io.druid.server.coordinator

Class CostBalancerStrategy

java.lang.Object

io.druid.server.coordinator.CostBalancerStrategy

All Implemented Interfaces:

BalancerStrategy

public class CostBalancerStrategy
extends Object
implements BalancerStrategy

Constructor Summary

Constructors

Constructor and Description
CostBalancerStrategy(org.joda.time.DateTime referenceTimestamp, int threadCount)

Method Summary

Methods

Modifier and Type	Method and Description
double	calculateInitialTotalCost(List<ServerHolder> serverHolders) Calculates the initial cost of the Druid segment configuration.
double	calculateNormalization(List<ServerHolder> serverHolders) Calculates the cost normalization.
protected com.metamx.common.Pair<Double,ServerHolder>	chooseBestServer(io.druid.timeline.DataSegment proposalSegment, Iterable<ServerHolder> serverHolders, boolean includeCurrentServer) For assignment, we want to move to the lowest cost server that isn't already serving the segment.
protected double	computeCost(io.druid.timeline.DataSegment proposalSegment, ServerHolder server, boolean includeCurrentServer)
double	computeJointSegmentCosts(io.druid.timeline.DataSegment segment1, io.druid.timeline.DataSegment segment2) This defines the unnormalized cost function between two segments.
void	emitStats(String tier, CoordinatorStats stats, List<ServerHolder> serverHolderList)
ServerHolder	findNewSegmentHomeBalancer(io.druid.timeline.DataSegment proposalSegment, List<ServerHolder> serverHolders)
ServerHolder	findNewSegmentHomeReplicator(io.druid.timeline.DataSegment proposalSegment, List<ServerHolder> serverHolders)
BalancerSegmentHolder	pickSegmentToMove(List<ServerHolder> serverHolders)

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

CostBalancerStrategy

public CostBalancerStrategy(org.joda.time.DateTime referenceTimestamp,
                    int threadCount)

Method Detail

findNewSegmentHomeReplicator

public ServerHolder findNewSegmentHomeReplicator(io.druid.timeline.DataSegment proposalSegment,
                                        List<ServerHolder> serverHolders)

Specified by:

findNewSegmentHomeReplicator in interface BalancerStrategy

findNewSegmentHomeBalancer

public ServerHolder findNewSegmentHomeBalancer(io.druid.timeline.DataSegment proposalSegment,
                                      List<ServerHolder> serverHolders)

Specified by:

findNewSegmentHomeBalancer in interface BalancerStrategy

computeJointSegmentCosts

public double computeJointSegmentCosts(io.druid.timeline.DataSegment segment1,
                              io.druid.timeline.DataSegment segment2)

This defines the unnormalized cost function between two segments. There is a base cost given by the minimum size of the two segments and additional penalties. recencyPenalty: it is more likely that recent segments will be queried together dataSourcePenalty: if two segments belong to the same data source, they are more likely to be involved in the same queries gapPenalty: it is more likely that segments close together in time will be queried together

Parameters:

segment1 - The first DataSegment.

segment2 - The second DataSegment.

Returns:

The joint cost of placing the two DataSegments together on one node.

pickSegmentToMove

public BalancerSegmentHolder pickSegmentToMove(List<ServerHolder> serverHolders)

Specified by:

pickSegmentToMove in interface BalancerStrategy

calculateInitialTotalCost

public double calculateInitialTotalCost(List<ServerHolder> serverHolders)

Calculates the initial cost of the Druid segment configuration.

Parameters:

serverHolders - A list of ServerHolders for a particular tier.

Returns:

The initial cost of the Druid tier.

calculateNormalization

public double calculateNormalization(List<ServerHolder> serverHolders)

Calculates the cost normalization. This is such that the normalized cost is lower bounded by 1 (e.g. when each segment gets its own historical node).

Parameters:

serverHolders - A list of ServerHolders for a particular tier.

Returns:

The normalization value (the sum of the diagonal entries in the pairwise cost matrix). This is the cost of a cluster if each segment were to get its own historical node.

emitStats

public void emitStats(String tier,
             CoordinatorStats stats,
             List<ServerHolder> serverHolderList)

Specified by:

emitStats in interface BalancerStrategy

computeCost

protected double computeCost(io.druid.timeline.DataSegment proposalSegment,
                 ServerHolder server,
                 boolean includeCurrentServer)

chooseBestServer

protected com.metamx.common.Pair<Double,ServerHolder> chooseBestServer(io.druid.timeline.DataSegment proposalSegment,
                                                           Iterable<ServerHolder> serverHolders,
                                                           boolean includeCurrentServer)

For assignment, we want to move to the lowest cost server that isn't already serving the segment.

Parameters:

proposalSegment - A DataSegment that we are proposing to move.

serverHolders - An iterable of ServerHolders for a particular tier.

Returns:

A ServerHolder with the new home for a segment.