Mike Hardy wrote:

This works for me, there are several pages out there (I recall using the
commands from a gentoo one most recently) that show the exact sequence
of grub things you should do to get grub in the MBR of both disks.

It sounds like your machine may not be set to boot off of anything other
than that one disk though? Is that maybe a BIOS thing?

I dunno, but I have definitely pulled a primary drive out of the system
completely and booted off the second one, then had linux come up with
(correctly) degraded arrays
 

Frequently a BIOS will boot a 2nd drive if the first is missing/dead, 
but not if it returns bad data (CRC error). A soft fail is not handled 
correctly by all BIOS' in use, possibly a majority of them.

-Mike

Herta Van den Eynde wrote:
 

quoted

(crossposted to linux-raid@vger.kernel.org and redhat-list@redhat.com)
(apologies for this, but this should have be operational last week)

I installed Red Hat EL AS 4 on a HP Proliant DL380, and configured all
system devices in software RAID 1.  I added an entry to grub.conf to
fallback to the second disk in case the first entry fails.  At boottime,
booting from hd0 works fine.  As does booting from hd1.

Until I physically remove hd0 from the system.

I tried manually installing grub on hd1,
I added hd1 to the device.map and subsequently re-installed grub on it,
I remapped hd0 to /dev/cciss/c0d1 and subsequently re-installed grub
all to no avail.

I previously installed this while the devices were in slots 2 and 3. The
system wouldn't even boot then.  It looks as though booting from sw
RAID1 will only work when there's a valid device in slot 0.  Still
preferable over hw RAID1, but even better would be if this worked all
the way.

Is this working for anyone?  Any idea what I may have overlooked?  Any
suggestions on how to debug this?

Kind regards,

Herta

Disclaimer: http://www.kuleuven.be/cwis/email_disclaimer.htm

-- 
bill davidsen [off-list ref]
  CTO TMR Associates, Inc
  Doing interesting things with small computers since 1979