From: Anton Blanchard <anton@samba.org>
To: Andrea Arcangeli <andrea@suse.de>
Cc: Daniel Phillips <phillips@bonn-fries.net>,
Russell King <rmk@arm.linux.org.uk>,
linux-kernel@vger.kernel.org, Jesse Barnes <jbarnes@sgi.com>
Subject: Re: Bug: Discontigmem virt_to_page() [Alpha,ARM,Mips64?]
Date: Fri, 3 May 2002 01:28:25 +1000 [thread overview]
Message-ID: <20020502152825.GE10495@krispykreme> (raw)
In-Reply-To: <20020426192711.D18350@flint.arm.linux.org.uk> <E171aOa-0001Q6-00@starship> <20020429153500.B28887@dualathlon.random> <E172K9n-0001Yv-00@starship> <20020501042341.G11414@dualathlon.random> <20020501180547.GA1212440@sgi.com> <20020502011750.M11414@dualathlon.random> <20020502002010.GA14243@krispykreme> <20020502030113.Q11414@dualathlon.random>
> is this machine a numa machine? If not then discontigmem will work just
> fine. also it's a matter of administration, even if it's a numa machine
> you can use it just optimally with discontigmem+numa. Regardless of what
> we do if the partitioning is bad the kernel will do bad. If you create
> zillon discontigous nodes of 256K each, you'd need waste memory to
> handle them regardless of nonlinear or discontigmem (with discontigmem
> you will waste more memory than nonlinear yes, exactly because it's more
> powerful, but I think a machine with an huge lot of non contigous 256K
> chunks is misconfigured, it's like if you pretend to install linux on a
> machine after you partitioned the HD with thousand of logical volumes
> large 256K each [for the sake of this example let's assume there are
> more than 256LV available in LVM], a sane partitioning requires you to
> have at least a partition for /usr large 1 giga, depends what you're
> doing of course, but requiring sane partitioning it's an admin problem
> not a kernel problem IMHO).
Its not a NUMA machine, its one that allows shared processor logical
partitions. While I would prefer the hypervisor to give each partition
a nice memory map (and internally maintain a mapping to real memory)
it does not. I can imagine if the machine has been up for many months
memory could become very fragmented.
Also when we do hotplug memory support will discontigmem be able to
efficiently handle memory turning up all over the place in the memory
map?
Anton
next prev parent reply other threads:[~2002-05-02 15:29 UTC|newest]
Thread overview: 152+ messages / expand[flat|nested] mbox.gz Atom feed top
2002-04-26 18:27 Bug: Discontigmem virt_to_page() [Alpha,ARM,Mips64?] Russell King
2002-04-26 22:46 ` Andrea Arcangeli
2002-04-29 17:50 ` Martin J. Bligh
2002-04-29 22:00 ` Roman Zippel
2002-04-30 0:43 ` Andrea Arcangeli
2002-04-27 22:10 ` Daniel Phillips
2002-04-29 13:35 ` Andrea Arcangeli
2002-04-29 23:02 ` Daniel Phillips
2002-05-01 2:23 ` Andrea Arcangeli
