From 1e5f75ecbe745640c4a4ba85dfe4f36364fa706f Mon Sep 17 00:00:00 2001 From: Matthew Ahrens Date: Wed, 10 May 2017 10:32:40 -0700 Subject: [PATCH] OpenZFS 8166 - zpool scrub thinks it repaired offline device Authored by: Matthew Ahrens Reviewed by: George Wilson Reviewed-by: loli10K Reviewed-by: Brian Behlendorf Ported-by: Matthew Ahrens If we do a scrub while a leaf device is offline (via "zpool offline"), we will inadvertently clear the DTL (dirty time log) of the offline device, even though it is still damaged. When the device comes back online, we will incompletely resilver it, thinking that the scrub repaired blocks written before the scrub was started. The incomplete resilver can lead to data loss if there is a subsequent failure of a different leaf device. The fix is to never clear the DTL of offline devices. Note that if a device is onlined while a scrub is in progress, the scrub will be restarted. The problem can be worked around by running "zpool scrub" after "zpool online". OpenZFS-issue: https://www.illumos.org/issues/8166 OpenZFS-commit: https://github.com/openzfs/openzfs/pull/372 Closes #5806 Closes #6103 --- module/zfs/vdev.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/module/zfs/vdev.c b/module/zfs/vdev.c index 7d814a63b4..8095b6177b 100644 --- a/module/zfs/vdev.c +++ b/module/zfs/vdev.c @@ -1799,6 +1799,9 @@ vdev_dtl_should_excise(vdev_t *vd) ASSERT0(scn->scn_phys.scn_errors); ASSERT0(vd->vdev_children); + if (vd->vdev_state < VDEV_STATE_DEGRADED) + return (B_FALSE); + if (vd->vdev_resilver_txg == 0 || range_tree_space(vd->vdev_dtl[DTL_MISSING]) == 0) return (B_TRUE);