All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Darrick J. Wong" <darrick.wong@oracle.com>
To: david@fromorbit.com, darrick.wong@oracle.com
Cc: linux-xfs@vger.kernel.org, xfs@oss.sgi.com
Subject: [PATCH 71/71] mkfs.xfs: format reflink enabled filesystems
Date: Thu, 25 Aug 2016 16:54:14 -0700	[thread overview]
Message-ID: <147216925429.4420.3323449215866524186.stgit@birch.djwong.org> (raw)
In-Reply-To: <147216879156.4420.2446767701729565218.stgit@birch.djwong.org>

Create the refcount btree at mkfs time and set the feature flag.

v2: Turn on the reflink feature when calculating the minimum log size.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 include/xfs_multidisk.h  |    3 +-
 libxfs/libxfs_api_defs.h |    1 +
 man/man8/mkfs.xfs.8      |   28 ++++++++++++++++++
 mkfs/maxtrres.c          |    5 +++
 mkfs/xfs_mkfs.c          |   70 ++++++++++++++++++++++++++++++++++++++++++----
 5 files changed, 99 insertions(+), 8 deletions(-)


diff --git a/include/xfs_multidisk.h b/include/xfs_multidisk.h
index 8dc3027..ce9bbce 100644
--- a/include/xfs_multidisk.h
+++ b/include/xfs_multidisk.h
@@ -68,6 +68,7 @@ extern void res_failed (int err);
 /* maxtrres.c */
 extern int max_trans_res(unsigned long agsize, int crcs_enabled, int dirversion,
 		int sectorlog, int blocklog, int inodelog, int dirblocklog,
-		int logversion, int log_sunit, int finobt, int rmapbt);
+		int logversion, int log_sunit, int finobt, int rmapbt,
+		int reflink);
 
 #endif	/* __XFS_MULTIDISK_H__ */
diff --git a/libxfs/libxfs_api_defs.h b/libxfs/libxfs_api_defs.h
index 8026522..8d57a66 100644
--- a/libxfs/libxfs_api_defs.h
+++ b/libxfs/libxfs_api_defs.h
@@ -141,5 +141,6 @@
 #define xfs_refcount_lookup_le		libxfs_refcount_lookup_le
 #define xfs_refcount_get_rec		libxfs_refcount_get_rec
 #define xfs_rmap_lookup_le_range	libxfs_rmap_lookup_le_range
+#define xfs_refc_block			libxfs_refc_block
 
 #endif /* __LIBXFS_API_DEFS_H__ */
diff --git a/man/man8/mkfs.xfs.8 b/man/man8/mkfs.xfs.8
index 9578c4d..6dab46a 100644
--- a/man/man8/mkfs.xfs.8
+++ b/man/man8/mkfs.xfs.8
@@ -213,6 +213,34 @@ for filesystems created with the (default)
 option set. When the option
 .B \-m crc=0
 is used, the reverse mapping btree feature is not supported and is disabled.
+.TP
+.BI reflink= value
+This option enables the use of a separate reference count btree index in each
+allocation group. The value is either 0 to disable the feature, or 1 to create
+a reference count btree in each allocation group.
+.IP
+The reference count btree enables the sharing of physical extents between
+the data forks of different files, which is commonly known as "reflink".
+Unlike traditional Unix filesystems which assume that every inode and
+logical block pair map to a unique physical block, a reflink-capable
+XFS filesystem removes the uniqueness requirement, allowing up to four
+billion arbitrary inode/logical block pairs to map to a physical block.
+If a program tries to write to a multiply-referenced block in a file, the write
+will be redirected to a new block, and that file's logical-to-physical
+mapping will be changed to the new block ("copy on write").  This feature
+enables the creation of per-file snapshots and deduplication.  It is only
+available for the data forks of regular files.
+.IP
+By default,
+.B mkfs.xfs
+will not create reference count btrees and therefore will not enable the
+reflink feature.  This feature is only available for filesystems created with
+the (default)
+.B \-m crc=1
+option set. When the option
+.B \-m crc=0
+is used, the reference count btree feature is not supported and reflink is
+disabled.
 .RE
 .TP
 .BI \-d " data_section_options"
diff --git a/mkfs/maxtrres.c b/mkfs/maxtrres.c
index d7978b6..fba7818 100644
--- a/mkfs/maxtrres.c
+++ b/mkfs/maxtrres.c
@@ -39,7 +39,8 @@ max_trans_res(
 	int		logversion,
 	int		log_sunit,
 	int		finobt,
-	int		rmapbt)
+	int		rmapbt,
+	int		reflink)
 {
 	xfs_sb_t	*sbp;
 	xfs_mount_t	mount;
@@ -75,6 +76,8 @@ max_trans_res(
 		sbp->sb_features_ro_compat |= XFS_SB_FEAT_RO_COMPAT_FINOBT;
 	if (rmapbt)
 		sbp->sb_features_ro_compat |= XFS_SB_FEAT_RO_COMPAT_RMAPBT;
+	if (reflink)
+		sbp->sb_features_ro_compat |= XFS_SB_FEAT_RO_COMPAT_REFLINK;
 
