Re: Speed on 1.3.60 disappointing?

Markus Gutschke (gutschk@uni-muenster.de)
14 Feb 1996 07:41:37 GMT


-----BEGIN PGP SIGNED MESSAGE-----

In article <4769.9602090250@calvay.dcs.ed.ac.uk> Stephen Tweedie <sct@dcs.ed.ac.uk> writes:
> With such a condemned list in memory, we'd never have to keep ANY
> memory free just in case. Even IRQs would be permitted to gobble up
> condemned pages. This scheme would give quite a lot of slack in the
> VM, and represents the best use of memory. But it would take a lot
> more work to implement than 1) to 4).

Would this mean, that we could implement swapping via NFS? As far as I
know, this is currently difficult because you need to allocate some
memory in order to do the swapping.

Markus

-----BEGIN PGP SIGNATURE-----
Version: 2.6.2
Comment: Processed by Mailcrypt 3.3, an Emacs/PGP interface

iQCVAgUBMSGSKhqJqDLErwMxAQFdJQQAr3T00nESMpc9DszQO0S3n7sbZ9KRF/V7
TkMz1qsjwoId6amIFJASUCvm7muKKhvmuuBS0uJ9+U8XPPD2PLtDIfNWGs1id84J
3QbCO7cOJc4EVUG7MuLQw9tvOmH9I5SnGATv2Vw3t145xV+idKvapdOZFQiTjil+
+Hhfw0iPngU=
=JoVB
-----END PGP SIGNATURE-----