On Thu, Aug 15, 2013 at 02:42:09PM +0100, Mel Gorman wrote:
> On Thu, Aug 15, 2013 at 10:19:35PM +0900, Minchan Kim wrote:
> > >
> > > Why? We're looking for pages to migrate. If the page is free and at the
> > > maximum order then there is no point searching in the middle of a free
> > > page.
>
On Thu, Aug 15, 2013 at 10:19:35PM +0900, Minchan Kim wrote:
> >
> > Why? We're looking for pages to migrate. If the page is free and at the
> > maximum order then there is no point searching in the middle of a free
> > page.
>
> isolate_migratepages_range API works with [low_pfn, end_pfn)
> and
Hi Mel,
On Thu, Aug 15, 2013 at 12:30:19PM +0100, Mel Gorman wrote:
> On Thu, Aug 15, 2013 at 01:17:55PM +0900, Minchan Kim wrote:
> > Hello,
> >
>
> Well, this thread managed to get out of control for no good reason!
>
> > > >
> > > > So, what's the result by that?
> > > > As I said, it's
On Thu, Aug 15, 2013 at 01:17:55PM +0900, Minchan Kim wrote:
> Hello,
>
Well, this thread managed to get out of control for no good reason!
> > >
> > > So, what's the result by that?
> > > As I said, it's just skipping (pageblock_nr_pages -1) at worst case
> >
> > Hi Minchan,
> > I mean if
On 2013/8/15 17:51, Wanpeng Li wrote:
> On Thu, Aug 15, 2013 at 03:45:11PM +0800, Xishi Qiu wrote:
>> On 2013/8/15 12:24, Minchan Kim wrote:
>>
Please read full thread in detail.
Mel suggested following as
if (PageBuddy(page)) {
int nr_pages = (1 <<
On 2013/8/15 17:51, Wanpeng Li wrote:
> On Thu, Aug 15, 2013 at 03:45:11PM +0800, Xishi Qiu wrote:
>> On 2013/8/15 12:24, Minchan Kim wrote:
>>
Please read full thread in detail.
Mel suggested following as
if (PageBuddy(page)) {
int nr_pages = (1 <<
On 2013/8/15 12:24, Minchan Kim wrote:
>> Please read full thread in detail.
>>
>> Mel suggested following as
>>
>> if (PageBuddy(page)) {
>> int nr_pages = (1 << page_order(page)) - 1;
>> if (PageBuddy(page)) {
>> nr_pages = min(nr_pages, MAX_ORDER_NR_PAGES - 1);
On 2013/8/15 12:17, Minchan Kim wrote:
>
> Please read full thread in detail.
>
> Mel suggested following as
>
> if (PageBuddy(page)) {
> int nr_pages = (1 << page_order(page)) - 1;
> if (PageBuddy(page)) {
> nr_pages = min(nr_pages, MAX_ORDER_NR_PAGES - 1);
>
On 2013/8/15 12:17, Minchan Kim wrote:
Please read full thread in detail.
Mel suggested following as
if (PageBuddy(page)) {
int nr_pages = (1 page_order(page)) - 1;
if (PageBuddy(page)) {
nr_pages = min(nr_pages, MAX_ORDER_NR_PAGES - 1);
On 2013/8/15 12:24, Minchan Kim wrote:
Please read full thread in detail.
Mel suggested following as
if (PageBuddy(page)) {
int nr_pages = (1 page_order(page)) - 1;
if (PageBuddy(page)) {
nr_pages = min(nr_pages, MAX_ORDER_NR_PAGES - 1);
On 2013/8/15 17:51, Wanpeng Li wrote:
On Thu, Aug 15, 2013 at 03:45:11PM +0800, Xishi Qiu wrote:
On 2013/8/15 12:24, Minchan Kim wrote:
Please read full thread in detail.
Mel suggested following as
if (PageBuddy(page)) {
int nr_pages = (1 page_order(page)) - 1;
if
On 2013/8/15 17:51, Wanpeng Li wrote:
On Thu, Aug 15, 2013 at 03:45:11PM +0800, Xishi Qiu wrote:
On 2013/8/15 12:24, Minchan Kim wrote:
Please read full thread in detail.
Mel suggested following as
if (PageBuddy(page)) {
int nr_pages = (1 page_order(page)) - 1;
if
On Thu, Aug 15, 2013 at 01:17:55PM +0900, Minchan Kim wrote:
Hello,
Well, this thread managed to get out of control for no good reason!
SNIP
So, what's the result by that?