 	libxfs_mount(&mount, sbp, 0,0,0,0);
 	maxfsb = libxfs_log_calc_minimum_size(&mount);
diff --git a/mkfs/xfs_mkfs.c b/mkfs/xfs_mkfs.c
index 580119e..fc565c0 100644
--- a/mkfs/xfs_mkfs.c
+++ b/mkfs/xfs_mkfs.c
@@ -672,6 +672,8 @@ struct opt_params mopts = {
 		"uuid",
 #define M_RMAPBT	3
 		"rmapbt",
+#define M_REFLINK	4
+		"reflink",
 		NULL
 	},
 	.subopt_params = {
@@ -697,6 +699,12 @@ struct opt_params mopts = {
 		  .maxval = 1,
 		  .defaultval = 0,
 		},
+		{ .index = M_REFLINK,
+		  .conflicts = { LAST_CONFLICT },
+		  .minval = 0,
+		  .maxval = 1,
+		  .defaultval = 0,
+		},
 	},
 };
 
@@ -1155,6 +1163,7 @@ struct sb_feat_args {
 	bool	dirftype;
 	bool	parent_pointers;
 	bool	rmapbt;
+	bool	reflink;
 };
 
 static void
@@ -1227,6 +1236,8 @@ sb_set_features(
 		sbp->sb_features_ro_compat = XFS_SB_FEAT_RO_COMPAT_FINOBT;
 	if (fp->rmapbt)
 		sbp->sb_features_ro_compat |= XFS_SB_FEAT_RO_COMPAT_RMAPBT;
+	if (fp->reflink)
+		sbp->sb_features_ro_compat |= XFS_SB_FEAT_RO_COMPAT_REFLINK;
 
 	/*
 	 * Sparse inode chunk support has two main inode alignment requirements.
@@ -1488,6 +1499,7 @@ main(
 		.dirftype = true,
 		.parent_pointers = false,
 		.rmapbt = false,
+		.reflink = false,
 	};
 
 	platform_uuid_generate(&uuid);
@@ -1776,6 +1788,10 @@ main(
 					sb_feat.rmapbt = getnum(
 						value, &mopts, M_RMAPBT);
 					break;
+				case M_REFLINK:
+					sb_feat.reflink = getnum(
+						value, &mopts, M_REFLINK);
+					break;
 				default:
 					unknown('m', value);
 				}
@@ -2115,6 +2131,13 @@ _("rmapbt not supported without CRC support\n"));
 			usage();
 		}
 		sb_feat.rmapbt = false;
+
+		if (sb_feat.reflink) {
+			fprintf(stderr,
+_("reflink not supported without CRC support\n"));
+			usage();
+		}
+		sb_feat.reflink = false;
 	}
 
