Wouldn't it be reasonable and mostly trivial that
1) when a process is terminated, that any of it's pages that are on swap are
issued a CP
diagnose to discard the page? (requires a bit of Endicott work)
2) when a page is swapped in, make that page anonymous again, and issue that
same
diagnose? This eliminates duplicate resources of expensive storage.
The result would be significantly less z/VM resources to maintain that swap
disk.
Rob van der Heij wrote:
On 10/13/07, Carsten Otte <[EMAIL PROTECTED]> wrote:
No method is in place to ever change a backing. Thus, a page will
never be moved from one swap slot to a different swap slot. This is
why linux is not very good at keeping swap usage local, and is not
good at using low prio swap for hot pages.
I don't think that were implied by what was suggested. It would even
be a bad idea to move pages through swap (because you might cause them
to page in just for re-ordering them). What would make a difference is
the way slots are allocated on swap devices. As I mentioned between
the lines of my posts, some of the apparent design criteria do not
apply to VDISK (or even mainframe disk I/O in general). But that
algorithm is probably in the generic part of Linux.
The right way would probably be to add a way to steer the algorithm.
In that case an option on swapon to select between first-fit and
best-fit, for example. And while working on my pony, I would also like
an API on the block device tell the driver to drop a block from
backing store (also COW devices would enjoy that).
Rob
--
Rob van der Heij
Velocity Software, Inc
http://velocitysoftware.com/
----------------------------------------------------------------------
For LINUX-390 subscribe / signoff / archive access instructions,
send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit
http://www.marist.edu/htbin/wlvindex?LINUX-390
----------------------------------------------------------------------
For LINUX-390 subscribe / signoff / archive access instructions,
send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit
http://www.marist.edu/htbin/wlvindex?LINUX-390
begin:vcard
fn:Barton Robinson
n:Robinson;Barton
adr;dom:;;PO 390640;Mountain View;CA;94039-0640
email;internet:[EMAIL PROTECTED]
title:Sr. Architect
tel;work:650-964-8867
note:If you can't measure it, I'm just not interested
x-mozilla-html:FALSE
url:http://velocitysoftware.com
version:2.1
end:vcard
