public inbox for [email protected]
 help / color / mirror / Atom feed
From: Stefan Roesch <[email protected]>
To: <[email protected]>, <[email protected]>,
	<[email protected]>, <[email protected]>,
	<[email protected]>
Cc: <[email protected]>, <[email protected]>, <[email protected]>,
	<[email protected]>, <[email protected]>, <[email protected]>,
	Christoph Hellwig <[email protected]>
Subject: [PATCH v9 05/14] iomap: Add async buffered write support
Date: Thu, 16 Jun 2022 14:22:12 -0700	[thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <[email protected]>

This adds async buffered write support to iomap.

This replaces the call to balance_dirty_pages_ratelimited() with the
call to balance_dirty_pages_ratelimited_flags. This allows to specify if
the write request is async or not.

In addition this also moves the above function call to the beginning of
the function. If the function call is at the end of the function and the
decision is made to throttle writes, then there is no request that
io-uring can wait on. By moving it to the beginning of the function, the
write request is not issued, but returns -EAGAIN instead. io-uring will
punt the request and process it in the io-worker.

By moving the function call to the beginning of the function, the write
throttling will happen one page later.

Signed-off-by: Stefan Roesch <[email protected]>
Reviewed-by: Jan Kara <[email protected]>
Reviewed-by: Christoph Hellwig <[email protected]>
---
 fs/iomap/buffered-io.c | 33 ++++++++++++++++++++++++++++-----
 1 file changed, 28 insertions(+), 5 deletions(-)

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 3c97b713f831..83cf093fcb92 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -559,6 +559,7 @@ static int __iomap_write_begin(const struct iomap_iter *iter, loff_t pos,
 	loff_t block_size = i_blocksize(iter->inode);
 	loff_t block_start = round_down(pos, block_size);
 	loff_t block_end = round_up(pos + len, block_size);
+	unsigned int nr_blocks = i_blocks_per_folio(iter->inode, folio);
 	size_t from = offset_in_folio(folio, pos), to = from + len;
 	size_t poff, plen;
 
@@ -567,6 +568,8 @@ static int __iomap_write_begin(const struct iomap_iter *iter, loff_t pos,
 	folio_clear_error(folio);
 
 	iop = iomap_page_create(iter->inode, folio, iter->flags);
+	if ((iter->flags & IOMAP_NOWAIT) && !iop && nr_blocks > 1)
+		return -EAGAIN;
 
 	do {
 		iomap_adjust_read_range(iter->inode, folio, &block_start,
@@ -584,7 +587,12 @@ static int __iomap_write_begin(const struct iomap_iter *iter, loff_t pos,
 				return -EIO;
 			folio_zero_segments(folio, poff, from, to, poff + plen);
 		} else {
-			int status = iomap_read_folio_sync(block_start, folio,
+			int status;
+
+			if (iter->flags & IOMAP_NOWAIT)
+				return -EAGAIN;
+
+			status = iomap_read_folio_sync(block_start, folio,
 					poff, plen, srcmap);
 			if (status)
 				return status;
@@ -613,6 +621,9 @@ static int iomap_write_begin(const struct iomap_iter *iter, loff_t pos,
 	unsigned fgp = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE | FGP_NOFS;
 	int status = 0;
 
+	if (iter->flags & IOMAP_NOWAIT)
+		fgp |= FGP_NOWAIT;
+
 	BUG_ON(pos + len > iter->iomap.offset + iter->iomap.length);
 	if (srcmap != &iter->iomap)
 		BUG_ON(pos + len > srcmap->offset + srcmap->length);
@@ -632,7 +643,7 @@ static int iomap_write_begin(const struct iomap_iter *iter, loff_t pos,
 	folio = __filemap_get_folio(iter->inode->i_mapping, pos >> PAGE_SHIFT,
 			fgp, mapping_gfp_mask(iter->inode->i_mapping));
 	if (!folio) {
-		status = -ENOMEM;
+		status = (iter->flags & IOMAP_NOWAIT) ? -EAGAIN : -ENOMEM;
 		goto out_no_page;
 	}
 	if (pos + len > folio_pos(folio) + folio_size(folio))
@@ -750,6 +761,8 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
 	loff_t pos = iter->pos;
 	ssize_t written = 0;
 	long status = 0;
+	struct address_space *mapping = iter->inode->i_mapping;
+	unsigned int bdp_flags = (iter->flags & IOMAP_NOWAIT) ? BDP_ASYNC : 0;
 
 	do {
 		struct folio *folio;
@@ -762,6 +775,11 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
 		bytes = min_t(unsigned long, PAGE_SIZE - offset,
 						iov_iter_count(i));
 again:
+		status = balance_dirty_pages_ratelimited_flags(mapping,
+							       bdp_flags);
+		if (unlikely(status))
+			break;
+
 		if (bytes > length)
 			bytes = length;
 
