Re: kern/39993: lockup on i386 SMP (raidframe related ?)

[Manuel Bouyer <bouyer%antioche.eu.org@localhost>]

The following reply was made to PR kern/39993; it has been noted by GNATS.

From: Manuel Bouyer <bouyer%antioche.eu.org@localhost>
To: gnats-bugs%NetBSD.org@localhost
Cc: kern-bug-people%NetBSD.org@localhost, gnats-admin%NetBSD.org@localhost, 
netbsd-bugs%NetBSD.org@localhost
Subject: Re: kern/39993: lockup on i386 SMP (raidframe related ?)
Date: Fri, 21 Nov 2008 20:29:18 +0100

 On Fri, Nov 21, 2008 at 03:20:03PM +0000, Greg Oster wrote:
 >  bouyer%antioche.eu.org@localhost writes:
 >  > I also have a core dump. The stack traces were indentical in all hangs I 
 > got.
 >  > disabling SMP at boot (boot -1) work around the problem.
 >  > LOCKDEBUG+DEBUG+DIAGNOSTIC does't give any additionnal info. 
 >  > This hardware was running without issues under 3.1 with SMP.
 >  > 
 >  > >How-To-Repeat:
 >  >   boot a SMP system with raidframe and generate I/O ?
 >  
 >  Were it only that simple, I'd be happy...  Unfortunately, I've got a 
 >  couple of different boxes w/ 5.0_BETA+SMP+RAIDframe+heavy IO and I 
 >  havn't seen this problem at all.. :( 
 >  
 >  What happens if you do:
 >  
 >    dd if=/dev/rsd0e of=/dev/null bs=1m &
 >    dd if=/dev/rsd1e of=/dev/null bs=1m &
 >  
 >  where rsd0e and rsd1e are the (raw) components of your RAID set?
 
 works fine (I tried with the different components of the RAID).
 
 I also tried to reproduce it on a athlonx2 with 2 SATA drives, no luck.
 
 other factors that may be relevant:
 - when this happens a background parity rewrite is running
 - there may be hardware issues with drives (like command timeouts),
   so there may be aborted transfers/I/O errors reported to the raidframe 
   layer.
 
 What I could do it try let it rebuild parity on the UP kernel, and reboot
 to the SMP kernel after.
 
 -- 
 Manuel Bouyer <bouyer%antioche.eu.org@localhost>
      NetBSD: 26 ans d'experience feront toujours la difference
 --