diff options
author | NeilBrown <neilb@suse.de> | 2012-04-01 13:48:38 (GMT) |
---|---|---|
committer | NeilBrown <neilb@suse.de> | 2012-04-03 05:36:17 (GMT) |
commit | 18b9837ea0dc3cf844c6c4196871ce91d047bddb (patch) | |
tree | de8be80b767d144405aeeaf7238c723f575b4b40 /fs/nfs | |
parent | 5220ea1e640869e70f894837678315c878c651fd (diff) | |
download | linux-18b9837ea0dc3cf844c6c4196871ce91d047bddb.tar.xz |
md/raid5: fix handling of bad blocks during recovery.
1/ We can only treat a known-bad-block like a read-error if we
have the data that belongs in that block. So fix that test.
2/ If we cannot recovery a stripe due to insufficient data,
don't tell "md_done_sync" that the sync failed unless we really
did fail something. If we successfully record bad blocks,
that is success.
Reported-by: "majianpeng" <majianpeng@gmail.com>
Signed-off-by: NeilBrown <neilb@suse.de>
Diffstat (limited to 'fs/nfs')
0 files changed, 0 insertions, 0 deletions