memcg: add per cgroup dirty page accounting

When modifying PG_Dirty on cached file pages, update the new
MEM_CGROUP_STAT_DIRTY counter.  This is done in the same places where
global NR_FILE_DIRTY is managed.  The new memcg stat is visible in the
per memcg memory.stat cgroupfs file.  The most recent past attempt at
this was http://thread.gmane.org/gmane.linux.kernel.cgroups/8632

The new accounting supports future efforts to add per cgroup dirty
page throttling and writeback.  It also helps an administrator break
down a container's memory usage and provides evidence to understand
memcg oom kills (the new dirty count is included in memcg oom kill
messages).

The ability to move page accounting between memcg
(memory.move_charge_at_immigrate) makes this accounting more
complicated than the global counter.  The existing
mem_cgroup_{begin,end}_page_stat() lock is used to serialize move
accounting with stat updates.
Typical update operation:
	memcg = mem_cgroup_begin_page_stat(page)
	if (TestSetPageDirty()) {
		[...]
		mem_cgroup_update_page_stat(memcg)
	}
	mem_cgroup_end_page_stat(memcg)

Summary of mem_cgroup_end_page_stat() overhead:
- Without CONFIG_MEMCG it's a no-op
- With CONFIG_MEMCG and no inter memcg task movement, it's just
  rcu_read_lock()
- With CONFIG_MEMCG and inter memcg  task movement, it's
  rcu_read_lock() + spin_lock_irqsave()

A memcg parameter is added to several routines because their callers
now grab mem_cgroup_begin_page_stat() which returns the memcg later
needed by for mem_cgroup_update_page_stat().

Because mem_cgroup_begin_page_stat() may disable interrupts, some
adjustments are needed:
- move __mark_inode_dirty() from __set_page_dirty() to its caller.
  __mark_inode_dirty() locking does not want interrupts disabled.
- use spin_lock_irqsave(tree_lock) rather than spin_lock_irq() in
  __delete_from_page_cache(), replace_page_cache_page(),
  invalidate_complete_page2(), and __remove_mapping().

   text    data     bss      dec    hex filename
8925147 1774832 1785856 12485835 be84cb vmlinux-!CONFIG_MEMCG-before
8925339 1774832 1785856 12486027 be858b vmlinux-!CONFIG_MEMCG-after
                            +192 text bytes
8965977 1784992 1785856 12536825 bf4bf9 vmlinux-CONFIG_MEMCG-before
8966750 1784992 1785856 12537598 bf4efe vmlinux-CONFIG_MEMCG-after
                            +773 text bytes

Performance tests run on v4.0-rc1-36-g4f671fe2f952.  Lower is better for
all metrics, they're all wall clock or cycle counts.  The read and write
fault benchmarks just measure fault time, they do not include I/O time.

* CONFIG_MEMCG not set:
                            baseline                              patched
  kbuild                 1m25.030000(+-0.088% 3 samples)       1m25.426667(+-0.120% 3 samples)
  dd write 100 MiB          0.859211561 +-15.10%                  0.874162885 +-15.03%
  dd write 200 MiB          1.670653105 +-17.87%                  1.669384764 +-11.99%
  dd write 1000 MiB         8.434691190 +-14.15%                  8.474733215 +-14.77%
  read fault cycles       254.0(+-0.000% 10 samples)            253.0(+-0.000% 10 samples)
  write fault cycles     2021.2(+-3.070% 10 samples)           1984.5(+-1.036% 10 samples)

* CONFIG_MEMCG=y root_memcg:
                            baseline                              patched
  kbuild                 1m25.716667(+-0.105% 3 samples)       1m25.686667(+-0.153% 3 samples)
  dd write 100 MiB          0.855650830 +-14.90%                  0.887557919 +-14.90%
  dd write 200 MiB          1.688322953 +-12.72%                  1.667682724 +-13.33%
  dd write 1000 MiB         8.418601605 +-14.30%                  8.673532299 +-15.00%
  read fault cycles       266.0(+-0.000% 10 samples)            266.0(+-0.000% 10 samples)
  write fault cycles     2051.7(+-1.349% 10 samples)           2049.6(+-1.686% 10 samples)

