From: Brian Foster <bfoster@redhat.com>
To: xfs@oss.sgi.com
Subject: [PATCH v3 03/20] xfs: support the XFS_BTNUM_FINOBT free inode btree type
Date: Thu, 10 Apr 2014 12:10:53 -0400 [thread overview]
Message-ID: <1397146270-42993-4-git-send-email-bfoster@redhat.com> (raw)
In-Reply-To: <1397146270-42993-1-git-send-email-bfoster@redhat.com>
Define the AGI fields for the finobt root/level and add magic
numbers. Update the btree code to add support for the new
XFS_BTNUM_FINOBT inode btree.
The finobt root block is reserved immediately following the inobt
root block in the AG. Update XFS_PREALLOC_BLOCKS() to determine the
starting AG data block based on whether finobt support is enabled.
Signed-off-by: Brian Foster <bfoster@redhat.com>
---
include/xfs_ag.h | 32 +++++++++++++++----------
include/xfs_btree.h | 3 +++
include/xfs_format.h | 14 ++++++++++-
include/xfs_types.h | 2 +-
libxfs/xfs_btree.c | 6 +++--
libxfs/xfs_ialloc.c | 37 +++++++++++++++++++++++++----
libxfs/xfs_ialloc_btree.c | 60 +++++++++++++++++++++++++++++++++++++++++++++--
7 files changed, 130 insertions(+), 24 deletions(-)
diff --git a/include/xfs_ag.h b/include/xfs_ag.h
index 0fdd410..2531658 100644
--- a/include/xfs_ag.h
+++ b/include/xfs_ag.h
@@ -166,24 +166,30 @@ typedef struct xfs_agi {
__be32 agi_pad32;
__be64 agi_lsn; /* last write sequence */
+ __be32 agi_free_root; /* root of the free inode btree */
+ __be32 agi_free_level;/* levels in free inode btree */
+
/* structure must be padded to 64 bit alignment */
} xfs_agi_t;
#define XFS_AGI_CRC_OFF offsetof(struct xfs_agi, agi_crc)
-#define XFS_AGI_MAGICNUM 0x00000001
-#define XFS_AGI_VERSIONNUM 0x00000002
-#define XFS_AGI_SEQNO 0x00000004
-#define XFS_AGI_LENGTH 0x00000008
-#define XFS_AGI_COUNT 0x00000010
-#define XFS_AGI_ROOT 0x00000020
-#define XFS_AGI_LEVEL 0x00000040
-#define XFS_AGI_FREECOUNT 0x00000080
-#define XFS_AGI_NEWINO 0x00000100
-#define XFS_AGI_DIRINO 0x00000200
-#define XFS_AGI_UNLINKED 0x00000400
-#define XFS_AGI_NUM_BITS 11
-#define XFS_AGI_ALL_BITS ((1 << XFS_AGI_NUM_BITS) - 1)
+#define XFS_AGI_MAGICNUM (1 << 0)
+#define XFS_AGI_VERSIONNUM (1 << 1)
+#define XFS_AGI_SEQNO (1 << 2)
+#define XFS_AGI_LENGTH (1 << 3)
+#define XFS_AGI_COUNT (1 << 4)
+#define XFS_AGI_ROOT (1 << 5)
+#define XFS_AGI_LEVEL (1 << 6)
+#define XFS_AGI_FREECOUNT (1 << 7)
+#define XFS_AGI_NEWINO (1 << 8)
+#define XFS_AGI_DIRINO (1 << 9)
+#define XFS_AGI_UNLINKED (1 << 10)
+#define XFS_AGI_NUM_BITS_R1 11 /* end of the 1st agi logging region */
+#define XFS_AGI_ALL_BITS_R1 ((1 << XFS_AGI_NUM_BITS_R1) - 1)
+#define XFS_AGI_FREE_ROOT (1 << 11)
+#define XFS_AGI_FREE_LEVEL (1 << 12)
+#define XFS_AGI_NUM_BITS_R2 13
/* disk block (xfs_daddr_t) in the AG */
#define XFS_AGI_DADDR(mp) ((xfs_daddr_t)(2 << (mp)->m_sectbb_log))
diff --git a/include/xfs_btree.h b/include/xfs_btree.h
index 6afe0b2..2590d40 100644
--- a/include/xfs_btree.h
+++ b/include/xfs_btree.h
@@ -37,6 +37,7 @@ extern kmem_zone_t *xfs_btree_cur_zone;
#define XFS_BTNUM_CNT ((xfs_btnum_t)XFS_BTNUM_CNTi)
#define XFS_BTNUM_BMAP ((xfs_btnum_t)XFS_BTNUM_BMAPi)
#define XFS_BTNUM_INO ((xfs_btnum_t)XFS_BTNUM_INOi)
+#define XFS_BTNUM_FINO ((xfs_btnum_t)XFS_BTNUM_FINOi)
/*
* For logging record fields.
