[ENBD] ENBD on 2.4.x

[jona@orac.ensor.org]

> Are you mounting the fs sync?

Mounting with '-o sync' works LOTS better.  I actually get through
the 'bonnie' test and get stats!  I think this has solved my problem.
 
> Probably vfs is full. File bigger than memory, etc. Is the fs mounted
> sync? If not, mount it sync. If that doesn't help, load the module with
> sync_intvl=1. That will flush VFS frequently, before it can ever fill
> up (well, small ram, fast cpu will still let it block, but we hope
> not).

I'd like to better understand why the 'VFS' fills up and doesn't let
anybody know about it. (messages in printk, etc).  I'd also like to
see if there's a way we can wait for the 'VFS' to 'empty out' before
we just end up in a deadlock.  Any inspiration you have on the subject
would be save me a lot of time.  Even if you don't have THE answer,
a hint would be helpful if you have one.
 
> I hope that is true! But then why don't I just put the real blocksize
> here. Someone should run a test with
> 
>   int nbd = MINOR(bh->b_rdev) >> NBD_SHIFT;
>   if (bh->b_size != blksize_size[NBD_MAJOR][nbd])
>     NBD_ALERT ...
> 
I also ran this test and never got the alert, so I think the code is
safe as it stands.  The problem I was observing here, I shame to admit,
may have been caused by some inadvertent changes I was making in an effort
to find the above 'sync' problem.

Humbly,
Jon Arney