 
@@ -2599,7 +2622,7 @@ an AG size that is one stripe unit smaller, for example %llu.\n"),
 				   sb_feat.crcs_enabled, sb_feat.dir_version,
 				   sectorlog, blocklog, inodelog, dirblocklog,
 				   sb_feat.log_version, lsunit, sb_feat.finobt,
-				   sb_feat.rmapbt);
+				   sb_feat.rmapbt, sb_feat.reflink);
 	ASSERT(min_logblocks);
 	min_logblocks = MAX(XFS_MIN_LOG_BLOCKS, min_logblocks);
 	if (!logsize && dblocks >= (1024*1024*1024) >> blocklog)
@@ -2734,7 +2757,7 @@ _("size %s specified for log subvolume is too large, maximum is %lld blocks\n"),
 		printf(_(
 		   "meta-data=%-22s isize=%-6d agcount=%lld, agsize=%lld blks\n"
 		   "         =%-22s sectsz=%-5u attr=%u, projid32bit=%u\n"
-		   "         =%-22s crc=%-8u finobt=%u, sparse=%u, rmapbt=%u\n"
+		   "         =%-22s crc=%-8u finobt=%u, sparse=%u, rmapbt=%u, reflink=%u\n"
 		   "data     =%-22s bsize=%-6u blocks=%llu, imaxpct=%u\n"
 		   "         =%-22s sunit=%-6u swidth=%u blks\n"
 		   "naming   =version %-14u bsize=%-6u ascii-ci=%d ftype=%d\n"
@@ -2745,7 +2768,7 @@ _("size %s specified for log subvolume is too large, maximum is %lld blocks\n"),
 			"", sectorsize, sb_feat.attr_version,
 				    !sb_feat.projid16bit,
 			"", sb_feat.crcs_enabled, sb_feat.finobt, sb_feat.spinodes,
-			sb_feat.rmapbt,
+			sb_feat.rmapbt, sb_feat.reflink,
 			"", blocksize, (long long)dblocks, imaxpct,
 			"", dsunit, dswidth,
 			sb_feat.dir_version, dirblocksize, sb_feat.nci,
@@ -2933,7 +2956,12 @@ _("size %s specified for log subvolume is too large, maximum is %lld blocks\n"),
 			agf->agf_levels[XFS_BTNUM_RMAPi] = cpu_to_be32(1);
 			agf->agf_rmap_blocks = cpu_to_be32(1);
 		}
-
+		if (xfs_sb_version_hasreflink(&mp->m_sb)) {
+			agf->agf_refcount_root = cpu_to_be32(
+					libxfs_refc_block(mp));
+			agf->agf_refcount_level = cpu_to_be32(1);
+			agf->agf_refcount_blocks = cpu_to_be32(1);
+		}
 		agf->agf_flfirst = 0;
 		agf->agf_fllast = cpu_to_be32(XFS_AGFL_SIZE(mp) - 1);
 		agf->agf_flcount = 0;
@@ -3102,6 +3130,24 @@ _("size %s specified for log subvolume is too large, maximum is %lld blocks\n"),
 		libxfs_writebuf(buf, LIBXFS_EXIT_ON_FAILURE);
 
 		/*
+		 * refcount btree root block
+		 */
+		if (xfs_sb_version_hasreflink(&mp->m_sb)) {
+			buf = libxfs_getbuf(mp->m_ddev_targp,
+					XFS_AGB_TO_DADDR(mp, agno,
+						libxfs_refc_block(mp)),
+					bsize);
+			buf->b_ops = &xfs_refcountbt_buf_ops;
+
+			block = XFS_BUF_TO_BLOCK(buf);
+			memset(block, 0, blocksize);
+			libxfs_btree_init_block(mp, buf, XFS_REFC_CRC_MAGIC, 0,
+						0, agno, XFS_BTREE_CRC_BLOCKS);
+
+			libxfs_writebuf(buf, LIBXFS_EXIT_ON_FAILURE);
+		}
+
+		/*
 		 * INO btree root block
 		 */
 		buf = libxfs_getbuf(mp->m_ddev_targp,
@@ -3189,9 +3235,21 @@ _("size %s specified for log subvolume is too large, maximum is %lld blocks\n"),
 			rrec->rm_offset = 0;
 			be16_add_cpu(&block->bb_numrecs, 1);
 
