Re: [patch 1/3 take2] smaps: extract pte walker from smaps code

2007-02-09 Thread Matt Mackall
On Wed, Feb 07, 2007 at 12:30:38AM -0800, Christoph Lameter wrote: > On Tue, 6 Feb 2007, David Rientjes wrote: > > > Extracts the page table entry walker from the smaps-specific code in > > fs/proc/task_mmu.c. This will be used later for clearing the reference > > bits on pages to measure the

Re: [patch 1/3 take2] smaps: extract pte walker from smaps code

2007-02-09 Thread Matt Mackall
On Wed, Feb 07, 2007 at 12:30:38AM -0800, Christoph Lameter wrote: On Tue, 6 Feb 2007, David Rientjes wrote: Extracts the page table entry walker from the smaps-specific code in fs/proc/task_mmu.c. This will be used later for clearing the reference bits on pages to measure the number of

Re: [patch 1/3 take2] smaps: extract pte walker from smaps code

2007-02-08 Thread David Rientjes
On Thu, 8 Feb 2007, Matt Mackall wrote: > I've been looking at a similar refactoring of other code and I think > the way to go is a callback per block-of-PTEs with start and end > pointers. That gets rid of most of the call indirection overhead. > Yes, but only in a limited number of cases

Re: [patch 1/3 take2] smaps: extract pte walker from smaps code

2007-02-08 Thread Matt Mackall
On Wed, Feb 07, 2007 at 03:29:34PM +0900, Paul Mundt wrote: > On Tue, Feb 06, 2007 at 10:15:47PM -0800, David Rientjes wrote: > > Extracts the page table entry walker from the smaps-specific code in > > fs/proc/task_mmu.c. This will be used later for clearing the reference > > bits on pages to

Re: [patch 1/3 take2] smaps: extract pte walker from smaps code

2007-02-08 Thread Matt Mackall
On Wed, Feb 07, 2007 at 03:29:34PM +0900, Paul Mundt wrote: On Tue, Feb 06, 2007 at 10:15:47PM -0800, David Rientjes wrote: Extracts the page table entry walker from the smaps-specific code in fs/proc/task_mmu.c. This will be used later for clearing the reference bits on pages to measure

Re: [patch 1/3 take2] smaps: extract pte walker from smaps code

2007-02-08 Thread David Rientjes
On Thu, 8 Feb 2007, Matt Mackall wrote: I've been looking at a similar refactoring of other code and I think the way to go is a callback per block-of-PTEs with start and end pointers. That gets rid of most of the call indirection overhead. Yes, but only in a limited number of cases

Re: [patch 1/3 take2] smaps: extract pte walker from smaps code

2007-02-07 Thread David Rientjes
On Wed, 7 Feb 2007, Christoph Lameter wrote: > Clearing reference bits? Ummm... That is a pretty inaccurate measure since > reclaim can remove pages and revert the reference bits. It can never work > reliably. > It's not intended to work precisely, it's intended to give a good estimate of

Re: [patch 1/3 take2] smaps: extract pte walker from smaps code

2007-02-07 Thread Christoph Lameter
On Tue, 6 Feb 2007, David Rientjes wrote: > Extracts the page table entry walker from the smaps-specific code in > fs/proc/task_mmu.c. This will be used later for clearing the reference > bits on pages to measure the number of pages accessed over a time period > through /proc/pid/smaps.

Re: [patch 1/3 take2] smaps: extract pte walker from smaps code

2007-02-07 Thread Christoph Lameter
On Tue, 6 Feb 2007, David Rientjes wrote: Extracts the page table entry walker from the smaps-specific code in fs/proc/task_mmu.c. This will be used later for clearing the reference bits on pages to measure the number of pages accessed over a time period through /proc/pid/smaps. Clearing

Re: [patch 1/3 take2] smaps: extract pte walker from smaps code

2007-02-07 Thread David Rientjes
On Wed, 7 Feb 2007, Christoph Lameter wrote: Clearing reference bits? Ummm... That is a pretty inaccurate measure since reclaim can remove pages and revert the reference bits. It can never work reliably. It's not intended to work precisely, it's intended to give a good estimate of task

Re: [patch 1/3 take2] smaps: extract pte walker from smaps code

2007-02-06 Thread Paul Mundt
On Tue, Feb 06, 2007 at 10:49:14PM -0800, Andrew Morton wrote: > On Wed, 7 Feb 2007 15:29:34 +0900 Paul Mundt <[EMAIL PROTECTED]> wrote: > > I like the general idea of this patch set, however.. > > David didn't really spell out the rationale. Userspace people ask "how > much memory is my

Re: [patch 1/3 take2] smaps: extract pte walker from smaps code

2007-02-06 Thread Andrew Morton
On Wed, 7 Feb 2007 15:29:34 +0900 Paul Mundt <[EMAIL PROTECTED]> wrote: > On Tue, Feb 06, 2007 at 10:15:47PM -0800, David Rientjes wrote: > > Extracts the page table entry walker from the smaps-specific code in > > fs/proc/task_mmu.c. This will be used later for clearing the reference > > bits

Re: [patch 1/3 take2] smaps: extract pte walker from smaps code

2007-02-06 Thread Paul Mundt
On Tue, Feb 06, 2007 at 10:15:47PM -0800, David Rientjes wrote: > Extracts the page table entry walker from the smaps-specific code in > fs/proc/task_mmu.c. This will be used later for clearing the reference > bits on pages to measure the number of pages accessed over a time period > through

[patch 1/3 take2] smaps: extract pte walker from smaps code

2007-02-06 Thread David Rientjes
Extracts the page table entry walker from the smaps-specific code in fs/proc/task_mmu.c. This will be used later for clearing the reference bits on pages to measure the number of pages accessed over a time period through /proc/pid/smaps. The new struct pte_walker includes the struct

[patch 1/3 take2] smaps: extract pte walker from smaps code

2007-02-06 Thread David Rientjes
Extracts the page table entry walker from the smaps-specific code in fs/proc/task_mmu.c. This will be used later for clearing the reference bits on pages to measure the number of pages accessed over a time period through /proc/pid/smaps. The new struct pte_walker includes the struct

Re: [patch 1/3 take2] smaps: extract pte walker from smaps code

2007-02-06 Thread Paul Mundt
On Tue, Feb 06, 2007 at 10:15:47PM -0800, David Rientjes wrote: Extracts the page table entry walker from the smaps-specific code in fs/proc/task_mmu.c. This will be used later for clearing the reference bits on pages to measure the number of pages accessed over a time period through

Re: [patch 1/3 take2] smaps: extract pte walker from smaps code

2007-02-06 Thread Andrew Morton
On Wed, 7 Feb 2007 15:29:34 +0900 Paul Mundt [EMAIL PROTECTED] wrote: On Tue, Feb 06, 2007 at 10:15:47PM -0800, David Rientjes wrote: Extracts the page table entry walker from the smaps-specific code in fs/proc/task_mmu.c. This will be used later for clearing the reference bits on pages

Re: [patch 1/3 take2] smaps: extract pte walker from smaps code

2007-02-06 Thread Paul Mundt
On Tue, Feb 06, 2007 at 10:49:14PM -0800, Andrew Morton wrote: On Wed, 7 Feb 2007 15:29:34 +0900 Paul Mundt [EMAIL PROTECTED] wrote: I like the general idea of this patch set, however.. David didn't really spell out the rationale. Userspace people ask how much memory is my application