MegaRAID 'Bad Slot' Kernel message and crash.

[Scott Long]

Tony Byrne wrote:

> Hello Doug,
> 
> Friday, January 14, 2005, 1:35:16 AM, you wrote:
> 
> DW> scottl has been able to reproduce this on a U320 controller he has. I only
> DW> have U160 equipment and can't get the txn rate up high enough to reproduce
> DW> the issue.  The driver needs KTR instrumentation so we can see where the
> DW> bad slot is popping up from.  The "bad slot" message appears when the
> DW> controller returns completion for a command that had already completed.
> 
> DW> The amr driver has several other issues and is in dire need of an
> DW> overhaul. Unfortunately LSI has not been forthcoming with documentation,
> DW> so Scott and I are pretty much scratching our heads without knowing where
> DW> to go.
> 
> DW> This is in 5.X and HEAD, at least.  I can't comment on 4.x.
> 
> We have switched off adaptive read caching on the card.  One of my
> other correspondents has said that he hasn't been experiencing this
> problem. He  sent me his configuration settings.  Only time will tell
> if this helps.
> 
> What is state-of-the-art, regarding SCSI RAID support in FreeBSD?
> Which cards / drivers are favoured for their stability?  We are
> building a second server, initially without RAID, but given our
> problems with amr we are considering another RAID controller supported by a
> different driver.  We want to do write caching and need a card that
> supports a battery backed cache.  How about the Adaptec cards?
> 
> Regards,
> 
> Tony.
> 

This question has been discussed at length on the freebsd-scsi mailing
list under the topic 'Recommended RAID controller'.  I can send you some
recap emails if you need.

Scott