Date: Wed, 03 Dec 2008 09:28:15 +0000 From: Richard Tector <richardtector@thekeelecentre.com> To: freebsd-stable@freebsd.org Cc: Jan Mikkelsen <janm@transactionware.com> Subject: Re: 7.1-PRERELEASE: arcmsr write performance problem Message-ID: <4936512F.5060406@thekeelecentre.com> In-Reply-To: <34C71E28-F128-4F83-80EF-75768172A59D@hiwaay.net> References: <2515BCEE3A2F4CBA8FFB9F1C052924AA@jmlaptop> <4934CB77.30906@transactionware.com> <34C71E28-F128-4F83-80EF-75768172A59D@hiwaay.net>
next in thread | previous in thread | raw e-mail | index | archive | help
[-- Attachment #1 --]
David Kelly wrote:
>
> On Dec 1, 2008, at 11:45 PM, Jan Mikkelsen wrote:
>
>> Replying to my own post ...
>>
>> I have done a test on the same machine comparing 6.3-p1 to 7.1-PRE.
>> The performance is the expected ~6MB/s (because of the lack of cache)
>> on 6.3-p1, so the BIOS change doesn't seem to be at fault.
>>
>> This seems to be a regression somewhere between 6.3 to 7.1. The Areca
>> driver is the same in 6.3 and 7.1, so the problem seems to be elsewhere.
>>
>> I think this is more than just a "performance" problem. The
>> observations with gstat showing extremely high ms/w values (I have
>> seen them as high as 22000) makes it look like IO completion
>> interrupts are being lost.
>>
>> Any suggestions on where to look next? Are there obvious candidates?
>
>
> ATA maximum block transfer has dropped from 128k to 64k in 7.x. Am not
> sure where the handle is to tweak it back up but has slowed peak thruput
> on my Dell PE400SC. Can watch with "systat -v"
>
> Worse, I have a stripped array of 2 drives that won't transfer more than
> 43k at a chunk because apparently the stripe metadata didn't align
> nicely on 64k multiples.
Would changes to ATA have affected arcmsr? As far as I know it is not
linked to the ATA subsystem at all, though it would explain some odd
instances of one of my machines becoming unresponsive a couple of times
a day.
Richard
[-- Attachment #2 --]
0 *H
01 0 + 0 *H
<000
*H
01 0 UUK10U
Staffordshire10 UKeele10U
The Keele Centre1/0-U&The Keele Centre Certificate Authority0
060929142538Z
100929142538Z01 0 UUK10U
Staffordshire10U
The Keele Centre10URichard Tector1/0- *H
richardtector@thekeelecentre.com00
*H
0 ;tbTjRsם N)B?fS?PYr ̏gxK?w;]؆!Lo -{,CzL`X0oA ,!
00 U 0 0, `HB
OpenSSL Generated Certificate0 U y56N|Ad¯. H0U #0 4@-MxoW01 0 UUK10U
Staffordshire10 UKeele10U
The Keele Centre1/0-U&The Keele Centre Certificate Authority Xl~ u0
*H
>a<<,a,u#8gfryQ31Zr_?&t Iooݔ_@ѝƶl!=7,C YE2&e5ss8 &K000
*H
01 0 UUK10U
Staffordshire10 UKeele10U
The Keele Centre1/0-U&The Keele Centre Certificate Authority0
060929142538Z
100929142538Z01 0 UUK10U
Staffordshire10U
The Keele Centre10URichard Tector1/0- *H
richardtector@thekeelecentre.com00
*H
0 ;tbTjRsם N)B?fS?PYr ̏gxK?w;]؆!Lo -{,CzL`X0oA ,!
00 U 0 0, `HB
OpenSSL Generated Certificate0 U y56N|Ad¯. H0U #0 4@-MxoW01 0 UUK10U
Staffordshire10 UKeele10U
The Keele Centre1/0-U&The Keele Centre Certificate Authority Xl~ u0
*H
>a<<,a,u#8gfryQ31Zr_?&t Iooݔ_@ѝƶl!=7,C YE2&e5ss8 &K10001 0 UUK10U
Staffordshire10 UKeele10U
The Keele Centre1/0-U&The Keele Centre Certificate Authority0 + 0 *H
1 *H
0 *H
1
081203092815Z0# *H
1fHƟ1q÷0R *H
1E0C0
*H
0*H
0
*H
@0+0
*H
(0 +71001 0 UUK10U
Staffordshire10 UKeele10U
The Keele Centre1/0-U&The Keele Centre Certificate Authority0 *H
101 0 UUK10U
Staffordshire10 UKeele10U
The Keele Centre1/0-U&The Keele Centre Certificate Authority0
*H
ek
RI@].tXV@7y[pvԡa]+֦ Y#uW!sR/u: @ER-}}h[$#~YcIO-FeËtkfq־
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?4936512F.5060406>