summaryrefslogtreecommitdiffstats
path: root/fs/xfs/xfs_mount.c
diff options
context:
space:
mode:
authorDavid Chinner <dgc@sgi.com>2007-05-24 15:26:31 +1000
committerTim Shimmin <tes@chook.melbourne.sgi.com>2007-07-14 15:28:50 +1000
commit92821e2ba4ae26887223326fb0b95cdab963b768 (patch)
treea40a2ef10e5b0791df3e522f3139193d39bf2454 /fs/xfs/xfs_mount.c
parent3260f78ad6d5b788e78ea709d377f58e569bee41 (diff)
downloadop-kernel-dev-92821e2ba4ae26887223326fb0b95cdab963b768.zip
op-kernel-dev-92821e2ba4ae26887223326fb0b95cdab963b768.tar.gz
[XFS] Lazy Superblock Counters
When we have a couple of hundred transactions on the fly at once, they all typically modify the on disk superblock in some way. create/unclink/mkdir/rmdir modify inode counts, allocation/freeing modify free block counts. When these counts are modified in a transaction, they must eventually lock the superblock buffer and apply the mods. The buffer then remains locked until the transaction is committed into the incore log buffer. The result of this is that with enough transactions on the fly the incore superblock buffer becomes a bottleneck. The result of contention on the incore superblock buffer is that transaction rates fall - the more pressure that is put on the superblock buffer, the slower things go. The key to removing the contention is to not require the superblock fields in question to be locked. We do that by not marking the superblock dirty in the transaction. IOWs, we modify the incore superblock but do not modify the cached superblock buffer. In short, we do not log superblock modifications to critical fields in the superblock on every transaction. In fact we only do it just before we write the superblock to disk every sync period or just before unmount. This creates an interesting problem - if we don't log or write out the fields in every transaction, then how do the values get recovered after a crash? the answer is simple - we keep enough duplicate, logged information in other structures that we can reconstruct the correct count after log recovery has been performed. It is the AGF and AGI structures that contain the duplicate information; after recovery, we walk every AGI and AGF and sum their individual counters to get the correct value, and we do a transaction into the log to correct them. An optimisation of this is that if we have a clean unmount record, we know the value in the superblock is correct, so we can avoid the summation walk under normal conditions and so mount/recovery times do not change under normal operation. One wrinkle that was discovered during development was that the blocks used in the freespace btrees are never accounted for in the AGF counters. This was once a valid optimisation to make; when the filesystem is full, the free space btrees are empty and consume no space. Hence when it matters, the "accounting" is correct. But that means the when we do the AGF summations, we would not have a correct count and xfs_check would complain. Hence a new counter was added to track the number of blocks used by the free space btrees. This is an *on-disk format change*. As a result of this, lazy superblock counters are a mkfs option and at the moment on linux there is no way to convert an old filesystem. This is possible - xfs_db can be used to twiddle the right bits and then xfs_repair will do the format conversion for you. Similarly, you can convert backwards as well. At some point we'll add functionality to xfs_admin to do the bit twiddling easily.... SGI-PV: 964999 SGI-Modid: xfs-linux-melb:xfs-kern:28652a Signed-off-by: David Chinner <dgc@sgi.com> Signed-off-by: Christoph Hellwig <hch@infradead.org> Signed-off-by: Tim Shimmin <tes@sgi.com>
Diffstat (limited to 'fs/xfs/xfs_mount.c')
-rw-r--r--fs/xfs/xfs_mount.c154
1 files changed, 148 insertions, 6 deletions
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 5de1f39..f6fe47d 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -643,6 +643,64 @@ xfs_mount_common(xfs_mount_t *mp, xfs_sb_t *sbp)
sbp->sb_inopblock);
mp->m_ialloc_blks = mp->m_ialloc_inos >> sbp->sb_inopblog;
}
+
+/*
+ * xfs_initialize_perag_data
+ *
+ * Read in each per-ag structure so we can count up the number of
+ * allocated inodes, free inodes and used filesystem blocks as this
+ * information is no longer persistent in the superblock. Once we have
+ * this information, write it into the in-core superblock structure.
