All of lore.kernel.org
 help / color / mirror / Atom feed
From: Naohiro Aota <naohiro.aota@wdc.com>
To: linux-btrfs@vger.kernel.org, David Sterba <dsterba@suse.com>
Cc: Chris Mason <clm@fb.com>, Josef Bacik <josef@toxicpanda.com>,
	Hannes Reinecke <hare@suse.com>,
	linux-fsdevel@vger.kernel.org,
	Naohiro Aota <naohiro.aota@wdc.com>
Subject: [PATCH v7 20/39] btrfs: limit ordered extent size to max_zone_append_size
Date: Fri, 11 Sep 2020 21:32:40 +0900	[thread overview]
Message-ID: <20200911123259.3782926-21-naohiro.aota@wdc.com> (raw)
In-Reply-To: <20200911123259.3782926-1-naohiro.aota@wdc.com>

With zone append writing, the logical address must be modified to match the
actual written physical address. If multiple bios serve one ordered extent,
the bios can reside in a non-contiguous physical region, resulting in the
non-contiguous logical region. It is troublesome to handle such a case, so
one ordered extent must be served by one bio, limited to
max_zone_apend_size. Thus, this commit limits the size of an ordered extent
as well.

This size limitation results in file extents fragmentation. In the future,
we can merge contiguous ordered extents as an optimization.

Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
---
 fs/btrfs/extent_io.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 63cdf67e6885..c21d1dbe314e 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1865,6 +1865,7 @@ noinline_for_stack bool find_lock_delalloc_range(struct inode *inode,
 				    u64 *end)
 {
 	struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	u64 max_bytes = BTRFS_MAX_EXTENT_SIZE;
 	u64 delalloc_start;
 	u64 delalloc_end;
@@ -1873,6 +1874,10 @@ noinline_for_stack bool find_lock_delalloc_range(struct inode *inode,
 	int ret;
 	int loops = 0;
 
+	if (fs_info && fs_info->max_zone_append_size)
+		max_bytes = ALIGN_DOWN(fs_info->max_zone_append_size,
+				       PAGE_SIZE);
+
 again:
 	/* step one, find a bunch of delalloc bytes starting at start */
 	delalloc_start = *start;
-- 
2.27.0


  parent reply	other threads:[~2020-09-11 17:42 UTC|newest]

