All of lore.kernel.org
 help / color / mirror / Atom feed
From: Goldwyn Rodrigues <rgoldwyn@suse.de>
To: linux-fsdevel@vger.kernel.org
Cc: 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: [PATCH 05/10] fs: return if direct write will trigger writeback
Date: Wed, 24 May 2017 11:41:45 -0500	[thread overview]
Message-ID: <20170524164150.9492-6-rgoldwyn@suse.de> (raw)
In-Reply-To: <20170524164150.9492-1-rgoldwyn@suse.de>

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>
---
 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

WARNING: multiple messages have this Message-ID (diff)
From: Goldwyn Rodrigues <rgoldwyn-l3A5Bk7waGM@public.gmane.org>
To: linux-fsdevel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
Cc: jack-IBi9RG/b67k@public.gmane.org,
	hch-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org,
	linux-block-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
	linux-btrfs-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
	linux-ext4-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
	linux-xfs-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
	axboe-tSWWG44O7X1aa/9Udqfwiw@public.gmane.org,
	linux-api-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
	adam.manzanares-Sjgp3cTcYWE@public.gmane.org,
	viro-RmSDqhL/yNMiFSDQTTA3OLVCufUGDwFn@public.gmane.org,
	Goldwyn Rodrigues <rgoldwyn-IBi9RG/b67k@public.gmane.org>
Subject: [PATCH 05/10] fs: return if direct write will trigger writeback
Date: Wed, 24 May 2017 11:41:45 -0500	[thread overview]
Message-ID: <20170524164150.9492-6-rgoldwyn@suse.de> (raw)
In-Reply-To: <20170524164150.9492-1-rgoldwyn-l3A5Bk7waGM@public.gmane.org>

From: Goldwyn Rodrigues <rgoldwyn-IBi9RG/b67k@public.gmane.org>

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-IBi9RG/b67k@public.gmane.org>
Reviewed-by: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
---
 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

  parent reply	other threads:[~2017-05-24 16:41 UTC|newest]

Thread overview: 36+ 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
2017-05-24 16:41 ` [PATCH 03/10] fs: Use RWF_* flags for AIO operations Goldwyn Rodrigues
2017-05-24 16:41   ` Goldwyn Rodrigues
2017-05-25  8:27   ` Jan Kara
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 ` Goldwyn Rodrigues [this message]
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
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
2017-05-28  9:31   ` Christoph Hellwig
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
2017-05-30 16:13         ` Goldwyn Rodrigues
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
2017-05-28  9:27 ` [PATCH 0/10 v9] No wait AIO Christoph Hellwig
2017-05-28  9:27   ` Christoph Hellwig
2017-05-29  2:38   ` Goldwyn Rodrigues
2017-05-29  8:32     ` Christoph Hellwig
  -- strict thread matches above, loose matches on Subject: below --
2017-06-15 15:59 [PATCH 0/10 v12] " 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=20170524164150.9492-6-rgoldwyn@suse.de \
    --to=rgoldwyn@suse.de \
    --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=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 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.