From: Brian Foster <bfoster@redhat.com>
To: Goldwyn Rodrigues <rgoldwyn@suse.de>
Cc: linux-xfs@vger.kernel.org, darrick.wong@oracle.com,
david@fromorbit.com, Goldwyn Rodrigues <rgoldwyn@suse.com>
Subject: Re: [PATCH v2 1/3] xfs_io: Add support for pwritev2()
Date: Mon, 9 Oct 2017 11:02:19 -0400 [thread overview]
Message-ID: <20171009150219.GA19322@bfoster.bfoster> (raw)
In-Reply-To: <20170929130035.24760-1-rgoldwyn@suse.de>
On Fri, Sep 29, 2017 at 08:00:33AM -0500, Goldwyn Rodrigues wrote:
> From: Goldwyn Rodrigues <rgoldwyn@suse.com>
>
> Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
> ---
> configure.ac | 1 +
> include/builddefs.in | 1 +
> io/Makefile | 4 ++++
> io/pwrite.c | 39 ++++++++++++++++++++++++++-------------
> m4/package_libcdev.m4 | 16 ++++++++++++++++
> 5 files changed, 48 insertions(+), 13 deletions(-)
>
...
> diff --git a/io/pwrite.c b/io/pwrite.c
> index 1c5dfca1..e7d411bb 100644
> --- a/io/pwrite.c
> +++ b/io/pwrite.c
...
> @@ -111,7 +120,8 @@ write_random(
> off64_t offset,
> long long count,
> unsigned int seed,
> - long long *total)
> + long long *total,
> + int pwritev2_flags)
> {
> off64_t off, range;
> ssize_t bytes;
> @@ -133,7 +143,7 @@ write_random(
> buffersize;
> else
> off = offset;
> - bytes = do_pwrite(file->fd, off, buffersize, buffersize);
> + bytes = do_pwrite(file->fd, off, buffersize, buffersize, pwritev2_flags);
Looks like a couple or so long lines here and below. We usually wrap
lines at 80 chars. Otherwise this seems fine to me.
Brian
> if (bytes == 0)
> break;
> if (bytes < 0) {
> @@ -153,7 +163,8 @@ static int
> write_backward(
> off64_t offset,
> long long *count,
> - long long *total)
> + long long *total,
> + int pwritev2_flags)
> {
> off64_t end, off = offset;
> ssize_t bytes = 0, bytes_requested;
> @@ -171,7 +182,7 @@ write_backward(
> if ((bytes_requested = (off % buffersize))) {
> bytes_requested = min(cnt, bytes_requested);
> off -= bytes_requested;
> - bytes = do_pwrite(file->fd, off, bytes_requested, buffersize);
> + bytes = do_pwrite(file->fd, off, bytes_requested, buffersize, pwritev2_flags);
> if (bytes == 0)
> return ops;
> if (bytes < 0) {
> @@ -189,7 +200,7 @@ write_backward(
> while (cnt > end) {
> bytes_requested = min(cnt, buffersize);
> off -= bytes_requested;
> - bytes = do_pwrite(file->fd, off, cnt, buffersize);
> + bytes = do_pwrite(file->fd, off, cnt, buffersize, pwritev2_flags);
> if (bytes == 0)
> break;
> if (bytes < 0) {
> @@ -212,7 +223,8 @@ write_buffer(
> size_t bs,
> int fd,
> off64_t skip,
> - long long *total)
> + long long *total,
> + int pwritev2_flags)
> {
> ssize_t bytes;
> long long bar = min(bs, count);
> @@ -224,7 +236,7 @@ write_buffer(
> if (read_buffer(fd, skip + *total, bs, &bar, 0, 1) < 0)
> break;
> }
> - bytes = do_pwrite(file->fd, offset, count, bar);
> + bytes = do_pwrite(file->fd, offset, count, bar, pwritev2_flags);
> if (bytes == 0)
> break;
> if (bytes < 0) {
> @@ -258,6 +270,7 @@ pwrite_f(
> int Cflag, qflag, uflag, dflag, wflag, Wflag;
> int direction = IO_FORWARD;
> int c, fd = -1;
> + int pwritev2_flags = 0;
>
> Cflag = qflag = uflag = dflag = wflag = Wflag = 0;
> init_cvtnum(&fsblocksize, &fssectsize);
> @@ -365,13 +378,13 @@ pwrite_f(
> case IO_RANDOM:
> if (!zeed) /* srandom seed */
> zeed = time(NULL);
> - c = write_random(offset, count, zeed, &total);
> + c = write_random(offset, count, zeed, &total, pwritev2_flags);
> break;
> case IO_FORWARD:
> - c = write_buffer(offset, count, bsize, fd, skip, &total);
> + c = write_buffer(offset, count, bsize, fd, skip, &total, pwritev2_flags);
> break;
> case IO_BACKWARD:
> - c = write_backward(offset, &count, &total);
> + c = write_backward(offset, &count, &total, pwritev2_flags);
> break;
> default:
> total = 0;
> diff --git a/m4/package_libcdev.m4 b/m4/package_libcdev.m4
> index fa5b6397..48da0783 100644
> --- a/m4/package_libcdev.m4
> +++ b/m4/package_libcdev.m4
> @@ -146,6 +146,22 @@ AC_DEFUN([AC_HAVE_PREADV],
> AC_SUBST(have_preadv)
> ])
>
> +#
> +# Check if we have a pwritev2 libc call (Linux)
> +#
> +AC_DEFUN([AC_HAVE_PWRITEV2],
> + [ AC_MSG_CHECKING([for pwritev2])
> + AC_TRY_LINK([
> +#define _BSD_SOURCE
> +#include <sys/uio.h>
> + ], [
> + pwritev2(0, 0, 0, 0, 0);
> + ], have_pwritev2=yes
> + AC_MSG_RESULT(yes),
> + AC_MSG_RESULT(no))
> + AC_SUBST(have_pwritev2)
> + ])
> +
> #
> # Check if we have a copy_file_range system call (Linux)
> #
> --
> 2.14.1
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-xfs" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
prev parent reply other threads:[~2017-10-09 15:02 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-09-29 13:00 [PATCH v2 1/3] xfs_io: Add support for pwritev2() Goldwyn Rodrigues
2017-09-29 13:00 ` [PATCH v2 2/3] xfs_io: Add RWF_NOWAIT to pwritev2() Goldwyn Rodrigues
2017-10-09 15:02 ` Brian Foster
2017-10-09 17:19 ` Darrick J. Wong
2017-10-09 21:11 ` Goldwyn Rodrigues
2017-10-09 22:37 ` Dave Chinner
2017-10-09 22:51 ` Goldwyn Rodrigues
2017-09-29 13:00 ` [PATCH v2 3/3] xfs_io: Allow partial writes Goldwyn Rodrigues
2017-10-09 15:02 ` Brian Foster
2017-10-09 17:15 ` Darrick J. Wong
2017-10-09 11:14 ` [PATCH v2 1/3] xfs_io: Add support for pwritev2() Goldwyn Rodrigues
2017-10-09 15:02 ` Brian Foster [this message]
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=20171009150219.GA19322@bfoster.bfoster \
--to=bfoster@redhat.com \
--cc=darrick.wong@oracle.com \
--cc=david@fromorbit.com \
--cc=linux-xfs@vger.kernel.org \
--cc=rgoldwyn@suse.com \
--cc=rgoldwyn@suse.de \
/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.