+			/* account for refcount btree root */
+			if (xfs_sb_version_hasreflink(&mp->m_sb)) {
+				rrec = XFS_RMAP_REC_ADDR(block, 5);
+				rrec->rm_startblock = cpu_to_be32(
+							libxfs_refc_block(mp));
+				rrec->rm_blockcount = cpu_to_be32(1);
+				rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_REFC);
+				rrec->rm_offset = 0;
+				be16_add_cpu(&block->bb_numrecs, 1);
+			}
+
 			/* account for the log space */
 			if (loginternal && agno == logagno) {
-				rrec = XFS_RMAP_REC_ADDR(block, 5);
+				rrec = XFS_RMAP_REC_ADDR(block,
+					be16_to_cpu(block->bb_numrecs) + 1);
 				rrec->rm_startblock = cpu_to_be32(
 						XFS_FSB_TO_AGBNO(mp, logstart));
 				rrec->rm_blockcount = cpu_to_be32(logblocks);
@@ -3446,7 +3504,7 @@ usage( void )
 {
 	fprintf(stderr, _("Usage: %s\n\
 /* blocksize */		[-b log=n|size=num]\n\
-/* metadata */		[-m crc=0|1,finobt=0|1,uuid=xxx,rmapbt=0|1]\n\
+/* metadata */		[-m crc=0|1,finobt=0|1,uuid=xxx,rmapbt=0|1,reflink=0|1]\n\
 /* data subvol */	[-d agcount=n,agsize=n,file,name=xxx,size=num,\n\
 			    (sunit=value,swidth=value|su=num,sw=num|noalign),\n\
 			    sectlog=n|sectsize=num\n\

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs

      parent reply	other threads:[~2016-08-25 23:54 UTC|newest]

