This week, read Data Center TCP (DCTCP).

• Skip section 3.3 except for the final paragraph, which gives an estimate for the parameter K.
• Skim section 4 (Results)
• Closely observe figures 15 and 19, which show the queue occupancy as a function of time, and number of sources.

DCTCP customizes the TCP congestion control algorithm for datacenters. It leverages the Explicit Congestion Notification (ECN) to obtain an early congestion feedback from routers/switches, before the queue drops packets. Further, DCTCP provides a smooth reaction to congestion, i.e., when congestion is limited, it reduces its congestion window by a small amount. In contrast, when congestion is severe, it reduces its congestion window by a large amount.

To help you as you read:

• Section 1 introduces the paper. Section 2 describes communication in datacenter networks. After this section, you should understand how datacenter traffic differs from "normal" Internet traffic.
• Section 3 describes the DCTCP algorithm. After this section, you should understand how DCTCP compares to TCP. Does it react sooner or later to congestion than TCP does? What does a DCTCP sender do when it infers that there is congestion on the network as compared to a TCP center? What are queues in a datacenter running DCTCP like (empty? full? etc.)?
• Section 4—which you should skim— gives the results of the authors' experiments. Check that the empirical results match your expectations

As you read, think about

• What are some unique characteristics of datacenter environments, especially compared to the Internet at large? There are many; you should name at least three.
• The paper describes a few performance issues in datacenter networks. Give a brief (1-2 sentence) explanation of each of the following: incast, queue buildup, and buffer pressure. From your descriptions, it should be clear how these issues, especially queue buildup and buffer pressure, differ.
• Take a look at Figure 15 in the paper. What does this tell you about the performance of DCTCP compared to TCP-RED? You should reference both of the graphs in this figure.
• DCTCP achieves both higher throughput and lower delay compared to other protocols. What does it trade-off in order to get this performance? What evidence do the authors give that this trade-off is reasonable?
• Would DCTCP work on the Internet at large? Why or why not?

Submit your answers to these questions on Canvas by 12:00pm on Friday 3/13. You should be writing a few sentences in response to each question (so we don't need you to write an essay for each one, but we're also expecting more than one-word answers). Your responses should be in your own words, not direct quotations from the paper.