Re: [Qemu-devel] Re: NBD server for QEMU images

[Avi Kivity <avi@qumranet.com>]

Anthony Liguori wrote:
>>
>> Mounting a partition being served on the same host as read-write can
>> cause deadlocks. From nbd-2.9.0 README file:
>
> This text is pretty old.  Is this still valid?  This would imply that 
> things like loop can result in dead locks.  I don't see why flushing 
> one device would depend on the completion of another device.  
> Otherwise, if you had two disk adapters, they would always be 
> operating in lock step.
>
> As I've said, I've never seen a problem doing-write with nbd on 
> localhost.

A deadlock can happen under heavy I/O load:

- write tons of data to nbd device, data ends up in pagecache
- memory gets low, kswapd wakes up, calls nbd device to actually write 
the data
- nbd issues a request, which ends up on the nbd server on the same machine
- the nbd server allocates memory
- memory allocation hangs waiting for kswapd

I submitted a patch/workaround for this some years ago (for a similar 
problem with a local mount to a userspace nfs server).


-- 
error compiling committee.c: too many arguments to function