IDE corruption during heavy bt878-induced interrupt load

IDE corruption during heavy bt878-induced interrupt load

[Chuck Ebbert]

> I am today replacing the IDE RAID with a 3WARE IDE-RAID that emulates SCSI on 
> the premise that the problem has to do with hardware bus arbitration.  But as 
> of yet I don't have any data to support that or show improvement.


  Did you use hdparm to enable unmaskirq and 32-bit IO on normal IDE?

  With lots of activity I find 8 sector IO to work better than 16,
and 32-bit IO with sync to be no slower than 32-bit IO without it, so
I put a line like this in /etc/rc.local for each disk on HPT370:

        hdparm -c 3 -u 1 -m 8 -a 8 /dev/hde

------
 Chuck

IDE corruption during heavy bt878-induced interrupt load

[joe briggs]

I am seeking comments or suggestions to this problem:

I create multi-channel digital surveillance systems using cards with 4 or more 
multiplexed bt878 framegrabbers; each one capturing 5 or more frames per 
second on each of its two input channels (total 4 * 2 * 5 = 40 fps).  
Typically I run using either a Promise or Adaptec HPT370 IDE-RAID controller 
with 2 WD-120GB/8MB-cache drives striped in RAID-0, with another IDE as hda 
for my system drive.  What happens is that every few seconds I get a "BTTV: 
RISC ERROR - resetting" from the frame grabber driver.  After a few days of 
this I have corruption on my Reiser file system; which usually I am able to 
clean up with mkreiserfs --fix-fixable or --rebuild-tree.  The corruption is 
both on my RAID and my system drive.  Missing doing this maintenance action 
can really ruin my day.

I am today replacing the IDE RAID with a 3WARE IDE-RAID that emulates SCSI on 
the premise that the problem has to do with hardware bus arbitration.  But as 
of yet I don't have any data to support that or show improvement.


All comments/suggestions/etc. appreciated.

Joe


-- 
Joe Briggs
Briggs Media Systems
105 Burnsen Ave.
Manchester NH 01304 USA
TEL/FAX 603-232-3115 MOBILE 603-493-2386
www.briggsmedia.com