h-DDSS: Heterogeneous Dynamic Dedicated Servers Scheduling in Cloud - - PowerPoint PPT Presentation

▶
h ddss heterogeneous dynamic dedicated servers scheduling
SMART_READER_LITE
LIVE PREVIEW

h-DDSS: Heterogeneous Dynamic Dedicated Servers Scheduling in Cloud - - PowerPoint PPT Presentation

Nov 29, 2022 319 likes •712 views

h-DDSS: Heterogeneous Dynamic Dedicated Servers Scheduling in Cloud Computing Husnu S aner Narman Md. Shohrab Hossain Mohammed Atiquzzaman School of Computer Science University of Oklahoma, USA. atiq@ou.edu www.cs.ou.edu/~atiq June 2014

slide-1
SLIDE 1

h-DDSS: Heterogeneous Dynamic Dedicated Servers Scheduling in Cloud Computing

Husnu Saner Narman

  • Md. Shohrab Hossain

Mohammed Atiquzzaman

School of Computer Science University of Oklahoma, USA. atiq@ou.edu www.cs.ou.edu/~atiq June 2014

slide-2
SLIDE 2

Scheduler

What is Cloud Computing

Mohammed Atiquzzaman 3 Cloud Servers Virtual Machine (VM) Virtual Machine (VM) Request Request VM Request VM Request

slide-3
SLIDE 3

Why Cloud Computing

  • Simplicity

– No need to set up software/hardware

  • Flexibility

– Easily extending memory/CPU capacity

  • Maintenance

– IT services

  • Time and energy

– No time or extra effort for desired environment

  • Pay as you go

– No need to pay for unused hardware or software

Mohammed Atiquzzaman 4

slide-4
SLIDE 4

Scheduler

What is Cloud Scheduling

Mohammed Atiquzzaman 5

  • 1. Request
  • 3. Assign VM to customer
  • 2. Find the best appropriate machine to create VM.
slide-5
SLIDE 5

Customer Type

  • Different customers classes?

– Paid and non-paid

  • Customer requirements

– Desired Platform based on Service Level Agreement

  • How to satisfy different customer classes?

– Reserve servers for each customer types

  • Dedicated Servers Scheduling

– Priority

  • High or Low

Mohammed Atiquzzaman 6

slide-6
SLIDE 6

Scheduler

Customer Priority

Mohammed Atiquzzaman 7 Non-paid (Low Priority) Paid (High Priority)

slide-7
SLIDE 7

Priority Level

Mohammed Atiquzzaman 8

High Low Unknown Without priority level in queuing theory High (Ψ1 = 4) Low (Ψ2 = 1) With priority level in cloud computing 3 High (Ψ1 = 5) Low (Ψ2 = 1) 4

slide-8
SLIDE 8

Reserved Servers

Mohammed Atiquzzaman 9 Non-paid Paid Non-paid Customer Servers Paid Customer Servers How many servers are needed for each group of customers?

Scheduler

slide-9
SLIDE 9

Mohammed Atiquzzaman 10 Non-paid Paid Non-paid Customer Servers Paid Customer Servers What happen when one type of customer arrival increases?

Dedicated Servers Scheduling

Assumption Servers are homogeneous DSS: No update of number of servers for each group.

Scheduler

slide-10
SLIDE 10

Dedicated Servers Scheduling

Mohammed Atiquzzaman 11

slide-11
SLIDE 11

Problems with DSS

  • Does not dynamically update number of

servers for each group

– If arrival rate changes – If priority level changes

  • Servers are homogeneous (Unrealistic)

Mohammed Atiquzzaman 12

slide-12
SLIDE 12

Dynamic Dedicated Server Scheduling (DDSS)

Mohammed Atiquzzaman 13

slide-13
SLIDE 13

Mohammed Atiquzzaman 14 Non-paid Paid Non-paid Customer Servers Paid Costumer Servers What happen when one type of customer arrival increases?

Dynamic Dedicated Servers Scheduling

DDSS: Updating number of servers for each group.

Scheduler

Assumption Servers are homogeneous

slide-14
SLIDE 14

Dynamic Dedicated Servers Scheduling

Mohammed Atiquzzaman 15

slide-15
SLIDE 15

Problems with DDSS

  • Servers are homogeneous (Unrealistic)

Mohammed Atiquzzaman 16

slide-16
SLIDE 16

Heterogeneous Dynamic Dedicated Server Scheduling (h-DDSS)

Mohammed Atiquzzaman 17

slide-17
SLIDE 17

Why Heterogeneous

  • Failed or misbehaved servers of a multi-

server system are replaced by new and more powerful ones

Mohammed Atiquzzaman 18

slide-18
SLIDE 18

Heterogeneous Servers

Mohammed Atiquzzaman 19 Heterogeneous Servers

Scheduler

slide-19
SLIDE 19

Objective

  • Improve performance of cloud systems for

heterogeneous servers

– Allowing heterogeneous servers to be dynamically allocated to customer classes based on

  • Priority level.
  • Arrival rate.

Mohammed Atiquzzaman 20

slide-20
SLIDE 20

Contribution

  • Propose Heterogeneous Dynamic Dedicated Servers Scheduling.
  • Develop Analytical Model to evaluate performance

– Average occupancy – Drop rate – Average delay – Throughput

  • Comparing performance of

– Heterogeneous Dynamic Dedicated Servers Scheduling – Dynamic Dedicated Servers Scheduling.

Mohammed Atiquzzaman 21

slide-21
SLIDE 21

Mohammed Atiquzzaman 22 Non-paid Paid Non-paid Customer Servers Paid Customer Servers What happen when one type of customer arrival increases?

Heterogeneous Dynamic Dedicated Servers Scheduling

h-DDSS: Updating number of servers for each group.

Scheduler

Assumption Servers are heterogeneous (Realistic)

slide-22
SLIDE 22

Heterogeneous Dynamic Dedicated Servers Scheduling

Mohammed Atiquzzaman 23

slide-23
SLIDE 23

Dynamic Approach

Mohammed Atiquzzaman 24

This formula can be used for r number customer types.

𝜈𝑢𝑝𝑢𝑏𝑚: Total service rate of servers Ψ1: Priority level of 𝐷1 customers 𝜇1: Arrival rate

  • f 𝐷1 customers

Ψ2: Priority level of 𝐷2 customers 𝜇2: Arrival rate

  • f 𝐷2 customers

𝜈𝑢𝑛: Total service rate assigned for 𝐷1 customers 𝜃𝑢𝑙: Total service rate assigned for 𝐷2 customers 𝜈𝑗: Service rate

  • f 𝑗 server
slide-24
SLIDE 24

Modeling Assumptions

  • System is under heavy traffic flows.
  • Arrivals follow Poisson distribution, and service times

for customers are exponentially distributed.

  • Type of queue discipline used in the analysis is FIFO.
  • Service rate of all servers can be different.

Mohammed Atiquzzaman 25

slide-25
SLIDE 25

Analytical Model

  • Only 𝐷1 customers performance metric developed.
  • Markov Chain Model :

Mohammed Atiquzzaman 26 𝑞0 𝑞1 𝑞2 𝑞𝑛−1 𝑞𝑛 𝑞𝑛+1 𝑞𝑛+𝑂

… …

𝜇1 𝜇1 𝜇1 𝜇1 𝜇1 𝜇1 𝜈𝑢 𝜈𝑢2 𝜈𝑢 𝑛−1 𝜈𝑢𝑛 𝜈𝑢𝑛 𝜈𝑢𝑛 𝜇1: Arrival rate

  • f 𝐷1 customers

𝑛: number of servers for 𝐷1 customers 𝜈𝑢𝑗 =

𝑘=1 𝑗

𝜈𝑘 𝑂: Queue size 𝑞𝑗: Probability of 𝑗 𝐷1 customer in the system 𝜍 = 𝜇1 𝜈𝑢𝑛

slide-26
SLIDE 26

Performance

  • Drop Probability :
  • Throughput: 𝛿 = 𝜇1 1 − 𝐸
  • Occupancy:
  • Delay: 𝜀 = 𝑜

γ

Mohammed Atiquzzaman 27 Occupancy Number of customers in the systems buffer. Throughput Number of customers served in the systems. Drop probability Rate of dropped customers from the systems buffer. Delay Average waiting time

  • f a customer in the

systems buffer.

slide-27
SLIDE 27

Results

  • We have used discrete event simulation to implement by

following 𝑁/𝑁𝑗/𝑂/𝑂 and proposed scheduling.

  • Each queue holds 30 customers.
  • We ran simulation with 20000 customers for each

arrival rate.

  • We show h-DDSS with Fastest Server First (FSF) and

Slowest Server First (SSF) to compare best and worst performance.

Mohammed Atiquzzaman 28

slide-28
SLIDE 28

Traffic Arrival Rates

  • Simulations were carried out with increased arrival rates
  • f all types of customers to observe the impact of heavy

traffic on the system.

