Re: [Cluster-devel] [PATCH 27/27] direct-io: remove random prefetches
On Fri, Apr 15, 2022 at 06:52:58AM +0200, Christoph Hellwig wrote: > Randomly poking into block device internals for manual prefetches isn't > exactly a very maintainable thing to do. And none of the performance > criticil direct I/O implementations still use this library function > anyway, so just drop it. > > Signed-off-by: Christoph Hellwig That the direct io function needed a valid bdev just for the prefetch but nothing else was one of the reasons we had to keep the latest_bdev in btrfs, so good riddance. You may want to add the reference to the patch that added the prefetch, 65dd2aa90aa1 ("dio: optimize cache misses in the submission path") and also remove #include as there are no more uses of prefetch in the file. With that Reviewed-by: David Sterba
[Cluster-devel] [PATCH 27/27] direct-io: remove random prefetches
Randomly poking into block device internals for manual prefetches isn't exactly a very maintainable thing to do. And none of the performance criticil direct I/O implementations still use this library function anyway, so just drop it. Signed-off-by: Christoph Hellwig --- fs/direct-io.c | 32 1 file changed, 4 insertions(+), 28 deletions(-) diff --git a/fs/direct-io.c b/fs/direct-io.c index aef06e607b405..840752006f601 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -1115,11 +1115,10 @@ static inline int drop_refcount(struct dio *dio) * individual fields and will generate much worse code. This is important * for the whole file. */ -static inline ssize_t -do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, - struct block_device *bdev, struct iov_iter *iter, - get_block_t get_block, dio_iodone_t end_io, - dio_submit_t submit_io, int flags) +ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, + struct block_device *bdev, struct iov_iter *iter, + get_block_t get_block, dio_iodone_t end_io, + dio_submit_t submit_io, int flags) { unsigned i_blkbits = READ_ONCE(inode->i_blkbits); unsigned blkbits = i_blkbits; @@ -1334,29 +1333,6 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, kmem_cache_free(dio_cache, dio); return retval; } - -ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, -struct block_device *bdev, struct iov_iter *iter, -get_block_t get_block, -dio_iodone_t end_io, dio_submit_t submit_io, -int flags) -{ - /* -* The block device state is needed in the end to finally -* submit everything. Since it's likely to be cache cold -* prefetch it here as first thing to hide some of the -* latency. -* -* Attempt to prefetch the pieces we likely need later. -*/ - prefetch(>bd_disk->part_tbl); - prefetch(bdev->bd_disk->queue); - prefetch((char *)bdev->bd_disk->queue + SMP_CACHE_BYTES); - - return do_blockdev_direct_IO(iocb, inode, bdev, iter, get_block, -end_io, submit_io, flags); -} - EXPORT_SYMBOL(__blockdev_direct_IO); static __init int dio_init(void) -- 2.30.2
[Cluster-devel] [PATCH 27/27] direct-io: remove random prefetches
Randomly poking into block device internals for manual prefetches isn't exactly a very maintainable thing to do. And none of the performance criticil direct I/O implementations still use this library function anyway, so just drop it. Signed-off-by: Christoph Hellwig --- fs/direct-io.c | 32 1 file changed, 4 insertions(+), 28 deletions(-) diff --git a/fs/direct-io.c b/fs/direct-io.c index aef06e607b405..840752006f601 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -1115,11 +1115,10 @@ static inline int drop_refcount(struct dio *dio) * individual fields and will generate much worse code. This is important * for the whole file. */ -static inline ssize_t -do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, - struct block_device *bdev, struct iov_iter *iter, - get_block_t get_block, dio_iodone_t end_io, - dio_submit_t submit_io, int flags) +ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, + struct block_device *bdev, struct iov_iter *iter, + get_block_t get_block, dio_iodone_t end_io, + dio_submit_t submit_io, int flags) { unsigned i_blkbits = READ_ONCE(inode->i_blkbits); unsigned blkbits = i_blkbits; @@ -1334,29 +1333,6 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, kmem_cache_free(dio_cache, dio); return retval; } - -ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, -struct block_device *bdev, struct iov_iter *iter, -get_block_t get_block, -dio_iodone_t end_io, dio_submit_t submit_io, -int flags) -{ - /* -* The block device state is needed in the end to finally -* submit everything. Since it's likely to be cache cold -* prefetch it here as first thing to hide some of the -* latency. -* -* Attempt to prefetch the pieces we likely need later. -*/ - prefetch(>bd_disk->part_tbl); - prefetch(bdev->bd_disk->queue); - prefetch((char *)bdev->bd_disk->queue + SMP_CACHE_BYTES); - - return do_blockdev_direct_IO(iocb, inode, bdev, iter, get_block, -end_io, submit_io, flags); -} - EXPORT_SYMBOL(__blockdev_direct_IO); static __init int dio_init(void) -- 2.30.2
[Cluster-devel] [PATCH 27/27] direct-io: remove random prefetches
Randomly poking into block device internals for manual prefetches isn't exactly a very maintainable thing to do. And none of the performance criticil direct I/O implementations still use this library function anyway, so just drop it. Signed-off-by: Christoph Hellwig --- fs/direct-io.c | 32 1 file changed, 4 insertions(+), 28 deletions(-) diff --git a/fs/direct-io.c b/fs/direct-io.c index aef06e607b405..840752006f601 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -1115,11 +1115,10 @@ static inline int drop_refcount(struct dio *dio) * individual fields and will generate much worse code. This is important * for the whole file. */ -static inline ssize_t -do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, - struct block_device *bdev, struct iov_iter *iter, - get_block_t get_block, dio_iodone_t end_io, - dio_submit_t submit_io, int flags) +ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, + struct block_device *bdev, struct iov_iter *iter, + get_block_t get_block, dio_iodone_t end_io, + dio_submit_t submit_io, int flags) { unsigned i_blkbits = READ_ONCE(inode->i_blkbits); unsigned blkbits = i_blkbits; @@ -1334,29 +1333,6 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, kmem_cache_free(dio_cache, dio); return retval; } - -ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, -struct block_device *bdev, struct iov_iter *iter, -get_block_t get_block, -dio_iodone_t end_io, dio_submit_t submit_io, -int flags) -{ - /* -* The block device state is needed in the end to finally -* submit everything. Since it's likely to be cache cold -* prefetch it here as first thing to hide some of the -* latency. -* -* Attempt to prefetch the pieces we likely need later. -*/ - prefetch(>bd_disk->part_tbl); - prefetch(bdev->bd_disk->queue); - prefetch((char *)bdev->bd_disk->queue + SMP_CACHE_BYTES); - - return do_blockdev_direct_IO(iocb, inode, bdev, iter, get_block, -end_io, submit_io, flags); -} - EXPORT_SYMBOL(__blockdev_direct_IO); static __init int dio_init(void) -- 2.30.2