_spin_unlock_irqrestore() has very high sampling rate when usingoprofile tool.

[Peter Huang(Peng)]

During TPC-C testing on IA64 platform, we binded LGWR process to 1 cpu, and find
 that sys% is over 50%.
With oprofile we find that _spin_unlock_irqrestore() rated over 31%, and try_to_wake_up()
caused this.
I don't understand why unlock operation has high sampling rate, is there anybody know about
this?

Thanks.

-sampling result
CPU: Itanium 2, speed 1.598e+06 MHz (estimated)
Counted CPU_CYCLES events (CPU Cycles) with a unit mask of 0x00 (No unit mask) count 75000
samples  %        app name                 symbol name
53204    31.4940  vmlinux                  _spin_unlock_irqrestore
19788    11.7135  oracle                   kcrfw_redo_write
12804     7.5793  oracle                   $_1$kslpstevent$TAG$GLOB
12004     7.1057  vmlinux                  search_module_extables
8859      5.2441  vmlinux                  search_extable
8150      4.8244  vmlinux                  try_atomic_semop
6121      3.6233  vmlinux                  update_queue
4402      2.6058  scsi_mod                 /scsi_mod
3698      2.1890  vmlinux                  ring_buffer_consume
3069      1.8167  vmlinux                  default_idle
2122      1.2561  oprofile                 /oprofile

-callgraph
CPU: Itanium 2, speed 1.598e+06 MHz (estimated)
Counted CPU_CYCLES events (CPU Cycles) with a unit mask of 0x00 (No unit mask) count 75000
samples  %        image name               app name                 symbol name
-------------------------------------------------------------------------------
  1         0.0021  vmlinux                  vmlinux                  cpufreq_cpu_get
  1         0.0021  vmlinux                  vmlinux                  sys_pfm_start
  1         0.0021  vmlinux                  vmlinux                  try_to_del_timer_sync
  1         0.0021  vmlinux                  vmlinux                  prepare_to_wait
  2         0.0041  vmlinux                  vmlinux                  set_cpus_allowed_ptr
  3         0.0062  vmlinux                  vmlinux                  cpu_quiet_msk
  3         0.0062  vmlinux                  vmlinux                  delayacct_end
  3         0.0062  vmlinux                  vmlinux                  __wake_up
  4         0.0082  vmlinux                  vmlinux                  rcu_process_gp_end
  4         0.0082  vmlinux                  vmlinux                  credit_entropy_bits
  6         0.0123  vmlinux                  vmlinux                  __queue_work
  6         0.0123  vmlinux                  vmlinux                  mod_timer
  23        0.0472  vmlinux                  vmlinux                  dio_bio_end_aio
  26        0.0534  vmlinux                  vmlinux                  __blockdev_direct_IO
  37        0.0760  vmlinux                  vmlinux                  dio_bio_submit
  38        0.0780  vmlinux                  vmlinux                  add_wait_queue_exclusive
  44        0.0903  vmlinux                  vmlinux                  remove_wait_queue
  165       0.3388  vmlinux                  vmlinux                  blk_run_queue
  529       1.0862  vmlinux                  vmlinux                  mix_pool_bytes_extract
  697       1.4312  vmlinux                  vmlinux                  blk_end_bidi_request
  783       1.6077  vmlinux                  vmlinux                  aio_complete
  46325    95.1193  vmlinux                  vmlinux                  try_to_wake_up
53204    31.4940  vmlinux                  vmlinux                  _spin_unlock_irqrestore
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/