Message-Id: <200410051744.i95Hii627981@unix-os.sc.intel.com>
From: "Chen, Kenneth W" <kenneth.w.chen@intel.com>
To: "'Ingo Molnar'" <mingo@elte.hu>
Cc: <linux-kernel@vger.kernel.org>, "Andrew Morton" <akpm@osdl.org>,
       "Nick Piggin" <nickpiggin@yahoo.com.au>
Subject: RE: bug in sched.c:activate_task()
Date: Tue, 5 Oct 2004 10:44:51 -0700
Thread-Index: AcSqs+eaeeVK4lKVQXW75lmRZGOjgwATt1Zg
In-Reply-To: <20041005081923.GA11258@elte.hu>
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1735
Lines: 42

* Chen, Kenneth W <kenneth.w.chen@intel.com> wrote:
> Update p->timestamp to "now" in activate_task() doesn't look right to
> me at all.  p->timestamp records last time it was running on a cpu.
> activate_task shouldn't update that variable when it queues a task on
> the runqueue.


Ingo Molnar wrote on Tuesday, October 05, 2004 1:19 AM
> it is being used for multiple purposes: measuring on-CPU time, measuring
> on-runqueue time (for interactivity) and measuring off-runqueue time
> (for interactivity). It is also used to measure cache-hotness, by the
> balancing code.
>
> now, this particular update of p->timestamp:
>
> > @@ -888,7 +888,6 @@ static void activate_task(task_t *p, run
>
> > -	p->timestamp = now;
>
> is important for the interactivity code that runs in schedule() - it
> wants to know how much time we spent on the runqueue without having run.
>
> but you are right that the task_hot() use of p->timestamp is incorrect
> for freshly woken up tasks - we want the balancer to be able to re-route
> tasks to another CPU, as long as the task has not hit the runqueue yet
> (which it hasnt where we consider it in the balancer).
>
> the clean solution is to separate the multiple uses of p->timestamp:
> with the patch below p->timestamp is purely used for the interactivity
> code, and p->last_ran is for the rebalancer. The patch is ontop of your
> task_hot() fix-patch. Does this work for your workload?

I will take this for a spin and report back the result.

- Ken


-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/