summaryrefslogtreecommitdiffstats
path: root/fs/xfs/libxfs/xfs_rmap_btree.c
diff options
context:
space:
mode:
authorDarrick J. Wong <darrick.wong@oracle.com>2016-10-03 09:11:44 -0700
committerDarrick J. Wong <darrick.wong@oracle.com>2016-10-05 16:26:27 -0700
commit84d6961910ea7b3ae8d8338f5b4df25dea68cee9 (patch)
treef9c9c9f6f34bce9ff3b035df350cfe70e16b24f1 /fs/xfs/libxfs/xfs_rmap_btree.c
parentf7ca35227253dc8244fd908140b06010e67a31e5 (diff)
downloadlinux-84d6961910ea7b3ae8d8338f5b4df25dea68cee9.tar.gz
linux-84d6961910ea7b3ae8d8338f5b4df25dea68cee9.tar.bz2
linux-84d6961910ea7b3ae8d8338f5b4df25dea68cee9.zip
xfs: preallocate blocks for worst-case btree expansion
To gracefully handle the situation where a CoW operation turns a single refcount extent into a lot of tiny ones and then run out of space when a tree split has to happen, use the per-AG reserved block pool to pre-allocate all the space we'll ever need for a maximal btree. For a 4K block size, this only costs an overhead of 0.3% of available disk space. When reflink is enabled, we have an unfortunate problem with rmap -- since we can share a block billions of times, this means that the reverse mapping btree can expand basically infinitely. When an AG is so full that there are no free blocks with which to expand the rmapbt, the filesystem will shut down hard. This is rather annoying to the user, so use the AG reservation code to reserve a "reasonable" amount of space for rmap. We'll prevent reflinks and CoW operations if we think we're getting close to exhausting an AG's free space rather than shutting down, but this permanent reservation should be enough for "most" users. Hopefully. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> [hch@lst.de: ensure that we invalidate the freed btree buffer] Signed-off-by: Christoph Hellwig <hch@lst.de>
Diffstat (limited to 'fs/xfs/libxfs/xfs_rmap_btree.c')
-rw-r--r--fs/xfs/libxfs/xfs_rmap_btree.c60
1 files changed, 60 insertions, 0 deletions
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index 9c0585e7db1f..83e672ff7577 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rmap_btree.c
@@ -35,6 +35,7 @@
#include "xfs_cksum.h"
#include "xfs_error.h"
#include "xfs_extent_busy.h"
+#include "xfs_ag_resv.h"
/*
* Reverse map btree.
@@ -533,3 +534,62 @@ xfs_rmapbt_compute_maxlevels(
mp->m_rmap_maxlevels = xfs_btree_compute_maxlevels(mp,
mp->m_rmap_mnr, mp->m_sb.sb_agblocks);
}
+
+/* Calculate the refcount btree size for some records. */
+xfs_extlen_t
+xfs_rmapbt_calc_size(
+ struct xfs_mount *mp,
+ unsigned long long len)
+{
+ return xfs_btree_calc_size(mp, mp->m_rmap_mnr, len);
+}
+
+/*
+ * Calculate the maximum refcount btree size.
+ */
+xfs_extlen_t
+xfs_rmapbt_max_size(
+ struct xfs_mount *mp)
+{
+ /* Bail out if we're uninitialized, which can happen in mkfs. */
+ if (mp->m_rmap_mxr[0] == 0)
+ return 0;
+
+ return xfs_rmapbt_calc_size(mp, mp->m_sb.sb_agblocks);
+}
+
+/*
+ * Figure out how many blocks to reserve and how many are used by this btree.
+ */
+int
+xfs_rmapbt_calc_reserves(
+ struct xfs_mount *mp,
+ xfs_agnumber_t agno,
+ xfs_extlen_t *ask,
+ xfs_extlen_t *used)
+{
+ struct xfs_buf *agbp;
+ struct xfs_agf *agf;
+ xfs_extlen_t pool_len;
+ xfs_extlen_t tree_len;
+ int error;
+
+ if (!xfs_sb_version_hasrmapbt(&mp->m_sb))
+ return 0;
+
+ /* Reserve 1% of the AG or enough for 1 block per record. */
+ pool_len = max(mp->m_sb.sb_agblocks / 100, xfs_rmapbt_max_size(mp));
+ *ask += pool_len;
+
+ error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agbp);
+ if (error)
+ return error;
+
+ agf = XFS_BUF_TO_AGF(agbp);
+ tree_len = be32_to_cpu(agf->agf_rmap_blocks);
+ xfs_buf_relse(agbp);
+
+ *used += tree_len;
+
+ return error;
+}