registry team mailing list archive

Thread
Date
[Bug 524281] Re: Tens of wakes per second in "[kernel scheduler] Load balancing tick" on Core 2 Duo even with only 1 core enabled

To: registry@xxxxxxxxxxxxxxxxxxx
From: lofas <henrik@xxxxxxxx>
Date: Mon, 16 Aug 2010 08:43:43 -0000
Reply-to: Bug 524281 <524281@xxxxxxxxxxxxxxxxxx>
Sender: bounces@xxxxxxxxxxxxx
Brian, I have tried the power3-generic patch and it improves some from
the nopatch kernel. The wakeups are halved but the load average of the
system is still running high. Output from powertop and top.

power3:

top - 10:22:59 up 14 min,  4 users,  load average: 0.13, 0.28, 0.23
Tasks: 183 total,   1 running, 182 sleeping,   0 stopped,   0 zombie
Cpu(s):  4.8%us,  1.4%sy,  0.0%ni, 92.5%id,  0.8%wa,  0.0%hi,  0.5%si,  0.0%st
Mem:   4008656k total,  1358760k used,  2649896k free,    80588k buffers
Swap:  3534264k total,        0k used,  3534264k free,   519024k cached

  PID USER      PR  NI  VIRT  RES  SHR S %CPU %MEM    TIME+  COMMAND            
 1230 root      20   0  160m  28m  12m S    4  0.7   0:29.74 Xorg               
 2663 lofas     20   0  928m 160m  14m S    3  4.1   0:34.86 chrome             
 2563 lofas     20   0  599m  57m  26m S    2  1.5   0:11.25 chrome             
 2683 lofas     20   0 59272  14m 9436 S    2  0.4   0:13.09 npviewer.bin       


 PowerTOP version 1.12      (C) 2007 Intel Corporation

Cn                Avg residency       P-states (frequencies)
C0 (cpu running)        ( 7.7%)       Turbo Mode     1.9%
polling           0.0ms ( 0.0%)         2.40 Ghz     0.2%
C1 mwait          0.2ms ( 0.0%)         1.60 Ghz     0.8%
C2 mwait          0.7ms ( 7.8%)          800 Mhz    97.1%
C6 mwait          2.0ms (84.5%)

Wakeups-from-idle per second : 539.4    interval: 10.0s
Power usage (5 minute ACPI estimate) :   0.3 W (244.4 hours left)

Top causes for wakeups:
  21.8% (140.4)   npviewer.bin
  16.7% (107.6)   [iwlagn] <interrupt>
  13.9% ( 89.5)   [extra timer interrupt]
  11.9% ( 76.4)   [kernel scheduler] Load balancing tick
  10.1% ( 65.2)   [i915] <interrupt>
   5.1% ( 32.6)   USB device 1-3.2 : USB-PS/2 Optical Mouse (Logitech)

NOPATCH:

top - 10:29:56 up 3 min,  3 users,  load average: 0.17, 0.37, 0.17
Tasks: 210 total,   2 running, 208 sleeping,   0 stopped,   0 zombie
Cpu(s):  6.2%us,  4.6%sy,  0.0%ni, 88.6%id,  0.0%wa,  0.0%hi,  0.5%si,  0.0%st
Mem:   4008656k total,  1287232k used,  2721424k free,    75072k buffers
Swap:  3534264k total,        0k used,  3534264k free,   458580k cached

  PID USER      PR  NI  VIRT  RES  SHR S %CPU %MEM    TIME+  COMMAND            
 1171 root      20   0  172m  30m  12m S    8  0.8   0:12.70 Xorg               
 1994 lofas     20   0  210m  15m  11m S    4  0.4   0:00.78 gnome-terminal     
 2417 lofas     20   0 59384  14m 9424 S    3  0.4   0:04.12 npviewer.bin       
 1814 lofas     20   0  325m  35m 8696 S    2  0.9   0:01.84 compiz             
 2038 root      20   0 12172 2540 1344 S    1  0.1   0:00.42 powertop           

PowerTOP version 1.12      (C) 2007 Intel Corporation

Cn                Avg residency       P-states (frequencies)
C0 (cpu running)        (10.1%)       Turbo Mode     1.0%
polling           0.0ms ( 0.0%)         2.40 Ghz     0.1%
C1 mwait          0.0ms ( 0.0%)         1.60 Ghz     0.3%
C2 mwait          0.5ms ( 5.5%)          800 Mhz    98.6%
C6 mwait          1.6ms (84.4%)

Wakeups-from-idle per second : 641.8    interval: 10.0s
Power usage (5 minute ACPI estimate) :   0.4 W (160.6 hours left)

Top causes for wakeups:
  22.2% (173.8)   [kernel scheduler] Load balancing tick
  17.7% (139.2)   npviewer.bin
  13.7% (107.6)   [iwlagn] <interrupt>
  11.9% ( 93.0)   [extra timer interrupt]

This can also be compared to the karmic-kernel 2.31 that I run instead
now, where the load avg is lower and the wakeups are comparable with the
power3 kernel.

top - 10:43:06 up 12 min,  3 users,  load average: 0.00, 0.13, 0.16
Tasks: 183 total,   2 running, 181 sleeping,   0 stopped,   0 zombie
Cpu(s):  1.2%us,  2.0%sy,  0.0%ni, 95.9%id,  0.0%wa,  0.5%hi,  0.5%si,  0.0%st
Mem:   4009716k total,  1375892k used,  2633824k free,    89808k buffers
Swap:  3534260k total,        0k used,  3534260k free,   513776k cached

  PID USER      PR  NI  VIRT  RES  SHR S %CPU %MEM    TIME+  COMMAND            
 5004 lofas     20   0 59232  14m 9436 S    3  0.4   0:12.05 npviewer.bin       
 3701 root      20   0  155m  30m  13m S    2  0.8   0:40.72 Xorg               
 4803 lofas     20   0  210m  15m  11m S    1  0.4   0:01.15 gnome-terminal     
 4842 lofas     20   0 19220 1460 1060 R    0  0.0   0:03.08 top                
    1 root      20   0 23692 1944 1268 S    0  0.0   0:00.93 init             

PowerTOP version 1.12      (C) 2007 Intel Corporation

Cn                Avg residency       P-states (frequencies)
C0 (cpu running)        ( 9.5%)       Turbo Mode     0.8%
polling           0.0ms ( 0.0%)         2.40 Ghz     0.1%
C1 mwait          0.0ms ( 0.0%)         1.60 Ghz     0.0%
C2 mwait          0.1ms ( 0.2%)          800 Mhz    99.1%
C6 mwait          2.1ms (90.3%)

Wakeups-from-idle per second : 448.4    interval: 10.0s
Power usage (5 minute ACPI estimate) :   0.2 W (312.8 hours left)

Top causes for wakeups:
  19.8% (139.0)   npviewer.bin
  17.3% (121.6)   [iwlagn] <interrupt>
  10.9% ( 76.7)   [extra timer interrupt]
  10.9% ( 76.4)   [kernel scheduler] Load balancing tick
   9.1% ( 64.1)   [i915] <interrupt>
   8.8% ( 61.6)   USB device 1-3.2 : USB-PS/2 Optical Mouse (Logitech)

-- 
Tens of wakes per second in "[kernel scheduler] Load balancing tick" on Core 2 Duo even with only 1 core enabled
https://bugs.launchpad.net/bugs/524281
You received this bug notification because you are a member of Registry
Administrators, which is the registrant for Debian.