[PATCH 10/14] Add /sys trigger for per-node memory compaction

[Mel Gorman]

This patch adds a per-node sysfs file called compact. When the file is
written to, each zone in that node is compacted. The intention that this
would be used by something like a job scheduler in a batch system before
a job starts so that the job can allocate the maximum number of
hugepages without significant start-up cost.

Signed-off-by: Mel Gorman <mel@xxxxxxxxx>
Acked-by: Rik van Riel <riel@xxxxxxxxxx>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
Reviewed-by: Christoph Lameter <cl@xxxxxxxxxxxxxxxxxxxx>
Reviewed-by: Minchan Kim <minchan.kim@xxxxxxxxx>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
---
 Documentation/ABI/testing/sysfs-devices-node |    7 +++++++
 drivers/base/node.c                          |    3 +++
 include/linux/compaction.h                   |   16 ++++++++++++++++
 mm/compaction.c                              |   23 +++++++++++++++++++++++
 4 files changed, 49 insertions(+), 0 deletions(-)
 create mode 100644 Documentation/ABI/testing/sysfs-devices-node

diff --git a/Documentation/ABI/testing/sysfs-devices-node b/Documentation/ABI/testing/sysfs-devices-node
new file mode 100644
index 0000000..453a210
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-devices-node
@@ -0,0 +1,7 @@
+What:		/sys/devices/system/node/nodeX/compact
+Date:		February 2010
+Contact:	Mel Gorman <mel@xxxxxxxxx>
+Description:
+		When this file is written to, all memory within that node
+		will be compacted. When it completes, memory will be freed
+		into blocks which have as many contiguous pages as possible
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 93b3ac6..07cdcc6 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -15,6 +15,7 @@
 #include <linux/cpu.h>
 #include <linux/device.h>
 #include <linux/swap.h>
+#include <linux/compaction.h>
 
 static struct sysdev_class_attribute *node_state_attrs[];
 
@@ -245,6 +246,8 @@ int register_node(struct node *node, int num, struct node *parent)
 		scan_unevictable_register_node(node);
 
 		hugetlb_register_node(node);
+
+		compaction_register_node(node);
 	}
 	return error;
 }
diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index fef591b..c4ab05f 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -12,4 +12,20 @@ extern int sysctl_compaction_handler(struct ctl_table *table, int write,
 			void __user *buffer, size_t *length, loff_t *ppos);
 #endif /* CONFIG_COMPACTION */
 
+#if defined(CONFIG_COMPACTION) && defined(CONFIG_SYSFS) && defined(CONFIG_NUMA)
+extern int compaction_register_node(struct node *node);
+extern void compaction_unregister_node(struct node *node);
+
+#else
+
+static inline int compaction_register_node(struct node *node)
+{
+	return 0;
+}
+
+static inline void compaction_unregister_node(struct node *node)
+{
+}
+#endif /* CONFIG_COMPACTION && CONFIG_SYSFS && CONFIG_NUMA */
+
 #endif /* _LINUX_COMPACTION_H */
diff --git a/mm/compaction.c b/mm/compaction.c
index 615b811..b058bae 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -13,6 +13,7 @@
 #include <linux/mm_inline.h>
 #include <linux/backing-dev.h>
 #include <linux/sysctl.h>
+#include <linux/sysfs.h>
 #include "internal.h"
 
 /*
@@ -437,3 +438,25 @@ int sysctl_compaction_handler(struct ctl_table *table, int write,
 
 	return 0;
 }
+
+#if defined(CONFIG_SYSFS) && defined(CONFIG_NUMA)
+ssize_t sysfs_compact_node(struct sys_device *dev,
+			struct sysdev_attribute *attr,
+			const char *buf, size_t count)
+{
+	compact_node(dev->id);
+
+	return count;
+}
+static SYSDEV_ATTR(compact, S_IWUSR, NULL, sysfs_compact_node);
+
+int compaction_register_node(struct node *node)
+{
+	return sysdev_create_file(&node->sysdev, &attr_compact);
+}
+
+void compaction_unregister_node(struct node *node)
+{
+	return sysdev_remove_file(&node->sysdev, &attr_compact);
+}
+#endif /* CONFIG_SYSFS && CONFIG_NUMA */
-- 
1.6.5

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/