Messages in this thread | | | Date | Sun, 7 Nov 1999 18:19:14 +0100 | From | Florian Lohoff <> | Subject | Raid/LVM ll_rw_blk problems Got xx request Was: (Re: LOTS OF BAD STUFF ...) |
| |
On Sat, Nov 06, 1999 at 08:40:08PM +0100, P.A.M. van Dam wrote: > Same here, but then with Mauelschagens LVM. An mkfs -t ext2 for the > first time (after bootup) on a striped LV will trigger the "Got LVM > request, not good" message (and accompanied by some "trying to ... > beyond end of device" messages). The second attempt will not generate > these messages. > > I'm sorry, but I still have the strong belief that this isn't hardware > nor RAID (only) related. There must be some bug lurking, we have to > stamp out before we can take 2.4 seriously.
I heard of that - I meat Heinz in Siegen where we already discussed this topic and i thought he had given me enough direction and/or infos to debug this topic on my own. I spent 2 days of hacking resulting in NULL.
> > I reproduced this with different hardware (machines, harddrives, > > scsi controllers etc - Even on sparc ...) > > Ok. Does SMP be the common denominator in your test? Almost all reports > are with SMP machines.
Nope - Single Processor Sparc, Single Processor i386 (P200) and a Dual Celeron 400 ... Sparc with Qlogic Controller, P200 with 2x Narrow NCR875 aka Symbios Controller and the Dual Celeron with a Ultra Wide SCSI Controller (Some NCR chip also - Tekram UW Controller)
Although i had a couple of other different problems on Sparc.
It isnt Hardware specific. I only saw that with Raid code although Heinz meant that he seens this under Heavy load in the LVM also ... So this seems to be a common thing between the different ll_rw_blk usages. I discovered this in the 2.2. area (10-13).
I am not used to kernel things very much - I see the error when i have the already mentioned setup. I then initiate the "mke2fs" - It displays writing a couple of superblock copies and in the moment the drives (Up to 12) should begin to write - Nothing happens and instead i get an "Got md request".
So it seems it happens in the moment the request queue/drive gets "unplugged" (Am i right with that ?)
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/
| |