From: mel@skynet.ie (Mel Gorman)

kswapd normally reclaims at order 0 unless there is a higher-order allocation
currently being serviced.  However, in some cases it is known that there is a
minimum order size that is generally required such as when SLUB is configured
to use higher orders for performance reasons.  This patch allows a minumum
order to be set, such that min_free_kbytes pages are kept at higher orders. 
This depends on lumpy-reclaim to work.

[clameter@sgi.com: Call raise_kswapd_order() on kmem_cache_open()]
Acked-by: Andy Whitcroft <apw@shadowen.org>
Acked-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 include/linux/mmzone.h |    1 +
 mm/slub.c              |    1 +
 mm/vmscan.c            |   34 +++++++++++++++++++++++++++++++---
 3 files changed, 33 insertions(+), 3 deletions(-)

diff -puN include/linux/mmzone.h~have-kswapd-keep-a-minimum-order-free-other-than-order-0 include/linux/mmzone.h
--- a/include/linux/mmzone.h~have-kswapd-keep-a-minimum-order-free-other-than-order-0
+++ a/include/linux/mmzone.h
@@ -507,6 +507,7 @@ typedef struct pglist_data {
 void get_zone_counts(unsigned long *active, unsigned long *inactive,
 			unsigned long *free);
 void build_all_zonelists(void);
+void raise_kswapd_order(unsigned int order);
 void wakeup_kswapd(struct zone *zone, int order);
 int zone_watermark_ok(struct zone *z, int order, unsigned long mark,
 		int classzone_idx, int alloc_flags);
diff -puN mm/slub.c~have-kswapd-keep-a-minimum-order-free-other-than-order-0 mm/slub.c
--- a/mm/slub.c~have-kswapd-keep-a-minimum-order-free-other-than-order-0
+++ a/mm/slub.c
@@ -2031,6 +2031,7 @@ static int kmem_cache_open(struct kmem_c
 #ifdef CONFIG_NUMA
 	s->defrag_ratio = 100;
 #endif
+	raise_kswapd_order(s->order);
 
 	if (init_kmem_cache_nodes(s, gfpflags & ~SLUB_DMA))
 		return 1;
diff -puN mm/vmscan.c~have-kswapd-keep-a-minimum-order-free-other-than-order-0 mm/vmscan.c
--- a/mm/vmscan.c~have-kswapd-keep-a-minimum-order-free-other-than-order-0
+++ a/mm/vmscan.c
@@ -1402,6 +1402,34 @@ out:
 	return nr_reclaimed;
 }
 
+static unsigned int kswapd_min_order __read_mostly;
+
+static inline int kswapd_order(unsigned int order)
+{
+	return max(kswapd_min_order, order);
+}
+
+/**
+ * raise_kswapd_order - Raise the minimum order that kswapd reclaims
+ * @order: The minimum order kswapd should reclaim at
+ *
+ * kswapd normally reclaims at order 0 unless there is a higher-order
+ * allocation being serviced. This function is used to set the minimum
+ * order that kswapd reclaims at when it is known there will be regular
+ * high-order allocations at a given order.
+ */
+void raise_kswapd_order(unsigned int order)
+{
+	if (order >= MAX_ORDER)
+		return;
+
+	/* Update order if necessary and inform if changed */
+	if (order > kswapd_min_order) {
+		kswapd_min_order = order;
+		printk(KERN_INFO "kswapd reclaim order set to %d\n", order);
+	}
+}
+
 /*
  * The background pageout daemon, started as a kernel thread
  * from the init process. 
@@ -1445,12 +1473,12 @@ static int kswapd(void *p)
 	 */
 	tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;
 
-	order = 0;
+	order = kswapd_order(0);
 	for ( ; ; ) {
 		unsigned long new_order;
 
 		prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
-		new_order = pgdat->kswapd_max_order;
+		new_order = kswapd_order(pgdat->kswapd_max_order);
 		pgdat->kswapd_max_order = 0;
 		if (order < new_order) {
 			/*
@@ -1462,7 +1490,7 @@ static int kswapd(void *p)
 			if (!freezing(current))
 				schedule();
 
-			order = pgdat->kswapd_max_order;
+			order = kswapd_order(pgdat->kswapd_max_order);
 		}
 		finish_wait(&pgdat->kswapd_wait, &wait);
 
_