1. 23 7月, 2009 3 次提交
    • J
      perf_counter: Add tracepoint support to perf list, perf stat · f6bdafef
      Jason Baron 提交于
      Add support to 'perf list' and 'perf stat' for kernel tracepoints. The
      implementation creates a 'for_each_subsystem' and 'for_each_event' for
      easy iteration over the tracepoints.
      Signed-off-by: NJason Baron <jbaron@redhat.com>
      Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
      LKML-Reference: <426129bf9fcc8ee63bb094cf736e7316a7dcd77a.1248190728.git.jbaron@redhat.com>
      f6bdafef
    • A
      perf symbol: C++ demangling · 28ac909b
      Arnaldo Carvalho de Melo 提交于
      [acme@doppio ~]$ perf report -s comm,dso,symbol -C firefox -d /usr/lib64/xulrunner-1.9.1/libxul.so | grep :: | head
           2.21%  [.] nsDeque::Push(void*)
           1.78%  [.] GraphWalker::DoWalk(nsDeque&)
           1.30%  [.] GCGraphBuilder::AddNode(void*, nsCycleCollectionParticipant*)
           1.27%  [.] XPCWrappedNative::CallMethod(XPCCallContext&, XPCWrappedNative::CallMode)
           1.18%  [.] imgContainer::DrawFrameTo(gfxIImageFrame*, gfxIImageFrame*, nsRect&)
           1.13%  [.] nsDeque::PopFront()
           1.11%  [.] nsGlobalWindow::RunTimeout(nsTimeout*)
           0.97%  [.] nsXPConnect::Traverse(void*, nsCycleCollectionTraversalCallback&)
           0.95%  [.] nsJSEventListener::cycleCollection::Traverse(void*, nsCycleCollectionTraversalCallback&)
           0.95%  [.] nsCOMPtr_base::~nsCOMPtr_base()
      [acme@doppio ~]$
      
      Cc: Pekka Enberg <penberg@cs.helsinki.fi>
      Cc: Vegard Nossum <vegard.nossum@gmail.com>
      Cc: Paul Mackerras <paulus@samba.org>
      Cc: Frédéric Weisbecker <fweisbec@gmail.com>
      Suggested-by: NClark Williams <williams@redhat.com>
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
      LKML-Reference: <20090720171412.GB10410@ghostprotocols.net>
      28ac909b
    • A
      perf: avoid structure size confusion by using a fixed size · dfe5a504
      Arjan van de Ven 提交于
      for some reason, this structure gets compiled as 36 bytes in some files
      (the ones that alloacte it) but 40 bytes in others (the ones that use it).
      The cause is an off_t type that gets a different size in different
      compilation units for some yet-to-be-explained reason.
      
      But the effect is disasterous; the size/offset members of the struct
      are at different offsets, and result in mostly complete garbage.
      The parser in perf is so robust that this all gets hidden, and after
      skipping an certain amount of samples, it recovers.... so this bug
      is not normally noticed.
      
      .... except when you want every sample to be exact.
      
      Fix this by just using an explicitly sized type.
      Signed-off-by: NArjan van de Ven <arjan@linux.intel.com>
      Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
      LKML-Reference: <4A655917.9080504@linux.intel.com>
      dfe5a504
  2. 13 7月, 2009 1 次提交
  3. 12 7月, 2009 2 次提交
    • A
      perf_counter tools: PLT info is stripped in -debuginfo packages · a25e46c4
      Arnaldo Carvalho de Melo 提交于
      So we need to get the richer .symtab from the debuginfo
      packages but the PLT info from the original DSO where we have
      just the leaner .dynsym symtab.
      
      Example:
      
