touch-packages team mailing list archive

[Steve Langasek <steve.langasek@xxxxxxxxxxxxx>]

Assigning to Foundations for the init script workaround.

** Package changed: ubuntu => sysvinit (Ubuntu)

** Changed in: sysvinit (Ubuntu)
   Importance: Undecided => High

** Changed in: sysvinit (Ubuntu)
       Status: New => Triaged

** Changed in: sysvinit (Ubuntu)
     Assignee: Taco Screen team (taco-screen-team) => Adam Conrad (adconrad)

-- 
You received this bug notification because you are a member of Ubuntu
Touch seeded packages, which is subscribed to sysvinit in Ubuntu.
https://bugs.launchpad.net/bugs/1483586

Title:
  On demand cpufreq govneror causes large amounts of jitter

Status in sysvinit package in Ubuntu:
  Triaged

Bug description:
  == Comment: #0 - Anton Blanchard <antonb@xxxxxxxxxxx> - 2015-07-16 22:22:09 ==
  We are seeing large amounts of jitter caused by od_dbs_timer(). We should slow down the rate of updates and or turn this into a timer. Having a workqueue execute so often is very noticeable.

  # echo 1 >
  /sys/kernel/debug/tracing/events/workqueue/workqueue_execute_start/enable

  (wait a while)

  # cat /sys/kernel/debug/trace

             <...>-67605 [040] .... 849622.393576: workqueue_execute_start: work struct c0000007fba1ba20: function od_dbs_timer
             <...>-67605 [040] .... 849622.403574: workqueue_execute_start: work struct c0000007fba1ba20: function od_dbs_timer
             <...>-116685 [048] .... 849622.403575: workqueue_execute_start: work struct c0000007fbc1ba20: function od_dbs_timer
             <...>-116685 [048] .... 849622.413574: workqueue_execute_start: work struct c0000007fbc1ba20: function od_dbs_timer
             <...>-67605 [040] .... 849622.413575: workqueue_execute_start: work struct c0000007fba1ba20: function od_dbs_timer
             <...>-67605 [040] .... 849622.423575: workqueue_execute_start: work struct c0000007fba1ba20: function od_dbs_timer
             <...>-116685 [048] .... 849622.433574: workqueue_execute_start: work struct c0000007fbc1ba20: function od_dbs_timer
             <...>-67605 [040] .... 849622.433574: workqueue_execute_start: work struct c0000007fba1ba20: function od_dbs_timer
             <...>-116685 [048] .... 849622.443573: workqueue_execute_start: work struct c0000007fbc1ba20: function od_dbs_timer

  == Comment: #1 - Shilpasri G. Bhat <shigbhat@xxxxxxxxxx> - 2015-07-22 19:42:38 ==
  Hi Anton,

  We can set the governor's tunable 'sampling_down_factor' to decrease
  the rate of updates. When this tunable is set to a value greater than
  1, the sampling period of the governor is increased during the peak
  load to sampling_period times sampling_down_factor. This will reduce
  the jitter caused by od_dbs_timer() when the cpu is busy.

  I am currently running benchmarks to find out the optimal value for
  this tunable and will post them soon.

  Thanks and Regards,
  Shilpa

  == Comment: #2 - Anton Blanchard <antonb@xxxxxxxxxxx> - 2015-07-31 03:44:49 ==
  FYI We are also seeing high levels of CPU consumed by this on a LAMP workload:

       2.54%  kworker/0:0  [kernel.kallsyms]         [k] osq_lock
              |       
              ---osq_lock
                 |                   
                 |--99.83%-- mutex_optimistic_spin
                 |          __mutex_lock_slowpath
                 |          mutex_lock
                 |          |                  
                 |          |--80.08%-- od_dbs_timer

  2.5% of total CPU time spent in the od_dbs_timer mutex.

  == Comment: #3 - Anton Blanchard <antonb@xxxxxxxxxxx> - 2015-07-31 06:00:45 ==
  Hitting this on a customer setup, raising priority

  == Comment: #4 - Shilpasri G. Bhat <shigbhat@xxxxxxxxxx> - 2015-08-03 06:47:40 ==
  I used `perf top` and `perf record` to observe the overhead caused by 'osq_lock'.
  Both with ebizzy and SPECPower's ssjb workload I am able to see an overhead of 0.03% caused by 'osq_lock' with default governor settings. 
  With sampling_down_factor=100, (1second) I am able to see 0.00% of overhead by 'osq_lock'.

  So this might not be a good data point to showcase, but by reducing
  the  od_dbs_timer interrupts we are guaranteed to decrease the
  overhead caused by 'osq_lock'.

  == Comment: #5 - VAIDYANATHAN SRINIVASAN <svaidyan@xxxxxxxxxx> - 2015-08-03 09:09:09 ==
  Hi Anton,

  Thanks for opening the bz to track and fix this issue.  Shilpa is
  trying different workarounds.  Here is our plan:

  (1) Use sampling_down_factor and other tunables in current Ubuntu
  releases to workaround the issue or minimise the impact.

  (2) Redesign cpufreq subsystem on powerpc similar to intel pstate
  driver so that we can program timers and cancel them dynamically based
  on different utilization points.  Target Ubuntu 16.04 and then
  backport to 14.04.x and other distros.

  (3) Enhance design for (2) buy estimating core level utilization
  without running timers in each thread and then decide the target
  PState

  (4) Explore hardware assist so that we can avoid per-core estimation
  in software but still be able to set per-core PState. We need to take
  an interrupt or work-queue only to change PState and not really for
  estimation of load.  Hence steady state load will experience zero
  jitter from cpufreq.

  --Vaidy

  
  == Comment: #7 - Shilpasri G. Bhat <shigbhat@xxxxxxxxxx> - 2015-08-04 07:49:23 ==
  Workaround using ondemand tunable 'sampling_down_factor':

  File: /etc/init.d/ondemand (shell script which sets the governor after boot)
          if [ "$GOVERNOR" = "ondemand" ]; then
                  echo 100 > /sys/devices/system/cpu/cpufreq/ondemand/sampling_down_factor
          fi

  Setting the value of 100 to sampling_down_factor will increase the
  sampling period of ondemand governor to one second when the cpu is
  busy.

To manage notifications about this bug go to:
https://bugs.launchpad.net/ubuntu/+source/sysvinit/+bug/1483586/+subscriptions