@@ -67,6 +68,7 @@ do { \
case XFS_BTNUM_CNT: __XFS_BTREE_STATS_INC(abtc, stat); break; \
case XFS_BTNUM_BMAP: __XFS_BTREE_STATS_INC(bmbt, stat); break; \
case XFS_BTNUM_INO: __XFS_BTREE_STATS_INC(ibt, stat); break; \
+ case XFS_BTNUM_FINO: __XFS_BTREE_STATS_INC(fibt, stat); break; \
case XFS_BTNUM_MAX: ASSERT(0); /* fucking gcc */ ; break; \
} \
} while (0)
@@ -80,6 +82,7 @@ do { \
case XFS_BTNUM_CNT: __XFS_BTREE_STATS_ADD(abtc, stat, val); break; \
case XFS_BTNUM_BMAP: __XFS_BTREE_STATS_ADD(bmbt, stat, val); break; \
case XFS_BTNUM_INO: __XFS_BTREE_STATS_ADD(ibt, stat, val); break; \
+ case XFS_BTNUM_FINO: __XFS_BTREE_STATS_ADD(fibt, stat, val); break; \
case XFS_BTNUM_MAX: ASSERT(0); /* fucking gcc */ ; break; \
} \
} while (0)
diff --git a/include/xfs_format.h b/include/xfs_format.h
index 77f6b8b..758052f 100644
--- a/include/xfs_format.h
+++ b/include/xfs_format.h
@@ -202,6 +202,8 @@ typedef __be32 xfs_alloc_ptr_t;
*/
#define XFS_IBT_MAGIC 0x49414254 /* 'IABT' */
#define XFS_IBT_CRC_MAGIC 0x49414233 /* 'IAB3' */
+#define XFS_FIBT_MAGIC 0x46494254 /* 'FIBT' */
+#define XFS_FIBT_CRC_MAGIC 0x46494233 /* 'FIB3' */
typedef __uint64_t xfs_inofree_t;
#define XFS_INODES_PER_CHUNK (NBBY * sizeof(xfs_inofree_t))
@@ -244,7 +246,17 @@ typedef __be32 xfs_inobt_ptr_t;
* block numbers in the AG.
*/
#define XFS_IBT_BLOCK(mp) ((xfs_agblock_t)(XFS_CNT_BLOCK(mp) + 1))
-#define XFS_PREALLOC_BLOCKS(mp) ((xfs_agblock_t)(XFS_IBT_BLOCK(mp) + 1))
+#define XFS_FIBT_BLOCK(mp) ((xfs_agblock_t)(XFS_IBT_BLOCK(mp) + 1))
+
+/*
+ * The first data block of an AG depends on whether the filesystem was formatted
+ * with the finobt feature. If so, account for the finobt reserved root btree
+ * block.
+ */
+#define XFS_PREALLOC_BLOCKS(mp) \
+ (xfs_sb_version_hasfinobt(&((mp)->m_sb)) ? \
+ XFS_FIBT_BLOCK(mp) + 1 : \
+ XFS_IBT_BLOCK(mp) + 1)
diff --git a/include/xfs_types.h b/include/xfs_types.h
index 82bbc34..65c6e66 100644
--- a/include/xfs_types.h
+++ b/include/xfs_types.h
@@ -134,7 +134,7 @@ typedef enum {
typedef enum {
XFS_BTNUM_BNOi, XFS_BTNUM_CNTi, XFS_BTNUM_BMAPi, XFS_BTNUM_INOi,
- XFS_BTNUM_MAX
+ XFS_BTNUM_FINOi, XFS_BTNUM_MAX
} xfs_btnum_t;
struct xfs_name {
diff --git a/libxfs/xfs_btree.c b/libxfs/xfs_btree.c
index 9be4abd..cc823f5 100644
--- a/libxfs/xfs_btree.c
+++ b/libxfs/xfs_btree.c
@@ -27,9 +27,10 @@ kmem_zone_t *xfs_btree_cur_zone;
* Btree magic numbers.