+ */
+STATIC int
+xfs_initialize_perag_data(xfs_mount_t *mp, xfs_agnumber_t agcount)
+{
+ xfs_agnumber_t index;
+ xfs_perag_t *pag;
+ xfs_sb_t *sbp = &mp->m_sb;
+ uint64_t ifree = 0;
+ uint64_t ialloc = 0;
+ uint64_t bfree = 0;
+ uint64_t bfreelst = 0;
+ uint64_t btree = 0;
+ int error;
+ int s;
+
+ for (index = 0; index < agcount; index++) {
+ /*
+ * read the agf, then the agi. This gets us
+ * all the inforamtion we need and populates the
+ * per-ag structures for us.
+ */
+ error = xfs_alloc_pagf_init(mp, NULL, index, 0);
+ if (error)
+ return error;
+
+ error = xfs_ialloc_pagi_init(mp, NULL, index);
+ if (error)
+ return error;
+ pag = &mp->m_perag[index];
+ ifree += pag->pagi_freecount;
+ ialloc += pag->pagi_count;
+ bfree += pag->pagf_freeblks;
+ bfreelst += pag->pagf_flcount;
+ btree += pag->pagf_btreeblks;
+ }
+ /*
+ * Overwrite incore superblock counters with just-read data
+ */
+ s = XFS_SB_LOCK(mp);
+ sbp->sb_ifree = ifree;
+ sbp->sb_icount = ialloc;
+ sbp->sb_fdblocks = bfree + bfreelst + btree;
+ XFS_SB_UNLOCK(mp, s);
+
+ /* Fixup the per-cpu counters as well. */
+ xfs_icsb_reinit_counters(mp);
+
+ return 0;
+}
+
/*
* xfs_mountfs
*
@@ -987,6 +1045,34 @@ xfs_mountfs(
}
/*
+ * Now the log is mounted, we know if it was an unclean shutdown or
+ * not. If it was, with the first phase of recovery has completed, we
+ * have consistent AG blocks on disk. We have not recovered EFIs yet,
+ * but they are recovered transactionally in the second recovery phase
+ * later.
+ *
+ * Hence we can safely re-initialise incore superblock counters from
+ * the per-ag data. These may not be correct if the filesystem was not
+ * cleanly unmounted, so we need to wait for recovery to finish before
+ * doing this.
+ *
+ * If the filesystem was cleanly unmounted, then we can trust the
+ * values in the superblock to be correct and we don't need to do
+ * anything here.
+ *
+ * If we are currently making the filesystem, the initialisation will
+ * fail as the perag data is in an undefined state.
+ */
+
+ if (xfs_sb_version_haslazysbcount(&mp->m_sb) &&
+ !XFS_LAST_UNMOUNT_WAS_CLEAN(mp) &&
+ !mp->m_sb.sb_inprogress) {
+ error = xfs_initialize_perag_data(mp, sbp->sb_agcount);
+ if (error) {
+ goto error2;
+ }
+ }
+ /*
* Get and sanity-check the root inode.
* Save the pointer to it in the mount structure.
*/
@@ -1049,6 +1135,7 @@ xfs_mountfs(
goto error4;
}
+
/*
* Complete the quota initialisation, post-log-replay component.
