summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--fs/fs-writeback.c2
-rw-r--r--include/linux/writeback.h6
-rw-r--r--mm/page-writeback.c74
3 files changed, 79 insertions, 3 deletions
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 5826992..227ff12 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -699,7 +699,7 @@ static inline bool over_bground_thresh(void)
static void wb_update_bandwidth(struct bdi_writeback *wb,
unsigned long start_time)
{
- __bdi_update_bandwidth(wb->bdi, start_time);
+ __bdi_update_bandwidth(wb->bdi, 0, 0, 0, 0, start_time);
}
/*
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 66862f2..e9d371b 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -84,6 +84,8 @@ static inline void laptop_sync_completion(void) { }
#endif
void throttle_vm_writeout(gfp_t gfp_mask);
+extern unsigned long global_dirty_limit;
+
/* These are exported to sysctl. */
extern int dirty_background_ratio;
extern unsigned long dirty_background_bytes;
@@ -119,6 +121,10 @@ unsigned long bdi_dirty_limit(struct backing_dev_info *bdi,
unsigned long dirty);
void __bdi_update_bandwidth(struct backing_dev_info *bdi,
+ unsigned long thresh,
+ unsigned long dirty,
+ unsigned long bdi_thresh,
+ unsigned long bdi_dirty,
unsigned long start_time);
void page_writeback_init(void);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 5f3e1b4..da95995 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -116,6 +116,7 @@ EXPORT_SYMBOL(laptop_mode);
/* End of sysctl-exported parameters */
+unsigned long global_dirty_limit;
/*
* Scale the writeback cache size proportional to the relative writeout speeds.
@@ -516,7 +517,67 @@ out:
bdi->avg_write_bandwidth = avg;
}
+/*
+ * The global dirtyable memory and dirty threshold could be suddenly knocked
+ * down by a large amount (eg. on the startup of KVM in a swapless system).
+ * This may throw the system into deep dirty exceeded state and throttle
+ * heavy/light dirtiers alike. To retain good responsiveness, maintain
+ * global_dirty_limit for tracking slowly down to the knocked down dirty
+ * threshold.
+ */
+static void update_dirty_limit(unsigned long thresh, unsigned long dirty)
+{
+ unsigned long limit = global_dirty_limit;
+
+ /*
+ * Follow up in one step.
+ */
+ if (limit < thresh) {
+ limit = thresh;
+ goto update;
+ }
+
+ /*
+ * Follow down slowly. Use the higher one as the target, because thresh
+ * may drop below dirty. This is exactly the reason to introduce
+ * global_dirty_limit which is guaranteed to lie above the dirty pages.
+ */
+ thresh = max(thresh, dirty);
+ if (limit > thresh) {
+ limit -= (limit - thresh) >> 5;
+ goto update;
+ }
+ return;
+update:
+ global_dirty_limit = limit;
+}
+
+static void global_update_bandwidth(unsigned long thresh,
+ unsigned long dirty,
+ unsigned long now)
+{
+ static DEFINE_SPINLOCK(dirty_lock);
+ static unsigned long update_time;
+
+ /*
+ * check locklessly first to optimize away locking for the most time
+ */
+ if (time_before(now, update_time + BANDWIDTH_INTERVAL))
+ return;
+
+ spin_lock(&dirty_lock);
+ if (time_after_eq(now, update_time + BANDWIDTH_INTERVAL)) {
+ update_dirty_limit(thresh, dirty);
+ update_time = now;
+ }
+ spin_unlock(&dirty_lock);
+}
+
void __bdi_update_bandwidth(struct backing_dev_info *bdi,
+ unsigned long thresh,
+ unsigned long dirty,
+ unsigned long bdi_thresh,
+ unsigned long bdi_dirty,
unsigned long start_time)
{
unsigned long now = jiffies;
@@ -538,6 +599,9 @@ void __bdi_update_bandwidth(struct backing_dev_info *bdi,
if (elapsed > HZ && time_before(bdi->bw_time_stamp, start_time))
goto snapshot;
+ if (thresh)
+ global_update_bandwidth(thresh, dirty, now);
+
bdi_update_write_bandwidth(bdi, elapsed, written);
snapshot:
@@ -546,12 +610,17 @@ snapshot:
}
static void bdi_update_bandwidth(struct backing_dev_info *bdi,
+ unsigned long thresh,
+ unsigned long dirty,
+ unsigned long bdi_thresh,
+ unsigned long bdi_dirty,
unsigned long start_time)
{
if (time_is_after_eq_jiffies(bdi->bw_time_stamp + BANDWIDTH_INTERVAL))
return;
spin_lock(&bdi->wb.list_lock);
- __bdi_update_bandwidth(bdi, start_time);
+ __bdi_update_bandwidth(bdi, thresh, dirty, bdi_thresh, bdi_dirty,
+ start_time);
spin_unlock(&bdi->wb.list_lock);
}
@@ -630,7 +699,8 @@ static void balance_dirty_pages(struct address_space *mapping,
if (!bdi->dirty_exceeded)
bdi->dirty_exceeded = 1;
- bdi_update_bandwidth(bdi, start_time);
+ bdi_update_bandwidth(bdi, dirty_thresh, nr_dirty,
+ bdi_thresh, bdi_dirty, start_time);
/* Note: nr_reclaimable denotes nr_dirty + nr_unstable.
* Unstable writes are a feature of certain networked