In this episode of the backend engineering show I go through and discuss the Homa Protocol paper which attempts to replace TCP as a protocol in the data centers. I learned a lot from this paper, I have my criticisms of certain aspects, timestamps for topics discussed below. It appears there is a path to replace TCP in the datacenter and professor John tries to explain this path. Referenced materials mentioned in the episode Overview paper https://web.stanford.edu/~ouster/cgi-bin/papers/replaceTcp.pdf Homa 2018 paper (Details) https://people.csail.mit.edu/alizadeh/papers/homa-sigcomm18.pdf NIC Offloading in Linux https://en.wikipedia.org/wiki/TCP_offload_engine#Support_in_Linux Curl disabling Nigel Algo https://github.com/curl/curl/commit/4732ca5724072f132876f520c8f02c7c5b654d9 0:00 Intro 3:00 The nature of networking data center 5:30 TCP Segments 7:30 There is no “Request” in TCP 12:00 What so unique about Data centers? 14:00 Message Throughput vs Data throughput 18:25 Congestion Control 22:38 Homa’s Congestion Control 25:00 Server Core Load Balancing 28:30 NIC offloading 30:00 Everything Wrong about TCP 37:00 Why not QUIC? 40:00 Limitation of Streaming 44:10 Load Balancing Stream Reading 47:15 Can we treat Segments as Messages? 51:00 Dispatching Messages is Easier 53:00 Connection Orientation 1:00:00 Sender Driven Congestion Control 1:03:00 In Order Packet Delivery 1:07:00 DCTCP 1:08:30 Homa is Message Based 1:11:00 Home is Connection Less 1:12:00 Receiver Driven Congestion Control 1:15:19 Out of Order Packets 1:16:20 Homa API is not Compatible with TCP 1:17:40 Will Homa come to HTTP? 1:18:45 Conclusion

Ask this episode

“What did the council decide on item 42?” — answered with the speaker and the moment.

Transcript

Related