Motivation
Systems
Roadmap
Reliable Multicast for Time-Critical Systems
A-Exam
Mahesh Balakrishnan 1
1Department of Computer Science
Cornell University
Mahesh Balakrishnan A-Exam: Reliable Multicast for Time-Critical Systems
Prepare for your exams
Study with the several resources on Docsity
Earn points to download
Earn points by helping other students or get them with a premium plan
Guidelines and tips
Prepare for your exams
Study with the several resources on Docsity
Earn points to download
Earn points by helping other students or get them with a premium plan
Reliable Multicast for Time-Critical Systems, Exercises of Data Communication Systems and Computer Networks
Combine error traffic for multiple groups within intersections, while conserving: Coherent, tunable per-group overhead: Ratio of data.
Typology: Exercises
2022/2023
1 / 55
This page cannot be seen from the preview
Don't miss anything!
Related documents
Partial preview of the text
Download Reliable Multicast for Time-Critical Systems and more Exercises Data Communication Systems and Computer Networks in PDF only on Docsity!
Motivation Systems Roadmap
Reliable Multicast for Time-Critical Systems
A-Exam
Mahesh Balakrishnan 1 (^1) Department of Computer Science Cornell University
Motivation Systems Roadmap
Outline
(^1) Motivation
(^2) Systems Ricochet PLATO Others
(^3) Roadmap
Motivation Systems Roadmap
Multicast in the Datacenter
Multicast is ubiquitous in the Datacenter... ... hidden under abstractions/middleware such as: Publish-Subscribe Eventing Replicated Data/Functionality In-memory Caching BEA Weblogic, JBoss, Tibco, RTI DDS, Tangosol, Gemfire...
Motivation Systems Roadmap
Time-Critical Applications
Mission-Critical: Finance, Aerospace, Military Scalability, Availability, Fault-Tolerance... Timeliness! Examples: Real-time automated trading Air-traffic Control System Foobooks.com?
Systems Roadmap PLATO Others
Outline
(^1) Motivation
(^2) Systems Ricochet PLATO Others
(^3) Roadmap
Systems Roadmap PLATO Others
Multicast Research
Many different reliable, scalable protocols Designed for streaming video/TV, file distribution Reliable: Packet Loss at WAN Routers, overlay node failures Scalable: Single group with massive numbers of receivers Not suited for datacenter multicast! Different failure mode Different scalability dimensions
Systems Roadmap PLATO Others
(Scalable) Multicast in the Datacenter
Financial Datacenter Example: Each equity is mapped to a multicast group. Each Node is interested in a different set of equities... ... each Node joins a different set of groups.
Tracking S&P 500 Tracking Portfolio
Lots of overlapping groups =⇒ Low per-group data rate.
Systems Roadmap PLATO Others
Designing a Time-Critical Multicast Primitive
Wanted: A reliable, scalable multicast protocol. Reliable: can tolerate end-host loss bursts Scalable: the size of the group the number of senders to a group the number of groups per node
Systems Roadmap PLATO Others
Designing a Time-Critical Multicast Primitive
Wanted: A reliable, scalable multicast protocol. Reliable: can tolerate end-host loss bursts Scalable: the size of the group the number of senders to a group the number of groups per node
Systems Roadmap PLATO Others
Design Space for Reliable Multicast
How does latency scale?
Two Phases: Discovery and Recovery of Lost Packets ACK/timeout: RMTP/RMTP-II Gossip-based: Bimodal Multicast, lpbcast NAK/sender-based sequencing: SRM Forward Error Correction Fundamental Insight: latencyα (^) datarate^1
Systems Roadmap PLATO Others
Forward Error Correction
Pros: Tunable, Proactive Overhead Time-Critical: Eliminates need for retransmission Cons: FEC packets are generated over a stream of data Have to wait for r data packets before generating FEC latencyα (^) datarate^1 data rate: at a single sender, in a single group
Systems Roadmap PLATO Others
Receiver-Based Forward Error Correction
Randomness: Each Receiver picks another Receiver randomly to send XOR to Tunability: Percentage of XOR packets to data is determined by rate-of-fire (r , c) latencyα (^) datarate^1 data rate: across all senders, in a single group
Data Data Lost Data
XOR
XOR
Systems Roadmap PLATO Others
Receiver-Based Forward Error Correction
Randomness: Each Receiver picks another Receiver randomly to send XOR to Tunability: Percentage of XOR packets to data is determined by rate-of-fire (r , c) latencyα (^) datarate^1 data rate: across all senders, in a single group
Data Data Lost Data
XOR
XOR
Systems Roadmap PLATO Others
Receiver-Based Forward Error Correction
Randomness: Each Receiver picks another Receiver randomly to send XOR to Tunability: Percentage of XOR packets to data is determined by rate-of-fire (r , c) latencyα (^) datarate^1 data rate: across all senders, in a single group
E D C B Kernel BufferA
F
F E Kernel BufferD
B C App Buffer App Buffer