[Beowulf] Slow RAID reads, no errors logged, why?

[David Mathog]

On Tue, 20 Mar 2018 00:55:01 +0000  Jörg Saßmannshausen wrote:

> I am wondering if that is not what you would expect.
> The long SMART test is quite thorough so the disc will be subject to 
> quite a
> bit of stress. Thus, it could well be that the controller is slowing 
> down the
> rest of the RAID as there is a bottle neck.

Long SMART tests are run on active RAID systems here all the time, this 
is the only machine so far where this massive slow down has been noted.  
The others might slow down a few percent, but a drop in the read rate 
from ~400Mb/s to 30Mb/s is just horrible.  I'm wondering if the disks on 
this one system (the only machine here with this model disk) disable 
readahead or command queuing or something of that sort when a long SMART 
test runs.  However, no change in the read ahead value is visible with 
"blockdev --report" with and without that SMART test running.  The disks 
are 2Tb 6.0Gb/s SAS with 128Mb cache and 4.16ms latency.

Regards,

David Mathog
mathog at caltech.edu
Manager, Sequence Analysis Facility, Biology Division, Caltech