Skip to contentSkip to conversation

Cleancache: core ops functions and configuration

PATCH New Dan Magenheimer 1 participant 1 message Sep 3, 2010

Subsystems (3)
lore
Share & tools
lore
#0 lore raw

PATCH v5 3/8 Cleancache: core ops functions and configuration

[PATCH V5 3/8] Cleancache: core ops functions and configuration

Cleancache core ops functions and configuration

Credits: Cleancache_ops design derived from Jeremy Fitzhardinge design for tmem; sysfs code modelled after mm/ksm.c

Note that CONFIG_CLEANCACHE defaults to on; all hooks devolve to a compare-function-pointer-to-NULL so performance impact should be negligible, but can be reduced to zero impact if config'ed off.

Diffstat:

 include/linux/cleancache.h               |  118 +++++++++
 mm/Kconfig                               |   22 +
 mm/Makefile                              |    1 
 mm/cleancache.c                          |  258 +++++++++++++++++++++
 4 files changed, 399 insertions(+)
include/linux/cleancache.h +118 -0
@@ -0,0 +1,118 @@
+#ifndef _LINUX_CLEANCACHE_H
+#define _LINUX_CLEANCACHE_H
+
+#include <linux/fs.h>
+#include <linux/exportfs.h>
+#include <linux/mm.h>
+
+#define CLEANCACHE_KEY_MAX 6
+
+/*
+ * cleancache requires every file with a page in cleancache to have a
+ * unique key unless/until the file is removed/truncated.  For some
+ * filesystems, the inode number is unique, but for "modern" filesystems
+ * an exportable filehandle is required (see exportfs.h)
+ */
+struct cleancache_filekey {
+	union {
+		ino_t ino;
+		__u32 fh[CLEANCACHE_KEY_MAX];
+		u32 key[CLEANCACHE_KEY_MAX];
+	} u;
+};
+
+struct cleancache_ops {
+	int (*init_fs)(size_t);
+	int (*init_shared_fs)(char *uuid, size_t);
+	int (*get_page)(int, struct cleancache_filekey,
+			pgoff_t, struct page *);
+	void (*put_page)(int, struct cleancache_filekey,
+			pgoff_t, struct page *);
+	void (*flush_page)(int, struct cleancache_filekey, pgoff_t);
+	void (*flush_inode)(int, struct cleancache_filekey);
+	void (*flush_fs)(int);
+};
+
+extern struct cleancache_ops
+	cleancache_register_ops(struct cleancache_ops *ops);
+extern void __cleancache_init_fs(struct super_block *);
+extern void __cleancache_init_shared_fs(char *, struct super_block *);
+extern int  __cleancache_get_page(struct page *);
+extern void __cleancache_put_page(struct page *);
+extern void __cleancache_flush_page(struct address_space *, struct page *);
+extern void __cleancache_flush_inode(struct address_space *);
+extern void __cleancache_flush_fs(struct super_block *);
+extern int cleancache_enabled;
+
+#ifdef CONFIG_CLEANCACHE
+#define cleancache_fs_enabled(_page) \
+	(_page->mapping->host->i_sb->cleancache_poolid >= 0)
+#define cleancache_fs_enabled_mapping(_mapping) \
+	(mapping->host->i_sb->cleancache_poolid >= 0)
+#else
+#define cleancache_enabled (0)
+#define cleancache_fs_enabled(_page) (0)
+#define cleancache_fs_enabled_mapping(_page) (0)
+#endif
+
+/*
+ * The shim layer provided by these inline functions allows the compiler
+ * to reduce all cleancache hooks to nothingness if CONFIG_CLEANCACHE
+ * is disabled, to a single global variable check if CONFIG_CLEANCACHE
+ * is enabled but no cleancache "backend" has dynamically enabled it,
+ * and, for the most frequent cleancache ops, to a single global variable
+ * check plus a superblock element comparison if CONFIG_CLEANCACHE is enabled
+ * and a cleancache backend has dynamically enabled cleancache, but the
+ * filesystem referenced by that cleancache op has not enabled cleancache.
+ * As a result, CONFIG_CLEANCACHE can be enabled by default with essentially
+ * no measurable performance impact.
+ */
+
+static inline void cleancache_init_fs(struct super_block *sb)
+{
+	if (cleancache_enabled)
+		__cleancache_init_fs(sb);
+}
+
+static inline void cleancache_init_shared_fs(char *uuid, struct super_block *sb)
+{
+	if (cleancache_enabled)
+		__cleancache_init_shared_fs(uuid, sb);
+}
+
+static inline int cleancache_get_page(struct page *page)
+{
+	int ret = -1;
+
+	if (cleancache_enabled && cleancache_fs_enabled(page))
+		ret = __cleancache_get_page(page);
+	return ret;
+}
+
+static inline void cleancache_put_page(struct page *page)
+{
+	if (cleancache_enabled && cleancache_fs_enabled(page))
+		__cleancache_put_page(page);
+}
+
+static inline void cleancache_flush_page(struct address_space *mapping,
+					struct page *page)
+{
+	/* careful... page->mapping is NULL sometimes when this is called */
+	if (cleancache_enabled && cleancache_fs_enabled_mapping(mapping))
+		__cleancache_flush_page(mapping, page);
+}
+
+static inline void cleancache_flush_inode(struct address_space *mapping)
+{
+	if (cleancache_enabled && cleancache_fs_enabled_mapping(mapping))
+		__cleancache_flush_inode(mapping);
+}
+
+static inline void cleancache_flush_fs(struct super_block *sb)
+{
+	if (cleancache_enabled)
+		__cleancache_flush_fs(sb);
+}
+
+#endif /* _LINUX_CLEANCACHE_H */
mm/cleancache.c +258 -0

258 lines not on this page · raw message

mm/Kconfig +22 -0
@@ -301,3 +301,25 @@ config NOMMU_INITIAL_TRIM_EXCESS
 	  of 1 says that all excess pages should be trimmed.
 
 	  See Documentation/nommu-mmap.txt for more information.
+
+config CLEANCACHE
+	bool "Enable cleancache pseudo-RAM driver to cache clean pages"
+	default y
+	help
+ 	  Cleancache can be thought of as a page-granularity victim cache
+	  for clean pages that the kernel's pageframe replacement algorithm
+	  (PFRA) would like to keep around, but can't since there isn't enough
+	  memory.  So when the PFRA "evicts" a page, it first attempts to put
+	  it into a synchronous concurrency-safe page-oriented pseudo-RAM
+	  device (such as Xen's Transcendent Memory, aka "tmem") which is not
+	  directly accessible or addressable by the kernel and is of unknown
+	  (and possibly time-varying) size.  And when a cleancache-enabled
+	  filesystem wishes to access a page in a file on disk, it first
+	  checks cleancache to see if it already contains it; if it does,
+ 	  the page is copied into the kernel and a disk access is avoided.
+	  When a pseudo-RAM device is available, a significant I/O reduction
+	  may be achieved.  When none is available, all cleancache calls
+	  are reduced to a single pointer-compare-against-NULL resulting
+	  in a negligible performance hit.
+
+	  If unsure, say Y to enable cleancache
mm/Makefile +1 -0
@@ -47,3 +47,4 @@ obj-$(CONFIG_MEMORY_FAILURE) += memory-f
 obj-$(CONFIG_HWPOISON_INJECT) += hwpoison-inject.o
 obj-$(CONFIG_DEBUG_KMEMLEAK) += kmemleak.o
 obj-$(CONFIG_DEBUG_KMEMLEAK_TEST) += kmemleak-test.o
+obj-$(CONFIG_CLEANCACHE) += cleancache.o