Hi, this is per-zone/reclaim support patch set for memory controller (cgroup).
Major changes from previous one is

 -- tested with 2.6.24-rc3-mm1 + ia64/NUMA

 -- applied comments.
I did small test on real NUMA machine.

My machine was ia64/8CPU/2Node NUMA. I tried to complile the kernel under 800M

bytes limit with 32 parallel make. (make -j 32)
 - 2.6.24-rc3-mm1 (+ scsi fix) .... shows soft lock-up.

   before soft lock-up, %sys was almost 100% in several times.
 - 2.6.24-rc3-mm1 (+ scsi fix) + this set .... completed succesfully

   It seems %iowait dominates the total performance.

   (current memory controller has no background reclaim)
Seems this set give us some progress.
(*) I'd like to merge YAMAMOTO-san's background page reclaim for memory

    controller before discussing about the number of performance.
Andrew, could you pick these up to -mm ?
Patch series brief description:
[1/10] ... add scan_global_lru() macro  (clean up)

[2/10] ... nid/zid helper function for cgroup

[3/10] ... introduce per-zone object for memory controller and add

           active/inactive counter.

[4/10] ... calculate mapper_ratio per cgroup (for memory reclaim)

[5/10] ... calculate active/inactive imbalance per cgroup (based on [3])

[6/10] ... remember reclaim priority in memory controller

[7/10] ... calculate the number of pages to be reclaimed per cgroup
[8/10] ... modifies vmscan.c to isolate global-lru-reclaim and

           memory-cgroup-reclaim in obvious manner.

           (this patch uses functions defined in [4 - 7])

[9/10] ... implement per-zone-lru for cgroup (based on [3])

[10/10] ... implement per-zone lru lock for cgroup (based on [3][9])
Any comments are welcome.
Thanks,

-Kame
-

Now, lru is per-zone.
Then, lru_lock can be (should be) per-zone, too.

This patch implementes per-zone lru lock.
lru_lock is placed into mem_cgroup_per_zone struct.
lock can be accessed by

   mz = mem_cgroup_zoneinfo(mem_cgroup, node, zone);

   &mz->lru_lock
   or

   mz = page_cgroup_zoneinfo(page_cgroup);

   &mz->lru_lock
Signed-off-by: KAMEZAWA hiroyuki <kmaezawa.hiroyu@jp.fujitsu.com>
 mm/memcontrol.c |   71 ++++++++++++++++++++++++++++++++++----------------------

 1 file changed, 44 insertions(+), 27 deletions(-)
Index: linux-2.6.24-rc3-mm1/mm/memcontrol.c

===================================================================

--- linux-2.6.24-rc3-mm1.orig/mm/memcontrol.c	2007-11-27 11:24:16.000000000 +0900

+++ linux-2.6.24-rc3-mm1/mm/memcontrol.c	2007-11-27 11:24:22.000000000 +0900

@@ -89,6 +89,10 @@

 };
 struct mem_cgroup_per_zone {

+	/*

+	 * spin_lock to protect the per cgroup LRU

+	 */

+	spinlock_t		lru_lock;

 	struct list_head	active_list;

 	struct list_head	inactive_list;

 	unsigned long count[NR_MEM_CGROUP_ZSTAT];

@@ -126,10 +130,7 @@

 	 * per zone LRU lists.

 	 */

 	struct mem_cgroup_lru_info info;

-	/*

-	 * spin_lock to protect the per cgroup LRU

-	 */

-	spinlock_t lru_lock;

+

 	unsigned long control_type;	/* control RSS or RSS+Pagecache */

 	int	prev_priority;	/* for recording reclaim priority */

 	/*

@@ -410,15 +411,16 @@

  */

 void mem_cgroup_move_lists(struct page_cgroup *pc, bool active)

 {

-	struct mem_cgroup *mem;

+	struct mem_cgroup_per_zone *mz;

+	unsigned long flags;

+

 	if (!pc)

 		return;
-	mem = pc->mem_cgroup;

-

-	spin_lock(&mem->lru_lock);

+	mz = page_cgroup_zoneinfo(pc);

+	spin_lock_irqsave(&mz->lru_lock, flags);

 	__mem_cgroup_move_lists(pc, active);

-	spin_unlock(&mem->lru_lock);

+	spin_unlock_irqrestore(&mz->lru_lock, flags);

 }
 /*

@@ -528,7 +530,7 @@

 		src = &mz->inactive_list;
-	spin_lock(&mem_cont->lru_lock);

+	spin_lock(&amp...
[ message continues ]

This patch implements per-zone lru for memory cgroup.

