X-Original-To: pgsql-performance-postgresql.org@postgresql.org Received: from localhost (mx1.hub.org [200.46.208.251]) by postgresql.org (Postfix) with ESMTP id F00809FB23B for ; Wed, 2 Aug 2006 18:44:21 -0300 (ADT) Received: from postgresql.org ([200.46.204.71]) by localhost (mx1.hub.org [200.46.208.251]) (amavisd-new, port 10024) with ESMTP id 93371-01 for ; Wed, 2 Aug 2006 18:44:13 -0300 (ADT) X-Greylist: domain auto-whitelisted by SQLgrey- Received: from mail.gmx.net (mail.gmx.de [213.165.64.21]) by postgresql.org (Postfix) with SMTP id DC90D9FB233 for ; Wed, 2 Aug 2006 18:44:13 -0300 (ADT) Received: (qmail invoked by alias); 02 Aug 2006 21:44:10 -0000 Received: from dslb-084-057-001-183.pools.arcor-ip.net (EHLO ltmku) [84.57.1.183] by mail.gmx.net (mp031) with SMTP; 02 Aug 2006 23:44:10 +0200 X-Authenticated: #23352258 From: "Milen Kulev" To: "'Steve Poe'" Cc: Subject: Re: XFS filessystem for Datawarehousing Date: Wed, 2 Aug 2006 23:44:06 +0200 Message-ID: <01ec01c6b67c$c76717a0$0a00a8c0@trivadis.com> MIME-Version: 1.0 Content-Type: multipart/alternative; boundary="----=_NextPart_000_01ED_01C6B68D.8AEFE7A0" X-Priority: 3 (Normal) X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook, Build 10.0.6626 Importance: Normal X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2800.1441 In-Reply-To: <721b21dc0608021426p26d2a79ap37e0f55b2328b453@mail.gmail.com> X-Y-GMX-Trusted: 0 X-Virus-Scanned: Maia Mailguard 1.0.1 X-Spam-Status: No, hits=0.316 tagged_above=0 required=5 tests=AWL, FORGED_RCVD_HELO, HTML_30_40, HTML_MESSAGE, SPF_PASS X-Spam-Level: X-Archive-Number: 200608/29 X-Sequence-Number: 20214 This is a multi-part message in MIME format. ------=_NextPart_000_01ED_01C6B68D.8AEFE7A0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable Hi Steve,=20 I hope that performance between EXT3 and XFS is not only 5-8% . Such = a small difference could be interpreted as "noise", as you already mentioned. I want to give many filesystem a try. Stability is also a concern, but I = don't want to favour any FS over another . =20 Best Regards. MIlen Kulev =20 -----Original Message----- From: Steve Poe [mailto:steve.poe@gmail.com]=20 Sent: Wednesday, August 02, 2006 11:27 PM To: Milen Kulev Cc: pgsql-performance@postgresql.org Subject: Re: [PERFORM] XFS filessystem for Datawarehousing Milen, For the past year, I have been running odbc-bench on a dual-opteron = with 4GB of RAM using a 8GB sample data. I found the performance difference between EXT3, JFS, and XFS is +/- 5-8%. This = could be written-off as "noise" just for normal server performance flux. If you plan on using the default kernel, ext3 = will likely perform best (what I found). When I added my own kernel, ext3 performed fair. What I've had to consider is = what does each file system offer me as far as data integrity goes. =20 You'll find greater ROI on performance by investing your time in other = areas than chasing down a few percentage point (like I have done). If you could borrow more RAM and/or more discs for = your tests, Testing newer kernels and read-ahead patches may benefit you as well. Best of luck. Steve Poe On 8/2/06, Milen Kulev wrote:=20 Hi Like, Mark , Alvaro and Andrew, Thank you very much for sharing you experience with me. I want to compare DHW performance of PG/Bizgres on different filesystems = and difffrent Block sizes. The hardware will be free for me in a week or too (at a moment another = project is running on it) and then I will test=20 diffrenet setups and will post the results. I MUST (sorry, no other choice) use SLES6 R3, 64 bit. I am not sure at = all that I will get enough budget to get approapriate RAID controller, and that is why I intent to use software = RAID.=20 I am pretty exited whether XFS will clearly outpertform ETX3 (no default = setups for both are planned !). I am not sure whether is it worth to include JFS in comparison too ... Best Regards, Milen Kulev -----Original Message----- From: Luke Lonergan [mailto: llonergan@greenplum.com = ] Sent: Wednesday, August 02, 2006 4:43 AM To: Milen Kulev; pgsql-performance@postgresql.org Subject: Re: [PERFORM] XFS filessystem for Datawarehousing=20 Milen, On 8/1/06 2:49 PM, "Milen Kulev" wrote: > Is anyone using XFS for storing/retrieving relatively large amount of > data (~ 200GB)? I concur with the previous poster's experiences with one additional observation: We have had instabilities with XFS with software RAID (md) on 32-bit = Xeons running RedHat4 U3 with the Centos 4.3 unsupported SMP kernel. XFS would occasionally kernel panic under load. We have had no problems with XFS running on the same OS/kernel on 64-bit = under heavy workloads for weeks of continuous usage. Each server (of 16=20 total) had four XFS filesystems, each with 250GB of table data (no = indexes) on them, total of 16 Terabytes. We tested with the TPC-H schema and queries. We use the default settings for XFS. Also - be aware that LVM has a serious performance bottleneck at about = 600MB/s - if you are working below that=20 threshold, you may not notice the issue, maybe some increase in CPU = consumption as you approach it. - Luke ---------------------------(end of broadcast)--------------------------- TIP 3: Have you checked our extensive FAQ?=20 http://www.postgresql.org/docs/faq ------=_NextPart_000_01ED_01C6B68D.8AEFE7A0 Content-Type: text/html; charset="us-ascii" Content-Transfer-Encoding: quoted-printable Nachricht
Hi=20 Steve,
I hope=20 that  performance between  EXT3 and XFS is not only  5-8% = . Such=20 a small difference could be interpreted  as "noise", as you already = mentioned.
I want=20 to give many filesystem a try. Stability is also a concern, but I don't = want to=20 favour any FS over another .
 
