Skip to content

cloud-kernel
cloud-kernel

openanolis / cloud-kernel
1 年多 前同步成功

通知 160
Star 36
Fork 7
cloud-kernel
cloud-kernel
切换分支/标签
  1. 27 6月, 2017 3 次提交
  3. 21 6月, 2017 2 次提交
  5. 20 6月, 2017 4 次提交
    • N
      perf ftrace: Add -D option for depth filter · 1096c35a
      由 Namhyung Kim 提交于 
      The -D/--graph-depth option is to set max graph depth.  The following
example traces max 2-depth of page fault handler.

  $ sudo perf ftrace -G __do_page_fault -D 2 -- hello
   ...
   0)               |  __do_page_fault() {
   0)   0.063 us    |    down_read_trylock();
   0)   0.251 us    |    find_vma();
   0)   5.374 us    |    handle_mm_fault();
   0)   0.054 us    |    up_read();
   0)   7.463 us    |  }
   ...
Signed-off-by: NNamhyung Kim <namhyung@kernel.org>
Tested-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: kernel-team@lge.com
Link: http://lkml.kernel.org/r/20170618142302.25390-4-namhyung@kernel.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      1096c35a
    • N
      perf ftrace: Add option for function filtering · 78b83e8b
      由 Namhyung Kim 提交于 
      The -T/--trace-funcs and -N/--notrace-funcs options are to specify
functions to enable/disable tracing dynamically.

The -G/--graph-funcs and -g/--nograph-funcs options are to set filters
for function graph tracer.

For example, to trace fault handling functions only:

  $ sudo perf ftrace -T *fault hello
   0)               |  __do_page_fault() {
   0)               |    handle_mm_fault() {
   0)   2.117 us    |      __handle_mm_fault();
   0)   3.627 us    |    }
   0)   7.811 us    |  }
   0)               |  __do_page_fault() {
   0)               |    handle_mm_fault() {
   0)   2.014 us    |      __handle_mm_fault();
   0)   2.424 us    |    }
   0)   2.951 us    |  }
   ...

To trace all functions executed in __do_page_fault:

  $ sudo perf ftrace -G __do_page_fault hello
   2)               |  __do_page_fault() {
   3)   0.060 us    |    down_read_trylock();
   3)               |    find_vma() {
   3)   0.075 us    |      vmacache_find();
   3)   0.053 us    |      vmacache_update();
   3)   1.246 us    |    }
   3)               |    handle_mm_fault() {
   3)   0.063 us    |      __rcu_read_lock();
   3)   0.056 us    |      mem_cgroup_from_task();
   3)   0.057 us    |      __rcu_read_unlock();
   3)               |      __handle_mm_fault() {
   3)               |        filemap_map_pages() {
   3)   0.058 us    |          __rcu_read_lock();
   3)               |          alloc_set_pte() {
   ...

But don't want to show details in handle_mm_fault:

  $ sudo perf ftrace -G __do_page_fault -g handle_mm_fault hello
   3)               |  __do_page_fault() {
   3)   0.049 us    |    down_read_trylock();
   3)               |    find_vma() {
   3)   0.048 us    |      vmacache_find();
   3)   0.041 us    |      vmacache_update();
   3)   0.680 us    |    }
   3)   0.036 us    |    up_read();
   3)   4.547 us    |  } /* __do_page_fault */
   ...
Signed-off-by: NNamhyung Kim <namhyung@kernel.org>
Tested-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: kernel-team@lge.com
Link: http://lkml.kernel.org/r/20170618142302.25390-3-namhyung@kernel.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      78b83e8b
    • M
      perf script: Support -F brstackoff,dso · 106dacd8
      由 Mark Santaniello 提交于 
      The idea here is to make AutoFDO easier in cloud environment with ASLR.
It's easiest to show how this is useful by example. I built a small test
akin to "while(1) { do_nothing(); }" where the do_nothing function is
loaded from a dso:

  $ cat burncpu.cpp
  #include <dlfcn.h>

  int main() {
    void* handle = dlopen("./dso.so", RTLD_LAZY);
    if (!handle) return -1;

    typedef void (*fp)();
    fp do_nothing = (fp) dlsym(handle, "do_nothing");

    while(1) {
      do_nothing();
    }
  }

  $ cat dso.cpp
  extern "C" void do_nothing() {}

  $ cat build.sh
  #!/bin/bash
  g++ -shared dso.cpp -o dso.so
  g++ burncpu.cpp -o burncpu -ldl

I sampled the execution of this program with perf record -b.

