advantage of using unsigned either and limiting it to INT_MAX either.
It's not a big deal.
--
Mel Gorman
SUSE Labs
--
To unsubscribe from this list: send the line unsubscribe linux-media in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo
frame_vector_to_pages(struct frame_vector *vec)
+{
I think it's probably best to make the relevant counters in frame_vector
signed and limit the maximum possible size of it. It's still not putting
any practical limit on the size of the frame_vector.
--
Mel Gorman
SUSE Labs
--
To unsubscribe from
*
--
2.1.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majord...@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: a href=mailto:d...@kvack.org; em...@kvack.org /a
--
Mel Gorman
SUSE Labs
--
To unsubscribe from this list
. Use the helper to get right of this ifdef CONFIG_CMA within
setup_per_zone_wmarks().
You'll still have the problem of kswapd not taking CMA pages properly into
account when deciding whether to reclaim or not though.
--
Mel Gorman
SUSE Labs
--
To unsubscribe from this list: send the line
:29 +0100, Mel Gorman m...@csn.ul.ie wrote:
I'm not quite seeing this. In free_hot_cold_page(), the pageblock
type is checked so the page private should be set to MIGRATE_CMA or
MIGRATE_ISOLATE for the CMA area. It's not clear how this can change a
pageblock to MIGRATE_MOVABLE in error.
Here's
places.
Signed-off-by: Michal Nazarewicz min...@mina86.com
Signed-off-by: Marek Szyprowski m.szyprow...@samsung.com
Acked-by: Mel Gorman m...@csn.ul.ie
--
Mel Gorman
SUSE Labs
--
To unsubscribe from this list: send the line unsubscribe linux-media in
the body of a message to majord
comments that can be handled as a follow-up but otherwise
Acked-by: Mel Gorman m...@csn.ul.ie
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 238fcec..993c375 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -750,6 +750,26 @@ void __meminit __free_pages_bootmem(struct page *page
and the machine hangs.
The damage is confined to CMA though so I am not going to lose sleep
over it but you might want to consider at least preventing parallel
updates to min_free_kbytes from proc.
--
Mel Gorman
SUSE Labs
--
To unsubscribe from this list: send the line unsubscribe linux-media
On Fri, Feb 03, 2012 at 01:18:43PM +0100, Marek Szyprowski wrote:
Welcome everyone again!
This is yet another quick update on Contiguous Memory Allocator patches.
This version includes another set of code cleanups requested by Mel
Gorman and a few minor bug fixes. I really hope
that it is not forgotten.
--
Mel Gorman
SUSE Labs
--
To unsubscribe from this list: send the line unsubscribe linux-media in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
with git blame but as it is comments that are affected;
Acked-by: Mel Gorman m...@csn.ul.ie
Thanks
--
Mel Gorman
SUSE Labs
--
To unsubscribe from this list: send the line unsubscribe linux-media in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org
to avoid a
storm of IPIs.
+ } else {
+ ++pfn;
+ }
+ }
+}
--
Mel Gorman
SUSE Labs
--
To unsubscribe from this list: send the line unsubscribe linux-media in
the body of a message to majord...@vger.kernel.org
More majordomo info at http
-by: Mel Gorman m...@csn.ul.ie
@@ -313,7 +316,7 @@ static isolate_migrate_t isolate_migratepages(struct zone
*zone,
} else if (!locked)
spin_lock_irq(zone-lru_lock);
- if (!pfn_valid_within(low_pfn))
+ if (!pfn_valid(low_pfn
;
+ }
+
+ /* We don't use freelists for anything. */
+ return pfn;
+}
+
/* Returns true if the page is within a block suitable for migration to */
static bool suitable_migration_target(struct page *page)
{
--
Mel Gorman
SUSE Labs
--
To unsubscribe from this list: send
On Mon, Jan 30, 2012 at 11:48:20AM +, Mel Gorman wrote:
+ if (!zone)
+ zone = page_zone(pfn_to_page(pfn));
+ else if (zone != page_zone(pfn_to_page(pfn)))
+ break;
+
So what you are checking for here is if you straddle zones
it. The only time this really matters is when it breaks
bisection but I do not think that is the case here.
Whether you fix this or not by moving the CONFIG_CMA check to the same
patch that declares it in Kconfig
Acked-by: Mel Gorman m...@csn.ul.ie
--
Mel Gorman
SUSE Labs
--
To unsubscribe from
or horrible jumped out
at me other than the page_isolation.h thing and that could be argued
either way so;
Acked-by: Mel Gorman m...@csn.ul.ie
/*
#ifdef CONFIG_MEMORY_HOTREMOVE
/*
* All pages in the range must be isolated before calling this.
