LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Rik van Riel <riel@surriel.com>
To: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@kernel.org>,
	Peter Zijlstra <peterz@infradead.org>,
	LKML <linux-kernel@vger.kernel.org>,
	Mel Gorman <mgorman@techsingularity.net>,
	Thomas Gleixner <tglx@linutronix.de>
Subject: Re: [PATCH 16/19] sched/numa: Detect if node actively handling migration
Date: Tue, 05 Jun 2018 09:07:54 -0400	[thread overview]
Message-ID: <1528204074.7898.126.camel@surriel.com> (raw)
In-Reply-To: <20180605035616.GD30328@linux.vnet.ibm.com>

[-- Attachment #1: Type: text/plain, Size: 2913 bytes --]

On Mon, 2018-06-04 at 20:56 -0700, Srikar Dronamraju wrote:
> * Rik van Riel <riel@surriel.com> [2018-06-04 16:05:55]:
> 
> > On Mon, 2018-06-04 at 15:30 +0530, Srikar Dronamraju wrote:
> > 
> > > @@ -1554,6 +1562,9 @@ static void task_numa_compare(struct
> > > task_numa_env *env,
> > >  	if (READ_ONCE(dst_rq->numa_migrate_on))
> > >  		return;
> > >  
> > > +	if (*move && READ_ONCE(pgdat->active_node_migrate))
> > > +		*move = false;
> > 
> > Why not do this check in task_numa_find_cpu?
> > 
> > That way you won't have to pass this in as a
> > pointer, and you also will not have to recalculate
> > NODE_DATA(cpu_to_node(env->dst_cpu)) for every CPU.
> > 
> 
> I thought about this. Lets say we evaluated that destination node can
> allow movement. While we iterate through the list of cpus trying to
> find
> the best cpu node, we find a idle cpu towards the end of the list.
> However if another task as already raced with us to move a task to
> this
> node, then we should bail out. Keeping the check in task_numa_compare
> will allow us to do this.

Your check is called once for every invocation
of task_numa_compare. It does not matter whether
it is inside or outside, except on the outside
the variable manipulation will be easier to read.

> > > +	 * task migration might only result in ping pong
> > > +	 * of tasks and also hurt performance due to cache
> > > +	 * misses.
> > > +	 */
> > > +	if (imp < SMALLIMP || imp <= env->best_imp + SMALLIMP /
> > > 2)
> > > +		goto unlock;
> > 
> > I can see a use for the first test, but why limit the
> > search for the best score once you are past the
> > threshold?
> > 
> > I don't understand the use for that second test.
> > 
> 
> Lets say few threads are racing with each other to find a cpu on the
> node. The first thread has already found a task/cpu 'A' to swap and
> finds another task/cpu 'B' thats slightly better than the current
> best_cpu which is 'A'. Currently we allow the second task/cpu 'B' to
> be
> set as best_cpu. However the second or subsequent threads cannot find
> the first task/cpu A because its suppose to be in active migration.
> By
> the time it reaches task/cpu B even that may look to be in active
> migration. It may never know that task/cpu A was cleared. In this
> way,
> the second and subsequent threads may not get a task/cpu in the
> preferred node to swap just because the first task kept hopping
> task/cpu
> as its choice of migration.
> 
> While we can't complete avoid this, the second check will try to make
> sure we don't hop on/hop off just for small incremental numa
> improvement.

However, all those racing tasks start searching
the CPUs on a node from the same start position.

That means they may all get stuck on the same
task/cpu A, and not select the better task/cpu B.

What am I missing? 

-- 
All Rights Reversed.

[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 488 bytes --]

  reply	other threads:[~2018-06-05 13:08 UTC|newest]

Thread overview: 66+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-06-04 10:00 [PATCH 00/19] Fixes for sched/numa_balancing Srikar Dronamraju
2018-06-04 10:00 ` [PATCH 01/19] sched/numa: Remove redundant field Srikar Dronamraju
2018-06-04 14:53   ` Rik van Riel
2018-06-05  8:41   ` Mel Gorman
2018-06-04 10:00 ` [PATCH 02/19] sched/numa: Evaluate move once per node Srikar Dronamraju
2018-06-04 14:51   ` Rik van Riel
2018-06-04 15:45     ` Srikar Dronamraju
2018-06-04 10:00 ` [PATCH 03/19] sched/numa: Simplify load_too_imbalanced Srikar Dronamraju
2018-06-04 14:57   ` Rik van Riel
2018-06-05  8:46   ` Mel Gorman
2018-06-04 10:00 ` [PATCH 04/19] sched/numa: Set preferred_node based on best_cpu Srikar Dronamraju
2018-06-04 12:18   ` Peter Zijlstra
2018-06-04 12:53     ` Srikar Dronamraju
2018-06-04 12:23   ` Peter Zijlstra
2018-06-04 12:59     ` Srikar Dronamraju
2018-06-04 13:39       ` Peter Zijlstra
2018-06-04 13:48         ` Srikar Dronamraju
2018-06-04 14:37       ` Rik van Riel
2018-06-04 15:56         ` Srikar Dronamraju
2018-06-04 10:00 ` [PATCH 05/19] sched/numa: Use task faults only if numa_group is not yet setup Srikar Dronamraju
2018-06-04 12:24   ` Peter Zijlstra
2018-06-04 13:09     ` Srikar Dronamraju
2018-06-04 10:00 ` [PATCH 06/19] sched/debug: Reverse the order of printing faults Srikar Dronamraju
2018-06-04 16:28   ` Rik van Riel
2018-06-05  8:50   ` Mel Gorman
2018-06-04 10:00 ` [PATCH 07/19] sched/numa: Skip nodes that are at hoplimit Srikar Dronamraju
2018-06-04 16:27   ` Rik van Riel
2018-06-05  8:50   ` Mel Gorman
2018-06-04 10:00 ` [PATCH 08/19] sched/numa: Remove unused task_capacity from numa_stats Srikar Dronamraju
2018-06-04 16:28   ` Rik van Riel
2018-06-05  8:57   ` Mel Gorman
2018-06-04 10:00 ` [PATCH 09/19] sched/numa: Modify migrate_swap to accept additional params Srikar Dronamraju
2018-06-04 17:00   ` Rik van Riel
2018-06-05  8:58   ` Mel Gorman
2018-06-04 10:00 ` [PATCH 10/19] sched/numa: Stop multiple tasks from moving to the cpu at the same time Srikar Dronamraju
2018-06-04 17:57   ` Rik van Riel
2018-06-05  9:51   ` Mel Gorman
2018-06-04 10:00 ` [PATCH 11/19] sched/numa: Restrict migrating in parallel to the same node Srikar Dronamraju
2018-06-04 17:59   ` Rik van Riel
2018-06-05  9:53   ` Mel Gorman
2018-06-06 12:58     ` Srikar Dronamraju
2018-06-04 10:00 ` [PATCH 12/19] sched:numa Remove numa_has_capacity Srikar Dronamraju
2018-06-04 18:07   ` Rik van Riel
2018-06-04 10:00 ` [PATCH 13/19] mm/migrate: Use xchg instead of spinlock Srikar Dronamraju
2018-06-04 18:22   ` Rik van Riel
2018-06-04 19:28   ` Peter Zijlstra
2018-06-05  7:24     ` Srikar Dronamraju
2018-06-05  8:16       ` Peter Zijlstra
2018-06-04 10:00 ` [PATCH 14/19] sched/numa: Updation of scan period need not be in lock Srikar Dronamraju
2018-06-04 18:24   ` Rik van Riel
2018-06-04 10:00 ` [PATCH 15/19] sched/numa: Use group_weights to identify if migration degrades locality Srikar Dronamraju
2018-06-04 18:56   ` Rik van Riel
2018-06-04 10:00 ` [PATCH 16/19] sched/numa: Detect if node actively handling migration Srikar Dronamraju
2018-06-04 20:05   ` Rik van Riel
2018-06-05  3:56     ` Srikar Dronamraju
2018-06-05 13:07       ` Rik van Riel [this message]
2018-06-06 12:55         ` Srikar Dronamraju
2018-06-06 13:55           ` Rik van Riel
2018-06-06 15:32             ` Srikar Dronamraju
2018-06-06 17:06               ` Rik van Riel
2018-06-04 10:00 ` [PATCH 17/19] sched/numa: Pass destination cpu as a parameter to migrate_task_rq Srikar Dronamraju
2018-06-04 10:00 ` [PATCH 18/19] sched/numa: Reset scan rate whenever task moves across nodes Srikar Dronamraju
2018-06-04 20:08   ` Rik van Riel
2018-06-05  9:58   ` Mel Gorman
2018-06-06 13:47     ` Srikar Dronamraju
2018-06-04 10:00 ` [PATCH 19/19] sched/numa: Move task_placement closer to numa_migrate_preferred 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=1528204074.7898.126.camel@surriel.com \
    --to=riel@surriel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mgorman@techsingularity.net \
    --cc=mingo@kernel.org \
    --cc=peterz@infradead.org \
    --cc=srikar@linux.vnet.ibm.com \
    --cc=tglx@linutronix.de \
    --subject='Re: [PATCH 16/19] sched/numa: Detect if node actively handling migration' \
    /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

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).