Thread overview: 51+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-09-11 12:32 [PATCH v7 00/39] btrfs: zoned block device support Naohiro Aota
2020-09-11 12:32 ` [PATCH v7 01/39] btrfs: introduce ZONED feature flag Naohiro Aota
2020-09-11 12:32 ` [PATCH v7 02/39] btrfs: Get zone information of zoned block devices Naohiro Aota
2020-09-11 12:32 ` [PATCH v7 03/39] btrfs: Check and enable ZONED mode Naohiro Aota
2020-09-11 12:32 ` [PATCH v7 04/39] btrfs: introduce max_zone_append_size Naohiro Aota
2020-09-11 12:32 ` [PATCH v7 05/39] btrfs: disallow space_cache in ZONED mode Naohiro Aota
2020-09-11 12:32 ` [PATCH v7 06/39] btrfs: disallow NODATACOW " Naohiro Aota
2020-09-11 12:32 ` [PATCH v7 07/39] btrfs: disable fallocate " Naohiro Aota
2020-09-11 12:32 ` [PATCH v7 08/39] btrfs: disallow mixed-bg " Naohiro Aota
2020-09-11 12:32 ` [PATCH v7 09/39] btrfs: disallow inode_cache " Naohiro Aota
2020-09-11 12:32 ` [PATCH v7 10/39] btrfs: implement log-structured superblock for " Naohiro Aota
2020-09-11 12:32 ` [PATCH v7 11/39] btrfs: implement zoned chunk allocator Naohiro Aota
2020-09-11 12:32 ` [PATCH v7 12/39] btrfs: verify device extent is aligned to zone Naohiro Aota
2020-09-11 12:32 ` [PATCH v7 13/39] btrfs: load zone's alloction offset Naohiro Aota
2020-09-11 12:32 ` [PATCH v7 14/39] btrfs: emulate write pointer for conventional zones Naohiro Aota
2020-09-11 12:32 ` [PATCH v7 15/39] btrfs: track unusable bytes for zones Naohiro Aota
2020-09-11 12:32 ` [PATCH v7 16/39] btrfs: do sequential extent allocation in ZONED mode Naohiro Aota
2020-09-11 12:32 ` [PATCH v7 17/39] btrfs: reset zones of unused block groups Naohiro Aota
2020-09-11 12:32 ` [PATCH v7 18/39] btrfs: redirty released extent buffers in ZONED mode Naohiro Aota
2020-09-14 11:48   ` Johannes Thumshirn
2020-09-11 12:32 ` [PATCH v7 19/39] btrfs: limit bio size under max_zone_append_size Naohiro Aota
2020-09-11 14:17   ` Christoph Hellwig
2020-09-12  4:14     ` Naohiro Aota
2020-09-12  5:30       ` Christoph Hellwig
2020-09-17  5:32         ` Naohiro Aota
2020-09-11 12:32 ` Naohiro Aota [this message]
2020-09-11 12:32 ` [PATCH v7 21/39] btrfs: extend btrfs_rmap_block for specifying a device Naohiro Aota
2020-09-11 12:32 ` [PATCH v7 22/39] btrfs: use ZONE_APPEND write for ZONED btrfs Naohiro Aota
2020-09-11 12:32 ` [PATCH v7 23/39] btrfs: handle REQ_OP_ZONE_APPEND as writing Naohiro Aota
2020-09-11 12:32 ` [PATCH v7 24/39] btrfs: enable zone append writing for direct IO Naohiro Aota
2020-09-11 12:32 ` [PATCH v7 25/39] btrfs: introduce dedicated data write path for ZONED mode Naohiro Aota
2020-09-11 12:32 ` [PATCH v7 26/39] btrfs: serialize meta IOs on " Naohiro Aota
2020-09-11 12:32 ` [PATCH v7 27/39] btrfs: wait existing extents before truncating Naohiro Aota
2020-09-11 12:32 ` [PATCH v7 28/39] btrfs: avoid async metadata checksum on ZONED mode Naohiro Aota
2020-09-11 12:32 ` [PATCH v7 29/39] btrfs: mark block groups to copy for device-replace Naohiro Aota
2020-09-11 12:32 ` [PATCH v7 30/39] btrfs: implement cloning for ZONED device-replace Naohiro Aota
2020-09-11 12:32 ` [PATCH v7 31/39] btrfs: implement copying " Naohiro Aota
2020-09-11 12:32 ` [PATCH v7 32/39] btrfs: support dev-replace in ZONED mode Naohiro Aota
2020-09-11 12:32 ` [PATCH v7 33/39] btrfs: enable relocation " Naohiro Aota
2020-09-11 12:32 ` [PATCH v7 34/39] btrfs: relocate block group to repair IO failure in ZONED Naohiro Aota
2020-09-11 12:32 ` [PATCH v7 35/39] btrfs: split alloc_log_tree() Naohiro Aota
2020-09-11 12:32 ` [PATCH v7 36/39] btrfs: extend zoned allocator to use dedicated tree-log block group Naohiro Aota
2020-09-11 12:32 ` [PATCH v7 37/39] btrfs: serialize log transaction on ZONED mode Naohiro Aota
2020-09-11 12:32 ` [PATCH v7 38/39] btrfs: reorder log node allocation Naohiro Aota
2020-09-11 12:32 ` [PATCH v7 39/39] btrfs: enable to mount ZONED incompat flag Naohiro Aota
2020-09-15  8:09 ` [PATCH v7 00/39] btrfs: zoned block device support David Sterba
2020-09-16 17:42   ` Johannes Thumshirn
2020-09-16 19:46     ` David Sterba
2020-09-16 19:50       ` Johannes Thumshirn
2020-09-17  5:40     ` Naohiro Aota
2020-09-17  7:14       ` Johannes Thumshirn

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=20200911123259.3782926-21-naohiro.aota@wdc.com \
    --to=naohiro.aota@wdc.com \
    --cc=clm@fb.com \
    --cc=dsterba@suse.com \
    --cc=hare@suse.com \
    --cc=josef@toxicpanda.com \
    --cc=linux-btrfs@vger.kernel.org \
    --cc=linux-fsdevel@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 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.