[ENBD] More on 2GB Limits... Huh...

[Peter T. Breuer]

"A month of sundays ago Kai Chen wrote:"
> The logical volumes are created by my FC controller, which is hardware 
> based.  The computer talks to the controller through a QLogic FC card over 
> FC wires.  These volumes are logical, because they are created over a RAID 5 
> array and do not correspond directly to physical devices.

I see. Well, I would guess that something in the driver has 32 bits
where it should have 64. Try and find out where the observed limit
comes from by varying the setup, removing or adding one element at a
time.

> My kernel is 2.2.18, and I haven't upgraded it to 2.4 because I'm running 
> AFS, which supports up to 2.2.18 only at this point.

OK

> OK.  It's the combination of "merge_requests=0" and "mount -o sync" together 
> that did the trick.  Missing one of them will again create deadlock.  
> Together they seem to work fine.

But merge_requests=0 is the makefile default (and is sure death in
2.2.18 if missed). And it seems to be the compiled-in default if
one doesn't say anything too. So I don't see how it can be involved.

> Yes.  I do have LVM, and it is a patch for 2.2.18.  I just haven't run it 
> with NBD yet.

Run it or applied it? Applying a patch is sufficient to alter your
kernel in many ways (if you compile it :-).

> >Effectively, you ARE running to localhost. You are talking to the lvm
> >layers, which are on localhost.
> 
> I see.  Because I plan to do that soon, please tell me how running LVM makes 
> a difference to the 2GB limit...

It shouldn't. There is no limit in the block layers in the kernel,
2.2.18 or 2.4.0. There is a limit in the FS codes in 2.2.18.

Peter