vmscan: fix a livelock in kswapd

[linux-flexiantxendom0-natty.git] / mm / vmscan.c

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 136dc5e..1e0eefe 100644 (file)
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2245,7 +2245,8 @@ static bool pgdat_balanced(pg_data_t *pgdat, unsigned long balanced_pages,
        for (i = 0; i <= classzone_idx; i++)
                present_pages += pgdat->node_zones[i].present_pages;
 
-       return balanced_pages > (present_pages >> 2);
+       /* A special case here: if zone has no page, we think it's balanced */
+       return balanced_pages >= (present_pages >> 2);
 }
 
 /* is kswapd sleeping prematurely? */
@@ -2381,7 +2382,6 @@ loop_again:
                        if (!zone_watermark_ok_safe(zone, order,
                                        high_wmark_pages(zone), 0, 0)) {
                                end_zone = i;
-                               *classzone_idx = i;
                                break;
                        }
                }
@@ -2458,8 +2458,11 @@ loop_again:
                            total_scanned > sc.nr_reclaimed + sc.nr_reclaimed / 2)
                                sc.may_writepage = 1;
 
-                       if (zone->all_unreclaimable)
+                       if (zone->all_unreclaimable) {
+                               if (end_zone && end_zone == i)
+                                       end_zone--;
                                continue;
+                       }
 
                        if (!zone_watermark_ok_safe(zone, order,
                                        high_wmark_pages(zone), end_zone, 0)) {
@@ -2639,8 +2642,8 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx)
  */
 static int kswapd(void *p)
 {
-       unsigned long order;
-       int classzone_idx;
+       unsigned long order, new_order;
+       int classzone_idx, new_classzone_idx;
        pg_data_t *pgdat = (pg_data_t*)p;
        struct task_struct *tsk = current;
 
@@ -2670,17 +2673,23 @@ static int kswapd(void *p)
        tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;
        set_freezable();
 
-       order = 0;
-       classzone_idx = MAX_NR_ZONES - 1;
+       order = new_order = 0;
+       classzone_idx = new_classzone_idx = pgdat->nr_zones - 1;
        for ( ; ; ) {
-               unsigned long new_order;
-               int new_classzone_idx;
                int ret;
 
-               new_order = pgdat->kswapd_max_order;
-               new_classzone_idx = pgdat->classzone_idx;
-               pgdat->kswapd_max_order = 0;
-               pgdat->classzone_idx = MAX_NR_ZONES - 1;
+               /*
+                * If the last balance_pgdat was unsuccessful it's unlikely a
+                * new request of a similar or harder type will succeed soon
+                * so consider going to sleep on the basis we reclaimed at
+                */
+               if (classzone_idx >= new_classzone_idx && order == new_order) {
+                       new_order = pgdat->kswapd_max_order;
+                       new_classzone_idx = pgdat->classzone_idx;
+                       pgdat->kswapd_max_order =  0;
+                       pgdat->classzone_idx = pgdat->nr_zones - 1;
+               }
+
                if (order < new_order || classzone_idx > new_classzone_idx) {
                        /*
                         * Don't sleep if someone wants a larger 'order'
@@ -2693,7 +2702,7 @@ static int kswapd(void *p)
                        order = pgdat->kswapd_max_order;
                        classzone_idx = pgdat->classzone_idx;
                        pgdat->kswapd_max_order = 0;
-                       pgdat->classzone_idx = MAX_NR_ZONES - 1;
+                       pgdat->classzone_idx = pgdat->nr_zones - 1;
                }
 
                ret = try_to_freeze();