[Date Prev][Date Next]   [Thread Prev][Thread Next]   [Thread Index] [Date Index] [Author Index]

Ordered vs. journal real-worl performance



Maybe I should've started a new thread with this question (it was in the
/proc/sys/vm/bdflush thread), so I am now :)

According to tests performed for this article:

http://www-106.ibm.com/developerworks/linux/library/l-fs8/

"ext3's data=journal mode is incredibly well-suited to situations where
data needs to be read from and written to disk at the same time."  This
is the situation that exists on my box.

My question is: has anyone had any other real-world experience to backup
the claims of the above statement?  I would love to get better
performance, AND have better data integrity, but that seems to good to
be true :)  

Also, if I do use data=journal would I need to retune the journal/fs?
It is a ~400GB file system with some fairly large files (none over 2GB
due to limitations with UniVerse - the RDBMS system we are using).

Thanks,
Andy.

PS Here are the specs for my CPU and disk subsystem.  Let me know if you
need any more info:

Quad Xeon 1.4GHz w/HT enabled
8GB RAM
Dell PERC (LSI/AMI Megaraid) HW RAID card
24 36GB 15K SCSI - /dev/md0 is ext3 file system on a software RAID0
array across 12 HW RAID1 arrays



Andrew Rechenberg
Infrastructure Team, Sherman Financial Group
arechenberg shermanfinancialgroup com
Phone: 513.707.3809
Fax:   513.707.3838





[Date Prev][Date Next]   [Thread Prev][Thread Next]   [Thread Index] [Date Index] [Author Index]