linux-kernel - Re: [PATCH 00/21] perf, c2c: Add new tool to analyze cacheline contention on NUMA systems

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: <20140210221159.GT25953@redhat.com>
Date:	Mon, 10 Feb 2014 17:11:59 -0500
From:	Don Zickus <dzickus@...hat.com>
To:	Peter Zijlstra <peterz@...radead.org>
Cc:	acme@...stprotocols.net, LKML <linux-kernel@...r.kernel.org>,
	jolsa@...hat.com, jmario@...hat.com, fowles@...each.com,
	eranian@...gle.com
Subject: Re: [PATCH 00/21] perf, c2c: Add new tool to analyze cacheline
 contention on NUMA systems

On Mon, Feb 10, 2014 at 10:18:25PM +0100, Peter Zijlstra wrote:
> On Mon, Feb 10, 2014 at 12:28:55PM -0500, Don Zickus wrote:
> > With the introduction of NUMA systems, came the possibility of remote memory accesses.
> > Combine those remote memory accesses with contention on the remote node (ie a modified
> > cacheline) and you have a possibility for very long latencies.  These latencies can
> > bottleneck a program.
> > 
> > The program added by these patches, helps detect the situation where two nodes are
> > 'tugging' on the same _data_ cacheline.  The term used through out this program and
> > the various changelogs is called a HITM.  This means nodeX went to read a cacheline
> > and it was discovered to be loaded in nodeY's LLC cache (hence the cacheHIT). The 
> > remote cacheline was also in a 'M'odified state thus creating a 'HIT M' for hit in
> > a modified state.  HITMs can happen locally and remotely.  This program's interest
> > is mainly in remote HITMs as they cause the longest latencies.
> 
> All of that is true of the traditional SMP system too. Just use lower
> level caches.

Yup.  We just focused on the longer latencies which is the remote case.  I
think the idea was overflowing an L1 and L2 wasn't that hard, so the gain
on solving local LLC HITMs wouldn't be that much.  Maybe we are wrong.

Anyway, if this tool can help solve any bottlenecks, NUMA or non-NUMA,
that would be great. :-)

Cheers,
Don

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/