      | [acme@doppio pahole]$ perf report --sort comm,dso,symbol > before
      | [acme@doppio pahole]$ perf report --sort comm,dso,symbol > after
      | [acme@doppio pahole]$ diff -U1 before after
      | --- before	2009-07-11 11:04:22.688595741 -0300
      | +++ after	2009-07-11 11:04:33.380595676 -0300
      | @@ -80,3 +80,2 @@
      |       0.07%  pahole ./build/pahole              [.] pahole_stealer
      | -     0.06%  pahole /usr/lib64/libdw-0.141.so   [.] 0x00000000007140
      |       0.06%  pahole /usr/lib64/libdw-0.141.so   [.] __libdw_getabbrev
      | @@ -91,2 +90,3 @@
      |       0.06%  pahole [kernel]                    [k] free_hot_cold_page
      | +     0.06%  pahole /usr/lib64/libdw-0.141.so   [.] tfind@plt
      |       0.05%  pahole ./build/libdwarves.so.1.0.0 [.] ftype__add_parameter
      | @@ -242,2 +242,3 @@
      |       0.01%  pahole [kernel]                    [k] account_group_user_time
      | +     0.01%  pahole /usr/lib64/libdw-0.141.so   [.] strlen@plt
      |       0.01%  pahole ./build/pahole              [.] strcmp@plt
      | [acme@doppio pahole]$
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      LKML-Reference: <1247325517-12272-4-git-send-email-acme@redhat.com>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      a25e46c4
    • A
      strlist: Introduce strlist__entry and strlist__nr_entries methods · 27d0fd41
      Arnaldo Carvalho de Melo 提交于
      The strlist__entry method allows accessing strlists like an
      array, will be used in the 'perf report' to access the first
      entry.
      
      We now keep the nr_entries so that we can check if we have just
      one entry, will be used in 'perf report' to improve the output
      by showing just at the top when we have just, say, one DSO.
      
      While at it use nr_entries to optimize strlist__is_empty by not
      using the far more costly rb_first based implementation.
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      LKML-Reference: <1247325517-12272-2-git-send-email-acme@redhat.com>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      27d0fd41
  4. 11 7月, 2009 1 次提交
    • A
      perf report: Adjust column width to the values sampled · 52d422de
      Arnaldo Carvalho de Melo 提交于
      Auto-adjust column width of perf report output to the
      longest occuring string length.
      
      Example:
      
      [acme@doppio pahole]$  perf report --sort comm,dso,symbol | head -13
      
          12.79%   pahole  /usr/lib64/libdw-0.141.so    [.] __libdw_find_attr
           8.90%   pahole  /lib64/libc-2.10.1.so        [.] _int_malloc
           8.68%   pahole  /usr/lib64/libdw-0.141.so    [.] __libdw_form_val_len
           8.15%   pahole  /lib64/libc-2.10.1.so        [.] __GI_strcmp
           6.80%   pahole  /lib64/libc-2.10.1.so        [.] __tsearch
           5.54%   pahole  ./build/libdwarves.so.1.0.0  [.] tag__recode_dwarf_type
      [acme@doppio pahole]$
      
      [acme@doppio pahole]$  perf report --sort comm,dso,symbol -d /lib64/libc-2.10.1.so | head -10
      
          21.92%   pahole  /lib64/libc-2.10.1.so  [.] _int_malloc
          20.08%   pahole  /lib64/libc-2.10.1.so  [.] __GI_strcmp
          16.75%   pahole  /lib64/libc-2.10.1.so  [.] __tsearch
      [acme@doppio pahole]$
      
      Also add these extra options to control the new behaviour:
      
        -w, --field-width
      
      Force each column width to the provided list, for large terminal
      readability.
      
        -t, --field-separator:
      
      Use a special separator character and don't pad with spaces, replacing
      all occurances of this separator in symbol names (and other output) with
      a '.' character, that thus it's the only non valid separator.
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      Cc: Frederic Weisbecker <fweisbec@gmail.com>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Paul Mackerras <paulus@samba.org>
      LKML-Reference: <20090711014728.GH3452@ghostprotocols.net>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      52d422de
  5. 10 7月, 2009 1 次提交
  6. 05 7月, 2009 2 次提交
    • F
      perf report: Add "Fractal" mode output - support callchains with relative overhead rate · 805d127d
      Frederic Weisbecker 提交于
      The current callchain displays the overhead rates as absolute:
      relative to the total overhead.
      
      This patch provides relative overhead percentage, in which each
      branch of the callchain tree is a independant instrumentated object.
      
      This provides a 'fractal' view of the call-chain profile: each
      sub-graph looks like a profile in itself - relative to its parent.
      
      You can produce such output by using the "fractal" mode
      that you can abbreviate via f, fr, fra, frac, etc...
      
