From: Darrick J. Wong <darrick.wong@xxxxxxxxxx> In commit 9851fd79bfb1, we added a slight amount of slack to the free space btrees being reconstructed so that the initial fix_freelist call (which is run against a totally empty AGFL) would never have to split either free space btree in order to populate the free list. The new btree bulk loading code in xfs_repair can re-create this situation because it can set the slack values to zero if the filesystem is very full. However, these days repair has the infrastructure needed to ensure that overestimations of the btree block counts end up on the AGFL or get freed back into the filesystem at the end of phase 5. Fix this problem by reserving extra blocks in the bnobt reservation, and checking that there are enough overages in the bnobt/cntbt fakeroots to populate the AGFL with the minimum number of blocks it needs to handle a split in the bno/cnt/rmap btrees. Note that we reserve blocks for the new bnobt/cntbt/AGFL at the very end of the reservation steps in phase 5, so the extra allocation should not cause repair to fail if it can't find blocks for btrees. Fixes: 9851fd79bfb1 ("repair: AGFL rebuild fails if btree split required") Signed-off-by: Darrick J. Wong <darrick.wong@xxxxxxxxxx> Reviewed-by: Brian Foster <bfoster@xxxxxxxxxx> --- v2: tweak the reserve_agblocks return logic a bit --- repair/agbtree.c | 52 ++++++++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 44 insertions(+), 8 deletions(-) diff --git a/repair/agbtree.c b/repair/agbtree.c index de8015ec..69821745 100644 --- a/repair/agbtree.c +++ b/repair/agbtree.c @@ -64,9 +64,12 @@ consume_freespace( } } -/* Reserve blocks for the new per-AG structures. */ -static void -reserve_btblocks( +/* + * Reserve blocks for the new per-AG structures. Returns true if all blocks + * were allocated, and false if we ran out of space. + */ +static bool +reserve_agblocks( struct xfs_mount *mp, xfs_agnumber_t agno, struct bt_rebuild *btr, @@ -86,8 +89,7 @@ reserve_btblocks( */ ext_ptr = findfirst_bcnt_extent(agno); if (!ext_ptr) - do_error( -_("error - not enough free space in filesystem\n")); + break; /* Use up the extent we've got. */ len = min(ext_ptr->ex_blockcount, nr_blocks - blocks_allocated); @@ -110,6 +112,20 @@ _("error - not enough free space in filesystem\n")); fprintf(stderr, "blocks_allocated = %d\n", blocks_allocated); #endif + return blocks_allocated == nr_blocks; +} + +static inline void +reserve_btblocks( + struct xfs_mount *mp, + xfs_agnumber_t agno, + struct bt_rebuild *btr, + uint32_t nr_blocks) +{ + if (!reserve_agblocks(mp, agno, btr, nr_blocks)) + do_error( + _("error - not enough free space in filesystem, AG %u\n"), + agno); } /* Feed one of the new btree blocks to the bulk loader. */ @@ -217,8 +233,11 @@ init_freespace_cursors( struct bt_rebuild *btr_bno, struct bt_rebuild *btr_cnt) { + unsigned int agfl_goal; int error; + agfl_goal = libxfs_alloc_min_freelist(sc->mp, NULL); + init_rebuild(sc, &XFS_RMAP_OINFO_AG, free_space, btr_bno); init_rebuild(sc, &XFS_RMAP_OINFO_AG, free_space, btr_cnt); @@ -243,6 +262,7 @@ init_freespace_cursors( do { unsigned int num_freeblocks; int delta_bno, delta_cnt; + int agfl_wanted; /* Compute how many bnobt blocks we'll need. */ error = -libxfs_btree_bload_compute_geometry(btr_bno->cur, @@ -268,16 +288,32 @@ _("Unable to compute free space by length btree geometry, error %d.\n"), -error) btr_cnt->bload.nr_blocks; /* We don't need any more blocks, so we're done. */ - if (delta_bno >= 0 && delta_cnt >= 0) { + if (delta_bno >= 0 && delta_cnt >= 0 && + delta_bno + delta_cnt >= agfl_goal) { *extra_blocks = delta_bno + delta_cnt; break; } /* Allocate however many more blocks we need this time. */ - if (delta_bno < 0) + if (delta_bno < 0) { reserve_btblocks(sc->mp, agno, btr_bno, -delta_bno); - if (delta_cnt < 0) + delta_bno = 0; + } + if (delta_cnt < 0) { reserve_btblocks(sc->mp, agno, btr_cnt, -delta_cnt); + delta_cnt = 0; + } + + /* + * Try to fill the bnobt cursor with extra blocks to populate + * the AGFL. If we don't get all the blocks we want, stop + * trying to fill the AGFL because the AG is totally out of + * space. + */ + agfl_wanted = agfl_goal - (delta_bno + delta_cnt); + if (agfl_wanted > 0 && + !reserve_agblocks(sc->mp, agno, btr_bno, agfl_wanted)) + agfl_goal = 0; /* Ok, now how many free space records do we have? */ *nr_extents = count_bno_extents_blocks(agno, &num_freeblocks);