This patch makes use of mem_cgroup_per_zone struct for per zone lru.
LRU can be accessed by
   mz = mem_cgroup_zoneinfo(mem_cgroup, node, zone);

   &mz->active_list

   &mz->inactive_list
   or

   mz = page_cgroup_zoneinfo(page_cgroup);

   &mz->active_list

   &mz->inactive_list
Changelog v1->v2

  - merged to mem_cgroup_per_zone struct.

  - handle page migraiton.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
 mm/memcontrol.c |   63 ++++++++++++++++++++++++++++++++++----------------------

 1 file changed, 39 insertions(+), 24 deletions(-)
Index: linux-2.6.24-rc3-mm1/mm/memcontrol.c

===================================================================

--- linux-2.6.24-rc3-mm1.orig/mm/memcontrol.c	2007-11-27 11:24:04.000000000 +0900

+++ linux-2.6.24-rc3-mm1/mm/memcontrol.c	2007-11-27 11:24:16.000000000 +0900

@@ -89,6 +89,8 @@

 };
 struct mem_cgroup_per_zone {

+	struct list_head	active_list;

+	struct list_head	inactive_list;

 	unsigned long count[NR_MEM_CGROUP_ZSTAT];

 };

 /* Macro for accessing counter */

@@ -122,10 +124,7 @@

 	/*

 	 * Per cgroup active and inactive list, similar to the

 	 * per zone LRU lists.

-	 * TODO: Consider making these lists per zone

 	 */

-	struct list_head active_list;

-	struct list_head inactive_list;

 	struct mem_cgroup_lru_info info;

 	/*

 	 * spin_lock to protect the per cgroup LRU

@@ -367,10 +366,10 @@
 	if (!to) {

 		MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_INACTIVE) += 1;

-		list_add(&pc->lru, &pc->mem_cgroup->inactive_list);

+		list_add(&pc->lru, &mz->inactive_list);

 	} else {

 		MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_ACTIVE) += 1;

-		list_add(&pc->lru, &pc->mem_cgroup->active_list);

+		list_add(&pc->lru, &mz->active_list);

 	}

 	mem_cgroup_charge_statistics(pc->mem_cgroup, pc->flags, true);

 }

@@ -388,11 +387,11 @@

 	if (active) {

 		MEM_...
[ message continues ]

When using memory controller, there are 2 levels of memory reclaim.

 1. zone memory reclaim because of system/zone memory shortage.

 2. memory cgroup memory reclaim because of hitting limit.
These two can be distinguished by sc->mem_cgroup parameter.

(scan_global_lru() macro)
This patch tries to make memory cgroup reclaim routine avoid affecting

system/zone memory reclaim. This patch inserts if (scan_global_lru()) and

hook to memory_cgroup reclaim support functions.
This patch can be a help for isolating system lru activity and group lru

activity and shows what additional functions are necessary.
 * mem_cgroup_calc_mapped_ratio() ... calculate mapped ratio for cgroup.

 * mem_cgroup_reclaim_imbalance() ... calculate active/inactive balance in

                                        cgroup.

 * mem_cgroup_calc_reclaim_active() ... calculate the number of active pages to

                                be scanned in this priority in mem_cgroup.
 * mem_cgroup_calc_reclaim_inactive() ... calculate the number of inactive pages

                                to be scanned in this priority in mem_cgroup.
 * mem_cgroup_all_unreclaimable() .. checks cgroup's page is all unreclaimable

                                     or not.

 * mem_cgroup_get_reclaim_priority() ...

 * mem_cgroup_note_reclaim_priority() ... record reclaim priority (temporal)

 * mem_cgroup_remember_reclaim_priority()

                             .... record reclaim priority as

                                  zone->prev_priority.

