Re: ext3 sucks

[Tom Sightler <ttsig tuxyturvy com>]

On Tue, 2005-10-25 at 13:42 -0400, Joshua Baker-LePain wrote:
> > Have you tried the kernel in the following bugzilla? I didn't
> > had the time to test it but it seems promising.
> > https://bugzilla.redhat.com/bugzilla/show_bug.cgi?id=156437
> > (Writing large file to 1TB ext3 volume sometimes very slow)

As the filer of this bug, I can say that I don't think this is his
problem.  This probably typically occurred only on large files (128MB or
greater) and was fairly random under most loads.

>       write   read
>       -----   ----
> ext2    81    180
> ext3    34    222
> XFS    109    213

I have a couple of questions, is access time important to you?  If not,
have you tried mounting with noatime?  Also, have you tried increasing
the size of the journal and the stride options (previous suggestion)?
My guess is that your having journal contention and having an external
journal might help.  Another option, you could attempt to tweak the
commit rate with the commit= mount option.  The default is 5 seconds
which seems too often for some disk arrays.

I had many of the same frustrations when I recently migrated a couple of
large volumes from JFS to ext3 on one of our SAN's.  Performance,
especially writes, dropped through the floor, but after much testing and
tweaking I was able to get most of this performance back.

In my case I ended up using a combination of the stride= option, noatime
and data=writeback mount options, but my stuff is nothing like a 3Ware
card so it's likely your tuning will be different.

Good luck, keep posting.

Later,
Tom