Using the existing "brstack,dso", we get absolute addresses that are
affected by ASLR, and could be different on different hosts. The address
does not uniquely identify a branch/target in the binary:

  $ perf script -F brstack,dso | sed 's/\/0 /\/0\n/g' | grep burncpu | grep dso.so | head -n 1
  0x7f967139b6aa(/tmp/burncpu/dso.so)/0x4006b1(/tmp/burncpu/exe)/P/-/-/0

Using the existing "brstacksym,dso" is a little better, because the
symbol plus offset and dso name *does* uniquely identify a branch/target
in the binary.  Ultimately, however, AutoFDO wants a simple offset into
the binary, so we'd have to undo all the work perf did to symbolize in
the first place:

  $ perf script -F brstacksym,dso | sed 's/\/0 /\/0\n/g' | grep burncpu | grep dso.so | head -n 1
  do_nothing+0x5(/tmp/burncpu/dso.so)/main+0x44(/tmp/burncpu/exe)/P/-/-/0

With the new "brstackoff,dso" we get what we need: a simple offset into a
specific dso/binary that uniquely identifies a branch/target:
  $ perf script -F brstackoff,dso | sed 's/\/0 /\/0\n/g' | grep burncpu | grep dso.so | head -n 1
  0x6aa(/tmp/burncpu/dso.so)/0x4006b1(/tmp/burncpu/exe)/P/-/-/0
Signed-off-by: NMark Santaniello <marksan@fb.com>
Tested-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20170619163825.2012979-2-marksan@fb.com
[ Updated documentation about 'brstackoff' using text from above ]
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      106dacd8
    • A
      perf script: Allow adding and removing fields · 36ce5651
      由 Andi Kleen 提交于 
      With 'perf script' it is common that we just want to add or remove a field.

Currently this requires figuring out the long list of default fields and
specifying them first, and then adding/removing the new field.

This patch adds a new + - syntax to merely add or remove fields,
that allows more succint and clearer command lines

For example to remove the comm field from PMU samples:

Previously

  $ perf script -F tid,cpu,time,event,sym,ip,dso,period | head -1
  swapper  0 [000] 504345.383126:          1 cycles:  ffffffff90060c66 native_write_msr ([kernel.kallsyms])

with the new syntax

  perf script -F -comm | head -1
  0 [000] 504345.383126:          1 cycles:  ffffffff90060c66 native_write_msr ([kernel.kallsyms])

The new syntax cannot be mixed with normal overriding.

v2: Fix example in description. Use tid vs pid. No functional changes.
v3: Don't skip initialization when user specified explicit type.
v4: Rebase. Remove empty line.

Committer testing:

  # perf record -a usleep 1
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 1.748 MB perf.data (14 samples) ]

Without a explicit field list specified via -F, defaults to:

  # perf script | head -2
      perf 6338 [000] 18467.058607: 1 cycles: ffffffff89060c36 native_write_msr (/lib/modules/4.11.0-rc8+/build/vmlinux)
   swapper    0 [001] 18467.058617: 1 cycles: ffffffff89060c36 native_write_msr (/lib/modules/4.11.0-rc8+/build/vmlinux)
  #

Which is equivalent to:

  # perf script -F comm,tid,cpu,time,period,event,ip,sym,dso | head -2
      perf 6338 [000] 18467.058607: 1 cycles: ffffffff89060c36 native_write_msr (/lib/modules/4.11.0-rc8+/build/vmlinux)
   swapper    0 [001] 18467.058617: 1 cycles: ffffffff89060c36 native_write_msr (/lib/modules/4.11.0-rc8+/build/vmlinux)
  #

So if we want to remove the comm, as in your original example, we would have to
figure out the default field list and remove ' comm' from it:

  # perf script -F tid,cpu,time,period,event,ip,sym,dso | head -2
   6338 [000] 18467.058607: 1 cycles: ffffffff89060c36 native_write_msr (/lib/modules/4.11.0-rc8+/build/vmlinux)
      0 [001] 18467.058617: 1 cycles: ffffffff89060c36 native_write_msr (/lib/modules/4.11.0-rc8+/build/vmlinux)
  #

With your patch this becomes simpler, one can remove fields by prefixing them
with '-':

  # perf script -F -comm | head -2
  6338 [000] 18467.058607: 1 cycles: ffffffff89060c36 native_write_msr (/lib/modules/4.11.0-rc8+/build/vmlinux)
     0 [001] 18467.058617: 1 cycles: ffffffff89060c36 native_write_msr (/lib/modules/4.11.0-rc8+/build/vmlinux)
  #
Signed-off-by: NAndi Kleen <ak@linux.intel.com>
Acked-by: NJiri Olsa <jolsa@kernel.org>
Tested-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: NMilian Wolff <milian.wolff@kdab.com>
Link: http://lkml.kernel.org/r/20170602154810.15875-1-andi@firstfloor.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      36ce5651
  7. 08 6月, 2017 5 次提交
  9. 24 5月, 2017 1 次提交
    • N
      perf script: Add --inline option for debugging · 325fbff5
      由 Namhyung Kim 提交于 
      The --inline option is to show inlined functions in callchains.

For example:

  $ perf script
  a.out  5644 11611.467597:     309961 cycles:u:
                     790 main (/home/namhyung/tmp/perf/a.out)
                   20511 __libc_start_main (/usr/lib/libc-2.25.so)
                     8ba _start (/home/namhyung/tmp/perf/a.out)
  ...

