lkml.org 
[lkml]   [2011]   [May]   [13]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[RFC][PATCH v7 13/14] writeback: make background writeback cgroup aware
Date
When the system is under background dirty memory threshold but a cgroup
is over its background dirty memory threshold, then only writeback
inodes associated with the over-limit cgroup(s).

In addition to checking if the system dirty memory usage is over the
system background threshold, over_bground_thresh() also checks if any
cgroups are over their respective background dirty memory thresholds.
The writeback_control.for_cgroup field is set to distinguish between a
system and memcg overage.

If performing cgroup writeback, move_expired_inodes() skips inodes that
do not contribute dirty pages to the cgroup being written back.

After writing some pages, wb_writeback() will call
mem_cgroup_writeback_done() to update the set of over-bg-limits memcg.

Signed-off-by: Greg Thelen <gthelen@google.com>
---
fs/fs-writeback.c | 31 +++++++++++++++++++++++--------
1 files changed, 23 insertions(+), 8 deletions(-)

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 0174fcf..b01bb2a 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -256,14 +256,17 @@ static void move_expired_inodes(struct list_head *delaying_queue,
LIST_HEAD(tmp);
struct list_head *pos, *node;
struct super_block *sb = NULL;
- struct inode *inode;
+ struct inode *inode, *tmp_inode;
int do_sb_sort = 0;

- while (!list_empty(delaying_queue)) {
- inode = wb_inode(delaying_queue->prev);
+ list_for_each_entry_safe_reverse(inode, tmp_inode, delaying_queue,
+ i_wb_list) {
if (wbc->older_than_this &&
inode_dirtied_after(inode, *wbc->older_than_this))
break;
+ if (wbc->for_cgroup &&
+ !should_writeback_mem_cgroup_inode(inode, wbc))
+ continue;
if (sb && sb != inode->i_sb)
do_sb_sort = 1;
sb = inode->i_sb;
@@ -614,14 +617,21 @@ void writeback_inodes_wb(struct bdi_writeback *wb,
*/
#define MAX_WRITEBACK_PAGES 1024

-static inline bool over_bground_thresh(void)
+static inline bool over_bground_thresh(struct bdi_writeback *wb,
+ struct writeback_control *wbc)
{
unsigned long background_thresh, dirty_thresh;

global_dirty_limits(&background_thresh, &dirty_thresh);

- return (global_page_state(NR_FILE_DIRTY) +
- global_page_state(NR_UNSTABLE_NFS) > background_thresh);
+ if (global_page_state(NR_FILE_DIRTY) +
+ global_page_state(NR_UNSTABLE_NFS) > background_thresh) {
+ wbc->for_cgroup = 0;
+ return true;
+ }
+
+ wbc->for_cgroup = 1;
+ return mem_cgroups_over_bground_dirty_thresh();
}

/*
@@ -700,7 +710,7 @@ static long wb_writeback(struct bdi_writeback *wb,
* For background writeout, stop when we are below the
* background dirty threshold
*/
- if (work->for_background && !over_bground_thresh())
+ if (work->for_background && !over_bground_thresh(wb, &wbc))
break;

if (work->for_kupdate || work->for_background) {
@@ -729,6 +739,9 @@ retry:
work->nr_pages -= write_chunk - wbc.nr_to_write;
wrote += write_chunk - wbc.nr_to_write;

+ if (write_chunk - wbc.nr_to_write > 0)
+ mem_cgroup_writeback_done();
+
/*
* Did we write something? Try for more
*
@@ -809,7 +822,9 @@ static unsigned long get_nr_dirty_pages(void)

static long wb_check_background_flush(struct bdi_writeback *wb)
{
- if (over_bground_thresh()) {
+ struct writeback_control wbc;
+
+ if (over_bground_thresh(wb, &wbc)) {

struct wb_writeback_work work = {
.nr_pages = LONG_MAX,
--
1.7.3.1


\
 
 \ /
  Last update: 2011-05-13 10:57    [W:0.095 / U:0.708 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site