Received: from localhost (unknown [200.46.204.184]) by postgresql.org (Postfix) with ESMTP id 95CB12E0121 for ; Thu, 13 Mar 2008 05:12:08 -0300 (ADT) Received: from postgresql.org ([200.46.204.71]) by localhost (mx1.hub.org [200.46.204.184]) (amavisd-maia, port 10024) with ESMTP id 64480-09 for ; Thu, 13 Mar 2008 05:11:58 -0300 (ADT) X-Greylist: from auto-whitelisted by SQLgrey-1.7.5 Received: from mail.emproshunts.com (mail.emproshunts.com [66.64.191.19]) by postgresql.org (Postfix) with ESMTP id ED8DB2E011F for ; Thu, 13 Mar 2008 05:12:01 -0300 (ADT) Received: from [127.0.0.1] by mail.emproshunts.com (GMS 15.00.3626/KX5895.00.ca7cb0e7) with ESMTP id bqpzgaaa for pgsql-performance@postgresql.org; Thu, 13 Mar 2008 04:11:59 -0400 Received: from [192.168.1.49] by mail.emproshunts.com (GMS 15.00.3626/KX5895.00.ca7cb0e7) with ESMTP id aqpzgaaa; Thu, 13 Mar 2008 04:11:59 -0400 Date: Thu, 13 Mar 2008 04:11:59 -0400 From: "Justin Graf" Subject: Re: Benchmark: Dell/Perc 6, 8 disk RAID 10 To: "Craig James" , "pgsql-performance@postgresql.org" Message-Id: <08115901408538@mail.emproshunts.com> X-Mailer: Gordano Messaging Suite v15.00.3626 X-Originating-IP: [192.168.1.49] In-Reply-To: <47D8B3B6.3010606@emolecules.com> References: <47D0AFC1.5070305@emolecules.com> <20080306060829.GA21084@a-kretschmer.de> <47CF8EA6.8070503@mark.mielke.cc> <20080306063643.GB21084@a-kretschmer.de> <3E9C3A51-C28E-4B75-9739-E344DAC72880@fastcrypt.com> <47D00DB2.7040007@emolecules.com> <18451.1204824562@sss.pgh.pa.us> <47D0AFC1.5070305@emolecules.com> X-Sender: justin@emproshunts.com Mime-Version: 1.0 X-DNSBL: 0 X-AntiSpam: Checked for restricted content by Gordano's AntiSpam Software X-Virus-Scanned: Maia Mailguard 1.0.1 Content-Type: multipart/alternative; boundary="==_08115904508540/mail.emproshunts.com==_" X-Archive-Number: 200803/272 X-Sequence-Number: 29226 This is a MIME-encapsulated message --==_08115904508539/mail.emproshunts.com==_ Content-Type: multipart/alternative; boundary="==_08115904508540/mail.emproshunts.com==_" --==_08115904508540/mail.emproshunts.com==_ Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Content-Disposition: inline I recent just got a new server also from dell 2 weeks ago went with more memory slower CPU, and smaller harddrives have not run pgbench=20 Dell PE 2950 III=20 2 Quad Core 1.866 Ghz =20 16 gigs of ram. =20 8 hard drives 73Gig 10k RPM SAS=20 2 drives in Mirrored for OS, Binaries, and WAL=20 6 in a raid 10=20 Dual Gig Ethernet=20 OS Ubuntu 7.10 ----------------------------------------------- Version 1.03 =20 ------Sequential Output------ --Sequential Input-= --Random-=20 -Per Chr- --Block-- -Rewrite- -Per Chr- --Block--= --Seeks--=20 Machine Size K/sec %CP K/sec %CP K/sec %CP K/sec %CP= K/sec %CP /sec %CP=20 PriData 70000M 51030 90 107488 29 50666 10 38464 = 65 102931 9 268.2 0=20 =20 ------Sequential Create------ --------Random Create--------=20 -Create-- --Read--- -Delete-- -Create-- --Read---= -Delete--=20 files /sec %CP /sec %CP /sec %CP /sec %CP /sec %CP /sec= %CP=20 16 +++++ +++ +++++ +++ +++++ +++ +++++ +++ +++++ +++ +++++= +++=20 PriData,70000M,51030,90,107488,29,50666,10,38464,65,102931,9,268.2,0,16,=20 +++++,+++,+++++,+++,+++++,+++,+++++,+++,+++++,+++,+++++,+++ the difference in our results are interesting. What are the setting on the RAID card . I have the cache turned on with= Read Ahead =20 ---- Message from mailto:craig_james@emolecules.com Craig James= at 03-12-2008 09:55:18 PM ------ I just received a new server and thought benchmarks would be interesting. = I think this looks pretty good, but maybe there are some suggestions about= the configuration file. This is a web app, a mix of read/write, where= writes tend to be "insert into ... (select ...)" where the resulting= insert is on the order of 100 to 10K rows of two integers. An external= process also uses a LOT of CPU power along with each query. Thanks, Craig Configuration: Dell 2950 8 CPU (Intel 2GHz Xeon) 8 GB memory Dell Perc 6i with battery-backed cache RAID 10 of 8x 146GB SAS 10K 2.5" disks Everything (OS, WAL and databases) are on the one RAID array. Diffs from original configuration: max_connections =3D 1000 shared_buffers =3D 400MB work_mem =3D 256MB max_fsm_pages =3D 1000000 max_fsm_relations =3D 5000 wal_buffers =3D 256kB effective_cache_size =3D 4GB Bonnie output (slightly reformatted) ---------------------------------------------------------------------------= --- Delete files in random order...done. Version 1.03 ------Sequential Output------ --Sequential Input- = --Random- -Per Chr- --Block-- -Rewrite- -Per Chr- --Block-- = --Seeks-- Size K/sec %CP K/sec %CP K/sec %CP K/sec %CP K/sec %CP /sec= %CP 16G 64205 99 234252 38 112924 26 65275 98 293852 24 940.3= 1 ------Sequential Create------ --------Random Create-------- -Create-- --Read--- -Delete-- -Create-- --Read--- -Delete-- files /sec %CP /sec %CP /sec %CP /sec %CP /sec %CP /sec %CP 16 12203 95 +++++ +++ 19469 94 12297 95 +++++ +++ 15578 82 www.xxx.com,16G,64205,99,234252,38,112924,26,65275,98,293852,24,940.3,1,16,= 12203,95,+++++,+++,19469,94,12297,95,+++++,+++,15578,82 ---------------------------------------------------------------------------= --- $ pgbench -c 10 -t 10000 -v test -U test starting vacuum...end. starting vacuum accounts...end. transaction type: TPC-B (sort of) scaling factor: 1 number of clients: 10 number of transactions per client: 10000 number of transactions actually processed: 100000/100000 tps =3D 2786.377933 (including connections establishing) tps =3D 2787.888209 (excluding connections establishing) --=20 Sent via pgsql-performance mailing list (pgsql-performance@postgresql.org) To make changes to your subscription: http://www.postgresql.org/mailpref/pgsql-performance --==_08115904508540/mail.emproshunts.com==_ Content-Type: text/html; charset="utf-8" Content-Transfer-Encoding: quoted-printable Content-Disposition: inline I recent just got a new server also from dell 2 weeks ago
went= with more memory slower CPU, and smaller harddrives
 have not run= pgbench