Best=20 Regards.
MIlen=20 Kulev
 
-----Original Message-----
From: Steve Poe=20 [mailto:steve.poe@gmail.com]
Sent: Wednesday, August 02, = 2006 11:27=20 PM
To: Milen Kulev
Cc:=20 pgsql-performance@postgresql.org
Subject: Re: [PERFORM] XFS=20 filessystem for Datawarehousing

Milen,

For = the=20 past  year, I have been running odbc-bench on a dual-opteron with = 4GB of=20 RAM using a 8GB sample data. I found the performance difference = between EXT3,=20 JFS, and XFS  is +/- 5-8%. This could be written-off as "noise" = just for=20 normal server performance flux. If you plan on using the default = kernel, ext3=20 will likely perform best (what I found). When I added my own kernel, = ext3=20 performed fair. What I've had to consider is what does each file = system offer=20 me as far as  data integrity goes. 

You'll find = greater ROI=20 on performance by investing your time in other areas than chasing down = a few=20 percentage point (like I have done).  If you could borrow more = RAM and/or=20 more discs for your tests,  Testing newer kernels and read-ahead = patches=20 may benefit you as well.

Best of luck.

Steve = Poe



On 8/2/06, Milen=20 Kulev <makulev@gmx.net>=20 wrote:
Hi=20 Like, Mark , Alvaro and Andrew,

Thank you very much for = sharing you=20 experience with me.
I want to compare DHW performance of = PG/Bizgres on=20 different filesystems and difffrent
Block sizes.

The = hardware will=20 be free for me in a week or too (at a moment another project is = running on=20 it) and then I will test
diffrenet setups and will post the=20 results.

I MUST (sorry, no other choice) use SLES6 R3, 64 = bit. I am=20 not sure at all that I will get enough budget to get
approapriate = RAID=20 controller, and that is why I intent to use software RAID.

I = am=20 pretty exited whether XFS will clearly outpertform ETX3 (no default = setups=20 for both are planned !).  I am not sure
whether is it = worth to=20 include JFS in comparison too=20 ...


Best  Regards,
Milen = Kulev

-----Original=20 Message-----
From: Luke Lonergan [mailto: = llonergan@greenplum.com]
Sent:=20 Wednesday, August 02, 2006 4:43 AM
To: Milen Kulev; pgsql-performance@postgr= esql.org
Subject:=20 Re: [PERFORM] XFS filessystem for Datawarehousing=20


Milen,

On 8/1/06 2:49 PM, "Milen Kulev" <makulev@gmx.net> = wrote:

> Is=20 anyone using XFS for storing/retrieving relatively large amount = of
>=20 data  (~ 200GB)?

I concur with the previous = poster's=20 experiences with one additional
observation:

We have had=20 instabilities with XFS with software RAID (md) on 32-bit Xeons = running=20 RedHat4 U3 with the Centos 4.3
unsupported SMP = kernel.  XFS=20 would occasionally kernel panic under load.

We have had no = problems=20 with XFS running on the same OS/kernel on 64-bit under heavy = workloads for=20 weeks of continuous
usage.  Each server (of 16 =
total) had=20 four XFS filesystems, each with 250GB of table data (no indexes) on = them,=20 total of 16 Terabytes.  We tested
with the TPC-H schema = and=20 queries.

We use the default settings for XFS.

Also - = be aware=20 that LVM has a serious performance bottleneck at about 600MB/s - if = you are=20 working below that
threshold, you may not notice the issue, = maybe some=20 increase in CPU consumption as you approach it.

-=20 Luke



---------------------------(end of=20 broadcast)---------------------------
TIP 3: Have you checked our = extensive FAQ?=20 =

           = ;   =20 http://www.postgresql.org/doc= s/faq

------=_NextPart_000_01ED_01C6B68D.8AEFE7A0--