On Thu, 2007-11-01 at 18:28 +0100, Miklos Szeredi wrote:
quoted text
> > The page not having PG_writeback set on return is a hint, but not fool
> > proof, it could be the device is just blazing fast.
>=20
> Hmm, does it actually has to be foolproof though?  What will happen if
> bdi_writeout_inc() is called twice for the page?  The device will get
> twice the number of pages it deserves?  That's not all that bad,
> especially since that is a really really fast device.

Basically, yes.

But then again, that would require auditing all ->writepage() callsites.