--
Mel Gorman
SUSE Labs
--
To unsubscribe from
marker. The letter change,
removes the implicit MIGRATE_UNMOVABLE from the end of each row which
was read by __rmqueue_fallback() function.
Signed-off-by: Michal Nazarewicz min...@mina86.com
Signed-off-by: Marek Szyprowski m.szyprow...@samsung.com
Acked-by: Mel Gorman m...@csn.ul.ie
--
Mel
,
Reserve,
+#ifdef CONFIG_CMA
+ CMA,
+#endif
Isolate,
};
--
1.7.1.569.g6f426
--
Mel Gorman
SUSE Labs
--
To unsubscribe from this list: send the line unsubscribe linux-media in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org
inline int
+__perform_reclaim(gfp_t gfp_mask, unsigned int order, struct zonelist
*zonelist,
+ nodemask_t *nodemask)
This function is too large to be inlined. Make it a static int. Once
that is fixed add a
Acked-by: Mel Gorman m...@csn.ul.ie
--
Mel Gorman
SUSE Labs
--
To unsubscribe
problem 3 as it
is, I would really like to see a comment explaning the problem for
future users of CMA on other arches (if they exist).
--
Mel Gorman
SUSE Labs
--
To unsubscribe from this list: send the line unsubscribe linux-media in
the body of a message to majord...@vger.kernel.org
More
Allocator patches. This version mainly includes code cleanups requested
by Mel Gorman and a few minor bug fixes.
Hi Marek,
Thanks for keeping up this work! I really hope it works out for the
next merge window.
Someone please tell me when it's time to start paying attention
again
)
spin_lock_irq(zone-lru_lock);
- if (!pfn_valid_within(low_pfn))
+ if (!pfn_valid(low_pfn))
continue;
nr_scanned++;
On Mon, 30 Jan 2012 12:24:28 +0100, Mel Gorman m...@csn.ul.ie wrote:
This chunk looks unrelated
unmovable pages in MIGRATE_CMA regions. This might have been part of
the problem.
--
Mel Gorman
SUSE Labs
--
To unsubscribe from this list: send the line unsubscribe linux-media in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
On Mon, Jan 30, 2012 at 04:41:22PM +0100, Michal Nazarewicz wrote:
On Mon, 30 Jan 2012 12:15:22 +0100, Mel Gorman m...@csn.ul.ie wrote:
On Thu, Jan 26, 2012 at 10:00:44AM +0100, Marek Szyprowski wrote:
From: Michal Nazarewicz min...@mina86.com
@@ -139,3 +139,27 @@ int test_pages_isolated
();
+ drain_all_pages();
+ if (WARN_ON(test_pages_isolated(start, end)))
+ ret = -EBUSY;
+ }
On Tue, 10 Jan 2012 15:16:13 +0100, Mel Gorman m...@csn.ul.ie wrote:
Another global IPI seems overkill. Drain pages only from the local CPU
(drain_pages(get_cpu()); put_cpu()) and test
;
+}
+
+void free_contig_range(unsigned long pfn, unsigned nr_pages)
+{
+ for (; nr_pages--; ++pfn)
+ __free_page(pfn_to_page(pfn));
+}
+
#ifdef CONFIG_MEMORY_HOTREMOVE
/*
* All pages in the range must be isolated before calling this.
--
1.7.1.569.g6f426
--
Mel Gorman
,
Movable,
Reserve,
+ Cma,
Isolate,
};
--
1.7.1.569.g6f426
--
Mel Gorman
SUSE Labs
--
To unsubscribe from this list: send the line unsubscribe linux-media in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
helper functions.
--
Mel Gorman
SUSE Labs
--
To unsubscribe from this list: send the line unsubscribe linux-media in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
set pageblocks MIGRATE_ISOLATE. The IPIs also have overhead but it
will be incurred for the rare rather than the common case.
--
Mel Gorman
SUSE Labs
--
To unsubscribe from this list: send the line unsubscribe linux-media in
the body of a message to majord...@vger.kernel.org
More majordomo info
--
Mel Gorman
SUSE Labs
--
To unsubscribe from this list: send the line unsubscribe linux-media in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
:19:53 +0100, Mel Gorman m...@csn.ul.ie wrote:
Is this necessary?
We are isolating pages, the largest of which is a MAX_ORDER_NR_PAGES
page. [...]
This is not true for CMA.
To be clear, I'm referring to a single page being isolated here. It may
or may not be a high-order page but it's
2011 14:42:35 +0100, Mel Gorman m...@csn.ul.ie wrote:
How much of a problem is this in practice?
