linux-kernel - Re: [PATCH v3] sched/topology: Improve load balancing on AMD EPYC

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]

Message-ID: <20190723114248.GJ24383@techsingularity.net>
Date:   Tue, 23 Jul 2019 12:42:48 +0100
From:   Mel Gorman <mgorman@...hsingularity.net>
To:     Matt Fleming <matt@...eblueprint.co.uk>
Cc:     Peter Zijlstra <peterz@...radead.org>,
        linux-kernel@...r.kernel.org,
        "Suthikulpanit, Suravee" <Suravee.Suthikulpanit@....com>,
        "Lendacky, Thomas" <Thomas.Lendacky@....com>,
        Borislav Petkov <bp@...en8.de>
Subject: Re: [PATCH v3] sched/topology: Improve load balancing on AMD EPYC

On Tue, Jul 23, 2019 at 11:48:30AM +0100, Matt Fleming wrote:
> SD_BALANCE_{FORK,EXEC} and SD_WAKE_AFFINE are stripped in sd_init()
> for any sched domains with a NUMA distance greater than 2 hops
> (RECLAIM_DISTANCE). The idea being that it's expensive to balance
> across domains that far apart.
> 
> However, as is rather unfortunately explained in
> 
>   commit 32e45ff43eaf ("mm: increase RECLAIM_DISTANCE to 30")
> 
> the value for RECLAIM_DISTANCE is based on node distance tables from
> 2011-era hardware.
> 
> Current AMD EPYC machines have the following NUMA node distances:
> 
> node distances:
> node   0   1   2   3   4   5   6   7
>   0:  10  16  16  16  32  32  32  32
>   1:  16  10  16  16  32  32  32  32
>   2:  16  16  10  16  32  32  32  32
>   3:  16  16  16  10  32  32  32  32
>   4:  32  32  32  32  10  16  16  16
>   5:  32  32  32  32  16  10  16  16
>   6:  32  32  32  32  16  16  10  16
>   7:  32  32  32  32  16  16  16  10
> 
> where 2 hops is 32.
> 
> The result is that the scheduler fails to load balance properly across
> NUMA nodes on different sockets -- 2 hops apart.
> 
> For example, pinning 16 busy threads to NUMA nodes 0 (CPUs 0-7) and 4
> (CPUs 32-39) like so,
> 
>   $ numactl -C 0-7,32-39 ./spinner 16
> 
> causes all threads to fork and remain on node 0 until the active
> balancer kicks in after a few seconds and forcibly moves some threads
> to node 4.
> 
> Override node_reclaim_distance for AMD Zen.
> 
> Signed-off-by: Matt Fleming <matt@...eblueprint.co.uk>
> Cc: "Suthikulpanit, Suravee" <Suravee.Suthikulpanit@....com>
> Cc: Mel Gorman <mgorman@...hsingularity.net>
> Cc: "Lendacky, Thomas" <Thomas.Lendacky@....com>
> Cc: Borislav Petkov <bp@...en8.de>

Acked-by: Mel Gorman <mgorman@...hsingularity.net>

The only caveat I can think of is that a future generation of Zen might
take a different magic number than 32 as their remote distance. If or
when this happens, it'll need additional smarts but lacking a crystal
ball, we can cross that bridge when we come to it.

-- 
Mel Gorman
SUSE Labs