Subject: Re: Do some disk accesses miss the UVM?
To: None <>
From: Perry E. Metzger <>
List: tech-kern
Date: 01/25/2002 12:18:34
Jason R Thorpe <> writes:
> On Fri, Jan 25, 2002 at 12:12:57AM -0500, Perry E. Metzger wrote:
>  > Well, the need is that it would be good for us to be able to do two
>  > find(1)s of a large tree and have the disk only spin on the first
>  > one. If you have the RAM, it is far less costly to cache all that
>  > data. This is of great practical importance at times for performance.
> So, while I agree this would be nice, stop to consider that if you
> also plop file metadata into the page cache:
> 	(1) You now have 3 policy knobs to futz with when picking
> 	    a page to evict: anon, file data, filesystem metadata.

Yup. Ultimately, we need to get rid of the knobs -- see my
"generational page replacement" notion or something similar.

> 	(2) You have to decide where the metadata pages will live,
> 	    i.e. which VM object they'll be associated with.

Yup, but we can figure that out.

> 	(3) To make (2) work, you probably have to UBC'ify all block
> 	    device access.

Messy but doable.

Perry E. Metzger
NetBSD Development, Support & CDs.