Re: [PATCH] mm/vmscan.c: avoid recording the original scan targets in shrink_lruvec()

2014-06-16 Thread Chen Yucong
On Mon, 2014-06-16 at 16:42 -0700, Andrew Morton wrote: > On Mon, 16 Jun 2014 20:57:54 +0800 Chen Yucong wrote: > > > On Mon, 2014-06-09 at 21:27 +0800, Chen Yucong wrote: > > > Via https://lkml.org/lkml/2013/4/10/334 , we can find that recording the > > > original scan targets introduces extra

Re: [PATCH] mm/vmscan.c: avoid recording the original scan targets in shrink_lruvec()

2014-06-16 Thread Minchan Kim
On Mon, Jun 16, 2014 at 04:42:37PM -0700, Andrew Morton wrote: > On Mon, 16 Jun 2014 20:57:54 +0800 Chen Yucong wrote: > > > On Mon, 2014-06-09 at 21:27 +0800, Chen Yucong wrote: > > > Via https://lkml.org/lkml/2013/4/10/334 , we can find that recording the > > > original scan targets introduces

Re: [PATCH] mm/vmscan.c: avoid recording the original scan targets in shrink_lruvec()

2014-06-16 Thread Minchan Kim
On Mon, Jun 16, 2014 at 08:57:54PM +0800, Chen Yucong wrote: > On Mon, 2014-06-09 at 21:27 +0800, Chen Yucong wrote: > > Via https://lkml.org/lkml/2013/4/10/334 , we can find that recording the > > original scan targets introduces extra 40 bytes on the stack. This patch > > is able to avoid this

Re: [PATCH] mm/vmscan.c: avoid recording the original scan targets in shrink_lruvec()

2014-06-16 Thread Andrew Morton
On Mon, 16 Jun 2014 20:57:54 +0800 Chen Yucong wrote: > On Mon, 2014-06-09 at 21:27 +0800, Chen Yucong wrote: > > Via https://lkml.org/lkml/2013/4/10/334 , we can find that recording the > > original scan targets introduces extra 40 bytes on the stack. This patch > > is able to avoid this

Re: [PATCH] mm/vmscan.c: avoid recording the original scan targets in shrink_lruvec()

2014-06-16 Thread Chen Yucong
On Mon, 2014-06-09 at 21:27 +0800, Chen Yucong wrote: > Via https://lkml.org/lkml/2013/4/10/334 , we can find that recording the > original scan targets introduces extra 40 bytes on the stack. This patch > is able to avoid this situation and the call to memcpy(). At the same time, > it does not

Re: [PATCH] mm/vmscan.c: avoid recording the original scan targets in shrink_lruvec()

2014-06-16 Thread Chen Yucong
On Sun, 2014-06-15 at 17:47 -0700, Hugh Dickins wrote: > On Wed, 11 Jun 2014, Chen Yucong wrote: > > On Tue, 2014-06-10 at 16:33 -0700, Andrew Morton wrote: > > > > break; > > > > > > > > if (nr_file > nr_anon) { > > > > - unsigned long

Re: [PATCH] mm/vmscan.c: avoid recording the original scan targets in shrink_lruvec()

2014-06-16 Thread Chen Yucong
On Sun, 2014-06-15 at 17:47 -0700, Hugh Dickins wrote: On Wed, 11 Jun 2014, Chen Yucong wrote: On Tue, 2014-06-10 at 16:33 -0700, Andrew Morton wrote: break; if (nr_file nr_anon) { - unsigned long scan_target =

Re: [PATCH] mm/vmscan.c: avoid recording the original scan targets in shrink_lruvec()

2014-06-16 Thread Chen Yucong
On Mon, 2014-06-09 at 21:27 +0800, Chen Yucong wrote: Via https://lkml.org/lkml/2013/4/10/334 , we can find that recording the original scan targets introduces extra 40 bytes on the stack. This patch is able to avoid this situation and the call to memcpy(). At the same time, it does not change

Re: [PATCH] mm/vmscan.c: avoid recording the original scan targets in shrink_lruvec()

