wb_over_bg_thresh() calls mem_cgroup_wb_stats() which invokes an rstat
flush, which can be expensive on large systems. Currently,
wb_writeback() calls wb_over_bg_thresh() within a lock section, so we
have to do the rstat flush atomically. On systems with a lot of
cpus and/or cgroups, this can cause us to disable irqs for a long time,
potentially causing problems.
Move the call to wb_over_bg_thresh() outside the lock section in
preparation to make the rstat flush in mem_cgroup_wb_stats() non-atomic.
The list_empty(&wb->work_list) check should be okay outside the lock
section of wb->list_lock as it is protected by a separate lock
(wb->work_lock), and wb_over_bg_thresh() doesn't seem like it is
modifying any of wb->b_* lists the wb->list_lock is protecting.
Also, the loop seems to be already releasing and reacquring the
lock, so this refactoring looks safe.
Signed-off-by: Yosry Ahmed <yosryahmed@xxxxxxxxxx>
Reviewed-by: Michal Koutný <mkoutny@xxxxxxxx>
Reviewed-by: Jan Kara <jack@xxxxxxx>
---
fs/fs-writeback.c | 16 +++++++++++-----
1 file changed, 11 insertions(+), 5 deletions(-)
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 1db3e3c24b43..11aa1652fb84 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -2024,7 +2024,6 @@ static long wb_writeback(struct bdi_writeback *wb,
struct blk_plug plug;
blk_start_plug(&plug);
- spin_lock(&wb->list_lock);
for (;;) {
/*
* Stop writeback when nr_pages has been consumed
@@ -2049,6 +2048,9 @@ static long wb_writeback(struct bdi_writeback *wb,
if (work->for_background && !wb_over_bg_thresh(wb))
break;
+
+ spin_lock(&wb->list_lock);
+
/*
* Kupdate and background works are special and we want to
* include all inodes that need writing. Livelock avoidance is
@@ -2078,13 +2080,19 @@ static long wb_writeback(struct bdi_writeback *wb,
* mean the overall work is done. So we keep looping as long
* as made some progress on cleaning pages or inodes.
*/
- if (progress)
+ if (progress) {
+ spin_unlock(&wb->list_lock);
continue;
+ }
+
/*
* No more inodes for IO, bail
*/
- if (list_empty(&wb->b_more_io))
+ if (list_empty(&wb->b_more_io)) {
+ spin_unlock(&wb->list_lock);
break;
+ }
+
/*
* Nothing written. Wait for some inode to
* become available for writeback. Otherwise
@@ -2096,9 +2104,7 @@ static long wb_writeback(struct bdi_writeback *wb,
spin_unlock(&wb->list_lock);
/* This function drops i_lock... */
inode_sleep_on_writeback(inode);
- spin_lock(&wb->list_lock);
}
- spin_unlock(&wb->list_lock);
blk_finish_plug(&plug);
return nr_pages - work->nr_pages;
--
2.40.0.634.g4ca3ef3211-goog
