Queue upcall locking (was: [dm-devel] [RFC][PATCH] fix dm_any_congested() to properly sync up with suspend code path)

[Christoph Hellwig]

On Mon, Nov 10, 2008 at 02:27:15PM +0000, Alasdair G Kergon wrote:
> Indeed - the blocking was a bug for which there's a patch, but that doesn't
> deal with how the function should be operating in the first place.
> 
> - If one device is found to be congested, why bother checking the remaining
> devices?
> 
> - If the device is suspended, the response should be that it is congested, I'd
> have thought.

Yes.  device congested is a quick an dirty check - if you encounter
anything long just return congested if I/O would hit this long delay,
too or not congested if you can't really know.