From: Vivek Goyal <vgoyal@redhat.com>
To: Liu Bo <bo.liu@linux.alibaba.com>
Cc: virtio-fs@redhat.com, Miklos Szeredi <mszeredi@redhat.com>
Subject: Re: [Virtio-fs] [PATCH 6/9] virtio-fs: let dax style override directIO style when dax+cache=none
Date: Tue, 16 Apr 2019 15:38:37 -0400 [thread overview]
Message-ID: <20190416193837.GE2222@redhat.com> (raw)
In-Reply-To: <20190416180322.65113-7-bo.liu@linux.alibaba.com>
On Wed, Apr 17, 2019 at 02:03:19AM +0800, Liu Bo wrote:
> In case of dax+cache=none, mmap uses dax style prior to directIO style,
> while read/write don't, but it seems that there is no reason not to do so.
>
> Signed-off-by: Liu Bo <bo.liu@linux.alibaba.com>
> Reviewed-by: Joseph Qi <joseph.qi@linux.alibaba.com>
This is interesting. I was thinking about it today itself. I noticed
that ext4 and xfs also check for DAX inode first and use dax path
if dax is enabled.
cache=never sets FOPEN_DIRECT_IO (even if application never asked for
direct IO). If dax is enabled, for data its equivalent to doing direct
IO. And for mmap() we are already checking for DAX first. So it makes
sense to do same thing for read/write path as well.
CCing Miklos as well. He might have some thougts on this. I am curios
that initially whey did he make this change only for mmap() and not
for read/write paths.
Thanks
Vivek
> ---
> fs/fuse/file.c | 11 ++++++-----
> 1 file changed, 6 insertions(+), 5 deletions(-)
>
> diff --git a/fs/fuse/file.c b/fs/fuse/file.c
> index c6090f5..620326e 100644
> --- a/fs/fuse/file.c
> +++ b/fs/fuse/file.c
> @@ -1158,12 +1158,12 @@ static ssize_t fuse_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
> struct inode *inode = file->f_mapping->host;
> struct fuse_conn *fc = get_fuse_conn(inode);
>
> - if (ff->open_flags & FOPEN_DIRECT_IO)
> - return fuse_direct_read_iter(iocb, to);
> -
> if (IS_DAX(inode))
> return fuse_dax_read_iter(iocb, to);
>
> + if (ff->open_flags & FOPEN_DIRECT_IO)
> + return fuse_direct_read_iter(iocb, to);
> +
> /*
> * In auto invalidate mode, always update attributes on read.
> * Otherwise, only update if we attempt to read past EOF (to ensure
> @@ -1426,11 +1426,12 @@ static ssize_t fuse_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
> ssize_t err;
> loff_t endbyte = 0;
>
> - if (ff->open_flags & FOPEN_DIRECT_IO)
> - return fuse_direct_write_iter(iocb, from);
> if (IS_DAX(inode))
> return fuse_dax_write_iter(iocb, from);
>
> + if (ff->open_flags & FOPEN_DIRECT_IO)
> + return fuse_direct_write_iter(iocb, from);
> +
> if (get_fuse_conn(inode)->writeback_cache) {
> /* Update size (EOF optimization) and mode (SUID clearing) */
> err = fuse_update_attributes(mapping->host, file);
> --
> 1.8.3.1
>
> _______________________________________________
> Virtio-fs mailing list
> Virtio-fs@redhat.com
> https://www.redhat.com/mailman/listinfo/virtio-fs
next prev parent reply other threads:[~2019-04-16 19:38 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-04-16 18:03 [Virtio-fs] [PATCH 0/9] virtio-fs fixes Liu Bo
2019-04-16 18:03 ` [Virtio-fs] [PATCH 1/9] virtio-fs: fix multiple tag support Liu Bo
2019-04-16 18:09 ` Vivek Goyal
2019-04-16 18:03 ` [Virtio-fs] [PATCH 2/9] virtio-fs: clean up dax mapping before aborting connection Liu Bo
2019-04-16 18:18 ` Vivek Goyal
2019-04-16 18:40 ` Liu Bo
2019-04-16 18:03 ` [Virtio-fs] [PATCH 3/9] fuse: export fuse_drop_waiting() Liu Bo
2019-04-16 18:28 ` Vivek Goyal
2019-04-16 18:43 ` Liu Bo
2019-04-16 18:03 ` [Virtio-fs] [PATCH 4/9] virtio-fs: fix use-after-free against virtio_fs_vq's fuse_dev info Liu Bo
2019-04-23 19:51 ` Vivek Goyal
2019-04-25 0:16 ` Liu Bo
2019-04-16 18:03 ` [Virtio-fs] [PATCH 5/9] fuse: do not write whole page while page straddles i_size Liu Bo
2019-04-16 20:16 ` Vivek Goyal
2019-04-17 0:12 ` Liu Bo
2019-04-16 18:03 ` [Virtio-fs] [PATCH 6/9] virtio-fs: let dax style override directIO style when dax+cache=none Liu Bo
2019-04-16 19:38 ` Vivek Goyal [this message]
2019-04-17 8:25 ` Miklos Szeredi
2019-04-17 19:35 ` Liu Bo
2019-04-25 18:35 ` Vivek Goyal
2019-04-17 20:56 ` Vivek Goyal
2019-04-22 18:55 ` Liu Bo
2019-04-22 18:14 ` Vivek Goyal
2019-04-16 18:03 ` [Virtio-fs] [PATCH 7/9] fuse: return early if punch_hole fails Liu Bo
2019-04-16 19:51 ` Vivek Goyal
2019-04-16 18:03 ` [Virtio-fs] [PATCH 8/9] virtio-fs: honor RLIMIT_FSIZE in fuse_file_fallocate Liu Bo
2019-04-16 19:57 ` Vivek Goyal
2019-04-16 18:03 ` [Virtio-fs] [PATCH 9/9] fuse: fix deadlock in __fuse_file_fallocate() Liu Bo
2019-04-16 18:07 ` Vivek Goyal
2019-05-02 22:10 ` Liu Bo
2019-05-03 15:22 ` Vivek Goyal
2019-04-24 18:41 ` [Virtio-fs] [PATCH 0/9] virtio-fs fixes Vivek Goyal
2019-04-24 23:12 ` Liu Bo
2019-04-25 14:59 ` Vivek Goyal
2019-04-25 18:10 ` Liu Bo
2019-04-27 0:58 ` Liu Bo
2019-04-29 13:18 ` Vivek Goyal
2019-04-30 1:38 ` Liu Bo
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20190416193837.GE2222@redhat.com \
--to=vgoyal@redhat.com \
--cc=bo.liu@linux.alibaba.com \
--cc=mszeredi@redhat.com \
--cc=virtio-fs@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.