"Rosenthal, Eric S." wrote:
>
[ ... ]
>
> As for the fact that direct I/O is slower than buffered I/O - we're
> running version 2.4.2 of the Kernel on a PC, and have 2 striped hard drives
> connected with a Scsi controller (we plan to add more drives). The disks
> are striped at 4K and the file system block size is 4K. I'll have to do
> some tests to see which sizes are optimal.
>
> The disk rate I got for direct I/O (25 MB/sec) is about what was expected
> but the rate with buffered I/O (27 MB/sec with the cache cleared) is higher
> than I would've throught. Could Linux just handle buffered I/O better than
> Irix/NT?
By I/O do you mean read, write or both? For streaming buffered
writes XFS will do nearly as good as raw I/O on the machines I've
tested (scsi disk) ... I can't readily account for better
buffered read performance.
ananth.
--------------------------------------------------------------------------
Rajagopal Ananthanarayanan ("ananth")
Member Technical Staff, SGI.
--------------------------------------------------------------------------
|