From: Dave Hansen <haveblue@us.ibm.com>
To: Yasunori Goto <ygoto@us.fujitsu.com>
Cc: Linux Kernel ML <linux-kernel@vger.kernel.org>,
Linux Hotplug Memory Support <lhms-devel@lists.sourceforge.net>,
Linux-Node-Hotplug <lhns-devel@lists.sourceforge.net>,
linux-mm <linux-mm@kvack.org>,
"BRADLEY CHRISTIANSEN [imap]" <bradc1@us.ibm.com>
Subject: Re: [Lhms-devel] Re: Merging Nonlinear and Numa style memory hotplug
Date: Fri, 25 Jun 2004 13:54:55 -0700 [thread overview]
Message-ID: <1088196895.29059.357.camel@nighthawk> (raw)
In-Reply-To: <20040625121110.2937.YGOTO@us.fujitsu.com>
Whoops. Hit CTRL-Enter during my ASCII art :)
On Fri, 2004-06-25 at 13:45, Yasunori Goto wrote:
> > > Are you sure that all architectures need phys_section?
> >
> > You don't *need* it, but the alternative is a scan of the mem_section[]
> > array, which would be much, much slower.
> >
> > Do you have an idea for an alternate implementation?
>
> I didn't find that scan of the mem_section[] is necessary.
> I thought just that mem_section index = phys_section index.
> May I ask why scan of mem_section is necessary?
> I might still have misunderstood something.
For now, the indexes happen to be the same. However, for discontiguous
memory systems, this will not be the case
Consider a system with 3 GB of RAM, 2GB@0x00000000 and 1 GB@0xC0000000
with 1 GB sections. The arrays would look like this:
mem | phys
----+-----
0 | 0
1 | 1
2 | 3
See the B-lpfn patch that I posted today for why this is important. It
basically allows us to represent sparse physical addresses in a much
more linear fashion.
-- Dave
WARNING: multiple messages have this Message-ID (diff)
From: Dave Hansen <haveblue@us.ibm.com>
To: Yasunori Goto <ygoto@us.fujitsu.com>
Cc: Linux Kernel ML <linux-kernel@vger.kernel.org>,
Linux Hotplug Memory Support <lhms-devel@lists.sourceforge.net>,
Linux-Node-Hotplug <lhns-devel@lists.sourceforge.net>,
linux-mm <linux-mm@kvack.org>,
"BRADLEY CHRISTIANSEN [imap]" <bradc1@us.ibm.com>
Subject: Re: [Lhms-devel] Re: Merging Nonlinear and Numa style memory hotplug
Date: Fri, 25 Jun 2004 13:54:55 -0700 [thread overview]
Message-ID: <1088196895.29059.357.camel@nighthawk> (raw)
In-Reply-To: <20040625121110.2937.YGOTO@us.fujitsu.com>
Whoops. Hit CTRL-Enter during my ASCII art :)
On Fri, 2004-06-25 at 13:45, Yasunori Goto wrote:
> > > Are you sure that all architectures need phys_section?
> >
> > You don't *need* it, but the alternative is a scan of the mem_section[]
> > array, which would be much, much slower.
> >
> > Do you have an idea for an alternate implementation?
>
> I didn't find that scan of the mem_section[] is necessary.
> I thought just that mem_section index = phys_section index.
> May I ask why scan of mem_section is necessary?
> I might still have misunderstood something.
For now, the indexes happen to be the same. However, for discontiguous
memory systems, this will not be the case
Consider a system with 3 GB of RAM, 2GB@0x00000000 and 1 GB@0xC0000000
with 1 GB sections. The arrays would look like this:
mem | phys
----+-----
0 | 0
1 | 1
2 | 3
See the B-lpfn patch that I posted today for why this is important. It
basically allows us to represent sparse physical addresses in a much
more linear fashion.
-- Dave
--
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:"aart@kvack.org"> aart@kvack.org </a>
next prev parent reply other threads:[~2004-06-25 20:57 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2004-06-22 19:00 Merging Nonlinear and Numa style memory hotplug Yasunori Goto
2004-06-22 19:00 ` Yasunori Goto
2004-06-23 22:32 ` [Lhns-devel] " Dave Hansen
2004-06-23 22:32 ` Dave Hansen
2004-06-24 3:04 ` Yasunori Goto
2004-06-24 3:04 ` Yasunori Goto
2004-06-24 3:26 ` Dave Hansen
2004-06-24 3:26 ` Dave Hansen
2004-06-24 13:28 ` [Lhms-devel] " Dave Hansen
2004-06-24 13:28 ` Dave Hansen
2004-06-24 22:19 ` Yasunori Goto
2004-06-24 22:19 ` Yasunori Goto
2004-06-24 22:37 ` Dave Hansen
2004-06-24 22:37 ` Dave Hansen
2004-06-25 3:11 ` [Lhms-devel] " Yasunori Goto
2004-06-25 3:11 ` Yasunori Goto
2004-06-25 3:19 ` Dave Hansen
2004-06-25 3:19 ` Dave Hansen
2004-06-25 18:48 ` Yasunori Goto
2004-06-25 18:48 ` Yasunori Goto
2004-06-25 18:59 ` Dave Hansen
2004-06-25 18:59 ` Dave Hansen
2004-06-25 20:45 ` Yasunori Goto
2004-06-25 20:45 ` Yasunori Goto
2004-06-25 20:49 ` Dave Hansen
2004-06-25 20:49 ` Dave Hansen
2004-06-25 20:54 ` Dave Hansen [this message]
2004-06-25 20:54 ` Dave Hansen
2004-06-25 4:49 ` [Lhms-devel] Re: [Lhns-devel] " Shai Fultheim
2004-06-25 4:49 ` Shai Fultheim
2004-06-25 15:16 ` Dave Hansen
2004-06-25 15:16 ` Dave Hansen
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=1088196895.29059.357.camel@nighthawk \
--to=haveblue@us.ibm.com \
--cc=bradc1@us.ibm.com \
--cc=lhms-devel@lists.sourceforge.net \
--cc=lhns-devel@lists.sourceforge.net \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=ygoto@us.fujitsu.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.