It makes no sense for vm_page_sleep_if_busy()'s helper, vm_page_sleep(),

to unconditionally set PG_REFERENCED on a page before sleeping.  In many
cases, it's perfectly ok for the page to disappear, i.e., be reclaimed by
the page daemon, before the caller to vm_page_sleep() is reawakened.
Instead, we now explicitly set PG_REFERENCED in those cases where having
the page persist until the caller is awakened is clearly desirable.  Note,
however, that setting PG_REFERENCED on the page is still only a hint,
and not a guarantee that the page should persist.

1 files changed, 10 insertions, 1 deletions

diff --git a/sys/kern/vfs_bio.c b/sys/kern/vfs_bio.c
index ea846a5..dbcd6e8 100644
--- a/sys/kern/vfs_bio.c
+++ b/sys/kern/vfs_bio.c
@@ -3024,8 +3024,17 @@ allocbuf(struct buf *bp, int size)
 				 *  vm_fault->getpages->cluster_read->allocbuf
 				 *
 				 */
-				if (vm_page_sleep_if_busy(m, FALSE, "pgtblk"))
+				if ((m->oflags & VPO_BUSY) != 0) {
+					/*
+					 * Reference the page before unlocking
+					 * and sleeping so that the page daemon
+					 * is less likely to reclaim it.  
+					 */
+					vm_page_lock_queues();
+					vm_page_flag_set(m, PG_REFERENCED);
+					vm_page_sleep(m, "pgtblk");
 					continue;
+				}
 
 				/*
 				 * We have a good page.