linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Preeti U Murthy <preeti@linux.vnet.ibm.com>
To: Alex Shi <alex.shi@intel.com>
Cc: rob@landley.net, mingo@redhat.com, peterz@infradead.org,
	gregkh@linuxfoundation.org, andre.przywara@amd.com, rjw@sisk.pl,
	paul.gortmaker@windriver.com, akpm@linux-foundation.org,
	paulmck@linux.vnet.ibm.com, linux-kernel@vger.kernel.org,
	pjt@google.com, vincent.guittot@linaro.org
Subject: Re: [PATCH 08/18] sched: consider runnable load average in move_tasks
Date: Wed, 12 Dec 2012 10:11:03 +0530	[thread overview]
Message-ID: <50C80ADF.8050504@linux.vnet.ibm.com> (raw)
In-Reply-To: <1355127754-8444-9-git-send-email-alex.shi@intel.com>

Hi Alex,
On 12/10/2012 01:52 PM, Alex Shi wrote:
> Except using runnable load average in background, move_tasks is also
> the key functions in load balance. We need consider the runnable load
> average in it in order to the apple to apple load comparison.
> 
> Signed-off-by: Alex Shi <alex.shi@intel.com>
> ---
>  kernel/sched/fair.c |   11 ++++++++++-
>  1 files changed, 10 insertions(+), 1 deletions(-)
> 
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 6d893a6..bbb069c 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -3741,6 +3741,15 @@ static unsigned long task_h_load(struct task_struct *p);
>  
>  static const unsigned int sched_nr_migrate_break = 32;
>  
> +static unsigned long task_h_load_avg(struct task_struct *p)
> +{
> +	u32 period = p->se.avg.runnable_avg_period;
> +	if (!period)
> +		return 0;
> +
> +	return task_h_load(p) * p->se.avg.runnable_avg_sum / period;
                        ^^^^^^^^^^^^
This might result in an overflow,considering you are multiplying two 32
bit integers.Below is how this is handled in
__update_task_entity_contrib in kernel/sched/fair.c

u32 contrib;
/* avoid overflowing a 32-bit type w/ SCHED_LOAD_SCALE */
contrib = se->avg.runnable_avg_sum * scale_load_down(se->load.weight);
contrib /= (se->avg.runnable_avg_period + 1);
se->avg.load_avg_contrib = scale_load(contrib);

Also why can't p->se.load_avg_contrib be used directly? as a return
value for task_h_load_avg? since this is already updated in
update_task_entity_contrib and update_group_entity_contrib.
> +}
> +
>  /*
>   * move_tasks tries to move up to imbalance weighted load from busiest to
>   * this_rq, as part of a balancing operation within domain "sd".
> @@ -3776,7 +3785,7 @@ static int move_tasks(struct lb_env *env)
>  		if (throttled_lb_pair(task_group(p), env->src_cpu, env->dst_cpu))
>  			goto next;
>  
> -		load = task_h_load(p);
> +		load = task_h_load_avg(p);
>  
>  		if (sched_feat(LB_MIN) && load < 16 && !env->sd->nr_balance_failed)
>  			goto next;
> 

Regards
Preeti U Murthy


  reply	other threads:[~2012-12-12  4:41 UTC|newest]