      ./perf report -s sym -c fractal
      
      Example:
      
           8.46%  [k] copy_user_generic_string
                      |
                      |--52.01%-- generic_file_aio_read
                      |          do_sync_read
                      |          vfs_read
                      |          |
                      |          |--97.20%-- sys_pread64
                      |          |          system_call_fastpath
                      |          |          pread64
                      |          |
                      |           --2.81%-- sys_read
                      |                     system_call_fastpath
                      |                     __read
                      |
                      |--39.85%-- generic_file_buffered_write
                      |          __generic_file_aio_write_nolock
                      |          generic_file_aio_write
                      |          do_sync_write
                      |          reiserfs_file_write
                      |          vfs_write
                      |          |
                      |          |--97.05%-- sys_pwrite64
                      |          |          system_call_fastpath
                      |          |          __pwrite64
                      |          |
                      |           --2.95%-- sys_write
                      |                     system_call_fastpath
                      |                     __write_nocancel
      [...]
      Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Paul Mackerras <paulus@samba.org>
      Cc: Anton Blanchard <anton@samba.org>
      Cc: Jens Axboe <jens.axboe@oracle.com>
      Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
      LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      805d127d
    • F
      perf_counter tools: callchains: Manage the cumul hits on the fly · e05b876c
      Frederic Weisbecker 提交于
      The cumul hits are the number of hits of every childs of a node
      plus the hits of the current nodes, required for percentage
      computing of a branch.
      
      Theses numbers are calculated during the sorting of the branches of
      the callchain tree using a depth first postfix traversal, so that
      cumulative hits are propagated in the right order.
      
      But if we plan to implement percentages relative to the parent and not
      absolute percentages (relative to the whole overhead), we need to know
      the cumulative hits of the parent before computing the children
      because the relative minimum acceptable number of entries (ie: minimum
      rate against the cumulative hits from the parent) is the basis to
      filter the children against a given rate.
      
      Then we need to handle the cumul hits on the fly to prepare the
      implementation of relative overhead rates.
      Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Paul Mackerras <paulus@samba.org>
      Cc: Anton Blanchard <anton@samba.org>
      Cc: Jens Axboe <jens.axboe@oracle.com>
      Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
      LKML-Reference: <1246772361-9960-4-git-send-email-fweisbec@gmail.com>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      e05b876c
  7. 03 7月, 2009 6 次提交
    • A
      perf_counter tools: Adjust symbols in ET_EXEC files too · 30d7a77d
      Arnaldo Carvalho de Melo 提交于
      Ingo Molnar wrote:
      
      > i just bisected a 'perf report' bug that would cause us to not
      > resolve all user-space symbols in a 'git gc' run to:
      >
      > f5812a7a is first bad commit
      > commit f5812a7a
      > Author: Arnaldo Carvalho de Melo <acme@redhat.com>
      > Date:   Tue Jun 30 11:43:17 2009 -0300
      >
      >     perf_counter tools: Adjust only prelinked symbol's addresses
      
      Rename ->prelinked to ->adjust_symbols and making what was done
      only for prelinked libraries also to ET_EXEC binaries, such as
      /usr/bin/git:
      
      [acme@doppio pahole]$ readelf -h /usr/bin/git | grep Type
        Type:                              EXEC (Executable file)
      [acme@doppio pahole]$
      
      And after installing the 'git-debuginfo' package, I get correct results:
      
      [acme@doppio linux-2.6-tip]$ perf report --sort comm,dso,symbol -d /usr/bin/git | head -20
      
       #
       # (1139614 samples)
       #
       # Overhead           Command  Shared Object              Symbol
       # ........  ................  .........................  ......
       #
          34.98%               git  /usr/bin/git               [.] send_sideband
          33.39%               git  /usr/bin/git               [.] enter_repo
           6.81%               git  /usr/bin/git               [.] diff_opt_parse
           4.95%               git  /usr/bin/git               [.] is_repository_shallow
           3.24%               git  /usr/bin/git               [.] odb_mkstemp
           1.39%               git  /usr/bin/git               [.] output
           1.34%               git  /usr/bin/git               [.] xmmap
           1.25%               git  /usr/bin/git               [.] receive_pack_config
           1.16%               git  /usr/bin/git               [.] git_pathdup
           0.90%               git  /usr/bin/git               [.] read_object_with_reference
           0.86%               git  /usr/bin/git               [.] show_patch_diff
           0.85%               git  /usr/bin/git               0x00000000095e2e
           0.69%               git  /usr/bin/git               [.] display
      [acme@doppio linux-2.6-tip]$
      
      I'll check what are the last cases where we can't resolve symbols, like
      this 0x00000000095e2e later.
      
