From: Christoph Hellwig <hch@infradead.org>
To: Jaegeuk Kim <jaegeuk@kernel.org>
Cc: linux-block@vger.kernel.org, linux-fsdevel@vger.kernel.org,
linux-kernel@vger.kernel.org,
linux-f2fs-devel@lists.sourceforge.net
Subject: Re: [f2fs-dev] [PATCH] f2fs: provide a way to attach HIPRI for Direct IO
Date: Tue, 9 Nov 2021 08:39:53 -0800 [thread overview]
Message-ID: <YYqkWWZZsMW49/xu@infradead.org> (raw)
In-Reply-To: <20211109021336.3796538-1-jaegeuk@kernel.org>
On Mon, Nov 08, 2021 at 06:13:36PM -0800, Jaegeuk Kim wrote:
> This patch adds a way to attach HIPRI by expanding the existing sysfs's
> data_io_flag. User can measure IO performance by enabling it.
NAK. This flag should only be used when explicitly specified by
the submitter of the I/O.
>
> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
> ---
> Documentation/ABI/testing/sysfs-fs-f2fs | 16 +++++++++-------
> fs/f2fs/data.c | 2 ++
> fs/f2fs/f2fs.h | 3 +++
> 3 files changed, 14 insertions(+), 7 deletions(-)
>
> diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs
> index b268e3e18b4a..ac52e1c6bcbc 100644
> --- a/Documentation/ABI/testing/sysfs-fs-f2fs
> +++ b/Documentation/ABI/testing/sysfs-fs-f2fs
> @@ -369,13 +369,15 @@ Contact: "Jaegeuk Kim" <jaegeuk@kernel.org>
> Description: Give a way to attach REQ_META|FUA to data writes
> given temperature-based bits. Now the bits indicate:
>
> - +-------------------+-------------------+
> - | REQ_META | REQ_FUA |
> - +------+------+-----+------+------+-----+
> - | 5 | 4 | 3 | 2 | 1 | 0 |
> - +------+------+-----+------+------+-----+
> - | Cold | Warm | Hot | Cold | Warm | Hot |
> - +------+------+-----+------+------+-----+
> + +------------+-------------------+-------------------+
> + | HIPRI_DIO | REQ_META | REQ_FUA |
> + +------------+------+------+-----+------+------+-----+
> + | 6 | 5 | 4 | 3 | 2 | 1 | 0 |
> + +------------+------+------+-----+------+------+-----+
> + | All | Cold | Warm | Hot | Cold | Warm | Hot |
> + +------------+------+------+-----+------+------+-----+
> +
> + Note that, HIPRI_DIO bit is only for direct IO path.
>
> What: /sys/fs/f2fs/<disk>/node_io_flag
> Date: June 2020
> diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
> index 9f754aaef558..faa40aca2848 100644
> --- a/fs/f2fs/data.c
> +++ b/fs/f2fs/data.c
> @@ -3707,6 +3707,8 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
> if (do_opu)
> down_read(&fi->i_gc_rwsem[READ]);
> }
> + if (sbi->data_io_flag & HIPRI_DIO)
> + iocb->ki_flags |= IOCB_HIPRI;
>
> err = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
> iter, rw == WRITE ? get_data_block_dio_write :
> diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
> index ce9fc9f13000..094f1e8ff82b 100644
> --- a/fs/f2fs/f2fs.h
> +++ b/fs/f2fs/f2fs.h
> @@ -1557,6 +1557,9 @@ struct decompress_io_ctx {
> #define MAX_COMPRESS_LOG_SIZE 8
> #define MAX_COMPRESS_WINDOW_SIZE(log_size) ((PAGE_SIZE) << (log_size))
>
> +/* HIPRI for direct IO used in sysfs/data_io_flag */
> +#define HIPRI_DIO (1 << 6)
> +
> struct f2fs_sb_info {
> struct super_block *sb; /* pointer to VFS super block */
> struct proc_dir_entry *s_proc; /* proc entry */
> --
> 2.34.0.rc0.344.g81b53c2807-goog
>
---end quoted text---
_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel
next prev parent reply other threads:[~2021-11-09 16:40 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-11-09 2:13 [f2fs-dev] [PATCH] f2fs: provide a way to attach HIPRI for Direct IO Jaegeuk Kim
2021-11-09 14:13 ` Chao Yu
2021-11-09 16:39 ` Christoph Hellwig [this message]
2021-11-09 16:42 ` Jens Axboe
2021-11-10 19:08 ` Jaegeuk Kim
2021-11-11 0:26 ` Jens Axboe
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=YYqkWWZZsMW49/xu@infradead.org \
--to=hch@infradead.org \
--cc=jaegeuk@kernel.org \
--cc=linux-block@vger.kernel.org \
--cc=linux-f2fs-devel@lists.sourceforge.net \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).