i3wangyi commented on a change in pull request #362: The WAGED rebalancer cluster model implementation URL: https://github.com/apache/helix/pull/362#discussion_r309977591
########## File path: helix-core/src/main/java/org/apache/helix/controller/rebalancer/waged/model/AssignableNode.java ########## @@ -19,10 +19,290 @@ * under the License. */ +import org.apache.helix.HelixException; +import org.apache.helix.controller.dataproviders.ResourceControllerDataProvider; +import org.apache.helix.model.ClusterConfig; +import org.apache.helix.model.InstanceConfig; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import java.util.Collection; +import java.util.Collections; +import java.util.HashMap; +import java.util.HashSet; +import java.util.List; +import java.util.Map; +import java.util.Set; + +import static java.lang.Math.max; + /** - * A placeholder before we have the implementation. - * - * This class represents a potential allocation of the replication. - * Note that AssignableNode is not thread safe. + * This class represents a possible allocation of the replication. + * Note that any usage updates to the AssignableNode are not thread safe. */ -public class AssignableNode { } +public class AssignableNode { + private static final Logger _logger = LoggerFactory.getLogger(AssignableNode.class.getName()); + + // proposed assignment tracking + // <resource name, partition name> + private Map<String, Set<String>> _currentAssignments; + // <resource name, top state partition name> + private Map<String, Set<String>> _currentTopStateAssignments; + // <capacity key, capacity value> + private Map<String, Integer> _currentCapacity; + // runtime usage tracking + private int _totalReplicaAssignmentCount; + private float _highestCapacityUtilization; + + // basic node information + private final String _instanceName; + private Set<String> _instanceTags; + private String _faultZone; + private Map<String, List<String>> _disabledPartitionsMap; + private Map<String, Integer> _maxCapacity; + private int _maxPartition; + + AssignableNode(ResourceControllerDataProvider clusterCache, String instanceName, + Collection<AssignableReplica> existingAssignment) { + _instanceName = instanceName; + refresh(clusterCache, existingAssignment); + } + + private void reset() { + _currentAssignments = new HashMap<>(); + _currentTopStateAssignments = new HashMap<>(); + _currentCapacity = new HashMap<>(); + _totalReplicaAssignmentCount = 0; + _highestCapacityUtilization = 0; + } + + /** + * Update the node with a ClusterDataCache. This resets the current assignment and recalculate currentCapacity. + * NOTE: While this is required to be used in the constructor, this can also be used when the clusterCache needs to be + * refreshed. This is under the assumption that the capacity mappings of InstanceConfig and ResourceConfig could + * subject to changes. If the assumption is no longer true, this function should become private. + * + * @param clusterCache - the current cluster cache to initial the AssignableNode. + */ + private void refresh(ResourceControllerDataProvider clusterCache, Review comment: Yes. By OO design, the data model constructor shouldn't have the parameter `DataProvider`. First, the object of `DataProvider` is mutable, which breaks the rule of **programming defensively**. You need to assume the client will destroy the object. In this case, the caller of the constructor has no control of the constructor behavior. Second, `DataProvider` logically doesn't belong to any data model and it shouldn't know the existence of data model. Builder pattern will allow you to fit the necessary field (data) coming from `DataProvider`. I know such constructors exist in the core package a lot, but it doesn't mean it's right. Mostly, it is just easy and you get used to it ---------------------------------------------------------------- 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: us...@infra.apache.org With regards, Apache Git Services