Apache9 commented on pull request #2328: URL: https://github.com/apache/hbase/pull/2328#issuecomment-686884566
> > So you mean we should all the table states in memory? For now it is cached on demand. > > yeah, but on-demand generates a large number of rpc requests. normally, all tables end up being loaded into memory, so i think we can load all tables at startup through multiple threads， which can improve mttr. But it will slow down the restart of HMaster? We can restart HMaster at any time, not only when a full cluster restart? ---------------------------------------------------------------- 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]