2002-04-30 23:12 ` Daniel Phillips
2002-05-01 1:05 ` Daniel Phillips
2002-05-02 0:47 ` Andrea Arcangeli
2002-05-01 1:26 ` Daniel Phillips
2002-05-02 1:43 ` Andrea Arcangeli
2002-05-01 2:41 ` Daniel Phillips
2002-05-02 13:34 ` Andrea Arcangeli
2002-05-02 15:18 ` Martin J. Bligh
2002-05-02 15:35 ` Andrea Arcangeli
2002-05-01 15:42 ` Daniel Phillips
2002-05-02 16:06 ` Andrea Arcangeli
2002-05-02 16:10 ` Martin J. Bligh
2002-05-02 16:40 ` Andrea Arcangeli
2002-05-02 17:16 ` William Lee Irwin III
2002-05-02 18:41 ` Andrea Arcangeli
2002-05-02 19:19 ` William Lee Irwin III
2002-05-02 19:27 ` Daniel Phillips
2002-05-02 19:38 ` William Lee Irwin III
2002-05-02 19:58 ` Daniel Phillips
2002-05-03 6:28 ` Andrea Arcangeli
2002-05-03 6:10 ` Andrea Arcangeli
2002-05-02 22:20 ` Martin J. Bligh
2002-05-02 21:28 ` William Lee Irwin III
2002-05-02 21:52 ` Kurt Ferreira
2002-05-02 21:55 ` William Lee Irwin III
2002-05-03 6:38 ` Andrea Arcangeli
2002-05-03 6:58 ` Martin J. Bligh
2002-05-03 6:04 ` Andrea Arcangeli
2002-05-03 6:33 ` Martin J. Bligh
2002-05-03 8:38 ` Andrea Arcangeli
2002-05-03 9:26 ` William Lee Irwin III
2002-05-03 15:38 ` Martin J. Bligh
2002-05-03 15:17 ` Virtual address space exhaustion (was Discontigmem virt_to_page() ) Martin J. Bligh
2002-05-03 15:58 ` Andrea Arcangeli
2002-05-03 16:10 ` Martin J. Bligh
2002-05-03 16:25 ` Andrea Arcangeli
2002-05-03 16:02 ` Daniel Phillips
2002-05-03 16:20 ` Andrea Arcangeli
2002-05-03 16:41 ` Daniel Phillips
2002-05-03 16:58 ` Andrea Arcangeli
2002-05-03 18:08 ` Daniel Phillips
2002-05-03 9:24 ` Bug: Discontigmem virt_to_page() [Alpha,ARM,Mips64?] William Lee Irwin III
2002-05-03 10:30 ` Andrea Arcangeli
2002-05-03 11:09 ` William Lee Irwin III
2002-05-03 11:27 ` Andrea Arcangeli
2002-05-03 15:42 ` Martin J. Bligh
2002-05-03 15:32 ` Martin J. Bligh
2002-05-02 19:22 ` Daniel Phillips
2002-05-03 6:06 ` Andrea Arcangeli
2002-05-02 18:25 ` Daniel Phillips
2002-05-02 18:44 ` Andrea Arcangeli
2002-05-02 19:31 ` Martin J. Bligh
2002-05-02 18:57 ` Andrea Arcangeli
2002-05-02 19:08 ` Daniel Phillips
2002-05-03 5:15 ` Andrea Arcangeli
2002-05-05 23:54 ` Daniel Phillips
2002-05-06 0:28 ` Andrea Arcangeli
2002-05-06 0:34 ` Daniel Phillips
2002-05-06 1:01 ` Andrea Arcangeli
2002-05-06 0:55 ` Russell King
2002-05-06 1:07 ` Daniel Phillips
2002-05-06 1:20 ` Andrea Arcangeli
2002-05-06 1:24 ` Daniel Phillips
2002-05-06 1:42 ` Andrea Arcangeli
2002-05-06 1:48 ` Daniel Phillips
2002-05-06 2:06 ` Andrea Arcangeli
2002-05-06 17:40 ` Daniel Phillips
2002-05-06 19:09 ` Martin J. Bligh
2002-05-06 1:09 ` Andrea Arcangeli
2002-05-06 1:13 ` Daniel Phillips
2002-05-06 2:03 ` Daniel Phillips
2002-05-06 2:31 ` Andrea Arcangeli
2002-05-06 8:57 ` Russell King
2002-05-06 8:54 ` Roman Zippel
2002-05-06 15:26 ` Daniel Phillips
