diff options
| author | KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> | 2008-10-18 20:28:16 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2008-10-20 08:52:39 -0700 |
| commit | 52d4b9ac0b985168009c2a57098324e67bae171f (patch) | |
| tree | b3e3b854166930af893be90ea30a7ab0d65c59e7 /include/linux/mmzone.h | |
| parent | c05555b572921c464d064d9267f7f7bc06d424fa (diff) | |
| download | talos-obmc-linux-52d4b9ac0b985168009c2a57098324e67bae171f.tar.gz talos-obmc-linux-52d4b9ac0b985168009c2a57098324e67bae171f.zip | |
memcg: allocate all page_cgroup at boot
Allocate all page_cgroup at boot and remove page_cgroup poitner from
struct page. This patch adds an interface as
struct page_cgroup *lookup_page_cgroup(struct page*)
All FLATMEM/DISCONTIGMEM/SPARSEMEM and MEMORY_HOTPLUG is supported.
Remove page_cgroup pointer reduces the amount of memory by
- 4 bytes per PAGE_SIZE.
- 8 bytes per PAGE_SIZE
if memory controller is disabled. (even if configured.)
On usual 8GB x86-32 server, this saves 8MB of NORMAL_ZONE memory.
On my x86-64 server with 48GB of memory, this saves 96MB of memory.
I think this reduction makes sense.
By pre-allocation, kmalloc/kfree in charge/uncharge are removed.
This means
- we're not necessary to be afraid of kmalloc faiulre.
(this can happen because of gfp_mask type.)
- we can avoid calling kmalloc/kfree.
- we can avoid allocating tons of small objects which can be fragmented.
- we can know what amount of memory will be used for this extra-lru handling.
I added printk message as
"allocated %ld bytes of page_cgroup"
"please try cgroup_disable=memory option if you don't want"
maybe enough informative for users.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Reviewed-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'include/linux/mmzone.h')
| -rw-r--r-- | include/linux/mmzone.h | 14 |
1 files changed, 13 insertions, 1 deletions
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index da2d053a95f1..35a7b5e19465 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -601,8 +601,11 @@ typedef struct pglist_data { struct zone node_zones[MAX_NR_ZONES]; struct zonelist node_zonelists[MAX_ZONELISTS]; int nr_zones; -#ifdef CONFIG_FLAT_NODE_MEM_MAP +#ifdef CONFIG_FLAT_NODE_MEM_MAP /* means !SPARSEMEM */ struct page *node_mem_map; +#ifdef CONFIG_CGROUP_MEM_RES_CTLR + struct page_cgroup *node_page_cgroup; +#endif #endif struct bootmem_data *bdata; #ifdef CONFIG_MEMORY_HOTPLUG @@ -931,6 +934,7 @@ static inline unsigned long early_pfn_to_nid(unsigned long pfn) #endif struct page; +struct page_cgroup; struct mem_section { /* * This is, logically, a pointer to an array of struct @@ -948,6 +952,14 @@ struct mem_section { /* See declaration of similar field in struct zone */ unsigned long *pageblock_flags; +#ifdef CONFIG_CGROUP_MEM_RES_CTLR + /* + * If !SPARSEMEM, pgdat doesn't have page_cgroup pointer. We use + * section. (see memcontrol.h/page_cgroup.h about this.) + */ + struct page_cgroup *page_cgroup; + unsigned long pad; +#endif }; #ifdef CONFIG_SPARSEMEM_EXTREME |