Thread overview: 56+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-12-10  8:22 [PATCH 0/18] sched: simplified fork, enable load average into LB and power awareness scheduling Alex Shi
2012-12-10  8:22 ` [PATCH 01/18] sched: select_task_rq_fair clean up Alex Shi
2012-12-11  4:23   ` Preeti U Murthy
2012-12-11  5:28     ` Alex Shi
2012-12-11  6:30       ` Preeti U Murthy
2012-12-11 11:53         ` Alex Shi
2012-12-12  5:26           ` Preeti U Murthy
2012-12-21  4:28         ` Namhyung Kim
2012-12-23 12:17           ` Alex Shi
2012-12-10  8:22 ` [PATCH 02/18] sched: fix find_idlest_group mess logical Alex Shi
2012-12-11  5:08   ` Preeti U Murthy
2012-12-11  5:29     ` Alex Shi
2012-12-11  5:50       ` Preeti U Murthy
2012-12-11 11:55         ` Alex Shi
2012-12-10  8:22 ` [PATCH 03/18] sched: don't need go to smaller sched domain Alex Shi
2012-12-10  8:22 ` [PATCH 04/18] sched: remove domain iterations in fork/exec/wake Alex Shi
2012-12-10  8:22 ` [PATCH 05/18] sched: load tracking bug fix Alex Shi
2012-12-10  8:22 ` [PATCH 06/18] sched: set initial load avg of new forked task as its load weight Alex Shi
2012-12-21  4:33   ` Namhyung Kim
2012-12-23 12:00     ` Alex Shi
2012-12-10  8:22 ` [PATCH 07/18] sched: compute runnable load avg in cpu_load and cpu_avg_load_per_task Alex Shi
2012-12-12  3:57   ` Preeti U Murthy
2012-12-12  5:52     ` Alex Shi
2012-12-13  8:45     ` Alex Shi
2012-12-21  4:35       ` Namhyung Kim
2012-12-23 11:42         ` Alex Shi
2012-12-10  8:22 ` [PATCH 08/18] sched: consider runnable load average in move_tasks Alex Shi
2012-12-12  4:41   ` Preeti U Murthy [this message]
2012-12-12  6:26     ` Alex Shi
2012-12-21  4:43       ` Namhyung Kim
2012-12-23 12:29         ` Alex Shi
2012-12-10  8:22 ` [PATCH 09/18] Revert "sched: Introduce temporary FAIR_GROUP_SCHED dependency for load-tracking" Alex Shi
2012-12-10  8:22 ` [PATCH 10/18] sched: add sched_policy in kernel Alex Shi
2012-12-10  8:22 ` [PATCH 11/18] sched: add sched_policy and it's sysfs interface Alex Shi
2012-12-10  8:22 ` [PATCH 12/18] sched: log the cpu utilization at rq Alex Shi
2012-12-10  8:22 ` [PATCH 13/18] sched: add power aware scheduling in fork/exec/wake Alex Shi
2012-12-10  8:22 ` [PATCH 14/18] sched: add power/performance balance allowed flag Alex Shi
2012-12-10  8:22 ` [PATCH 15/18] sched: don't care if the local group has capacity Alex Shi
2012-12-10  8:22 ` [PATCH 16/18] sched: pull all tasks from source group Alex Shi
2012-12-10  8:22 ` [PATCH 17/18] sched: power aware load balance, Alex Shi
2012-12-10  8:22 ` [PATCH 18/18] sched: lazy powersaving balance Alex Shi
2012-12-11  0:51 ` [PATCH 0/18] sched: simplified fork, enable load average into LB and power awareness scheduling Alex Shi
2012-12-11 12:10   ` Alex Shi
2012-12-11 15:48     ` Borislav Petkov
2012-12-11 16:03       ` Arjan van de Ven
2012-12-11 16:13         ` Borislav Petkov
2012-12-11 16:40           ` Arjan van de Ven
2012-12-12  9:52             ` Amit Kucheria
2012-12-12 13:55               ` Alex Shi
2012-12-12 14:21                 ` Vincent Guittot
2012-12-13  2:51                   ` Alex Shi
2012-12-12 14:41             ` Borislav Petkov
2012-12-13  3:07               ` Alex Shi
2012-12-13 11:35                 ` Borislav Petkov
2012-12-14  1:56                   ` Alex Shi
2012-12-12  1:14           ` Alex Shi

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=50C80ADF.8050504@linux.vnet.ibm.com \
    --to=preeti@linux.vnet.ibm.com \
    --cc=akpm@linux-foundation.org \
    --cc=alex.shi@intel.com \
    --cc=andre.przywara@amd.com \
    --cc=gregkh@linuxfoundation.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=paul.gortmaker@windriver.com \
    --cc=paulmck@linux.vnet.ibm.com \
    --cc=peterz@infradead.org \
    --cc=pjt@google.com \
    --cc=rjw@sisk.pl \
    --cc=rob@landley.net \
    --cc=vincent.guittot@linaro.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).