memcg: remove refcnt from page_cgroup

memcg: performance improvements

Patch Description
 1/5 ... remove refcnt fron page_cgroup patch (shmem handling is fixed)
 2/5 ... swapcache handling patch
 3/5 ... add helper function for shmem's memory reclaim patch
 4/5 ... optimize by likely/unlikely ppatch
 5/5 ... remove redundunt check patch (shmem handling is fixed.)

Unix bench result.

== 2.6.26-rc2-mm1 + memory resource controller
Execl Throughput                           2915.4 lps   (29.6 secs, 3 samples)
C Compiler Throughput                      1019.3 lpm   (60.0 secs, 3 samples)
Shell Scripts (1 concurrent)               5796.0 lpm   (60.0 secs, 3 samples)
Shell Scripts (8 concurrent)               1097.7 lpm   (60.0 secs, 3 samples)
Shell Scripts (16 concurrent)               565.3 lpm   (60.0 secs, 3 samples)
File Read 1024 bufsize 2000 maxblocks    1022128.0 KBps  (30.0 secs, 3 samples)
File Write 1024 bufsize 2000 maxblocks   544057.0 KBps  (30.0 secs, 3 samples)
File Copy 1024 bufsize 2000 maxblocks    346481.0 KBps  (30.0 secs, 3 samples)
File Read 256 bufsize 500 maxblocks      319325.0 KBps  (30.0 secs, 3 samples)
File Write 256 bufsize 500 maxblocks     148788.0 KBps  (30.0 secs, 3 samples)
File Copy 256 bufsize 500 maxblocks       99051.0 KBps  (30.0 secs, 3 samples)
File Read 4096 bufsize 8000 maxblocks    2058917.0 KBps  (30.0 secs, 3 samples)
File Write 4096 bufsize 8000 maxblocks   1606109.0 KBps  (30.0 secs, 3 samples)
File Copy 4096 bufsize 8000 maxblocks    854789.0 KBps  (30.0 secs, 3 samples)
Dc: sqrt(2) to 99 decimal places         126145.2 lpm   (30.0 secs, 3 samples)

                     INDEX VALUES
TEST                                        BASELINE     RESULT      INDEX

Execl Throughput                                43.0     2915.4      678.0
File Copy 1024 bufsize 2000 maxblocks         3960.0   346481.0      875.0
File Copy 256 bufsize 500 maxblocks           1655.0    99051.0      598.5
File Copy 4096 bufsize 8000 maxblocks         5800.0   854789.0     1473.8
Shell Scripts (8 concurrent)                     6.0     1097.7     1829.5
                                                                 =========
     FINAL SCORE                                                     991.3

== 2.6.26-rc2-mm1 + this set ==
Execl Throughput                           3012.9 lps   (29.9 secs, 3 samples)
C Compiler Throughput                       981.0 lpm   (60.0 secs, 3 samples)
Shell Scripts (1 concurrent)               5872.0 lpm   (60.0 secs, 3 samples)
Shell Scripts (8 concurrent)               1120.3 lpm   (60.0 secs, 3 samples)
Shell Scripts (16 concurrent)               578.0 lpm   (60.0 secs, 3 samples)
File Read 1024 bufsize 2000 maxblocks    1003993.0 KBps  (30.0 secs, 3 samples)
File Write 1024 bufsize 2000 maxblocks   550452.0 KBps  (30.0 secs, 3 samples)
File Copy 1024 bufsize 2000 maxblocks    347159.0 KBps  (30.0 secs, 3 samples)
File Read 256 bufsize 500 maxblocks      314644.0 KBps  (30.0 secs, 3 samples)
File Write 256 bufsize 500 maxblocks     151852.0 KBps  (30.0 secs, 3 samples)
File Copy 256 bufsize 500 maxblocks      101000.0 KBps  (30.0 secs, 3 samples)
File Read 4096 bufsize 8000 maxblocks    2033256.0 KBps  (30.0 secs, 3 samples)
File Write 4096 bufsize 8000 maxblocks   1611814.0 KBps  (30.0 secs, 3 samples)
File Copy 4096 bufsize 8000 maxblocks    847979.0 KBps  (30.0 secs, 3 samples)
Dc: sqrt(2) to 99 decimal places         128148.7 lpm   (30.0 secs, 3 samples)

                     INDEX VALUES
TEST                                        BASELINE     RESULT      INDEX

Execl Throughput                                43.0     3012.9      700.7
File Copy 1024 bufsize 2000 maxblocks         3960.0   347159.0      876.7
File Copy 256 bufsize 500 maxblocks           1655.0   101000.0      610.3
File Copy 4096 bufsize 8000 maxblocks         5800.0   847979.0     1462.0
Shell Scripts (8 concurrent)                     6.0     1120.3     1867.2
                                                                 =========
     FINAL SCORE                                                    1004.6

This patch:

Remove refcnt from page_cgroup().