                                  This value is used for calc reclaim_mapped.

Changelog V1->V2:

 - merged calc_reclaim_mapped patch in previous version.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
 mm/vmscan.c |  326 ++++++++++++++++++++++++++++++++++++------------------------

 1 file changed, 197 insertions(+), 129 deletions(-)
Index: linux-2.6.24-rc3-mm1/mm/vmscan.c

===================================================================

--- linu...
[ message continues ]

Define function for calculating the number of scan target on each Zone/LRU.
Changelog V1->V2.

 - fixed types of variable.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
 include/linux/memcontrol.h |   15 +++++++++++++++

 mm/memcontrol.c            |   33 +++++++++++++++++++++++++++++++++

 2 files changed, 48 insertions(+)
Index: linux-2.6.24-rc3-mm1/include/linux/memcontrol.h

===================================================================

--- linux-2.6.24-rc3-mm1.orig/include/linux/memcontrol.h	2007-11-27 11:22:14.000000000 +0900

+++ linux-2.6.24-rc3-mm1/include/linux/memcontrol.h	2007-11-27 11:22:51.000000000 +0900

@@ -73,6 +73,10 @@

 extern void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem,

 							int priority);
+extern long mem_cgroup_calc_reclaim_active(struct mem_cgroup *mem,

+				struct zone *zone, int priority);

+extern long mem_cgroup_calc_reclaim_inactive(struct mem_cgroup *mem,

+				struct zone *zone, int priority);
 #else /* CONFIG_CGROUP_MEM_CONT */

 static inline void mm_init_cgroup(struct mm_struct *mm,

@@ -173,6 +177,17 @@

 	return 0;

 }
+static inline long mem_cgroup_calc_reclaim_active(struct mem_cgroup *mem,

+					struct zone *zone, int priority)

+{

+	return 0;

+}

+

+static inline long mem_cgroup_calc_reclaim_inactive(struct mem_cgroup *mem,

+					struct zone *zone, int priority)

+{

+	return 0;

+}

 #endif /* CONFIG_CGROUP_MEM_CONT */
 #endif /* _LINUX_MEMCONTROL_H */

Index: linux-2.6.24-rc3-mm1/mm/memcontrol.c

===================================================================

--- linux-2.6.24-rc3-mm1.orig/mm/memcontrol.c	2007-11-27 11:22:14.000000000 +0900

+++ linux-2.6.24-rc3-mm1/mm/memcontrol.c	2007-11-27 11:24:04.000000000 +0900

@@ -472,6 +472,39 @@

 	mem->prev_priority = priority;

 }
+/*

+ * Calculate # of pages to be scanned in this priority/zone.

+ * See also vmscan.c

+ *

+ * priority starts from "DEF_PRIORITY" and decremented in each loop.

+ * (see include/linux/mmzone....
[ message continues ]

Functions to remember reclaim priority per cgroup (as zone->prev_priority)
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
 include/linux/memcontrol.h |   23 +++++++++++++++++++++++

 mm/memcontrol.c            |   20 ++++++++++++++++++++

 2 files changed, 43 insertions(+)
Index: linux-2.6.24-rc3-mm1/mm/memcontrol.c

===================================================================

--- linux-2.6.24-rc3-mm1.orig/mm/memcontrol.c	2007-11-27 11:19:51.000000000 +0900

+++ linux-2.6.24-rc3-mm1/mm/memcontrol.c	2007-11-27 11:22:14.000000000 +0900

@@ -132,6 +132,7 @@

 	 */

 	spinlock_t lru_lock;

 	unsigned long control_type;	/* control RSS or RSS+Pagecache */

+	int	prev_priority;	/* for recording reclaim priority */

 	/*

 	 * statistics.

 	 */

@@ -452,6 +453,25 @@

 	return (long) (active / (inactive + 1));

 }
+/*

+ * prev_priority control...this will be used in memory reclaim path.

