Tesseract A 4D Network Control Plane Carnegie Mellon University Microsoft Research Rice University Presented by: Alberto Gonzalez, Whitney Young
Current Designs No direct control Subtle dependencies Example: load balance forwarding by tuning OSPF link weights, but impacts inter-domain routing
4D Architecture Control plane: Decision Dissemination Discovery Data Services: Dissemination Node configuration
Design
Design Goals Timely reaction to network changes Resilient to decision plane failure Robust and secure control channels Minimal switch configuration Backward compatibility Support diverse decision algorithms Support multiple data planes
Implementation Overview Switch Implements data plane Decision Element (DE) Implements discovery, dissemination, and decision planes
Decision Plane Any network control algorithm can be easily integrated Incremental shortest path first Spanning tree Joint packet filtering/routing Link cost-based traffic engineering Resiliency to DE failure Hot standbys receiving heartbeats
Dissemination Plane Goal: communication between DEs and switches DEs handle most of dissemination plane, but switches help out Path to destination handled by DE Switches have separate queue and dissemination packets have higher priority Security (protects switches, info passed through dissemination plane, and compromised DEs)
Discovery Plane Goal: minimize manual configuration Switches send HELLO messages DEs handle instructing the switches on what to do once active Initiate eBGP session with outside world Backward compatibility (bootstrapping end hosts) Discovery plane as DHCP proxy
Data Plane Configured by decision plane WriteTable exposed with simple interface to provide configuration service to decision plane Allows easy implementation of different services Decision/Dissemination Interface Function independently of each other Only 3 functions used to interface between them (2 more simply to improve performance)
Performance Evaluation Single Link Failures Switch& Regional Failures Link Flapping 10-hop to 12-hop change Tesseract can handle network changes
Performance Evaluation 1347 nodes & 6244 edges DE Computation Time Worst Case: 151ms 99th percentile: 40ms Bandwidth overhead Worst Case: 4.4MB 90% of switched updated with new state
Performance Evaluation Failover times
Applications In enterprise network: Computers both new routes & packet filter placements Loads into routers with no forbidden traffic leaked No human involvement once security policy is specified
Ethernet Key features Tesseract keeps these properties. Widely implemented frame format Support for broadcasting frames Transparent address learning model Tesseract keeps these properties.
Ethernet Through point comparisons Control Plane for TCP flows Started at 570Mbps Leveled at 280Mbps after a failure Conventional RSTP Control Plane Starts at 280Mbps Hit zero after failure Recovered after 7-8 seconds at ~180Mbps
Summary Tesseract Robust Secure Resuable Good Performance Scalable Decission/Dissemination Planes Secure Enterprise Network Resuable Ethernet or IP Good Performance Convergence & Throughput Scalable 1,000+ Switches Enables direct Control Easier to Understand and Deploy