From 23227313a2016449176cbfcbae2d4fc463a2bc09 Mon Sep 17 00:00:00 2001 From: Chunwei Chen Date: Tue, 30 Jan 2018 13:39:11 -0800 Subject: [PATCH] Fix zdb -c traverse stop on damaged objset root If a corruption happens to be on a root block of an objset, zdb -c will not correctly report the error, and it will not traverse the datasets that come after. This is because traverse_visitbp, which does the callback and reset error for TRAVERSE_HARD, is skipped when traversing zil is failed in traverse_impl. Here's example of what 'zdb -eLcc' command looks like on a pool with damaged objset root: == before patch: Traversing all blocks to verify checksums ... Error counts: errno count block traversal size 379392 != alloc 33987072 (unreachable 33607680) bp count: 172 ganged count: 0 bp logical: 1678336 avg: 9757 bp physical: 130560 avg: 759 compression: 12.85 bp allocated: 379392 avg: 2205 compression: 4.42 bp deduped: 0 ref>1: 0 deduplication: 1.00 SPA allocated: 33987072 used: 0.80% additional, non-pointer bps of type 0: 71 Dittoed blocks on same vdev: 101 == after patch: Traversing all blocks to verify checksums ... zdb_blkptr_cb: Got error 52 reading <54, 0, -1, 0> -- skipping Error counts: errno count 52 1 block traversal size 33963520 != alloc 33987072 (unreachable 23552) bp count: 447 ganged count: 0 bp logical: 36093440 avg: 80745 bp physical: 33699840 avg: 75391 compression: 1.07 bp allocated: 33963520 avg: 75981 compression: 1.06 bp deduped: 0 ref>1: 0 deduplication: 1.00 SPA allocated: 33987072 used: 0.80% additional, non-pointer bps of type 0: 76 Dittoed blocks on same vdev: 115 == Reviewed-by: Brian Behlendorf Reviewed-by: loli10K Signed-off-by: Chunwei Chen Closes #7099 --- module/zfs/dmu_traverse.c | 26 +++++++++++++++++--------- 1 file changed, 17 insertions(+), 9 deletions(-) diff --git a/module/zfs/dmu_traverse.c b/module/zfs/dmu_traverse.c index c78228d745..b494bef358 100644 --- a/module/zfs/dmu_traverse.c +++ b/module/zfs/dmu_traverse.c @@ -599,19 +599,27 @@ traverse_impl(spa_t *spa, dsl_dataset_t *ds, uint64_t objset, blkptr_t *rootbp, /* See comment on ZIL traversal in dsl_scan_visitds. */ if (ds != NULL && !ds->ds_is_snapshot && !BP_IS_HOLE(rootbp)) { + enum zio_flag zio_flags = ZIO_FLAG_CANFAIL; uint32_t flags = ARC_FLAG_WAIT; objset_phys_t *osp; arc_buf_t *buf; - err = arc_read(NULL, td->td_spa, rootbp, - arc_getbuf_func, &buf, - ZIO_PRIORITY_ASYNC_READ, ZIO_FLAG_CANFAIL, &flags, czb); - if (err != 0) - return (err); - - osp = buf->b_data; - traverse_zil(td, &osp->os_zil_header); - arc_buf_destroy(buf, &buf); + err = arc_read(NULL, td->td_spa, rootbp, arc_getbuf_func, + &buf, ZIO_PRIORITY_ASYNC_READ, zio_flags, &flags, czb); + if (err != 0) { + /* + * If both TRAVERSE_HARD and TRAVERSE_PRE are set, + * continue to visitbp so that td_func can be called + * in pre stage, and err will reset to zero. + */ + if (!(td->td_flags & TRAVERSE_HARD) || + !(td->td_flags & TRAVERSE_PRE)) + return (err); + } else { + osp = buf->b_data; + traverse_zil(td, &osp->os_zil_header); + arc_buf_destroy(buf, &buf); + } } if (!(flags & TRAVERSE_PREFETCH_DATA) ||