  $ perf script --inline
  a.out  5644 11611.467597:     309961 cycles:u:
                     790 main (/home/namhyung/tmp/perf/a.out)
                         std::__detail::_Adaptor<std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul>, double>::operator()
                         std::uniform_real_distribution<double>::operator()<std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul> >
                         std::uniform_real_distribution<double>::operator()<std::linear_congruential_engine<unsigned long, 16807ul, 0ul, 2147483647ul> >
                         main
                   20511 __libc_start_main (/usr/lib/libc-2.25.so)
                     8ba _start (/home/namhyung/tmp/perf/a.out)
  ...
Reviewed-and-tested-by: NMilian Wolff <milian.wolff@kdab.com>
Signed-off-by: NNamhyung Kim <namhyung@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: kernel-team@lge.com
Link: http://lkml.kernel.org/r/20170524062129.32529-5-namhyung@kernel.orgSigned-off-by: NIngo Molnar <mingo@kernel.org>
      325fbff5
  11. 04 5月, 2017 1 次提交
  13. 13 4月, 2017 1 次提交
    • R
      perf trace: Add usage of --no-syscalls in man page · 739cf305
      由 Ravi Bangoria 提交于 
      perf trace supports --no-syscalls option but it's not listed in the man
page. (Though, I see an example using --no-syscalls in EXAMPLES
section.)

Committer note:

The --no-syscalls option tells 'perf trace' not to automagically ask for
raw_syscalls:sys_{enter,exit} to then format it in a strace like way.

This become more used as 'perf trace' got support for arbitrary events,
such as tracepoints, so more and more we use:

  # perf trace --no-syscalls -e nmi:*
     0.000 nmi:nmi_handler:perf_event_nmi_handler() delta_ns: 36649 handled: 1)
     0.019 nmi:nmi_handler:nmi_cpu_backtrace_handler() delta_ns: 2907 handled: 0)
     0.676 nmi:nmi_handler:perf_event_nmi_handler() delta_ns: 9401 handled: 1)
     0.680 nmi:nmi_handler:nmi_cpu_backtrace_handler() delta_ns: 288 handled: 0)
     0.701 nmi:nmi_handler:perf_event_nmi_handler() delta_ns: 4977 handled: 1)
     0.703 nmi:nmi_handler:nmi_cpu_backtrace_handler() delta_ns: 67 handled: 0)
     0.736 nmi:nmi_handler:perf_event_nmi_handler() delta_ns: 8549 handled: 1)
  ^C#
Signed-off-by: NRavi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexis Berlemont <alexis.berlemont@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1492063332-5745-1-git-send-email-ravi.bangoria@linux.vnet.ibm.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      739cf305
  15. 12 4月, 2017 1 次提交
  17. 27 3月, 2017 3 次提交
    • M
      perf report: Enable sorting by srcline as key · 5dfa210e
      由 Milian Wolff 提交于 
      Often it is interesting to know how costly a given source line is in
total. Previously, one had to build these sums manually based on all
addresses that pointed to the same source line. This patch introduces
srcline as a sort key, which will do the aggregation for us.

Paired with the recent addition of showing inline frames, this makes
perf report much more useful for many C++ work loads.

The following shows the new feature in action. First, let's show the
status quo output when we sort by address. The result contains many hist
entries that generate the same output:

  ~~~~~~~~~~~~~~~~
  $ perf report --stdio --inline -g address
  # Children      Self  Command       Shared Object        Symbol
  # ........  ........  ............  ...................  .........................................
  #
      99.89%    35.34%  cpp-inlining  cpp-inlining         [.] main
            |
            |--64.55%--main complex:655
            |          /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline)
            |          /usr/include/c++/6.3.1/complex:664 (inline)
            |          |
            |          |--60.31%--hypot +20
            |          |          |
            |          |          |--8.52%--__hypot_finite +273
            |          |          |
            |          |          |--7.32%--__hypot_finite +411
...
             --35.34%--_start +4194346
                       __libc_start_main +241
                       |
                       |--6.65%--main random.tcc:3326
                       |          /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline)
                       |          /usr/include/c++/6.3.1/bits/random.h:1809 (inline)
                       |          /usr/include/c++/6.3.1/bits/random.h:1818 (inline)
                       |          /usr/include/c++/6.3.1/bits/random.h:185 (inline)
                       |
                       |--2.70%--main random.tcc:3326
                       |          /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline)
                       |          /usr/include/c++/6.3.1/bits/random.h:1809 (inline)
                       |          /usr/include/c++/6.3.1/bits/random.h:1818 (inline)
                       |          /usr/include/c++/6.3.1/bits/random.h:185 (inline)
                       |
                       |--1.69%--main random.tcc:3326
                       |          /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline)
                       |          /usr/include/c++/6.3.1/bits/random.h:1809 (inline)
                       |          /usr/include/c++/6.3.1/bits/random.h:1818 (inline)
                       |          /usr/include/c++/6.3.1/bits/random.h:185 (inline)
  ...
  ~~~~~~~~~~~~~~~~

