1 / 16

On Controller Performance in Software-Defined Networks

On Controller Performance in Software-Defined Networks. Author : Amin Tootoonchian , Sergey Gorbunov , Yashar Ganjali , Martin Casado and Rob Sherwood Publisher : Presenter: Yu Hao , Tseng Date: 2013/05/29. Outline. Introduction NOX-MT Experiment Setup Controller Throughput

abril
Download Presentation

On Controller Performance in Software-Defined Networks

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. On Controller Performance in Software-Defined Networks Author: Amin Tootoonchian, Sergey Gorbunov, YasharGanjali, Martin Casado and Rob Sherwood Publisher: Presenter: Yu Hao, Tseng Date: 2013/05/29

  2. Outline • Introduction • NOX-MT • Experiment Setup • Controller Throughput • Controller Response Time • Cbench

  3. Introduction • How fast can the controller respond to data path requests? • How many data path requests can it handle per second? • For example : • NOXhandles around 30k flow initiation events per second while maintaining a sub-10ms flow install time [14]. • Kandula et al. [9] found that a 1500-server cluster has a median flow arrival rate of 100k flows per second. • Benson et al. [2] show that a network with 100 switches can have spikes of 10M flows arrivals per second in the worst case. • We present NOX-MT a publicly-available multithreaded successor of NOX.

  4. NOX-MT • NOX is not optimized for performance and is single-threaded. • The techniques to optimize NOX are including : • I/O batching to minimize the overhead of I/O • Port the I/O handling harness to Boost Asynchronous I/O (ASIO) library • Use a fast multiprocessor-aware mallocimplementation • NOX-MT is far from perfect. • Heavy use of dynamic memory allocation and redundant memory copies on a per-request basis • Using locking were robust wait-free alternatives exist

  5. Experiment Setup • Cbench emulates a configurable number of OpenFlow switches that all communicate with a single OpenFlow controller. • Each emulated switch sends a configurable number of new flow messages to the OpenFlow controller, waits for the appropriate flow setup responses, and records the difference in time between request and response. • Cbench supports two modes of operation : • Latency • Throughput

  6. Controller Throughput • Maximum throughput

  7. Controller Throughput (Cont.) • Relation with the number of active switches

  8. Controller Throughput (Cont.) • Relation with the load level

  9. Controller Throughput (Cont.) • Effect of write-intensive workload

  10. Controller Response Time • Minimum response time • Average response times of all controllers are between 100 and 150 microseconds. • Maximum response time

  11. Controller Response Time (Cont.) • Relation with the load level

  12. Controller Response Time (Cont.) • Relation with the number of active switches

  13. Cbench

  14. Cbench (Cont.)

  15. Cbench (Cont.) • http://www.openflow.org/wk/index.php/Controller_Performance_Comparisons

  16. Cbench (Cont.)

More Related