linux-fsdevel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Naohiro Aota <naohiro.aota@wdc.com>
To: linux-btrfs@vger.kernel.org, dsterba@suse.com
Cc: hare@suse.com, linux-fsdevel@vger.kernel.org,
	Naohiro Aota <naohiro.aota@wdc.com>
Subject: [PATCH v8 34/41] btrfs: support dev-replace in ZONED mode
Date: Fri,  2 Oct 2020 03:36:41 +0900	[thread overview]
Message-ID: <b2e3485645132a247fe73698b73d54f954f2b33d.1601574234.git.naohiro.aota@wdc.com> (raw)
In-Reply-To: <dece91bca322ce44bed19f2b0f460fa5ded2e512.1601574234.git.naohiro.aota@wdc.com>

This is 4/4 patch to implement device-replace on ZONED mode.

Even after the copying is done, the write pointers of the source device and
the destination device may not be synchronized. For example, when the last
allocated extent is freed before device-replace process, the extent is not
copied, leaving a hole there.

This patch synchronize the write pointers by writing zeros to the
destination device.

Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
---
 fs/btrfs/scrub.c | 36 +++++++++++++++++++++++++
 fs/btrfs/zoned.c | 69 ++++++++++++++++++++++++++++++++++++++++++++++++
 fs/btrfs/zoned.h |  8 ++++++
 3 files changed, 113 insertions(+)

diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 65e460670160..2e607caa5ab9 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -3019,6 +3019,31 @@ static void sync_replace_for_zoned(struct scrub_ctx *sctx)
 		   atomic_read(&sctx->bios_in_flight) == 0);
 }
 
+static int sync_write_pointer_for_zoned(struct scrub_ctx *sctx, u64 logical,
+					u64 physical, u64 physical_end)
+{
+	struct btrfs_fs_info *fs_info = sctx->fs_info;
+	int ret = 0;
+
+	if (!btrfs_fs_incompat(fs_info, ZONED))
+		return 0;
+
+	wait_event(sctx->list_wait, atomic_read(&sctx->bios_in_flight) == 0);
+
+	mutex_lock(&sctx->wr_lock);
+	if (sctx->write_pointer < physical_end) {
+		ret = btrfs_sync_zone_write_pointer(sctx->wr_tgtdev, logical,
+						    physical,
+						    sctx->write_pointer);
+		if (ret)
+			btrfs_err(fs_info, "failed to recover write pointer");
+	}
+	mutex_unlock(&sctx->wr_lock);
+	btrfs_dev_clear_zone_empty(sctx->wr_tgtdev, physical);
+
+	return ret;
+}
+
 static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
 					   struct map_lookup *map,
 					   struct btrfs_device *scrub_dev,
@@ -3416,6 +3441,17 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
 	blk_finish_plug(&plug);
 	btrfs_free_path(path);
 	btrfs_free_path(ppath);
+
+	if (sctx->is_dev_replace && ret >= 0) {
+		int ret2;
+
+		ret2 = sync_write_pointer_for_zoned(sctx, base + offset,
+						    map->stripes[num].physical,
+						    physical_end);
+		if (ret2)
+			ret = ret2;
+	}
+
 	return ret < 0 ? ret : 0;
 }
 
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 7ff2a590c93f..f28a70eaa20a 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -18,6 +18,7 @@
 #include "block-group.h"
 #include "transaction.h"
 #include "dev-replace.h"
+#include "space-info.h"
 
