From: David Rientjes <rientjes@cs.washington.edu>
To: Paul Jackson <pj@sgi.com>
Cc: linux-mm@kvack.org, akpm@osdl.org, nickpiggin@yahoo.com.au,
ak@suse.de, mbligh@google.com, rohitseth@google.com,
menage@google.com, clameter@sgi.com
Subject: Re: [RFC] another way to speed up fake numa node page_alloc
Date: Mon, 2 Oct 2006 00:05:11 -0700 (PDT) [thread overview]
Message-ID: <Pine.LNX.4.64N.0610020001240.7510@attu3.cs.washington.edu> (raw)
In-Reply-To: <20061001234858.fe91109e.pj@sgi.com>
On Sun, 1 Oct 2006, Paul Jackson wrote:
> I'm not sure what you have in mind by "scale this."
>
I'm talking about this:
+struct zonelist_faster {
+ nodemask_t fullnodes; /* nodes recently lacking free memory */
+ unsigned long last_full_zap; /* jiffies when fullnodes last zero'd */
+ unsigned short node_id[MAX_NUMNODES * MAX_NR_ZONES]; /* zone -> nid */
+};
With NODES_SHIFT equal to 10 as you recommend, you can't get away with an
unsigned short there. Likewise, your nodemask_t would need to be 128
bytes. So this doesn't scale appropriately when you simply change
NODES_SHIFT.
> This speedup should apply regardless of how many nodes (fake or
> real or mixed) are present.
>
It doesn't (see above).
> But whatever benefit this proposal has should be independent of the
> value of NODES_SHIFT.
>
It's not (see above).
David
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2006-10-02 7:05 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-09-25 9:14 Paul Jackson
2006-09-26 6:08 ` David Rientjes
2006-09-26 7:06 ` Paul Jackson
2006-09-26 18:17 ` David Rientjes
2006-09-26 19:24 ` Paul Jackson
2006-09-26 19:58 ` David Rientjes
2006-09-26 21:48 ` Paul Jackson
2006-10-02 6:18 ` Paul Jackson
2006-10-02 6:31 ` David Rientjes
2006-10-02 6:48 ` Paul Jackson
2006-10-02 7:05 ` David Rientjes [this message]
2006-10-02 8:41 ` Paul Jackson
2006-10-03 18:15 ` Paul Jackson
2006-10-03 19:37 ` David Rientjes
2006-10-04 15:45 ` Paul Jackson
2006-10-04 16:11 ` Christoph Lameter
2006-10-04 22:10 ` David Rientjes
2006-10-05 2:27 ` Paul Jackson
2006-10-05 2:37 ` David Rientjes
2006-10-05 2:53 ` Paul Jackson
2006-10-05 3:00 ` David Rientjes
2006-10-05 3:26 ` Paul Jackson
2006-10-05 3:49 ` David Rientjes
2006-10-05 4:07 ` Andrew Morton
2006-10-05 4:14 ` Paul Jackson
2006-10-05 4:50 ` David Rientjes
2006-10-05 4:53 ` Paul Jackson
2006-10-11 3:42 ` Paul Jackson
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=Pine.LNX.4.64N.0610020001240.7510@attu3.cs.washington.edu \
--to=rientjes@cs.washington.edu \
--cc=ak@suse.de \
--cc=akpm@osdl.org \
--cc=clameter@sgi.com \
--cc=linux-mm@kvack.org \
--cc=mbligh@google.com \
--cc=menage@google.com \
--cc=nickpiggin@yahoo.com.au \
--cc=pj@sgi.com \
--cc=rohitseth@google.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox