Received: from localhost (unknown [200.46.204.183]) by mail.postgresql.org (Postfix) with ESMTP id 618E064FC57 for ; Wed, 10 Dec 2008 03:59:07 -0400 (AST) Received: from mail.postgresql.org ([200.46.204.86]) by localhost (mx1.hub.org [200.46.204.183]) (amavisd-maia, port 10024) with ESMTP id 72269-04 for ; Wed, 10 Dec 2008 03:59:01 -0400 (AST) X-Greylist: from auto-whitelisted by SQLgrey-1.7.6 Received: from EXHUB018-1.exch018.msoutlookonline.net (exhub018-1.exch018.msoutlookonline.net [64.78.17.16]) by mail.postgresql.org (Postfix) with ESMTP id CD40064FC4C for ; Wed, 10 Dec 2008 03:59:00 -0400 (AST) Received: from EXVMBX018-1.exch018.msoutlookonline.net ([64.78.17.47]) by EXHUB018-1.exch018.msoutlookonline.net ([64.78.17.16]) with mapi; Tue, 9 Dec 2008 23:58:59 -0800 From: Scott Carey To: Mario Weilguni , Scott Marlowe CC: Alan Hodgson , "pgsql-performance@postgresql.org" Date: Tue, 9 Dec 2008 23:58:57 -0800 Subject: Re: Experience with HP Smart Array P400 and SATA drives? Thread-Topic: [PERFORM] Experience with HP Smart Array P400 and SATA drives? Thread-Index: Aclam1WJAOg5B/ewS/uywblQ/xqkYgAAdGeH Message-ID: In-Reply-To: <493F739C.9080800@sime.com> Accept-Language: en-US Content-Language: en X-MS-Has-Attach: X-MS-TNEF-Correlator: acceptlanguage: en-US Content-Type: multipart/alternative; boundary="_000_C564B6C1FCFscottrichrelevancecom_" MIME-Version: 1.0 X-Virus-Scanned: Maia Mailguard 1.0.1 X-Spam-Status: No, hits=0.001 tagged_above=0 required=5 tests=HTML_MESSAGE=0.001 X-Spam-Level: X-Archive-Number: 200812/110 X-Sequence-Number: 32146 --_000_C564B6C1FCFscottrichrelevancecom_ Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable It could be the drives, it could be a particular interaction between them a= nd the drivers or firmware. Do you know if NCQ is activated for them? Can you test a single drive JBOD through the array to the same drive throug= h something else, perhaps the motherboard's SATA port? You may also have better luck with software raid-0 on top of 2 4 disk raid = 5's or raid 10s. But not if a single disk JBOD still performs well under p= ar. You may need new drivers for the card, or firmware for the drive and = or card. Or, the card may simply be incompatible with those drives. I've = seen several hard drive - raid card incompatibilities before. On 12/9/08 11:45 PM, "Mario Weilguni" wrote: Scott Marlowe schrieb: > On Tue, Dec 9, 2008 at 5:17 AM, Mario Weilguni wrote= : > >> Alan Hodgson schrieb: >> >>>>>>> Mario Weilguni wrote: >>>>>>> >>>>>>> >>>>> strange values. An individual drive is capable of delivering 91 >>>>> MB/sec >>>>> sequential read performance, and we get values ~102MB/sec out of= a >>>>> 8-drive RAID5, seems to be ridiculous slow. >>>>> >>> What command are you using to test the reads? >>> >>> Some recommendations to try: >>> >>> 1) /sbin/blockdev --setra 2048 device (where device is the partition or >>> LVM volume) >>> >>> 2) Use XFS, and make sure your stripe settings match the RAID. >>> >>> Having said that, 102MB/sec sounds really low for any modern controller >>> with 8 drives, regardless of tuning or filesystem choice. >>> >>> >>> >> First, thanks alot for this and all the other answers. >> >> I measured the raw device performance: >> dd if=3D/dev/cciss/c0d0 bs=3D64k count=3D100000 of=3D/dev/null >> >> I get poor performance when all 8 drives are configured as one, large >> RAID-5, and slightly poorer performance when configured as JBOD. In >> production, we use XFS as FS, but I doubt this has anything to do with F= S >> tuning. >> > > Yeah, having just trawled the pgsql-performance archives, there are > plenty of instances of people having terrible performance from HP > smart array controllers before the P800. Is it possible for you to > trade up to a better RAID controller? Whichever salesman sold you the > P400 should take one for the team and make this right for you. > > A customer of us uses the P400 on a different machine, 8 SAS drives (Raid 5 as well), and the performance is very, very good. So we thought it's a good choice. Maybe the SATA drives are the root of this problem? -- Sent via pgsql-performance mailing list (pgsql-performance@postgresql.org) To make changes to your subscription: http://www.postgresql.org/mailpref/pgsql-performance --_000_C564B6C1FCFscottrichrelevancecom_ Content-Type: text/html; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable Re: [PERFORM] Experience with HP Smart Array P400 and SATA drives?