1. 15 3月, 2011 8 次提交
    • A
      perf evlist: New command to list the names of events present in a perf.data file · 43adec95
      Arnaldo Carvalho de Melo 提交于
      [root@emilia ~]# perf record -a -e sched:* -e timer:timer* sleep 5
      [ perf record: Woken up 1 times to write data ]
      [ perf record: Captured and wrote 0.172 MB perf.data (~7530 samples) ]
      [root@emilia ~]# perf evlist
      sched:sched_kthread_stop
      sched:sched_kthread_stop_ret
      sched:sched_wakeup
      sched:sched_wakeup_new
      sched:sched_switch
      sched:sched_migrate_task
      sched:sched_process_free
      sched:sched_process_exit
      sched:sched_wait_task
      sched:sched_process_wait
      sched:sched_process_fork
      sched:sched_stat_wait
      sched:sched_stat_sleep
      sched:sched_stat_iowait
      sched:sched_stat_runtime
      sched:sched_pi_setprio
      timer:timer_init
      timer:timer_start
      timer:timer_expire_entry
      timer:timer_expire_exit
      timer:timer_cancel
      [root@emilia ~]#
      
      Cc: Frederic Weisbecker <fweisbec@gmail.com>
      Cc: Ingo Molnar <mingo@elte.hu>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Paul Mackerras <paulus@samba.org>
      Cc: Peter Zijlstra <peterz@infradead.org>
      Cc: Stephane Eranian <eranian@google.com>
      Cc: Tom Zanussi <tzanussi@gmail.com>
      LKML-Reference: <new-submission>
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      43adec95
    • D
      perf script: Add support for H/W and S/W events · 1424dc96
      David Ahern 提交于
      Custom fields set for each type by prepending field argument with type.
      For file with multiple event types (e.g., trace and S/W) display of an
      event type suppressed by setting output fields to "".
      
      e.g.,
      perf record -ga -e sched:sched_switch -e cpu-clock -c 10000000 -R -- sleep 1
      perf script
      
      openssl 11496 [000]  9711.807107: cpu-clock-msecs:
              ffffffff810c22dc arch_local_irq_restore ([kernel.kallsyms])
              ffffffff810c518c __alloc_pages_nodemask ([kernel.kallsyms])
              ffffffff810297b2 pte_alloc_one ([kernel.kallsyms])
              ffffffff810d8b98 __pte_alloc ([kernel.kallsyms])
              ffffffff810daf07 handle_mm_fault ([kernel.kallsyms])
              ffffffff8138763a do_page_fault ([kernel.kallsyms])
              ffffffff81384a65 page_fault ([kernel.kallsyms])
                  7f6130507d70 asn1_check_tlen (/lib64/libcrypto.so.1.0.0c)
                             0  ()
      
               openssl 11496 [000]  9711.808042: sched_switch: prev_comm=openssl ...
           kworker/0:0     4 [000]  9711.808067: sched_switch: prev_comm=kworker/...
               swapper     0 [001]  9711.808090: sched_switch: prev_comm=kworker/...
                  sshd 11451 [001]  9711.808185: sched_switch: prev_comm=sshd pre...
      swapper     0 [001]  9711.816155: cpu-clock-msecs:
              ffffffff81023609 native_safe_halt ([kernel.kallsyms])
              ffffffff8100132a cpu_idle ([kernel.kallsyms])
              ffffffff8137cf9b start_secondary ([kernel.kallsyms])
      
      openssl 11496 [000]  9711.817104: cpu-clock-msecs:
                  7f61304ad723 AES_cbc_encrypt (/lib64/libcrypto.so.1.0.0c)
                  7fff3402f950  ()
              12f0debc9a785634  ()
      
      swapper     0 [001]  9711.826155: cpu-clock-msecs:
              ffffffff81023609 native_safe_halt ([kernel.kallsyms])
              ffffffff8100132a cpu_idle ([kernel.kallsyms])
              ffffffff8137cf9b start_secondary ([kernel.kallsyms])
      
      To suppress trace events within the file and use default output for S/W events:
      perf script -f trace:
      
      or to suppress S/W events and do default display for trace events:
      perf script -f sw:
      
