Make the db_stress reopen loop in OperateDb() more robust (#5893)
Summary: The loop in OperateDb() is getting quite complicated with the introduction of multiple key operations such as MultiGet and Reseeks. This is resulting in a number of corner cases that hangs db_stress due to synchronization problems during reopen (i.e when -reopen=<> option is specified). This PR makes it more robust by ensuring all db_stress threads vote to reopen the DB the exact same number of times. Most of the changes in this diff are due to indentation. Pull Request resolved: https://github.com/facebook/rocksdb/pull/5893 Test Plan: Run crash test Differential Revision: D17823827 Pulled By: anand1976 fbshipit-source-id: ec893829f611ac7cac4057c0d3d99f9ffb6a6dd9main
parent
5b123813f8
commit
80ad996b35
Loading…
Reference in new issue