From: Andy Whitcroft <apw@shadowen.org>
To: Dave Hansen <haveblue@us.ibm.com>
Cc: Christoph Lameter <clameter@sgi.com>, linux-mm@kvack.org
Subject: Re: [PATCH] Get rid of zone_table
Date: Fri, 15 Sep 2006 14:28:35 +0100 [thread overview]
Message-ID: <450AAA83.3040905@shadowen.org> (raw)
In-Reply-To: <1158184047.9141.164.camel@localhost.localdomain>
Dave Hansen wrote:
> Now that I think about it, we should have room to encode that thing
> inside of the section number on 32-bit platforms.
>
> We have 32-bits of space, and we need to encode a number that is a
> maximum of 4 bits in size. That leaves 28 bits minus the one that we
> use for the section present bit. Our minimum section size on x86 is
> something like 64 or 128MB. Let's say 64MB. So, on a 64GB system, we
> only need 1k sections, and 10 bits.
>
> So, the node number would almost certainly fit in the existing
> mem_section. We'd just need to set it and mask it out.
>
> Andy, what do you think?
The flags field only has a 9 bit space for these value fields. Into
which we normally shove NODE,ZONE. With SPARSEMEM that is SECTION,ZONE
and so there is only room for 6-7 bits of information in this field.
The section table only contains an adjusted pointer to the mem_map for
that section? We use the bottom two bits of that pointer for a couple
of flags. I don't think there is any space in it.
Are you thinking of somewhere else?
-apw
--
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:[~2006-09-15 13:28 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-09-13 20:44 Christoph Lameter
2006-09-13 20:53 ` Dave Hansen
2006-09-13 21:40 ` Christoph Lameter
2006-09-13 21:47 ` Dave Hansen
2006-09-13 21:54 ` Christoph Lameter
2006-09-13 21:58 ` Dave Hansen
2006-09-13 22:02 ` Christoph Lameter
2006-09-15 13:28 ` Andy Whitcroft [this message]
2006-09-15 16:32 ` Dave Hansen
2006-09-15 17:13 ` Christoph Lameter
2006-09-15 17:51 ` Christoph Lameter
2006-09-14 10:33 ` Andy Whitcroft
2006-09-14 21:46 ` Christoph Lameter
2006-09-15 13:07 ` Andy Whitcroft
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=450AAA83.3040905@shadowen.org \
--to=apw@shadowen.org \
--cc=clameter@sgi.com \
--cc=haveblue@us.ibm.com \
--cc=linux-mm@kvack.org \
/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