Cloud Server with OpenFlow: Load Balancing
Surya Prateek Surampalli
Information Technology Department, Southern Polytechnic State University
Abstract—in high-traffic Internet today, it is often desirable to have multiple servers that represent a single logical destination server to share the load. A typical configuration comprises multiple servers behind a load balancer that would determine which server would serve the request of a client. Such equipment is expensive, has a rigid set of rules, and is a single point of failure. In this paper, I propose an idea and design for an alternative load-balancing architecture with the help of an OpenFlow switch connected to a NOX controller that gains political flexibility, less expensive, and has the potential to be more robust to failure with future generations of switches
In today’s increasingly internet-based cloud services, a client sends a request to URL or a logical server and receives a response from a potentially multiple servers acts as a logical address server. Google server is said to be the best example, the request is sent to server farm as soon as the client resolves the IP address from the URL .
Load balancers are expensive that acts as a reverse proxy and distributes network or application traffic across a number of servers. Load balancers are used to increase capacity (concurrent users) and reliability of applications. They improve the overall performance of applications by decreasing the burden on servers associated with managing and maintaining application and network sessions, as well as by performing application-specific tasks . Since load balancers are not basic equipment and run custom software, policies are rigid in their choices. Specific administrators are required and also the arbitrary policies are not possible to implement. Since running policy and the switch are connected it is reduced to a single point of failure .
The order of magnitude will cost less than a commercial load-balancer if architecture with an OpenFlow switch is implemented which is controlled by the commodity server and also provides flexibility for writing patterns which allow the controller to be applied arbitrary political .
If the next generation of OpenFlow switches has the capability of connecting to multiple controllers, there is a chance of making the system much robust to abortion by keeping the any server behind the which that acts as the controller .
A. Load Balancing
Load balancing helps make networks more efficient. It distributes the processing and traffic evenly across a network, making sure no single device is overwhelmed . Web servers, as in the example above, often use load balancing to evenly split the traffic load among several different servers. This allows them to use the available bandwidth more effectively, and therefore provides faster access to the websites they host .
Whether load balancing is done on a local network or a large Web server, it requires hardware or software that divides incoming traffic among the available servers. Networks that receive high amounts of traffic may even have one or more servers dedicated to balancing the load among the other servers and devices in the network. These servers are often called (not surprisingly) load balancers .
Load balancing can be performed using dedicated hardware devices such as load balancers or having intelligent DNS servers. A DNS server can redirect traffic data centre with a heavy load or redirect requests made by customers for a data centre that is less network stretches from clients. Many data centres use of expensive hardware load balancing equipment that makes in distributing the network traffic across multiple machines to avoid congestion on a server.
A DNS server resolves a hostname to a single IP address where the client sends the request. To the outside...
References:  OpenFlow Switch Specification. Version 0.8.9 (Wire Protocol 0x97). Current maintainer: Brandon Heller (firstname.lastname@example.org). December 2, 2008.
 C. E. Leiserson. Fat-trees: Universal networks for hardware-efﬁcient supercomputing. IEEE Transactions on Computers, 1985.
 T. Benson, A. Anand, A. Akella, and M. Zhang. Understanding Datacenter Trafﬁc Characteristics. SIGCOMM WREN workshop, 2009.
 HOPPS, C. Analysis of an Equal-Cost Multi-Path Algorithm. RFC 2992, IETF, 2000.
 W. J. Dally and B. Towles. Principles and Practices of Interconnection Networks. Morgan Kaufmann Publisher, 2004.
 N. McKeown, T. Anderson, H. Balakrishnan, G. Parulkar, L. Peterson, J. Rexford, S. Shenker, and J. Turner. OpenFlow: Enabling Innovation in Campus Networks. ACM SIGCOMM CCR, 2008.
 R. N. Mysore, A. Pamporis, N. Farrington, N. Huang, P. Miri, S. Radhakrishnan, V. Subramanya, and A. Vahdat. PortLand: A Scalable, Fault-Tolerant Layer 2 Data Center Network Fabric. ACM SIGCOMM, 2009.
 B. Lantz, B. Heller, and N. McKeown. A Network in a Laptop: Rapid Prototyping for Software-Deﬁnded Networks. ACM SIGCOMM, 2010.
 Y. Zhang, H. Kameda, S. L. Hung. Comparison of dynamic and static load-balancing strategies in heterogeneous distributed systems. Computers and Digital Techniques, IEE, 1997.
 N. Handigol, S. Seetharaman, M. Flajslik, N. McKeown, and R. Johari. Plug-n-Serve: Load-balancing web trafﬁc using OpenFlow. ACM SIGCOMM Demo, 2009.
 R. Wang, D. Butnariu, J. Rexford. OpenFlow-Based Server Load Balancing Gone Wild. Hot ICE, 2011.
 M. Koerner, O. Kao. Multiple service load-balancing with OpenFlow. IEEE HPSR, 2012.
Please join StudyMode to read the full document