From: "Kevin P. Fleming" <kpfleming@backtobasicsmgmt.com>
To: linux-lvm@redhat.com
Cc: Miquel van Smoorenburg <miquels@cistron.nl>
Subject: Re: [linux-lvm] Re: IO scheduler, queue depth, nr_requests
Date: Mon Feb 16 19:32:00 2004 [thread overview]
Message-ID: <40316114.30207@backtobasicsmgmt.com> (raw)
In-Reply-To: <20040216133047.GA9330@suse.de>
Jens Axboe wrote:
> On Mon, Feb 16 2004, Miquel van Smoorenburg wrote:
>
>>Hello,
>>
>> as you might have seen from the linux-kernel mailinglist
>>I have been testing for months now with a fileserver set up to
>>use XFS over LVM2 on a 3ware RAID5 controller.
>>
I too have been fighting lower-than-expected performance with this
identical combination, other than using a P4 2.8GHz instead of 3.0GHz,
and 1GB RAM instead of 2GB. My 3ware 8506-8 has six Seagate Barracuda
SATA drives behind it, which are very fast on their own :-) Try as I
might, with the 2.6 kernel I have not been able to generate a bonnie++
or iozone run that provided performance better than a single disk, even
with the 3ware card in JBOD, RAID-0 or RAID-1 mode. I had been
conversing with 3ware about it, but to no real effect given than they
don't support 2.6 yet.
>>By fiddling about today I just found that changing
>>/sys/block/sda/queue/nr_requests from 128 to something above
>>the queue depth of the 3ware controller (256 doesn't work,
>>384 and up do) also fixes the problem.
I will try this as well this evening and report my results.
next prev parent reply other threads:[~2004-02-17 0:33 UTC|newest]
Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top
2004-02-16 9:11 [linux-lvm] IO scheduler, queue depth, nr_requests Miquel van Smoorenburg
2004-02-16 8:30 ` [linux-lvm] " Jens Axboe
2004-02-16 9:01 ` Joe Thornber
2004-02-16 19:32 ` Kevin P. Fleming [this message]
2004-02-17 1:46 ` Kevin P. Fleming
2004-02-18 10:29 ` Miquel van Smoorenburg
2004-02-19 8:51 ` Miquel van Smoorenburg
2004-02-19 8:50 ` Andrew Morton
2004-02-19 9:08 ` Miquel van Smoorenburg
2004-02-19 9:08 ` Andrew Morton
2004-02-19 10:23 ` Miquel van Smoorenburg
2004-02-19 10:26 ` Jens Axboe
2004-02-19 15:58 ` Miquel van Smoorenburg
2004-02-19 17:52 ` Nick Piggin
2004-02-19 18:52 ` Miquel van Smoorenburg
2004-02-19 19:15 ` Nick Piggin
2004-02-19 20:16 ` [linux-lvm] [PATCH] per process request limits (was Re: IO scheduler, queue depth, nr_requests) Nick Piggin
2004-02-19 20:25 ` [linux-lvm] " Andrew Morton
2004-02-19 20:40 ` Nick Piggin
2004-02-19 21:32 ` Andrew Morton
2004-02-23 8:41 ` [linux-lvm] [PATCH] bdi_congestion_funp (was: Re: [PATCH] per process request limits (was Re: IO scheduler, queue depth, nr_requests)) Miquel van Smoorenburg
2004-02-20 9:56 ` [linux-lvm] " Joe Thornber
2004-02-20 9:59 ` Jens Axboe
2004-02-23 8:45 ` Miquel van Smoorenburg
2004-02-22 14:55 ` Andrew Morton
2004-02-20 9:57 ` Jens Axboe
2004-02-24 12:54 ` [linux-lvm] Queue congestion: passing down vs passing up [PATCH] Miquel van Smoorenburg
2004-02-19 20:52 ` [linux-lvm] Re: [PATCH] per process request limits (was Re: IO scheduler, queue depth, nr_requests) Nick Piggin
2004-02-19 9:11 ` [linux-lvm] Re: IO scheduler, queue depth, nr_requests Nick Piggin
2004-02-19 10:26 ` Jens Axboe
2004-02-19 8:51 ` Nick Piggin
2004-02-19 9:00 ` Miquel van Smoorenburg
2004-02-19 9:00 ` Nick Piggin
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=40316114.30207@backtobasicsmgmt.com \
--to=kpfleming@backtobasicsmgmt.com \
--cc=linux-lvm@redhat.com \
--cc=miquels@cistron.nl \
/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