*/
static const __uint32_t xfs_magics[2][XFS_BTNUM_MAX] = {
- { XFS_ABTB_MAGIC, XFS_ABTC_MAGIC, XFS_BMAP_MAGIC, XFS_IBT_MAGIC },
+ { XFS_ABTB_MAGIC, XFS_ABTC_MAGIC, XFS_BMAP_MAGIC, XFS_IBT_MAGIC,
+ XFS_FIBT_MAGIC },
{ XFS_ABTB_CRC_MAGIC, XFS_ABTC_CRC_MAGIC,
- XFS_BMAP_CRC_MAGIC, XFS_IBT_CRC_MAGIC }
+ XFS_BMAP_CRC_MAGIC, XFS_IBT_CRC_MAGIC, XFS_FIBT_CRC_MAGIC }
};
#define xfs_btree_magic(cur) \
xfs_magics[!!((cur)->bc_flags & XFS_BTREE_CRC_BLOCKS)][cur->bc_btnum]
@@ -1099,6 +1100,7 @@ xfs_btree_set_refs(
xfs_buf_set_ref(bp, XFS_ALLOC_BTREE_REF);
break;
case XFS_BTNUM_INO:
+ case XFS_BTNUM_FINO:
xfs_buf_set_ref(bp, XFS_INO_BTREE_REF);
break;
case XFS_BTNUM_BMAP:
diff --git a/libxfs/xfs_ialloc.c b/libxfs/xfs_ialloc.c
index d4a4511..4a7746a 100644
--- a/libxfs/xfs_ialloc.c
+++ b/libxfs/xfs_ialloc.c
@@ -1482,6 +1482,8 @@ xfs_ialloc_log_agi(
offsetof(xfs_agi_t, agi_newino),
offsetof(xfs_agi_t, agi_dirino),
offsetof(xfs_agi_t, agi_unlinked),
+ offsetof(xfs_agi_t, agi_free_root),
+ offsetof(xfs_agi_t, agi_free_level),
sizeof(xfs_agi_t)
};
#ifdef DEBUG
@@ -1491,14 +1493,39 @@ xfs_ialloc_log_agi(
ASSERT(agi->agi_magicnum == cpu_to_be32(XFS_AGI_MAGIC));
#endif
/*
- * Compute byte offsets for the first and last fields.
+ * The growth of the agi buffer over time now requires that we interpret
+ * the buffer as two logical regions delineated at the end of the unlinked
+ * list. This is due to the size of the hash table and its location in the
+ * middle of the agi.
+ *
+ * For example, a request to log a field before agi_unlinked and a field
+ * after agi_unlinked could cause us to log the entire hash table and use
+ * an excessive amount of log space. To avoid this behavior, log the
+ * region up through agi_unlinked in one call and the region after
+ * agi_unlinked through the end of the structure in another.
*/
- xfs_btree_offsets(fields, offsets, XFS_AGI_NUM_BITS, &first, &last);
+ xfs_trans_buf_set_type(tp, bp, XFS_BLFT_AGI_BUF);
+
/*
- * Log the allocation group inode header buffer.
+ * Compute byte offsets for the first and last fields in the first
+ * region and log agi buffer. This only logs up through agi_unlinked.
*/
- xfs_trans_buf_set_type(tp, bp, XFS_BLFT_AGI_BUF);
- xfs_trans_log_buf(tp, bp, first, last);
+ if (fields & XFS_AGI_ALL_BITS_R1) {
+ xfs_btree_offsets(fields, offsets, XFS_AGI_NUM_BITS_R1,
+ &first, &last);
+ xfs_trans_log_buf(tp, bp, first, last);
+ }
+
+ /*
+ * Mask off the bits in the first region and calculate the first and last
+ * field offsets for any bits in the second region.
