From fe0f07d08ee35fb13d2cb048970072fe4f71ad14 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 15 Apr 2015 17:05:48 -0600 Subject: 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 Cc: Christoph Hellwig Cc: Theodore Ts'o Cc: Elliott, Robert (Server Storage) Cc: Al Viro Signed-off-by: Jens Axboe Signed-off-by: Al Viro --- fs/ext4/indirect.c | 6 +++--- fs/ext4/inode.c | 4 ++-- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'fs/ext4') diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index 3580629e42d3..958824019509 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -682,11 +682,11 @@ retry: * via ext4_inode_block_unlocked_dio(). Check inode's state * while holding extra i_dio_count ref. */ - atomic_inc(&inode->i_dio_count); + inode_dio_begin(inode); smp_mb(); if (unlikely(ext4_test_inode_state(inode, EXT4_STATE_DIOREAD_LOCK))) { - inode_dio_done(inode); + inode_dio_end(inode); goto locked; } if (IS_DAX(inode)) @@ -697,7 +697,7 @@ retry: inode->i_sb->s_bdev, iter, offset, ext4_get_block, NULL, NULL, 0); - inode_dio_done(inode); + inode_dio_end(inode); } else { locked: if (IS_DAX(inode)) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 063052e4aa8b..bccec41fb94b 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2977,7 +2977,7 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter, * overwrite DIO as i_dio_count needs to be incremented under i_mutex. */ if (iov_iter_rw(iter) == WRITE) - atomic_inc(&inode->i_dio_count); + inode_dio_begin(inode); /* If we do a overwrite dio, i_mutex locking can be released */ overwrite = *((int *)iocb->private); @@ -3079,7 +3079,7 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter, retake_lock: if (iov_iter_rw(iter) == WRITE) - inode_dio_done(inode); + inode_dio_end(inode); /* take i_mutex locking again if we do a ovewrite dio */ if (overwrite) { up_read(&EXT4_I(inode)->i_data_sem); -- cgit v1.2.3-58-ga151