
 #
    13.22%             1  [k] 0xffff88042f08ebc0                                                       swapper:    0
     9.27%             1  [k] 0xffff88082e8cea80                                                       swapper:    0
     3.59%             2  [k] 0xffffffff819ba180                                                       swapper:    0
     0.32%             1  [k] arch_trigger_all_cpu_backtrace_handler_na.23901+0xffffffffffffffe0       swapper:    0
     0.32%             1  [k] timekeeper_seq+0xfffffffffffffff8                                        swapper:    0

Note:  Added a '+1' to symlen size in hists__calc_col_len to prevent the next column
from prematurely tabbing over and mis-aligning.  Not sure what the problem is.
Signed-off-by: NDon Zickus <dzickus@redhat.com>
Link: http://lkml.kernel.org/r/1401208087-181977-8-git-send-email-dzickus@redhat.comSigned-off-by: NJiri Olsa <jolsa@kernel.org>
      9b32ba71
    • D
      perf tools: Add cpumode to struct hist_entry · 7365be55
      由 Don Zickus 提交于 
      The next patch needs to sort on cpumode, so add it to hist_entry to be tracked.
Signed-off-by: NDon Zickus <dzickus@redhat.com>
Link: http://lkml.kernel.org/r/1401208087-181977-6-git-send-email-dzickus@redhat.comSigned-off-by: NJiri Olsa <jolsa@kernel.org>
      7365be55