The start time in writeback_inodes_wb() is not very useful because it
slips at each invocation time. Preferrably one _constant_ time shall be
used at the beginning to cover the whole sync() work.
The newly dirtied inodes are now guarded at the queue_io() time instead
of the b_io walk time. This is more natural: non-empty b_io/b_more_io
means "more work pending".
The timestamp is now grabbed the sync work submission time, and may be
further optimized to the initial sync() call time.
CC: Jan Kara <jack@xxxxxxx>
Signed-off-by: Wu Fengguang <fengguang.wu@xxxxxxxxx>
---
fs/fs-writeback.c | 16 ++++++----------
include/linux/writeback.h | 4 ++--
2 files changed, 8 insertions(+), 12 deletions(-)
--- linux-next.orig/fs/fs-writeback.c 2010-07-29 17:13:49.000000000 +0800
+++ linux-next/fs/fs-writeback.c 2010-07-29 17:13:58.000000000 +0800
@@ -228,6 +228,10 @@ static void move_expired_inodes(struct l
struct inode *inode;
int do_sb_sort = 0;
+ if (wbc->for_sync) {
+ expire_interval = 1;
+ older_than_this = wbc->sync_after;
+ }
if (wbc->for_kupdate || wbc->for_background) {
expire_interval = msecs_to_jiffies(dirty_expire_interval * 10);
older_than_this = jiffies - expire_interval;
@@ -507,12 +511,6 @@ static int writeback_sb_inodes(struct su
requeue_io(inode);
continue;
}
- /*
- * Was this inode dirtied after sync_sb_inodes was called?
- * This keeps sync from extra jobs and livelock.
- */
- if (inode_dirtied_after(inode, wbc->wb_start))
- return 1;
BUG_ON(inode->i_state & I_FREEING);
__iget(inode);
@@ -541,10 +539,9 @@ void writeback_inodes_wb(struct bdi_writ
{
int ret = 0;
- wbc->wb_start = jiffies; /* livelock avoidance */
spin_lock(&inode_lock);
- if (!(wbc->for_kupdate || wbc->for_background) || list_empty(&wb->b_io))
+ if (list_empty(&wb->b_io))
queue_io(wb, wbc);
while (!list_empty(&wb->b_io)) {
@@ -571,9 +568,8 @@ static void __writeback_inodes_sb(struct
{
WARN_ON(!rwsem_is_locked(&sb->s_umount));
- wbc->wb_start = jiffies; /* livelock avoidance */
spin_lock(&inode_lock);
- if (!(wbc->for_kupdate || wbc->for_background) || list_empty(&wb->b_io))
+ if (list_empty(&wb->b_io))
queue_io(wb, wbc);
writeback_sb_inodes(sb, wb, wbc, true);
spin_unlock(&inode_lock);
--- linux-next.orig/include/linux/writeback.h 2010-07-29 17:13:18.000000000 +0800
+++ linux-next/include/linux/writeback.h 2010-07-29 17:13:58.000000000 +0800
@@ -28,8 +28,8 @@ enum writeback_sync_modes {
*/
struct writeback_control {
enum writeback_sync_modes sync_mode;
- unsigned long wb_start; /* Time writeback_inodes_wb was
- called. This is needed to avoid
+ unsigned long sync_after; /* Only sync inodes dirtied after this
+ timestamp. This is needed to avoid
extra jobs and livelock */
long nr_to_write; /* Write this many pages, and decrement
this for each page written */
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxxx For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>