[PATCH] FAT: rewrite the cache for file allocation table lookup

This rewrites the cache stuff for file allocation table (FAT).

This cache stocks the more pieces of FAT-chain by counting the number
of contiguous data blocks. And if cache hit, since a block number can
calculate without looking FAT-chain up, fat_get_block() become more
fast.

But if data blocks was fragmenting, unfortunately this cache is unuseful.

read from block device

[1st]# time dd if=/dev/hda6 of=/dev/null bs=1M count=2048
2147483648 bytes transferred in 229.524189 seconds (9356241 bytes/sec)
real    3m49.557s, user    0m0.026s, sys     1m20.414s
[2nd]# time dd if=/dev/hda6 of=/dev/null bs=1M count=2048
2147483648 bytes transferred in 229.539358 seconds (9355623 bytes/sec)
real    3m49.647s, user    0m0.036s, sys     1m20.144s

read from full contiguous file with this patch

[1st]# time dd if=data of=/dev/null bs=1M count=2048
2147483648 bytes transferred in 337.959477 seconds (6354264 bytes/sec)
real    5m37.970s, user    0m0.031s, sys     1m21.915s
[2nd]# time dd if=data of=/dev/null bs=1M count=2048
2147483648 bytes transferred in 225.401699 seconds (9527362 bytes/sec)
real    3m45.476s, user    0m0.027s, sys     1m19.286s

read from full fragmented file with this patch

[1st]# time dd if=data of=/dev/null bs=1M count=2048
2147483647 bytes transferred in 1146.529081 seconds (1873030 bytes/sec)
real    19m6.538s, user    0m0.020s, sys     1m32.774s
[2nd]# time dd if=data of=/dev/null bs=1M count=2048
2147483647 bytes transferred in 1045.084822 seconds (2054841 bytes/sec)
real    17m25.152s, user    0m0.022s, sys     1m34.801s

read from full contiguous file without this patch

[1st]# time dd if=data of=/dev/null bs=1M count=2048
2147483648 bytes transferred in 348.144707 seconds (6168365 bytes/sec)
real    5m48.169s, user    0m0.019s, sys     1m29.962s
[2nd]# time dd if=data of=/dev/null bs=1M count=2048
2147483648 bytes transferred in 324.017361 seconds (6627681 bytes/sec)
real    5m24.038s, user    0m0.023s, sys     1m20.602s

read from full fragmented file without this patch

[1st]# time dd if=data of=/dev/null bs=1M count=2048
2147483647 bytes transferred in 1156.845693 seconds (1856327 bytes/sec)
real    19m16.855s, user    0m0.031s, sys     1m32.172s
[2nd]# time dd if=data of=/dev/null bs=1M count=2048
2147483647 bytes transferred in 1066.518713 seconds (2013545 bytes/sec)
real    17m46.526s, user    0m0.023s, sys     1m33.630s
Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

fs/fat/fatfs_syms.c

@@ -24,16 +24,23 @@ EXPORT_SYMBOL(fat_scan);
 EXPORT_SYMBOL(fat_add_entries);
 EXPORT_SYMBOL(fat_dir_empty);
 
+int __init fat_cache_init(void);
+void __exit fat_cache_destroy(void);
 int __init fat_init_inodecache(void);
 void __exit fat_destroy_inodecache(void);
 static int __init init_fat_fs(void)
 {
+	int ret;
 	fat_hash_init();
+	ret = fat_cache_init();
+	if (ret < 0)
+		return ret;
 	return fat_init_inodecache();
 }
 
 static void __exit exit_fat_fs(void)
 {
+	fat_cache_destroy();
 	fat_destroy_inodecache();
 }
 

fs/fat/inode.c

@@ -533,7 +533,6 @@ static int fat_read_root(struct inode *inode)
 	struct msdos_sb_info *sbi = MSDOS_SB(sb);
 	int error;
 
-	MSDOS_I(inode)->file_cluster = MSDOS_I(inode)->disk_cluster = 0;
 	MSDOS_I(inode)->i_pos = 0;
 	inode->i_uid = sbi->options.fs_uid;
 	inode->i_gid = sbi->options.fs_gid;
@@ -736,6 +735,8 @@ static void init_once(void * foo, kmem_cache_t * cachep, unsigned long flags)
 
 	if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) ==
 	    SLAB_CTOR_CONSTRUCTOR) {
+		ei->nr_caches = 0;
+		INIT_LIST_HEAD(&ei->cache_lru);
 		INIT_HLIST_NODE(&ei->i_fat_hash);
 		inode_init_once(&ei->vfs_inode);
 	}
@@ -819,7 +820,7 @@ int fat_fill_super(struct super_block *sb, void *data, int silent,
 	if (error)
 		goto out_fail;
 
-	fat_cache_init(sb);
+	spin_lock_init(&MSDOS_SB(sb)->cache_lock);
 	/* set up enough so that it can read an inode */
 	init_MUTEX(&sbi->fat_lock);
 
@@ -1164,7 +1165,6 @@ static int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de)
 	struct msdos_sb_info *sbi = MSDOS_SB(sb);
 	int error;
 
-	MSDOS_I(inode)->file_cluster = MSDOS_I(inode)->disk_cluster = 0;
 	MSDOS_I(inode)->i_pos = 0;
 	inode->i_uid = sbi->options.fs_uid;
 	inode->i_gid = sbi->options.fs_gid;

fs/fat/misc.c

@@ -155,7 +155,7 @@ int fat_add_cluster(struct inode *inode)
 		ret = fat_access(sb, last, new_dclus);
 		if (ret < 0)
 			return ret;
-		fat_cache_add(inode, new_fclus, new_dclus);
+//		fat_cache_add(inode, new_fclus, new_dclus);
 	} else {
 		MSDOS_I(inode)->i_start = new_dclus;
 		MSDOS_I(inode)->i_logstart = new_dclus;

include/linux/msdos_fs.h

@@ -232,8 +232,6 @@ static inline void fatwchar_to16(__u8 *dst, const wchar_t *src, size_t len)
 extern int fat_access(struct super_block *sb, int nr, int new_value);
 extern int __fat_access(struct super_block *sb, int nr, int new_value);
 extern int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys);
-extern void fat_cache_init(struct super_block *sb);
-extern void fat_cache_add(struct inode *inode, int f_clu, int d_clu);
 extern void fat_cache_inval_inode(struct inode *inode);
 extern int fat_get_cluster(struct inode *inode, int cluster,
 			   int *fclus, int *dclus);

include/linux/msdos_fs_i.h

@@ -8,9 +8,8 @@
  */
 
 struct msdos_inode_info {
-	/* cache of lastest accessed cluster */
-	int file_cluster;	/* cluster number in the file. */
-	int disk_cluster;	/* cluster number on disk. */
+	struct list_head cache_lru;
+	int nr_caches;
 
 	loff_t mmu_private;
 	int i_start;	/* first cluster or 0 */

include/linux/msdos_fs_sb.h

@@ -26,15 +26,6 @@ struct fat_mount_options {
 		 nocase:1;	  /* Does this need case conversion? 0=need case conversion*/
 };
 
-#define FAT_CACHE_NR	8 /* number of FAT cache */
-
-struct fat_cache {
-	int start_cluster; /* first cluster of the chain. */
-	int file_cluster; /* cluster number in the file. */
-	int disk_cluster; /* cluster number on disk. */
-	struct fat_cache *next; /* next cache entry */
-};
-
 struct msdos_sb_info {
 	unsigned short sec_per_clus; /* sectors/cluster */
 	unsigned short cluster_bits; /* log2(cluster_size) */
@@ -59,7 +50,6 @@ struct msdos_sb_info {
 	int dir_per_block_bits;	     /* log2(dir_per_block) */
 
 	spinlock_t cache_lock;
-	struct fat_cache cache_array[FAT_CACHE_NR], *cache;
 };
 
 #endif