If a device/controller queue is building with the I/O requests, the fastest path in the world is still going to perform like a dog. Try setting up the test disk with a striped logical volume. If you do this, the results would be good to post.
On Wed, 2003-12-10 at 11:02, Jason Herne wrote: > Nope, the DASD is Ficon attached with 2 channel paths. > > - Jason Herne > > On Thu, 2003-12-11 at 05:15, Vic Cross wrote: > > On Tue, 9 Dec 2003, Jason Herne wrote: > > > > > Linux is using a single 3390 DASD with ext3. > > > > If this 3390 is ESCON-attached, 17MB/s (megaBytes/sec) is the absolute > > maximum data transfer speed you'll get to the disk. As Rich mentioned, > > you'll need to look at LVM striping (or PAV using LVM) to get higher than > > this. > > > > That's if DASD is the bottleneck, as Barton suggests... > > > > Hoo-roo, > > Vic -- Rich Smrcina Sr. Systems Engineer Sytek Services - A Division of DSG Milwaukee, WI rsmrcina at wi.rr.com rsmrcina at dsgroup.com Catch the WAVV! Stay for requirements and the free-for-all. Update your zSeries skills in 4 days for a very reasonable price. WAVV 2004 in Chattanooga, TN April 30-May 4, 2004 For details see http://www.wavv.org
