1. 21 Dec, 2010 4 commits
    • Masami Hiramatsu's avatar
      perf probe: Cleanup messages · 0e43e5d2
      Masami Hiramatsu authored
      
      
      Add new lines for error or debug messages, change dwarf related words to more
      generic words (or just removed).
      
      Cc: 2nddept-manager@sdl.hitachi.co.jp
      Cc: Ingo Molnar <mingo@elte.hu>
      Cc: Paul Mackerras <paulus@samba.org>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
      Cc: Steven Rostedt <rostedt@goodmis.org>
      LKML-Reference: <20101217131211.24123.40437.stgit@ltc236.sdl.hitachi.co.jp>
      Signed-off-by: default avatarMasami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
      Signed-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      0e43e5d2
    • David Ahern's avatar
      perf symbols: Add symfs option for off-box analysis using specified tree · ec5761ea
      David Ahern authored
      
      
      The symfs argument allows analysis of perf.data file using a locally accessible
      filesystem tree with debug symbols - e.g., tree created during image builds,
      sshfs mount, loop mounted KVM disk images, USB keys, initrds, etc. Anything
      with an OS tree can be analyzed from anywhere without the need to populate a
      local data store with build-ids.
      
      Commiter notes:
      
      o Fixed up symfs="/" variants handling.
      
      o prefixed DSO__ORIG_GUEST_KMODULE case with symfs too, avoiding use of files
        outside the symfs directory.
      
      LKML-Reference: <1291926427-28846-1-git-send-email-daahern@cisco.com>
      Signed-off-by: default avatarDavid Ahern <daahern@cisco.com>
      Signed-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      ec5761ea
    • Ian Munsie's avatar
      perf record,report,annotate,diff: Process events in order · eac23d1c
      Ian Munsie authored
      
      
      This patch changes perf report to ask for the ID info on all events be
      default if recording from multiple CPUs.
      
      Perf report, annotate and diff will now process the events in order if
      the kernel is able to provide timestamps on all events. This ensures
      that events such as COMM and MMAP which are necessary to correctly
      interpret samples are processed prior to those samples so that they are
      attributed correctly.
      
      Before:
       # perf record ./cachetest
       # perf report
      
       # Events: 6K cycles
       #
       # Overhead  Command      Shared Object                           Symbol
       # ........  .......  .................  ...............................
       #
           74.11%    :3259  [unknown]          [k] 0x4a6c
            1.50%  cachetest  ld-2.11.2.so       [.] 0x1777c
            1.46%    :3259  [kernel.kallsyms]  [k] .perf_event_mmap_ctx
            1.25%    :3259  [kernel.kallsyms]  [k] restore
            0.74%    :3259  [kernel.kallsyms]  [k] ._raw_spin_lock
            0.71%    :3259  [kernel.kallsyms]  [k] .filemap_fault
            0.66%    :3259  [kernel.kallsyms]  [k] .memset
            0.54%  cachetest  [kernel.kallsyms]  [k] .sha_transform
            0.54%    :3259  [kernel.kallsyms]  [k] .copy_4K_page
            0.54%    :3259  [kernel.kallsyms]  [k] .find_get_page
            0.52%    :3259  [kernel.kallsyms]  [k] .trace_hardirqs_off
            0.50%    :3259  [kernel.kallsyms]  [k] .__do_fault
      <SNIP>
      
      After:
       # perf report
      
       # Events: 6K cycles
       #
       # Overhead  Command      Shared Object                           Symbol
       # ........  .......  .................  ...............................
       #
           44.28%  cachetest  cachetest          [.] sumArrayNaive
           22.53%  cachetest  cachetest          [.] sumArrayOptimal
            6.59%  cachetest  ld-2.11.2.so       [.] 0x1777c
            2.13%  cachetest  [unknown]          [k] 0x340
            1.46%  cachetest  [kernel.kallsyms]  [k] .perf_event_mmap_ctx
            1.25%  cachetest  [kernel.kallsyms]  [k] restore
            0.74%  cachetest  [kernel.kallsyms]  [k] ._raw_spin_lock
            0.71%  cachetest  [kernel.kallsyms]  [k] .filemap_fault
            0.66%  cachetest  [kernel.kallsyms]  [k] .memset
            0.54%  cachetest  [kernel.kallsyms]  [k] .copy_4K_page
            0.54%  cachetest  [kernel.kallsyms]  [k] .find_get_page
            0.54%  cachetest  [kernel.kallsyms]  [k] .sha_transform
            0.52%  cachetest  [kernel.kallsyms]  [k] .trace_hardirqs_off
            0.50%  cachetest  [kernel.kallsyms]  [k] .__do_fault
      <SNIP>
      
      Cc: Frederic Weisbecker <fweisbec@gmail.com>
      Cc: Ingo Molnar <mingo@elte.hu>
      Cc: Paul Mackerras <paulus@samba.org>
      Cc: Peter Zijlstra <peterz@infradead.org>
      Cc: Thomas Gleixner <tglx@linutronix.de>
      LKML-Reference: <1291872833-839-1-git-send-email-imunsie@au1.ibm.com>
      Signed-off-by: default avatarIan Munsie <imunsie@au1.ibm.com>
      Signed-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      eac23d1c
    • Ian Munsie's avatar
      perf session: Fallback to unordered processing if no sample_id_all · 21ef97f0
      Ian Munsie authored
      
      
      If we are running the new perf on an old kernel without support for
      sample_id_all, we should fall back to the old unordered processing of
      events. If we didn't than we would *always* process events without
      timestamps out of order, whether or not we hit a reordering race. In
      other words, instead of there being a chance of not attributing samples
      correctly, we would guarantee that samples would not be attributed.
      
      While processing all events without timestamps before events with
      timestamps may seem like an intuitive solution, it falls down as
      PERF_RECORD_EXIT events would also be processed before any samples.
      Even with a workaround for that case, samples before/after an exec would
      not be attributed correctly.
      
      This patch allows commands to indicate whether they need to fall back to
      unordered processing, so that commands that do not care about timestamps
      on every event will not be affected. If we do fallback, this will print
      out a warning if report -D was invoked.
      
      This patch adds the test in perf_session__new so that we only need to
      test once per session. Commands that do not use an event_ops (such as
      record and top) can simply pass NULL in it's place.
      Acked-by: default avatarThomas Gleixner <tglx@linutronix.de>
      Cc: Frederic Weisbecker <fweisbec@gmail.com>
      Cc: Ingo Molnar <mingo@elte.hu>
      Cc: Peter Zijlstra <peterz@infradead.org>
      Cc: Thomas Gleixner <tglx@linutronix.de>
      LKML-Reference: <1291951882-sup-6069@au1.ibm.com>
      Signed-off-by: default avatarIan Munsie <imunsie@au1.ibm.com>
      Signed-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      21ef97f0
  2. 16 Dec, 2010 9 commits
  3. 13 Dec, 2010 1 commit
  4. 09 Dec, 2010 15 commits
  5. 08 Dec, 2010 6 commits
  6. 07 Dec, 2010 5 commits