</= TITLE> </HEAD> <BODY> <FONT FACE=3D"Calibri, Verdana, Helvetica, Arial"><SPAN STYLE=3D'font-size:= 11pt'>It could be the drives, it could be a particular interaction between = them and the drivers or firmware.<BR> <BR> Do you know if NCQ is activated for them?<BR> Can you test a single drive JBOD through the array to the same drive throug= h something else, perhaps the motherboard’s SATA port?<BR> <BR> You may also have better luck with software raid-0 on top of 2 4 disk raid = 5’s or raid 10s.  But not if a single disk JBOD still performs w= ell under par.  You may need new drivers for the card, or firmware for= the drive  and or card.  Or, the card may simply be incompatible= with those drives.  I’ve seen several hard drive – raid c= ard incompatibilities before. <BR> <BR> <BR> <BR> On 12/9/08 11:45 PM, "Mario Weilguni" <<a href=3D"mweilguni@si= me.com">mweilguni@sime.com</a>> wrote:<BR> <BR> </SPAN></FONT><BLOCKQUOTE><FONT FACE=3D"Calibri, Verdana, Helvetica, Arial"= ><SPAN STYLE=3D'font-size:11pt'>Scott Marlowe schrieb:<BR> > On Tue, Dec 9, 2008 at 5:17 AM, Mario Weilguni <<a href=3D"mweilgun= i@sime.com">mweilguni@sime.com</a>> wrote:<BR> ><BR> >> Alan Hodgson schrieb:<BR> >><BR> >>>>>>> Mario Weilguni <<a href=3D"mweilguni@sime.c= om">mweilguni@sime.com</a>> wrote:<BR> >>>>>>><BR> >>>>>>><BR> >>>>> strange values. An individual drive is capable of deli= vering 91<BR> >>>>> MB/sec<BR> >>>>>      sequential read performa= nce, and we get values ~102MB/sec out of a<BR> >>>>> 8-drive RAID5, seems to be ridiculous slow.<BR> >>>>><BR> >>> What command are you using to test the reads?<BR> >>><BR> >>> Some recommendations to try:<BR> >>><BR> >>> 1) /sbin/blockdev --setra 2048 device (where device is the par= tition or<BR> >>> LVM volume)<BR> >>><BR> >>> 2) Use XFS, and make sure your stripe settings match the RAID.= <BR> >>><BR> >>> Having said that, 102MB/sec sounds really low for any modern c= ontroller<BR> >>> with 8 drives, regardless of tuning or filesystem choice.<BR> >>><BR> >>><BR> >>><BR> >> First, thanks alot for this and all the other answers.<BR> >><BR> >> I measured the raw device performance:<BR> >> dd if=3D/dev/cciss/c0d0 bs=3D64k count=3D100000 of=3D/dev/null<BR> >><BR> >> I get poor performance when all 8 drives are configured as one, la= rge<BR> >> RAID-5, and slightly poorer performance when configured as JBOD. I= n<BR> >> production, we use XFS as FS, but I doubt this has anything to do = with FS<BR> >> tuning.<BR> >><BR> ><BR> > Yeah, having just trawled the pgsql-performance archives, there are<BR= > > plenty of instances of people having terrible performance from HP<BR> > smart array controllers before the P800.  Is it possible for you = to<BR> > trade up to a better RAID controller?  Whichever salesman sold yo= u the<BR> > P400 should take one for the team and make this right for you.<BR> ><BR> ><BR> A customer of us uses the P400 on a different machine, 8 SAS drives<BR> (Raid 5 as well), and the performance is very, very good. So we thought<BR> it's a good choice. Maybe the SATA drives are the root of this problem?<BR> <BR> <BR> <BR> --<BR> Sent via pgsql-performance mailing list (<a href=3D"pgsql-performance@postg= resql.org">pgsql-performance@postgresql.org</a>)<BR> To make changes to your subscription:<BR> <a href=3D"http://www.postgresql.org/mailpref/pgsql-performance">http://www= .postgresql.org/mailpref/pgsql-performance</a><BR> <BR> </SPAN></FONT></BLOCKQUOTE> </BODY> </HTML> --_000_C564B6C1FCFscottrichrelevancecom_--