From: Preeti U Murthy <preeti@linux.vnet.ibm.com>
To: Alex Shi <alex.shi@intel.com>
Cc: mingo@redhat.com, peterz@infradead.org, tglx@linutronix.de,
akpm@linux-foundation.org, arjan@linux.intel.com, bp@alien8.de,
pjt@google.com, namhyung@kernel.org, efault@gmx.de,
vincent.guittot@linaro.org, gregkh@linuxfoundation.org,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH v3 03/22] sched: fix find_idlest_group mess logical
Date: Fri, 11 Jan 2013 10:29:21 +0530 [thread overview]
Message-ID: <50EF9C29.9070201@linux.vnet.ibm.com> (raw)
In-Reply-To: <1357375071-11793-4-git-send-email-alex.shi@intel.com>
On 01/05/2013 02:07 PM, Alex Shi wrote:
> There is 4 situations in the function:
> 1, no task allowed group;
> so min_load = ULONG_MAX, this_load = 0, idlest = NULL
> 2, only local group task allowed;
> so min_load = ULONG_MAX, this_load assigned, idlest = NULL
> 3, only non-local task group allowed;
> so min_load assigned, this_load = 0, idlest != NULL
> 4, local group + another group are task allowed.
> so min_load assigned, this_load assigned, idlest != NULL
>
> Current logical will return NULL in first 3 kinds of scenarios.
> And still return NULL, if idlest group is heavier then the
> local group in the 4th situation.
>
> Actually, I thought groups in situation 2,3 are also eligible to host
> the task. And in 4th situation, agree to bias toward local group.
> So, has this patch.
>
> Signed-off-by: Alex Shi <alex.shi@intel.com>
> ---
> kernel/sched/fair.c | 12 +++++++++---
> 1 file changed, 9 insertions(+), 3 deletions(-)
>
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 6d3a95d..3c7b09a 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -3181,6 +3181,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
> int this_cpu, int load_idx)
> {
> struct sched_group *idlest = NULL, *group = sd->groups;
> + struct sched_group *this_group = NULL;
> unsigned long min_load = ULONG_MAX, this_load = 0;
> int imbalance = 100 + (sd->imbalance_pct-100)/2;
>
> @@ -3215,14 +3216,19 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
>
> if (local_group) {
> this_load = avg_load;
> - } else if (avg_load < min_load) {
> + this_group = group;
> + }
> + if (avg_load < min_load) {
> min_load = avg_load;
> idlest = group;
> }
> } while (group = group->next, group != sd->groups);
>
> - if (!idlest || 100*this_load < imbalance*min_load)
> - return NULL;
> + if (this_group && idlest != this_group)
> + /* Bias toward our group again */
> + if (100*this_load < imbalance*min_load)
> + idlest = this_group;
> +
> return idlest;
> }
>
Reviewed-by:Preeti U Murthy
next prev parent reply other threads:[~2013-01-11 5:00 UTC|newest]
Thread overview: 91+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-01-05 8:37 [PATCH V3 0/22] sched: simplified fork, enable load average into LB and power awareness scheduling Alex Shi
2013-01-05 8:37 ` [PATCH v3 01/22] sched: set SD_PREFER_SIBLING on MC domain to reduce a domain level Alex Shi
2013-01-05 8:37 ` [PATCH v3 02/22] sched: select_task_rq_fair clean up Alex Shi
2013-01-11 4:57 ` Preeti U Murthy
2013-01-05 8:37 ` [PATCH v3 03/22] sched: fix find_idlest_group mess logical Alex Shi
2013-01-11 4:59 ` Preeti U Murthy [this message]
2013-01-05 8:37 ` [PATCH v3 04/22] sched: don't need go to smaller sched domain Alex Shi
2013-01-09 17:38 ` Morten Rasmussen
2013-01-10 3:16 ` Mike Galbraith
2013-01-11 5:02 ` Preeti U Murthy
2013-01-05 8:37 ` [PATCH v3 05/22] sched: remove domain iterations in fork/exec/wake Alex Shi
2013-01-09 18:21 ` Morten Rasmussen
2013-01-11 2:46 ` Alex Shi
2013-01-11 10:07 ` Morten Rasmussen
2013-01-11 14:50 ` Alex Shi
2013-01-14 8:55 ` li guang
2013-01-14 9:18 ` Alex Shi
2013-01-11 4:56 ` Preeti U Murthy
2013-01-11 8:01 ` li guang
2013-01-11 14:56 ` Alex Shi
