rpms/xfsprogs
7
0
Fork 0
Code Issues Pull Requests Releases Activity
6f6d622224
xfsprogs/SOURCES/xfsprogs-5.7.0-xfs_repair-fix-rebuilding-btree-block-less-than-minr.patch
CentOS Sources e1ec33f6ac import xfsprogs-5.0.0-10.el8
2022-05-10 12:04:34 +00:00

291 lines
9.6 KiB
Diff
Executable File
Raw Blame History

From 6df28d12d7760701c9d11e659e374665c5ffd0b9 Mon Sep 17 00:00:00 2001
From: Gao Xiang <hsiangkao@redhat.com>
Date: Fri, 10 Jul 2020 15:32:36 -0400
Subject: [PATCH] xfs_repair: fix rebuilding btree block less than minrecs
In production, we found that sometimes xfs_repair phase 5
rebuilds freespace node block with pointers less than minrecs
and if we trigger xfs_repair again it would report such
the following message:
bad btree nrecs (39, min=40, max=80) in btbno block 0/7882
The background is that xfs_repair starts to rebuild AGFL
after the freespace btree is settled in phase 5 so we may
need to leave necessary room in advance for each btree
leaves in order to avoid freespace btree split and then
result in AGFL rebuild fails. The old mathematics uses
ceil(num_extents / maxrecs) to decide the number of node
blocks. That would be fine without leaving extra space
since minrecs = maxrecs / 2 but if some slack was decreased
from maxrecs, the result would be larger than what is
expected and cause num_recs_pb less than minrecs, i.e:
num_extents = 79, adj_maxrecs = 80 - 2 (slack) = 78
so we'd get
num_blocks = ceil(79 / 78) = 2,
num_recs_pb = 79 / 2 = 39, which is less than
minrecs = 80 / 2 = 40
OTOH, btree bulk loading code behaves in a different way.
As in xfs_btree_bload_level_geometry it wrote
num_blocks = floor(num_extents / maxrecs)
which will never go below minrecs. And when it goes above
maxrecs, just increment num_blocks and recalculate so we
can get the reasonable results.
Later, btree bulk loader will replace the current repair code.
But we may still want to look for a backportable solution
for stable versions. Hence, keep the same logic to avoid
the freespace as well as rmap btree minrecs underflow for now.
Cc: "Darrick J. Wong" <darrick.wong@oracle.com>
Cc: Dave Chinner <dchinner@redhat.com>
Cc: Eric Sandeen <sandeen@sandeen.net>
Fixes: 9851fd79bfb1 ("repair: AGFL rebuild fails if btree split required")
Signed-off-by: Gao Xiang <hsiangkao@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Eric Sandeen <sandeen@sandeen.net>
---
repair/phase5.c | 152 ++++++++++++++++++++----------------------------
1 file changed, 63 insertions(+), 89 deletions(-)
Index: xfsprogs-5.0.0/repair/phase5.c
===================================================================
--- xfsprogs-5.0.0.orig/repair/phase5.c
+++ xfsprogs-5.0.0/repair/phase5.c
@@ -346,11 +346,32 @@ finish_cursor(bt_status_t *curs)
* failure at runtime. Hence leave a couple of records slack space in
* each block to allow immediate modification of the tree without
* requiring splits to be done.
- *
- * XXX(hch): any reason we don't just look at mp->m_alloc_mxr?
*/
-#define XR_ALLOC_BLOCK_MAXRECS(mp, level) \
- (libxfs_allocbt_maxrecs((mp), (mp)->m_sb.sb_blocksize, (level) == 0) - 2)
+static void
+compute_level_geometry(
+ struct xfs_mount *mp,
+ struct bt_stat_level *lptr,
+ uint64_t nr_this_level,
+ int slack,
+ bool leaf)
+{
+ unsigned int maxrecs = mp->m_alloc_mxr[!leaf];
+ unsigned int desired_npb;
+
+ desired_npb = max(mp->m_alloc_mnr[!leaf], maxrecs - slack);
+ lptr->num_recs_tot = nr_this_level;
+ lptr->num_blocks = max(1ULL, nr_this_level / desired_npb);
+
+ lptr->num_recs_pb = nr_this_level / lptr->num_blocks;
+ lptr->modulo = nr_this_level % lptr->num_blocks;
+ if (lptr->num_recs_pb > maxrecs ||
+ (lptr->num_recs_pb == maxrecs && lptr->modulo)) {
+ lptr->num_blocks++;
+
+ lptr->num_recs_pb = nr_this_level / lptr->num_blocks;
+ lptr->modulo = nr_this_level % lptr->num_blocks;
+ }
+}
/*
* this calculates a freespace cursor for an ag.