      And I guess this will fix the problems Mike were seeing too:
      
       [acme@doppio linux-2.6-tip]$ readelf -h ../build/perf/vmlinux | grep Type
         Type:                              EXEC (Executable file)
       [acme@doppio linux-2.6-tip]$
      
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Paul Mackerras <paulus@samba.org>
      Cc: Frederic Weisbecker <fweisbec@gmail.com>
      LKML-Reference: <new-submission>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      30d7a77d
    • F
      perf_counter tools: Provide helper to print percents color · 1e11fd82
      Frederic Weisbecker 提交于
      Among perf annotate, perf report and perf top, we can find the
      common colored printing of percents according to the following
      rules:
      
          High overhead =  > 5%, colored in red
          Mid overhead =  > 0.5%, colored in green
          Low overhead =  < 0.5%, default color
      
      Factorize these multiple checks in a single function named
      percent_color_fprintf() and also provide a get_percent_color()
      for sites which print percentages and other things at the same
      time.
      Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Paul Mackerras <paulus@samba.org>
      Cc: Anton Blanchard <anton@samba.org>
      Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
      LKML-Reference: <1246558475-10624-2-git-send-email-fweisbec@gmail.com>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      1e11fd82
    • F
      perf_counter tools: Set the minimum percent for callchains to be displayed · c20ab37e
      Frederic Weisbecker 提交于
      Callchains output may become a burden on a trace because even
      rarely hit site are exposed. This can be too much information.
      
      Let the user set a threshold as a minimum percent of hits using
      the new pattern for the -c option:
      
          -c mode,min_percent
      
      Example:
      
      $ perf report -s sym -c flat,4
      
           8.25%  [k] copy_user_generic_string
                   4.19%
                      copy_user_generic_string
                      generic_file_aio_read
                      do_sync_read
                      vfs_read
                      sys_pread64
                      system_call_fastpath
                      pread64
      
           5.39%  [k] search_by_key
           4.63%  0x00000000009e0a
           2.36%  [k] memcpy_c
      [...]
      
      $ perf report -s sym -c graph,2
      
           8.25%  [k] copy_user_generic_string
                      |
                      |--4.31%-- generic_file_aio_read
                      |          do_sync_read
                      |          vfs_read
                      |          |
                      |           --4.19%-- sys_pread64
                      |                     system_call_fastpath
                      |                     pread64
                      |
                       --3.24%-- generic_file_buffered_write
                                 __generic_file_aio_write_nolock
                                 generic_file_aio_write
                                 do_sync_write
                                 reiserfs_file_write
                                 vfs_write
                                 |
                                  --3.14%-- sys_pwrite64
                                            system_call_fastpath
                                            __pwrite64
      
           5.39%  [k] search_by_key
                      |
                       --2.23%-- reiserfs_update_sd_size
      
           4.63%  0x00000000009e0a
      
           2.36%  [k] memcpy_c
      [...]
      
      You can also omit it and it will default to 0.
      Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Paul Mackerras <paulus@samba.org>
      Cc: Anton Blanchard <anton@samba.org>
      Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
      LKML-Reference: <1246558475-10624-1-git-send-email-fweisbec@gmail.com>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      c20ab37e
    • F
      perf report: Add support for callchain graph output · 4eb3e478
      Frederic Weisbecker 提交于
      Currently, the printing of callchains is done in a single
      vertical level, this is the "flat" mode:
      
      8.25%  [k] copy_user_generic_string
                   4.19%
                      copy_user_generic_string
                      generic_file_aio_read
                      do_sync_read
                      vfs_read
                      sys_pread64
                      system_call_fastpath
                      pread64
      
      This patch introduces a new "graph" mode which provides a
      hierarchical output of factorized paths recursively sorted:
      
       8.25%  [k] copy_user_generic_string
                      |
                      |--4.31%-- generic_file_aio_read
                      |          do_sync_read
                      |          vfs_read
                      |          |
                      |          |--4.19%-- sys_pread64
                      |          |          system_call_fastpath
                      |          |          pread64
                      |          |
                      |           --0.12%-- sys_read
                      |                     system_call_fastpath
                      |                     __read
                      |
                      |--3.24%-- generic_file_buffered_write
                      |          __generic_file_aio_write_nolock
                      |          generic_file_aio_write
                      |          do_sync_write
                      |          reiserfs_file_write
                      |          vfs_write
                      |          |
                      |          |--3.14%-- sys_pwrite64
                      |          |          system_call_fastpath
                      |          |          __pwrite64
                      |          |
                      |           --0.10%-- sys_write
      [...]
      
      The command line has then changed.
      