2002-05-06 19:07 ` Roman Zippel
2002-05-08 15:57 ` Daniel Phillips
2002-05-08 23:11 ` Roman Zippel
2002-05-09 16:08 ` Daniel Phillips
2002-05-09 22:06 ` Roman Zippel
2002-05-09 22:22 ` Daniel Phillips
2002-05-09 23:00 ` Roman Zippel
2002-05-09 23:22 ` Daniel Phillips
2002-05-10 0:13 ` Roman Zippel
2002-05-02 22:39 ` Martin J. Bligh
2002-05-03 7:04 ` Andrea Arcangeli
2002-05-02 23:42 ` Daniel Phillips
2002-05-03 7:45 ` Andrea Arcangeli
2002-05-02 16:07 ` Martin J. Bligh
2002-05-02 16:58 ` Gerrit Huizenga
2002-05-02 18:10 ` Andrea Arcangeli
2002-05-02 19:28 ` Gerrit Huizenga
2002-05-02 22:23 ` Martin J. Bligh
2002-05-03 6:20 ` Andrea Arcangeli
2002-05-03 6:39 ` Martin J. Bligh
2002-05-02 16:00 ` William Lee Irwin III
2002-05-02 2:37 ` William Lee Irwin III
2002-05-02 15:59 ` Andrea Arcangeli
2002-05-02 16:06 ` William Lee Irwin III
2002-05-01 18:05 ` Jesse Barnes
2002-05-01 23:17 ` Andrea Arcangeli
2002-05-01 23:23 ` discontiguous memory platforms Jesse Barnes
2002-05-02 0:51 ` Ralf Baechle
2002-05-02 1:27 ` Andrea Arcangeli
2002-05-02 1:32 ` Ralf Baechle
2002-05-02 8:50 ` Roman Zippel
2002-05-01 13:21 ` Daniel Phillips
2002-05-02 14:00 ` Roman Zippel
2002-05-01 14:08 ` Daniel Phillips
2002-05-02 17:56 ` Roman Zippel
2002-05-01 17:59 ` Daniel Phillips
2002-05-02 18:26 ` Roman Zippel
2002-05-02 18:32 ` Daniel Phillips
2002-05-02 19:40 ` Roman Zippel
2002-05-02 20:14 ` Daniel Phillips
2002-05-03 6:34 ` Andrea Arcangeli
2002-05-03 9:33 ` Roman Zippel
2002-05-03 6:30 ` Andrea Arcangeli
2002-05-02 18:35 ` Geert Uytterhoeven
2002-05-02 18:39 ` Daniel Phillips
2002-05-02 0:20 ` Bug: Discontigmem virt_to_page() [Alpha,ARM,Mips64?] Anton Blanchard
2002-05-01 1:35 ` Daniel Phillips
2002-05-02 1:45 ` William Lee Irwin III
2002-05-01 2:02 ` Daniel Phillips
2002-05-02 2:33 ` William Lee Irwin III
2002-05-01 2:44 ` Daniel Phillips
2002-05-02 1:46 ` Andrea Arcangeli
2002-05-01 1:56 ` Daniel Phillips
2002-05-02 1:01 ` Andrea Arcangeli
2002-05-02 15:28 ` Anton Blanchard [this message]
2002-05-01 16:10 ` Daniel Phillips
2002-05-02 15:59 ` Dave Engebretsen
2002-05-01 17:24 ` Daniel Phillips
2002-05-02 16:44 ` Dave Engebretsen
2002-05-02 16:31 ` William Lee Irwin III
2002-05-02 16:21 ` Dave Engebretsen
2002-05-02 17:28 ` William Lee Irwin III
2002-05-02 23:05 ` Daniel Phillips
2002-05-03 0:05 ` William Lee Irwin III
2002-05-03 1:19 ` Daniel Phillips
2002-05-03 19:47 ` Dave Engebretsen
2002-05-03 22:06 ` Daniel Phillips
2002-05-03 23:52 ` David Mosberger
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=20020502152825.GE10495@krispykreme \
--to=anton@samba.org \
--cc=andrea@suse.de \
--cc=jbarnes@sgi.com \
--cc=linux-kernel@vger.kernel.org \
--cc=phillips@bonn-fries.net \
--cc=rmk@arm.linux.org.uk \
/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