As I said, it's just skipping (pageblock_nr_pages -1) at worst case
Hi Minchan,
I mean if the private is
Hi Mel,
On Thu, Aug 15, 2013 at 12:30:19PM +0100, Mel Gorman wrote:
On Thu, Aug 15, 2013 at 01:17:55PM +0900, Minchan Kim wrote:
Hello,
Well, this thread managed to get out of control for no good reason!
SNIP
So, what's the result by that?
As I said, it's just skipping
On Thu, Aug 15, 2013 at 10:19:35PM +0900, Minchan Kim wrote:
Why? We're looking for pages to migrate. If the page is free and at the
maximum order then there is no point searching in the middle of a free
page.
isolate_migratepages_range API works with [low_pfn, end_pfn)
and we can't
On Thu, Aug 15, 2013 at 02:42:09PM +0100, Mel Gorman wrote:
On Thu, Aug 15, 2013 at 10:19:35PM +0900, Minchan Kim wrote:
Why? We're looking for pages to migrate. If the page is free and at the
maximum order then there is no point searching in the middle of a free
page.
On Thu, Aug 15, 2013 at 01:17:55PM +0900, Minchan Kim wrote:
> Hello,
>
> On Thu, Aug 15, 2013 at 11:46:07AM +0800, Xishi Qiu wrote:
> > On 2013/8/15 10:44, Minchan Kim wrote:
> >
> > > Hi Xishi,
> > >
> > > On Thu, Aug 15, 2013 at 10:32:50AM +0800, Xishi Qiu wrote:
> > >> On 2013/8/15 2:00,
Hello,
On Thu, Aug 15, 2013 at 11:46:07AM +0800, Xishi Qiu wrote:
> On 2013/8/15 10:44, Minchan Kim wrote:
>
> > Hi Xishi,
> >
> > On Thu, Aug 15, 2013 at 10:32:50AM +0800, Xishi Qiu wrote:
> >> On 2013/8/15 2:00, Mel Gorman wrote:
> >>
> > Even if the page is still page buddy, there is no
On 2013/8/15 10:44, Minchan Kim wrote:
> Hi Xishi,
>
> On Thu, Aug 15, 2013 at 10:32:50AM +0800, Xishi Qiu wrote:
>> On 2013/8/15 2:00, Mel Gorman wrote:
>>
> Even if the page is still page buddy, there is no guarantee that it's
> the same page order as the first read. It could have be
Hi Xishi,
On Thu, Aug 15, 2013 at 10:32:50AM +0800, Xishi Qiu wrote:
> On 2013/8/15 2:00, Mel Gorman wrote:
>
> >>> Even if the page is still page buddy, there is no guarantee that it's
> >>> the same page order as the first read. It could have be currently
> >>> merging with adjacent buddies
On 2013/8/15 2:00, Mel Gorman wrote:
>>> Even if the page is still page buddy, there is no guarantee that it's
>>> the same page order as the first read. It could have be currently
>>> merging with adjacent buddies for example. There is also a really
>>> small race that a page was freed,
On Wed, Aug 14, 2013 at 01:26:02PM -0700, Andrew Morton wrote:
> On Thu, 15 Aug 2013 00:52:29 +0900 Minchan Kim wrote:
>
> > On Wed, Aug 14, 2013 at 09:57:11AM +0100, Mel Gorman wrote:
> > > On Wed, Aug 14, 2013 at 12:45:41PM +0800, Xishi Qiu wrote:
> > > > A large free page buddy block will
On Thu, 15 Aug 2013 00:52:29 +0900 Minchan Kim wrote:
> On Wed, Aug 14, 2013 at 09:57:11AM +0100, Mel Gorman wrote:
> > On Wed, Aug 14, 2013 at 12:45:41PM +0800, Xishi Qiu wrote:
> > > A large free page buddy block will continue many times, so if the page
> > > is free, skip the whole page
On Wed, Aug 14, 2013 at 07:00:12PM +0100, Mel Gorman wrote:
> On Thu, Aug 15, 2013 at 01:39:21AM +0900, Minchan Kim wrote:
> > On Wed, Aug 14, 2013 at 05:16:42PM +0100, Mel Gorman wrote:
> > > On Thu, Aug 15, 2013 at 12:52:29AM +0900, Minchan Kim wrote:
