Linux-BTRFS Archive on lore.kernel.org
 help / color / 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>,
	Nikolay Borisov <nborisov@suse.com>,
	Damien Le Moal <damien.lemoal@wdc.com>,
	Matias Bjorling <Matias.Bjorling@wdc.com>,
	Johannes Thumshirn <jthumshirn@suse.de>,
	Hannes Reinecke <hare@suse.com>,
	linux-fsdevel@vger.kernel.org,
	Naohiro Aota <naohiro.aota@wdc.com>
Subject: [PATCH v3 13/27] btrfs: reset zones of unused block groups
Date: Thu,  8 Aug 2019 18:30:24 +0900
Message-ID: <20190808093038.4163421-14-naohiro.aota@wdc.com> (raw)
In-Reply-To: <20190808093038.4163421-1-naohiro.aota@wdc.com>

For an HMZONED volume, a block group maps to a zone of the device. For
deleted unused block groups, the zone of the block group can be reset to
rewind the zone write pointer at the start of the zone.

Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
---
 fs/btrfs/extent-tree.c | 27 +++++++++++++++++++--------
 fs/btrfs/hmzoned.c     | 18 ++++++++++++++++++
 fs/btrfs/hmzoned.h     | 18 ++++++++++++++++++
 3 files changed, 55 insertions(+), 8 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index d0d887448bb5..8665aba61bb9 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -1936,6 +1936,9 @@ int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr,
 
 
 		for (i = 0; i < bbio->num_stripes; i++, stripe++) {
+			struct btrfs_device *dev = stripe->dev;
+			u64 physical = stripe->physical;
+			u64 length = stripe->length;
 			u64 bytes;
 			struct request_queue *req_q;
 
@@ -1943,19 +1946,23 @@ int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr,
 				ASSERT(btrfs_test_opt(fs_info, DEGRADED));
 				continue;
 			}
+
 			req_q = bdev_get_queue(stripe->dev->bdev);
-			if (!blk_queue_discard(req_q))
+
+			/* zone reset in HMZONED mode */
+			if (btrfs_can_zone_reset(dev, physical, length))
+				ret = btrfs_reset_device_zone(dev, physical,
+							      length, &bytes);
+			else if (blk_queue_discard(req_q))
+				ret = btrfs_issue_discard(dev->bdev, physical,
+							  length, &bytes);
+			else
 				continue;
 
-			ret = btrfs_issue_discard(stripe->dev->bdev,
-						  stripe->physical,
-						  stripe->length,
-						  &bytes);
 			if (!ret)
 				discarded_bytes += bytes;
 			else if (ret != -EOPNOTSUPP)
 				break; /* Logic errors or -ENOMEM, or -EIO but I don't know how that could happen JDM */
-
 			/*
 			 * Just in case we get back EOPNOTSUPP for some reason,
 			 * just ignore the return value so we don't screw up
@@ -8985,8 +8992,12 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		spin_unlock(&block_group->lock);
 		spin_unlock(&space_info->lock);
 
-		/* DISCARD can flip during remount */
-		trimming = btrfs_test_opt(fs_info, DISCARD);
+		/*
+		 * DISCARD can flip during remount. In HMZONED mode,
+		 * we need to reset sequential required zones.
+		 */
+		trimming = btrfs_test_opt(fs_info, DISCARD) ||
+				btrfs_fs_incompat(fs_info, HMZONED);
 
 		/* Implicit trim during transaction commit. */
 		if (trimming)
diff --git a/fs/btrfs/hmzoned.c b/fs/btrfs/hmzoned.c
index 38cc1bbfe118..5968ef621fa7 100644
--- a/fs/btrfs/hmzoned.c
+++ b/fs/btrfs/hmzoned.c
@@ -596,3 +596,21 @@ int btrfs_hmzoned_check_metadata_space(struct btrfs_fs_info *fs_info)
 
 	return btrfs_commit_transaction(trans);
 }
+
+int btrfs_reset_device_zone(struct btrfs_device *device, u64 physical,
+			    u64 length, u64 *bytes)
+{
+	int ret;
+
+	ret = blkdev_reset_zones(device->bdev,
+				 physical >> SECTOR_SHIFT,
+				 length >> SECTOR_SHIFT,
+				 GFP_NOFS);
+	if (!ret) {
+		*bytes = length;
+		set_bit(physical >> device->zone_info->zone_size_shift,
+			device->zone_info->empty_zones);
+	}
+
+	return ret;
+}
diff --git a/fs/btrfs/hmzoned.h b/fs/btrfs/hmzoned.h
index e95139d4c072..40b4151fc935 100644
--- a/fs/btrfs/hmzoned.h
+++ b/fs/btrfs/hmzoned.h
@@ -32,6 +32,8 @@ int btrfs_check_mountopts_hmzoned(struct btrfs_fs_info *info);
 bool btrfs_check_allocatable_zones(struct btrfs_device *device, u64 pos,
 				   u64 num_bytes);
 int btrfs_load_block_group_zone_info(struct btrfs_block_group_cache *cache);
+int btrfs_reset_device_zone(struct btrfs_device *device, u64 physical,
+			    u64 length, u64 *bytes);
 int btrfs_hmzoned_check_metadata_space(struct btrfs_fs_info *fs_info);
 
