From: Andrew Cooper <andrew.cooper3@citrix.com>
To: Steven Haigh <netwiz@crc.id.au>
Cc: Roger Pau Monne <roger.pau@citrix.com>,
Jan Beulich <JBeulich@suse.com>,
"xen-devel@lists.xen.org" <xen-devel@lists.xen.org>
Subject: Re: 4.2.1: Poor write performance for DomU.
Date: Wed, 20 Feb 2013 12:48:03 +0000 [thread overview]
Message-ID: <5124C603.6000902@citrix.com> (raw)
In-Reply-To: <5124AECA.4060503@crc.id.au>
On 20/02/13 11:08, Steven Haigh wrote:
> On 20/02/2013 10:06 PM, Andrew Cooper wrote:
>> On 20/02/13 10:12, Jan Beulich wrote:
>>>>>> On 20.02.13 at 10:49, Steven Haigh <netwiz@crc.id.au> wrote:
>>>> My build of Xen 4.2.1 also has all of the recent security advisories
>>>> patched as well. Although it is interesting to note that
>>>> downgrading to
>>>> Xen 4.1.2 made no difference to write speeds.
>>> Not surprising at all, considering that the hypervisor is only a
>>> passive
>>> library for all PV I/O purposes. You're likely hunting for a kernel
>>> side
>>> regression (and hence the mentioning of the hypervisor version as
>>> the main factor in the subject is probably misleading).
>>>
>>> Jan
>>
>> Further to this, do try to verify if your disk driver has changed
>> recently to use >0 order page allocations for DMA. If it has, then
>> speed will be much slower as there will now be the swiotlb cpu-copy
>> overhead.
>
> Any hints on how to do this? ;)
>
> The kernel modules in use for my SATA drives are ahci and sata_mv.
> There are 6 drives in total on the system.
>
> sda + sdb = RAID1
> sd[c-f] = RAID6
>
> sda, sdb, sdc and sdd are on the onboard SATA controller (ahci)
> sde, sdf are on the sata_mv 4x PCIe controller.
>
Sadly that is a hard question to answer, and is driver specific. I cant
suggest an easy way other than digging into the source.
~Andrew
next prev parent reply other threads:[~2013-02-20 12:48 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-02-20 2:10 4.2.1: Poor write performance for DomU Steven Haigh
2013-02-20 8:26 ` Roger Pau Monné
2013-02-20 8:49 ` Steven Haigh
2013-02-20 9:49 ` Steven Haigh
2013-02-20 10:12 ` Jan Beulich
2013-02-20 11:06 ` Andrew Cooper
2013-02-20 11:08 ` Steven Haigh
2013-02-20 12:48 ` Andrew Cooper [this message]
2013-02-20 13:18 ` Pasi Kärkkäinen
2013-03-08 20:42 ` Konrad Rzeszutek Wilk
2013-03-08 8:54 ` Steven Haigh
2013-03-08 9:43 ` Roger Pau Monné
2013-03-08 9:46 ` Steven Haigh
2013-03-08 9:54 ` Roger Pau Monné
2013-03-08 20:49 ` Konrad Rzeszutek Wilk
2013-03-08 22:30 ` Steven Haigh
2013-03-11 13:30 ` Konrad Rzeszutek Wilk
2013-03-11 13:37 ` Steven Haigh
2013-03-12 13:04 ` Konrad Rzeszutek Wilk
2013-03-12 14:08 ` Steven Haigh
[not found] ` <514EA337.7030303@crc.id.au>
[not found] ` <514EA6B0.8010504@crc.id.au>
[not found] ` <514EA741.7050403@crc.id.au>
2013-03-24 9:10 ` Steven Haigh
2013-03-24 9:54 ` Steven Haigh
2013-03-25 2:21 ` Steven Haigh
2013-08-20 16:48 ` Konrad Rzeszutek Wilk
2013-08-20 18:25 ` Steven Haigh
2013-09-05 8:28 ` Steven Haigh
2013-09-06 13:33 ` Konrad Rzeszutek Wilk
2013-09-06 23:06 ` Steven Haigh
2013-09-06 23:37 ` Konrad Rzeszutek Wilk
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=5124C603.6000902@citrix.com \
--to=andrew.cooper3@citrix.com \
--cc=JBeulich@suse.com \
--cc=netwiz@crc.id.au \
--cc=roger.pau@citrix.com \
--cc=xen-devel@lists.xen.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.