      By providing the -c option, the callchain will output in the
      flat mode by default.
      
      But you can override it:
      
          perf report -c graph
      
      or
      
          perf report -c flat
      
      You can also pass the abreviated mode:
      
          perf report -c g
      
      or
      
          perf report -c gra
      
      will both make use of the graph mode.
      Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Paul Mackerras <paulus@samba.org>
      Cc: Anton Blanchard <anton@samba.org>
      Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
      LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      4eb3e478
    • F
      perf_counter tools: Add new OPT_CALLBACK_DEFAULT option · 5a4b1817
      Frederic Weisbecker 提交于
      There is no predefined macro to create an option that can have
      a custom value or a default one if none is given.
      
      This patch provides a new helper OPT_CALLBACK_DEFAULT() which
      defines such kind of option.
      
      For example, considering an option -c, we want to get the
      default value in the following cases:
      
          perf command -c -d
          perf command -d -c
      
      And the foo value when it's given:
      
          perf command -c foo -d
          perf command -d -c foo
      
      That's also why PARSE_OPT_LASTARG_DEFAULT is extended here to
      support default values whatever the position of the option, not
      only in the end.
      
      Should it now be renamed to PARSE_OPT_ARG_DEFAULT ?
      Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Paul Mackerras <paulus@samba.org>
      Cc: Anton Blanchard <anton@samba.org>
      Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
      Cc: git@vger.kernel.org
      LKML-Reference: <1246550301-8954-2-git-send-email-fweisbec@gmail.com>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      5a4b1817
    • F
      perf_counter tools: Create new chain_for_each_child() iterator · 14f4654c
      Frederic Weisbecker 提交于
      Iterating through children of a node in the callchain tree
      shows something that may be quite confusing at a first glance.
      The head is the children field of the parent and the list nodes
      are in the brothers field of the children.
      
      This is because the childs are linked to the parent as a list
      of "brothers" using the "children" list of the parent as a
      head:
      
        ---------------
       | Parent (head) |-------------------------------------
        ---------------                                      |
           |                                                 |
        children                                             |
           |                                                 |
        -----------               -----------                |
       | 1st child |---brother---| 2nd child |---brother-----
        -----------               -----------
      
      This makes the following strange pattern often occuring:
      
       list_for_each_entry(child, &parent->children, brothers) {
              // do something with children
       }
      
      Abstract it to chain_for_each_child() to factorize and simplify
      this pattern.
      Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Paul Mackerras <paulus@samba.org>
      Cc: Anton Blanchard <anton@samba.org>
      Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
      LKML-Reference: <1246550301-8954-1-git-send-email-fweisbec@gmail.com>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      14f4654c
  8. 02 7月, 2009 5 次提交
  9. 01 7月, 2009 7 次提交
    • J
      perf list: Add cache events · 73c24cb8
      Jaswinder Singh Rajput 提交于
      After:
      
      $ ./perf list
      
      List of pre-defined events (to be used in -e):
      
        cpu-cycles OR cycles                     [Hardware event]
        instructions                             [Hardware event]
        cache-references                         [Hardware event]
        cache-misses                             [Hardware event]
        branch-instructions OR branches          [Hardware event]
        branch-misses                            [Hardware event]
        bus-cycles                               [Hardware event]
      
        cpu-clock                                [Software event]
        task-clock                               [Software event]
        page-faults OR faults                    [Software event]
        minor-faults                             [Software event]
        major-faults                             [Software event]
        context-switches OR cs                   [Software event]
        cpu-migrations OR migrations             [Software event]
      
        L1-d$-loads                              [Hardware cache event]
        L1-d$-load-misses                        [Hardware cache event]
        L1-d$-stores                             [Hardware cache event]
        L1-d$-store-misses                       [Hardware cache event]
        L1-d$-prefetches                         [Hardware cache event]
        L1-d$-prefetch-misses                    [Hardware cache event]
        L1-i$-loads                              [Hardware cache event]
        L1-i$-load-misses                        [Hardware cache event]
        L1-i$-prefetches                         [Hardware cache event]
        L1-i$-prefetch-misses                    [Hardware cache event]
        LLC-loads                                [Hardware cache event]
        LLC-load-misses                          [Hardware cache event]
        LLC-stores                               [Hardware cache event]
        LLC-store-misses                         [Hardware cache event]
        LLC-prefetches                           [Hardware cache event]
        LLC-prefetch-misses                      [Hardware cache event]
        dTLB-loads                               [Hardware cache event]
        dTLB-load-misses                         [Hardware cache event]
        dTLB-stores                              [Hardware cache event]
        dTLB-store-misses                        [Hardware cache event]
        dTLB-prefetches                          [Hardware cache event]
        dTLB-prefetch-misses                     [Hardware cache event]
        iTLB-loads                               [Hardware cache event]
        iTLB-load-misses                         [Hardware cache event]
        branch-loads                             [Hardware cache event]
        branch-load-misses                       [Hardware cache event]
      
        rNNN                                     [raw hardware event descriptor]
      Signed-off-by: NJaswinder Singh Rajput <jaswinderrajput@gmail.com>
      Cc: Peter Zijlstra <peterz@infradead.org>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Paul Mackerras <paulus@samba.org>
      Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
      Cc: Frederic Weisbecker <fweisbec@gmail.com>
      LKML-Reference: <1246453578.3072.1.camel@ht.satnam>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      73c24cb8
    • I
      perf_counter tools: Add more warnings and fix/annotate them · f37a291c
      Ingo Molnar 提交于
      Enable -Wextra. This found a few real bugs plus a number
      of signed/unsigned type mismatches/uncleanlinesses. It
      also required a few annotations
      
      All things considered it was still worth it so lets try with
      this enabled for now.
      
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Paul Mackerras <paulus@samba.org>
      Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
      Cc: Frederic Weisbecker <fweisbec@gmail.com>
      LKML-Reference: <new-submission>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      f37a291c
    • P
      perf_counter tools: Rework event string parsing/syntax · 61c45981
      Paul Mackerras 提交于
      This reworks the parser for event descriptors to make it more
      consistent in what it accepts.  It is now structured as a
      recursive descent parser for the following grammar:
      
      events		::= event ( ("," | space) space* event )*
      event		::= ( raw_event | numeric_event | symbolic_event |
      		      generic_hw_event ) [ event_modifier ]
      raw_event	::= "r" hex_number
      numeric_event	::= number ":" number
      number		::= decimal_number | "0x" hex_number | "0" octal_number
      symbolic_event	::= string_from_event_symbols_array
      generic_hw_event::= cache_type ( "-" ( cache_op | cache_result ) )*
      event_modifier	::= ":" ( "u" | "k" | "h" )+
      
      with the extra restriction that you can have at most one
      cache_op and at most one cache_result.
      
      We pass the current string pointer by reference (i.e. as a
      const char **) to the various parsing functions so that they
      can advance the pointer to indicate how much they consumed.
      They return 0 if they didn't recognize the thing at the pointer
      or 1 if they did (and advance the pointer past it).
      
      This also fixes parse_aliases to take the longest matching
      alias from the table, not the first one.  Otherwise "l1-data"
      would match the "l1-d" alias and the "ata" would not be
      consumed.
      
      This allows event modifiers indicating what processor modes to
      count in to be applied to any event, not just numeric events,
      and adds a ":h" modifier to indicate counting in hypervisor
      mode.  Specifying ":u" now sets both exclude_kernel and
      exclude_hv, and so on.  Multiple modes can be specified, e.g.
      ":uk" will count in user or hypervisor mode (i.e. only
      exclude_kernel will be set).
      Signed-off-by: NPaul Mackerras <paulus@samba.org>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Paul Mackerras <paulus@samba.org>
      Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
      Cc: Frederic Weisbecker <fweisbec@gmail.com>
      LKML-Reference: <19018.53826.843815.189847@cargo.ozlabs.ibm.com>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      61c45981
    • F
      perf_counter tools: Various fixes for callchains · deac911c
      Frederic Weisbecker 提交于
      The symbol resolving has of course revealed some bugs in the
      callchain tree handling. This patch fixes some of them,
      including:
      
      - inherit the children from the parents while splitting a node
      - fix list range moving
      - fix indexes setting in callchains
      - create a child on the current node if the path doesn't match in
        the existent children (was only done on the root)
      - compare using symbols when possible so that we can match a function
        using any ip inside by referring to its start address.
      
      The practical effects are:
      
      - remove double callchains
      - fix upside down or any random order of callchains
      - fix wrong paths
      - fix bad hits and percentage accounts
      Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Paul Mackerras <paulus@samba.org>
      Cc: Anton Blanchard <anton@samba.org>
      Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
      LKML-Reference: <1246419315-9968-4-git-send-email-fweisbec@gmail.com>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      deac911c
    • F
      perf_counter tools: Resolve symbols in callchains · 4424961a
      Frederic Weisbecker 提交于
      This patch resolves the names, when possible, of each ip
      present in the callchains while using the -c option with perf
      report.
      
