Ethan Solomita <[EMAIL PROTECTED]> wrote:
> I suggest a variant on what Andrew says: don't change reclaim.
> Instead, when referencing a page, don't mark the page as referenced if
> the current task is not permitted to allocate from the page's node. I'm
> thinking in terms of cpusets, with eac
Herbert Poetzl wrote:
On Sat, Mar 24, 2007 at 12:19:06PM -0800, Andrew Morton wrote:
Or change the reclaim code so that a page which hasn't
been referenced from a process within its hardware
container is considered unreferenced (so it gets reclaimed).
that might easily lead to some pi
Andrew Morton wrote:
[...skip]
> The problem is memory reclaim. A number of schemes which have been
> proposed require a per-container page reclaim mechanism - basically a
> separate scanner.
>
> This is a huge, huge, huge problem. The present scanner has been under
> development for over a
Andrew Morton wrote:
On Mon, 26 Mar 2007 08:06:07 +0530 Balbir Singh <[EMAIL PROTECTED]> wrote:
Andrew Morton wrote:
Don't we break the global LRU with this scheme?
Sure, but that's deliberate!
(And we don't have a global LRU - the LRUs are per-zone).
Yes, true. But if we use zones for con
On Mon, 26 Mar 2007 08:06:07 +0530 Balbir Singh <[EMAIL PROTECTED]> wrote:
> Andrew Morton wrote:
> >> Don't we break the global LRU with this scheme?
> >
> > Sure, but that's deliberate!
> >
> > (And we don't have a global LRU - the LRUs are per-zone).
> >
>
> Yes, true. But if we use zones f
Andrew Morton wrote:
Don't we break the global LRU with this scheme?
Sure, but that's deliberate!
(And we don't have a global LRU - the LRUs are per-zone).
Yes, true. But if we use zones for containers and say we have 400
of them, with all of them under limit. When the system wants
to recla
On Sun, 25 Mar 2007 15:20:35 +0530 Balbir Singh <[EMAIL PROTECTED]> wrote:
> Andrew Morton wrote:
>
> > The problem is memory reclaim. A number of schemes which have been
> > proposed require a per-container page reclaim mechanism - basically a
> > separate scanner.
> >
> > This is a huge, huge
On Sat, Mar 24, 2007 at 08:29:51PM -0800, Andrew Morton wrote:
> On Sun, 25 Mar 2007 04:21:56 +0200 Herbert Poetzl <[EMAIL PROTECTED]> wrote:
>
> > > a) slice the machine into 128 fake NUMA nodes, use each node as the
> > >basic block of memory allocation, manage the binding between these
> >
Andrew Morton wrote:
The problem is memory reclaim. A number of schemes which have been
proposed require a per-container page reclaim mechanism - basically a
separate scanner.
This is a huge, huge, huge problem. The present scanner has been under
development for over a decade and has had trem
On Sun, 25 Mar 2007 04:21:56 +0200 Herbert Poetzl <[EMAIL PROTECTED]> wrote:
> > a) slice the machine into 128 fake NUMA nodes, use each node as the
> >basic block of memory allocation, manage the binding between these
> >memory hunks and process groups with cpusets.
>
> 128 sounds a litt
On Sat, Mar 24, 2007 at 12:19:06PM -0800, Andrew Morton wrote:
> On Sat, 24 Mar 2007 19:38:06 +0100 Herbert Poetzl <[EMAIL PROTECTED]> wrote:
>
> > On Fri, Mar 23, 2007 at 09:42:35PM -0800, Andrew Morton wrote:
> > > On Fri, 23 Mar 2007 20:30:00 +0100 Herbert Poetzl <[EMAIL PROTECTED]>
> > > wrot
On Sat, 24 Mar 2007 19:38:06 +0100 Herbert Poetzl <[EMAIL PROTECTED]> wrote:
> On Fri, Mar 23, 2007 at 09:42:35PM -0800, Andrew Morton wrote:
> > On Fri, 23 Mar 2007 20:30:00 +0100 Herbert Poetzl <[EMAIL PROTECTED]> wrote:
> >
> > >
> > > Hi Eric!
> > > Hi Folks!
> > >
> > > here is a real worl
On Fri, Mar 23, 2007 at 09:42:35PM -0800, Andrew Morton wrote:
> On Fri, 23 Mar 2007 20:30:00 +0100 Herbert Poetzl <[EMAIL PROTECTED]> wrote:
>
> >
> > Hi Eric!
> > Hi Folks!
> >
> > here is a real world example result from one of my tests
> > regarding the benefit of sharing over separate memor
On Fri, 23 Mar 2007 20:30:00 +0100 Herbert Poetzl <[EMAIL PROTECTED]> wrote:
>
> Hi Eric!
> Hi Folks!
>
> here is a real world example result from one of my tests
> regarding the benefit of sharing over separate memory
>
> the setup is quite simple, a typical machine used by
> providers all ove
Hi Eric!
Hi Folks!
here is a real world example result from one of my tests
regarding the benefit of sharing over separate memory
the setup is quite simple, a typical machine used by
providers all over the world, a dual Pentium D 3.2GHz
with 4GB of memory and a single 160GB SATA disk running
a L
15 matches
Mail list logo
