[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-ID: <4F322585.3010407@sx.jp.nec.com>
Date: Wed, 08 Feb 2012 16:34:29 +0900
From: Kazuya Mio <k-mio@...jp.nec.com>
To: ext4 <linux-ext4@...r.kernel.org>, jan Kara <jack@...e.cz>,
Andreas Dilger <adilger@...ger.ca>
Subject: [PATCH v2] ext3: Update ctime in ext3_splice_branch() only when needed
Currently ext3 updates ctime in ext3_splice_branch() which is called whenever
we allocate one block. But it is wasteful because ext3 doesn't support
nanosecond timestamp. This leads to a performance loss.
Signed-off-by: Kazuya Mio <k-mio@...jp.nec.com>
---
fs/ext3/inode.c | 9 ++++++---
1 file changed, 6 insertions(+), 3 deletions(-)
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 2d0afec..3c7fd63 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -756,6 +756,7 @@ static int ext3_splice_branch(handle_t *handle, struct inode *inode,
struct ext3_block_alloc_info *block_i;
ext3_fsblk_t current_block;
struct ext3_inode_info *ei = EXT3_I(inode);
+ struct timespec now;
block_i = ei->i_block_alloc_info;
/*
@@ -795,9 +796,11 @@ static int ext3_splice_branch(handle_t *handle, struct inode *inode,
}
/* We are done with atomic stuff, now do the rest of housekeeping */
-
- inode->i_ctime = CURRENT_TIME_SEC;
- ext3_mark_inode_dirty(handle, inode);
+ now = CURRENT_TIME_SEC;
+ if (!timespec_equal(&inode->i_ctime, &now) || !where->bh) {
+ inode->i_ctime = now;
+ ext3_mark_inode_dirty(handle, inode);
+ }
/* ext3_mark_inode_dirty already updated i_sync_tid */
atomic_set(&ei->i_datasync_tid, handle->h_transaction->t_tid);
--
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists