From: Mel Gorman <mgorman@suse.de>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>,
Ingo Molnar <mingo@kernel.org>,
Andrea Arcangeli <aarcange@redhat.com>,
Johannes Weiner <hannes@cmpxchg.org>,
Linux-MM <linux-mm@kvack.org>,
LKML <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 13/13] sched: Account for the number of preferred tasks running on a node when selecting a preferred node
Date: Thu, 4 Jul 2013 15:40:18 +0100 [thread overview]
Message-ID: <20130704144018.GS1875@suse.de> (raw)
In-Reply-To: <20130704140612.GO18898@dyad.programming.kicks-ass.net>
On Thu, Jul 04, 2013 at 04:06:13PM +0200, Peter Zijlstra wrote:
> On Thu, Jul 04, 2013 at 02:54:15PM +0100, Mel Gorman wrote:
> > diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> > index 9247345..387f28d 100644
> > --- a/kernel/sched/fair.c
> > +++ b/kernel/sched/fair.c
> > @@ -863,9 +863,13 @@ find_idlest_cpu_node(int this_cpu, int nid)
> > load = weighted_cpuload(i);
> >
> > if (load < min_load) {
> > - /* Do not preempt a task running on a preferred node */
> > + /*
> > + * Do not preempt a task running on a preferred node or
> > + * tasks are are pinned to their current CPU
> > + */
> > struct task_struct *p = cpu_rq(i)->curr;
> > - if (p->numa_preferred_nid != nid) {
> > + if (p->numa_preferred_nid != nid &&
> > + cpumask_weight(tsk_cpus_allowed(p)) > 1) {
>
> We have p->nr_cpus_allowed for that.
>
/me slaps self
That's a bit easier to calculate, thanks.
--
Mel Gorman
SUSE Labs
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
WARNING: multiple messages have this Message-ID (diff)
From: Mel Gorman <mgorman@suse.de>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>,
Ingo Molnar <mingo@kernel.org>,
Andrea Arcangeli <aarcange@redhat.com>,
Johannes Weiner <hannes@cmpxchg.org>,
Linux-MM <linux-mm@kvack.org>,
LKML <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 13/13] sched: Account for the number of preferred tasks running on a node when selecting a preferred node
Date: Thu, 4 Jul 2013 15:40:18 +0100 [thread overview]
Message-ID: <20130704144018.GS1875@suse.de> (raw)
In-Reply-To: <20130704140612.GO18898@dyad.programming.kicks-ass.net>
On Thu, Jul 04, 2013 at 04:06:13PM +0200, Peter Zijlstra wrote:
> On Thu, Jul 04, 2013 at 02:54:15PM +0100, Mel Gorman wrote:
> > diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> > index 9247345..387f28d 100644
> > --- a/kernel/sched/fair.c
> > +++ b/kernel/sched/fair.c
> > @@ -863,9 +863,13 @@ find_idlest_cpu_node(int this_cpu, int nid)
> > load = weighted_cpuload(i);
> >
> > if (load < min_load) {
> > - /* Do not preempt a task running on a preferred node */
> > + /*
> > + * Do not preempt a task running on a preferred node or
> > + * tasks are are pinned to their current CPU
> > + */
> > struct task_struct *p = cpu_rq(i)->curr;
> > - if (p->numa_preferred_nid != nid) {
> > + if (p->numa_preferred_nid != nid &&
> > + cpumask_weight(tsk_cpus_allowed(p)) > 1) {
>
> We have p->nr_cpus_allowed for that.
>
/me slaps self
That's a bit easier to calculate, thanks.
--
Mel Gorman
SUSE Labs
next prev parent reply other threads:[~2013-07-04 14:40 UTC|newest]
Thread overview: 86+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-07-03 14:21 [PATCH 0/13] Basic scheduler support for automatic NUMA balancing V2 Mel Gorman
2013-07-03 14:21 ` Mel Gorman
2013-07-03 14:21 ` [PATCH 01/13] mm: numa: Document automatic NUMA balancing sysctls Mel Gorman
2013-07-03 14:21 ` Mel Gorman
2013-07-03 14:21 ` [PATCH 02/13] sched: Track NUMA hinting faults on per-node basis Mel Gorman
2013-07-03 14:21 ` Mel Gorman
2013-07-03 14:21 ` [PATCH 03/13] sched: Select a preferred node with the most numa hinting faults Mel Gorman
2013-07-03 14:21 ` Mel Gorman
2013-07-03 14:21 ` [PATCH 04/13] sched: Update NUMA hinting faults once per scan Mel Gorman
2013-07-03 14:21 ` Mel Gorman
2013-07-03 14:21 ` [PATCH 05/13] sched: Favour moving tasks towards the preferred node Mel Gorman
2013-07-03 14:21 ` Mel Gorman
2013-07-03 14:21 ` [PATCH 06/13] sched: Reschedule task on preferred NUMA node once selected Mel Gorman
2013-07-03 14:21 ` Mel Gorman
2013-07-04 12:26 ` Srikar Dronamraju
2013-07-04 12:26 ` Srikar Dronamraju
2013-07-04 13:29 ` Mel Gorman
2013-07-04 13:29 ` Mel Gorman
2013-07-03 14:21 ` [PATCH 07/13] sched: Split accounting of NUMA hinting faults that pass two-stage filter Mel Gorman
2013-07-03 14:21 ` Mel Gorman
2013-07-03 21:56 ` Johannes Weiner
2013-07-03 21:56 ` Johannes Weiner
2013-07-04 9:23 ` Mel Gorman
2013-07-04 9:23 ` Mel Gorman
2013-07-04 14:24 ` Rik van Riel
2013-07-04 14:24 ` Rik van Riel
2013-07-04 19:36 ` Johannes Weiner
2013-07-04 19:36 ` Johannes Weiner
2013-07-05 9:41 ` Mel Gorman
2013-07-05 9:41 ` Mel Gorman
2013-07-05 10:48 ` Peter Zijlstra
2013-07-05 10:48 ` Peter Zijlstra
2013-07-03 14:21 ` [PATCH 08/13] sched: Increase NUMA PTE scanning when a new preferred node is selected Mel Gorman
2013-07-03 14:21 ` Mel Gorman
2013-07-03 14:21 ` [PATCH 09/13] sched: Favour moving tasks towards nodes that incurred more faults Mel Gorman
2013-07-03 14:21 ` Mel Gorman
2013-07-03 18:27 ` Peter Zijlstra
2013-07-03 18:27 ` Peter Zijlstra
2013-07-04 9:25 ` Mel Gorman
2013-07-04 9:25 ` Mel Gorman
2013-07-03 14:21 ` [PATCH 10/13] sched: Set the scan rate proportional to the size of the task being scanned Mel Gorman
2013-07-03 14:21 ` Mel Gorman
2013-07-03 14:21 ` [PATCH 11/13] sched: Check current->mm before allocating NUMA faults Mel Gorman
2013-07-03 14:21 ` Mel Gorman
2013-07-03 15:33 ` Mel Gorman
2013-07-03 15:33 ` Mel Gorman
2013-07-04 12:48 ` Srikar Dronamraju
2013-07-04 12:48 ` Srikar Dronamraju
2013-07-05 10:07 ` Mel Gorman
2013-07-05 10:07 ` Mel Gorman
2013-07-03 14:21 ` [PATCH 12/13] mm: numa: Scan pages with elevated page_mapcount Mel Gorman
2013-07-03 14:21 ` Mel Gorman
2013-07-03 18:35 ` Peter Zijlstra
2013-07-03 18:35 ` Peter Zijlstra
2013-07-04 9:27 ` Mel Gorman
2013-07-04 9:27 ` Mel Gorman
2013-07-03 18:41 ` Peter Zijlstra
2013-07-03 18:41 ` Peter Zijlstra
2013-07-04 9:32 ` Mel Gorman
2013-07-04 9:32 ` Mel Gorman
2013-07-03 18:42 ` Peter Zijlstra
2013-07-03 18:42 ` Peter Zijlstra
2013-07-03 14:21 ` [PATCH 13/13] sched: Account for the number of preferred tasks running on a node when selecting a preferred node Mel Gorman
2013-07-03 14:21 ` Mel Gorman
2013-07-03 18:32 ` Peter Zijlstra
2013-07-03 18:32 ` Peter Zijlstra
2013-07-04 9:37 ` Mel Gorman
2013-07-04 9:37 ` Mel Gorman
2013-07-04 13:07 ` Srikar Dronamraju
2013-07-04 13:07 ` Srikar Dronamraju
2013-07-04 13:54 ` Mel Gorman
2013-07-04 13:54 ` Mel Gorman
2013-07-04 14:06 ` Peter Zijlstra
2013-07-04 14:06 ` Peter Zijlstra
2013-07-04 14:40 ` Mel Gorman [this message]
2013-07-04 14:40 ` Mel Gorman
2013-07-03 16:19 ` [PATCH 0/13] Basic scheduler support for automatic NUMA balancing V2 Mel Gorman
2013-07-03 16:19 ` Mel Gorman
2013-07-03 16:26 ` Mel Gorman
2013-07-03 16:26 ` Mel Gorman
2013-07-04 18:02 ` [PATCH RFC WIP] Process weights based scheduling for better consolidation Srikar Dronamraju
2013-07-04 18:02 ` Srikar Dronamraju
2013-07-05 10:16 ` Peter Zijlstra
2013-07-05 10:16 ` Peter Zijlstra
2013-07-05 12:49 ` Srikar Dronamraju
2013-07-05 12:49 ` Srikar Dronamraju
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=20130704144018.GS1875@suse.de \
--to=mgorman@suse.de \
--cc=aarcange@redhat.com \
--cc=hannes@cmpxchg.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mingo@kernel.org \
--cc=peterz@infradead.org \
--cc=srikar@linux.vnet.ibm.com \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.