+ */

+int mem_cgroup_get_reclaim_priority(struct mem_cgroup *mem)

+{

+	return mem->prev_priority;

+}

+

+void mem_cgroup_note_reclaim_priority(struct mem_cgroup *mem, int priority)

+{

+	if (priority < mem->prev_priority)

+		mem->prev_priority = priority;

+}

+

+void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem, int priority)

+{

+	mem->prev_priority = priority;

+}

+

 unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,

 					struct list_head *dst,

 					unsigned long *scanned, int order,

Index: linux-2.6.24-rc3-mm1/include/linux/memcontrol.h

===================================================================

--- linux-2.6.24-rc3-mm1.orig/include/linux/memcontrol.h	2007-11-27 11:19:00.000000000 +0900

+++ linux-2.6.24-rc3-mm1/include/linux/memcontrol.h	2007-11-27 11:22:14.000000000 +0900

@@ -67,6 +67,11 @@

 extern int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem);

 extern long mem_cgroup_reclaim_imbalance(struct mem_cgroup *mem);
+extern int mem_cgroup_get_reclaim_priority(struct mem_cgroup *mem);

+extern void mem_cg...
[ message continues ]

calculate active/inactive imbalance per memory cgroup.
Changelog V1 -> V2:

 - removed "total" (just count inactive and active)

 - fixed comment

 - fixed return type to be "long".
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
 include/linux/memcontrol.h |    8 ++++++++

 mm/memcontrol.c            |   14 ++++++++++++++

 2 files changed, 22 insertions(+)
Index: linux-2.6.24-rc3-mm1/mm/memcontrol.c

===================================================================

--- linux-2.6.24-rc3-mm1.orig/mm/memcontrol.c	2007-11-27 10:44:19.000000000 +0900

+++ linux-2.6.24-rc3-mm1/mm/memcontrol.c	2007-11-27 11:19:51.000000000 +0900

@@ -437,6 +437,20 @@

 	rss = (long)mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_RSS);

 	return (int)((rss * 100L) / total);

 }

+/*

+ * This function is called from vmscan.c. In page reclaiming loop. balance

+ * between active and inactive list is calculated. For memory controller

+ * page reclaiming, we should use using mem_cgroup's imbalance rather than

+ * zone's global lru imbalance.

+ */

+long mem_cgroup_reclaim_imbalance(struct mem_cgroup *mem)

+{

+	unsigned long active, inactive;

+	/* active and inactive are the number of pages. 'long' is ok.*/

+	active = mem_cgroup_get_all_zonestat(mem, MEM_CGROUP_ZSTAT_ACTIVE);

+	inactive = mem_cgroup_get_all_zonestat(mem, MEM_CGROUP_ZSTAT_INACTIVE);

+	return (long) (active / (inactive + 1));

+}
 unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,

 					struct list_head *dst,

Index: linux-2.6.24-rc3-mm1/include/linux/memcontrol.h

===================================================================

--- linux-2.6.24-rc3-mm1.orig/include/linux/memcontrol.h	2007-11-27 10:44:19.000000000 +0900

+++ linux-2.6.24-rc3-mm1/include/linux/memcontrol.h	2007-11-27 11:19:00.000000000 +0900

@@ -65,6 +65,8 @@

  * For memory reclaim.

  */

 extern int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem);

+extern long mem_cgroup_reclaim_imbalance(struct mem_cgroup *mem);

+

 ...
[ message continues ]

Define function for calculating mapped_ratio in memory cgroup.
Changelog V1->V2

 - Fixed possible divide-by-zero bug.

 - Use "long" to avoid 64bit division on 32 bit system.

   and does necessary type casts.

 - Added comments.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
 include/linux/memcontrol.h |   11 ++++++++++-

 mm/memcontrol.c            |   17 +++++++++++++++++

 2 files changed, 27 insertions(+), 1 deletion(-)
Index: linux-2.6.24-rc3-mm1/mm/memcontrol.c

===================================================================

--- linux-2.6.24-rc3-mm1.orig/mm/memcontrol.c	2007-11-26 16:39:02.000000000 +0900

+++ linux-2.6.24-rc3-mm1/mm/memcontrol.c	2007-11-26 16:41:34.000000000 +0900

@@ -421,6 +421,23 @@

 	spin_unlock(&mem->lru_lock);

 }
+/*

+ * Calculate mapped_ratio under memory controller. This will be used in

+ * vmscan.c for deteremining we have to reclaim mapped pages.

