You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Current Pegasus load balance strategy will only consider table level balance, if all tables are balanced, Pegasus consider it as balanced. However, all tables balanced is not equal to cluster balanced, especially for a large cluster who has lots of small partition tables. When cluster node count is bigger than the table total partition count, this table's partition won't be moved in current load balance strategy.
Reference for kudu's rebalance strategy rebalance_algo.cc, Pegasus also should provide a cluster load balance strategy.
The text was updated successfully, but these errors were encountered:
Feature Request
Current Pegasus load balance strategy will only consider table level balance, if all tables are balanced, Pegasus consider it as balanced. However, all tables balanced is not equal to cluster balanced, especially for a large cluster who has lots of small partition tables. When cluster node count is bigger than the table total partition count, this table's partition won't be moved in current load balance strategy.
Reference for kudu's rebalance strategy rebalance_algo.cc, Pegasus also should provide a cluster load balance strategy.
The text was updated successfully, but these errors were encountered: