aboutsummaryrefslogtreecommitdiffstats
path: root/include/linux
diff options
context:
space:
mode:
authorWu Fengguang <fengguang.wu@intel.com>2010-08-29 13:22:30 -0400
committerWu Fengguang <fengguang.wu@intel.com>2011-07-10 01:09:01 -0400
commite98be2d599207c6b31e9bb340d52a231b2f3662d (patch)
tree3ae28e7d621a6e2ddf8e7462f8d282901c113d5c /include/linux
parentf7d2b1ecd0c714adefc7d3a942ef87beb828a763 (diff)
writeback: bdi write bandwidth estimation
The estimation value will start from 100MB/s and adapt to the real bandwidth in seconds. It tries to update the bandwidth only when disk is fully utilized. Any inactive period of more than one second will be skipped. The estimated bandwidth will be reflecting how fast the device can writeout when _fully utilized_, and won't drop to 0 when it goes idle. The value will remain constant at disk idle time. At busy write time, if not considering fluctuations, it will also remain high unless be knocked down by possible concurrent reads that compete for the disk time and bandwidth with async writes. The estimation is not done purely in the flusher because there is no guarantee for write_cache_pages() to return timely to update bandwidth. The bdi->avg_write_bandwidth smoothing is very effective for filtering out sudden spikes, however may be a little biased in long term. The overheads are low because the bdi bandwidth update only occurs at 200ms intervals. The 200ms update interval is suitable, because it's not possible to get the real bandwidth for the instance at all, due to large fluctuations. The NFS commits can be as large as seconds worth of data. One XFS completion may be as large as half second worth of data if we are going to increase the write chunk to half second worth of data. In ext4, fluctuations with time period of around 5 seconds is observed. And there is another pattern of irregular periods of up to 20 seconds on SSD tests. That's why we are not only doing the estimation at 200ms intervals, but also averaging them over a period of 3 seconds and then go further to do another level of smoothing in avg_write_bandwidth. CC: Li Shaohua <shaohua.li@intel.com> CC: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Diffstat (limited to 'include/linux')
-rw-r--r--include/linux/backing-dev.h5
-rw-r--r--include/linux/writeback.h3
2 files changed, 8 insertions, 0 deletions
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 469d56443c63..a008982e7c08 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -73,6 +73,11 @@ struct backing_dev_info {
73 73
74 struct percpu_counter bdi_stat[NR_BDI_STAT_ITEMS]; 74 struct percpu_counter bdi_stat[NR_BDI_STAT_ITEMS];
75 75
76 unsigned long bw_time_stamp; /* last time write bw is updated */
77 unsigned long written_stamp; /* pages written at bw_time_stamp */
78 unsigned long write_bandwidth; /* the estimated write bandwidth */
79 unsigned long avg_write_bandwidth; /* further smoothed write bw */
80
76 struct prop_local_percpu completions; 81 struct prop_local_percpu completions;
77 int dirty_exceeded; 82 int dirty_exceeded;
78 83
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index df1b7f18f100..66862f2d90c8 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -118,6 +118,9 @@ void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty);
118unsigned long bdi_dirty_limit(struct backing_dev_info *bdi, 118unsigned long bdi_dirty_limit(struct backing_dev_info *bdi,
119 unsigned long dirty); 119 unsigned long dirty);
120 120
121void __bdi_update_bandwidth(struct backing_dev_info *bdi,
122 unsigned long start_time);
123
121void page_writeback_init(void); 124void page_writeback_init(void);
122void balance_dirty_pages_ratelimited_nr(struct address_space *mapping, 125void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
123 unsigned long nr_pages_dirtied); 126 unsigned long nr_pages_dirtied);