--f61P+fpdnY2FZS1u
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
Content-Transfer-Encoding: quoted-printable

On Mon, Oct 29, 2007 at 12:04:47AM +0200, Jukka Marin wrote:
> On Sun, Oct 28, 2007 at 10:55:53PM +0100, Michael van Elst wrote:
> > On Sun, Oct 28, 2007 at 10:50:31PM +0200, Jukka Marin wrote:
> >=20
> > > No swap is in use, if that's what you mean.  But no, 4 GB of RAM is n=
ot
> > > enough to buffer 10 GB files.. :)
> >=20
> > I guess this is the problem. When you run out of buffers then the
> > VM system and thus the file cache gets very slow.
>=20
> Then why is RAID5 slow and a plain disk isn't (when extracting the same
> pkgsrc tarball)?  I'm trying to find out whether I can use RAID5 or not,
> that's why I'm asking ;)

What could be happening is that you're doing a lot of RMW operations when=
=20
you write metadata. They are slow and add synchronous reads into important=
=20
i/o points.

> (Although I need to find a way to break the 2 TB disklabel barrier first.=
.)

Disklabels don't break 2 TB. That's why we have wedges.

Take care,

Bill

--f61P+fpdnY2FZS1u
Content-Type: application/pgp-signature
Content-Disposition: inline

-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.7 (NetBSD)

iD8DBQFHJ1JsWz+3JHUci9cRAlRXAJsF8eGphMbSA+c0RwBSN2kGfgp2VQCfXcCV
y49BvvISykDdLj2gryKlSrQ=
=Xwt3
-----END PGP SIGNATURE-----

--f61P+fpdnY2FZS1u--