> -----Original Message-----
> From: Stewart Smith [mailto:stewart@xxxxxxxxx]
> Sent: Thursday, 7 April 2005 9:59 PM
> To: Steve Lord
> Cc: Scott Fagg; linux-xfs@xxxxxxxxxxx
> Subject: database filesystem (ab)use [Was: Re: realtime ( was
> RE:unexpected high fragmentation, any ideas? )]
>
> On Wed, 2005-04-06 at 20:49 -0500, Steve Lord wrote:
> > So if you want big fat files which get layed out in one chunk, and
> > spindles where no other I/O gets in the way of the data I/O, then
> > it can be handy. It does sound like something a database might
> > like to use.
>
> For MySQL, with InnoDB tables (the on-disk ones with transactions etc)
> keeps one (or n) big data file(s) that grows dynamically (or you can
> statically allocate them in chunks) - typical grow size is 5 or 10MB.
It's mysql i'm using, and it was a performance problem on a new server
that prompted the question. I'm getting 5 times the throughput on a 4
year old desktop than i am with 1 month old server.
Using InnoDB and binary logs gets about 1MB/s throughput on the server,
but 5MB/s on the desktop.
I was wondering if a change of filesystem would help, but it sounds as
though it would not.
Using MyISAM and turning off binary logs, gets me reasonable performance
, so perhaps i have a filesystem problem or a storage array (hardware
raid) problem.
I've also tried toggling between mysql v3 and v5, the FC3 kernel RPM and
a vanilla kernel from kernel.org, but all that has had little impact.
Other processes can write to disc at much higher rates than mysql, so
perhaps i should take this problem to a different forum ..
>
> ideally, the ibdata files (and *especially* the ib_logfiles) would be
> contiguous on disk (and close to each other on disk).
>
> fsync performance is much more important for innodb (for transaction
> throughput). XFS is slower than ext3 in this regard (from benchmarks
> i've run*, data less than physical mem size).
regards,
|