*/
@@ -1111,10 +1198,9 @@ xfs_unmountfs(xfs_mount_t *mp, struct cred *cr)
xfs_binval(mp->m_rtdev_targp);
}
+ xfs_log_sbcount(mp, 1);
xfs_unmountfs_writesb(mp);
-
xfs_unmountfs_wait(mp); /* wait for async bufs */
-
xfs_log_unmount(mp); /* Done! No more fs ops. */
xfs_freesb(mp);
@@ -1161,6 +1247,62 @@ xfs_unmountfs_wait(xfs_mount_t *mp)
}
int
+xfs_fs_writable(xfs_mount_t *mp)
+{
+ bhv_vfs_t *vfsp = XFS_MTOVFS(mp);
+
+ return !(vfs_test_for_freeze(vfsp) || XFS_FORCED_SHUTDOWN(mp) ||
+ (vfsp->vfs_flag & VFS_RDONLY));
+}
+
+/*
+ * xfs_log_sbcount
+ *
+ * Called either periodically to keep the on disk superblock values
+ * roughly up to date or from unmount to make sure the values are
+ * correct on a clean unmount.
+ *
+ * Note this code can be called during the process of freezing, so
+ * we may need to use the transaction allocator which does not not
+ * block when the transaction subsystem is in its frozen state.
+ */
+int
+xfs_log_sbcount(
+ xfs_mount_t *mp,
+ uint sync)
+{
+ xfs_trans_t *tp;
+ int error;
+
+ if (!xfs_fs_writable(mp))
+ return 0;
+
+ xfs_icsb_sync_counters(mp);
+
+ /*
+ * we don't need to do this if we are updating the superblock
+ * counters on every modification.
+ */
+ if (!xfs_sb_version_haslazysbcount(&mp->m_sb))
+ return 0;
+
+ tp = _xfs_trans_alloc(mp, XFS_TRANS_SB_COUNT);
+ error = xfs_trans_reserve(tp, 0, mp->m_sb.sb_sectsize + 128, 0, 0,
+ XFS_DEFAULT_LOG_COUNT);
+ if (error) {
+ xfs_trans_cancel(tp, 0);
+ return error;
+ }
+
+ xfs_mod_sb(tp, XFS_SB_IFREE | XFS_SB_ICOUNT | XFS_SB_FDBLOCKS);
+ if (sync)
+ xfs_trans_set_sync(tp);
+ xfs_trans_commit(tp, 0);
+
+ return 0;
+}
+
+int
xfs_unmountfs_writesb(xfs_mount_t *mp)
{
xfs_buf_t *sbp;
@@ -1171,16 +1313,15 @@ xfs_unmountfs_writesb(xfs_mount_t *mp)
* skip superblock write if fs is read-only, or
* if we are doing a forced umount.
*/
- sbp = xfs_getsb(mp, 0);
if (!(XFS_MTOVFS(mp)->vfs_flag & VFS_RDONLY ||
XFS_FORCED_SHUTDOWN(mp))) {
- xfs_icsb_sync_counters(mp);
+ sbp = xfs_getsb(mp, 0);
+ sb = XFS_BUF_TO_SBP(sbp);
/*
* mark shared-readonly if desired
*/
- sb = XFS_BUF_TO_SBP(sbp);
if (mp->m_mk_sharedro) {
if (!(sb->sb_flags & XFS_SBF_READONLY))
sb->sb_flags |= XFS_SBF_READONLY;
@@ -1189,6 +1330,7 @@ xfs_unmountfs_writesb(xfs_mount_t *mp)
xfs_fs_cmn_err(CE_NOTE, mp,
"Unmounting, marking shared read-only");
}
+
XFS_BUF_UNDONE(sbp);
XFS_BUF_UNREAD(sbp);
XFS_BUF_UNDELAYWRITE(sbp);
@@ -1203,8 +1345,8 @@ xfs_unmountfs_writesb(xfs_mount_t *mp)
mp, sbp, XFS_BUF_ADDR(sbp));
if (error && mp->m_mk_sharedro)
xfs_fs_cmn_err(CE_ALERT, mp, "Superblock write error detected while unmounting. Filesystem may not be marked shared readonly");
+ xfs_buf_relse(sbp);
}
- xfs_buf_relse(sbp);
return error;
}
OpenPOWER on IntegriCloud