After a week of testing i decided to go with JFS as the FS for Postgres.
im not an expert benchmarker so I hope I initiated the right parameters
in bonnie pgbench.
The bonnie command:
bonnie++ -u miki -b -d /data/bonnie/ -s 6080:8k -m pr1
pgbench commands:
pgbench -i -s 10 test
pgbench -c
-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] On Behalf Of Michael Ben-Nes
Sent: Wednesday, September 14, 2005 10:58 AM
To: [EMAIL PROTECTED]
Cc: linux-il@linux.org.il
Subject: Re: sys / db performance block size
After a week of testing i decided to go with JFS as the FS
After few test, not certain yet i found *Surprise*Surprise* ext3 is
quite fast especially when using dir_index
This is the command i issued. i was recommended going on Journal size of
400 ( not really sure why ).
mke2fs -j -J size=400 -O dir_index -T largefile /dev/sdb1
testing it with
On 9/5/05, Michael Ben-Nes [EMAIL PROTECTED] wrote:
Im setting up a Postgresql sql server on IBM x345, dual xeon, raid1 ( 2
disks ), raid10 ( 4 disks ).
The db data will be stored on the RAID10 and will consist mostly of
product table of 5 mil rows and keywords table with 60 mil rows.
..
First, its better to ask the experts on this matters at
pgsql-general@postgresql.org
It is not definitive that for postgresql you'd better set
8kb block size since the OS already coalleses the files close
together anyway and there is no guarentee the page will be aligned
to the hardware block
