direct-io: only inc/dec inode->i_dio_count for file systems

do_blockdev_direct_IO() increments and decrements the inode
->i_dio_count for each IO operation. It does this to protect against
truncate of a file. Block devices don't need this sort of protection.

For a capable multiqueue setup, this atomic int is the only shared
state between applications accessing the device for O_DIRECT, and it
presents a scaling wall for that. In my testing, as much as 30% of
system time is spent incrementing and decrementing this value. A mixed
read/write workload improved from ~2.5M IOPS to ~9.6M IOPS, with
better latencies too. Before:

clat percentiles (usec):
 |  1.00th=[   33],  5.00th=[   34], 10.00th=[   34], 20.00th=[   34],
 | 30.00th=[   34], 40.00th=[   34], 50.00th=[   35], 60.00th=[   35],
 | 70.00th=[   35], 80.00th=[   35], 90.00th=[   37], 95.00th=[   80],
 | 99.00th=[   98], 99.50th=[  151], 99.90th=[  155], 99.95th=[  155],
 | 99.99th=[  165]

After:

clat percentiles (usec):
 |  1.00th=[   95],  5.00th=[  108], 10.00th=[  129], 20.00th=[  149],
 | 30.00th=[  155], 40.00th=[  161], 50.00th=[  167], 60.00th=[  171],
 | 70.00th=[  177], 80.00th=[  185], 90.00th=[  201], 95.00th=[  270],
 | 99.00th=[  390], 99.50th=[  398], 99.90th=[  418], 99.95th=[  422],
 | 99.99th=[  438]

In other setups, Robert Elliott reported seeing good performance
improvements:

https://lkml.org/lkml/2015/4/3/557

The more applications accessing the device, the worse it gets.

Add a new direct-io flags, DIO_SKIP_DIO_COUNT, which tells
do_blockdev_direct_IO() that it need not worry about incrementing
or decrementing the inode i_dio_count for this caller.

Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: Elliott, Robert (Server Storage) <elliott@hp.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Jens Axboe <axboe@fb.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

1 files changed, 5 insertions, 5 deletions

diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index ed0e6031be88..b2cbc3a6cdd9 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -386,7 +386,7 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq, bool write)
 	if (write)
 		nfs_zap_mapping(inode, inode->i_mapping);
 
-	inode_dio_done(inode);
+	inode_dio_end(inode);
 
 	if (dreq->iocb) {
 		long res = (long) dreq->error;
@@ -486,7 +486,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
 			     &nfs_direct_read_completion_ops);
 	get_dreq(dreq);
 	desc.pg_dreq = dreq;
-	atomic_inc(&inode->i_dio_count);
+	inode_dio_begin(inode);
 
 	while (iov_iter_count(iter)) {
 		struct page **pagevec;
@@ -538,7 +538,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
 	 * generic layer handle the completion.
 	 */
 	if (requested_bytes == 0) {
-		inode_dio_done(inode);
+		inode_dio_end(inode);
 		nfs_direct_req_release(dreq);
 		return result < 0 ? result : -EIO;
 	}
@@ -872,7 +872,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 			      &nfs_direct_write_completion_ops);
 	desc.pg_dreq = dreq;
 	get_dreq(dreq);
-	atomic_inc(&inode->i_dio_count);
+	inode_dio_begin(inode);
 
 	NFS_I(inode)->write_io += iov_iter_count(iter);
 	while (iov_iter_count(iter)) {
@@ -928,7 +928,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 	 * generic layer handle the completion.
 	 */
 	if (requested_bytes == 0) {
-		inode_dio_done(inode);
+		inode_dio_end(inode);
 		nfs_direct_req_release(dreq);
 		return result < 0 ? result : -EIO;
 	}