 /* Maximum number of zones to report per blkdev_report_zones() call */
 #define BTRFS_REPORT_NR_ZONES   4096
@@ -1195,3 +1196,71 @@ int btrfs_zoned_issue_zeroout(struct btrfs_device *device, u64 physical,
 				    length >> SECTOR_SHIFT,
 				    GFP_NOFS, 0);
 }
+
+static int read_zone_info(struct btrfs_fs_info *fs_info, u64 logical,
+			  struct blk_zone *zone)
+{
+	struct btrfs_bio *bbio = NULL;
+	u64 mapped_length = PAGE_SIZE;
+	unsigned int nofs_flag;
+	int nmirrors;
+	int i, ret;
+
+	ret = btrfs_map_sblock(fs_info, BTRFS_MAP_GET_READ_MIRRORS, logical,
+			       &mapped_length, &bbio);
+	if (ret || !bbio || mapped_length < PAGE_SIZE) {
+		btrfs_put_bbio(bbio);
+		return -EIO;
+	}
+
+	if (bbio->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK)
+		return -EINVAL;
+
+	nofs_flag = memalloc_nofs_save();
+	nmirrors = (int)bbio->num_stripes;
+	for (i = 0; i < nmirrors; i++) {
+		u64 physical = bbio->stripes[i].physical;
+		struct btrfs_device *dev = bbio->stripes[i].dev;
+
+		/* missing device */
+		if (!dev->bdev)
+			continue;
+
+		ret = btrfs_get_dev_zone(dev, physical, zone);
+		/* failing device */
+		if (ret == -EIO || ret == -EOPNOTSUPP)
+			continue;
+		break;
+	}
+	memalloc_nofs_restore(nofs_flag);
+
+	return ret;
+}
+
+int btrfs_sync_zone_write_pointer(struct btrfs_device *tgt_dev, u64 logical,
+				    u64 physical_start, u64 physical_pos)
+{
+	struct btrfs_fs_info *fs_info = tgt_dev->fs_info;
+	struct blk_zone zone;
+	u64 length;
+	u64 wp;
+	int ret;
+
+	if (!btrfs_dev_is_sequential(tgt_dev, physical_pos))
+		return 0;
+
+	ret = read_zone_info(fs_info, logical, &zone);
+	if (ret)
+		return ret;
+
+	wp = physical_start + ((zone.wp - zone.start) << SECTOR_SHIFT);
+
+	if (physical_pos == wp)
+		return 0;
+
+	if (physical_pos > wp)
+		return -EUCLEAN;
+
+	length = wp - physical_pos;
+	return btrfs_zoned_issue_zeroout(tgt_dev, physical_pos, length);
+}
diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h
index d5b2d31e6c91..d857538660f1 100644
--- a/fs/btrfs/zoned.h
+++ b/fs/btrfs/zoned.h
@@ -60,6 +60,8 @@ void btrfs_revert_meta_write_pointer(struct btrfs_block_group *cache,
 				     struct extent_buffer *eb);
 int btrfs_zoned_issue_zeroout(struct btrfs_device *device, u64 physical,
 			      u64 length);
+int btrfs_sync_zone_write_pointer(struct btrfs_device *tgt_dev, u64 logical,
+				  u64 physical_start, u64 physical_pos);
 #else /* CONFIG_BLK_DEV_ZONED */
 static inline int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos,
 				     struct blk_zone *zone)
@@ -152,6 +154,12 @@ static inline int btrfs_zoned_issue_zeroout(struct btrfs_device *device,
 {
 	return -EOPNOTSUPP;
 }
+static inline int btrfs_sync_zone_write_pointer(struct btrfs_device *tgt_dev,
+						u64 logical, u64 physical_start,
+						u64 physical_pos)
+{
+	return -EOPNOTSUPP;
+}
 #endif
 
 static inline bool btrfs_dev_is_sequential(struct btrfs_device *device, u64 pos)
-- 
2.27.0


  parent reply	other threads:[~2020-10-01 18:39 UTC|newest]

