Fix congestion_wait() sync/async vs read/write confusion

[safe/jmp/linux-2.6] / mm / page-writeback.c

diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index bb553c3..81627eb 100644 (file)
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -265,18 +265,19 @@ static void bdi_writeout_fraction(struct backing_dev_info *bdi,
  * This avoids exceeding the total dirty_limit when the floating averages
  * fluctuate too quickly.
  */
-static void
-clip_bdi_dirty_limit(struct backing_dev_info *bdi, long dirty, long *pbdi_dirty)
+static void clip_bdi_dirty_limit(struct backing_dev_info *bdi,
+               unsigned long dirty, unsigned long *pbdi_dirty)
 {
-       long avail_dirty;
+       unsigned long avail_dirty;
 
-       avail_dirty = dirty -
-               (global_page_state(NR_FILE_DIRTY) +
+       avail_dirty = global_page_state(NR_FILE_DIRTY) +
                 global_page_state(NR_WRITEBACK) +
                 global_page_state(NR_UNSTABLE_NFS) +
-                global_page_state(NR_WRITEBACK_TEMP));
+                global_page_state(NR_WRITEBACK_TEMP);
 
-       if (avail_dirty < 0)
+       if (avail_dirty < dirty)
+               avail_dirty = dirty - avail_dirty;
+       else
                avail_dirty = 0;
 
        avail_dirty += bdi_stat(bdi, BDI_RECLAIMABLE) +
@@ -299,10 +300,10 @@ static inline void task_dirties_fraction(struct task_struct *tsk,
  *
  *   dirty -= (dirty/8) * p_{t}
  */
-static void task_dirty_limit(struct task_struct *tsk, long *pdirty)
+static void task_dirty_limit(struct task_struct *tsk, unsigned long *pdirty)
 {
        long numerator, denominator;
-       long dirty = *pdirty;
+       unsigned long dirty = *pdirty;
        u64 inv = dirty >> 3;
 
        task_dirties_fraction(tsk, &numerator, &denominator);
@@ -540,8 +541,11 @@ static void balance_dirty_pages(struct address_space *mapping)
                 * filesystems (i.e. NFS) in which data may have been
                 * written to the server's write cache, but has not yet
                 * been flushed to permanent storage.
+                * Only move pages to writeback if this bdi is over its
+                * threshold otherwise wait until the disk writes catch
+                * up.
                 */
-               if (bdi_nr_reclaimable) {
+               if (bdi_nr_reclaimable > bdi_thresh) {
                        writeback_inodes(&wbc);
                        pages_written += write_chunk - wbc.nr_to_write;
                        get_dirty_limits(&background_thresh, &dirty_thresh,
@@ -571,7 +575,7 @@ static void balance_dirty_pages(struct address_space *mapping)
                if (pages_written >= write_chunk)
                        break;          /* We've done our duty */
 
-               congestion_wait(WRITE, HZ/10);
+               congestion_wait(BLK_RW_ASYNC, HZ/10);
        }
 
        if (bdi_nr_reclaimable + bdi_nr_writeback < bdi_thresh &&
@@ -665,7 +669,7 @@ void throttle_vm_writeout(gfp_t gfp_mask)
                 if (global_page_state(NR_UNSTABLE_NFS) +
                        global_page_state(NR_WRITEBACK) <= dirty_thresh)
                                break;
-                congestion_wait(WRITE, HZ/10);
+                congestion_wait(BLK_RW_ASYNC, HZ/10);
 
                /*
                 * The caller might hold locks which can prevent IO completion
@@ -711,7 +715,7 @@ static void background_writeout(unsigned long _min_pages)
                if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) {
                        /* Wrote less than expected */
                        if (wbc.encountered_congestion || wbc.more_io)
-                               congestion_wait(WRITE, HZ/10);
+                               congestion_wait(BLK_RW_ASYNC, HZ/10);
                        else
                                break;
                }
@@ -783,7 +787,7 @@ static void wb_kupdate(unsigned long arg)
                writeback_inodes(&wbc);
                if (wbc.nr_to_write > 0) {
                        if (wbc.encountered_congestion || wbc.more_io)
-                               congestion_wait(WRITE, HZ/10);
+                               congestion_wait(BLK_RW_ASYNC, HZ/10);
                        else
                                break;  /* All the old data is written */
                }