Thread overview: 72+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-08-25 23:46 [PATCH v8 00/71] xfsprogs: add reflink and dedupe support Darrick J. Wong
2016-08-25 23:46 ` [PATCH 01/71] xfs: remove xfs_btree_bigkey Darrick J. Wong
2016-08-25 23:46 ` [PATCH 02/71] xfs: create a standard btree size calculator code Darrick J. Wong
2016-08-25 23:46 ` [PATCH 03/71] xfs: count the blocks in a btree Darrick J. Wong
2016-08-25 23:46 ` [PATCH 04/71] xfs: defer should allow ->finish_item to request a new transaction Darrick J. Wong
2016-08-25 23:47 ` [PATCH 05/71] xfs: set up per-AG free space reservations Darrick J. Wong
2016-08-25 23:47 ` [PATCH 06/71] xfs: introduce refcount btree definitions Darrick J. Wong
2016-08-25 23:47 ` [PATCH 07/71] xfs: add refcount btree stats infrastructure Darrick J. Wong
2016-08-25 23:47 ` [PATCH 08/71] xfs: refcount btree add more reserved blocks Darrick J. Wong
2016-08-25 23:47 ` [PATCH 09/71] xfs: define the on-disk refcount btree format Darrick J. Wong
2016-08-25 23:47 ` [PATCH 10/71] xfs: account for the refcount btree in the alloc/free log reservation Darrick J. Wong
2016-08-25 23:47 ` [PATCH 11/71] xfs: add refcount btree operations Darrick J. Wong
2016-08-25 23:47 ` [PATCH 12/71] xfs: create refcount update intent log items Darrick J. Wong
2016-08-25 23:47 ` [PATCH 13/71] xfs: log refcount intent items Darrick J. Wong
2016-08-25 23:48 ` [PATCH 14/71] xfs: adjust refcount of an extent of blocks in refcount btree Darrick J. Wong
2016-08-25 23:48 ` [PATCH 15/71] xfs: connect refcount adjust functions to upper layers Darrick J. Wong
2016-08-25 23:48 ` [PATCH 16/71] xfs: adjust refcount when unmapping file blocks Darrick J. Wong
2016-08-25 23:48 ` [PATCH 17/71] xfs: refcount btree requires more reserved space Darrick J. Wong
2016-08-25 23:48 ` [PATCH 18/71] xfs: introduce reflink utility functions Darrick J. Wong
2016-08-25 23:48 ` [PATCH 19/71] xfs: create bmbt update intent log items Darrick J. Wong
2016-08-25 23:48 ` [PATCH 20/71] xfs: log bmap intent items Darrick J. Wong
2016-08-25 23:48 ` [PATCH 21/71] xfs: map an inode's offset to an exact physical block Darrick J. Wong
2016-08-25 23:48 ` [PATCH 22/71] xfs: pass bmapi flags through to bmap_del_extent Darrick J. Wong
2016-08-25 23:48 ` [PATCH 23/71] xfs: implement deferred bmbt map/unmap operations Darrick J. Wong
2016-08-25 23:49 ` [PATCH 24/71] xfs: return work remaining at the end of a bunmapi operation Darrick J. Wong
2016-08-25 23:49 ` [PATCH 25/71] xfs: add reflink feature flag to geometry Darrick J. Wong
2016-08-25 23:49 ` [PATCH 26/71] xfs: don't allow reflinked dir/dev/fifo/socket/pipe files Darrick J. Wong
2016-08-25 23:49 ` [PATCH 27/71] xfs: introduce the CoW fork Darrick J. Wong
2016-08-25 23:49 ` [PATCH 28/71] xfs: support bmapping delalloc extents in " Darrick J. Wong
2016-08-25 23:49 ` [PATCH 29/71] xfs: support allocating delayed extents in " Darrick J. Wong
2016-08-25 23:49 ` [PATCH 30/71] xfs: support removing extents from " Darrick J. Wong
2016-08-25 23:49 ` [PATCH 31/71] xfs: store in-progress CoW allocations in the refcount btree Darrick J. Wong
2016-08-25 23:49 ` [PATCH 32/71] xfs: teach get_bmapx and fiemap about shared extents and the CoW fork Darrick J. Wong
2016-08-25 23:50 ` [PATCH 33/71] xfs: support FS_XFLAG_REFLINK on reflink filesystems Darrick J. Wong
2016-08-25 23:50 ` [PATCH 34/71] xfs: create a separate cow extent size hint for the allocator Darrick J. Wong
2016-08-25 23:50 ` [PATCH 35/71] xfs: preallocate blocks for worst-case btree expansion Darrick J. Wong
2016-08-25 23:50 ` [PATCH 36/71] xfs: try other AGs to allocate a BMBT block Darrick J. Wong
2016-08-25 23:50 ` [PATCH 37/71] xfs: increase log reservations for reflink Darrick J. Wong
