From: Don Zickus <dzickus@redhat.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Joe Mario <jmario@redhat.com>, Andi Kleen <andi@firstfloor.org>,
Davidlohr Bueso <davidlohr@hp.com>,
acme@ghostprotocols.net, LKML <linux-kernel@vger.kernel.org>,
jolsa@redhat.com, fowles@inreach.com, eranian@google.com,
Arnaldo Carvalho de Melo <acme@redhat.com>,
David Ahern <dsahern@gmail.com>,
Frederic Weisbecker <fweisbec@gmail.com>,
Mike Galbraith <efault@gmx.de>, Paul Mackerras <paulus@samba.org>,
Richard Fowles <rfowles@redhat.com>
Subject: Re: [PATCH 08/19] perf c2c: Shared data analyser
Date: Mon, 3 Mar 2014 15:30:34 -0500 [thread overview]
Message-ID: <20140303203034.GH25953@redhat.com> (raw)
In-Reply-To: <20140303184117.GL9987@twins.programming.kicks-ass.net>
On Mon, Mar 03, 2014 at 07:41:17PM +0100, Peter Zijlstra wrote:
> On Mon, Mar 03, 2014 at 01:07:00PM -0500, Joe Mario wrote:
> > If you only sample on the HITMs then you don't get the store misses.
> > That means you'll not be able to detect who is simultaneously tugging
> > on the same cache lines. That gives up much of the value of "perf
> > c2c".
>
> As long as you know which lines are hurting bringing in (loads) you can
> often figure out who is doing the stores on them.
If you are familar with the code I guess. One scenario that would be
difficult for is shared memory (ie databases) as it may not be obvious who
is writing to a cacheline.
>
> > As we developed this, we ended up settling on Ivy Bridge to get the
> > behavior we wanted.
>
> Wouldn't SNB also work?
We started with SNB, but because latency info was not working (due to a GO
bug) and some other event quirks, we found ourselves migrating to a more
stable IVB platform instead.
Now that we stablized our test case and tool, SNB may work. We just
haven't tried in along time.
Cheers,
Don
next prev parent reply other threads:[~2014-03-03 20:31 UTC|newest]
Thread overview: 56+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-02-28 17:42 [PATCH 00/19 V2] perf, c2c: Add new tool to analyze cacheline contention on NUMA systems Don Zickus
2014-02-28 17:42 ` [PATCH 01/19] Revert "perf: Disable PERF_RECORD_MMAP2 support" Don Zickus
2014-02-28 17:42 ` [PATCH 02/19] perf, sort: Add physid sorting based on mmap2 data Don Zickus
2014-03-19 10:45 ` Jiri Olsa
2014-03-19 13:36 ` Don Zickus
2014-02-28 17:42 ` [PATCH 03/19] perf, sort: Allow unique sorting instead of combining hist_entries Don Zickus
2014-02-28 17:42 ` [PATCH 04/19] perf: Allow ability to map cpus to nodes easily Don Zickus
2014-03-19 12:48 ` Jiri Olsa
2014-03-19 13:38 ` Don Zickus
2014-03-19 13:22 ` Jiri Olsa
2014-02-28 17:42 ` [PATCH 05/19] perf, kmem: Utilize the new generic cpunode_map Don Zickus
2014-02-28 17:42 ` [PATCH 06/19] perf: Fix stddev calculation Don Zickus
2014-02-28 17:42 ` [PATCH 07/19] perf, callchain: Add generic callchain print handler for stdio Don Zickus
2014-02-28 17:42 ` [PATCH 08/19] perf c2c: Shared data analyser Don Zickus
2014-02-28 19:08 ` Andi Kleen
2014-02-28 19:46 ` Don Zickus
2014-02-28 21:03 ` Davidlohr Bueso
2014-02-28 22:28 ` Joe Mario
2014-03-01 0:50 ` Andi Kleen
2014-03-03 14:13 ` Don Zickus
2014-03-03 15:05 ` Don Zickus
2014-03-03 17:23 ` Andi Kleen
2014-03-03 18:07 ` Joe Mario
2014-03-03 18:41 ` Peter Zijlstra
2014-03-03 18:58 ` Andi Kleen
2014-03-03 19:48 ` Peter Zijlstra
2014-03-03 20:32 ` Don Zickus
2014-03-03 21:38 ` Andi Kleen
2014-03-03 21:41 ` Don Zickus
2014-03-03 20:30 ` Don Zickus [this message]
2014-03-03 20:26 ` Don Zickus
2014-03-03 21:36 ` Andi Kleen
2014-03-04 9:42 ` Peter Zijlstra
2014-03-03 18:21 ` Davidlohr Bueso
2014-02-28 17:42 ` [PATCH 09/19] perf c2c: Dump raw records, decode data_src bits Don Zickus
2014-02-28 17:42 ` [PATCH 10/19] perf, c2c: Rework setup code to prepare for features Don Zickus
2014-02-28 17:43 ` [PATCH 11/19] perf, c2c: Add in sort on physid Don Zickus
2014-02-28 18:59 ` Andi Kleen
2014-02-28 19:44 ` Don Zickus
2014-03-01 1:07 ` Andi Kleen
2014-03-01 1:27 ` Namhyung Kim
2014-02-28 17:43 ` [PATCH 12/19] perf, c2c: Add stats to track data source bits and cpu to node maps Don Zickus
2014-02-28 17:43 ` [PATCH 13/19] perf, c2c: Sort based on hottest cache line Don Zickus
2014-02-28 17:43 ` [PATCH 14/19] perf, c2c: Display cacheline HITM analysis to stdout Don Zickus
2014-02-28 17:43 ` [PATCH 15/19] perf, c2c: Add callchain support Don Zickus
2014-03-19 13:00 ` Jiri Olsa
2014-03-19 13:53 ` Don Zickus
2014-03-19 14:05 ` Jiri Olsa
2014-02-28 17:43 ` [PATCH 16/19] perf, c2c: Output summary stats Don Zickus
2014-02-28 17:43 ` [PATCH 17/19] perf, c2c: Dump rbtree for debugging Don Zickus
2014-02-28 17:43 ` [PATCH 18/19] perf, c2c: Add symbol count table Don Zickus
2014-02-28 17:43 ` [PATCH 19/19] perf, c2c: Add shared cachline summary table Don Zickus
2014-02-28 18:57 ` [PATCH 00/19 V2] perf, c2c: Add new tool to analyze cacheline contention on NUMA systems Andi Kleen
2014-02-28 19:42 ` Don Zickus
2014-02-28 21:54 ` Andi Kleen
2014-03-03 14:04 ` Don Zickus
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20140303203034.GH25953@redhat.com \
--to=dzickus@redhat.com \
--cc=acme@ghostprotocols.net \
--cc=acme@redhat.com \
--cc=andi@firstfloor.org \
--cc=davidlohr@hp.com \
--cc=dsahern@gmail.com \
--cc=efault@gmx.de \
--cc=eranian@google.com \
--cc=fowles@inreach.com \
--cc=fweisbec@gmail.com \
--cc=jmario@redhat.com \
--cc=jolsa@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=paulus@samba.org \
--cc=peterz@infradead.org \
--cc=rfowles@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox