7 files changed, 69 insertions, 14 deletions

diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index 86754eb390da..7cee90223d3a 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -28,6 +28,7 @@ Currently, these files are in /proc/sys/vm:
 - block_dump
 - drop-caches
 - zone_reclaim_mode
+- min_unmapped_ratio
 - panic_on_oom
 
 ==============================================================
@@ -168,6 +169,19 @@ in all nodes of the system.
 
 =============================================================
 
+min_unmapped_ratio:
+
+This is available only on NUMA kernels.
+
+A percentage of the file backed pages in each zone.  Zone reclaim will only
+occur if more than this percentage of pages are file backed and unmapped.
+This is to insure that a minimal amount of local pages is still available for
+file I/O even if the node is overallocated.
+
+The default is 1 percent.
+
+=============================================================
+
 panic_on_oom
 
 This enables or disables panic on out-of-memory feature.  If this is set to 1,
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 27e748eb72b0..656b588a9f96 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -150,6 +150,10 @@ struct zone {
         unsigned long           lowmem_reserve[MAX_NR_ZONES];
 
 #ifdef CONFIG_NUMA
+        /*
+         * zone reclaim becomes active if more unmapped pages exist.
+         */
+        unsigned long           min_unmapped_ratio;
         struct per_cpu_pageset  *pageset[NR_CPUS];
 #else
         struct per_cpu_pageset  pageset[NR_CPUS];
@@ -414,6 +418,8 @@ int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, struct file *,
                                         void __user *, size_t *, loff_t *);
 int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *, int, struct file *,
                                         void __user *, size_t *, loff_t *);
+int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *, int,
+                        struct file *, void __user *, size_t *, loff_t *);
 
 #include <linux/topology.h>
 /* Returns the number of the current Node. */
diff --git a/include/linux/swap.h b/include/linux/swap.h
index cf6ca6e377bd..5e59184c9096 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -189,6 +189,7 @@ extern long vm_total_pages;
 
 #ifdef CONFIG_NUMA
 extern int zone_reclaim_mode;
+extern int sysctl_min_unmapped_ratio;
 extern int zone_reclaim(struct zone *, gfp_t, unsigned int);
 #else
 #define zone_reclaim_mode 0
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 46e4d8f2771f..e4b1a4d4dcf3 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -188,7 +188,7 @@ enum
         VM_DROP_PAGECACHE=29,   /* int: nuke lots of pagecache */
         VM_PERCPU_PAGELIST_FRACTION=30,/* int: fraction of pages in each percpu_pagelist */
         VM_ZONE_RECLAIM_MODE=31, /* reclaim local zone memory before going off node */
-        VM_ZONE_RECLAIM_INTERVAL=32, /* time period to wait after reclaim failure */
+        VM_MIN_UNMAPPED=32,     /* Set min percent of unmapped pages */
         VM_PANIC_ON_OOM=33,     /* panic at out-of-memory */
         VM_VDSO_ENABLED=34,     /* map VDSO into new processes? */
 };
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 99a58f279077..362a0cc37138 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -932,6 +932,17 @@ static ctl_table vm_table[] = {
                 .strategy       = &sysctl_intvec,
                 .extra1         = &zero,
         },
+        {
+                .ctl_name       = VM_MIN_UNMAPPED,
+                .procname       = "min_unmapped_ratio",
+                .data           = &sysctl_min_unmapped_ratio,
+                .maxlen         = sizeof(sysctl_min_unmapped_ratio),
+                .mode           = 0644,
+                .proc_handler   = &sysctl_min_unmapped_ratio_sysctl_handler,
+                .strategy       = &sysctl_intvec,
+                .extra1         = &zero,
+                .extra2         = &one_hundred,
+        },
 #endif
 #ifdef CONFIG_X86_32
         {
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3e792a583f3b..54a4f5375bba 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2005,6 +2005,10 @@ static void __meminit free_area_init_core(struct pglist_data *pgdat,
 
                 zone->spanned_pages = size;
                 zone->present_pages = realsize;
+#ifdef CONFIG_NUMA
+                zone->min_unmapped_ratio = (realsize*sysctl_min_unmapped_ratio)
+                                                / 100;
+#endif
                 zone->name = zone_names[j];
                 spin_lock_init(&zone->lock);
                 spin_lock_init(&zone->lru_lock);
@@ -2298,6 +2302,24 @@ int min_free_kbytes_sysctl_handler(ctl_table *table, int write,
         return 0;
 }
 
+#ifdef CONFIG_NUMA
+int sysctl_min_unmapped_ratio_sysctl_handler(ctl_table *table, int write,
+        struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
+{
+        struct zone *zone;
+        int rc;
+
+        rc = proc_dointvec_minmax(table, write, file, buffer, length, ppos);
+        if (rc)
+                return rc;
+
+        for_each_zone(zone)
+                zone->min_unmapped_ratio = (zone->present_pages *
+                                sysctl_min_unmapped_ratio) / 100;
+        return 0;
+}
+#endif
+
 /*
  * lowmem_reserve_ratio_sysctl_handler - just a wrapper around
  *      proc_dointvec() so that we can call setup_per_zone_lowmem_reserve()
diff --git a/mm/vmscan.c b/mm/vmscan.c
index ff2ebe9458a3..5d4c4d02254d 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1503,10 +1503,6 @@ module_init(kswapd_init)
  *
  * If non-zero call zone_reclaim when the number of free pages falls below
  * the watermarks.
- *
- * In the future we may add flags to the mode. However, the page allocator
- * should only have to check that zone_reclaim_mode != 0 before calling
- * zone_reclaim().
  */
 int zone_reclaim_mode __read_mostly;
 
@@ -1524,6 +1520,12 @@ int zone_reclaim_mode __read_mostly;
 #define ZONE_RECLAIM_PRIORITY 4
 
 /*
+ * Percentage of pages in a zone that must be unmapped for zone_reclaim to
+ * occur.
+ */
+int sysctl_min_unmapped_ratio = 1;
+
+/*
  * Try to free up some pages from this zone through reclaim.
  */
 static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
@@ -1590,18 +1592,17 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
         int node_id;
 
         /*
-         * Do not reclaim if there are not enough reclaimable pages in this
-         * zone that would satify this allocations.
+         * Zone reclaim reclaims unmapped file backed pages.
          *
-         * All unmapped pagecache pages are reclaimable.
-         *
-         * Both counters may be temporarily off a bit so we use
-         * SWAP_CLUSTER_MAX as the boundary. It may also be good to
-         * leave a few frequently used unmapped pagecache pages around.
+         * A small portion of unmapped file backed pages is needed for
+         * file I/O otherwise pages read by file I/O will be immediately
+         * thrown out if the zone is overallocated. So we do not reclaim
+         * if less than a specified percentage of the zone is used by
+         * unmapped file backed pages.
          */
         if (zone_page_state(zone, NR_FILE_PAGES) -
-                zone_page_state(zone, NR_FILE_MAPPED) < SWAP_CLUSTER_MAX)
-                        return 0;
+            zone_page_state(zone, NR_FILE_MAPPED) <= zone->min_unmapped_ratio)
+                return 0;
 
         /*
          * Avoid concurrent zone reclaims, do not reclaim in a zone that does