From: Dharmendra Singh <dsingh@xxxxxxx>
In general, as of now, in FUSE, direct writes on the same file are
serialized over inode lock i.e we hold inode lock for the full duration
of the write request. I could not found in fuse code a comment which
clearly explains why this exclusive lock is taken for direct writes.
Following might be the reasons for acquiring exclusive lock but not
limited to
1) Our guess is some USER space fuse implementations might be relying
on this lock for seralization.
2) This lock protects for the issues arising due to file size
assumptions.
3) Ruling out any issues arising due to multiple writes where some
writes succeeded and some failed.
This patch relaxes this exclusive lock for non-extending direct writes.
With these changes, we allows non-extending parallel direct writes
on the same file with the help of a flag called FOPEN_PARALLEL_WRITES.
If this flag is set on the file (flag is passed from libfuse to fuse
kernel as part of file open/create), we do not take exclusive lock
instead use shared lock so that all non-extending writes can run in
parallel.
Best practise would be to enable parallel direct writes of all kinds
including extending writes as well but we see some issues such as
1) When one write completes on one server and other fails on another
server, how we should truncate(if needed) the file if underlying file
system does not support holes (For file systems which supports holes,
there might be a possibility of enabling parallel writes for all cases).
FUSE implementations which rely on this inode lock for serialisation
can continue to do so and this is default behaviour i.e no parallel
direct writes.
Signed-off-by: Dharmendra Singh <dsingh@xxxxxxx>
Signed-off-by: Bernd Schubert <bschubert@xxxxxxx>
---
fs/fuse/file.c | 46 ++++++++++++++++++++++++++++++++++++---
include/uapi/linux/fuse.h | 2 ++
2 files changed, 45 insertions(+), 3 deletions(-)
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 829094451774..72524612bd5c 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1541,14 +1541,50 @@ static ssize_t fuse_direct_read_iter(struct kiocb *iocb, struct iov_iter *to)
return res;
}
+static bool fuse_direct_write_extending_i_size(struct kiocb *iocb,
+ struct iov_iter *iter)
+{
+ struct inode *inode = file_inode(iocb->ki_filp);
+
+ return (iocb->ki_flags & IOCB_APPEND ||
+ iocb->ki_pos + iov_iter_count(iter) > i_size_read(inode));
+}
+
static ssize_t fuse_direct_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct inode *inode = file_inode(iocb->ki_filp);
+ struct file *file = iocb->ki_filp;
+ struct fuse_file *ff = file->private_data;
struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(iocb);
ssize_t res;
+ bool exclusive_lock = !(ff->open_flags & FOPEN_PARALLEL_WRITES ||
+ fuse_direct_write_extending_i_size(iocb, from));
+
+ /*
+ * Take exclusive lock if
+ * - parallel writes are disabled.
+ * - parallel writes are enabled and i_size is being extended
+ * Take shared lock if
+ * - parallel writes are enabled but i_size does not extend.
+ */
+retry:
+ if (exclusive_lock)
+ inode_lock(inode);
+ else {
+ inode_lock_shared(inode);
+
+ /*
+ * Its possible that truncate reduced the file size after the check
+ * but before acquiring shared lock. If its so than drop shared lock and
+ * acquire exclusive lock.
+ */
+ if (fuse_direct_write_extending_i_size(iocb, from)) {
+ inode_unlock_shared(inode);
+ exclusive_lock = true;
+ goto retry;
+ }
+ }
- /* Don't allow parallel writes to the same file */
- inode_lock(inode);
res = generic_write_checks(iocb, from);
if (res > 0) {
if (!is_sync_kiocb(iocb) && iocb->ki_flags & IOCB_DIRECT) {
@@ -1559,7 +1595,10 @@ static ssize_t fuse_direct_write_iter(struct kiocb *iocb, struct iov_iter *from)
fuse_write_update_attr(inode, iocb->ki_pos, res);
}
}
- inode_unlock(inode);
+ if (exclusive_lock)
+ inode_unlock(inode);
+ else
+ inode_unlock_shared(inode);
return res;
}
@@ -2901,6 +2940,7 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
if (iov_iter_rw(iter) == WRITE) {
fuse_write_update_attr(inode, pos, ret);
+ /* For extending writes we already hold exclusive lock */
if (ret < 0 && offset + count > i_size)
fuse_do_truncate(file);
}
diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h
index d6ccee961891..ee5379d41906 100644
--- a/include/uapi/linux/fuse.h
+++ b/include/uapi/linux/fuse.h
@@ -301,6 +301,7 @@ struct fuse_file_lock {
* FOPEN_CACHE_DIR: allow caching this directory
* FOPEN_STREAM: the file is stream-like (no file position at all)
* FOPEN_NOFLUSH: don't flush data cache on close (unless FUSE_WRITEBACK_CACHE)
+ * FOPEN_PARALLEL_WRITES: Allow concurrent writes on the same inode
*/
#define FOPEN_DIRECT_IO (1 << 0)
#define FOPEN_KEEP_CACHE (1 << 1)
@@ -308,6 +309,7 @@ struct fuse_file_lock {
#define FOPEN_CACHE_DIR (1 << 3)
#define FOPEN_STREAM (1 << 4)
#define FOPEN_NOFLUSH (1 << 5)
+#define FOPEN_PARALLEL_WRITES (1 << 6)
/**
* INIT request/reply flags
--
2.17.1