With this patch and `-g srcline` we instead get the following output:

  ~~~~~~~~~~~~~~~~
  $ perf report --stdio --inline -g srcline
  # Children      Self  Command       Shared Object        Symbol
  # ........  ........  ............  ...................  .........................................
  #
      99.89%    35.34%  cpp-inlining  cpp-inlining         [.] main
            |
            |--64.55%--main complex:655
            |          /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline)
            |          /usr/include/c++/6.3.1/complex:664 (inline)
            |          |
            |          |--64.02%--hypot
            |          |          |
            |          |           --59.81%--__hypot_finite
            |          |
            |           --0.53%--cabs
            |
             --35.34%--_start
                       __libc_start_main
                       |
                       |--12.48%--main random.tcc:3326
                       |          /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline)
                       |          /usr/include/c++/6.3.1/bits/random.h:1809 (inline)
                       |          /usr/include/c++/6.3.1/bits/random.h:1818 (inline)
                       |          /usr/include/c++/6.3.1/bits/random.h:185 (inline)
  ...
  ~~~~~~~~~~~~~~~~
Signed-off-by: NMilian Wolff <milian.wolff@kdab.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Yao Jin <yao.jin@linux.intel.com>
Link: http://lkml.kernel.org/r/20170318214928.9047-1-milian.wolff@kdab.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      5dfa210e
    • J
      perf report: Introduce --inline option · f3a60646
      由 Jin Yao 提交于 
      It takes some time to look for inline stack for callgraph addresses.  So
it provides new option "--inline" to let user decide if enable this
feature.

  --inline:

  If a callgraph address belongs to an inlined function, the inline stack
  will be printed. Each entry is the inline function name or file/line.
Signed-off-by: NYao Jin <yao.jin@linux.intel.com>
Tested-by: NMilian Wolff <milian.wolff@kdab.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@intel.com>
Link: http://lkml.kernel.org/r/1490474069-15823-4-git-send-email-yao.jin@linux.intel.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      f3a60646
    • R
      perf list sdt: Show option in man page · 6963d3c3
      由 Ravi Bangoria 提交于 
      Commit 40218dae ("perf list: Show SDT and pre-cached events") added
sdt support in perf list, but it missed to update documentation.

Show sdt option in man perf-list.
Signed-off-by: NRavi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
Acked-by: NMasami Hiramatsu <mhiramat@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/20170327025538.1753-1-ravi.bangoria@linux.vnet.ibm.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      6963d3c3
  19. 23 3月, 2017 1 次提交
  21. 22 3月, 2017 1 次提交
    • A
      perf stat: Collapse identically named events · 430daf2d
      由 Andi Kleen 提交于 
      The uncore PMU has a lot of duplicated PMUs for different subsystems.
When expanding an uncore alias we usually end up with a large
number of identically named aliases, which makes perf stat
output difficult to read.

Automatically sum them up in perf stat, unless --no-merge is specified.

This can be default because only the uncores generally have duplicated
aliases. Other PMUs have unique names.

Before:

  % perf stat --no-merge -a -e unc_c_llc_lookup.any sleep 1

  Performance counter stats for 'system wide':

           694,976 Bytes unc_c_llc_lookup.any
           706,304 Bytes unc_c_llc_lookup.any
           956,608 Bytes unc_c_llc_lookup.any
           782,720 Bytes unc_c_llc_lookup.any
           605,696 Bytes unc_c_llc_lookup.any
           442,816 Bytes unc_c_llc_lookup.any
           659,328 Bytes unc_c_llc_lookup.any
           509,312 Bytes unc_c_llc_lookup.any
           263,936 Bytes unc_c_llc_lookup.any
           592,448 Bytes unc_c_llc_lookup.any
           672,448 Bytes unc_c_llc_lookup.any
           608,640 Bytes unc_c_llc_lookup.any
           641,024 Bytes unc_c_llc_lookup.any
           856,896 Bytes unc_c_llc_lookup.any
           808,832 Bytes unc_c_llc_lookup.any
           684,864 Bytes unc_c_llc_lookup.any
           710,464 Bytes unc_c_llc_lookup.any
           538,304 Bytes unc_c_llc_lookup.any

       1.002577660 seconds time elapsed

After:

  % perf stat -a -e unc_c_llc_lookup.any sleep 1

  Performance counter stats for 'system wide':

         2,685,120 Bytes unc_c_llc_lookup.any

       1.002648032 seconds time elapsed

v2: Split collect_aliases. Rename alias flag.
v3: Make sure unsupported/not counted is always printed.
v4: Factor out callback change into separate patch.
v5: Move check for bad results here
    Move merged check into collect_data
Signed-off-by: NAndi Kleen <ak@linux.intel.com>
Acked-by: NJiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20170320201711.14142-3-andi@firstfloor.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      430daf2d
  23. 21 3月, 2017 1 次提交
  25. 16 3月, 2017 1 次提交
    • A
      perf script: Add 'brstackinsn' for branch stacks · 48d02a1d
      由 Andi Kleen 提交于 
      Implement printing instruction sequences as hex dump for branch stacks.

This relies on the x86 instruction decoder used by the PT decoder to
find the lengths of instructions to dump them individually.

This is good enough for pattern matching.

This allows to study hot paths for individual samples, together with
branch misprediction and cycle count / IPC information if available (on
Skylake systems).

  % perf record -b ...
  % perf script -F brstackinsn
  ...
    read_hpet+67:
          ffffffff9905b843        insn: 74 ea                     # PRED
          ffffffff9905b82f        insn: 85 c9
          ffffffff9905b831        insn: 74 12
          ffffffff9905b833        insn: f3 90
          ffffffff9905b835        insn: 48 8b 0f
          ffffffff9905b838        insn: 48 89 ca
          ffffffff9905b83b        insn: 48 c1 ea 20
          ffffffff9905b83f        insn: 39 f2
          ffffffff9905b841        insn: 89 d0
          ffffffff9905b843        insn: 74 ea                     # PRED

Only works when no special branch filters are specified.

