Andrew Wong has uploaded a new change for review. http://gerrit.cloudera.org:8080/7784
Change subject: open FS layout in presence of disk failure ...................................................................... open FS layout in presence of disk failure Currently, if a Kudu server starts up with a failed disk, the server will crash. There are a number of reasons for this, but the pressing ones are that the path instance files may not be readable, meaning the directories' UUIDs may not be available. This patch changes this by introducing an "unhealthy" instance in-memory for all each instance that failsto load, lock, canonicalize, etc. Such instances are ignored when it comes to checking the integrity of the FS layout, and are simply marked failed by the directory manager. Testing is done in data_dirs-test, log_block_manager-test, and fs_manager-test to ensure failed directories do not impede the mangers' startups. Change-Id: Ib2a1c824526ed52a6b90ddfbc735cecc4c491118 --- M src/kudu/fs/block_manager-stress-test.cc M src/kudu/fs/block_manager-test.cc M src/kudu/fs/block_manager_util-test.cc M src/kudu/fs/block_manager_util.cc M src/kudu/fs/block_manager_util.h M src/kudu/fs/data_dirs-test.cc M src/kudu/fs/data_dirs.cc M src/kudu/fs/data_dirs.h M src/kudu/fs/fs_manager-test.cc M src/kudu/fs/fs_manager.cc M src/kudu/fs/fs_manager.h M src/kudu/fs/log_block_manager-test.cc M src/kudu/fs/log_block_manager.cc 13 files changed, 607 insertions(+), 162 deletions(-) git pull ssh://gerrit.cloudera.org:29418/kudu refs/changes/84/7784/1 -- To view, visit http://gerrit.cloudera.org:8080/7784 To unsubscribe, visit http://gerrit.cloudera.org:8080/settings Gerrit-MessageType: newchange Gerrit-Change-Id: Ib2a1c824526ed52a6b90ddfbc735cecc4c491118 Gerrit-PatchSet: 1 Gerrit-Project: kudu Gerrit-Branch: master Gerrit-Owner: Andrew Wong <aw...@cloudera.com>
