This idea is from ext4. By this patch, we can make the dio write parallel,
and improve the performance.

We needn't worry about the race between dio write and truncate, because the
truncate need wait untill all the dio write end.

And we also needn't worry about the race between dio write and punch hole,
because we have extent lock to protect our operation.

I ran fio to test the performance of this feature.

== Hardware ==
CPU: Intel(R) Core(TM)2 Duo CPU     E7500  @ 2.93GHz
Mem: 2GB
SSD: Intel X25-M 120GB (Test Partition: 60GB)

== config file ==
[global]
ioengine=psync
direct=1
bs=4k
size=32G
runtime=60
directory=/mnt/btrfs/
filename=testfile
group_reporting
thread

[file1]
numjobs=1 # 2 4
rw=randwrite

== result (KBps) ==
write   1       2       4
lock    24936   24738   24726
nolock  24962   30866   32101

== result (iops) ==
write   1       2       4
lock    6234    6184    6181
nolock  6240    7716    8025

Signed-off-by: Miao Xie <[email protected]>
---
 fs/btrfs/inode.c | 24 +++++++++++++-----------
 1 file changed, 13 insertions(+), 11 deletions(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index d17a04b..091593a 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6589,31 +6589,33 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb 
*iocb,
        struct file *file = iocb->ki_filp;
        struct inode *inode = file->f_mapping->host;
        int flags = 0;
-       bool wakeup = false;
+       bool wakeup = true;
        int ret;
 
        if (check_direct_IO(BTRFS_I(inode)->root, rw, iocb, iov,
                            offset, nr_segs))
                return 0;
 
-       if (rw == READ) {
-               atomic_inc(&inode->i_dio_count);
-               smp_mb__after_atomic_inc();
-               if (unlikely(test_bit(BTRFS_INODE_READDIO_NEED_LOCK,
-                                     &BTRFS_I(inode)->runtime_flags))) {
-                       inode_dio_done(inode);
-                       flags = DIO_LOCKING | DIO_SKIP_HOLES;
-               } else {
-                       wakeup = true;
-               }
+       atomic_inc(&inode->i_dio_count);
+       smp_mb__after_atomic_inc();
+       if (rw == WRITE) {
+               mutex_unlock(&inode->i_mutex);
+       } else if (unlikely(test_bit(BTRFS_INODE_READDIO_NEED_LOCK,
+                                    &BTRFS_I(inode)->runtime_flags))) {
+               inode_dio_done(inode);
+               flags = DIO_LOCKING | DIO_SKIP_HOLES;
+               wakeup = false;
        }
 
        ret = __blockdev_direct_IO(rw, iocb, inode,
                        BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev,
                        iov, offset, nr_segs, btrfs_get_blocks_direct, NULL,
                        btrfs_submit_direct, flags);
+
        if (wakeup)
                inode_dio_done(inode);
+       if (rw == WRITE)
+               mutex_lock(&inode->i_mutex);
        return ret;
 }
 
-- 
1.7.11.7
--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in
the body of a message to [email protected]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Reply via email to