Hello Kudu Jenkins,
I'd like you to reexamine a change. Please visit
http://gerrit.cloudera.org:8080/7028
to look at the new patch set (#2).
Change subject: disk failure: make DataDirManager failure-aware
......................................................................
disk failure: make DataDirManager failure-aware
The DataDirManager must record what directories are unhealthy in order
to avoid placing new data on failed disks. This patch achieves this by
maintaining a set of UUID indices in the DataDirManager that correspond
to failed directories. Additionally, a count of the number of known
failed directories is maintained as a metric.
Tests are added to data_dirs-test to ensure that failed directories are
not used and are not returned as part of newly created DataDirGroups. If
no healthy directories exist, callers will return an IOError with posix
code ENODEV.
Change-Id: Iee212793152de5de5198751d649ab34fb97f6aa2
---
M src/kudu/fs/data_dirs-test.cc
M src/kudu/fs/data_dirs.cc
M src/kudu/fs/data_dirs.h
3 files changed, 160 insertions(+), 13 deletions(-)
git pull ssh://gerrit.cloudera.org:29418/kudu refs/changes/28/7028/2
--
To view, visit http://gerrit.cloudera.org:8080/7028
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-MessageType: newpatchset
Gerrit-Change-Id: Iee212793152de5de5198751d649ab34fb97f6aa2
Gerrit-PatchSet: 2
Gerrit-Project: kudu
Gerrit-Branch: master
Gerrit-Owner: Andrew Wong <[email protected]>
Gerrit-Reviewer: Adar Dembo <[email protected]>
Gerrit-Reviewer: David Ribeiro Alves <[email protected]>
Gerrit-Reviewer: Kudu Jenkins
Gerrit-Reviewer: Todd Lipcon <[email protected]>
