linux-kernel - Re: [PATCH] sched: Only migrate tasks due to interrupts on an idle CPU if prev and target CPUs share cache

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 for Android: free password hash cracker in your pocket

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

Message-ID: <20171216182808.gc63wdzpxqw5p732@techsingularity.net>
Date:   Sat, 16 Dec 2017 18:28:08 +0000
From:   Mel Gorman <mgorman@...hsingularity.net>
To:     Mike Galbraith <efault@....de>
Cc:     Peter Zijlstra <peterz@...radead.org>,
        Ingo Molnar <mingo@...hat.com>, linux-kernel@...r.kernel.org,
        Matt Fleming <matt@...eblueprint.co.uk>
Subject: Re: [PATCH] sched: Only migrate tasks due to interrupts on an idle
 CPU if prev and target CPUs share cache

On Fri, Dec 15, 2017 at 09:38:06PM +0100, Mike Galbraith wrote:
> On Fri, 2017-12-15 at 16:52 +0000, Mel Gorman wrote:
> > 
> > It's a small improvement...
> 
> From my log on corr.arch.suse.de (2x8 box)
> 
> 4.15.0.g2db767d-default
> Throughput 2665.88 MB/sec  8 clients  8 procs  max_latency=21.472 ms
> 4.15.0.g2db767d-default NO_WA_IDLE
> Throughput 3416.35 MB/sec  8 clients  8 procs  max_latency=9.825 ms
> 
> Not so small improvement.  WA_IDLE ripped corr up pretty bad, turning
> it off restored 4.4 performance.
> 

Sounds plausible. I expect it depends on the remote access latency as
well as whether the data gets prefetched fast enough.

-- 
Mel Gorman
SUSE Labs