acm sigcomm

Can we get network latency between any two servers at any time in large-scale data center networks? The collected latency data can then be used to address a series of challenges: telling if an application perceived latency issue is caused by the network or not, defining and tracking network service level agreement (SLA), and automatic network troubleshooting. We have developed the Pingmesh system for largescale data center network latency measurement and analysis to answer the above question affirmatively.

Modern datacenter applications demand high throughput (40Gbps) and ultra-low latency (< 10 us per hop) from the network, with low CPU overhead. Standard TCP/IP stacks cannot meet these requirements, but Remote Direct Memory Access (RDMA) can. On IP-routed datacenter networks, RDMA is deployed using RoCEv2 protocol, which relies on Priority-based Flow Control (PFC) to enable a drop-free network. However, PFC can lead to poor application performance due to problems like head-of-line blocking and unfairness.

Data center networks encode locality and topology information into their server and switch addresses for performance and routing purposes. For this reason, the traditional address configuration protocols such as DHCP require huge amount of manual input, leaving them error-prone.

This paper presents BCube, a new network architecture specifically designed for shipping-container based, modular data centers. At the core of the BCube architecture is its server-centric network structure, where servers with multi- ple network ports connect to multiple layers of COTS (com- modity on-the-shelf) mini-switches. Servers act as not only end hosts, but also relay nodes for each other.

A fundamental challenge in data center networking is how to efficiently interconnect an exponentially increasing number of servers. This paper presents DCell, a novel network structure that has many desirable features for data center networking. DCell is a recursively defined structure, in which a high-level DCell is constructed from many low-level DCells and DCells at the same level are fully connected with one another. DCell scales doubly exponentially as the node degree increases.