From: Asai Thambi S P <asamymuthupa@micron.com>
To: Jeff Moyer <jmoyer@redhat.com>
Cc: Alan Cox <alan@lxorguk.ukuu.org.uk>, linux-ide@vger.kernel.org
Subject: Re: New driver mtipx2xx submission
Date: Wed, 6 Jul 2011 15:39:21 -0600 [thread overview]
Message-ID: <4E14D609.1010404@micron.com> (raw)
In-Reply-To: <x49boxirnl8.fsf@segfault.boston.devel.redhat.com>
On 6/28/2011 9:18 AM, Jeff Moyer wrote:
> From the perf report, I would have guessed that the CPU utilization for
> the ahci test case would have been lower than the Micron block driver.
> Odd, I wonder what I'm missing. Asai, did you notice if any of the CPUs
> was completely pegged during testing with ahci?
Yes, whichever cpu was handling interrupts was pegged in both cases.
The driver is configured to use a single MSI interrupt.
You're using a NUMA
> box, right? I also wonder what the irq distribution looked like, and
> whether rq_affinity is hurting performance for the ahci case.
No, it's not a NUMA box. Our runs were done with rq_affinity=0. If you
think it would be helpful, we can re-run with rq_affinity=1.
Also,
> does the Micron driver do any sort of interrupt coalescing that maybe
> the ahci driver isn't doing?
>
We have a scheme to coalesce multiple completions into a single
interrupt. Both drivers were using this feature for these runs.
next prev parent reply other threads:[~2011-07-06 21:39 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-04-28 15:53 New driver mtipx2xx submission Asai Thambi Samymuthu Pattrayasamy (asamymuthupa) [CONTRACTOR]
2011-04-28 22:06 ` Alan Cox
2011-05-02 12:40 ` Asai Thambi Samymuthu Pattrayasamy (asamymuthupa) [CONTRACTOR]
2011-05-02 17:42 ` Alan Cox
2011-05-03 20:07 ` [PATCH 0/3] " Asai Thambi Samymuthu Pattrayasamy (asamymuthupa) [CONTRACTOR]
2011-05-11 17:40 ` Asai Thambi Samymuthu Pattrayasamy (asamymuthupa) [CONTRACTOR]
2011-05-11 19:20 ` Alan Cox
2011-05-21 2:26 ` Asai Thambi S P
2011-05-25 14:36 ` Jeff Moyer
[not found] ` <22A973199D2C2F46933448F6E7990A300239EA77@ntxboimbx31.micron.com>
2011-06-01 19:51 ` Jeff Moyer
2011-06-01 20:21 ` Alan Cox
2011-06-15 1:29 ` Asai Thambi S P
2011-06-15 14:43 ` Jeff Moyer
2011-06-27 23:38 ` Asai Thambi Samymuthu Pattrayasamy (asamymuthupa) [CONTRACTOR]
2011-06-28 15:18 ` Jeff Moyer
2011-06-28 15:31 ` Alan Cox
2011-06-28 15:38 ` Jeff Moyer
2011-07-06 21:43 ` Asai Thambi S P
2011-07-07 7:37 ` Alan Cox
2011-07-26 10:46 ` Alan Cox
2011-07-26 10:46 ` Alan Cox
2011-07-26 11:44 ` Christoph Hellwig
2011-07-26 11:49 ` Alan Cox
2011-07-26 18:50 ` Jeff Garzik
2011-07-29 18:13 ` Asai Thambi S P
2011-07-29 18:13 ` Asai Thambi S P
2011-08-11 18:36 ` Asai Thambi S P
2011-08-11 18:36 ` Asai Thambi S P
2011-07-06 21:39 ` Asai Thambi S P [this message]
2011-06-02 1:21 ` David Dillow
2011-06-15 1:33 ` Asai Thambi S P
2011-06-15 3:12 ` David Dillow
2011-05-02 18:40 ` Jeff Moyer
2011-05-02 18:52 ` Alan Cox
2011-05-03 15:04 ` Mark Lord
2011-05-03 15:07 ` Alan Cox
2011-05-03 15:08 ` Mark Lord
2011-05-03 15:02 ` Mark Lord
2011-05-12 14:39 ` Jeff Garzik
-- strict thread matches above, loose matches on Subject: below --
2011-05-03 11:09 Jordan_Hargrave
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=4E14D609.1010404@micron.com \
--to=asamymuthupa@micron.com \
--cc=alan@lxorguk.ukuu.org.uk \
--cc=jmoyer@redhat.com \
--cc=linux-ide@vger.kernel.org \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.