Re: [PATCH v3 17/17] (Avoid overload)


On Sat, 17 Nov 2007, Gregory Haskins wrote:

On Sat, Nov 17, 2007 at 1:33 AM, in message
This patch changes the searching for a run queue by a waking RT task
to try to pick another runqueue if the currently running task
is an RT task.

The reason is that RT tasks behave different than normal
tasks. Preempting a normal task to run a RT task to keep
its cache hot is fine, because the preempted non-RT task
may wait on that same runqueue to run again unless the
migration thread comes along and pulls it off.

RT tasks behave differently. If one is preempted, it makes
an active effort to continue to run. So by having a high
priority task preempt a lower priority RT task, that lower
RT task will then quickly try to run on another runqueue.
This will cause that lower RT task to replace its nice
hot cache (and TLB) with a completely cold one. This is
for the hope that the new high priority RT task will keep
its cache hot.

Remeber that this high priority RT task was just woken up.
So it may likely have been sleeping for several milliseconds,
and will end up with a cold cache anyway. RT tasks run till
they voluntarily stop, or are preempted by a higher priority
task. This means that it is unlikely that the woken RT task
will have a hot cache to wake up to. So pushing off a lower
RT task is just killing its cache for no good reason.

You make some excellent points here. Out of curiosity, have you tried a comparison to see if it helps?

hehe, I was waiting for the "where's the numbers". Right now I don't have
them. Mainly because I don't have boxes with more that 4 CPUs on them. And
4 really doesn't make much of a difference.

If others out there would like to test, I'll write up a couple of versions
of this code and that way we can really get numbers for them.

Or perhaps someone would like to send me a 16way box. Although my wife
would kill me. ;-)

Hmm, I'm sure I can get to our lab and run some tests too.

-- Steve

-
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/

Relevant Pages

  • Re: [PATCH v3 17/17] (Avoid overload)
    ... to try to pick another runqueue if the currently running task ... Preempting a normal task to run a RT task to keep ... priority task preempt a lower priority RT task, ... hot cache with a completely cold one. ...
    (Linux-Kernel)
  • [PATCH v4 16/20] Avoid overload
    ... to try to pick another runqueue if the currently running task ... Preempting a normal task to run a RT task to keep ... priority task preempt a lower priority RT task, ... hot cache with a completely cold one. ...
    (Linux-Kernel)
  • [PATCH 16/23] Subject: SCHED - Avoid overload
    ... to try to pick another runqueue if the currently running task ... Preempting a normal task to run a RT task to keep ... priority task preempt a lower priority RT task, ... hot cache with a completely cold one. ...
    (Linux-Kernel)
  • Re: [PATCH v3 17/17] (Avoid overload)
    ... This patch changes the searching for a run queue by a waking RT task ... Preempting a normal task to run a RT task to keep ... priority task preempt a lower priority RT task, ... hot cache with a completely cold one. ...
    (Linux-Kernel)
  • Re: Scheduler: Process priority fed back to parent?
    ... Mac OS X has a special cache ... on disk of things that get loaded on boot. ... >>initial priority is a guess, and isn't set until the priority info has ... This prefetch activity could be turned on/off ...
    (Linux-Kernel)