Dell PE 2950 III
2 Quad Core 1.866 Ghz =20
16 gigs of ram. =20
8 hard drives 73Gig 10k RPM SAS
2 drives in Mirrored for OS, Binaries, and WAL
6 in a raid 10
Dual Gig Ethernet
OS Ubuntu= 7.10
-----------------------------------------------

Version 1.03 =
           &nbs= p;         ------Sequential= Output------ --Sequential Input- --Random-
       =                -Per Chr- --Block--= -Rewrite- -Per Chr- --Block-- --Seeks--
Machine Size        K/sec= %CP  K/sec   %CP    K/sec %CP  = K/sec %CP K/sec    %CP /sec %CP
PriData 70000M  51030   90  = 107488    29      50666 = 10     38464 65    = 102931     9    268.2 0
=20
------Sequential Create------ --------Random Create--------
-Create-- --Read--- -Delete-- -Create-- --Read---= -Delete--
files /sec %CP /sec %CP /sec %CP /sec %CP /sec %CP /sec= %CP
16 +++++ +++ +++++ +++ +++++ +++ +++++ +++ +++++ +++ +++++= +++
PriData,70000M,51030,90,107488,29,50666,10,38464,65,102931,9,268.2,0,16,
+++++,+++,+++++,+++,+++++,+++,+++++,+++,+++++,+++,+++++,+++

the difference in= our results are interesting.

What are the setting on the RAID card= .  I have the cache turned on with Read Ahead 


----= Message from Craig James= <craig_james@emolecules.com> at 03-12-2008 09:55:18 PM= ------
I just received a new server and= thought benchmarks would be interesting.  I think this looks pretty= good, but maybe there are some suggestions about the configuration file.=  This is a web app, a mix of read/write, where writes tend to be= "insert into ... (select ...)" where the resulting insert is on the order= of 100 to 10K rows of two integers.  An external process also uses a= LOT of CPU power along with each query.

Thanks,
Craig


Configuration:
  Dell 2950
  8 CPU (Intel 2GHz Xeon)
  8 GB memory
  Dell Perc 6i with battery-backed cache
  RAID 10 of 8x 146GB SAS 10K 2.5" disks

Everything (OS, WAL and databases) are on the one RAID array.

Diffs from original configuration:

max_connections =3D 1000
shared_buffers =3D 400MB
work_mem =3D 256MB
max_fsm_pages =3D 1000000
max_fsm_relations =3D 5000
wal_buffers =3D 256kB
effective_cache_size =3D 4GB

Bonnie output (slightly reformatted)

---------------------------------------------------------------------------= ---

Delete files in random order...done.
Version  1.03
         ------Sequential= Output------       --Sequential Input-=      --Random-
      -Per Chr-   --Block--=    -Rewrite-     -Per Chr-=   --Block--    --Seeks--
 Size K/sec %CP   K/sec  %CP   K/sec=  %CP    K/sec %CP   K/sec  %CP=    /sec %CP
  16G 64205  99   234252  38=   112924  26    65275  98=   293852  24   940.3   1

         ------Sequential= Create------    --------Random Create--------
      -Create--   --Read---=   -Delete--   -Create--   --Read---=   -Delete--
files  /sec %CP    /sec %CP    /sec %CP=    /sec %CP    /sec %CP=    /sec %CP
   16 12203  95   +++++ +++   19469=  94   12297  95   +++++ +++=   15578  82

www.xxx.com,16G,64205,99,234252,38,112924,26,65275,98,293852,24,940.3,1,16,= 12203,95,+++++,+++,19469,94,12297,95,+++++,+++,15578,82

---------------------------------------------------------------------------= ---

$ pgbench -c 10 -t 10000 -v test -U test
starting vacuum...end.
starting vacuum accounts...end.
transaction type: TPC-B (sort of)
scaling factor: 1
number of clients: 10
number of transactions per client: 10000
number of transactions actually processed: 100000/100000
tps =3D 2786.377933 (including connections establishing)
tps =3D 2787.888209 (excluding connections establishing)



--
Sent via pgsql-performance mailing list= (pgsql-performance@postgresql.org)
To make changes to your subscription:
http://www.postgresql.org/mailpref/pgsql-performance


--==_08115904508540/mail.emproshunts.com==_-- --==_08115904508539/mail.emproshunts.com==_--