2019-11-20 05:01:21

by Ritesh Harjani

Subject: [RFCv3 1/4] ext4: fix ext4_dax_read/write inode locking sequence for IOCB_NOWAIT

Apparently our current rwsem code doesn't like doing the trylock, then
lock for real scheme. So change our dax read/write methods to just do the
trylock for the RWF_NOWAIT case.
This seems to fix AIM7 regression in some scalable filesystems upto ~25%
in some cases. Claimed in commit 942491c9e6d6 ("xfs: fix AIM7 regression")

Signed-off-by: Ritesh Harjani <[email protected]>
---
fs/ext4/file.c | 10 ++++++----
1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 6a7293a5cda2..977ac58dc718 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -88,9 +88,10 @@ static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
struct inode *inode = file_inode(iocb->ki_filp);
ssize_t ret;

- if (!inode_trylock_shared(inode)) {
- if (iocb->ki_flags & IOCB_NOWAIT)
+ if (iocb->ki_flags & IOCB_NOWAIT) {
+ if (!inode_trylock_shared(inode))
return -EAGAIN;
+ } else {
inode_lock_shared(inode);
}
/*
@@ -487,9 +488,10 @@ ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
bool extend = false;
struct inode *inode = file_inode(iocb->ki_filp);

- if (!inode_trylock(inode)) {
- if (iocb->ki_flags & IOCB_NOWAIT)
+ if (iocb->ki_flags & IOCB_NOWAIT) {
+ if (!inode_trylock(inode))
return -EAGAIN;
+ } else {
inode_lock(inode);
}

--
2.21.0

2019-11-20 13:37:22

by Jan Kara

Subject: Re: [RFCv3 1/4] ext4: fix ext4_dax_read/write inode locking sequence for IOCB_NOWAIT

On Wed 20-11-19 10:30:21, Ritesh Harjani wrote:
> Apparently our current rwsem code doesn't like doing the trylock, then
> lock for real scheme. So change our dax read/write methods to just do the
> trylock for the RWF_NOWAIT case.
> This seems to fix AIM7 regression in some scalable filesystems upto ~25%
> in some cases. Claimed in commit 942491c9e6d6 ("xfs: fix AIM7 regression")
>
> Signed-off-by: Ritesh Harjani <[email protected]>

Looks good to me. You can add:

Reviewed-by: Jan Kara <[email protected]>

Honza

> ---
> fs/ext4/file.c | 10 ++++++----
> 1 file changed, 6 insertions(+), 4 deletions(-)
>
> diff --git a/fs/ext4/file.c b/fs/ext4/file.c
> index 6a7293a5cda2..977ac58dc718 100644
> --- a/fs/ext4/file.c
> +++ b/fs/ext4/file.c
> @@ -88,9 +88,10 @@ static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
> struct inode *inode = file_inode(iocb->ki_filp);
> ssize_t ret;
>
> - if (!inode_trylock_shared(inode)) {
> - if (iocb->ki_flags & IOCB_NOWAIT)
> + if (iocb->ki_flags & IOCB_NOWAIT) {
> + if (!inode_trylock_shared(inode))
> return -EAGAIN;
> + } else {
> inode_lock_shared(inode);
> }
> /*
> @@ -487,9 +488,10 @@ ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
> bool extend = false;
> struct inode *inode = file_inode(iocb->ki_filp);
>
> - if (!inode_trylock(inode)) {
> - if (iocb->ki_flags & IOCB_NOWAIT)
> + if (iocb->ki_flags & IOCB_NOWAIT) {
> + if (!inode_trylock(inode))
> return -EAGAIN;
> + } else {
> inode_lock(inode);
> }
>
> --
> 2.21.0
>
--
Jan Kara <[email protected]>
SUSE Labs, CR

2019-11-22 05:55:35

by Matthew Bobrowski

Subject: Re: [RFCv3 1/4] ext4: fix ext4_dax_read/write inode locking sequence for IOCB_NOWAIT

On Wed, Nov 20, 2019 at 10:30:21AM +0530, Ritesh Harjani wrote:
> Apparently our current rwsem code doesn't like doing the trylock, then
> lock for real scheme. So change our dax read/write methods to just do the
> trylock for the RWF_NOWAIT case.
> This seems to fix AIM7 regression in some scalable filesystems upto ~25%
> in some cases. Claimed in commit 942491c9e6d6 ("xfs: fix AIM7 regression")
>
> Signed-off-by: Ritesh Harjani <[email protected]>

This looks OK to me. Feel free to add:

Reviewed-by: Matthew Bobrowski <[email protected]>

/M