* CONFIG_MEMCG=y non-root_memcg:
                            baseline                              patched
  kbuild                 1m26.120000(+-0.273% 3 samples)       1m25.763333(+-0.127% 3 samples)
  dd write 100 MiB          0.861723964 +-15.25%                  0.818129350 +-14.82%
  dd write 200 MiB          1.669887569 +-13.30%                  1.698645885 +-13.27%
  dd write 1000 MiB         8.383191730 +-14.65%                  8.351742280 +-14.52%
  read fault cycles       265.7(+-0.172% 10 samples)            267.0(+-0.000% 10 samples)
  write fault cycles     2070.6(+-1.512% 10 samples)           2084.4(+-2.148% 10 samples)

As expected anon page faults are not affected by this patch.

tj: Updated to apply on top of the recent cancel_dirty_page() changes.

Signed-off-by: Sha Zhengju <handai.szj@gmail.com>
Signed-off-by: Greg Thelen <gthelen@google.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@fb.com>

1 files changed, 27 insertions, 7 deletions

diff --git a/fs/buffer.c b/fs/buffer.c
index f21327d1f673..23b640d5d6e9 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -623,21 +623,22 @@ EXPORT_SYMBOL(mark_buffer_dirty_inode);
  *
  * If warn is true, then emit a warning if the page is not uptodate and has
  * not been truncated.
+ *
+ * The caller must hold mem_cgroup_begin_page_stat() lock.
  */
-static void __set_page_dirty(struct page *page,
-		struct address_space *mapping, int warn)
+static void __set_page_dirty(struct page *page, struct address_space *mapping,
+			     struct mem_cgroup *memcg, int warn)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(&mapping->tree_lock, flags);
 	if (page->mapping) {	/* Race with truncate? */
 		WARN_ON_ONCE(warn && !PageUptodate(page));
-		account_page_dirtied(page, mapping);
+		account_page_dirtied(page, mapping, memcg);
 		radix_tree_tag_set(&mapping->page_tree,
 				page_index(page), PAGECACHE_TAG_DIRTY);
 	}
 	spin_unlock_irqrestore(&mapping->tree_lock, flags);
-	__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
 }
 
 /*
@@ -668,6 +669,7 @@ static void __set_page_dirty(struct page *page,
 int __set_page_dirty_buffers(struct page *page)
 {
 	int newly_dirty;
+	struct mem_cgroup *memcg;
 	struct address_space *mapping = page_mapping(page);
 
 	if (unlikely(!mapping))
@@ -683,11 +685,22 @@ int __set_page_dirty_buffers(struct page *page)
 			bh = bh->b_this_page;
 		} while (bh != head);
 	}
+	/*
+	 * Use mem_group_begin_page_stat() to keep PageDirty synchronized with
+	 * per-memcg dirty page counters.
+	 */
+	memcg = mem_cgroup_begin_page_stat(page);
 	newly_dirty = !TestSetPageDirty(page);
 	spin_unlock(&mapping->private_lock);
 
 	if (newly_dirty)
-		__set_page_dirty(page, mapping, 1);
+		__set_page_dirty(page, mapping, memcg, 1);
+
+	mem_cgroup_end_page_stat(memcg);
+
+	if (newly_dirty)
+		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
+
 	return newly_dirty;
 }
 EXPORT_SYMBOL(__set_page_dirty_buffers);
@@ -1158,11 +1171,18 @@ void mark_buffer_dirty(struct buffer_head *bh)
 
 	if (!test_set_buffer_dirty(bh)) {
 		struct page *page = bh->b_page;
+		struct address_space *mapping = NULL;
+		struct mem_cgroup *memcg;
+
+		memcg = mem_cgroup_begin_page_stat(page);
 		if (!TestSetPageDirty(page)) {
-			struct address_space *mapping = page_mapping(page);
+			mapping = page_mapping(page);
 			if (mapping)
-				__set_page_dirty(page, mapping, 0);
+				__set_page_dirty(page, mapping, memcg, 0);
 		}
+		mem_cgroup_end_page_stat(memcg);
+		if (mapping)
+			__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
 	}
 }
 EXPORT_SYMBOL(mark_buffer_dirty);