Occasionally the path does not reach up to the sample IP, as the LBRs
may be frozen before executing a final jump. In this case we print a
special message.

The instruction dumper piggy backs on the existing infrastructure from
the IP PT decoder.

An earlier iteration of this patch relied on a disassembler, but this
version only uses the existing instruction decoder.

Committer note:

Added hint about how to get suitable perf.data files for use with
'-F brstackinsm':

  $ perf record usleep 1
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.018 MB perf.data (8 samples) ]
  $
  $ perf script -F brstackinsn
  Display of branch stack assembler requested, but non all-branch filter set
  Hint: run 'perf record -b ...'
  $
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: Michael Ellerman <mpe@ellerman.id.au>
Link: http://lkml.kernel.org/r/20170223234634.583-1-andi@firstfloor.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      48d02a1d
  27. 15 3月, 2017 3 次提交
    • B
      perf sched timehist: Add --next option · 292c4a8f
      由 Brendan Gregg 提交于 
      The --next option shows the next task for each context switch, providing
more context for the sequence of scheduler events.

  $ perf sched timehist --next | head
  Samples do not have callchains.
       time  cpu task name  waittime schdelay run time
                 [tid/pid]     (msec) (msec) (msec)
  ---------- --- ---------- --------- ------ -----
  374.793792 [0] <idle>         0.000  0.000 0.000 next: rngd[1524]
  374.793801 [0] rngd[1524]     0.000  0.000 0.009 next: swapper/0[0]
  374.794048 [7] <idle>         0.000  0.000 0.000 next: yes[30884]
  374.794066 [7] yes[30884]     0.000  0.000 0.018 next: swapper/7[0]
  374.794126 [2] <idle>         0.000  0.000 0.000 next: rngd[1524]
  374.794140 [2] rngd[1524]     0.325  0.006 0.013 next: swapper/2[0]
  374.794281 [3] <idle>         0.000  0.000 0.000 next: perf[31070]
Signed-off-by: NBrendan Gregg <bgregg@netflix.com>
Tested-by: NArnaldo Carvalho de Melo <acme@redhat.com>
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/1489456589-32555-1-git-send-email-bgregg@netflix.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      292c4a8f
    • H
      perf tools: Add 'cgroup_id' sort order keyword · d890a98c
      由 Hari Bathini 提交于 
      This patch introduces a cgroup identifier entry field in perf report to
identify or distinguish data of different cgroups. It uses the device
number and inode number of cgroup namespace, included in perf data with
the new PERF_RECORD_NAMESPACES event, as cgroup identifier.

With the assumption that each container is created with it's own cgroup
namespace,  this allows assessment/analysis of multiple containers at
once.

A simple test for this would be to clone a few processes passing
SIGCHILD & CLONE_NEWCROUP flags to each of them, execute shell and run
different workloads  on each of those contexts,  while running perf
record command with --namespaces option.

Shown below is the output of perf report, sorted with cgroup identifier,
on perf.data generated with the above test scenario, clearly indicating
one context's considerable use of kernel memory in comparison with
others:

	$ perf report -s cgroup_id,sample --stdio
	#
	# Total Lost Samples: 0
	#
	# Samples: 5K of event 'kmem:kmalloc'
	# Event count (approx.): 5965
	#
	# Overhead  cgroup id (dev/inode)       Samples
	# ........  .....................  ............
	#
	    81.27%  3/0xeffffffb                   4848
	    16.24%  3/0xf00000d0                    969
	     1.16%  3/0xf00000ce                     69
	     0.82%  3/0xf00000cf                     49
	     0.50%  0/0x0                            30

While this is a start, there is further scope of improving this. For
example, instead of cgroup namespace's device and inode numbers, dev
and inode numbers of some or all namespaces may be used to distinguish
which processes are running in a given container context.

Also, scripts to map device and inode info to containers sounds
plausible for better tracing of containers.
Signed-off-by: NHari Bathini <hbathini@linux.vnet.ibm.com>
Tested-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Starovoitov <ast@fb.com>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Aravinda Prasad <aravinda@linux.vnet.ibm.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sargun Dhillon <sargun@sargun.me>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/148891933338.25309.756882900782042645.stgit@hbathini.in.ibm.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      d890a98c
    • H
      perf script: Add script print support for namespace events · 96a44bbc
      由 Hari Bathini 提交于 
      Introduce a new option to display events of type PERF_RECORD_NAMESPACES
and update perf-script documentation accordingly.

Shown below is output (trimmed) of perf script command with the newly
introduced option, on perf.data generated with perf record command using
--namespaces option.