@@ -770,6 +788,10 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
 		 * Otherwise there's a nasty deadlock on copying from the
 		 * same page as we're writing to, without it being marked
 		 * up-to-date.
+		 *
+		 * For async buffered writes the assumption is that the user
+		 * page has already been faulted in. This can be optimized by
+		 * faulting the user page.
 		 */
 		if (unlikely(fault_in_iov_iter_readable(i, bytes) == bytes)) {
 			status = -EFAULT;
@@ -781,7 +803,7 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
 			break;
 
 		page = folio_file_page(folio, pos >> PAGE_SHIFT);
-		if (mapping_writably_mapped(iter->inode->i_mapping))
+		if (mapping_writably_mapped(mapping))
 			flush_dcache_page(page);
 
 		copied = copy_page_from_iter_atomic(page, offset, bytes, i);
@@ -806,8 +828,6 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
 		pos += status;
 		written += status;
 		length -= status;
-
-		balance_dirty_pages_ratelimited(iter->inode->i_mapping);
 	} while (iov_iter_count(i) && length);
 
 	return written ? written : status;
@@ -825,6 +845,9 @@ iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *i,
 	};
 	int ret;
 
+	if (iocb->ki_flags & IOCB_NOWAIT)
+		iter.flags |= IOMAP_NOWAIT;
+
 	while ((ret = iomap_iter(&iter, ops)) > 0)
 		iter.processed = iomap_write_iter(&iter, i);
 	if (iter.pos == iocb->ki_pos)
-- 
2.30.2



  parent reply	other threads:[~2022-06-16 21:52 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-06-16 21:22 [PATCH v9 00/14] io-uring/xfs: support async buffered writes Stefan Roesch
2022-06-16 21:22 ` [PATCH v9 01/14] mm: Move starting of background writeback into the main balancing loop Stefan Roesch
2022-06-16 21:22 ` [PATCH v9 02/14] mm: Move updates of dirty_exceeded into one place Stefan Roesch
2022-06-16 21:22 ` [PATCH v9 03/14] mm: Add balance_dirty_pages_ratelimited_flags() function Stefan Roesch
2022-06-16 21:22 ` [PATCH v9 04/14] iomap: Add flags parameter to iomap_page_create() Stefan Roesch
2022-06-16 21:22 ` Stefan Roesch [this message]
2022-06-16 21:22 ` [PATCH v9 06/14] iomap: Return -EAGAIN from iomap_write_iter() Stefan Roesch
2022-06-16 21:22 ` [PATCH v9 07/14] fs: Add check for async buffered writes to generic_write_checks Stefan Roesch
2022-06-16 21:22 ` [PATCH v9 08/14] fs: add __remove_file_privs() with flags parameter Stefan Roesch
2022-06-16 21:22 ` [PATCH v9 09/14] fs: Split off inode_needs_update_time and __file_update_time Stefan Roesch
2022-06-16 21:22 ` [PATCH v9 10/14] fs: Add async write file modification handling Stefan Roesch
2022-06-16 21:22 ` [PATCH v9 11/14] io_uring: Add support for async buffered writes Stefan Roesch
2022-06-16 21:22 ` [PATCH v9 12/14] io_uring: Add tracepoint for short writes Stefan Roesch
2022-06-16 21:22 ` [PATCH v9 13/14] xfs: Specify lockmode when calling xfs_ilock_for_iomap() Stefan Roesch
2022-06-16 21:22 ` [PATCH v9 14/14] xfs: Add async buffered write support Stefan Roesch
2022-06-22 17:41 ` [PATCH v9 00/14] io-uring/xfs: support async buffered writes Jens Axboe
     [not found]   ` <[email protected]>
2022-06-22 19:37     ` Jens Axboe
2022-06-22 21:24   ` Jan Kara
2022-06-22 22:27 ` Jens Axboe
2022-06-23  0:29   ` Darrick J. Wong
2022-06-23  0:50     ` 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 \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    /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