      Example:
      
      5.40%  [k] __d_lookup
                   5.37%
                      perf_callchain
                      perf_counter_overflow
                      intel_pmu_handle_irq
                      perf_counter_nmi_handler
                      notifier_call_chain
                      atomic_notifier_call_chain
                      notify_die
                      do_nmi
                      nmi
                      do_lookup
                      __link_path_walk
                      path_walk
                      do_path_lookup
                      user_path_at
                      sys_faccessat
                      sys_access
                      system_call_fastpath
                      0x7fb609846f77
      
                   0.01%
                      perf_callchain
                      perf_counter_overflow
                      intel_pmu_handle_irq
                      perf_counter_nmi_handler
                      notifier_call_chain
                      atomic_notifier_call_chain
                      notify_die
                      do_nmi
                      nmi
                      do_lookup
                      __link_path_walk
                      path_walk
                      do_path_lookup
                      user_path_at
                      sys_faccessat
      Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Paul Mackerras <paulus@samba.org>
      Cc: Anton Blanchard <anton@samba.org>
      Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
      LKML-Reference: <1246419315-9968-3-git-send-email-fweisbec@gmail.com>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      4424961a
    • F
      perf_counter tools: Fix storage size allocation of callchain list · 9198aa77
      Frederic Weisbecker 提交于
      Fix a confusion while giving the size of a callchain list
      during its allocation. We are using the wrong structure size.
      Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Paul Mackerras <paulus@samba.org>
      Cc: Anton Blanchard <anton@samba.org>
      Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
      LKML-Reference: <1246419315-9968-2-git-send-email-fweisbec@gmail.com>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      9198aa77
    • A
      perf report: Add --dsos parameter · 25903407
      Arnaldo Carvalho de Melo 提交于
      So that we can filter by dso. Symbols in other dsos won't be
      accounted for.
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Peter Zijlstra <peterz@infradead.org>
      Cc: Paul Mackerras <paulus@samba.org>
      LKML-Reference: <1246399282-20934-2-git-send-email-acme@redhat.com>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      25903407
  10. 30 6月, 2009 1 次提交
    • A
      perf_counter tools: Adjust only prelinked symbol's addresses · f5812a7a
      Arnaldo Carvalho de Melo 提交于
      I.e. we can't handle these two kinds of files in the same way:
      
      1) prelinked system library:
      
      [acme@doppio pahole]$ readelf -s /usr/lib64/libdw-0.141.so | egrep 'FUNC.+GLOBAL.+dwfl_report_elf'
         278: 00000030450105a0   261 FUNC    GLOBAL DEFAULT   12 dwfl_report_elf@@ELFUTILS_0.122
      
      2) not prelinked library with debug information from a -debuginfo package:
      
      [acme@doppio pahole]$ readelf -s /usr/lib/debug/usr/lib64/libdw-0.141.so.debug | egrep 'FUNC.+GLOBAL.+dwfl_report_elf'
         629: 00000000000105a0   261 FUNC    GLOBAL DEFAULT   12 dwfl_report_elf
      [acme@doppio pahole]$
      
      Now the numbers I got for a pahole perf run are in line with
      the numbers I get from oprofile.
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      Cc: Peter Zijlstra <peterz@infradead.org>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Paul Mackerras <paulus@samba.org>
      Cc: Frederic Weisbecker <fweisbec@gmail.com>
      LKML-Reference: <20090630144317.GB12663@ghostprotocols.net>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      f5812a7a
  11. 27 6月, 2009 1 次提交
    • I
      perf_counter tools: Remove dead code · fde953c1
      Ingo Molnar 提交于
      Vince Weaver reported that there's a handful of #ifdef __MINGW32__
      sections in the code.
      
      Remove them as they are in essence dead code - as unlike upstream
      Git, the perf tool is unlikely to be ported to Windows.
      Reported-by: NVince Weaver <vince@deater.net>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Paul Mackerras <paulus@samba.org>
      Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
      LKML-Reference: <new-submission>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      fde953c1
  12. 26 6月, 2009 3 次提交
  13. 25 6月, 2009 2 次提交
    • J
      perf_counter tools: Shorten names for events · e5c59547
      Jaswinder Singh Rajput 提交于
      Added new alias for events.
      
