Re: i/o scheduling (was Re: NEW_BUFQ_STRATEGY)

On Wed, Dec 17, 2003 at 01:34:02PM +0900, YAMAMOTO Takashi wrote:
> > 
> > I'd like to see this too. IMHO, this can share the same queue as delayed
> > writes. Only wake up the disk when there's too much requests in the queue, or
> > we have something else to do.
> > This would also prevent writes to log files to wake up the disk.
> 
> it isn't so easy.
> "delayed writes" can't be delayed so much because e.g. synchronous
> read requests can happen on the delayed-writed page and we have no way
> to look up corresponding buf from a page.

I don't understand what you mean here. If we have a read request for a
delayed-write page, why would the read end in the disk's queue at all ?
UVM should find the data in memory.

--
Manuel Bouyer, LIP6, Universite Paris VI.           [email protected]
     NetBSD: 24 ans d'experience feront toujours la difference
--