add extra free kbytes tunable

Add a userspace visible knob to tell the VM to keep an extra amount
of memory free, by increasing the gap between each zone's min and
low watermarks.

This is useful for realtime applications that call system
calls and have a bound on the number of allocations that happen
in any short time period.  In this application, extra_free_kbytes
would be left at an amount equal to or larger than than the
maximum number of allocations that happen in any burst.

It may also be useful to reduce the memory use of virtual
machines (temporarily?), in a way that does not cause memory
fragmentation like ballooning does.

[ccross]
Revived for use on old kernels where no other solution exists.
The tunable will be removed on kernels that do better at avoiding
direct reclaim.

Change-Id: I765a42be8e964bfd3e2886d1ca85a29d60c3bb3e
Signed-off-by: Rik van Riel<riel@redhat.com>
Signed-off-by: Colin Cross <ccross@android.com>

1 files changed, 25 insertions, 7 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 348ca037b05..2be8811e57f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -204,10 +204,22 @@ static char * const zone_names[MAX_NR_ZONES] = {
 	 "Movable",
 };
 
+/*
+ * Try to keep at least this much lowmem free.  Do not allow normal
+ * allocations below this point, only high priority ones. Automatically
+ * tuned according to the amount of memory in the system.
+ */
 int min_free_kbytes = 1024;
 int user_min_free_kbytes = -1;
 int min_free_order_shift = 1;
 
+/*
+ * Extra memory for the system to try freeing. Used to temporarily
+ * free memory, to make space for new workloads. Anyone can allocate
+ * down to the min watermarks controlled by min_free_kbytes above.
+ */
+int extra_free_kbytes = 0;
+
 static unsigned long __meminitdata nr_kernel_pages;
 static unsigned long __meminitdata nr_all_pages;
 static unsigned long __meminitdata dma_reserve;
@@ -5605,6 +5617,7 @@ static void setup_per_zone_lowmem_reserve(void)
 static void __setup_per_zone_wmarks(void)
 {
 	unsigned long pages_min = min_free_kbytes >> (PAGE_SHIFT - 10);
+	unsigned long pages_low = extra_free_kbytes >> (PAGE_SHIFT - 10);
 	unsigned long lowmem_pages = 0;
 	struct zone *zone;
 	unsigned long flags;
@@ -5616,11 +5629,14 @@ static void __setup_per_zone_wmarks(void)
 	}
 
 	for_each_zone(zone) {
-		u64 tmp;
+		u64 min, low;
 
 		spin_lock_irqsave(&zone->lock, flags);
-		tmp = (u64)pages_min * zone->managed_pages;
-		do_div(tmp, lowmem_pages);
+		min = (u64)pages_min * zone->managed_pages;
+		do_div(min, lowmem_pages);
+		low = (u64)pages_low * zone->managed_pages;
+		do_div(low, vm_total_pages);
+
 		if (is_highmem(zone)) {
 			/*
 			 * __GFP_HIGH and PF_MEMALLOC allocations usually don't
@@ -5641,11 +5657,13 @@ static void __setup_per_zone_wmarks(void)
 			 * If it's a lowmem zone, reserve a number of pages
 			 * proportionate to the zone's size.
 			 */
-			zone->watermark[WMARK_MIN] = tmp;
+			zone->watermark[WMARK_MIN] = min;
 		}
 
-		zone->watermark[WMARK_LOW]  = min_wmark_pages(zone) + (tmp >> 2);
-		zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1);
+		zone->watermark[WMARK_LOW]  = min_wmark_pages(zone) +
+					low + (min >> 2);
+		zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) +
+					low + (min >> 1);
 
 		__mod_zone_page_state(zone, NR_ALLOC_BATCH,
 				      high_wmark_pages(zone) -
@@ -5770,7 +5788,7 @@ module_init(init_per_zone_wmark_min)
 /*
  * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so
  *	that we can call two helper functions whenever min_free_kbytes
- *	changes.
+ *	or extra_free_kbytes changes.
  */
 int min_free_kbytes_sysctl_handler(ctl_table *table, int write,
 	void __user *buffer, size_t *length, loff_t *ppos)