+ */

+int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem)

+{

+	long total, rss;

+

+	/*

+	 * usage is recorded in bytes. But, here, we assume the number of

+	 * physical pages can be represented by "long" on any arch.

+	 */

+	total = (long) (mem->res.usage >> PAGE_SHIFT) + 1L;

+	rss = (long)mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_RSS);

+	return (int)((rss * 100L) / total);

+}

+

 unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,

 					struct list_head *dst,

 					unsigned long *scanned, int order,

Index: linux-2.6.24-rc3-mm1/include/linux/memcontrol.h

===================================================================

--- linux-2.6.24-rc3-mm1.orig/include/linux/memcontrol.h	2007-11-26 15:31:19.000000000 +0900

+++ linux-2.6.24-rc3-mm1/include/linux/memcontrol.h	2007-11-26 16:39:05.000000000 +0900

@@ -61,6 +61,12 @@

 extern void mem_cgroup_end_migration(struct page *page);

 extern void mem_cgroup_page_migration(struct page *page, struct page *newpage);
+/*

+ * For memory reclaim.

+ */

+extern int mem_cgrou...
[ message continues ]

Counting active/inactive per-zone in memory controller.
This patch adds per-zone status in memory cgroup.

These values are often read (as per-zone value) by page reclaiming.
In current design, per-zone stat is just a unsigned long value and

not an atomic value because they are modified only under lru_lock.

(So, atomic_ops is not necessary.)
This patch adds ACTIVE and INACTIVE per-zone status values.
For handling per-zone status, this patch adds

  struct mem_cgroup_per_zone {

		...

  }

and some helper functions. This will be useful to add per-zone objects

in mem_cgroup.
This patch turns memory controller's early_init to be 0 for calling

kmalloc() in initialization.
Changelog V2 -> V3

  - fixed comments.
Changelog V1 -> V2

  - added mem_cgroup_per_zone struct.

      This will help following patches to implement per-zone objects and

      pack them into a struct.

  - added __mem_cgroup_add_list() and __mem_cgroup_remove_list()

  - fixed page migration handling.

  - renamed zstat to info (per-zone-info)

    This will be place for per-zone information(lru, lock, ..)

  - use page_cgroup_nid()/zid() funcs.
Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com>

Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
 mm/memcontrol.c |  164 +++++++++++++++++++++++++++++++++++++++++++++++++++++---

 1 file changed, 157 insertions(+), 7 deletions(-)
Index: linux-2.6.24-rc3-mm1/mm/memcontrol.c

===================================================================

--- linux-2.6.24-rc3-mm1.orig/mm/memcontrol.c	2007-11-26 16:39:00.000000000 +0900

+++ linux-2.6.24-rc3-mm1/mm/memcontrol.c	2007-11-26 16:39:02.000000000 +0900

@@ -78,6 +78,31 @@

 }
 /*

+ * per-zone information in memory controller.

+ */

+

+enum mem_cgroup_zstat_index {

+	MEM_CGROUP_ZSTAT_ACTIVE,

+	MEM_CGROUP_ZSTAT_INACTIVE,

+

+	NR_MEM_CGROUP_ZSTAT,

+};

+

+struct mem_cgroup_per_zone {

+	unsigned long count[NR_MEM_CGROUP_ZSTAT];

+};

+/* Macro for accessing counter */

+#de...
[ message continues ]

can this be true?
-

On Thu, 29 Nov 2007 12:33:28 +0900 (JST)
When I set early_init=1, I added that check.

