pkuwm commented on a change in pull request #362: The WAGED rebalancer cluster
model implementation
URL: https://github.com/apache/helix/pull/362#discussion_r307940906
##########
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());
+
+ // 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;
+
+ // 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;
+
+ 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,
+ Collection<AssignableReplica> existingAssignment) {
+ reset();
+
+ InstanceConfig instanceConfig =
clusterCache.getInstanceConfigMap().get(_instanceName);
+ ClusterConfig clusterConfig = clusterCache.getClusterConfig();
+
+ _currentCapacity.putAll(instanceConfig.getInstanceCapacityMap());
+ _faultZone = computeFaultZone(clusterConfig, instanceConfig);
+ _instanceTags = new HashSet<>(instanceConfig.getTags());
+ _disabledPartitionsMap = instanceConfig.getDisabledPartitionsMap();
+ _maxCapacity = instanceConfig.getInstanceCapacityMap();
+ _maxPartition = clusterConfig.getMaxPartitionsPerInstance();
+
+ assignNewBatch(existingAssignment);
+ }
+
+ /**
+ * Assign a replica to the node.
+ *
+ * @param assignableReplica - the replica to be assigned
+ */
+ void assign(AssignableReplica assignableReplica) {
+ if (!addToAssignmentRecord(assignableReplica, _currentAssignments)) {
+ throw new HelixException(String
+ .format("Resource {} already has a replica from partition {} on this
node",
+ assignableReplica.getResourceName(),
assignableReplica.getPartitionName()));
+ } else {
+ if (assignableReplica.isReplicaTopState()) {
+ addToAssignmentRecord(assignableReplica, _currentTopStateAssignments);
+ }
+ _totalReplicaAssignmentCount += 1;
+ assignableReplica.getCapacity().entrySet().stream()
+ .forEach(entry -> updateCapacityAndUtilization(entry.getKey(),
entry.getValue()));
+ }
+ }
+
+ /**
+ * Release a replica from the node.
+ * If the replication is not on this node, the assignable node is not
updated.
+ *
+ * @param assignableReplica - the replica to be released
+ */
+ void release(AssignableReplica assignableReplica) throws
IllegalArgumentException {
+ String resourceName = assignableReplica.getResourceName();
+ String partitionName = assignableReplica.getPartitionName();
+ if (!_currentAssignments.containsKey(resourceName)) {
+ _logger.warn("Resource " + resourceName + " is not on this node. Ignore
the release call.");
+ return;
+ }
+
+ Set<String> partitions = _currentAssignments.get(resourceName);
+ if (!partitions.contains(partitionName)) {
+ _logger.warn(String
+ .format("Resource {} does not have a replica from partition {} on
this node",
+ resourceName, partitionName));
+ return;
+ }
+
+ partitions.remove(assignableReplica.getPartitionName());
+ if (assignableReplica.isReplicaTopState()) {
+ _currentTopStateAssignments.get(resourceName).remove(partitionName);
+ }
+ _totalReplicaAssignmentCount -= 1;
+ // Recalculate utilization because of release
+ _highestCapacityUtilization = 0;
+ assignableReplica.getCapacity().entrySet().stream()
+ .forEach(entry -> updateCapacityAndUtilization(entry.getKey(), -1 *
entry.getValue()));
+ }
+
+ public Map<String, Set<String>> getCurrentAssignmentsMap() {
+ return _currentAssignments;
+ }
+
+ public Set<String> getCurrentAssignmentsByResource(String resource) {
+ if (!_currentAssignments.containsKey(resource)) {
+ return Collections.emptySet();
+ }
+ return _currentAssignments.get(resource);
Review comment:
Just personal preference, for this, I would use java 8 style `getOrDefault`
to make it a bit cleaner :)
```java
_currentAssignments.getOrDefault(resource, Collections.emptySet());
```
----------------------------------------------------------------
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
