Network utilization with SDN in on-demand application-specific - - PowerPoint PPT Presentation

network utilization with sdn in on demand application
SMART_READER_LITE
LIVE PREVIEW

Network utilization with SDN in on-demand application-specific - - PowerPoint PPT Presentation

Introduction Theoretical Framework Implementation Findings and Conclusions Network utilization with SDN in on-demand application-specific networks Ioannis Grafis Ioannis.Grafis@os3.nl Supervised by: Marc X. Makkes M.X.Makkes@uva.nl System


slide-1
SLIDE 1

Introduction Theoretical Framework Implementation Findings and Conclusions

Network utilization with SDN in on-demand application-specific networks

Ioannis Grafis Ioannis.Grafis@os3.nl

Supervised by: Marc X. Makkes M.X.Makkes@uva.nl

System and Network Engineering Universiteit van Amsterdam

July 1, 2015

Ioannis Grafis Universiteit van Amsterdam July 1, 2015 1 / 16

slide-2
SLIDE 2

Introduction Theoretical Framework Implementation Findings and Conclusions

Internet factories

Internet factories: Creating application-specific networks on-demand[1] Uses Infastructure-as-a-Service clouds Create, configure and modify the infastructure Second implementation Compute factory

Ioannis Grafis Universiteit van Amsterdam July 1, 2015 2 / 16

slide-3
SLIDE 3

Introduction Theoretical Framework Implementation Findings and Conclusions

Overlay networks

A network built on top of one or more existing networks Add extra functionality

Ioannis Grafis Universiteit van Amsterdam July 1, 2015 3 / 16

slide-4
SLIDE 4

Introduction Theoretical Framework Implementation Findings and Conclusions

OSPF / SDN comparison

Open Shortest Path First (OSPF) : Mature protocol Widely used and supported Uses Dijkstra’s algorithm Used by Compute factory Software Defined Networking (SDN): Separation between control plane and data plane Centralized managment Programmability Routing granularity

Ioannis Grafis Universiteit van Amsterdam July 1, 2015 4 / 16

slide-5
SLIDE 5

Introduction Theoretical Framework Implementation Findings and Conclusions

Hypothesis

If the created overlay networks make use of SDN (OpenFlow), Compute factory’s control loops that observe and modify the behavior can gain benefits.

Ioannis Grafis Universiteit van Amsterdam July 1, 2015 5 / 16

slide-6
SLIDE 6

Introduction Theoretical Framework Implementation Findings and Conclusions

Related work

B4: Experience with a Globally-Deployed Software Defined WAN[2] MiceTrap: Scalable Traffic Engineering of Datacenter Mice Flows using OpenFlow[3] SDN Based Load Balancing Mechanism for Elephant Flow in Data Center Networks[4]

Ioannis Grafis Universiteit van Amsterdam July 1, 2015 6 / 16

slide-7
SLIDE 7

Introduction Theoretical Framework Implementation Findings and Conclusions

Differences from our case

Virtual Machine migration Connection speed Dynamic infrastructure

Ioannis Grafis Universiteit van Amsterdam July 1, 2015 7 / 16

slide-8
SLIDE 8

Introduction Theoretical Framework Implementation Findings and Conclusions

Elephants and Mice flows

Elephant flow: Long-lived flow with large data transfer Mice flow: Short-lived flow with small data transfer

Ioannis Grafis Universiteit van Amsterdam July 1, 2015 8 / 16

slide-9
SLIDE 9

Introduction Theoretical Framework Implementation Findings and Conclusions

Compute factory

Ioannis Grafis Universiteit van Amsterdam July 1, 2015 9 / 16

slide-10
SLIDE 10

Introduction Theoretical Framework Implementation Findings and Conclusions

Compute factory flow control loop

Ioannis Grafis Universiteit van Amsterdam July 1, 2015 10 / 16

slide-11
SLIDE 11

Introduction Theoretical Framework Implementation Findings and Conclusions

Scenarios

First Transfer sequential small and large file in empty path Second Transfer simultaneously small and large file with the Copmute factory control loop disabled Third Transfer simultaneously small and large file with the Copmute factory control loop enabled

Ioannis Grafis Universiteit van Amsterdam July 1, 2015 11 / 16

slide-12
SLIDE 12

Introduction Theoretical Framework Implementation Findings and Conclusions

Scenario results

Total time transferring a file

Ioannis Grafis Universiteit van Amsterdam July 1, 2015 12 / 16

slide-13
SLIDE 13

Introduction Theoretical Framework Implementation Findings and Conclusions

CPU utilization

CPU utilization in the intermediate switches

Ioannis Grafis Universiteit van Amsterdam July 1, 2015 13 / 16

slide-14
SLIDE 14

Introduction Theoretical Framework Implementation Findings and Conclusions

Conclusions

Increase stability in data transfer Dicrease jitter Balance the CPU load in intermediate switches Not increase network utilization

Ioannis Grafis Universiteit van Amsterdam July 1, 2015 14 / 16

slide-15
SLIDE 15

Introduction Theoretical Framework Implementation Findings and Conclusions

Thank you

Ioannis Grafis Universiteit van Amsterdam July 1, 2015 15 / 16

slide-16
SLIDE 16

Introduction Theoretical Framework Implementation Findings and Conclusions

References I

Rudolf Strijkers, Marc X. Makkes, Cees de Laat, Robert Meijer Internet factories: Creating application-specific networks on-demand Computer Networks, 68:187-198, 2014. Sushant Jain et al. B4: Experience with a Globally-Deployed Software Defined WAN ACM SIGCOMM, 3-14, 2013. Trestian R., Muntean G.-M., Katrinis K. MiceTrap: Scalable Traffic Engineering of Datacenter Mice Flows using OpenFlow Integrated Network Management, 904-907 , 2013. Jing Liu, Jie Li, Guochu Shou, Yihong Hu, Zhigang Guo, Wei Dai SDN Based Load Balancing Mechanism for Elephant Flow in Data Center Networks Wireless Personal Multimedia Communications, 486-490, 2014.

Ioannis Grafis Universiteit van Amsterdam July 1, 2015 16 / 16