> > > > Hi Mel,
> > > >
> > > > On Wed, Aug
On Thu, Aug 15, 2013 at 01:39:21AM +0900, Minchan Kim wrote:
> On Wed, Aug 14, 2013 at 05:16:42PM +0100, Mel Gorman wrote:
> > On Thu, Aug 15, 2013 at 12:52:29AM +0900, Minchan Kim wrote:
> > > Hi Mel,
> > >
> > > On Wed, Aug 14, 2013 at 09:57:11AM +0100, Mel Gorman wrote:
> > > > On Wed, Aug 14,
On Wed, Aug 14, 2013 at 05:16:42PM +0100, Mel Gorman wrote:
> On Thu, Aug 15, 2013 at 12:52:29AM +0900, Minchan Kim wrote:
> > Hi Mel,
> >
> > On Wed, Aug 14, 2013 at 09:57:11AM +0100, Mel Gorman wrote:
> > > On Wed, Aug 14, 2013 at 12:45:41PM +0800, Xishi Qiu wrote:
> > > > A large free page
On Thu, Aug 15, 2013 at 12:52:29AM +0900, Minchan Kim wrote:
> Hi Mel,
>
> On Wed, Aug 14, 2013 at 09:57:11AM +0100, Mel Gorman wrote:
> > On Wed, Aug 14, 2013 at 12:45:41PM +0800, Xishi Qiu wrote:
> > > A large free page buddy block will continue many times, so if the page
> > > is free, skip
Hi Mel,
On Wed, Aug 14, 2013 at 09:57:11AM +0100, Mel Gorman wrote:
> On Wed, Aug 14, 2013 at 12:45:41PM +0800, Xishi Qiu wrote:
> > A large free page buddy block will continue many times, so if the page
> > is free, skip the whole page buddy block instead of one page.
> >
> > Signed-off-by:
On 2013/8/14 16:57, Mel Gorman wrote:
> On Wed, Aug 14, 2013 at 12:45:41PM +0800, Xishi Qiu wrote:
>> A large free page buddy block will continue many times, so if the page
>> is free, skip the whole page buddy block instead of one page.
>>
>> Signed-off-by: Xishi Qiu
>
> page_order cannot be
On Wed, Aug 14, 2013 at 12:45:41PM +0800, Xishi Qiu wrote:
> A large free page buddy block will continue many times, so if the page
> is free, skip the whole page buddy block instead of one page.
>
> Signed-off-by: Xishi Qiu
page_order cannot be used unless zone->lock is held which is not held
Hello,
On Wed, Aug 14, 2013 at 12:45:41PM +0800, Xishi Qiu wrote:
> A large free page buddy block will continue many times, so if the page
> is free, skip the whole page buddy block instead of one page.
>
> Signed-off-by: Xishi Qiu
Nitpick is it could change nr_scanned's result so that
Hello,
On Wed, Aug 14, 2013 at 12:45:41PM +0800, Xishi Qiu wrote:
A large free page buddy block will continue many times, so if the page
is free, skip the whole page buddy block instead of one page.
Signed-off-by: Xishi Qiu qiuxi...@huawei.com
Nitpick is it could change nr_scanned's
On Wed, Aug 14, 2013 at 12:45:41PM +0800, Xishi Qiu wrote:
A large free page buddy block will continue many times, so if the page
is free, skip the whole page buddy block instead of one page.
Signed-off-by: Xishi Qiu qiuxi...@huawei.com
page_order cannot be used unless zone-lock is held
On 2013/8/14 16:57, Mel Gorman wrote:
On Wed, Aug 14, 2013 at 12:45:41PM +0800, Xishi Qiu wrote:
A large free page buddy block will continue many times, so if the page
is free, skip the whole page buddy block instead of one page.
Signed-off-by: Xishi Qiu qiuxi...@huawei.com
page_order
Hi Mel,
On Wed, Aug 14, 2013 at 09:57:11AM +0100, Mel Gorman wrote:
On Wed, Aug 14, 2013 at 12:45:41PM +0800, Xishi Qiu wrote:
A large free page buddy block will continue many times, so if the page
is free, skip the whole page buddy block instead of one page.
