🚀 go-pugleaf

Can anyone suggest why linux would lock up when copying large
amounts of data to a PCI/SCSI disk ?  I saw a reference to this
regarding 1.3.x kernels, but I have 2.0.26.

I have a DPT PM2044UW (Smart Cache IV, Ultra-Wide), connected to a 
single IBM 2 Gb drive.  When copying (cp -dpR) from one partition 
to another, or across NFS, the system would lock-up after about 
10-20 Mb had copied.  One one occasion I got continuous console 
errors like "eata-reset: slot 1 locked, did reset ...".

A power-off or hard reset was required which of course damaged the 
filesystem.

I seem to have cured the problem by configuring the DPT BIOS so
that all SCSI transfers are asynchronous, and there is no command
queueing (max simultaneous cmds = 1).  Might this mean:

    1. The Linux SCSI driver doesn't support syncronous mode or
       command queuing ?

    2. The kernel should support it but has a bug ?

    3. The motherboard doesn't support DMA properly ?

    4. I have a hardware fault ?

    5. Something else entirely ?

And what have I done to the performance of the disk system by 
turning off the useful features ?

Any ideas gratefully accepted.

-- 
--------------------------------------------------------------------
 Graham Kean                                  g.kean@auckland.ac.nz
 University of Auckland Medical School
 Private Bag 92019, Auckland, New Zealand.
--------------------------------------------------------------------