apurtell commented on issue #1407: HBASE-24099 Use a fair ReentrantReadWriteLock for the locks used to guard region closing and updates URL: https://github.com/apache/hbase/pull/1407#issuecomment-608059787 Currently, testing with LoadTestTool with 10, 50, and 100 client threads, with 10/90, 50/50, and 90/10 read vs write load distribution. Testing with YCSB next. PE isn't a good tool for getting latency measures but might be ok for throughput (total wall clock time) Other suggestions? Also, I know I said the updates lock was also implicated on the close path but there is no evidence we are starving this lock, so I have been testing a change that only touches the close lock. Let me push an update here.
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