@@ -368,6 +389,7 @@ calculate_freespace_cursor(xfs_mount_t *
int i;
int extents_used;
int extra_blocks;
+ uint64_t old_blocks;
bt_stat_level_t *lptr;
bt_stat_level_t *p_lptr;
extent_tree_node_t *ext_ptr;
@@ -386,10 +408,7 @@ calculate_freespace_cursor(xfs_mount_t *
* of the tree and set up the cursor for the leaf level
* (note that the same code is duplicated further down)
*/
- lptr->num_blocks = howmany(num_extents, XR_ALLOC_BLOCK_MAXRECS(mp, 0));
- lptr->num_recs_pb = num_extents / lptr->num_blocks;
- lptr->modulo = num_extents % lptr->num_blocks;
- lptr->num_recs_tot = num_extents;
+ compute_level_geometry(mp, lptr, num_extents, 2, true);
level = 1;
#ifdef XR_BLD_FREE_TRACE
@@ -403,30 +422,23 @@ calculate_freespace_cursor(xfs_mount_t *
* if we need more levels, set them up. # of records
* per level is the # of blocks in the level below it
*/
- if (lptr->num_blocks > 1) {
- for (; btree_curs->level[level - 1].num_blocks > 1
- && level < XFS_BTREE_MAXLEVELS;
- level++) {
- lptr = &btree_curs->level[level];
- p_lptr = &btree_curs->level[level - 1];
- lptr->num_blocks = howmany(p_lptr->num_blocks,
- XR_ALLOC_BLOCK_MAXRECS(mp, level));
- lptr->modulo = p_lptr->num_blocks
- % lptr->num_blocks;
- lptr->num_recs_pb = p_lptr->num_blocks
- / lptr->num_blocks;
- lptr->num_recs_tot = p_lptr->num_blocks;
+ while (lptr->num_blocks > 1) {
+ p_lptr = lptr;
+ lptr = &btree_curs->level[level];
+
+ compute_level_geometry(mp, lptr,
+ p_lptr->num_blocks, 0, false);
#ifdef XR_BLD_FREE_TRACE
- fprintf(stderr, "%s %d %d %d %d %d\n", __func__,
- level,
- lptr->num_blocks,
- lptr->num_recs_pb,
- lptr->modulo,
- lptr->num_recs_tot);
+ fprintf(stderr, "%s %d %d %d %d %d\n", __func__,
+ level,
+ lptr->num_blocks,
+ lptr->num_recs_pb,
+ lptr->modulo,
+ lptr->num_recs_tot);
#endif
- }
+ level++;
}
-
+ ASSERT(level < XFS_BTREE_MAXLEVELS);
ASSERT(lptr->num_blocks == 1);
btree_curs->num_levels = level;
@@ -494,8 +506,11 @@ calculate_freespace_cursor(xfs_mount_t *
* see if the number of leaf blocks will change as a result
* of the number of extents changing
*/
- if (howmany(num_extents, XR_ALLOC_BLOCK_MAXRECS(mp, 0))
- != btree_curs->level[0].num_blocks) {
+ old_blocks = btree_curs->level[0].num_blocks;
+ compute_level_geometry(mp, &btree_curs->level[0], num_extents, 2, true);
+ extra_blocks = 0;
+
+ if (old_blocks != btree_curs->level[0].num_blocks) {
/*
* yes -- recalculate the cursor. If the number of
* excess (overallocated) blocks is < xfs_agfl_size/2, we're ok.
