From: Chandra Seetharaman <sekharan@us.ibm.com>
To: Magnus Damm <magnus.damm@gmail.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>,
Magnus Damm <magnus@valinux.co.jp>,
Linux Kernel <linux-kernel@vger.kernel.org>,
linux-mm@kvack.org, Valerie Clement <Valerie.Clement@bull.net>
Subject: Re: [PATCH 03/03] Unmapped: Add guarantee code
Date: Fri, 10 Mar 2006 07:41:17 -0800 [thread overview]
Message-ID: <1142005277.8174.107.camel@linuxchandra> (raw)
In-Reply-To: <aec7e5c30603092204h21fa7639wf90e6d4e2fdee128@mail.gmail.com>
On Fri, 2006-03-10 at 15:04 +0900, Magnus Damm wrote:
> On 3/10/06, Nick Piggin <nickpiggin@yahoo.com.au> wrote:
> > Magnus Damm wrote:
> > > Implement per-LRU guarantee through sysctl.
> > >
> > > This patch introduces the two new sysctl files "node_mapped_guar" and
> > > "node_unmapped_guar". Each file contains one percentage per node and tells
> > > the system how many percentage of all pages that should be kept in RAM as
> > > unmapped or mapped pages.
> > >
> >
> > The whole Linux VM philosophy until now has been to get away from stuff
> > like this.
>
> Yeah, and Linux has never supported memory resource control either, right?
>
> > If your app is really that specialised then maybe it can use mlock. If
> > not, maybe the VM is currently broken.
> >
> > You do have a real-world workload that is significantly improved by this,
> > right?
>
> Not really, but I think there is a demand for memory resource control today.
As a person who is working on CKRM, I totally agree with this :)
>
> The memory controller in ckrm also breaks out the LRU, but puts one
> LRU instance in each class. My code does not depend on ckrm, but it
> should be possible to have some kind of resource control with this
i do not understand how breaking lru lists into mapped/unmapped pages
and providing a knob to control the proportion of mapped/unmapped pages
in a node help in resource control.
Can you explain, please. I am very interested.
> patch and cpusets. And yeah, add numa emulation if you are out of
> nodes. =)
>
> Thanks,
>
> / magnus
>
> --
> 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>
--
----------------------------------------------------------------------
Chandra Seetharaman | Be careful what you choose....
- sekharan@us.ibm.com | .......you may get it.
----------------------------------------------------------------------
WARNING: multiple messages have this Message-ID (diff)
From: Chandra Seetharaman <sekharan@us.ibm.com>
To: Magnus Damm <magnus.damm@gmail.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>,
Magnus Damm <magnus@valinux.co.jp>,
Linux Kernel <linux-kernel@vger.kernel.org>,
linux-mm@kvack.org, Valerie Clement <Valerie.Clement@bull.net>
Subject: Re: [PATCH 03/03] Unmapped: Add guarantee code
Date: Fri, 10 Mar 2006 07:41:17 -0800 [thread overview]
Message-ID: <1142005277.8174.107.camel@linuxchandra> (raw)
In-Reply-To: <aec7e5c30603092204h21fa7639wf90e6d4e2fdee128@mail.gmail.com>
On Fri, 2006-03-10 at 15:04 +0900, Magnus Damm wrote:
> On 3/10/06, Nick Piggin <nickpiggin@yahoo.com.au> wrote:
> > Magnus Damm wrote:
> > > Implement per-LRU guarantee through sysctl.
> > >
> > > This patch introduces the two new sysctl files "node_mapped_guar" and
> > > "node_unmapped_guar". Each file contains one percentage per node and tells
> > > the system how many percentage of all pages that should be kept in RAM as
> > > unmapped or mapped pages.
> > >
> >
> > The whole Linux VM philosophy until now has been to get away from stuff
> > like this.
>
> Yeah, and Linux has never supported memory resource control either, right?
>
> > If your app is really that specialised then maybe it can use mlock. If
> > not, maybe the VM is currently broken.
> >
> > You do have a real-world workload that is significantly improved by this,
> > right?
>
> Not really, but I think there is a demand for memory resource control today.
