linuxppc-dev.lists.ozlabs.org archive mirror
 help / color / mirror / Atom feed
From: Michael Ellerman <michael@ellerman.id.au>
To: Mel Gorman <mel@csn.ul.ie>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>,
	linux-mm@kvack.org, libhugetlbfs-devel@lists.sourceforge.net,
	linux-kernel@vger.kernel.org, linuxppc-dev@ozlabs.org,
	Eric Munson <ebmunson@us.ibm.com>,
	Andrew Morton <akpm@linux-foundation.org>
Subject: Re: [RFC] [PATCH 0/5 V2] Huge page backed user-space stacks
Date: Fri, 01 Aug 2008 00:32:55 +1000	[thread overview]
Message-ID: <1217514775.19050.41.camel@localhost> (raw)
In-Reply-To: <20080731135016.GG1704@csn.ul.ie>

[-- Attachment #1: Type: text/plain, Size: 2059 bytes --]

On Thu, 2008-07-31 at 14:50 +0100, Mel Gorman wrote:
> On (31/07/08 21:51), Nick Piggin didst pronounce:
> > On Thursday 31 July 2008 21:27, Mel Gorman wrote:
> > > On (31/07/08 16:26), Nick Piggin didst pronounce:
> > 
> > > > I imagine it should be, unless you're using a CPU with seperate TLBs for
> > > > small and huge pages, and your large data set is mapped with huge pages,
> > > > in which case you might now introduce *new* TLB contention between the
> > > > stack and the dataset :)
> > >
> > > Yes, this can happen particularly on older CPUs. For example, on my
> > > crash-test laptop the Pentium III there reports
> > >
> > > TLB and cache info:
> > > 01: Instruction TLB: 4KB pages, 4-way set assoc, 32 entries
> > > 02: Instruction TLB: 4MB pages, 4-way set assoc, 2 entries
> > 
> > Oh? Newer CPUs tend to have unified TLBs?
> > 
> 
> I've seen more unified DTLBs (ITLB tends to be split) than not but it could
> just be where I'm looking. For example, on the machine I'm writing this
> (Core Duo), it's
> 
> TLB and cache info:
> 51: Instruction TLB: 4KB and 2MB or 4MB pages, 128 entries
> 5b: Data TLB: 4KB and 4MB pages, 64 entries
> 
> DTLB is unified there but on my T60p laptop where I guess they want the CPU
> to be using less power and be cheaper, it's
> 
> TLB info
>  Instruction TLB: 4K pages, 4-way associative, 128 entries.
>  Instruction TLB: 4MB pages, fully associative, 2 entries
>  Data TLB: 4K pages, 4-way associative, 128 entries.
>  Data TLB: 4MB pages, 4-way associative, 8 entries

Clearly I've been living under a rock, but I didn't know one could get
such nicely formatted info.

In case I'm not the only one, a bit of googling turned up "x86info",
courtesy of davej - apt-get'able and presumably yum'able too.

cheers

-- 
Michael Ellerman
OzLabs, IBM Australia Development Lab

wwweb: http://michael.ellerman.id.au
phone: +61 2 6212 1183 (tie line 70 21183)

We do not inherit the earth from our ancestors,
we borrow it from our children. - S.M.A.R.T Person

[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 189 bytes --]

  reply	other threads:[~2008-07-31 14:32 UTC|newest]

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-07-28 19:17 [RFC] [PATCH 0/5 V2] Huge page backed user-space stacks Eric Munson
2008-07-28 19:17 ` [PATCH 1/5 V2] Align stack boundaries based on personality Eric Munson
2008-07-28 20:09   ` Dave Hansen
2008-07-28 19:17 ` [PATCH 2/5 V2] Add shared and reservation control to hugetlb_file_setup Eric Munson
2008-07-28 19:17 ` [PATCH 3/5] Split boundary checking from body of do_munmap Eric Munson
2008-07-28 19:17 ` [PATCH 4/5 V2] Build hugetlb backed process stacks Eric Munson
2008-07-28 20:37   ` Dave Hansen
2008-07-28 19:17 ` [PATCH 5/5 V2] [PPC] Setup stack memory segment for hugetlb pages Eric Munson
2008-07-28 20:33 ` [RFC] [PATCH 0/5 V2] Huge page backed user-space stacks Dave Hansen
2008-07-28 21:23   ` Eric B Munson
2008-07-30  8:41 ` Andrew Morton
2008-07-30 15:04   ` Eric B Munson
2008-07-30 15:08   ` Eric B Munson
2008-07-30  8:43 ` Andrew Morton
2008-07-30 17:23   ` Mel Gorman
2008-07-30 17:34     ` Andrew Morton
2008-07-30 19:30       ` Mel Gorman
2008-07-30 19:40         ` Christoph Lameter
2008-07-30 20:07         ` Andrew Morton
2008-07-31 10:31           ` Mel Gorman
2008-08-04 21:10             ` Dave Hansen
2008-08-05 11:11               ` Mel Gorman
2008-08-05 16:12                 ` Dave Hansen
2008-08-05 16:28                   ` Mel Gorman
2008-08-05 17:53                     ` Dave Hansen
2008-08-06  9:02                       ` Mel Gorman
2008-08-06 19:50                         ` Dave Hansen
2008-08-07 16:06                           ` Mel Gorman
2008-08-07 17:29                             ` Dave Hansen
2008-08-11  8:04                               ` Mel Gorman
2008-07-31  6:04       ` Nick Piggin
2008-07-31  6:14         ` Andrew Morton
2008-07-31  6:26           ` Nick Piggin
2008-07-31 11:27             ` Mel Gorman
2008-07-31 11:51               ` Nick Piggin
2008-07-31 13:50                 ` Mel Gorman
2008-07-31 14:32                   ` Michael Ellerman [this message]
2008-08-06 18:49       ` Andi Kleen

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=1217514775.19050.41.camel@localhost \
    --to=michael@ellerman.id.au \
    --cc=akpm@linux-foundation.org \
    --cc=ebmunson@us.ibm.com \
    --cc=libhugetlbfs-devel@lists.sourceforge.net \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linuxppc-dev@ozlabs.org \
    --cc=mel@csn.ul.ie \
    --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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).