 static inline bool btrfs_dev_is_sequential(struct btrfs_device *device, u64 pos)
@@ -107,4 +109,20 @@ static inline u64 btrfs_zone_align(struct btrfs_device *device, u64 pos)
 	return ALIGN(pos, device->zone_info->zone_size);
 }
 
+static inline bool btrfs_can_zone_reset(struct btrfs_device *device,
+					u64 physical, u64 length)
+{
+	u64 zone_size;
+
+	if (!btrfs_dev_is_sequential(device, physical))
+		return false;
+
+	zone_size = device->zone_info->zone_size;
+	if (!IS_ALIGNED(physical, zone_size) ||
+	    !IS_ALIGNED(length, zone_size))
+		return false;
+
+	return true;
+}
+
 #endif
-- 
2.22.0


  parent reply index

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-08-08  9:30 [PATCH v3 00/27] btrfs zoned block device support Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 01/27] btrfs: introduce HMZONED feature flag Naohiro Aota
2019-08-16  4:49   ` Anand Jain
2019-08-08  9:30 ` [PATCH v3 02/27] btrfs: Get zone information of zoned block devices Naohiro Aota
2019-08-16  4:44   ` Anand Jain
2019-08-16 14:19     ` Damien Le Moal
2019-08-16 23:47       ` Anand Jain
2019-08-16 23:55         ` Damien Le Moal
2019-08-08  9:30 ` [PATCH v3 03/27] btrfs: Check and enable HMZONED mode Naohiro Aota
2019-08-16  5:46   ` Anand Jain
2019-08-16 14:23     ` Damien Le Moal
2019-08-16 23:56       ` Anand Jain
2019-08-17  0:05         ` Damien Le Moal
2019-08-20  5:07         ` Naohiro Aota
2019-08-20 13:05           ` David Sterba
2019-08-08  9:30 ` [PATCH v3 04/27] btrfs: disallow RAID5/6 in " Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 05/27] btrfs: disallow space_cache " Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 06/27] btrfs: disallow NODATACOW " Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 07/27] btrfs: disable tree-log " Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 08/27] btrfs: disable fallocate " Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 09/27] btrfs: align device extent allocation to zone boundary Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 10/27] btrfs: do sequential extent allocation in HMZONED mode Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 11/27] btrfs: make unmirroed BGs readonly only if we have at least one writable BG Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 12/27] btrfs: ensure metadata space available on/after degraded mount in HMZONED Naohiro Aota
2019-08-08  9:30 ` Naohiro Aota [this message]
2019-08-08  9:30 ` [PATCH v3 14/27] btrfs: limit super block locations in HMZONED mode Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 15/27] btrfs: redirty released extent buffers in sequential BGs Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 16/27] btrfs: serialize data allocation and submit IOs Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 17/27] btrfs: implement atomic compressed IO submission Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 18/27] btrfs: support direct write IO in HMZONED Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 19/27] btrfs: serialize meta IOs on HMZONED mode Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 20/27] btrfs: wait existing extents before truncating Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 21/27] btrfs: avoid async checksum/submit on HMZONED mode Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 22/27] btrfs: disallow mixed-bg in " Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 23/27] btrfs: disallow inode_cache " Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 24/27] btrfs: support dev-replace " Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 25/27] btrfs: enable relocation " Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 26/27] btrfs: relocate block group to repair IO failure in HMZONED Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 27/27] btrfs: enable to mount HMZONED incompat flag Naohiro Aota

Reply instructions:

You may reply publically 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=20190808093038.4163421-14-naohiro.aota@wdc.com \
    --to=naohiro.aota@wdc.com \
    --cc=Matias.Bjorling@wdc.com \
    --cc=clm@fb.com \
    --cc=damien.lemoal@wdc.com \
    --cc=dsterba@suse.com \
    --cc=hare@suse.com \
    --cc=josef@toxicpanda.com \
    --cc=jthumshirn@suse.de \
    --cc=linux-btrfs@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=nborisov@suse.com \
    /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

Linux-BTRFS Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-btrfs/0 linux-btrfs/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-btrfs linux-btrfs/ https://lore.kernel.org/linux-btrfs \
		linux-btrfs@vger.kernel.org linux-btrfs@archiver.kernel.org
	public-inbox-index linux-btrfs


Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-btrfs


AGPL code for this site: git clone https://public-inbox.org/ public-inbox