As a person who is working on CKRM, I totally agree with this :)
>
> The memory controller in ckrm also breaks out the LRU, but puts one
> LRU instance in each class. My code does not depend on ckrm, but it
> should be possible to have some kind of resource control with this
i do not understand how breaking lru lists into mapped/unmapped pages
and providing a knob to control the proportion of mapped/unmapped pages
in a node help in resource control.
Can you explain, please. I am very interested.
> patch and cpusets. And yeah, add numa emulation if you are out of
> nodes. =)
>
> Thanks,
>
> / magnus
>
> --
> 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>
--
----------------------------------------------------------------------
Chandra Seetharaman | Be careful what you choose....
- sekharan@us.ibm.com | .......you may get it.
----------------------------------------------------------------------
--
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:[~2006-03-10 15:42 UTC|newest]
Thread overview: 50+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-03-10 3:44 [PATCH 00/03] Unmapped: Separate unmapped and mapped pages Magnus Damm
2006-03-10 3:44 ` Magnus Damm
2006-03-10 3:44 ` [PATCH 01/03] Unmapped: Implement two LRU:s Magnus Damm
2006-03-10 3:44 ` Magnus Damm
2006-03-10 19:16 ` Christoph Lameter
2006-03-10 19:16 ` Christoph Lameter
2006-03-11 12:14 ` Magnus Damm
2006-03-11 12:14 ` Magnus Damm
2006-03-10 3:44 ` [PATCH 02/03] Unmapped: Modify LRU behaviour Magnus Damm
2006-03-10 3:44 ` Magnus Damm
2006-03-10 3:44 ` [PATCH 03/03] Unmapped: Add guarantee code Magnus Damm
2006-03-10 3:44 ` Magnus Damm
2006-03-10 4:57 ` Nick Piggin
2006-03-10 4:57 ` Nick Piggin
2006-03-10 6:04 ` Magnus Damm
2006-03-10 6:04 ` Magnus Damm
2006-03-10 15:41 ` Chandra Seetharaman [this message]
2006-03-10 15:41 ` Chandra Seetharaman
2006-03-11 12:29 ` Magnus Damm
2006-03-11 12:29 ` Magnus Damm
2006-03-15 15:32 ` Chandra Seetharaman
2006-03-15 15:32 ` Chandra Seetharaman
2006-03-10 4:55 ` [PATCH 00/03] Unmapped: Separate unmapped and mapped pages Nick Piggin
2006-03-10 4:55 ` Nick Piggin
2006-03-10 5:55 ` Magnus Damm
2006-03-10 5:55 ` Magnus Damm
2006-03-10 7:52 ` Arjan van de Ven
2006-03-10 7:52 ` Arjan van de Ven
2006-03-10 13:19 ` Magnus Damm
2006-03-10 13:19 ` Magnus Damm
2006-03-10 14:05 ` Arjan van de Ven
2006-03-10 14:05 ` Arjan van de Ven
2006-03-11 11:52 ` Magnus Damm
2006-03-11 11:52 ` Magnus Damm
2006-03-11 20:58 ` Peter Zijlstra
2006-03-11 20:58 ` Peter Zijlstra
2006-03-13 2:28 ` Magnus Damm
2006-03-13 2:28 ` Magnus Damm
2006-03-10 12:22 ` Peter Zijlstra
2006-03-10 12:22 ` Peter Zijlstra
2006-03-10 13:38 ` Magnus Damm
2006-03-10 13:38 ` Magnus Damm
2006-03-11 21:08 ` Peter Zijlstra
2006-03-11 21:08 ` Peter Zijlstra
2006-03-13 3:05 ` Magnus Damm
2006-03-13 3:05 ` Magnus Damm
2006-03-10 19:12 ` Christoph Lameter
2006-03-10 19:12 ` Christoph Lameter
2006-03-11 11:56 ` Magnus Damm
2006-03-11 11:56 ` Magnus Damm
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=1142005277.8174.107.camel@linuxchandra \
--to=sekharan@us.ibm.com \
--cc=Valerie.Clement@bull.net \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=magnus.damm@gmail.com \
--cc=magnus@valinux.co.jp \
--cc=nickpiggin@yahoo.com.au \
/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.