BUG_ON() is better ?
Thanks,

-Kame
-

'active' seems unused.
YAMAMOTO Takashi

-

On Thu, 29 Nov 2007 12:19:37 +0900 (JST)

ok, I will post clean-up against -mm2.
Thanks,

-Kame
-

Just a "heads up":  This patch is the apparent cause of a boot time

panic--null pointer deref--on my numa platform.  See below.
As soon as this loop hits the first non-existent node on my platform, I

get a NULL pointer deref down in __alloc_pages.  Stack trace below.
Perhaps N_POSSIBLE should be N_HIGH_MEMORY?  That would require handling

of memory/node hotplug for each memory control group, right?  But, I'm

going to try N_HIGH_MEMORY as a work around.
Initializing cgroup subsys memory

Unable to handle kernel NULL pointer dereference (address 0000000000003c80)

swapper[0]: Oops 11012296146944 [1]

Modules linked in:
Pid: 0, CPU 0, comm:              swapper

psr : 00001210084a6010 ifs : 8000000000000b1a ip  : [<a000000100132e11>]    Not tainted

ip is at __alloc_pages+0x31/0x6e0

unat: 0000000000000000 pfs : 000000000000060f rsc : 0000000000000003

rnat: a0000001009db3b8 bsps: a0000001009e0490 pr  : 656960155aa65659

ldrs: 0000000000000000 ccv : 0000000000000000 fpsr: 0009804c8a70433f

csd : 0000000000000000 ssd : 0000000000000000

b0  : a000000100187370 b6  : a000000100194440 b7  : a00000010086d560

f6  : 1003e0000000000000000 f7  : 1003e0000000000000055

f8  : 1003e00000000000000c0 f9  : 1003e0000000000003fc0

f10 : 1003e00000000000000c0 f11 : 1003e0000000000000055

r1  : a000000100bc0f10 r2  : ffffffffffe00006 r3  : 0000000000020000

r8  : 0000000000071ef0 r9  : 0000000000000005 r10 : e00007002034d588

r11 : e00007002034d580 r12 : a0000001008e3df0 r13 : a0000001008dc000

r14 : 0000000000000001 r15 : e00007002034d5b0 r16 : 0000000000001e78

r17 : ffffffffffff04e0 r18 : 0000000000100002 r19 : 0000000000000000

r20 : 0000000000100002 r21 : 00000000000003cf r22 : 000000000000000f

r23 : 00000000000003c0 r24 : 0000000000000010 r25 : 0000000000000001

r26 : a0000001008e3e20 r27 : 0000000000000000 r28 : e0000701813dc088

r29 : e0000701813dc080 r30 : 0000000000000000 r31 : a000000100918ea8
Call Trace:

 [<a000000100014de0>] show_stack+0x80/0xa0

                                sp=a0...
[ message continues ]

On Wed, 28 Nov 2007 16:19:59 -0500

Maybe zonelists of NODE_DATA() is not initialized. you are right.

I think N_HIGH_MEMORY will be suitable here...(I'll consider node-hotplug case later.)
Thank you for test!
Regards,

-Kame
-

On Thu, 29 Nov 2007 10:37:02 +0900

Could you try this ? 
Thanks,

-Kame

==
Don't call kmalloc() against possible but offline node.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
 mm/memcontrol.c |   10 ++++++++--

 1 file changed, 8 insertions(+), 2 deletions(-)
Index: test-2.6.24-rc3-mm1/mm/memcontrol.c

===================================================================

--- test-2.6.24-rc3-mm1.orig/mm/memcontrol.c

+++ test-2.6.24-rc3-mm1/mm/memcontrol.c

@@ -1117,8 +1117,14 @@ static int alloc_mem_cgroup_per_zone_inf

 	struct mem_cgroup_per_node *pn;

 	struct mem_cgroup_per_zone *mz;

 	int zone;

-

-	pn = kmalloc_node(sizeof(*pn), GFP_KERNEL, node);

+	/*

+	 * This routine is called against possible nodes.

+	 * But it's BUG to call kmalloc() against offline node.

+	 */

+	if (node_state(N_ONLINE, node))

+		pn = kmalloc_node(sizeof(*pn), GFP_KERNEL, node);

+	else

+		pn = kmalloc(sizeof(*pn), GFP_KERNEL);

 	if (!pn)

 		return 1;
-

On Thu, 29 Nov 2007 11:24:06 +0900

Sorry..this can be a workaround but I noticed I miss something..
ok, just use N_HIGH_MEMORY here and add comment for hotplugging support is not yet.
Christoph-san, Lee-san, could you confirm following ?
- when SLAB is used, kmalloc_node() against offline node will success.

