Message-ID: <1398412733.11930.56.camel@marge.simpson.net>
Subject: Re: [PATCH 1/3] sched, balancing: Update rq->max_idle_balance_cost
 whenever newidle balance is attempted
From: Mike Galbraith <umgwanakikbuti@gmail.com>
To: Jason Low <jason.low2@hp.com>
Cc: Preeti U Murthy <preeti@linux.vnet.ibm.com>,
        Peter Zijlstra <peterz@infradead.org>, mingo@kernel.org,
        linux-kernel@vger.kernel.org, daniel.lezcano@linaro.org,
        alex.shi@linaro.org, vincent.guittot@linaro.org,
        morten.rasmussen@arm.com, aswin@hp.com, chegu_vinod@hp.com
Date: Fri, 25 Apr 2014 09:58:53 +0200
In-Reply-To: <1398409990.12047.27.camel@j-VirtualBox>
References: <1398303035-18255-1-git-send-email-jason.low2@hp.com>
	 <1398303035-18255-2-git-send-email-jason.low2@hp.com>
	 <5358E417.8090503@linux.vnet.ibm.com>
	 <20140424120415.GS11096@twins.programming.kicks-ass.net>
	 <20140424124438.GT13658@twins.programming.kicks-ass.net>
	 <1398358417.3509.11.camel@j-VirtualBox>
	 <20140424171453.GZ11096@twins.programming.kicks-ass.net>
	 <1398377917.3509.32.camel@j-VirtualBox>
	 <5359EEBE.2030808@linux.vnet.ibm.com>
	 <1398409990.12047.27.camel@j-VirtualBox>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: 7bit
Mime-Version: 1.0
Sender: linux-kernel-owner@vger.kernel.org

On Fri, 2014-04-25 at 00:13 -0700, Jason Low wrote: 
> On Fri, 2014-04-25 at 10:42 +0530, Preeti U Murthy wrote:
> > I agree with this. However I am concerned with an additional point that
> > I have mentioned in my reply to Peter's mail on this thread.
> > 
> > Should we verify if rq->next_balance update is independent of
> > pulled_tasks? sd->balance_interval is changed during load_balance() and
> > rq->next_balance should perhaps consider that?
> 
> Hi Preeti,
> 
> I agree that we may want to consider having rq->next balance update be
> independent of pulled_task. As you mentioned, load_balance() can modify
> the balance_interval.
> 
> There are a few things I'm wondering if we would need to also add then:
> 
> 1. In the case that this_rq->avg_idle < sysctl_sched_migration_cost, we
>    would need to also traverse the domains to properly compute
>    next_balance (without the sd->busy_factor) as we would be going idle.
>    Otherwise, next_balance could get set to jiffies + HZ while the
>    CPU goes idle.

Avoiding high frequency cache misses and cycle wastage on micro-idle was
what avg-idle was about.  If you're going to traverse anyway, or have a
better way to not do that too frequently, you can just nuke it.

-Mike

--
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/