kern/104406: [ufs] Processes get stuck in "ufs" stateunderpersistent CPU load

[Kris Kennaway]

Oleg Derevenetz wrote:
>> Anyway, I looked at the ddb output already, said that it looks as either
>> driver or hw problem with very high confidence.
>>
>> I think the time of the project could be spent more productive elsewere,
>> while submitter checks his hardware, for instance, by changing 
>> controller,
>> disks, or controller type.
> 
> I already said that:
> 
> 1. This controller and disks succesfully works earlier with FreeBSD 
> 4.6.2 without any problems;

Yes, as Kostik says it may be a driver problem.  Or it could be a 
hardware problem because the driver is quite different than in 4.x, and 
may be exercising the hardware in a different way that provokes a 
hardware bug.

> 2. I tried to replace a disk with another one (the same model), but it 
> doesn't help. Unfortunately, I have no another free SCSI controller (but 
> see #1);
> 3. I have another AMD64 machine with different hardware (including disks 
> and SCSI controller) that periodically suffers from the same problem. 
> Unfortunately, that machine is in production and heavily loaded, so I 
> can't overload it even more with INVARIANTS, WITNESS, and DIAGNOSTIC - 
> my clients will not forgive me for that.

Many different problems can have similar symptoms when you do not look 
closely.  Indeed, the PR you are replying to is itself a completely 
different issue that has nothing to do with your own bug report, and 
someone else also replied to it with what looks like yet another 
completely different issue.

There is no evidence so far pointing anywhere apart from the mylex 
controller, so that argues against the hypothesis that your second 
problem is the same.

Kris