From: Brian Foster <bfoster@redhat.com>
To: xfs@oss.sgi.com
Subject: [RFC PATCH 09/11] xfs: use and update the finobt on inode allocation
Date: Tue, 3 Sep 2013 14:25:06 -0400 [thread overview]
Message-ID: <1378232708-57156-10-git-send-email-bfoster@redhat.com> (raw)
In-Reply-To: <1378232708-57156-1-git-send-email-bfoster@redhat.com>
Replace xfs_dialloc_ag() with an implementation that looks for a
record in the finobt. The finobt only tracks records with at least
one free inode. This eliminates the need for the intra-ag scan in
the original algorithm. Once the inode is allocated, update the
finobt appropriately (possibly removing the record) as well as the
inobt.
Move the original xfs_dialloc_ag() algorithm to
xfs_dialloc_ag_slow() and fall back as such if finobt support is
not enabled.
Signed-off-by: Brian Foster <bfoster@redhat.com>
---
fs/xfs/xfs_ialloc.c | 136 +++++++++++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 135 insertions(+), 1 deletion(-)
diff --git a/fs/xfs/xfs_ialloc.c b/fs/xfs/xfs_ialloc.c
index e64a728..516f4af 100644
--- a/fs/xfs/xfs_ialloc.c
+++ b/fs/xfs/xfs_ialloc.c
@@ -708,7 +708,7 @@ xfs_ialloc_get_rec(
* available.
*/
STATIC int
-xfs_dialloc_ag(
+xfs_dialloc_ag_slow(
struct xfs_trans *tp,
struct xfs_buf *agbp,
xfs_ino_t parent,
@@ -966,6 +966,140 @@ error0:
return error;
}
+STATIC int
+xfs_dialloc_ag(
+ struct xfs_trans *tp,
+ struct xfs_buf *agbp,
+ xfs_ino_t parent,
+ xfs_ino_t *inop)
+{
+ struct xfs_mount *mp = tp->t_mountp;
+ struct xfs_agi *agi = XFS_BUF_TO_AGI(agbp);
+ xfs_agnumber_t agno = be32_to_cpu(agi->agi_seqno);
+ xfs_agino_t pagino = XFS_INO_TO_AGINO(mp, parent);
+ struct xfs_perag *pag;
+ struct xfs_btree_cur *fcur;
+ struct xfs_btree_cur *icur;
+ struct xfs_inobt_rec_incore frec;
+ struct xfs_inobt_rec_incore irec;
+ xfs_ino_t ino;
+ int error;
+ int offset;
+ int i;
+
+ if (!xfs_sb_version_hasfinobt(&mp->m_sb))
+ return xfs_dialloc_ag_slow(tp, agbp, parent, inop);
+
+ pag = xfs_perag_get(mp, agno);
+
+ /*
+ * If pagino is 0 (this is the root inode allocation) use newino.
+ * This must work because we've just allocated some.
+ */
+ if (!pagino)
+ pagino = be32_to_cpu(agi->agi_newino);
+
+ fcur = xfs_inobt_init_cursor(mp, tp, agbp, agno, XFS_BTNUM_FINO);
+ icur = xfs_inobt_init_cursor(mp, tp, agbp, agno, XFS_BTNUM_INO);
+
+ error = xfs_check_agi_freecount(fcur, agi);
+ if (error)
+ goto error;
+ error = xfs_check_agi_freecount(icur, agi);
+ if (error)
+ goto error;
+
+ /*
+ * Search the finobt.
+ */
+ error = xfs_inobt_lookup(fcur, pagino, XFS_LOOKUP_LE, &i);
+ if (error)
+ goto error;
+ if (i == 0) {
+ error = xfs_inobt_lookup(fcur, pagino, XFS_LOOKUP_GE, &i);
+ if (error)
+ goto error;
+ XFS_WANT_CORRUPTED_GOTO(i == 1, error);
+ }
+
+ error = xfs_inobt_get_rec(fcur, &frec, &i);
+ if (error)
+ goto error;
+ XFS_WANT_CORRUPTED_GOTO(i == 1, error);
+
+ offset = xfs_lowbit64(frec.ir_free);
+ ASSERT(offset >= 0);
+ ASSERT(offset < XFS_INODES_PER_CHUNK);
+ ASSERT((XFS_AGINO_TO_OFFSET(mp, frec.ir_startino) %
+ XFS_INODES_PER_CHUNK) == 0);
+ ino = XFS_AGINO_TO_INO(mp, agno, frec.ir_startino + offset);
+
+ /*
+ * Modify or remove the finobt record.
+ */
+ frec.ir_free &= ~XFS_INOBT_MASK(offset);
+ frec.ir_freecount--;
+ if (frec.ir_freecount)
+ error = xfs_inobt_update(fcur, &frec);
+ else
+ error = xfs_btree_delete(fcur, &i);
+ if (error)
+ goto error;
+
+ /*
+ * Lookup and modify the equivalent record in the inobt.
