xfs
[Top] [All Lists]

[PATCH v4 04/11] xfs: update inode allocation/free transaction reservati

To: xfs@xxxxxxxxxxx
Subject: [PATCH v4 04/11] xfs: update inode allocation/free transaction reservations for finobt
From: Brian Foster <bfoster@xxxxxxxxxx>
Date: Mon, 24 Feb 2014 09:29:56 -0500
Delivered-to: xfs@xxxxxxxxxxx
In-reply-to: <1393252203-7423-1-git-send-email-bfoster@xxxxxxxxxx>
References: <1393252203-7423-1-git-send-email-bfoster@xxxxxxxxxx>
Create the xfs_calc_finobt_res() helper to calculate the finobt log
reservation for inode allocation and free. Update
XFS_IALLOC_SPACE_RES() to reserve blocks for the additional finobt
insertion on inode allocation. Create XFS_IFREE_SPACE_RES() to
reserve blocks for the potential finobt record insertion on inode
free (i.e., if an inode chunk was previously fully allocated).

Signed-off-by: Brian Foster <bfoster@xxxxxxxxxx>
---
 fs/xfs/xfs_inode.c       | 25 ++++++++++++++++++++++-
 fs/xfs/xfs_trans_resv.c  | 53 +++++++++++++++++++++++++++++++++++++++++++++---
 fs/xfs/xfs_trans_space.h |  7 ++++++-
 3 files changed, 80 insertions(+), 5 deletions(-)

diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 3a137e9..08c3a31 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1726,8 +1726,31 @@ xfs_inactive_ifree(
        int                     error;
 
        tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE);
-       error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ifree, 0, 0);
+
+       /*
+        * The ifree transaction might need to allocate blocks for record
+        * insertion to the finobt. We don't want to fail here at ENOSPC, so
+        * allow ifree to dip into the reserved block pool if necessary.
+        *
+        * Freeing large sets of inodes generally means freeing inode chunks,
+        * directory and file data blocks, so this should be relatively safe.
+        * Only under severe circumstances should it be possible to free enough
+        * inodes to exhaust the reserve block pool via finobt expansion while
+        * at the same time not creating free space in the filesystem.
+        *
+        * Send a warning if the reservation does happen to fail, as the inode
+        * now remains allocated and sits on the unlinked list until the fs is
+        * repaired.
+        */
+       tp->t_flags |= XFS_TRANS_RESERVE;
+       error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ifree,
+                                 XFS_IFREE_SPACE_RES(mp), 0);
        if (error) {
+               if (error == ENOSPC)
+                       xfs_warn_ratelimited(mp,
+                       "Failed to remove inode(s) from unlinked list. "
+                       "Please free space, unmount and run xfs_repair.");
+
                ASSERT(XFS_FORCED_SHUTDOWN(mp));
                xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES);
                return error;
diff --git a/fs/xfs/xfs_trans_resv.c b/fs/xfs/xfs_trans_resv.c
index 2ffd3e3..7746ba9 100644
--- a/fs/xfs/xfs_trans_resv.c
+++ b/fs/xfs/xfs_trans_resv.c
@@ -98,6 +98,47 @@ xfs_calc_inode_res(
 }
 
 /*
+ * The free inode btree is a conditional feature and the log reservation
+ * requirements differ slightly from that of the traditional inode allocation
+ * btree. The finobt tracks records for inode chunks with at least one free
+ * inode. A record can be removed from the tree for an inode allocation
+ * or free and thus the finobt reservation is unconditional across:
+ *
+ *     - inode allocation
+ *     - inode free
+ *     - inode chunk allocation
+ *
+ * The 'modify' param indicates to include the record modification scenario. 
The
+ * 'alloc' param indicates to include the reservation for free space btree
+ * modifications on behalf of finobt modifications. This is required only for
+ * transactions that do not already account for free space btree modifications.
+ *
+ * the free inode btree: max depth * block size
+ * the allocation btrees: 2 trees * (max depth - 1) * block size
+ * the free inode btree entry: block size
+ */
+STATIC uint
+xfs_calc_finobt_res(
+       struct xfs_mount        *mp,
+       int                     alloc,
+       int                     modify)
+{
+       uint res;
+
+       if (!xfs_sb_version_hasfinobt(&mp->m_sb))
+               return 0;
+
+       res = xfs_calc_buf_res(mp->m_in_maxlevels, XFS_FSB_TO_B(mp, 1));
+       if (alloc)
+               res += xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 1), 
+                                       XFS_FSB_TO_B(mp, 1));
+       if (modify)
+               res += (uint)XFS_FSB_TO_B(mp, 1);
+
+       return res;
+}
+
+/*
  * Various log reservation values.
  *
  * These are based on the size of the file system block because that is what
@@ -267,6 +308,7 @@ xfs_calc_remove_reservation(
  *    the superblock for the nlink flag: sector size
  *    the directory btree: (max depth + v2) * dir block size
  *    the directory inode's bmap btree: (max depth + v2) * block size
+ *    the finobt (record modification and allocation btrees)
  */
 STATIC uint
 xfs_calc_create_resv_modify(
@@ -275,7 +317,8 @@ xfs_calc_create_resv_modify(
        return xfs_calc_inode_res(mp, 2) +
                xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) +
                (uint)XFS_FSB_TO_B(mp, 1) +
-               xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp), XFS_FSB_TO_B(mp, 1));
+               xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp), XFS_FSB_TO_B(mp, 1)) +
+               xfs_calc_finobt_res(mp, 1, 1);
 }
 
 /*
@@ -313,6 +356,7 @@ __xfs_calc_create_reservation(
  *    the superblock for the nlink flag: sector size
  *    the inode btree: max depth * blocksize
  *    the allocation btrees: 2 trees * (max depth - 1) * block size
+ *    the finobt (record insertion)
  */
 STATIC uint
 xfs_calc_icreate_resv_alloc(
@@ -322,7 +366,8 @@ xfs_calc_icreate_resv_alloc(
                mp->m_sb.sb_sectsize +
                xfs_calc_buf_res(mp->m_in_maxlevels, XFS_FSB_TO_B(mp, 1)) +
                xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 1),
-                                XFS_FSB_TO_B(mp, 1));
+                                XFS_FSB_TO_B(mp, 1)) +
+               xfs_calc_finobt_res(mp, 0, 0);
 }
 
 STATIC uint
@@ -376,6 +421,7 @@ xfs_calc_symlink_reservation(
  *    the on disk inode before ours in the agi hash list: inode cluster size
  *    the inode btree: max depth * blocksize
  *    the allocation btrees: 2 trees * (max depth - 1) * block size
+ *    the finobt (record insertion, removal or modification)
  */
 STATIC uint
 xfs_calc_ifree_reservation(
@@ -390,7 +436,8 @@ xfs_calc_ifree_reservation(
                xfs_calc_buf_res(2 + mp->m_ialloc_blks +
                                 mp->m_in_maxlevels, 0) +
                xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 1),
-                                XFS_FSB_TO_B(mp, 1));
+                                XFS_FSB_TO_B(mp, 1)) +
+               xfs_calc_finobt_res(mp, 0, 1);
 }
 
 /*
diff --git a/fs/xfs/xfs_trans_space.h b/fs/xfs/xfs_trans_space.h
index af5dbe0..df4c1f8 100644
--- a/fs/xfs/xfs_trans_space.h
+++ b/fs/xfs/xfs_trans_space.h
@@ -47,7 +47,9 @@
 #define        XFS_DIRREMOVE_SPACE_RES(mp)     \
        XFS_DAREMOVE_SPACE_RES(mp, XFS_DATA_FORK)
 #define        XFS_IALLOC_SPACE_RES(mp)        \
-       ((mp)->m_ialloc_blks + (mp)->m_in_maxlevels - 1)
+       ((mp)->m_ialloc_blks + \
+        (xfs_sb_version_hasfinobt(&mp->m_sb) ? 2 : 1 * \
+         ((mp)->m_in_maxlevels - 1)))
 
 /*
  * Space reservation values for various transactions.
@@ -82,5 +84,8 @@
        (XFS_DIRREMOVE_SPACE_RES(mp) + XFS_DIRENTER_SPACE_RES(mp,nl))
 #define        XFS_SYMLINK_SPACE_RES(mp,nl,b)  \
        (XFS_IALLOC_SPACE_RES(mp) + XFS_DIRENTER_SPACE_RES(mp,nl) + (b))
+#define XFS_IFREE_SPACE_RES(mp)                \
+       (xfs_sb_version_hasfinobt(&mp->m_sb) ? (mp)->m_in_maxlevels : 0)
+
 
 #endif /* __XFS_TRANS_SPACE_H__ */
-- 
1.8.3.1

<Prev in Thread] Current Thread [Next in Thread>