2016-08-25 23:50 ` [PATCH 38/71] xfs: add shared rmap map/unmap/convert log item types Darrick J. Wong
2016-08-25 23:50 ` [PATCH 39/71] xfs: use interval query for rmap map and unmap operations on shared files Darrick J. Wong
2016-08-25 23:50 ` [PATCH 40/71] xfs: convert unwritten status of shared-extent reverse mappings " Darrick J. Wong
2016-08-25 23:50 ` [PATCH 41/71] xfs: don't allow realtime and reflinked files to mix Darrick J. Wong
2016-08-25 23:51 ` [PATCH 42/71] xfs: don't mix reflink and DAX mode for now Darrick J. Wong
2016-08-25 23:51 ` [PATCH 43/71] xfs: recognize the reflink feature bit Darrick J. Wong
2016-08-25 23:51 ` [PATCH 44/71] xfs_db: dump refcount btree data Darrick J. Wong
2016-08-25 23:51 ` [PATCH 45/71] xfs_db: add support for checking the refcount btree Darrick J. Wong
2016-08-25 23:51 ` [PATCH 46/71] xfs_db: metadump should copy the refcount btree too Darrick J. Wong
2016-08-25 23:51 ` [PATCH 47/71] xfs_db: deal with the CoW extent size hint Darrick J. Wong
2016-08-25 23:51 ` [PATCH 48/71] xfs_db: print one array element per line Darrick J. Wong
2016-08-25 23:51 ` [PATCH 49/71] xfs_growfs: report the presence of the reflink feature Darrick J. Wong
2016-08-25 23:51 ` [PATCH 50/71] xfs_io: bmap should support querying CoW fork, shared blocks Darrick J. Wong
2016-08-25 23:52 ` [PATCH 51/71] libxfs: add configure option to override system header fsxattr Darrick J. Wong
2016-08-25 23:52 ` [PATCH 52/71] xfs_io: get and set the CoW extent size hint Darrick J. Wong
2016-08-25 23:52 ` [PATCH 53/71] xfs_io: add refcount+bmap error injection types Darrick J. Wong
2016-08-25 23:52 ` [PATCH 54/71] xfs_logprint: support cowextsize reporting in log contents Darrick J. Wong
2016-08-25 23:52 ` [PATCH 55/71] xfs_logprint: support refcount redo items Darrick J. Wong
2016-08-25 23:52 ` [PATCH 56/71] xfs_logprint: support bmap " Darrick J. Wong
2016-08-25 23:52 ` [PATCH 57/71] man: document the reflink inode flag in fsxattr Darrick J. Wong
2016-08-25 23:52 ` [PATCH 58/71] man: document the inode cowextsize flags & fields Darrick J. Wong
2016-08-25 23:52 ` [PATCH 59/71] xfs_repair: fix get_agino_buf to avoid corrupting inodes Darrick J. Wong
2016-08-25 23:53 ` [PATCH 60/71] xfs_repair: check the existing refcount btree Darrick J. Wong
2016-08-25 23:53 ` [PATCH 61/71] xfs_repair: handle multiple owners of data blocks Darrick J. Wong
2016-08-25 23:53 ` [PATCH 62/71] xfs_repair: process reverse-mapping data into refcount data Darrick J. Wong
2016-08-25 23:53 ` [PATCH 63/71] xfs_repair: record reflink inode state Darrick J. Wong
2016-08-25 23:53 ` [PATCH 64/71] xfs_repair: fix inode reflink flags Darrick J. Wong
2016-08-25 23:53 ` [PATCH 65/71] xfs_repair: check the refcount btree against our observed reference counts when -n Darrick J. Wong
2016-08-25 23:53 ` [PATCH 66/71] xfs_repair: rebuild the refcount btree Darrick J. Wong
2016-08-25 23:53 ` [PATCH 67/71] xfs_repair: complain about copy-on-write leftovers Darrick J. Wong
2016-08-25 23:53 ` [PATCH 68/71] xfs_repair: check the CoW extent size hint Darrick J. Wong
2016-08-25 23:54 ` [PATCH 69/71] xfs_repair: use range query when while checking rmaps Darrick J. Wong
2016-08-25 23:54 ` [PATCH 70/71] xfs_repair: check for mergeable refcount records Darrick J. Wong
2016-08-25 23:54 ` Darrick J. Wong [this message]

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=147216925429.4420.3323449215866524186.stgit@birch.djwong.org \
    --to=darrick.wong@oracle.com \
    --cc=david@fromorbit.com \
    --cc=linux-xfs@vger.kernel.org \
    --cc=xfs@oss.sgi.com \
    --subject='Re: [PATCH 71/71] mkfs.xfs: format reflink enabled filesystems' \
    /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

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.