Experiences with Perf SONAR and a Control Plane

Experiences with Perf. SONAR and a Control Plane for Software Defined Measurement Yan Luo Department of Electrical and Computer Engineering University of Massachusetts Lowell Slide 1

FLowell Project at a Glance • Slide 2

FLowell Project Status • UML Campus SDN Network – In-lab Testbed Completed: Six Open. Flow switches (Extreme Networks) + Open. Day. Light Controller – Campus-wide Deployment In Progress (two buildings completed, other two buildings by Oct’ 15) • Layer-2 10 Gbps Link (UML<--->MGHPCC) in progress (new Ciena optics pack in order) • Layer-2 10 Gbps Link (UML<-->Internet 2) in progress (new Cisco switch ordered) • Science DMZ in progress (architectural design and verification, vendor selection) • GENI Rack in progress (vendor selection) Slide 3

Performance Tests • DTN – CPU: Intel Core 2 @2. 33 GHz, 2 cores – Hard Disk: Read/Write Speed: 125 MB/s – 1 Gbps edge link (production net) • Perf. SONAR Inside firewall File Size Speed Ave(MB/s) 10 M 3. 62 50 M 11. 92 100 M 23. 84 1 G 42. 47 10 G 37. 48 50 G 36. 51 Test server: anl-diskpt 1. es. net Outside firewall Slide 4

Perf. SONAR Today • Over 1400 public perf. SONAR nodes Slide 5

Perf. SONAR’s Scaling Challenges • Challenges – Control, coordination and execution of network measurements – Monitor healthiness of networks besides major networks – Network issues caused by multiple problematic links • Our Research – Using measurement archives (MA) to build a traceroute graph – Propose a control plane on top of perf. SONAR to support software defined measurement and troubleshooting – A joint work with ESnet (Brian Tierney) and AMPATH/FIU (Jeronimo Bezerra) Slide 6

Motivation of Perf. SONAR Control Plane • Typical Workflow • Finding the Longest Clean Path Slide 7

Objectives of Perf. SONAR Control Plane • Measurement Archive Data Analysis – How were the measurement results? – What can we learn from them? • Automatic perf. SONAR Peer Selection – Quickly identify the best suitable PS node(s) on the routes in question • Programmable Measurement and Troubleshooting – Define measurement task and conditions with software Slide 8

The Design of Perf. SONAR Control Plane • Perf. SONAR Node Discovery – Finding nearest perf. SONAR node of a target router on the path • Measurement Task Control – Initiating tests between (any) two chosen perf. SONAR nodes – Monitoring the performance on the path – Locating the problematic link(s) Slide 9

The Operation of Perf. SONAR Control Plane • Obtain traceroute information from MAs • Build a traceroute graph based on the dataset e n li f f O • Find a set of perf. SONAR node pairs to start bandwidth e tests and monitor the results n i l n • Diagnostic analysis and troubleshooting network. O issues Slide 10

Evaluation of Perf. SONAR Control Plane • Traceroute Dataset – 95 MA hosts in the central US and eastern US regions – 1831 traceroute records • Traceroute Graph – 2377 perf. SONAR hosts and routers in total Slide 11

A Use Case of the New Control Plane • pr 20. uml. edu --- typhoon. pub. alcf. anl. gov (140. 221. 68. 2) • A python program with less than 300 lines of code • “Troubleshooting” procedure took about 15 minutes Slide 12

Conclusion and Future Work • FLowell project at UMass Lowell in good progress • Gained experiences with DTN and Perf. SONAR • A Control Plane for Perf. SONAR show promising results – Open source at: https: //github. com/ACANETS/pscp – Community feedback welcomed! • Tasks in the Upcoming FY: – – Science DMZ Deployment at UML GENI Rack operational at MGHPCC Campus wide outreach to researchers Perf. SONAR Control Plane Collaboration Contact info: Yan Luo, yan_luo@uml. edu Slide 13