“…A large-scale data center comprises hundreds of thousands of servers, and hosts a diverse set of online services that require high bandwidth, low latency or both from the network. To meet such requirements, lots of recent advances [5,32,37,28,10,11,40,34,30,44,29,46,45] have focused on improving TCP congestion control (CC) algorithms, by leveraging path diversity [37,28,10,11], exploiting explicit congestion signals from network switches [5,10,40,45,34], measuring delays [29,32], etc.…”