Possible explanation for mptsas ATA pass-through hangs

I have a research cluster of around 140 nodes, and have been affected by this problem since we put them online. The machines are Tyan boards with dual E54x0 CPUs and onboard SAS, with four SATA drives attached.

The half of the cluster with very high disk usage displayed this issue on perhaps one machine every two days, while the other half only had problems when SMART requests were issued. The bus would reset, and a drive would be logically ejected and reinserted (but at a different place, like /dev/sde).

Regardless of mptscsih.c being the correct place to enforce alignment, applying the patch Ryan Kuester provided to the kernel (2.6.32) running on the cluster has 1) stopped future occurrences of this problem, 2) made it immune against problems from running Ryan's bomb program and 3) remaining drive problems only occurred on unpatched nodes.

These messages still appear regularly though:-

[702162.202899] sd 4:0:3:0: [sdd] Sense Key : Recovered Error [current] [descriptor]
[702162.293329] Descriptor sense data with sense descriptors (in hex):
[702162.368629]         72 01 00 1d 00 00 00 0e 09 0c 00 00 00 00 00 00
[702162.447985]         00 4f 00 c2 40 50
[702162.494805] sd 4:0:3:0: [sdd] Add. Sense: ATA pass through information available

I haven't seen other messages yet from mptsas users that Ryan's patch works, so I provide my experience.

Greetings,
Michael.