@@ -551,31 +566,19 @@ calculate_freespace_cursor(xfs_mount_t *
}
lptr = &btree_curs->level[0];
- lptr->num_blocks = howmany(num_extents,
- XR_ALLOC_BLOCK_MAXRECS(mp, 0));
- lptr->num_recs_pb = num_extents / lptr->num_blocks;
- lptr->modulo = num_extents % lptr->num_blocks;
- lptr->num_recs_tot = num_extents;
level = 1;
/*
* if we need more levels, set them up
*/
- if (lptr->num_blocks > 1) {
- for (level = 1; btree_curs->level[level-1].num_blocks
- > 1 && level < XFS_BTREE_MAXLEVELS;
- level++) {
- lptr = &btree_curs->level[level];
- p_lptr = &btree_curs->level[level-1];
- lptr->num_blocks = howmany(p_lptr->num_blocks,
- XR_ALLOC_BLOCK_MAXRECS(mp, level));
- lptr->modulo = p_lptr->num_blocks
- % lptr->num_blocks;
- lptr->num_recs_pb = p_lptr->num_blocks
- / lptr->num_blocks;
- lptr->num_recs_tot = p_lptr->num_blocks;
- }
+ while (lptr->num_blocks > 1) {
+ p_lptr = lptr;
+ lptr = &btree_curs->level[level++];
+
+ compute_level_geometry(mp, lptr,
+ p_lptr->num_blocks, 0, false);
}
+ ASSERT(level < XFS_BTREE_MAXLEVELS);
ASSERT(lptr->num_blocks == 1);
btree_curs->num_levels = level;
@@ -589,22 +592,6 @@ calculate_freespace_cursor(xfs_mount_t *
ASSERT(blocks_allocated_total >= blocks_needed);
extra_blocks = blocks_allocated_total - blocks_needed;
- } else {
- if (extents_used > 0) {
- /*
- * reset the leaf level geometry to account
- * for consumed extents. we can leave the
- * rest of the cursor alone since the number
- * of leaf blocks hasn't changed.
- */
- lptr = &btree_curs->level[0];
-
- lptr->num_recs_pb = num_extents / lptr->num_blocks;
- lptr->modulo = num_extents % lptr->num_blocks;
- lptr->num_recs_tot = num_extents;
- }
-
- extra_blocks = 0;
}
btree_curs->num_tot_blocks = blocks_allocated_pt;
@@ -1335,7 +1322,6 @@ init_rmapbt_cursor(
struct bt_stat_level *lptr;
struct bt_stat_level *p_lptr;
xfs_extlen_t blocks_allocated;
- int maxrecs;
if (!xfs_sb_version_hasrmapbt(&mp->m_sb)) {
memset(btree_curs, 0, sizeof(struct bt_status));
@@ -1371,32 +1357,20 @@ init_rmapbt_cursor(
* Leave enough slack in the rmapbt that we can insert the
* metadata AG entries without too many splits.
*/
- maxrecs = mp->m_rmap_mxr[0];
- if (num_recs > maxrecs)
- maxrecs -= 10;
- blocks_allocated = lptr->num_blocks = howmany(num_recs, maxrecs);
-
- lptr->modulo = num_recs % lptr->num_blocks;
- lptr->num_recs_pb = num_recs / lptr->num_blocks;
- lptr->num_recs_tot = num_recs;
+ compute_level_geometry(mp, lptr, num_recs,
+ num_recs > mp->m_rmap_mxr[0] ? 10 : 0, true);
+ blocks_allocated = lptr->num_blocks;
level = 1;
- if (lptr->num_blocks > 1) {
- for (; btree_curs->level[level-1].num_blocks > 1
- && level < XFS_BTREE_MAXLEVELS;
- level++) {
- lptr = &btree_curs->level[level];
- p_lptr = &btree_curs->level[level - 1];
- lptr->num_blocks = howmany(p_lptr->num_blocks,
- mp->m_rmap_mxr[1]);
- lptr->modulo = p_lptr->num_blocks % lptr->num_blocks;
- lptr->num_recs_pb = p_lptr->num_blocks
- / lptr->num_blocks;
- lptr->num_recs_tot = p_lptr->num_blocks;
-
- blocks_allocated += lptr->num_blocks;
- }
+ while (lptr->num_blocks > 1) {
+ p_lptr = lptr;
+ lptr = &btree_curs->level[level++];
+
+ compute_level_geometry(mp, lptr,
+ p_lptr->num_blocks, 0, false);
+ blocks_allocated += lptr->num_blocks;
}
+ ASSERT(level < XFS_BTREE_MAXLEVELS);
ASSERT(lptr->num_blocks == 1);
btree_curs->num_levels = level;
Reference in New Issue View Git Blame Copy Permalink