Thread overview: 61+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-10-01 18:36 [PATCH v8 00/41] btrfs: zoned block device support Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 01/41] block: add bio_add_zone_append_page Naohiro Aota
2020-10-01 18:36   ` [PATCH v8 02/41] btrfs: introduce ZONED feature flag Naohiro Aota
2020-10-01 18:36   ` [PATCH v8 03/41] btrfs: Get zone information of zoned block devices Naohiro Aota
2020-10-13 15:53     ` David Sterba
2020-10-15  7:45       ` Johannes Thumshirn
2020-10-01 18:36   ` [PATCH v8 04/41] btrfs: Check and enable ZONED mode Naohiro Aota
2020-10-13 15:56     ` David Sterba
2020-10-28 14:49       ` Johannes Thumshirn
2020-10-13 16:13     ` David Sterba
2020-10-01 18:36   ` [PATCH v8 05/41] btrfs: introduce max_zone_append_size Naohiro Aota
2020-10-01 18:36   ` [PATCH v8 06/41] btrfs: disallow space_cache in ZONED mode Naohiro Aota
2020-10-01 18:36   ` [PATCH v8 07/41] btrfs: disallow NODATACOW " Naohiro Aota
2020-10-13 15:39     ` David Sterba
2020-10-21  8:53       ` Johannes Thumshirn
2020-10-01 18:36   ` [PATCH v8 08/41] btrfs: disable fallocate " Naohiro Aota
2020-10-01 18:36   ` [PATCH v8 09/41] btrfs: disallow mixed-bg " Naohiro Aota
2020-10-01 18:36   ` [PATCH v8 10/41] btrfs: disallow inode_cache " Naohiro Aota
2020-10-13 15:41     ` David Sterba
2020-10-22  6:48       ` Naohiro Aota
2020-10-01 18:36   ` [PATCH v8 11/41] btrfs: implement log-structured superblock for " Naohiro Aota
2020-10-01 18:36   ` [PATCH v8 12/41] btrfs: implement zoned chunk allocator Naohiro Aota
2020-10-01 18:36   ` [PATCH v8 13/41] btrfs: verify device extent is aligned to zone Naohiro Aota
2020-10-01 18:36   ` [PATCH v8 14/41] btrfs: load zone's alloction offset Naohiro Aota
2020-10-01 18:36   ` [PATCH v8 15/41] btrfs: emulate write pointer for conventional zones Naohiro Aota
2020-10-01 18:36   ` [PATCH v8 16/41] btrfs: track unusable bytes for zones Naohiro Aota
2020-10-01 18:36   ` [PATCH v8 17/41] btrfs: do sequential extent allocation in ZONED mode Naohiro Aota
2020-10-01 18:36   ` [PATCH v8 18/41] btrfs: reset zones of unused block groups Naohiro Aota
2020-10-01 18:36   ` [PATCH v8 19/41] btrfs: redirty released extent buffers in ZONED mode Naohiro Aota
2020-10-01 18:36   ` [PATCH v8 20/41] btrfs: extract page adding function Naohiro Aota
2020-10-01 18:36   ` [PATCH v8 21/41] btrfs: use bio_add_zone_append_page for zoned btrfs Naohiro Aota
2020-10-01 18:36   ` [PATCH v8 22/41] btrfs: handle REQ_OP_ZONE_APPEND as writing Naohiro Aota
2020-10-01 18:36   ` [PATCH v8 23/41] btrfs: split ordered extent when bio is sent Naohiro Aota
2020-10-01 18:36   ` [PATCH v8 24/41] btrfs: extend btrfs_rmap_block for specifying a device Naohiro Aota
2020-10-01 18:36   ` [PATCH v8 25/41] btrfs: use ZONE_APPEND write for ZONED btrfs Naohiro Aota
2020-10-13 16:45     ` David Sterba
2020-10-01 18:36   ` [PATCH v8 26/41] btrfs: enable zone append writing for direct IO Naohiro Aota
2020-10-01 18:36   ` [PATCH v8 27/41] btrfs: introduce dedicated data write path for ZONED mode Naohiro Aota
2020-10-01 18:36   ` [PATCH v8 28/41] btrfs: serialize meta IOs on " Naohiro Aota
2020-10-01 18:36   ` [PATCH v8 29/41] btrfs: wait existing extents before truncating Naohiro Aota
2020-10-01 18:36   ` [PATCH v8 30/41] btrfs: avoid async metadata checksum on ZONED mode Naohiro Aota
2020-10-01 18:36   ` [PATCH v8 31/41] btrfs: mark block groups to copy for device-replace Naohiro Aota
2020-10-01 18:36   ` [PATCH v8 32/41] btrfs: implement cloning for ZONED device-replace Naohiro Aota
2020-10-01 18:36   ` [PATCH v8 33/41] btrfs: implement copying " Naohiro Aota
2020-10-01 18:36   ` Naohiro Aota [this message]
2020-10-01 18:36   ` [PATCH v8 35/41] btrfs: enable relocation in ZONED mode Naohiro Aota
2020-10-01 18:36   ` [PATCH v8 36/41] btrfs: relocate block group to repair IO failure in ZONED Naohiro Aota
2020-10-01 18:36   ` [PATCH v8 37/41] btrfs: split alloc_log_tree() Naohiro Aota
2020-10-01 18:36   ` [PATCH v8 38/41] btrfs: extend zoned allocator to use dedicated tree-log block group Naohiro Aota
2020-10-13 16:26     ` David Sterba
2020-10-15  7:21       ` Johannes Thumshirn
2020-10-01 18:36   ` [PATCH v8 39/41] btrfs: serialize log transaction on ZONED mode Naohiro Aota
2020-10-01 18:36   ` [PATCH v8 40/41] btrfs: reorder log node allocation Naohiro Aota
2020-10-01 18:36   ` [PATCH v8 41/41] btrfs: enable to mount ZONED incompat flag Naohiro Aota
2020-10-02 13:39   ` [PATCH v8 01/41] block: add bio_add_zone_append_page Martin K. Petersen
2020-10-05  1:46     ` Damien Le Moal
2020-10-05 13:43     ` Christoph Hellwig
2020-10-06  1:26       ` Martin K. Petersen
2020-10-06  5:12         ` Damien Le Moal
2020-10-09 15:40 ` [PATCH v8 00/41] btrfs: zoned block device support Josef Bacik
2020-10-12  9:17   ` Naohiro Aota

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=b2e3485645132a247fe73698b73d54f954f2b33d.1601574234.git.naohiro.aota@wdc.com \
    --to=naohiro.aota@wdc.com \
    --cc=dsterba@suse.com \
    --cc=hare@suse.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 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).