[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <1420579582-8516-16-git-send-email-tj@kernel.org>
Date: Tue, 6 Jan 2015 16:25:52 -0500
From: Tejun Heo <tj@...nel.org>
To: axboe@...nel.dk
Cc: linux-kernel@...r.kernel.org, jack@...e.cz, hch@...radead.org,
hannes@...xchg.org, linux-fsdevel@...r.kernel.org,
vgoyal@...hat.com, lizefan@...wei.com, cgroups@...r.kernel.org,
linux-mm@...ck.org, mhocko@...e.cz, clm@...com,
fengguang.wu@...el.com, david@...morbit.com,
Tejun Heo <tj@...nel.org>
Subject: [PATCH 15/45] writeback: make bdi_has_dirty_io() take multiple bdi_writeback's into account
bdi_has_dirty_io() used to only reflect whether the root wb
(bdi_writeback) has dirty inodes. For cgroup writeback support, it
needs to take all active wb's into account. If any wb on the bdi has
dirty inodes, bdi_has_dirty_io() should return true.
To achieve that, as inode_wb_list_{move|del}_locked() now keep track
of the dirty state transition of each wb, the number of dirty wbs can
be counted in the bdi; however, bdi is already aggregating
wb->avg_write_bandwidth which can easily be guaranteed to be > 0 if
there are any dirty inodes by ensuring wb->avg_write_bandwidth can't
dip below 1. bdi_has_dirty_io() can simply test whether
bdi->tot_write_bandwidth is zero or not.
While this bumps the value of wb->avg_write_bandwidth to one when it
used to be zero, this shouldn't cause any meaningful behavior
difference.
bdi_has_dirty_io() is made an inline function which tests whether
->tot_write_bandwidth is non-zero. Also, WARN_ON_ONCE()'s on its
value are added to inode_wb_list_{move|del}_locked().
Signed-off-by: Tejun Heo <tj@...nel.org>
Cc: Jens Axboe <axboe@...nel.dk>
Cc: Jan Kara <jack@...e.cz>
---
fs/fs-writeback.c | 5 +++--
include/linux/backing-dev-defs.h | 8 ++++++--
include/linux/backing-dev.h | 10 +++++++++-
mm/backing-dev.c | 5 -----
mm/page-writeback.c | 10 +++++++---
5 files changed, 25 insertions(+), 13 deletions(-)
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index d41728b..35d32ad 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -312,6 +312,7 @@ static bool inode_wb_list_move_locked(struct inode *inode,
return false;
} else {
set_bit(WB_has_dirty_io, &wb->state);
+ WARN_ON_ONCE(!wb->avg_write_bandwidth);
atomic_long_add(wb->avg_write_bandwidth,
&wb->bdi->tot_write_bandwidth);
return true;
@@ -336,8 +337,8 @@ static void inode_wb_list_del_locked(struct inode *inode,
if (wb_has_dirty_io(wb) && list_empty(&wb->b_dirty) &&
list_empty(&wb->b_io) && list_empty(&wb->b_more_io)) {
clear_bit(WB_has_dirty_io, &wb->state);
- atomic_long_sub(wb->avg_write_bandwidth,
- &wb->bdi->tot_write_bandwidth);
+ WARN_ON_ONCE(atomic_long_sub_return(wb->avg_write_bandwidth,
+ &wb->bdi->tot_write_bandwidth) < 0);
}
}
diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index e1f5f08..4ceda83 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -60,7 +60,7 @@ struct bdi_writeback {
unsigned long dirtied_stamp;
unsigned long written_stamp; /* pages written at bw_time_stamp */
unsigned long write_bandwidth; /* the estimated write bandwidth */
- unsigned long avg_write_bandwidth; /* further smoothed write bw */
+ unsigned long avg_write_bandwidth; /* further smoothed write bw, > 0 */
/*
* The base dirty throttle rate, re-calculated on every 200ms.
@@ -100,7 +100,11 @@ struct backing_dev_info {
unsigned int min_ratio;
unsigned int max_ratio, max_prop_frac;
- atomic_long_t tot_write_bandwidth; /* sum of active avg_write_bw */
+ /*
+ * Sum of avg_write_bw of wbs with dirty inodes. > 0 if there are
+ * any dirty wbs, which is depended upon by bdi_has_dirty().
+ */
+ atomic_long_t tot_write_bandwidth;
struct bdi_writeback wb; /* the root writeback info for this bdi */
#ifdef CONFIG_CGROUP_WRITEBACK
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 533ff86..49feb0b 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -30,7 +30,6 @@ void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
enum wb_reason reason);
void bdi_start_background_writeback(struct backing_dev_info *bdi);
void wb_workfn(struct work_struct *work);
-bool bdi_has_dirty_io(struct backing_dev_info *bdi);
void wb_wakeup_delayed(struct bdi_writeback *wb);
extern spinlock_t bdi_lock;
@@ -43,6 +42,15 @@ static inline bool wb_has_dirty_io(struct bdi_writeback *wb)
return test_bit(WB_has_dirty_io, &wb->state);
}
+static inline bool bdi_has_dirty_io(struct backing_dev_info *bdi)
+{
+ /*
+ * @bdi->tot_write_bandwidth is guaranteed to be > 0 if there are
+ * any dirty wbs. See wb_update_write_bandwidth().
+ */
+ return atomic_long_read(&bdi->tot_write_bandwidth);
+}
+
static inline void __add_wb_stat(struct bdi_writeback *wb,
enum wb_stat_item item, s64 amount)
{
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 9d69e7c..b4a5d9b 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -307,11 +307,6 @@ static int __init default_bdi_init(void)
}
subsys_initcall(default_bdi_init);
-bool bdi_has_dirty_io(struct backing_dev_info *bdi)
-{
- return wb_has_dirty_io(&bdi->wb);
-}
-
/*
* This function is used when the first inode for this wb is marked dirty. It
* wakes-up the corresponding bdi thread which should then take care of the
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 176d0fb..cc0ce70 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -879,9 +879,13 @@ static void wb_update_write_bandwidth(struct bdi_writeback *wb,
avg += (old - avg) >> 3;
out:
- if (wb_has_dirty_io(wb))
- atomic_long_add(avg - wb->avg_write_bandwidth,
- &wb->bdi->tot_write_bandwidth);
+ /* keep avg > 0 to guarantee that tot > 0 if there are dirty wbs */
+ avg = max(avg, 1LU);
+ if (wb_has_dirty_io(wb)) {
+ long delta = avg - wb->avg_write_bandwidth;
+ WARN_ON_ONCE(atomic_long_add_return(delta,
+ &wb->bdi->tot_write_bandwidth) <= 0);
+ }
wb->write_bandwidth = bw;
wb->avg_write_bandwidth = avg;
}
--
2.1.0
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists