Congestion control algorithms, such as RENO and CUBIC, are vital for the Internet. However, numerous bugs have been discovered and reported in the Congestion Control Algorithm Implementations (CCAIs), even in those that have been extensively tested and used on the Internet for years, such as Linux RENO and Linux CUBIC. Some of these bugs have potentially severe impacts on the performance and stability of the Internet. Unfortunately, current CCAI testing and verification methods are inadequate for proving the absence of bugs, require substantial verification expertise, or are not scalable to a large number of acknowledgment packets (ACKs) that trigger CCAI actions. To address all these shortcomings, we propose an ACK Scalable Method, called ASM. Our experiments with two representative loss-based CCAIs, Linux RENO and CUBIC, demonstrate the promising performance of the proposed ASM even with tens of thousands of ACKs.

Google introduced BBR representing a new model-based TCP class in 2016, which improves throughput and latency of Google's backbone and services and is now the second most popular TCP on the Internet. As BBR is designed as a general-purpose congestion control to replace current widely deployed congestion control such as Reno and CUBIC, this raises the importance of studying its performance in different types of networks. In this paper, we study BBR's performance in cloud networks, which have grown rapidly but have not been studied in the existing BBR works. For the first time, we show both analytically and experimentally that due to the virtual machine (VM) scheduling in cloud networks, BBR underestimates the pacing rate, delivery rate, and estimated bandwidth, which are three key elements of its control loop. This underestimation can exacerbate iteratively and exponentially over time, and can cause BBR's throughput to reduce to almost zero. We propose a BBR patch that captures the VM scheduling impact on BBR's model and improves its throughput in cloud networks. Our evaluation of the modified BBR on the testbed and EC2 shows a significant improvement in the throughput and bandwidth estimation accuracy over the original BBR in cloud networks with heavy VM scheduling.

Network protocols are challenging to test for correctness due to the huge number of packet dynamics possibilities. Network simulators are popular in evaluating the performance of network protocols but unable to test the correctness under different packet dynamics efficiently. Random testing and symbolic execution are two effective automated correctness testing techniques that can explore different program execution possibilities. Random testing is simple and scalable in checking typical cases but often misses corner ones with low probabilities. Symbolic execution is more efficient in exploring these corner cases but suffers from the scalability problem. In this paper, we propose a testing platform built upon a network simulator by implementing a combination of symbolic execution and random testing to mitigate their limitations. Then we evaluate the efficiency of different techniques in testing Linux network stack under multiple possibilities of packet dynamics.

The correctness of network protocol implementations is difficult to test mainly because of the temporal uncertain nature of network events. In order to test the correctness of a network protocol implementation using network simulators, we need to systematically simulate the behavior of the network protocol under all possible cases of temporal uncertain events, which is very time consuming. The recently proposed Symbolic Execution based Interval Branching (SEIB) simulates a group of uncertain cases together in a single simulation branch, and thus is more efficient than brute force testing. In this paper, we argue that the efficiency of SEIB could be further exponentially improved by eliminating unnecessary comparisons of the event timestamps. Specifically, we summarize and present three general types of unnecessary comparisons when SEIB is applied to a general network simulator, and then correspondingly propose three novel techniques to eliminate them. Our extensive simulations show that our techniques can improve the efficiency of SEIB by several orders of magnitude, such as from days to minutes.