+ */
+ fields &= ~XFS_AGI_ALL_BITS_R1;
+ if (fields) {
+ xfs_btree_offsets(fields, offsets, XFS_AGI_NUM_BITS_R2,
+ &first, &last);
+ xfs_trans_log_buf(tp, bp, first, last);
+ }
}
#ifdef DEBUG
diff --git a/libxfs/xfs_ialloc_btree.c b/libxfs/xfs_ialloc_btree.c
index 2027bc6..c337389 100644
--- a/libxfs/xfs_ialloc_btree.c
+++ b/libxfs/xfs_ialloc_btree.c
@@ -48,6 +48,21 @@ xfs_inobt_set_root(
xfs_ialloc_log_agi(cur->bc_tp, agbp, XFS_AGI_ROOT | XFS_AGI_LEVEL);
}
+STATIC void
+xfs_finobt_set_root(
+ struct xfs_btree_cur *cur,
+ union xfs_btree_ptr *nptr,
+ int inc) /* level change */
+{
+ struct xfs_buf *agbp = cur->bc_private.a.agbp;
+ struct xfs_agi *agi = XFS_BUF_TO_AGI(agbp);
+
+ agi->agi_free_root = nptr->s;
+ be32_add_cpu(&agi->agi_free_level, inc);
+ xfs_ialloc_log_agi(cur->bc_tp, agbp,
+ XFS_AGI_FREE_ROOT | XFS_AGI_FREE_LEVEL);
+}
+
STATIC int
xfs_inobt_alloc_block(
struct xfs_btree_cur *cur,
@@ -155,6 +170,17 @@ xfs_inobt_init_ptr_from_cur(
ptr->s = agi->agi_root;
}
+STATIC void
+xfs_finobt_init_ptr_from_cur(
+ struct xfs_btree_cur *cur,
+ union xfs_btree_ptr *ptr)
+{
+ struct xfs_agi *agi = XFS_BUF_TO_AGI(cur->bc_private.a.agbp);
+
+ ASSERT(cur->bc_private.a.agno == be32_to_cpu(agi->agi_seqno));
+ ptr->s = agi->agi_free_root;
+}
+
STATIC __int64_t
xfs_inobt_key_diff(
struct xfs_btree_cur *cur,
@@ -185,6 +211,7 @@ xfs_inobt_verify(
*/
switch (block->bb_magic) {
case cpu_to_be32(XFS_IBT_CRC_MAGIC):
+ case cpu_to_be32(XFS_FIBT_CRC_MAGIC):
if (!xfs_sb_version_hascrc(&mp->m_sb))
return false;
if (!uuid_equal(&block->bb_u.s.bb_uuid, &mp->m_sb.sb_uuid))
@@ -196,6 +223,7 @@ xfs_inobt_verify(
return false;
/* fall through */
case cpu_to_be32(XFS_IBT_MAGIC):
+ case cpu_to_be32(XFS_FIBT_MAGIC):
break;
default:
return 0;
@@ -372,6 +400,28 @@ static const struct xfs_btree_ops xfs_inobt_ops = {
#endif
};
+static const struct xfs_btree_ops xfs_finobt_ops = {
+ .rec_len = sizeof(xfs_inobt_rec_t),
+ .key_len = sizeof(xfs_inobt_key_t),
+
+ .dup_cursor = xfs_inobt_dup_cursor,
+ .set_root = xfs_finobt_set_root,
+ .alloc_block = xfs_inobt_alloc_block,
+ .free_block = xfs_inobt_free_block,
+ .get_minrecs = xfs_inobt_get_minrecs,
+ .get_maxrecs = xfs_inobt_get_maxrecs,
+ .init_key_from_rec = xfs_inobt_init_key_from_rec,
+ .init_rec_from_key = xfs_inobt_init_rec_from_key,
+ .init_rec_from_cur = xfs_inobt_init_rec_from_cur,
+ .init_ptr_from_cur = xfs_finobt_init_ptr_from_cur,
+ .key_diff = xfs_inobt_key_diff,
+ .buf_ops = &xfs_inobt_buf_ops,
+#if defined(DEBUG) || defined(XFS_WARN)
+ .keys_inorder = xfs_inobt_keys_inorder,
+ .recs_inorder = xfs_inobt_recs_inorder,
+#endif
+};
+
/*
* Allocate a new inode btree cursor.