+ */
+ error = xfs_inobt_lookup(icur, frec.ir_startino, XFS_LOOKUP_EQ, &i);
+ if (error)
+ goto error;
+ XFS_WANT_CORRUPTED_GOTO(i == 1, error);
+
+ error = xfs_inobt_get_rec(icur, &irec, &i);
+ if (error)
+ goto error;
+ XFS_WANT_CORRUPTED_GOTO(i == 1, error);
+ ASSERT((XFS_AGINO_TO_OFFSET(mp, irec.ir_startino) %
+ XFS_INODES_PER_CHUNK) == 0);
+
+ irec.ir_free &= ~XFS_INOBT_MASK(offset);
+ irec.ir_freecount--;
+
+ XFS_WANT_CORRUPTED_GOTO((frec.ir_free == irec.ir_free) &&
+ (frec.ir_freecount == irec.ir_freecount),
+ error);
+
+ error = xfs_inobt_update(icur, &irec);
+ if (error)
+ goto error;
+
+ /*
+ * Update the perag and superblock.
+ */
+ be32_add_cpu(&agi->agi_freecount, -1);
+ xfs_ialloc_log_agi(tp, agbp, XFS_AGI_FREECOUNT);
+ pag->pagi_freecount--;
+
+ xfs_trans_mod_sb(tp, XFS_TRANS_SB_IFREE, -1);
+ xfs_perag_put(pag);
+
+ error = xfs_check_agi_freecount(fcur, agi);
+ if (error)
+ goto error;
+ error = xfs_check_agi_freecount(icur, agi);
+ if (error)
+ goto error;
+
+ xfs_btree_del_cursor(icur, XFS_BTREE_NOERROR);
+ xfs_btree_del_cursor(fcur, XFS_BTREE_ERROR);
+ *inop = ino;
+ return 0;
+error:
+ xfs_perag_put(pag);
+ xfs_btree_del_cursor(icur, XFS_BTREE_ERROR);
+ xfs_btree_del_cursor(fcur, XFS_BTREE_ERROR);
+ return error;
+}
+
/*
* Allocate an inode on disk.
*
--
1.8.1.4
_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs
next prev parent reply other threads:[~2013-09-03 18:25 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-09-03 18:24 [RFC PATCH 00/11] xfs: introduce the free inode btree Brian Foster
2013-09-03 18:24 ` [RFC PATCH 01/11] xfs: refactor xfs_ialloc_btree.c to support multiple inobt numbers Brian Foster
2013-09-05 0:36 ` Dave Chinner
2013-09-03 18:24 ` [RFC PATCH 02/11] xfs: reserve v5 superblock read-only compat. feature bit for finobt Brian Foster
2013-09-05 0:39 ` Dave Chinner
2013-09-03 18:25 ` [RFC PATCH 03/11] xfs: support the XFS_BTNUM_FINOBT free inode btree type Brian Foster
2013-09-05 0:54 ` Dave Chinner
2013-09-05 16:17 ` Brian Foster
2013-09-06 0:07 ` Dave Chinner
2013-09-06 11:25 ` Brian Foster
2013-09-06 21:22 ` Dave Chinner
2013-09-03 18:25 ` [RFC PATCH 04/11] xfs: update inode allocation transaction reservations for finobt Brian Foster
2013-09-05 0:59 ` Dave Chinner
2013-09-05 16:17 ` Brian Foster
2013-09-06 0:11 ` Dave Chinner
2013-09-03 18:25 ` [RFC PATCH 05/11] xfs: update ifree " Brian Foster
2013-09-05 1:00 ` Dave Chinner
2013-09-03 18:25 ` [RFC PATCH 06/11] xfs: use correct transaction reservations in xfs_inactive() Brian Foster
2013-09-05 1:35 ` Dave Chinner
2013-09-05 16:18 ` Brian Foster
2013-09-03 18:25 ` [RFC PATCH 07/11] xfs: retry trans reservation on ENOSPC " Brian Foster
2013-09-05 1:40 ` Dave Chinner
2013-09-05 16:18 ` Brian Foster
2013-09-06 0:17 ` Dave Chinner
2013-09-06 11:30 ` Brian Foster
2013-09-03 18:25 ` [RFC PATCH 08/11] xfs: insert newly allocated inode chunks into the finobt Brian Foster
2013-09-05 2:10 ` Dave Chinner
2013-09-03 18:25 ` Brian Foster [this message]
2013-09-05 2:27 ` [RFC PATCH 09/11] xfs: use and update the finobt on inode allocation Dave Chinner
2013-09-05 16:18 ` Brian Foster
2013-09-03 18:25 ` [RFC PATCH 10/11] xfs: update the finobt on inode free Brian Foster
2013-09-05 2:54 ` Dave Chinner
2013-09-05 16:19 ` Brian Foster
2013-09-06 0:28 ` Dave Chinner
2013-09-06 11:39 ` Brian Foster
2013-09-06 21:24 ` Dave Chinner
2013-09-07 12:30 ` Brian Foster
2013-09-08 20:08 ` Michael L. Semon
2013-09-09 2:34 ` Better numbers " Michael L. Semon
2013-09-03 18:25 ` [RFC PATCH 11/11] xfs: add finobt support to growfs Brian Foster
2013-09-05 2:55 ` Dave Chinner
2013-09-05 21:17 ` [RFC PATCH 00/11] xfs: introduce the free inode btree Michael L. Semon
2013-09-06 11:17 ` Brian Foster
2013-09-06 21:35 ` Dave Chinner
2013-09-07 12:31 ` Brian Foster
2013-09-08 1:04 ` Michael L. Semon
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=1378232708-57156-10-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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox