applications are routinely accessing and interacting with data on remote resources As data sizes become increasingly large often combined with their locations being far from the applications the well known impact of lower TCP throughput over large delaybandwidth product paths becomes more sig ID: 563989
Download Presentation The PPT/PDF document "With the recent rise in cloud computing," is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
Slide1
With the recent rise in cloud computing, applications are routinely accessing and interacting with data on remote resources. As data sizes become increasingly large, often combined with their locations being far from the applications, the well known impact of lower TCP throughput over large delay-bandwidth product paths becomes more significant to these applications. While myriads of solutions exist to alleviate the problem, they require specialized software at both the application host and the remote data server, making it hard to scale up to a large range of applications and execution environments. A software defined networking based solution called Steroid OpenFlow Service (SOS) has been proposed as a network service that transparently increases the throughput of data transfers across large networks. The SOS architecture has been refined to support data transfer at scale. In an OpenFlow-based environment such as GENI, SOS can leverage the use of multiple agents to provide increased network throughput for many applications simultaneously. A cloud-based approach is particularly beneficial to applications in environments without access to high performance networks. This demo introduces the scalable SOS architecture and demonstrates its viability and scalability in GENI and a private AL2S network between Clemson and Utah.
Ryan Izard,
Geddings
Barrineau, Junaid Zulfiqar, Kuang-Ching Wang{rizard, cbarrin, jzulfiq, kwang}@clemson.edu
Agent(s) at various geographic locations; can use multiple agents at each site
Physical
OpenFlow
switches in network connecting clients, servers, and agents
Floodlight
OpenFlow controller orchestrates SOS for applicable TCP connectionsOpenFlow used to intercept and redirect client-to-server TCP connections to/from SOS agents. The redirect is transparent with respect to the client and server.Agents implement parallel TCP using many TCP connections over large network
SOS Architecture
Goals and Motivation
Steroid
OpenFlow
Service: A Transparent and Scalable Data Transfer Solution
Scalability Results in GENI
Conclusion and Future Work
Demonstration Scenario
10Gbps link between Clemson and Utah via AL2S
Goal is to improve data transfer rate transparently for the client and server using SOS
Results show SOS increases data transfer rate from ~200Mbps to over 5Gbps
CPU on agent is bottleneck
Through experiments in
GENI and over a private network on AL2S,
SOS shows great potential as a data transfer solution across large delay bandwidth product networks. Unlike existing solutions, SOS is transparent and “lives” within the network, automatically optimizing user data transfers without any configuration or installation of software on the client or server machines. Furthermore, through the results obtained in GENI, the SOS architecture is scalable.Future work is planned to assess the performance of SOS in high performance environments. The next step for SOS is to evaluate its performance in CloudLab, where multiple physical agents will be used to try and fill a 10Gbps link between Clemson and Utah.