  $ perf script --show-namespace-events
      swapper   0 [000]     0.000000: PERF_RECORD_NAMESPACES 1/1 - nr_namespaces: 7
                [0/net: 3/0xf000001c, 1/uts: 3/0xeffffffe, 2/ipc: 3/0xefffffff, 3/pid: 3/0xeffffffc,
                 4/user: 3/0xeffffffd, 5/mnt: 3/0xf0000000, 6/cgroup: 3/0xeffffffb]
      swapper   0 [000]     0.000000: PERF_RECORD_NAMESPACES 2/2 - nr_namespaces: 7
                [0/net: 3/0xf000001c, 1/uts: 3/0xeffffffe, 2/ipc: 3/0xefffffff, 3/pid: 3/0xeffffffc,
                 4/user: 3/0xeffffffd, 5/mnt: 3/0xf0000000, 6/cgroup: 3/0xeffffffb]

Commiter notes:

Testing it:

Investigating that double PERF_RECORD_NAMESPACES for the 19155
pid/tid... Its more than that, there are two PERF_RECORD_COMM as well,
and with zeroed timestamps, so probably a synthesizing artifact...

  # perf script --show-task --show-namespace
  <SNIP>
      perf     0 [000]     0.000000: PERF_RECORD_COMM: perf:19154/19154
      perf     0 [000]     0.000000: PERF_RECORD_FORK(19155:19155):(19154:19154)
      perf     0 [000]     0.000000: PERF_RECORD_NAMESPACES 19155/19155 - nr_namespaces: 7
          [0/net: 3/0xf0000081, 1/uts: 3/0xeffffffe, 2/ipc: 3/0xefffffff, 3/pid: 3/0xeffffffc,
           4/user: 3/0xeffffffd, 5/mnt: 3/0xf0000000, 6/cgroup: 3/0xeffffffb]
      perf     0 [000]     0.000000: PERF_RECORD_COMM: perf:19155/19155
      perf     0 [000]     0.000000: PERF_RECORD_COMM: perf:19155/19155
      perf     0 [000]     0.000000: PERF_RECORD_NAMESPACES 19155/19155 - nr_namespaces: 7
          [0/net: 3/0xf0000081, 1/uts: 3/0xeffffffe, 2/ipc: 3/0xefffffff, 3/pid: 3/0xeffffffc,
           4/user: 3/0xeffffffd, 5/mnt: 3/0xf0000000, 6/cgroup: 3/0xeffffffb]
   swapper     0 [000]  3110.881834:          1 cycles:  ffffffffa7060bf6 native_write_msr (/lib/modules/4.11.0-rc1+/build/vmlinux)

  <SNIP>
Signed-off-by: NHari Bathini <hbathini@linux.vnet.ibm.com>
Tested-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: NJiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Starovoitov <ast@fb.com>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Aravinda Prasad <aravinda@linux.vnet.ibm.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sargun Dhillon <sargun@sargun.me>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/148891932627.25309.1941587059154176221.stgit@hbathini.in.ibm.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      96a44bbc
  29. 14 3月, 2017 1 次提交
    • H
      perf tools: Add PERF_RECORD_NAMESPACES to include namespaces related info · f3b3614a
      由 Hari Bathini 提交于 
      Introduce a new option to record PERF_RECORD_NAMESPACES events emitted
by the kernel when fork, clone, setns or unshare are invoked. And update
perf-record documentation with the new option to record namespace
events.

Committer notes:

Combined it with a later patch to allow printing it via 'perf report -D'
and be able to test the feature introduced in this patch. Had to move
here also perf_ns__name(), that was introduced in another later patch.

Also used PRIu64 and PRIx64 to fix the build in some enfironments wrt:

  util/event.c:1129:39: error: format '%lx' expects argument of type 'long unsigned int', but argument 6 has type 'long long unsigned int' [-Werror=format=]
     ret  += fprintf(fp, "%u/%s: %lu/0x%lx%s", idx
                                         ^
Testing it:

  # perf record --namespaces -a
  ^C[ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 1.083 MB perf.data (423 samples) ]
  #
  # perf report -D
  <SNIP>
  3 2028902078892 0x115140 [0xa0]: PERF_RECORD_NAMESPACES 14783/14783 - nr_namespaces: 7
                [0/net: 3/0xf0000081, 1/uts: 3/0xeffffffe, 2/ipc: 3/0xefffffff, 3/pid: 3/0xeffffffc,
                 4/user: 3/0xeffffffd, 5/mnt: 3/0xf0000000, 6/cgroup: 3/0xeffffffb]

  0x1151e0 [0x30]: event: 9
  .
  . ... raw event: size 48 bytes
  .  0000:  09 00 00 00 02 00 30 00 c4 71 82 68 0c 7f 00 00  ......0..q.h....
  .  0010:  a9 39 00 00 a9 39 00 00 94 28 fe 63 d8 01 00 00  .9...9...(.c....
  .  0020:  03 00 00 00 00 00 00 00 ce c4 02 00 00 00 00 00  ................
  <SNIP>
        NAMESPACES events:          1
  <SNIP>
  #
Signed-off-by: NHari Bathini <hbathini@linux.vnet.ibm.com>
Acked-by: NJiri Olsa <jolsa@kernel.org>
Tested-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Starovoitov <ast@fb.com>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Aravinda Prasad <aravinda@linux.vnet.ibm.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sargun Dhillon <sargun@sargun.me>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/148891930386.25309.18412039920746995488.stgit@hbathini.in.ibm.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      f3b3614a
  31. 13 3月, 2017 1 次提交
  33. 04 3月, 2017 3 次提交
    • N
      perf ftrace: Add support for -a and -C option · dc231032
      由 Namhyung Kim 提交于 
      The -a/--all-cpus and -C/--cpu option is for controlling tracing cpus.
Signed-off-by: NNamhyung Kim <namhyung@kernel.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: kernel-team@lge.com
Link: http://lkml.kernel.org/r/20170224011251.14946-3-namhyung@kernel.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      dc231032
    • N
      perf ftrace: Add support for --pid option · a9af6be5
      由 Namhyung Kim 提交于 
      The -p (--pid) option enables to trace existing process by its pid.

