Locality Aware Dynamic Load Management for Massively Multiplayer Games

1
Locality Aware Dynamic Load Management for
Massively Multiplayer Games

• Jin Chen, Baohua Wu, Margaret Delap,
• Bjorn Knutson, Honghui Lu and Cristina Amza

presented by Sagnik Nandy
2
Basic Idea

• How to schedule game regions across multiple
  servers in a massively parallel multiplayer game
  environment?

3
Overview

• Problem Description
• Existing Techniques
• Suggested Solution
• Experimental Results
• Conclusion

4
Overview

• Problem Description
• Existing Techniques
• Suggested Solution
• Experimental Results
• Conclusion

5
Problem Description

• How do you map various regions of a multiplayer
  game across different servers?

6
Issue 1 - Locality
1
1
7
Issue 1 - Locality
1
1
8
Issue 2 Load balancing
2
1
3
4
1
2
4
3
9
Problem Statement

• Balance server load by replicating existing game
  world partitions across several servers
• Decrease inter-server communication by
  maintaining locality of adjacent regions

10
Overview

• Problem Description
• Existing Techniques
• Suggested Solution
• Experimental Results
• Conclusion

11
Existing Solutions

• Built-in load balancing in the game concept (e.g.
  countries, airports etc.)
• Static Partitioning row based, column based,
  cyclic, etc.
• Dynamic Uniform Load Spread (Spread)
• Tries to minimize the difference between most and
  least loaded nodes
• Doesnt consider locality

12
Existing Solutions (contd.)

• Dynamic Load Shedding to Lightest Loaded Node
  (Lightest)
• Choose loaded server and shed load to system-wide
  lightest loaded node
• Locality is not an objective (but can get
  maintained)

13
Suggested Solution (Locality Aware Dynamic Load
Management)

• SLA violation
• 90 users exceed update interval
• Overload threshold
• load ( users) for which violation happens
• Safe load threshold
• max load for which all users meet SLA
• Light load
• 2safe_load over_load

14
Objectives

• Meet SLA ( load balancing)
• Happy users
• Maintain locality of game regions
• Reduce transition time
• Minimize of region migrations
• Reduce inter-server communication

15
Overview

• Problem Description
• Existing Techniques
• Suggested Solution
• Experimental Results
• Conclusion

16
Suggested Approach

• Load shedding algorithm
• How to distributed load and meet SLA requirements
• Load aggregation algorithm
• Help restore locality
• Help in future load shedding

17
Load Shedding Algorithm

• If load gt over_load
• While load gt over_load
• Find lightest (neighbor lt safety_load) and shed
  load
• If no neighbor exists then do this globally
  across system

18
Shed Load

• How to choose a component to shed?
• Given a neighbor Sj
• Choose a boundary node for Sj
• With node as root
• Find strongly connected cluster using BFS as long
  cluster weight within bounds

19
Load Aggregation

• Reasons
• Load can be shed to remote server
• Load can be shed across multiple neighbors
• Tries to reduce number of boundaries
• For each neighbor of Si
• Find partition such that new_load lt safe_load
• Transfer cluster if boundaries reduce

20
Overview

• Problem Description
• Existing Techniques
• Suggested Solution
• Experimental Results
• Conclusion

21
Experiments

• First did single server and a smaller cluster
  based experiment
• Used results to simulate more comprehensive
  system
• Simulated for CPU and network usage
• Simulated for a LAN and WAN setting

22
Real Experiments (single server)
23
Real Experiments (multiple server)
24
Simulation results (LAN)
25
Simulation results (WAN)
26
Conclusions

• The paper introduces the issue of locality into
  scheduling
• Dynamic scheduling is better than static
  scheduling
• Locality is more important as the network spreads
  out (curious to know effect on Internet scale
  games)
• Aggregation didnt help much