2013-01-14 9:03 ` li guang
2013-01-15 2:34 ` Alex Shi
2013-01-16 1:54 ` li guang
2013-01-11 10:54 ` Morten Rasmussen
2013-01-16 5:43 ` Alex Shi
2013-01-16 7:41 ` Alex Shi
2013-01-05 8:37 ` [PATCH v3 06/22] sched: load tracking bug fix Alex Shi
2013-01-05 8:37 ` [PATCH v3 07/22] sched: set initial load avg of new forked task Alex Shi
2013-01-11 5:10 ` Preeti U Murthy
2013-01-11 5:44 ` Alex Shi
2013-01-05 8:37 ` [PATCH v3 08/22] sched: update cpu load after task_tick Alex Shi
2013-01-05 8:37 ` [PATCH v3 09/22] sched: compute runnable load avg in cpu_load and cpu_avg_load_per_task Alex Shi
2013-01-05 8:56 ` Alex Shi
2013-01-06 7:54 ` Alex Shi
2013-01-06 18:31 ` Linus Torvalds
2013-01-07 7:00 ` Preeti U Murthy
2013-01-08 14:27 ` Alex Shi
2013-01-11 6:31 ` Alex Shi
2013-01-21 14:47 ` Alex Shi
2013-01-22 3:20 ` Alex Shi
2013-01-22 6:55 ` Mike Galbraith
2013-01-22 7:50 ` Alex Shi
2013-01-22 9:52 ` Mike Galbraith
2013-01-23 0:36 ` Alex Shi
2013-01-23 1:47 ` Mike Galbraith
2013-01-23 2:01 ` Alex Shi
2013-01-05 8:37 ` [PATCH v3 10/22] sched: consider runnable load average in move_tasks Alex Shi
2013-01-05 8:37 ` [PATCH v3 11/22] sched: consider runnable load average in effective_load Alex Shi
2013-01-10 11:28 ` Morten Rasmussen
2013-01-11 3:26 ` Alex Shi
2013-01-14 12:01 ` Morten Rasmussen
2013-01-16 5:30 ` Alex Shi
2013-01-05 8:37 ` [PATCH v3 12/22] Revert "sched: Introduce temporary FAIR_GROUP_SCHED dependency for load-tracking" Alex Shi
2013-01-05 8:37 ` [PATCH v3 13/22] sched: add sched_policy in kernel Alex Shi
2013-01-05 8:37 ` [PATCH v3 14/22] sched: add sched_policy and it's sysfs interface Alex Shi
2013-01-14 6:53 ` Namhyung Kim
2013-01-14 8:11 ` Alex Shi
2013-01-05 8:37 ` [PATCH v3 15/22] sched: log the cpu utilization at rq Alex Shi
2013-01-10 11:40 ` Morten Rasmussen
2013-01-11 3:30 ` Alex Shi
2013-01-14 13:59 ` Morten Rasmussen
2013-01-16 5:53 ` Alex Shi
2013-01-05 8:37 ` [PATCH v3 16/22] sched: add power aware scheduling in fork/exec/wake Alex Shi
2013-01-10 15:01 ` Morten Rasmussen
2013-01-11 7:08 ` Alex Shi
2013-01-14 16:09 ` Morten Rasmussen
2013-01-16 6:02 ` Alex Shi
2013-01-16 14:27 ` Morten Rasmussen
2013-01-17 5:47 ` Namhyung Kim
2013-01-18 13:41 ` Alex Shi
2013-01-14 7:03 ` Namhyung Kim
2013-01-14 8:30 ` Alex Shi
2013-01-05 8:37 ` [PATCH v3 17/22] sched: packing small tasks in wake/exec balancing Alex Shi
2013-01-10 17:17 ` Morten Rasmussen
2013-01-11 3:47 ` Alex Shi
2013-01-14 7:13 ` Namhyung Kim
2013-01-16 6:11 ` Alex Shi
2013-01-16 12:52 ` Namhyung Kim
2013-01-14 17:00 ` Morten Rasmussen
2013-01-16 7:32 ` Alex Shi
2013-01-16 15:08 ` Morten Rasmussen
2013-01-18 14:06 ` Alex Shi
2013-01-05 8:37 ` [PATCH v3 18/22] sched: add power/performance balance allowed flag Alex Shi
2013-01-05 8:37 ` [PATCH v3 19/22] sched: pull all tasks from source group Alex Shi
2013-01-05 8:37 ` [PATCH v3 20/22] sched: don't care if the local group has capacity Alex Shi
2013-01-05 8:37 ` [PATCH v3 21/22] sched: power aware load balance, Alex Shi
2013-01-05 8:37 ` [PATCH v3 22/22] sched: lazy powersaving balance Alex Shi
2013-01-14 8:39 ` Namhyung Kim
2013-01-14 8:45 ` Alex Shi
2013-01-09 17:16 ` [PATCH V3 0/22] sched: simplified fork, enable load average into LB and power awareness scheduling Morten Rasmussen
2013-01-10 3:49 ` 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=50EF9C29.9070201@linux.vnet.ibm.com \
--to=preeti@linux.vnet.ibm.com \
--cc=akpm@linux-foundation.org \
--cc=alex.shi@intel.com \
--cc=arjan@linux.intel.com \
--cc=bp@alien8.de \
--cc=efault@gmx.de \
--cc=gregkh@linuxfoundation.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=namhyung@kernel.org \
--cc=peterz@infradead.org \
--cc=pjt@google.com \
--cc=tglx@linutronix.de \
--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).