      Custom field selections:
      perf script -f sw:comm,tid,time -f trace:time,trace
      
               openssl 11496  9711.797162:
               swapper     0  9711.807071:
               openssl 11496  9711.807107:
       9711.808042: prev_comm=openssl prev_pid=11496 prev_prio=120 prev_state=R ...
       9711.808067: prev_comm=kworker/0:0 prev_pid=4 prev_prio=120 prev_state=S ...
       9711.808090: prev_comm=kworker/0:0 prev_pid=0 prev_prio=120 prev_state=R ...
       9711.808185: prev_comm=sshd prev_pid=11451 prev_prio=120 prev_state=S ==>...
               swapper     0  9711.816155:
               openssl 11496  9711.817104:
               swapper     0  9711.826155:
      Acked-by: NFrederic Weisbecker <fweisbec@gmail.com>
      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: <1299734608-5223-7-git-send-email-daahern@cisco.com>
      Signed-off-by: NDavid Ahern <daahern@cisco.com>
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      1424dc96
    • D
      perf script: Add support for dumping symbols · c0230b2b
      David Ahern 提交于
      Add option to dump symbols found in events.
      
      e.g., perf script -f comm,pid,tid,time,trace,sym
      
      swapper     0/0       537.037184: prev_comm=swapper prev_pid=0 prev_prio=120...
              ffffffff81030350 perf_trace_sched_switch ([kernel.kallsyms])
              ffffffff81382ac5 schedule ([kernel.kallsyms])
              ffffffff8100134a cpu_idle ([kernel.kallsyms])
              ffffffff81370b39 rest_init ([kernel.kallsyms])
              ffffffff81696c23 start_kernel ([kernel.kallsyms].init.text)
              ffffffff816962af x86_64_start_reservations ([kernel.kallsyms].init.text)
              ffffffff816963b9 x86_64_start_kernel ([kernel.kallsyms].init.text)
      
      sshd  1675/1675    537.037309: prev_comm=sshd prev_pid=1675 prev_prio=120...
              ffffffff81030350 perf_trace_sched_switch ([kernel.kallsyms])
              ffffffff81382ac5 schedule ([kernel.kallsyms])
              ffffffff813837aa schedule_hrtimeout_range_clock ([kernel.kallsyms])
              ffffffff81383886 schedule_hrtimeout_range ([kernel.kallsyms])
              ffffffff8110c4f9 poll_schedule_timeout ([kernel.kallsyms])
              ffffffff8110cd20 do_select ([kernel.kallsyms])
              ffffffff8110ced8 core_sys_select ([kernel.kallsyms])
              ffffffff8110d00d sys_select ([kernel.kallsyms])
              ffffffff81002bc2 system_call ([kernel.kallsyms])
                  7f1647e56e93 __GI_select (/lib64/libc-2.12.90.so)
      
      netstat  1692/1692    537.038664: prev_comm=netstat prev_pid=1692 prev_prio=...
              ffffffff81030350 perf_trace_sched_switch ([kernel.kallsyms])
              ffffffff81382ac5 schedule ([kernel.kallsyms])
              ffffffff81002c3a sysret_careful ([kernel.kallsyms])
                  7f7a6cd1b210 __GI___libc_read (/lib64/libc-2.12.90.so)
      Acked-by: NFrederic Weisbecker <fweisbec@gmail.com>
      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: <1299734608-5223-6-git-send-email-daahern@cisco.com>
      Signed-off-by: NDavid Ahern <daahern@cisco.com>
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      c0230b2b
    • D
      perf script: Support custom field selection for output · 745f43e3
      David Ahern 提交于
      Allow a user to select which fields to print to stdout for event data.
      Options include comm (command name), tid (thread id), pid (process id),
      time (perf timestamp), cpu, event (for event name), and trace (for
      trace data).
      
      Default is set to maintain compatibility with current output; this
      feature does alter output format slightly -- no '-' between command
      and pid/tid.
      
      Thanks to Frederic Weisbecker for detailed suggestions on this approach.
      
      Examples (output compressed)
      
      1. trace, default format
      
      perf record -ga -e sched:sched_switch
      perf script
      
      swapper    0 [000] 537.037184: sched_switch: prev_comm=swapper prev_pid=0...
         sshd 1675 [000] 537.037309: sched_switch: prev_comm=sshd prev_pid=1675...
      netstat 1692 [001] 537.038664: sched_switch: prev_comm=netstat prev_pid=1692...
      