Signed-off-by: Xishi Qiu
On Thu, Aug 15, 2013 at 12:52:29AM +0900, Minchan Kim wrote:
Hi Mel,
On Wed, Aug 14, 2013 at 09:57:11AM +0100, Mel Gorman wrote:
On Wed, Aug 14, 2013 at 12:45:41PM +0800, Xishi Qiu wrote:
A large free page buddy block will continue many times, so if the page
is free, skip the whole
On Wed, Aug 14, 2013 at 05:16:42PM +0100, Mel Gorman wrote:
On Thu, Aug 15, 2013 at 12:52:29AM +0900, Minchan Kim wrote:
Hi Mel,
On Wed, Aug 14, 2013 at 09:57:11AM +0100, Mel Gorman wrote:
On Wed, Aug 14, 2013 at 12:45:41PM +0800, Xishi Qiu wrote:
A large free page buddy block will
On Thu, Aug 15, 2013 at 01:39:21AM +0900, Minchan Kim wrote:
On Wed, Aug 14, 2013 at 05:16:42PM +0100, Mel Gorman wrote:
On Thu, Aug 15, 2013 at 12:52:29AM +0900, Minchan Kim wrote:
Hi Mel,
On Wed, Aug 14, 2013 at 09:57:11AM +0100, Mel Gorman wrote:
On Wed, Aug 14, 2013 at
On Wed, Aug 14, 2013 at 07:00:12PM +0100, Mel Gorman wrote:
On Thu, Aug 15, 2013 at 01:39:21AM +0900, Minchan Kim wrote:
On Wed, Aug 14, 2013 at 05:16:42PM +0100, Mel Gorman wrote:
On Thu, Aug 15, 2013 at 12:52:29AM +0900, Minchan Kim wrote:
Hi Mel,
On Wed, Aug 14, 2013 at
On Thu, 15 Aug 2013 00:52:29 +0900 Minchan Kim minc...@kernel.org wrote:
On Wed, Aug 14, 2013 at 09:57:11AM +0100, Mel Gorman wrote:
On Wed, Aug 14, 2013 at 12:45:41PM +0800, Xishi Qiu wrote:
A large free page buddy block will continue many times, so if the page
is free, skip the whole
On Wed, Aug 14, 2013 at 01:26:02PM -0700, Andrew Morton wrote:
On Thu, 15 Aug 2013 00:52:29 +0900 Minchan Kim minc...@kernel.org wrote:
On Wed, Aug 14, 2013 at 09:57:11AM +0100, Mel Gorman wrote:
On Wed, Aug 14, 2013 at 12:45:41PM +0800, Xishi Qiu wrote:
A large free page buddy block
On 2013/8/15 2:00, Mel Gorman wrote:
Even if the page is still page buddy, there is no guarantee that it's
the same page order as the first read. It could have be currently
merging with adjacent buddies for example. There is also a really
small race that a page was freed, allocated with some
Hi Xishi,
On Thu, Aug 15, 2013 at 10:32:50AM +0800, Xishi Qiu wrote:
On 2013/8/15 2:00, Mel Gorman wrote:
Even if the page is still page buddy, there is no guarantee that it's
the same page order as the first read. It could have be currently
merging with adjacent buddies for example.
On 2013/8/15 10:44, Minchan Kim wrote:
Hi Xishi,
On Thu, Aug 15, 2013 at 10:32:50AM +0800, Xishi Qiu wrote:
On 2013/8/15 2:00, Mel Gorman wrote:
Even if the page is still page buddy, there is no guarantee that it's
the same page order as the first read. It could have be currently
merging
Hello,
On Thu, Aug 15, 2013 at 11:46:07AM +0800, Xishi Qiu wrote:
On 2013/8/15 10:44, Minchan Kim wrote:
Hi Xishi,
On Thu, Aug 15, 2013 at 10:32:50AM +0800, Xishi Qiu wrote:
On 2013/8/15 2:00, Mel Gorman wrote:
Even if the page is still page buddy, there is no guarantee that it's
On Thu, Aug 15, 2013 at 01:17:55PM +0900, Minchan Kim wrote:
Hello,
On Thu, Aug 15, 2013 at 11:46:07AM +0800, Xishi Qiu wrote:
On 2013/8/15 10:44, Minchan Kim wrote:
Hi Xishi,
On Thu, Aug 15, 2013 at 10:32:50AM +0800, Xishi Qiu wrote:
On 2013/8/15 2:00, Mel Gorman wrote:
A large free page buddy block will continue many times, so if the page
is free, skip the whole page buddy block instead of one page.
Signed-off-by: Xishi Qiu
---
mm/compaction.c |5 +++--
1 files changed, 3 insertions(+), 2 deletions(-)
diff --git a/mm/compaction.c b/mm/compaction.c
index
A large free page buddy block will continue many times, so if the page
is free, skip the whole page buddy block instead of one page.
Signed-off-by: Xishi Qiu qiuxi...@huawei.com
---
mm/compaction.c |5 +++--
1 files changed, 3 insertions(+), 2 deletions(-)
diff --git a/mm/compaction.c
48 matches
Mail list logo
