[PATCH] drop-pagecache

Add /proc/sys/vm/drop_caches.  When written to, this will cause the kernel to
discard as much pagecache and/or reclaimable slab objects as it can.  THis
operation requires root permissions.

It won't drop dirty data, so the user should run `sync' first.

Caveats:

a) Holds inode_lock for exorbitant amounts of time.

b) Needs to be taught about NUMA nodes: propagate these all the way through
   so the discarding can be controlled on a per-node basis.

This is a debugging feature: useful for getting consistent results between
filesystem benchmarks.  We could possibly put it under a config option, but
it's less than 300 bytes.

Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

2 files changed, 69 insertions, 1 deletions

diff --git a/fs/Makefile b/fs/Makefile
index 73676111ebbe..35e9aec608e4 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -10,7 +10,7 @@ obj-y :=	open.o read_write.o file_table.o buffer.o  bio.o super.o \
                 ioctl.o readdir.o select.o fifo.o locks.o dcache.o inode.o \
                 attr.o bad_inode.o file.o filesystems.o namespace.o aio.o \
                 seq_file.o xattr.o libfs.o fs-writeback.o mpage.o direct-io.o \
-                ioprio.o pnode.o
+                ioprio.o pnode.o drop_caches.o
 
 obj-$(CONFIG_INOTIFY)           += inotify.o
 obj-$(CONFIG_EPOLL)             += eventpoll.o
diff --git a/fs/drop_caches.c b/fs/drop_caches.c
new file mode 100644
index 000000000000..4e4762389bdc
--- /dev/null
+++ b/fs/drop_caches.c
@@ -0,0 +1,68 @@
+/*
+ * Implement the manual drop-all-pagecache function
+ */
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/fs.h>
+#include <linux/writeback.h>
+#include <linux/sysctl.h>
+#include <linux/gfp.h>
+
+/* A global variable is a bit ugly, but it keeps the code simple */
+int sysctl_drop_caches;
+
+static void drop_pagecache_sb(struct super_block *sb)
+{
+        struct inode *inode;
+
+        spin_lock(&inode_lock);
+        list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
+                if (inode->i_state & (I_FREEING|I_WILL_FREE))
+                        continue;
+                invalidate_inode_pages(inode->i_mapping);
+        }
+        spin_unlock(&inode_lock);
+}
+
+void drop_pagecache(void)
+{
+        struct super_block *sb;
+
+        spin_lock(&sb_lock);
+restart:
+        list_for_each_entry(sb, &super_blocks, s_list) {
+                sb->s_count++;
+                spin_unlock(&sb_lock);
+                down_read(&sb->s_umount);
+                if (sb->s_root)
+                        drop_pagecache_sb(sb);
+                up_read(&sb->s_umount);
+                spin_lock(&sb_lock);
+                if (__put_super_and_need_restart(sb))
+                        goto restart;
+        }
+        spin_unlock(&sb_lock);
+}
+
+void drop_slab(void)
+{
+        int nr_objects;
+
+        do {
+                nr_objects = shrink_slab(1000, GFP_KERNEL, 1000);
+        } while (nr_objects > 10);
+}
+
+int drop_caches_sysctl_handler(ctl_table *table, int write,
+        struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
+{
+        proc_dointvec_minmax(table, write, file, buffer, length, ppos);
+        if (write) {
+                if (sysctl_drop_caches & 1)
+                        drop_pagecache();
+                if (sysctl_drop_caches & 2)
+                        drop_slab();
+        }
+        return 0;
+}