writeback: implement backing_dev_info->tot_write_bandwidth

cgroup writeback support needs to keep track of the sum of
avg_write_bandwidth of all wb's (bdi_writeback's) with dirty inodes to
distribute write workload.  This patch adds bdi->tot_write_bandwidth
and updates inode_wb_list_move_locked(), inode_wb_list_del_locked()
and wb_update_write_bandwidth() to adjust it as wb's gain and lose
dirty inodes and its avg_write_bandwidth gets updated.

As the update events are not synchronized with each other,
bdi->tot_write_bandwidth is an atomic_long_t.

Signed-off-by: Tejun Heo <[email protected]>
Cc: Jens Axboe <[email protected]>
Cc: Jan Kara <[email protected]>
Signed-off-by: Jens Axboe <[email protected]>

Author: htejun

fs/fs-writeback.c

@@ -99,15 +99,20 @@ static bool wb_io_lists_populated(struct bdi_writeback *wb)
 		return false;
 	} else {
 		set_bit(WB_has_dirty_io, &wb->state);
+		atomic_long_add(wb->avg_write_bandwidth,
+				&wb->bdi->tot_write_bandwidth);
 		return true;
 	}
 }
 
 static void wb_io_lists_depopulated(struct bdi_writeback *wb)
 {
 	if (wb_has_dirty_io(wb) && list_empty(&wb->b_dirty) &&
-	    list_empty(&wb->b_io) && list_empty(&wb->b_more_io))
+	    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);
+	}
 }
 
 /**

include/linux/backing-dev-defs.h

@@ -142,6 +142,8 @@ 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 */
+
 	struct bdi_writeback wb;  /* the root writeback info for this bdi */
 	struct bdi_writeback_congested wb_congested; /* its congested state */
 #ifdef CONFIG_CGROUP_WRITEBACK

mm/page-writeback.c

@@ -881,6 +881,9 @@ 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);
 	wb->write_bandwidth = bw;
 	wb->avg_write_bandwidth = avg;
 }