ext4: improve smp scalability for inode generation

->s_next_generation is protected by s_next_gen_lock but its usage pattern is very primitive. We don't actually need sequentially increasing new generation numbers, so let's use prandom_u32() instead. Reported-by: Dmitry Monakhov <[email protected]> Signed-off-by: Theodore Ts'o <[email protected]>
opendata26 · Nov 9, 2017 · 2325306 · 2325306
1 parent d77147f
commit 2325306
Show file tree

Hide file tree

Showing 4 changed files with 4 additions and 12 deletions.
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
@@ -1355,8 +1355,6 @@ struct ext4_sb_info {
 	int s_first_ino;
 	unsigned int s_inode_readahead_blks;
 	unsigned int s_inode_goal;
-	spinlock_t s_next_gen_lock;
-	u32 s_next_generation;
 	u32 s_hash_seed[4];
 	int s_def_hash_version;
 	int s_hash_unsigned;	/* 3 if hash should be signed, 0 if not */

diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
@@ -1138,9 +1138,7 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
 			   inode->i_ino);
 		goto out;
 	}
-	spin_lock(&sbi->s_next_gen_lock);
-	inode->i_generation = sbi->s_next_generation++;
-	spin_unlock(&sbi->s_next_gen_lock);
+	inode->i_generation = prandom_u32();
 
 	/* Precompute checksum seed for inode metadata */
 	if (ext4_has_metadata_csum(sb)) {

diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
@@ -14,6 +14,7 @@
 #include <linux/mount.h>
 #include <linux/file.h>
 #include <linux/quotaops.h>
+#include <linux/random.h>
 #include <linux/uuid.h>
 #include <linux/uaccess.h>
 #include <linux/delay.h>
@@ -98,7 +99,6 @@ static long swap_inode_boot_loader(struct super_block *sb,
 	int err;
 	struct inode *inode_bl;
 	struct ext4_inode_info *ei_bl;
-	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
 	if (inode->i_nlink != 1 || !S_ISREG(inode->i_mode))
 		return -EINVAL;
@@ -157,10 +157,8 @@ static long swap_inode_boot_loader(struct super_block *sb,
 
 	inode->i_ctime = inode_bl->i_ctime = current_time(inode);
 
-	spin_lock(&sbi->s_next_gen_lock);
-	inode->i_generation = sbi->s_next_generation++;
-	inode_bl->i_generation = sbi->s_next_generation++;
-	spin_unlock(&sbi->s_next_gen_lock);
+	inode->i_generation = prandom_u32();
+	inode_bl->i_generation = prandom_u32();
 
 	ext4_discard_preallocations(inode);
 

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
@@ -3982,8 +3982,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	}
 
 	sbi->s_gdb_count = db_count;
-	get_random_bytes(&sbi->s_next_generation, sizeof(u32));
-	spin_lock_init(&sbi->s_next_gen_lock);
 
 	timer_setup(&sbi->s_err_report, print_daily_error_info, 0);