This series depends on http://lists.wpkg.org/pipermail/sheepdog/2012-August/006322.html
We shouldn't remove objects until object recovery completely finishes. With this patch, even if we wrongly stop more sheeps than the redundancy level at the same time, sheepdog can recover objects automatically after they start up. Even if sheepdog crashes unexpectedly, we can recover objects from the stale directory manually at worst. I'll create a patch to clean up stale objects after recovery finished tomorrow or later. MORITA Kazutaka (2): tests: add test to check recovery after many nodes failed store: make objects stale when starting sheep sheep/group.c | 6 ++-- sheep/plain_store.c | 2 +- tests/033 | 59 ++++++++++++++++++++++++++++++++++++ tests/033.out | 82 +++++++++++++++++++++++++++++++++++++++++++++++++++ tests/group | 1 + 5 files changed, 146 insertions(+), 4 deletions(-) create mode 100755 tests/033 create mode 100644 tests/033.out -- 1.7.2.5 -- sheepdog mailing list [email protected] http://lists.wpkg.org/mailman/listinfo/sheepdog