- when SLUB is used, kmalloc_node() against offline node will panic.
Then, the caller should take care that node is online before kmalloc().
Regards,

-Kame 
-

Hmmmm... An offline node implies that the per node structure does not

exist. SLAB should fail too. If there is something wrong with the allocs

then its likely a difference in the way hotplug was put into SLAB and

SLUB.
-

Add macro to get node_id and zone_id of page_cgroup.

Will be used in per-zone-xxx patches and others.
Changelog:

 - returns zone_type instead of int.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
 mm/memcontrol.c |   10 ++++++++++

 1 file changed, 10 insertions(+)
Index: linux-2.6.24-rc3-mm1/mm/memcontrol.c

===================================================================

--- linux-2.6.24-rc3-mm1.orig/mm/memcontrol.c	2007-11-26 15:31:19.000000000 +0900

+++ linux-2.6.24-rc3-mm1/mm/memcontrol.c	2007-11-26 16:39:00.000000000 +0900

@@ -135,6 +135,16 @@

 #define PAGE_CGROUP_FLAG_CACHE	(0x1)	/* charged as cache */

 #define PAGE_CGROUP_FLAG_ACTIVE (0x2)	/* page is active in this cgroup */
+static inline int page_cgroup_nid(struct page_cgroup *pc)

+{

+	return page_to_nid(pc->page);

+}

+

+static inline enum zone_type page_cgroup_zid(struct page_cgroup *pc)

+{

+	return page_zonenum(pc->page);

+}

+

 enum {

 	MEM_CGROUP_TYPE_UNSPEC = 0,

 	MEM_CGROUP_TYPE_MAPPED,
-

add macro scan_global_lru().
This is used to detect which scan_control scans global lru or

mem_cgroup lru. And compiled to be static value (1) when

memory controller is not configured. This may make the meaning obvious.
Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com>

Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
 mm/vmscan.c |   17 ++++++++++++-----

 1 file changed, 12 insertions(+), 5 deletions(-)
Index: linux-2.6.24-rc3-mm1/mm/vmscan.c

===================================================================

--- linux-2.6.24-rc3-mm1.orig/mm/vmscan.c	2007-11-26 15:31:19.000000000 +0900

+++ linux-2.6.24-rc3-mm1/mm/vmscan.c	2007-11-26 16:38:46.000000000 +0900

@@ -127,6 +127,12 @@

 static LIST_HEAD(shrinker_list);

 static DECLARE_RWSEM(shrinker_rwsem);
+#ifdef CONFIG_CGROUP_MEM_CONT

+#define scan_global_lru(sc)	(!(sc)->mem_cgroup)

+#else

+#define scan_global_lru(sc)	(1)

+#endif

+

 /*

  * Add a shrinker callback to be called from the vm

  */

@@ -1290,11 +1296,12 @@

 		 * Don't shrink slabs when reclaiming memory from

 		 * over limit cgroups

 		 */

-		if (sc->mem_cgroup == NULL)

+		if (scan_global_lru(sc)) {

 			shrink_slab(sc->nr_scanned, gfp_mask, lru_pages);

-		if (reclaim_state) {

-			nr_reclaimed += reclaim_state->reclaimed_slab;

-			reclaim_state->reclaimed_slab = 0;

+			if (reclaim_state) {

+				nr_reclaimed += reclaim_state->reclaimed_slab;

+				reclaim_state->reclaimed_slab = 0;

+			}

 		}

 		total_scanned += sc->nr_scanned;

 		if (nr_reclaimed >= sc->swap_cluster_max) {

@@ -1321,7 +1328,7 @@

 			congestion_wait(WRITE, HZ/10);

 	}

 	/* top priority shrink_caches still had more to do? don't OOM, then */

-	if (!sc->all_unreclaimable && sc->mem_cgroup == NULL)

+	if (!sc->all_unreclaimable && scan_global_lru(sc))

 		ret = 1;

 out:

 	/*
-