      On AMD box:
      
       $ ./perf stat -e l1d -e l1d-misses -e l1d-write -e l1d-prefetch -e l1d-prefetch-miss -e l1i -e l1i-misses -e l1i-prefetch -e l2 -e l2-misses -e l2-write -e dtlb -e dtlb-misses -e itlb -e itlb-misses -e bpu -e bpu-misses -- ls -lR /usr/include/ > /dev/null
      
      Before :
      
       Performance counter stats for 'ls -lR /usr/include/':
      
            248064467  L1-data-Cache-Load-Referencees  (scaled from 23.27%)
              1001433  L1-data-Cache-Load-Misses  (scaled from 23.34%)
               153691  L1-data-Cache-Store-Referencees  (scaled from 23.34%)
               423248  L1-data-Cache-Prefetch-Referencees  (scaled from 23.33%)
               302138  L1-data-Cache-Prefetch-Misses  (scaled from 23.25%)
            251217546  L1-instruction-Cache-Load-Referencees  (scaled from 23.25%)
              5757005  L1-instruction-Cache-Load-Misses  (scaled from 23.23%)
                93435  L1-instruction-Cache-Prefetch-Referencees  (scaled from 23.24%)
              6496073  L2-Cache-Load-Referencees  (scaled from 23.32%)
               609485  L2-Cache-Load-Misses  (scaled from 23.45%)
              6876991  L2-Cache-Store-Referencees  (scaled from 23.71%)
            248922840  Data-TLB-Cache-Load-Referencees  (scaled from 23.94%)
              5828386  Data-TLB-Cache-Load-Misses  (scaled from 24.17%)
            257613506  Instruction-TLB-Cache-Load-Referencees  (scaled from 24.20%)
                 6833  Instruction-TLB-Cache-Load-Misses  (scaled from 23.88%)
            109043606  Branch-Cache-Load-Referencees  (scaled from 23.64%)
              5552296  Branch-Cache-Load-Misses  (scaled from 23.42%)
      
          0.413702461  seconds time elapsed.
      
      After :
      
       Peformance counter stats for 'ls -lR /usr/include/':
      
            266590464  L1-d$-loads           (scaled from 23.03%)
              1222273  L1-d$-load-misses     (scaled from 23.58%)
               146204  L1-d$-stores          (scaled from 23.83%)
               406344  L1-d$-prefetches      (scaled from 24.09%)
               283748  L1-d$-prefetch-misses (scaled from 24.10%)
            249650965  L1-i$-loads           (scaled from 23.80%)
              3353961  L1-i$-load-misses     (scaled from 23.82%)
               104599  L1-i$-prefetches      (scaled from 23.68%)
              4836405  LLC-loads             (scaled from 23.67%)
               498214  LLC-load-misses       (scaled from 23.66%)
              4953994  LLC-stores            (scaled from 23.64%)
            243354097  dTLB-loads            (scaled from 23.77%)
              6468584  dTLB-load-misses      (scaled from 23.74%)
            249719549  iTLB-loads            (scaled from 23.25%)
                 5060  iTLB-load-misses      (scaled from 23.00%)
            112343016  branch-loads          (scaled from 22.76%)
              5528876  branch-load-misses    (scaled from 22.54%)
      
          0.427154051  seconds time elapsed.
      
      Reported-by : Ingo Molnar <mingo@elte.hu>
      Signed-off-by: NJaswinder Singh Rajput <jaswinderrajput@gmail.com>
      Cc: Peter Zijlstra <peterz@infradead.org>
      LKML-Reference: <1245934522.5308.39.camel@hpdv5.satnam>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      e5c59547
    • J
      perf_counter tools: Check for valid cache operations · 06813f6c
      Jaswinder Singh Rajput 提交于
      Made new table for cache operartion stat 'hw_cache_stat' as:
      
       L1I : Read and prefetch only
       ITLB and BPU : Read-only
      
      introduce is_cache_op_valid() for cache operation validity
      
      And checks for valid cache operations.
      
      Reported-by : Ingo Molnar <mingo@elte.hu>
      Signed-off-by: NJaswinder Singh Rajput <jaswinderrajput@gmail.com>
      Cc: Peter Zijlstra <peterz@infradead.org>
      LKML-Reference: <1245930367.5308.33.camel@localhost.localdomain>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      06813f6c
  14. 24 6月, 2009 1 次提交
  15. 22 6月, 2009 4 次提交