[PATCH 05/11] direct-io: only inc/dec inode->i_dio_count for file systems

[Jens Axboe]

We don't need truncate protection for block devices, so add a flag
bypassing this cache line dirtying twice for every IO. This easily
contributes to 5-10% of the CPU time on high IOPS O_DIRECT testing.

Cc: Christoph Hellwig <hch@xxxxxxxxxxxxx>
Cc: Al Viro <viro@xxxxxxxxxxxxxxxxxx>
Signed-off-by: Jens Axboe <axboe@xxxxxxxxx>
---
 fs/block_dev.c     |  3 ++-
 fs/direct-io.c     | 14 +++++++++++++-
 fs/inode.c         |  7 ++++++-
 include/linux/fs.h |  4 ++++
 4 files changed, 25 insertions(+), 3 deletions(-)

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 1e86823..e20b7c1 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -172,7 +172,8 @@ blkdev_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
 	struct inode *inode = file->f_mapping->host;
 
 	return __blockdev_direct_IO(rw, iocb, inode, I_BDEV(inode), iov, offset,
-				    nr_segs, blkdev_get_block, NULL, NULL, 0);
+				    nr_segs, blkdev_get_block, NULL, NULL,
+				    DIO_IGNORE_TRUNCATE);
 }
 
 int __sync_blockdev(struct block_device *bdev, int wait)
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 0e04142..3c96479 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -265,7 +265,11 @@ static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret,
 	if (dio->end_io && dio->result)
 		dio->end_io(dio->iocb, offset, transferred, dio->private);
 
-	inode_dio_done(dio->inode);
+	if (dio->flags & DIO_IGNORE_TRUNCATE)
+		__inode_dio_done(dio->inode);
+	else
+		inode_dio_done(dio->inode);
+
 	if (is_async) {
 		if (dio->rw & WRITE) {
 			int err;
@@ -1194,6 +1198,14 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
 	}
 
 	/*
+	 * Will be decremented at I/O completion time. For a block device
+	 * we don't need to protect against truncate, so don't increment
+	 * the inode direct IO count.
+	 */
+	if (!(dio->flags & DIO_IGNORE_TRUNCATE))
+		atomic_inc(&inode->i_dio_count);
+
+	/*
 	 * For file extending writes updating i_size before data
 	 * writeouts complete can expose uninitialized blocks. So
 	 * even for AIO, we need to wait for i/o to complete before
diff --git a/fs/inode.c b/fs/inode.c
index b33ba8e..22319db 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1854,6 +1854,11 @@ void inode_dio_wait(struct inode *inode)
 }
 EXPORT_SYMBOL(inode_dio_wait);
 
+void __inode_dio_done(struct inode *inode)
+{
+	wake_up_bit(&inode->i_state, __I_DIO_WAKEUP);
+}
+
 /*
  * inode_dio_done - signal finish of a direct I/O requests
  * @inode: inode the direct I/O happens on
@@ -1864,6 +1869,6 @@ EXPORT_SYMBOL(inode_dio_wait);
 void inode_dio_done(struct inode *inode)
 {
 	if (atomic_dec_and_test(&inode->i_dio_count))
-		wake_up_bit(&inode->i_state, __I_DIO_WAKEUP);
+		__inode_dio_done(inode);
 }
 EXPORT_SYMBOL(inode_dio_done);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 3f40547..d90a688 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2468,6 +2468,9 @@ enum {
 
 	/* filesystem does not support filling holes */
 	DIO_SKIP_HOLES	= 0x02,
+
+	/* inode/fs/bdev does not need truncate protection */
+	DIO_IGNORE_TRUNCATE = 0x04,
 };
 
 void dio_end_io(struct bio *bio, int error);
@@ -2488,6 +2491,7 @@ static inline ssize_t blockdev_direct_IO(int rw, struct kiocb *iocb,
 #endif
 
 void inode_dio_wait(struct inode *inode);
+void __inode_dio_done(struct inode *inode);
 void inode_dio_done(struct inode *inode);
 
 extern const struct file_operations generic_ro_fops;
-- 
1.8.1.2

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/