Evan Tschannen
Evan Tschannen
Currently, a lot of simple queries can only be implemented in very inefficient ways because there is no ability to filter or aggregate results on the server processes. For instance,...
Changing storage engines on a live clusters currently has a number of different problems. The way it is currently implemented, data distribution will mark all storage servers as unhealthy, and...
This feature will improve write bandwidth when initially loading data into a database. During the load, the range will not be readable. The design needs to consider how to get...
If a single process in a database is much slower than the other processes, the entire database will slow down. This means that failures which cause a process to slow...
If mutations and conflict ranges for a large transaction were divided across multiple proxies, we could reduce the latency of the commit. The mutations need to be committed in order,...
The buffered cursor is merging the mutations from a lot of different cursors. It currently is implemented by sorting results pulled from all of the cursors, but a priority_queue of...
After a remote region has failed and the comes back online, the remote storage servers will attempt to catch up as fast as possible. This causes Ratekeeper to limit traffic...