summaryrefslogtreecommitdiffstats
path: root/mm/backing-dev.c
diff options
context:
space:
mode:
authorMel Gorman <mel@csn.ul.ie>2010-10-26 14:21:45 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2010-10-26 16:52:07 -0700
commit0e093d99763eb4cea09f8ca4f1d01f34e121d10b (patch)
treefad38f9c3651c81db298521141a79d9468f71986 /mm/backing-dev.c
parent08fc468f4eaf6683bae5bdb94743a09d8630cb80 (diff)
downloadlinux-0e093d99763eb4cea09f8ca4f1d01f34e121d10b.tar.gz
linux-0e093d99763eb4cea09f8ca4f1d01f34e121d10b.tar.bz2
linux-0e093d99763eb4cea09f8ca4f1d01f34e121d10b.zip
writeback: do not sleep on the congestion queue if there are no congested BDIs or if significant congestion is not being encountered in the current zone
If congestion_wait() is called with no BDI congested, the caller will sleep for the full timeout and this may be an unnecessary sleep. This patch adds a wait_iff_congested() that checks congestion and only sleeps if a BDI is congested else, it calls cond_resched() to ensure the caller is not hogging the CPU longer than its quota but otherwise will not sleep. This is aimed at reducing some of the major desktop stalls reported during IO. For example, while kswapd is operating, it calls congestion_wait() but it could just have been reclaiming clean page cache pages with no congestion. Without this patch, it would sleep for a full timeout but after this patch, it'll just call schedule() if it has been on the CPU too long. Similar logic applies to direct reclaimers that are not making enough progress. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Rik van Riel <riel@redhat.com> Cc: Jens Axboe <axboe@kernel.dk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/backing-dev.c')
-rw-r--r--mm/backing-dev.c61
1 files changed, 59 insertions, 2 deletions
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 55627306abe0..5ad3c106606b 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -729,6 +729,7 @@ static wait_queue_head_t congestion_wqh[2] = {
__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]),
__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1])
};
+static atomic_t nr_bdi_congested[2];
void clear_bdi_congested(struct backing_dev_info *bdi, int sync)
{
@@ -736,7 +737,8 @@ void clear_bdi_congested(struct backing_dev_info *bdi, int sync)
wait_queue_head_t *wqh = &congestion_wqh[sync];
bit = sync ? BDI_sync_congested : BDI_async_congested;
- clear_bit(bit, &bdi->state);
+ if (test_and_clear_bit(bit, &bdi->state))
+ atomic_dec(&nr_bdi_congested[sync]);
smp_mb__after_clear_bit();
if (waitqueue_active(wqh))
wake_up(wqh);
@@ -748,7 +750,8 @@ void set_bdi_congested(struct backing_dev_info *bdi, int sync)
enum bdi_state bit;
bit = sync ? BDI_sync_congested : BDI_async_congested;
- set_bit(bit, &bdi->state);
+ if (!test_and_set_bit(bit, &bdi->state))
+ atomic_inc(&nr_bdi_congested[sync]);
}
EXPORT_SYMBOL(set_bdi_congested);
@@ -779,3 +782,57 @@ long congestion_wait(int sync, long timeout)
}
EXPORT_SYMBOL(congestion_wait);
+/**
+ * wait_iff_congested - Conditionally wait for a backing_dev to become uncongested or a zone to complete writes
+ * @zone: A zone to check if it is heavily congested
+ * @sync: SYNC or ASYNC IO
+ * @timeout: timeout in jiffies
+ *
+ * In the event of a congested backing_dev (any backing_dev) and the given
+ * @zone has experienced recent congestion, this waits for up to @timeout
+ * jiffies for either a BDI to exit congestion of the given @sync queue
+ * or a write to complete.
+ *
+ * In the absense of zone congestion, cond_resched() is called to yield
+ * the processor if necessary but otherwise does not sleep.
+ *
+ * The return value is 0 if the sleep is for the full timeout. Otherwise,
+ * it is the number of jiffies that were still remaining when the function
+ * returned. return_value == timeout implies the function did not sleep.
+ */
+long wait_iff_congested(struct zone *zone, int sync, long timeout)
+{
+ long ret;
+ unsigned long start = jiffies;
+ DEFINE_WAIT(wait);
+ wait_queue_head_t *wqh = &congestion_wqh[sync];
+
+ /*
+ * If there is no congestion, or heavy congestion is not being
+ * encountered in the current zone, yield if necessary instead
+ * of sleeping on the congestion queue
+ */
+ if (atomic_read(&nr_bdi_congested[sync]) == 0 ||
+ !zone_is_reclaim_congested(zone)) {
+ cond_resched();
+
+ /* In case we scheduled, work out time remaining */
+ ret = timeout - (jiffies - start);
+ if (ret < 0)
+ ret = 0;
+
+ goto out;
+ }
+
+ /* Sleep until uncongested or a write happens */
+ prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
+ ret = io_schedule_timeout(timeout);
+ finish_wait(wqh, &wait);
+
+out:
+ trace_writeback_wait_iff_congested(jiffies_to_usecs(timeout),
+ jiffies_to_usecs(jiffies - start));
+
+ return ret;
+}
+EXPORT_SYMBOL(wait_iff_congested);