Optimal Virtual Machine Placement Across Multiple Cloud Providers

Optimal Virtual Machine Placement across Multiple Cloud Providers

Sivadon Chaisiri , Bu-Sung Lee, and Dusit NiyatoSchool of Computer EngineeringNanyang Technological University, Singapore

Tuesday, December 8, 2009

Presented in IEEE Asia-Pacific Services Computing Conference (APSCC), Singapore

Outline

• Introduction• Optimal Virtual Machine Placement• System Model• Problem Formulation• Performance Evaluation• Conclusion

Introduction: This Paper

3

• Virtual machine placement • Allocate a virtual machine (VM) to a physical machine

• Cloud computing – (public) utility service• Cloud providers e.g., Amazon, Google, Microsoft, Salesforce etc.• Leveraging virtualization e.g., Infrastructure-as-a-Service (IaaS)• IaaS Providers e.g., Amazon, GoGrid, FlexiScale, Redplaid, …

• Our Work – Optimal Virtual Machine Placement (OVMP)• Optimally allocate VMs to cloud providers• Optimally advance reserve resources• Also consider uncertainty of demands and prices

Introduction: Cloud Computing

4

Cloud Computing

Cloudprovider

Cloudprovider

Cloudprovider

Cloudprovider

Cloudprovider

Physical compute resources

Pool of resources

Cloudconsumer

Cloudconsumer

Cloudconsumer

Cloudconsumer

Cloudconsumer

Software

Storage

Hardware infrastructure

Network

Cloud Computing• Large distributed system

• Large pool of resources

• Multiple providers

• Virtualization

• Internet access

• Pay-per-use basis

• On-demand provisioning

Optimal Virtual Machine Placement (OVMP)

5

• Based on Infrastructure-as-a-Service (IaaS)• Two payment plans to provision resources

• Reservation plan: cheaper but may not meet actual demand

• On-demand plan: dynamically provisioning resources• e.g., Amazon EC2 and GoGrid

• Under price and demand uncertainty, OVMP algorithm can minimize the cost spending in each plan• Optimally reserve resources• Optimally allocate VMs to cloud providers

• OVMP is achieved by stochastic integer programming with two stage recourse

OVMP: System Model Diagram

6

OVMP: Assumption

7

• Provided resources: computing power, storage, network bandwidth, and electric power

• Price in the reservation plan is cheaper than that in the on-demand plan

• VM class represents a distinct type of applications• Each VM class has different resource requirement• The number of VMs in each VM class depends on the

demand from the user• Reserved VMs = reserved resources to execute a

certain number of VMs

OVMP: Three Provisioning Phases

8

• First stage• Reservation phase = reserve cheaper resources in advance

• Second stage• Utilization phase = utilize the reserved resources • On-demand phase = pay for additional resources

[optimal reservation] [optimal allocation]First stage Second stage

Reservation phase Utilization phase

On-demandphase

OVMP: 3 Possible Cases

9

On-demand cost > 0 Oversubscribed cost > 0

Formulation: Stochastic Integer Programming

10

Objective Function

Cost in first stageCost in second stage

Constraints

Number of VMs of class allocatedto provider under realizationin utilization phase

Number of VMs of class allocatedto provider under realizationin on-demand phase

Number of VMs of class, reserved from provider

Cost for reserving VMs of class from provider

Utilization constraint

Demand constraint

Capacity constraint

Boundary constraint

Formulation: Deterministic Equivalence

11

cost in the first stagecost in the second stage

objective function

constraints

12

• Evaluations• Numerical studies – solving in NEOS server• Simulation – simulating by MATLAB

• Assumption• 4 cloud providers and 3 VM classes

• Required number of VMs is the same for all VM classes

• Required number of VMs = {1,2, …, 50}

• Probability distributions = normal dist., uniform dist., and dist. from test data*

Performance Evaluation

* Test data was obtained from Institute of High Performance Computing (IHPC)

Parameter Setting• Resources required by 3 VM classes (VM1, VM2, VM3)

13

VM1 VM2 VM3

CPU-hours 12 18 24

Storage (GBs/day)

20 5 10

Network bandwidth (GBs/day)

33.33

66.67

266.67• Resources offered by 4 cloud providers (P1, P2, P3, P4)

P1 P2 P3 P4

CPU-hours 480 480 1,200

1,200

Storage (GBs/day) 1,000

1,000

1,000

1,000

Network bandwidth (GBs/day)

6.67 6.67 6.67 6.67• Prices defined by each provider (not shown here)

Evaluation: Numerical Studies

• Optimal solution in a simple environment

14

Optimal number of reserved VMs = 31

Evaluation: Numerical Studies

• Virtual machine placement in different phases

15

Optimal number of reserved VMs = 29

* Total cost = Reservation cost + Utilization cost + On-demand cost

Evaluation: Numerical Studies

• Total cost under different variances and prices

16

Evaluation: Numerical Studies• Comparison between OVMP (based on SIP) and EVF

17

SIP = Our stochastic integer programming formulationEVF = Expected-value formulation

Conclusion

18

• We propose OVMP to tackle complexity and uncertainty to provision resources in the cloud

• With OVMP, the tradeoff between the advance reservation and the allocation of on-demand

resources is adjusted to be optimal• Future work: OVMP with multiple decision stages

Thank you

19

Contact us – [email protected]

Deterministic Integer Programming

20

Different Variances

21

Fixed mean = 25.50

Evaluation: Simulation• Simulation result

22

• When on-demand prices are doubled

Parameter Setting

• Prices defined by each cloud provider

23