I don't want to comment on the 10540 ticket since it seems very well
focused on vnode-aligned sstable partitioning and compaction. I'm pretty
excited about that ticket. RACS should enable:
- smaller scale LCS, more constrained I/O consumption
- less sstables to hit in read path
- multithreaded/mul
Cheers Dinesh, not too worried about that one in 4.0's case though as it's
a bug but it will need a committer.
As for improvements for 4.0:
https://issues.apache.org/jira/browse/CASSANDRA-13010 - More verbose
nodetool compactionstats. Speaks for itself.
https://issues.apache.org/jira/browse/CASSAN
I've had similar thoughts in the past about RACS and manual tokens. I think
it would be a good idea to be able to split it based on some configurable
factor other than vnodes. I think Marcus may have already addressed this to
some extent as well but if not it's theoretically possible.
On 20 July