IIRC, this lead to allocation being made from area marked as isolated
or some such.
And I believe that nothing prevents that from happening. I was just
wondering how common it was in practice
On Mon, Dec 12, 2011 at 03:41:04PM +0100, Michal Nazarewicz wrote:
On Mon, 12 Dec 2011 15:29:07 +0100, Mel Gorman m...@csn.ul.ie wrote:
On Fri, Nov 18, 2011 at 05:43:11PM +0100, Marek Szyprowski wrote:
From: Michal Nazarewicz min...@mina86.com
This commit exports some of the functions from
:19:53 +0100, Mel Gorman m...@csn.ul.ie wrote:
Is this necessary?
We are isolating pages, the largest of which is a MAX_ORDER_NR_PAGES
page. [...]
On Mon, 12 Dec 2011 15:40:30 +0100, Mel Gorman m...@csn.ul.ie wrote:
To be clear, I'm referring to a single page being isolated here. It may
to provide a freelist and then validate if pages on it are
added in order).
Please do and double check that __free_page logic too.
--
Mel Gorman
SUSE Labs
--
To unsubscribe from this list: send the line unsubscribe linux-media in
the body of a message to majord...@vger.kernel.org
More majordomo
On Mon, Dec 12, 2011 at 05:46:13PM +0100, Michal Nazarewicz wrote:
On Mon, 12 Dec 2011 17:30:52 +0100, Mel Gorman m...@csn.ul.ie wrote:
On Mon, Dec 12, 2011 at 04:22:39PM +0100, Michal Nazarewicz wrote:
SNIP
+ if (!pfn_valid_within(pfn))
+ goto skip;
The flow
that all pages in range
are in buddy system.
On Tue, 18 Oct 2011 05:21:09 -0700, Mel Gorman m...@csn.ul.ie wrote:
Straight away, I'm wondering why you didn't use
mm/compaction.c#isolate_freepages()
Does the below look like a step in the right direction?
It basically moves
the idea of making it static and removing from
header file.
I see no problem with that. It'll be separate from split_page() but that
is not earth shattering.
Thanks.
--
Mel Gorman
SUSE Labs
--
To unsubscribe from this list: send the line unsubscribe linux-media in
the body of a message to majord
On Tue, Oct 18, 2011 at 10:26:37AM -0700, Michal Nazarewicz wrote:
On Tue, 18 Oct 2011 05:21:09 -0700, Mel Gorman m...@csn.ul.ie wrote:
At this point, I'm going to apologise for not reviewing this a long long
time ago.
On Thu, Oct 06, 2011 at 03:54:42PM +0200, Marek Szyprowski wrote:
From
on memory hotplug.
--
Mel Gorman
SUSE Labs
--
To unsubscribe from this list: send the line unsubscribe linux-media in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
At this point, I'm going to apologise for not reviewing this a long long
time ago.
On Thu, Oct 06, 2011 at 03:54:42PM +0200, Marek Szyprowski wrote:
From: KAMEZAWA Hiroyuki kamezawa.hir...@jp.fujitsu.com
This commit introduces alloc_contig_freed_pages() function
which allocates (ie. removes
On Thu, Oct 06, 2011 at 03:54:43PM +0200, Marek Szyprowski wrote:
From: Michal Nazarewicz m.nazarew...@samsung.com
This commit adds the alloc_contig_range() function which tries
to allocate given range of pages. It tries to migrate all
already allocated pages that fall in the range thus
On Thu, Oct 06, 2011 at 03:54:44PM +0200, Marek Szyprowski wrote:
From: Michal Nazarewicz m.nazarew...@samsung.com
The MIGRATE_CMA migration type has two main characteristics:
(i) only movable pages can be allocated from MIGRATE_CMA
pageblocks and (ii) page allocator will never change
On Thu, Oct 06, 2011 at 03:54:46PM +0200, Marek Szyprowski wrote:
The Contiguous Memory Allocator is a set of helper functions for DMA
mapping framework that improves allocations of contiguous memory chunks.
CMA grabs memory on system boot, marks it with CMA_MIGRATE_TYPE and
gives back to
of memory in a zone unusable by non-movable
allocationos. It would be a lot trickier when interacting with reclaim
though so using ZONE_MOVABLE would have less gotchas.
--
Mel Gorman
Part-time Phd Student Linux Technology Center
University of Limerick IBM
...@kvack.org; em...@kvack.org /a
--
Mel Gorman
Part-time Phd Student Linux Technology Center
University of Limerick IBM Dublin Software Lab
--
To unsubscribe from this list: send the line unsubscribe linux-media in
the body of a message to majord
47 matches
Mail list logo