diff options
| -rw-r--r-- | include/linux/backing-dev-defs.h | 1 | ||||
| -rw-r--r-- | include/linux/writeback.h | 1 | ||||
| -rw-r--r-- | mm/backing-dev.c | 10 | ||||
| -rw-r--r-- | mm/page-writeback.c | 39 |
4 files changed, 37 insertions, 14 deletions
diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index 06fb8e13f6bc..33207004cfde 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -143,6 +143,7 @@ struct bdi_writeback { spinlock_t work_lock; /* protects work_list & dwork scheduling */ struct list_head work_list; struct delayed_work dwork; /* work item used for writeback */ + struct delayed_work bw_dwork; /* work item used for bandwidth estimate */ unsigned long dirty_sleep; /* last wait */ diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 2480322c06a7..cbaef099645e 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -379,6 +379,7 @@ int dirty_writeback_centisecs_handler(struct ctl_table *table, int write, void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty); unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh); +void wb_update_bandwidth(struct bdi_writeback *wb); void balance_dirty_pages_ratelimited(struct address_space *mapping); bool wb_over_bg_thresh(struct bdi_writeback *wb); diff --git a/mm/backing-dev.c b/mm/backing-dev.c index b4c707ddedb1..6122c78ce914 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -271,6 +271,14 @@ void wb_wakeup_delayed(struct bdi_writeback *wb) spin_unlock_bh(&wb->work_lock); } +static void wb_update_bandwidth_workfn(struct work_struct *work) +{ + struct bdi_writeback *wb = container_of(to_delayed_work(work), + struct bdi_writeback, bw_dwork); + + wb_update_bandwidth(wb); +} + /* * Initial write bandwidth: 100 MB/s */ @@ -303,6 +311,7 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi, spin_lock_init(&wb->work_lock); INIT_LIST_HEAD(&wb->work_list); INIT_DELAYED_WORK(&wb->dwork, wb_workfn); + INIT_DELAYED_WORK(&wb->bw_dwork, wb_update_bandwidth_workfn); wb->dirty_sleep = jiffies; err = fprop_local_init_percpu(&wb->completions, gfp); @@ -351,6 +360,7 @@ static void wb_shutdown(struct bdi_writeback *wb) mod_delayed_work(bdi_wq, &wb->dwork, 0); flush_delayed_work(&wb->dwork); WARN_ON(!list_empty(&wb->work_list)); + flush_delayed_work(&wb->bw_dwork); } static void wb_exit(struct bdi_writeback *wb) diff --git a/mm/page-writeback.c b/mm/page-writeback.c index e4a381b8944b..156f5888c09d 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1336,18 +1336,19 @@ static void __wb_update_bandwidth(struct dirty_throttle_control *gdtc, { struct bdi_writeback *wb = gdtc->wb; unsigned long now = jiffies; - unsigned long elapsed = now - wb->bw_time_stamp; + unsigned long elapsed; unsigned long dirtied; unsigned long written; - lockdep_assert_held(&wb->list_lock); + spin_lock(&wb->list_lock); /* - * rate-limit, only update once every 200ms. + * Lockless checks for elapsed time are racy and delayed update after + * IO completion doesn't do it at all (to make sure written pages are + * accounted reasonably quickly). Make sure elapsed >= 1 to avoid + * division errors. */ - if (elapsed < BANDWIDTH_INTERVAL) - return; - + elapsed = max(now - wb->bw_time_stamp, 1UL); dirtied = percpu_counter_read(&wb->stat[WB_DIRTIED]); written = percpu_counter_read(&wb->stat[WB_WRITTEN]); @@ -1369,15 +1370,14 @@ static void __wb_update_bandwidth(struct dirty_throttle_control *gdtc, wb->dirtied_stamp = dirtied; wb->written_stamp = written; wb->bw_time_stamp = now; + spin_unlock(&wb->list_lock); } -static void wb_update_bandwidth(struct bdi_writeback *wb) +void wb_update_bandwidth(struct bdi_writeback *wb) { struct dirty_throttle_control gdtc = { GDTC_INIT(wb) }; - spin_lock(&wb->list_lock); __wb_update_bandwidth(&gdtc, NULL, false); - spin_unlock(&wb->list_lock); } /* Interval after which we consider wb idle and don't estimate bandwidth */ @@ -1722,11 +1722,8 @@ free_running: wb->dirty_exceeded = 1; if (time_is_before_jiffies(wb->bw_time_stamp + - BANDWIDTH_INTERVAL)) { - spin_lock(&wb->list_lock); + BANDWIDTH_INTERVAL)) __wb_update_bandwidth(gdtc, mdtc, true); - spin_unlock(&wb->list_lock); - } /* throttle according to the chosen dtc */ dirty_ratelimit = wb->dirty_ratelimit; @@ -2374,7 +2371,13 @@ int do_writepages(struct address_space *mapping, struct writeback_control *wbc) cond_resched(); congestion_wait(BLK_RW_ASYNC, HZ/50); } - wb_update_bandwidth(wb); + /* + * Usually few pages are written by now from those we've just submitted + * but if there's constant writeback being submitted, this makes sure + * writeback bandwidth is updated once in a while. + */ + if (time_is_before_jiffies(wb->bw_time_stamp + BANDWIDTH_INTERVAL)) + wb_update_bandwidth(wb); return ret; } @@ -2754,6 +2757,14 @@ static void wb_inode_writeback_start(struct bdi_writeback *wb) static void wb_inode_writeback_end(struct bdi_writeback *wb) { atomic_dec(&wb->writeback_inodes); + /* + * Make sure estimate of writeback throughput gets updated after + * writeback completed. We delay the update by BANDWIDTH_INTERVAL + * (which is the interval other bandwidth updates use for batching) so + * that if multiple inodes end writeback at a similar time, they get + * batched into one bandwidth update. + */ + queue_delayed_work(bdi_wq, &wb->bw_dwork, BANDWIDTH_INTERVAL); } int test_clear_page_writeback(struct page *page) |