2014-06-16 Thread Andrew Morton
On Mon, 16 Jun 2014 20:57:54 +0800 Chen Yucong sla...@gmail.com wrote: On Mon, 2014-06-09 at 21:27 +0800, Chen Yucong wrote: Via https://lkml.org/lkml/2013/4/10/334 , we can find that recording the original scan targets introduces extra 40 bytes on the stack. This patch is able to avoid

Re: [PATCH] mm/vmscan.c: avoid recording the original scan targets in shrink_lruvec()

2014-06-16 Thread Minchan Kim
On Mon, Jun 16, 2014 at 08:57:54PM +0800, Chen Yucong wrote: On Mon, 2014-06-09 at 21:27 +0800, Chen Yucong wrote: Via https://lkml.org/lkml/2013/4/10/334 , we can find that recording the original scan targets introduces extra 40 bytes on the stack. This patch is able to avoid this

Re: [PATCH] mm/vmscan.c: avoid recording the original scan targets in shrink_lruvec()

2014-06-16 Thread Minchan Kim
On Mon, Jun 16, 2014 at 04:42:37PM -0700, Andrew Morton wrote: On Mon, 16 Jun 2014 20:57:54 +0800 Chen Yucong sla...@gmail.com wrote: On Mon, 2014-06-09 at 21:27 +0800, Chen Yucong wrote: Via https://lkml.org/lkml/2013/4/10/334 , we can find that recording the original scan targets

Re: [PATCH] mm/vmscan.c: avoid recording the original scan targets in shrink_lruvec()

2014-06-16 Thread Chen Yucong
On Mon, 2014-06-16 at 16:42 -0700, Andrew Morton wrote: On Mon, 16 Jun 2014 20:57:54 +0800 Chen Yucong sla...@gmail.com wrote: On Mon, 2014-06-09 at 21:27 +0800, Chen Yucong wrote: Via https://lkml.org/lkml/2013/4/10/334 , we can find that recording the original scan targets introduces

Re: [PATCH] mm/vmscan.c: avoid recording the original scan targets in shrink_lruvec()

2014-06-15 Thread Hugh Dickins
On Wed, 11 Jun 2014, Chen Yucong wrote: > On Tue, 2014-06-10 at 16:33 -0700, Andrew Morton wrote: > > > break; > > > > > > if (nr_file > nr_anon) { > > > - unsigned long scan_target = > > targets[LRU_INACTIVE_ANON] + > > > > > -

Re: [PATCH] mm/vmscan.c: avoid recording the original scan targets in shrink_lruvec()

2014-06-15 Thread Hugh Dickins
On Wed, 11 Jun 2014, Chen Yucong wrote: On Tue, 2014-06-10 at 16:33 -0700, Andrew Morton wrote: break; if (nr_file nr_anon) { - unsigned long scan_target = targets[LRU_INACTIVE_ANON] + -

Re: [PATCH] mm/vmscan.c: avoid recording the original scan targets in shrink_lruvec()

2014-06-10 Thread Chen Yucong
On Tue, 2014-06-10 at 16:33 -0700, Andrew Morton wrote: > > break; > > > > if (nr_file > nr_anon) { > > - unsigned long scan_target = > targets[LRU_INACTIVE_ANON] + > > > -

Re: [PATCH] mm/vmscan.c: avoid recording the original scan targets in shrink_lruvec()

2014-06-10 Thread Chen Yucong
On Tue, 2014-06-10 at 16:33 -0700, Andrew Morton wrote: > On Mon, 9 Jun 2014 21:27:16 +0800 Chen Yucong wrote: > > > Via https://lkml.org/lkml/2013/4/10/334 , we can find that recording the > > original scan targets introduces extra 40 bytes on the stack. This patch > > is able to avoid this

Re: [PATCH] mm/vmscan.c: avoid recording the original scan targets in shrink_lruvec()

2014-06-10 Thread Andrew Morton
On Mon, 9 Jun 2014 21:27:16 +0800 Chen Yucong wrote: > Via https://lkml.org/lkml/2013/4/10/334 , we can find that recording the > original scan targets introduces extra 40 bytes on the stack. This patch > is able to avoid this situation and the call to memcpy(). At the same time, > it does not

Re: [PATCH] mm/vmscan.c: avoid recording the original scan targets in shrink_lruvec()

2014-06-10 Thread Andrew Morton
On Mon, 9 Jun 2014 21:27:16 +0800 Chen Yucong sla...@gmail.com wrote: Via https://lkml.org/lkml/2013/4/10/334 , we can find that recording the original scan targets introduces extra 40 bytes on the stack. This patch is able to avoid this situation and the call to memcpy(). At the same time,

Re: [PATCH] mm/vmscan.c: avoid recording the original scan targets in shrink_lruvec()

2014-06-10 Thread Chen Yucong
On Tue, 2014-06-10 at 16:33 -0700, Andrew Morton wrote: On Mon, 9 Jun 2014 21:27:16 +0800 Chen Yucong sla...@gmail.com wrote: Via https://lkml.org/lkml/2013/4/10/334 , we can find that recording the original scan targets introduces extra 40 bytes on the stack. This patch is able to avoid

Re: [PATCH] mm/vmscan.c: avoid recording the original scan targets in shrink_lruvec()

2014-06-10 Thread Chen Yucong
On Tue, 2014-06-10 at 16:33 -0700, Andrew Morton wrote: break; if (nr_file nr_anon) { - unsigned long scan_target = targets[LRU_INACTIVE_ANON] + - targets[LRU_ACTIVE_ANON] + 1; +

Re: [PATCH] mm/vmscan.c: avoid recording the original scan targets in shrink_lruvec()

2014-06-09 Thread Minchan Kim
On Tue, Jun 10, 2014 at 08:10:51AM +0800, Chen Yucong wrote: > On Tue, 2014-06-10 at 08:24 +0900, Minchan Kim wrote: > > Hello, > > > > On Mon, Jun 09, 2014 at 09:27:16PM +0800, Chen Yucong wrote: > > > Via https://lkml.org/lkml/2013/4/10/334 , we can find that recording the > > > original scan

Re: [PATCH] mm/vmscan.c: avoid recording the original scan targets in shrink_lruvec()

2014-06-09 Thread Chen Yucong
On Tue, 2014-06-10 at 08:24 +0900, Minchan Kim wrote: > Hello, > > On Mon, Jun 09, 2014 at 09:27:16PM +0800, Chen Yucong wrote: > > Via https://lkml.org/lkml/2013/4/10/334 , we can find that recording the > > original scan targets introduces extra 40 bytes on the stack. This patch > > is able to

Re: [PATCH] mm/vmscan.c: avoid recording the original scan targets in shrink_lruvec()

2014-06-09 Thread Minchan Kim
Hello, On Mon, Jun 09, 2014 at 09:27:16PM +0800, Chen Yucong wrote: > Via https://lkml.org/lkml/2013/4/10/334 , we can find that recording the > original scan targets introduces extra 40 bytes on the stack. This patch > is able to avoid this situation and the call to memcpy(). At the same time, >

Re: [PATCH] mm/vmscan.c: avoid recording the original scan targets in shrink_lruvec()

2014-06-09 Thread Minchan Kim
Hello, On Mon, Jun 09, 2014 at 09:27:16PM +0800, Chen Yucong wrote: Via https://lkml.org/lkml/2013/4/10/334 , we can find that recording the original scan targets introduces extra 40 bytes on the stack. This patch is able to avoid this situation and the call to memcpy(). At the same time, it

Re: [PATCH] mm/vmscan.c: avoid recording the original scan targets in shrink_lruvec()

2014-06-09 Thread Chen Yucong
On Tue, 2014-06-10 at 08:24 +0900, Minchan Kim wrote: Hello, On Mon, Jun 09, 2014 at 09:27:16PM +0800, Chen Yucong wrote: Via https://lkml.org/lkml/2013/4/10/334 , we can find that recording the original scan targets introduces extra 40 bytes on the stack. This patch is able to avoid

Re: [PATCH] mm/vmscan.c: avoid recording the original scan targets in shrink_lruvec()

2014-06-09 Thread Minchan Kim
On Tue, Jun 10, 2014 at 08:10:51AM +0800, Chen Yucong wrote: On Tue, 2014-06-10 at 08:24 +0900, Minchan Kim wrote: Hello, On Mon, Jun 09, 2014 at 09:27:16PM +0800, Chen Yucong wrote: Via https://lkml.org/lkml/2013/4/10/334 , we can find that recording the original scan targets