Skip to content

L
linux
An error occurred fetching the project authors.
Switch branch/tag
  1. 05 Sep, 2007 3 commits
  3. 28 Aug, 2007 1 commit
    • Ingo Molnar's avatar
      sched: make the scheduler converge to the ideal latency · f6cf891c
      Ingo Molnar authored 
      de-HZ-ification of the granularity defaults unearthed a pre-existing
property of CFS: while it correctly converges to the granularity goal,
it does not prevent run-time fluctuations in the range of
[-gran ... 0 ... +gran].

With the increase of the granularity due to the removal of HZ
dependencies, this becomes visible in chew-max output (with 5 tasks
running):

 out:  28 . 27. 32 | flu:  0 .  0 | ran:    9 .   13 | per:   37 .   40
 out:  27 . 27. 32 | flu:  0 .  0 | ran:   17 .   13 | per:   44 .   40
 out:  27 . 27. 32 | flu:  0 .  0 | ran:    9 .   13 | per:   36 .   40
 out:  29 . 27. 32 | flu:  2 .  0 | ran:   17 .   13 | per:   46 .   40
 out:  28 . 27. 32 | flu:  0 .  0 | ran:    9 .   13 | per:   37 .   40
 out:  29 . 27. 32 | flu:  0 .  0 | ran:   18 .   13 | per:   47 .   40
 out:  28 . 27. 32 | flu:  0 .  0 | ran:    9 .   13 | per:   37 .   40

average slice is the ideal 13 msecs and the period is picture-perfect 40
msecs. But the 'ran' field fluctuates around 13.33 msecs and there's no
mechanism in CFS to keep that from happening: it's a perfectly valid
solution that CFS finds.

to fix this we add a granularity/preemption rule that knows about
the "target latency", which makes tasks that run longer than the ideal
latency run a bit less. The simplest approach is to simply decrease the
preemption granularity when a task overruns its ideal latency. For this
we have to track how much the task executed since its last preemption.

( this adds a new field to task_struct, but we can eliminate that
  overhead in 2.6.24 by putting all the scheduler timestamps into an
  anonymous union. )

with this change in place, chew-max output is fluctuation-less all
around:

 out:  28 . 27. 39 | flu:  0 .  2 | ran:   13 .   13 | per:   41 .   40
 out:  28 . 27. 39 | flu:  0 .  2 | ran:   13 .   13 | per:   41 .   40
 out:  28 . 27. 39 | flu:  0 .  2 | ran:   13 .   13 | per:   41 .   40
 out:  28 . 27. 39 | flu:  0 .  2 | ran:   13 .   13 | per:   41 .   40
 out:  28 . 27. 39 | flu:  0 .  1 | ran:   13 .   13 | per:   41 .   40
 out:  28 . 27. 39 | flu:  0 .  1 | ran:   13 .   13 | per:   41 .   40

this patch has no impact on any fastpath or on any globally observable
scheduling property. (unless you have sharp enough eyes to see
millisecond-level ruckles in glxgears smoothness :-)
Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
Signed-off-by: default avatarPeter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: default avatarMike Galbraith <efault@gmx.de>
      f6cf891c
  5. 25 Aug, 2007 3 commits
  7. 24 Aug, 2007 2 commits
  9. 23 Aug, 2007 5 commits
    • Ingo Molnar's avatar
      sched: tweak the sched_runtime_limit tunable · 505c0efd
      Ingo Molnar authored 
      Michael Gerdau reported reniced task CPU usage weirdnesses.
Such symptoms can be caused by limit underruns so double the
sched_runtime_limit.
Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      505c0efd
    • Suresh Siddha's avatar
      sched: skip updating rq's next_balance under null SD · f549da84
      Suresh Siddha authored 
      Was playing with sched_smt_power_savings/sched_mc_power_savings and
found out that while the scheduler domains are reconstructed when sysfs
settings change, rebalance_domains() can get triggered with null domain
on other cpus, which is setting next_balance to jiffies + 60*HZ.
Resulting in no idle/busy balancing for 60 seconds.

Fix this.
Signed-off-by: default avatarSuresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      f549da84
    • Suresh Siddha's avatar
      sched: fix broken SMT/MC optimizations · f8700df7
      Suresh Siddha authored 
      On a four package system with HT - HT load balancing optimizations were
broken.  For example, if two tasks end up running on two logical threads
of one of the packages, scheduler is not able to pull one of the tasks
to a completely idle package.

In this scenario, for nice-0 tasks, imbalance calculated by scheduler
will be 512 and find_busiest_queue() will return 0 (as each cpu's load
is 1024 > imbalance and has only one task running).

Similarly MC scheduler optimizations also get fixed with this patch.

[ mingo@elte.hu: restored fair balancing by increasing the fuzz and
                 adding it back to the power decision, without the /2
                 factor. ]
Signed-off-by: default avatarSuresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      f8700df7
    • Eric W. Biederman's avatar
      sched: fix sysctl directory permissions · c57baf1e
      Eric W. Biederman authored 
      There are two remaining gotchas:

- The directories have impossible permissions (writeable).

- The ctl_name for the kernel directory is inconsistent with
  everything else.  It should be CTL_KERN.
Signed-off-by: default avatarEric W. Biederman <ebiederm@xmission.com>
Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      c57baf1e
    • Ingo Molnar's avatar
      sched: sched_clock_idle_[sleep|wakeup]_event() · 2aa44d05
      Ingo Molnar authored 
      construct a more or less wall-clock time out of sched_clock(), by
using ACPI-idle's existing knowledge about how much time we spent
idling. This allows the rq clock to work around TSC-stops-in-C2,
TSC-gets-corrupted-in-C3 type of problems.

( Besides the scheduler's statistics this also benefits blktrace and
  printk-timestamps as well. )

Furthermore, the precise before-C2/C3-sleep and after-C2/C3-wakeup
callbacks allow the scheduler to get out the most of the period where
the CPU has a reliable TSC. This results in slightly more precise
task statistics.

the ACPI bits were acked by Len.
Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
Acked-by: default avatarLen Brown <len.brown@intel.com>
      2aa44d05
  11. 12 Aug, 2007 2 commits
  13. 10 Aug, 2007 1 commit
  15. 09 Aug, 2007 23 commits
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7