From: Jan Kara <jack@suse.cz>
To: Goldwyn Rodrigues <rgoldwyn@suse.de>
Cc: linux-fsdevel@vger.kernel.org, jack@suse.com, hch@infradead.org,
linux-block@vger.kernel.org, linux-btrfs@vger.kernel.org,
linux-ext4@vger.kernel.org, linux-xfs@vger.kernel.org,
axboe@kernel.dk, linux-api@vger.kernel.org,
adam.manzanares@wdc.com, viro@zeniv.linux.org.uk,
Goldwyn Rodrigues <rgoldwyn@suse.com>
Subject: Re: [PATCH 05/10] fs: return if direct write will trigger writeback
Date: Thu, 25 May 2017 10:32:32 +0200 [thread overview]
Message-ID: <20170525083232.GF28950@quack2.suse.cz> (raw)
In-Reply-To: <20170524164150.9492-6-rgoldwyn@suse.de>
On Wed 24-05-17 11:41:45, Goldwyn Rodrigues wrote:
> From: Goldwyn Rodrigues <rgoldwyn@suse.com>
>
> Find out if the write will trigger a wait due to writeback. If yes,
> return -EAGAIN.
>
> Return -EINVAL for buffered AIO: there are multiple causes of
> delay such as page locks, dirty throttling logic, page loading
> from disk etc. which cannot be taken care of.
>
> Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
> Reviewed-by: Christoph Hellwig <hch@lst.de>
Looks good. You can add:
Reviewed-by: Jan Kara <jack@suse.cz>
Honza
> ---
> mm/filemap.c | 17 ++++++++++++++---
> 1 file changed, 14 insertions(+), 3 deletions(-)
>
> diff --git a/mm/filemap.c b/mm/filemap.c
> index 097213275461..bc146efa6815 100644
> --- a/mm/filemap.c
> +++ b/mm/filemap.c
> @@ -2675,6 +2675,9 @@ inline ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from)
>
> pos = iocb->ki_pos;
>
> + if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT))
> + return -EINVAL;
> +
> if (limit != RLIM_INFINITY) {
> if (iocb->ki_pos >= limit) {
> send_sig(SIGXFSZ, current, 0);
> @@ -2743,9 +2746,17 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from)
> write_len = iov_iter_count(from);
> end = (pos + write_len - 1) >> PAGE_SHIFT;
>
> - written = filemap_write_and_wait_range(mapping, pos, pos + write_len - 1);
> - if (written)
> - goto out;
> + if (iocb->ki_flags & IOCB_NOWAIT) {
> + /* If there are pages to writeback, return */
> + if (filemap_range_has_page(inode->i_mapping, pos,
> + pos + iov_iter_count(from)))
> + return -EAGAIN;
> + } else {
> + written = filemap_write_and_wait_range(mapping, pos,
> + pos + write_len - 1);
> + if (written)
> + goto out;
> + }
>
> /*
> * After a write we want buffered reads to be sure to go to disk to get
> --
> 2.12.0
>
--
Jan Kara <jack@suse.com>
SUSE Labs, CR
next prev parent reply other threads:[~2017-05-25 8:32 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-05-24 16:41 [PATCH 0/10 v9] No wait AIO Goldwyn Rodrigues
2017-05-24 16:41 ` [PATCH 01/10] fs: Separate out kiocb flags setup based on RWF_* flags Goldwyn Rodrigues
2017-05-25 8:16 ` Jan Kara
2017-05-24 16:41 ` [PATCH 02/10] fs: Introduce filemap_range_has_page() Goldwyn Rodrigues
2017-05-25 8:25 ` Jan Kara
[not found] ` <20170524164150.9492-1-rgoldwyn-l3A5Bk7waGM@public.gmane.org>
2017-05-24 16:41 ` [PATCH 03/10] fs: Use RWF_* flags for AIO operations Goldwyn Rodrigues
2017-05-25 8:27 ` Jan Kara
2017-05-24 16:41 ` [PATCH 05/10] fs: return if direct write will trigger writeback Goldwyn Rodrigues
2017-05-25 8:32 ` Jan Kara [this message]
2017-05-28 9:27 ` [PATCH 0/10 v9] No wait AIO Christoph Hellwig
2017-05-29 2:38 ` Goldwyn Rodrigues
2017-05-29 8:32 ` Christoph Hellwig
2017-05-24 16:41 ` [PATCH 04/10] fs: Introduce RWF_NOWAIT Goldwyn Rodrigues
2017-05-25 8:30 ` Jan Kara
2017-05-24 16:41 ` [PATCH 06/10] fs: Introduce IOMAP_NOWAIT Goldwyn Rodrigues
2017-05-25 8:33 ` Jan Kara
2017-05-24 16:41 ` [PATCH 07/10] fs: return on congested block device Goldwyn Rodrigues
2017-05-24 16:41 ` [PATCH 08/10] ext4: nowait aio support Goldwyn Rodrigues
2017-05-24 16:41 ` [PATCH 09/10] xfs: " Goldwyn Rodrigues
2017-05-24 16:49 ` Darrick J. Wong
[not found] ` <20170524164150.9492-10-rgoldwyn-l3A5Bk7waGM@public.gmane.org>
2017-05-28 9:31 ` Christoph Hellwig
2017-05-29 2:38 ` Goldwyn Rodrigues
2017-05-29 8:21 ` Jan Kara
2017-05-29 8:33 ` Christoph Hellwig
[not found] ` <20170529083338.GC1899-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org>
2017-05-30 16:13 ` Goldwyn Rodrigues
2017-05-31 8:51 ` Jan Kara
2017-05-24 16:41 ` [PATCH 10/10] btrfs: " Goldwyn Rodrigues
-- strict thread matches above, loose matches on Subject: below --
2017-06-15 15:59 [PATCH 0/10 v12] No wait AIO Goldwyn Rodrigues
2017-06-15 15:59 ` [PATCH 05/10] fs: return if direct write will trigger writeback Goldwyn Rodrigues
2017-06-06 11:19 [PATCH 0/10 v11] No wait AIO Goldwyn Rodrigues
2017-06-06 11:19 ` [PATCH 05/10] fs: return if direct write will trigger writeback Goldwyn Rodrigues
2017-06-05 5:35 [PATCH 0/10 v10] No wait AIO Goldwyn Rodrigues
2017-06-05 5:35 ` [PATCH 05/10] fs: return if direct write will trigger writeback Goldwyn Rodrigues
2017-05-11 19:17 [PATCH 0/10 v8] No wait AIO Goldwyn Rodrigues
2017-05-11 19:17 ` [PATCH 05/10] fs: return if direct write will trigger writeback Goldwyn Rodrigues
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=20170525083232.GF28950@quack2.suse.cz \
--to=jack@suse.cz \
--cc=adam.manzanares@wdc.com \
--cc=axboe@kernel.dk \
--cc=hch@infradead.org \
--cc=jack@suse.com \
--cc=linux-api@vger.kernel.org \
--cc=linux-block@vger.kernel.org \
--cc=linux-btrfs@vger.kernel.org \
--cc=linux-ext4@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-xfs@vger.kernel.org \
--cc=rgoldwyn@suse.com \
--cc=rgoldwyn@suse.de \
--cc=viro@zeniv.linux.org.uk \
/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).