  • Customer arrival rates at different trials:

𝜇1={1, 2, 3, 4, 5, 6, 7, 8, 9, 10}, 𝜇2={2, 4, 6, 8, 10, 12, 14, 16, 18, 20}, Ψ1={2 ,3}, Ψ2={1} and 𝜈 = 1, 2, … 7 for heterogeneous servers and 𝜈 = 4, for homogeneous servers with 7 servers.

Mohammed Atiquzzaman 29

slide-29
SLIDE 29

Validation of Analytic Formulas: Occupancy

Mohammed Atiquzzaman 30 Occupancy of 𝐷2 for analytical and simulation matches. Occupancy of 𝐷1 for analytical and simulation closely matches. Ψ1 - Priority level of 𝐷1 customers Ψ2 - Priority level of 𝐷2 customers Occupancy model matches with simulation. Occupancy Number of customers in the systems buffer.

slide-30
SLIDE 30

Validation of Analytic Formulas: Throughput

Mohammed Atiquzzaman 31 Throughput of 𝐷2 for analytical and simulation closely matches. Throughput of 𝐷1 for analytical and simulation closely matches. Ψ1 - Priority level of 𝐷1 customers Ψ2 - Priority level of 𝐷2 customers Throughput model matches with simulation. Throughput Number of customers are served in the systems.

slide-31
SLIDE 31

h-DDSS vs DDSS

Mohammed Atiquzzaman 32

DDSS is homogeneous. h-DDSS is heterogeneous.

Occupancy of 𝐷2 for DDSS is lower than occupancy

  • f 𝐷2 for h-DDSS.

Occupancy of 𝐷1 for DDSS and h-DDSS are same. DDSS shows better occupancy than h-DDSS for these priority levels. Objective We would like to see effects of priority level Ψ1 = 2 on occupancy.

slide-32
SLIDE 32

h-DDSS vs DDSS

Mohammed Atiquzzaman 33

DDSS is homogeneous. h-DDSS is heterogeneous.

Occupancy of 𝐷2 for DDSS is higher than occupancy

  • f 𝐷2 for h-DDSS.

Occupancy of 𝐷1 for DDSS and h-DDSS shows small differences. h-DDSS shows better occupancy than DDSS for these priority levels. Objective We would like to see effects of priority level Ψ1 = 3 on occupancy.

slide-33
SLIDE 33

h-DDSS vs DDSS

Mohammed Atiquzzaman 34

DDSS is homogeneous. h-DDSS is heterogeneous.

Throughput of 𝐷2 for DDSS is higher than throughput

  • f 𝐷2 for h-DDSS.

Throughput of 𝐷1 for DDSS and h-DDSS are same. DDSS shows better throughput than h-DDSS for these priority levels. Objective We would like to see effects of priority level Ψ1 = 2 on throughput.

slide-34
SLIDE 34

h-DDSS vs DDSS

Mohammed Atiquzzaman 35

DDSS is homogeneous. h-DDSS is heterogeneous.

Throughput of 𝐷2 for DDSS is lower than throughput

  • f 𝐷2 for h-DDSS.

Throughput of 𝐷1 for DDSS and h-DDSS are same. h-DDSS shows better throughput than DDSS for these priority levels. Objective We would like to see effects of priority level Ψ1 = 3 on throughput.

slide-35
SLIDE 35

Summary of Results

  • Priority levels do not affect the performance of DDSS and h-

DDSS under low traffic.

  • Under heavy traffic, priority levels have a significant impact
  • n the class performances of DDSS.
  • Under heavy traffic, performances of FSF and SSF in h-DDSS

are same while FSF is better for low traffic arrivals.

  • h-DDSS can be more efficient than DDSS for selected class

priority levels

Mohammed Atiquzzaman 36

slide-36
SLIDE 36

Conclusion

  • We have proposed a novel scheduling algorithm for cloud

computing considering priority, arrival rate and heterogeneous servers.

  • Performance metrics of the proposed cloud computing system are

presented through different cases.

  • h-DDSS and DDSS are compared under different priority levels.
  • Proposed scheduling algorithm can help Cloud Computing with

homogenous and heterogeneous servers systems have higher throughput and be more balanced.

Mohammed Atiquzzaman 37

slide-37
SLIDE 37

Thank You

http://cs.ou.edu/~atiq atiq@ou.edu

Mohammed Atiquzzaman 38