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  PHC 
Open Source and information security mailing list archives
 
Hash Suite for Android: free password hash cracker in your pocket
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date:   Mon, 17 Feb 2020 15:31:06 +0000
From:   Mel Gorman <mgorman@...hsingularity.net>
To:     Peter Zijlstra <peterz@...radead.org>
Cc:     Vincent Guittot <vincent.guittot@...aro.org>,
        Ingo Molnar <mingo@...nel.org>,
        Juri Lelli <juri.lelli@...hat.com>,
        Dietmar Eggemann <dietmar.eggemann@....com>,
        Steven Rostedt <rostedt@...dmis.org>,
        Ben Segall <bsegall@...gle.com>,
        Valentin Schneider <valentin.schneider@....com>,
        Phil Auld <pauld@...hat.com>, Hillf Danton <hdanton@...a.com>,
        LKML <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH 00/13] Reconcile NUMA balancing decisions with the load
 balancer v3

On Mon, Feb 17, 2020 at 03:52:16PM +0100, Peter Zijlstra wrote:
> On Mon, Feb 17, 2020 at 02:49:11PM +0100, Vincent Guittot wrote:
> > > Patches 4-5 are Vincent's and use very similar code patterns and logic
> > > between NUMA and load balancer. Patch 6 is a fix to Vincent's work that
> > > is necessary to avoid serious imbalances being introduced by the NUMA
> > 
> > Yes the test added in load_too_imbalanced() by patch 5 doesn't seem to
> > be a good choice.
> > I haven't remove it as it was done by your patch 6 but it might worth
> > removing it directly if a new version is needed
> 
> Aside of that, Vincent's patches look good to me.

Fully agreed, I think it's now much easier to understand the two balancers
when put side by side in addition to getting some performance gains.
Even if a regression is found, I think it'll be due to a workload seeing
an advantage when NUMA balancer constantly overrides the load balancer.
If that happens, the imbalance can be governed by adjust_numa_balance so
that the two balancers avoid fighting each other again.

-- 
Mel Gorman
SUSE Labs

Powered by blists - more mailing lists