      2. trace, custom format
      
      perf record -ga -e sched:sched_switch
      perf script -f comm,pid,time,trace     <--- omitting cpu and event name
      
      swapper    0 537.037184: prev_comm=swapper prev_pid=0 prev_prio=120 ...
         sshd 1675 537.037309: prev_comm=sshd prev_pid=1675 prev_prio=120 ...
      netstat 1692 537.038664: prev_comm=netstat prev_pid=1692 prev_prio=120 ...
      Acked-by: NFrederic Weisbecker <fweisbec@gmail.com>
      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: <1299734608-5223-5-git-send-email-daahern@cisco.com>
      Signed-off-by: NDavid Ahern <daahern@cisco.com>
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      745f43e3
    • D
      perf script: Move printing of 'common' data from print_event and rename · c70c94b4
      David Ahern 提交于
      This change does impact output: latency data is trace specific and is
      now printed after the common data - comm, tid, cpu, time and event name.
      Acked-by: NFrederic Weisbecker <fweisbec@gmail.com>
      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: <1299734608-5223-4-git-send-email-daahern@cisco.com>
      Signed-off-by: NDavid Ahern <daahern@cisco.com>
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      c70c94b4
    • D
      perf tracing: Remove print_graph_cpu and print_graph_proc from trace-event-parse · 2ee7a49f
      David Ahern 提交于
      Next patch moves printing of 'common' data into perf-script which
      removes the need for these functions.
      Acked-by: NFrederic Weisbecker <fweisbec@gmail.com>
      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: <1299734608-5223-3-git-send-email-daahern@cisco.com>
      Signed-off-by: NDavid Ahern <daahern@cisco.com>
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      2ee7a49f
    • D
      perf script: Change process_event prototype · be6d842a
      David Ahern 提交于
      Prepare for handling of samples for any event type.
      Acked-by: NFrederic Weisbecker <fweisbec@gmail.com>
      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: <1299734608-5223-2-git-send-email-daahern@cisco.com>
      Signed-off-by: NDavid Ahern <daahern@cisco.com>
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      be6d842a
    • F
      perf stat: Provide support for filters · cfd748ae
      Frederic Weisbecker 提交于
      Now the --filter option is usable with perf stat too.
      
      Cc: Ingo Molnar <mingo@elte.hu>
      Cc: Paul Mackerras <paulus@samba.org>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Stephane Eranian <eranian@google.com>
      LKML-Reference: <1300117230-8404-1-git-send-email-fweisbec@gmail.com>
      Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      cfd748ae
  2. 12 3月, 2011 4 次提交
    • A
      perf symbol: Move sym_entry->skip to symbol->ignore · 171b3be9
      Arnaldo Carvalho de Melo 提交于
      While going thru each of the sym_entry fields looking to reduce it to
      the set of entries needed when in an active symbols list, 'skip' should
      really be in symbol, as we set it when loading the symtab.
      
      And the space used by the basic symbol allocation remains the same as
      we had 5 bytes of padding.
      
      Cc: Frederic Weisbecker <fweisbec@gmail.com>
      Cc: Ingo Molnar <mingo@elte.hu>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Paul Mackerras <paulus@samba.org>
      Cc: Peter Zijlstra <peterz@infradead.org>
      Cc: Stephane Eranian <eranian@google.com>
      Cc: Tom Zanussi <tzanussi@gmail.com>
      LKML-Reference: <new-submission>
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      171b3be9
    • A
      perf symbols: Rename dso->origin to dso->symtab_type · 878b439d
      Arnaldo Carvalho de Melo 提交于
      And the DSO__ORIG_ enum to SYMTAB__, to clarify that this is about from
      where the symtab was obtained.
      
      Cc: Frederic Weisbecker <fweisbec@gmail.com>
      Cc: Ingo Molnar <mingo@elte.hu>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Paul Mackerras <paulus@samba.org>
      Cc: Peter Zijlstra <peterz@infradead.org>
      Cc: Stephane Eranian <eranian@google.com>
      Cc: Tom Zanussi <tzanussi@gmail.com>
      LKML-Reference: <new-submission>
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      878b439d
    • A
      perf top: Remove redundant syme->origin field · 8b8ba4a9
      Arnaldo Carvalho de Melo 提交于
      We can get it from syme->map->dso->kernel (that should be renamed to
      origin, but leave this for another patch).
      
      Cc: Frederic Weisbecker <fweisbec@gmail.com>
      Cc: Ingo Molnar <mingo@elte.hu>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Paul Mackerras <paulus@samba.org>
      Cc: Peter Zijlstra <peterz@infradead.org>
      Cc: Stephane Eranian <eranian@google.com>
      Cc: Tom Zanussi <tzanussi@gmail.com>
      LKML-Reference: <new-submission>
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      8b8ba4a9
    • A
      perf top: Remove redundant perf_top->sym_counter · ec52d976
      Arnaldo Carvalho de Melo 提交于
      We can get that counter index from perf_top->sym_evsel->idx instead.
      