After this,

 * A page is charged only when !page_mapped() && no page_cgroup is assigned.
	* Anon page is newly mapped.
	* File page is added to mapping->tree.

 * A page is uncharged only when
	* Anon page is fully unmapped.
	* File page is removed from LRU.

There is no change in behavior from user's view.

This patch also removes unnecessary calls in rmap.c which was used only for
refcnt mangement.

[akpm@linux-foundation.org: fix warning]
[hugh@veritas.com: fix shmem_unuse_inode charging]
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Pavel Emelyanov <xemul@openvz.org>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: YAMAMOTO Takashi <yamamoto@valinux.co.jp>
Cc: Paul Menage <menage@google.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 24 insertions, 11 deletions

diff --git a/mm/shmem.c b/mm/shmem.c
index 9ffbea9b79e..d58305e8a48 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -922,20 +922,26 @@ found:
 	error = 1;
 	if (!inode)
 		goto out;
-	/* Precharge page while we can wait, compensate afterwards */
+	/* Precharge page using GFP_KERNEL while we can wait */
 	error = mem_cgroup_cache_charge(page, current->mm, GFP_KERNEL);
 	if (error)
 		goto out;
 	error = radix_tree_preload(GFP_KERNEL);
-	if (error)
-		goto uncharge;
+	if (error) {
+		mem_cgroup_uncharge_cache_page(page);
+		goto out;
+	}
 	error = 1;
 
 	spin_lock(&info->lock);
 	ptr = shmem_swp_entry(info, idx, NULL);
-	if (ptr && ptr->val == entry.val)
+	if (ptr && ptr->val == entry.val) {
 		error = add_to_page_cache(page, inode->i_mapping,
 						idx, GFP_NOWAIT);
+		/* does mem_cgroup_uncharge_cache_page on error */
+	} else	/* we must compensate for our precharge above */
+		mem_cgroup_uncharge_cache_page(page);
+
 	if (error == -EEXIST) {
 		struct page *filepage = find_get_page(inode->i_mapping, idx);
 		error = 1;
@@ -961,8 +967,6 @@ found:
 		shmem_swp_unmap(ptr);
 	spin_unlock(&info->lock);
 	radix_tree_preload_end();
-uncharge:
-	mem_cgroup_uncharge_page(page);
 out:
 	unlock_page(page);
 	page_cache_release(page);
@@ -1319,7 +1323,7 @@ repeat:
 					page_cache_release(swappage);
 					goto failed;
 				}
-				mem_cgroup_uncharge_page(swappage);
+				mem_cgroup_uncharge_cache_page(swappage);
 			}
 			page_cache_release(swappage);
 			goto repeat;
@@ -1358,6 +1362,8 @@ repeat:
 		}
 
 		if (!filepage) {
+			int ret;
+
 			spin_unlock(&info->lock);
 			filepage = shmem_alloc_page(gfp, info, idx);
 			if (!filepage) {
@@ -1386,10 +1392,18 @@ repeat:
 				swap = *entry;
 				shmem_swp_unmap(entry);
 			}
-			if (error || swap.val || 0 != add_to_page_cache_lru(
-					filepage, mapping, idx, GFP_NOWAIT)) {
+			ret = error || swap.val;
+			if (ret)
+				mem_cgroup_uncharge_cache_page(filepage);
+			else
+				ret = add_to_page_cache_lru(filepage, mapping,
+						idx, GFP_NOWAIT);
+			/*
+			 * At add_to_page_cache_lru() failure, uncharge will
+			 * be done automatically.
+			 */
+			if (ret) {
 				spin_unlock(&info->lock);
-				mem_cgroup_uncharge_page(filepage);
 				page_cache_release(filepage);
 				shmem_unacct_blocks(info->flags, 1);
 				shmem_free_blocks(inode, 1);
@@ -1398,7 +1412,6 @@ repeat:
 					goto failed;
 				goto repeat;
 			}
-			mem_cgroup_uncharge_page(filepage);
 			info->flags |= SHMEM_PAGEIN;
 		}