linux-kernel - Re: [PATCH 2/3] sched/numa: Allow a floating imbalance between NUMA nodes

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Tue, 17 Nov 2020 14:44:38 +0000
From:   Mel Gorman <mgorman@...hsingularity.net>
To:     Vincent Guittot <vincent.guittot@...aro.org>
Cc:     LKML <linux-kernel@...r.kernel.org>,
        Ingo Molnar <mingo@...nel.org>,
        Peter Zijlstra <peterz@...radead.org>,
        Valentin Schneider <valentin.schneider@....com>,
        Juri Lelli <juri.lelli@...hat.com>
Subject: Re: [PATCH 2/3] sched/numa: Allow a floating imbalance between NUMA
 nodes

On Tue, Nov 17, 2020 at 03:24:56PM +0100, Vincent Guittot wrote:
> On Tue, 17 Nov 2020 at 14:42, Mel Gorman <mgorman@...hsingularity.net> wrote:
> >
> > Currently, an imbalance is only allowed when a destination node
> > is almost completely idle. This solved one basic class of problems
> > and was the cautious approach.
> >
> > This patch revisits the possibility that NUMA nodes can be imbalanced
> > until 25% of the CPUs are occupied. The reasoning behind 25% is somewhat
> > superficial -- it's half the cores when HT is enabled.  At higher
> > utilisations, balancing should continue as normal and keep things even
> > until scheduler domains are fully busy or over utilised.
> 
> This reminds me previous discussions on the same topic: how much
> imbalance is allowed that will not screw up the bandwidth of the node
> I'm worried that there is no topology insight in the decision like
> hyperthreading, or number of cpus in the LLC
> 

We still don't have a good answer for that. It could be a tunable I guess
but it would be horrible to tune properly.

-- 
Mel Gorman
SUSE Labs