Committer notes:

Testing it:

Using the function_graph tracer on a process that is just waiting for user
input and thus will make 'perf ftrace' sit there waiting for that, then press
any key on that mutt session and see what happens:

  # perf ftrace -t function_graph -p `pidof mutt` | head -40
  2)   1.038 us    |  switch_mm_irqs_off();
  ------------------------------------------
  2)    <idle>-0    =>   mutt-3595
  ------------------------------------------

  2)               |              finish_task_switch() {
  2)               |                smp_irq_work_interrupt() {
  2)               |                  irq_enter() {
  2)   0.180 us    |                    rcu_irq_enter();
  2)   1.248 us    |                  }
  2)               |                  __wake_up() {
  2)   0.126 us    |                    _raw_spin_lock_irqsave();
  2)               |                    __wake_up_common() {
  2)               |                      pollwake() {
  2)               |                        default_wake_function() {
  2)               |                          try_to_wake_up() {
  2)   0.662 us    |                            _raw_spin_lock_irqsave();
  2)               |                            select_task_rq_fair() {
  2)   1.719 us    |                              effective_load.isra.41();
  2)   1.343 us    |                              effective_load.isra.41();
  2)               |                              select_idle_sibling() {
  2)   0.331 us    |                                idle_cpu();
  2)   1.458 us    |                              }
  2)   8.350 us    |                            }
  2)   0.200 us    |                            _raw_spin_lock();
  2)               |                            ttwu_do_activate() {
  2)               |                              activate_task() {
  2)   0.136 us    |                                update_rq_clock.part.77();
  2)               |                                enqueue_task_fair() {
  2)               |                                  enqueue_entity() {
  2)   0.146 us    |                                    update_curr();
  2)   0.330 us    |                                    account_entity_enqueue();
  2)   0.280 us    |                                    update_cfs_shares();
  2)   0.321 us    |                                    place_entity();
  2)   0.206 us    |                                    __enqueue_entity();
  2)   6.926 us    |                                  }
  2)               |                                  enqueue_entity() {
  2)   0.105 us    |                                    update_curr();
  2)   0.175 us    |                                    account_entity_enqueue();
  2)   0.531 us    |                                    update_cfs_shares();
 #
Signed-off-by: NNamhyung Kim <namhyung@kernel.org>
Tested-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: kernel-team@lge.com
Link: http://lkml.kernel.org/r/20170224011251.14946-1-namhyung@kernel.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      a9af6be5
    • C
      perf tools: Allow sorting by symbol size · 7768f8da
      由 Charles Baylis 提交于 
      Add new sort key 'symbol_size' to allow user to sort by symbol size, or
(more usefully) display the symbol size using --fields=...,symbol_size.

Committer note:

Testing it together with the recently added -q, to remove the headers,
and using the '+' sign with -s, to add the symbol_size sort order to
the default, which is '-s/--sort comm,dso,symbol':

  # perf report -q -s +symbol_size | head -10
  10.39%  swapper       [kernel.vmlinux] [k] intel_idle               270
   3.45%  swapper       [kernel.vmlinux] [k] update_blocked_averages 1546
   2.61%  swapper       [kernel.vmlinux] [k] update_load_avg         1292
   2.36%  swapper       [kernel.vmlinux] [k] update_cfs_shares        240
   1.83%  swapper       [kernel.vmlinux] [k] __hrtimer_run_queues     606
   1.74%  swapper       [kernel.vmlinux] [k] update_cfs_rq_load_avg. 1187
   1.66%  swapper       [kernel.vmlinux] [k] apic_timer_interrupt     152
   1.60%  CPU 0/KVM     [kvm]            [k] kvm_set_msr_common      3046
   1.60%  gnome-shell   libglib-2.0.so.0 [.] g_slist_find              37
   1.46%  gnome-termina libglib-2.0.so.0 [.] g_hash_table_lookup      370
  #
Signed-off-by: NCharles Baylis <charles.baylis@linaro.org>
Tested-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Maxim Kuvyrkov <maxim.kuvyrkov@linaro.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1487943176-13840-1-git-send-email-charles.baylis@linaro.org
[ Use symbol__size(), remove needless %lld + (long long) casting ]
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      7768f8da
  35. 28 2月, 2017 1 次提交
  37. 20 2月, 2017 3 次提交
    • N
      perf annotate: Add -q/--quiet option · eddaef88
      由 Namhyung Kim 提交于 
      The -q/--quiet option is to suppress any message.  Sometimes users just
want to see the numbers and it can be used for that case.
Signed-off-by: NNamhyung Kim <namhyung@kernel.org>
Suggested-and-Tested-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: kernel-team@lge.com
Link: http://lkml.kernel.org/r/20170217081742.17417-6-namhyung@kernel.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      eddaef88
    • N
      perf diff: Add -q/--quiet option · 63b42fce
      由 Namhyung Kim 提交于 
      The -q/--quiet option is to suppress any message.  Sometimes users just
want to see the numbers and it can be used for that case.

