Re: LOTS OF BAD STUFF in raid0: raid0145-19990824-2.2.11 is unstable

Florian Lohoff (flo@rfc822.org)
Sat, 6 Nov 1999 15:44:47 +0100

On Fri, Nov 05, 1999 at 12:49:07PM -0500, David Mansfield wrote:
> (system details at bottom, summary 2xPII 450, 2.2.13pre14+raid0145latest)
>
> I am STILL having the same old bug in the raid code/kernel that has
> existed for about 6 months, at least. It no longer oopses because the new
> debug code that checks for this (that I suggested BTW, and others have
> triggered as well). But nonetheless this is really, really bad. Does
> anyone have any ideas?
>
> * I am willing to try out test patches to track this down, as I seem to
> have a way to reproduce it *

This is not the only bug in the alpha raid code which is reproducable
well and doesnt get fixed - I tried to look into the kernel but am not
that deep into buffer_head, ll_rw_block and raid things to fix it
myself and i dont blame anyone ...

Easy setup

raid0 of raid5s ...

read:

/dev/md0 raid0 /dev/md1 /dev/md2
/dev/md1 raid5 scsi disks (tried with 6 and 3)
/dev/md2 raid5 scsi disks (tried with 6 and 3)

As soon as you initiate a "mke2fs /dev/md0" the machine
hangs with "Got md request, not good" (md.c -> do_md_request())

I reproduced this with different hardware (machines, harddrives, scsi controllers etc - Even on sparc ...)

>From the manpage this is a feature which should work.

Flo

-- 
Florian Lohoff		flo@rfc822.org		      	+49-5241-470566
  ...  The failure can be random; however, when it does occur, it is
  catastrophic and is repeatable  ...             Cisco Field Notice




-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/