      Cc: Frederic Weisbecker <fweisbec@gmail.com>
      Cc: Ingo Molnar <mingo@elte.hu>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Paul Mackerras <paulus@samba.org>
      Cc: Peter Zijlstra <peterz@infradead.org>
      Cc: Stephane Eranian <eranian@google.com>
      Cc: Tom Zanussi <tzanussi@gmail.com>
      LKML-Reference: <new-submission>
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      ec52d976
  3. 11 3月, 2011 1 次提交
  4. 10 3月, 2011 19 次提交
  5. 09 3月, 2011 3 次提交
    • J
      kprobes: Disabling optimized kprobes for entry text section · 2a8247a2
      Jiri Olsa 提交于
      You can crash the kernel (with root/admin privileges) using kprobe tracer by running:
      
       echo "p system_call_after_swapgs" > ./kprobe_events
       echo 1 > ./events/kprobes/enable
      
      The reason is that at the system_call_after_swapgs label, the
      kernel stack is not set up. If optimized kprobes are enabled,
      the user space stack is being used in this case (see optimized
      kprobe template) and this might result in a crash.
      
      There are several places like this over the entry code
      (entry_$BIT). As it seems there's no any reasonable/maintainable
      way to disable only those places where the stack is not ready, I
      switched off the whole entry code from kprobe optimizing.
      Signed-off-by: NJiri Olsa <jolsa@redhat.com>
      Acked-by: NMasami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
      Cc: acme@redhat.com
      Cc: fweisbec@gmail.com
      Cc: ananth@in.ibm.com
      Cc: davem@davemloft.net
      Cc: a.p.zijlstra@chello.nl
      Cc: eric.dumazet@gmail.com
      Cc: 2nddept-manager@sdl.hitachi.co.jp
      LKML-Reference: <1298298313-5980-3-git-send-email-jolsa@redhat.com>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      2a8247a2
    • J
      x86: Separate out entry text section · ea714547
      Jiri Olsa 提交于
      Put x86 entry code into a separate link section: .entry.text.
      
      Separating the entry text section seems to have performance
      benefits - caused by more efficient instruction cache usage.
      
      Running hackbench with perf stat --repeat showed that the change
      compresses the icache footprint. The icache load miss rate went
      down by about 15%:
      
       before patch:
               19417627  L1-icache-load-misses      ( +-   0.147% )
      
       after patch:
               16490788  L1-icache-load-misses      ( +-   0.180% )
      
      The motivation of the patch was to fix a particular kprobes
      bug that relates to the entry text section, the performance
      advantage was discovered accidentally.
      
      Whole perf output follows:
      
       - results for current tip tree:
      
        Performance counter stats for './hackbench/hackbench 10' (500 runs):
      
               19417627  L1-icache-load-misses      ( +-   0.147% )
             2676914223  instructions             #      0.497 IPC     ( +- 0.079% )
             5389516026  cycles                     ( +-   0.144% )
      
            0.206267711  seconds time elapsed   ( +-   0.138% )
      
       - results for current tip tree with the patch applied:
      
        Performance counter stats for './hackbench/hackbench 10' (500 runs):
      
               16490788  L1-icache-load-misses      ( +-   0.180% )
             2717734941  instructions             #      0.502 IPC     ( +- 0.079% )
             5414756975  cycles                     ( +-   0.148% )
      
            0.206747566  seconds time elapsed   ( +-   0.137% )
      Signed-off-by: NJiri Olsa <jolsa@redhat.com>
      Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
      Cc: Frederic Weisbecker <fweisbec@gmail.com>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Linus Torvalds <torvalds@linux-foundation.org>
      Cc: Andrew Morton <akpm@linux-foundation.org>
      Cc: Nick Piggin <npiggin@kernel.dk>
      Cc: Eric Dumazet <eric.dumazet@gmail.com>
      Cc: masami.hiramatsu.pt@hitachi.com
      Cc: ananth@in.ibm.com
      Cc: davem@davemloft.net
      Cc: 2nddept-manager@sdl.hitachi.co.jp
      LKML-Reference: <20110307181039.GB15197@jolsa.redhat.com>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      ea714547
    • I
      Merge commit 'v2.6.38-rc8' into perf/core · 86cb2ec7
      Ingo Molnar 提交于
      Merge reason: Merge latest fixes.
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      86cb2ec7
  6. 08 3月, 2011 5 次提交