Committer notes:

Before:

  # perf diff | head -10
  Failed to open /tmp/perf-6678.map, continuing without symbols
  Failed to open /tmp/perf-6678.map, continuing without symbols
  Failed to open /tmp/perf-2646.map, continuing without symbols
  # Event 'cycles'
  #
  # Baseline  Delta Abs  Shared Object               Symbol
  # ........  .........  ..........................  ............................................
  #
       5.36%     -1.76%  [kernel.vmlinux]            [k] intel_idle
       2.80%     +1.48%  firefox                     [.] 0x00000000000101fe
      57.12%     -1.25%  libxul.so                   [.] 0x00000000009bea92
       1.36%     -1.11%  [kernel.vmlinux]            [k] __schedule
       4.26%     -1.00%  perf-6678.map               [.] 0x00007fac4b0e9320

After:

  # perf diff -q | head -10
       5.36%     -1.76%  [kernel.vmlinux]            [k] intel_idle
       2.80%     +1.48%  firefox                     [.] 0x00000000000101fe
      57.12%     -1.25%  libxul.so                   [.] 0x00000000009bea92
       1.36%     -1.11%  [kernel.vmlinux]            [k] __schedule
       4.26%     -1.00%  perf-6678.map               [.] 0x00007fac4b0e9320
       1.86%     +0.95%  [kernel.vmlinux]            [k] update_blocked_averages
       0.80%     -0.70%  [kernel.vmlinux]            [k] native_sched_clock
       0.74%     -0.58%  [kernel.vmlinux]            [k] native_write_msr
       0.76%     -0.56%  qemu-system-x86_64          [.] 0x00000000002395c0
                 +0.54%  libpulsecommon-10.0.so      [.] 0x000000000002d91b
  #
Signed-off-by: NNamhyung Kim <namhyung@kernel.org>
Suggested-and-Tested-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: kernel-team@lge.com
Link: http://lkml.kernel.org/r/20170217081742.17417-5-namhyung@kernel.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      63b42fce
    • N
      perf report: Add -q/--quiet option · 27fafab5
      由 Namhyung Kim 提交于 
      The -q/--quiet option is to suppress any message.  Sometimes users just
want to see the numbers and it can be used for that case.

Before:

  $ perf report | head -15
  Failed to open /lib/modules/3.19.3-3-ARCH/kernel/fs/ext4/ext4.ko.gz, continuing without symbols
  Failed to open /lib/modules/3.19.3-3-ARCH/kernel/fs/jbd2/jbd2.ko.gz, continuing without symbols
  Failed to open /tmp/perf-14507.map, continuing without symbols
  ...
  # To display the perf.data header info, please use --header/--header-only options.
  #
  #
  # Total Lost Samples: 0
  #
  # Samples: 39K of event 'cycles'
  # Event count (approx.): 30444796573
  #
  # Overhead  Command      Shared Object        Symbol
  # ........  ...........  ...................  .........................
  #
       9.28%  swapper	   [kernel.vmlinux]     [k] intel_idle
       5.64%  swapper	   [kernel.vmlinux]     [k] native_write_msr_safe
       1.93%  swapper	   [kernel.vmlinux]     [k] __switch_to
       1.89%  swapper	   [kernel.vmlinux]     [k] menu_select
       1.75%  sched-pipe   [kernel.vmlinux]     [k] __switch_to

After:

  $ perf report -q | head
       9.28%  swapper	   [kernel.vmlinux]     [k] intel_idle
       5.64%  swapper	   [kernel.vmlinux]     [k] native_write_msr_safe
       1.93%  swapper	   [kernel.vmlinux]     [k] __switch_to
       1.89%  swapper	   [kernel.vmlinux]     [k] menu_select
       1.75%  sched-pipe   [kernel.vmlinux]     [k] __switch_to
       1.67%  swapper	   [kernel.vmlinux]     [k] cpu_startup_entry
       1.48%  sched-pipe   [kernel.vmlinux]     [k] enqueue_entity
       1.46%  swapper	   [kernel.vmlinux]     [k] __schedule
       1.36%  swapper	   [kernel.vmlinux]     [k] native_read_tsc
       1.34%  sched-pipe   [kernel.vmlinux]     [k] __schedule
Signed-off-by: NNamhyung Kim <namhyung@kernel.org>
Suggested-and-Tested-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: kernel-team@lge.com
Link: http://lkml.kernel.org/r/20170217081742.17417-4-namhyung@kernel.org
[ Removed builtin-report.c verbose > 0 hunk added to the previous patch ]
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      27fafab5
  39. 18 2月, 2017 2 次提交
  41. 14 2月, 2017 1 次提交