*/
@@ -390,11 +440,17 @@ xfs_inobt_init_cursor(
cur->bc_tp = tp;
cur->bc_mp = mp;
- cur->bc_nlevels = be32_to_cpu(agi->agi_level);
cur->bc_btnum = btnum;
+ if (btnum == XFS_BTNUM_INO) {
+ cur->bc_nlevels = be32_to_cpu(agi->agi_level);
+ cur->bc_ops = &xfs_inobt_ops;
+ } else {
+ cur->bc_nlevels = be32_to_cpu(agi->agi_free_level);
+ cur->bc_ops = &xfs_finobt_ops;
+ }
+
cur->bc_blocklog = mp->m_sb.sb_blocklog;
- cur->bc_ops = &xfs_inobt_ops;
if (xfs_sb_version_hascrc(&mp->m_sb))
cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
--
1.8.3.1
_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs
next prev parent reply other threads:[~2014-04-10 16:11 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-04-10 16:10 [PATCH v3 00/20] xfsprogs: introduce the free inode btree Brian Foster
2014-04-10 16:10 ` [PATCH v3 01/20] xfs: refactor xfs_ialloc_btree.c to support multiple inobt numbers Brian Foster
2014-04-10 16:10 ` [PATCH v3 02/20] xfs: reserve v5 superblock read-only compat. feature bit for finobt Brian Foster
2014-04-10 16:10 ` Brian Foster [this message]
2014-04-10 16:10 ` [PATCH v3 04/20] xfs: update inode allocation/free transaction reservations " Brian Foster
2014-04-10 16:10 ` [PATCH v3 05/20] xfs: insert newly allocated inode chunks into the finobt Brian Foster
2014-04-10 16:10 ` [PATCH v3 06/20] xfs: use and update the finobt on inode allocation Brian Foster
2014-04-10 16:10 ` [PATCH v3 07/20] xfs: refactor xfs_difree() inobt bits into xfs_difree_inobt() helper Brian Foster
2014-04-10 16:10 ` [PATCH v3 08/20] xfs: update the finobt on inode free Brian Foster
2014-04-10 16:10 ` [PATCH v3 09/20] xfs: report finobt status in fs geometry Brian Foster
2014-04-10 16:11 ` [PATCH v3 10/20] xfs: enable the finobt feature on v5 superblocks Brian Foster
2014-04-10 16:11 ` [PATCH v3 11/20] xfsprogs/mkfs: finobt mkfs support Brian Foster
2014-04-23 6:03 ` Dave Chinner
2014-04-23 20:01 ` Brian Foster
2014-04-10 16:11 ` [PATCH v3 12/20] xfsprogs/db: finobt support Brian Foster
2014-04-10 16:11 ` [PATCH v3 13/20] xfsprogs/repair: account for finobt in ag 0 geometry pre-calculation Brian Foster
2014-04-23 6:12 ` Dave Chinner
2014-04-23 20:02 ` Brian Foster
2014-04-23 22:53 ` Dave Chinner
2014-04-10 16:11 ` [PATCH v3 14/20] xfsprogs/repair: phase 2 finobt scan Brian Foster
2014-04-23 6:10 ` Dave Chinner
2014-04-23 6:19 ` Dave Chinner
2014-04-23 20:01 ` Brian Foster
2014-04-23 23:06 ` Dave Chinner
2014-04-24 0:39 ` Brian Foster
2014-04-10 16:11 ` [PATCH v3 15/20] xfsprogs/repair: pass btree block magic as param to build_ino_tree() Brian Foster
2014-04-10 16:11 ` [PATCH v3 16/20] xfsprogs/repair: pull the build_agi() call up out of the inode tree build Brian Foster
2014-04-10 16:11 ` [PATCH v3 17/20] xfsprogs/repair: helpers for finding in-core inode records w/ free inodes Brian Foster
2014-04-23 6:24 ` Dave Chinner
2014-04-23 20:02 ` Brian Foster
2014-04-23 22:58 ` Dave Chinner
2014-04-10 16:11 ` [PATCH v3 18/20] xfsprogs/repair: reconstruct the finobt in phase 5 Brian Foster
2014-04-10 16:11 ` [PATCH v3 19/20] xfsprogs/growfs: report finobt status in fs geometry (xfs_info) Brian Foster
2014-04-10 16:11 ` [PATCH v3 20/20] xfsprogs/db: add finobt support to metadump Brian Foster
2014-04-23 6:35 ` [PATCH v3 00/20] xfsprogs: introduce the free inode btree Dave Chinner
2014-04-23 20:02 ` Brian Foster
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=1397146270-42993-4-git-send-email-bfoster@redhat.com \
--to=bfoster@redhat.com \
--cc=xfs@oss.sgi.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
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.