DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.co.uk;
	h=X-YMail-OSG:Received:X-Mailer:Date:From:Subject:To:Cc:MIME-Version:Content-Type:Content-Transfer-Encoding:Message-ID;
	b=XT2oqby8krXUUSp+C+/jQH/naQvGwZqSwNk5iUiCyIdi0++Ewv6I2dJtqu6DvSg974xuMvUUwXS9o5IluFNmOv+mDdJdKfdDTAljJhhgf69+L7/DiT98BXU5AcRiVISJ8zo/W5XQC/Y2lC5S/dsDKC/WlQW7T3N3Op/dWbXQYwY=;
Date: Thu, 13 Mar 2008 16:10:49 +0000 (GMT)
From: Glyn Astill <glynastill@yahoo.co.uk>
Subject: Re: Recomendations on raid controllers raid 1+0
To: Guillaume Smet <guillaume.smet@gmail.com>
Cc: pgsql-performance@postgresql.org
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: quoted-printable
Message-ID: <992988.82686.qm@web25812.mail.ukl.yahoo.com>

Bonie++ benchmarks below.=0A=0AI believe the the Perc 5/i Raid 10 mode is a=
ctually a span of mirrors, rather than the expected stripe of mirrors we sh=
ould expect from 1+0, and that this is the reason for the shitty performanc=
e.=0A=0A=0ARAID 5=0A=3D=3D=3D=3D=3D=3D=0AVersion  1.03       ------Sequenti=
al Output------ --Sequential Input- --Random-=0A                    -Per Ch=
r- --Block-- -Rewrite- -Per Chr- --Block-- --Seeks--=0AMachine        Size =
K/sec %CP K/sec %CP K/sec %CP K/sec %CP K/sec %CP  /sec %CP=0Away5a        =
32096M 55354  97 201375  59 109586  23 59934  97 427541  33 767.9   1=0A   =
                 ------Sequential Create------ --------Random Create-------=
-=0A                    -Create-- --Read--- -Delete-- -Create-- --Read--- -=
Delete--=0A              files  /sec %CP  /sec %CP  /sec %CP  /sec %CP  /se=
c %CP  /sec %CP=0A                 16 +++++ +++ +++++ +++ +++++ +++ +++++ +=
++ +++++ +++ +++++ +++=0Away5a,32096M,55354,97,201375,59,109586,23,59934,97=
,427541,33,767.9,1,16,+++++,+++,+++++,+++,+++++,+++,+++++,+++,+++++,+++,+++=
++,+++=0A=0ARAID 10=0A=3D=3D=3D=3D=3D=3D=3D=0AVersion  1.03       ------Seq=
uential Output------ --Sequential Input- --Random-=0A                    -P=
er Chr- --Block-- -Rewrite- -Per Chr- --Block-- --Seeks--=0AMachine        =
Size K/sec %CP K/sec %CP K/sec %CP K/sec %CP K/sec %CP  /sec %CP=0AWay5a   =
     32096M 53479  99 131640  33 66718  10 58225  95 339287  25 699.1   1=
=0A                    ------Sequential Create------ --------Random Create-=
-------=0A                    -Create-- --Read--- -Delete-- -Create-- --Rea=
d--- -Delete--=0A              files  /sec %CP  /sec %CP  /sec %CP  /sec %C=
P  /sec %CP  /sec %CP=0A                 16 +++++ +++ +++++ +++ +++++ +++ +=
++++ +++ +++++ +++ +++++ +++=0AWay5a,32096M,53479,99,131640,33,66718,10,582=
25,95,339287,25,699.1,1,16,+++++,+++,+++++,+++,+++++,+++,+++++,+++,+++++,++=
+,+++++,+++=0A=0A=0A----- Original Message ----=0A> From: Guillaume Smet <g=
uillaume.smet@gmail.com>=0A> To: Glyn Astill <glynastill@yahoo.co.uk>=0A> C=
c: pgsql-performance@postgresql.org=0A> Sent: Thursday, 13 March, 2008 3:58=
:41 PM=0A> Subject: Re: [PERFORM] Recomendations on raid controllers raid 1=
+0=0A> =0A> Glyn,=0A> =0A> On Thu, Mar 13, 2008 at 1:33 PM, Glyn Astill wro=
te:=0A> > I'm looking at switching out the perc5i (lsi megaraid) cards from=
 our=0A> > Dell 2950s for something else as they're crap at raid 10.=0A> =
=0A> Do you have numbers? Perc 5/i cards perform quite well for us (we have=
=0A> a 8 disks RAID 10 in a 2900 server with the traditional Perc 5/i).=0A>=
 =0A> --=0A> Guillaume=0A=0A=0A      ______________________________________=
_____________________ =0ARise to the challenge for Sport Relief with Yahoo!=
 For Good  =0A=0Ahttp://uk.promotions.yahoo.com/forgood/