Re: [PATCH] fix page_alloc for larger I/O segments (improved)

2007-12-20 Thread Matthew Wilcox
On Fri, Dec 14, 2007 at 11:13:40AM -0700, Matthew Wilcox wrote: > I'll send it to our DB team to see if this improves our numbers at all. It does, by approximately 0.67%. This is about double the margin of error, and a significant improvement. Thanks! -- Intel are signing my paycheques ... the

Re: [PATCH] fix page_alloc for larger I/O segments (improved)

2007-12-16 Thread Mel Gorman
On (14/12/07 13:07), Mark Lord didst pronounce: > > > That (also) works for me here, regularly generating 64KB I/O segments with > SLAB. > Brilliant. Thanks a lot Mark. -- Mel Gorman Part-time Phd Student Linux Technology Center University of Limerick

Re: [PATCH] fix page_alloc for larger I/O segments (improved)

2007-12-14 Thread Mark Lord
Matthew Wilcox wrote: On Fri, Dec 14, 2007 at 05:42:37PM +, Mel Gorman wrote: Regrettably this interferes with anti-fragmentation because the "next" page on the list on return from rmqueue_bulk is not guaranteed to be of the right mobility type. I fixed it as an additional patch but it adds

Re: [PATCH] fix page_alloc for larger I/O segments (improved)

2007-12-14 Thread Matthew Wilcox
On Fri, Dec 14, 2007 at 05:42:37PM +, Mel Gorman wrote: > Regrettably this interferes with anti-fragmentation because the "next" page > on the list on return from rmqueue_bulk is not guaranteed to be of the right > mobility type. I fixed it as an additional patch but it adds additional cost > t

Re: [PATCH] fix page_alloc for larger I/O segments (improved)

2007-12-14 Thread Mark Lord
Mel Gorman wrote: On (13/12/07 19:46), Mark Lord didst pronounce: "Improved version", more similar to the 2.6.23 code: Fix page allocator to give better chance of larger contiguous segments (again). Signed-off-by: Mark Lord <[EMAIL PROTECTED] Regrettably this interferes with anti-fragmenta

Re: [PATCH] fix page_alloc for larger I/O segments (improved)

2007-12-14 Thread Mel Gorman
On (13/12/07 19:46), Mark Lord didst pronounce: > > "Improved version", more similar to the 2.6.23 code: > > Fix page allocator to give better chance of larger contiguous segments > (again). > > Signed-off-by: Mark Lord <[EMAIL PROTECTED] Regrettably this interferes with anti-fragmentation bec

Re: [PATCH] fix page_alloc for larger I/O segments (improved)

2007-12-13 Thread Mark Lord
Andrew Morton wrote: On Thu, 13 Dec 2007 19:57:29 -0500 James Bottomley <[EMAIL PROTECTED]> wrote: On Thu, 2007-12-13 at 19:46 -0500, Mark Lord wrote: "Improved version", more similar to the 2.6.23 code: Fix page allocator to give better chance of larger contiguous segments (again). Signed-o

Re: [PATCH] fix page_alloc for larger I/O segments (improved)

2007-12-13 Thread Andrew Morton
On Thu, 13 Dec 2007 19:57:29 -0500 James Bottomley <[EMAIL PROTECTED]> wrote: > > On Thu, 2007-12-13 at 19:46 -0500, Mark Lord wrote: > > "Improved version", more similar to the 2.6.23 code: > > > > Fix page allocator to give better chance of larger contiguous segments > > (again). > > > > Sig

Re: [PATCH] fix page_alloc for larger I/O segments (improved)

2007-12-13 Thread James Bottomley
On Thu, 2007-12-13 at 19:46 -0500, Mark Lord wrote: > "Improved version", more similar to the 2.6.23 code: > > Fix page allocator to give better chance of larger contiguous segments > (again). > > Signed-off-by: Mark Lord <[EMAIL PROTECTED] > --- > > --- old/mm/page_alloc.c 2007-12-13 19

[PATCH] fix page_alloc for larger I/O segments (improved)

2007-12-13 Thread Mark Lord
"Improved version", more similar to the 2.6.23 code: Fix page allocator to give better chance of larger contiguous segments (again). Signed-off-by: Mark Lord <[EMAIL PROTECTED] --- --- old/mm/page_alloc.c 2007-12-13 19:25:15.0 -0500 +++ linux-2.6/mm/page_alloc.c 2007-12-13 19:43:07.0