Congestion control schemes based on information, such as queue size and traffic load, have become increasingly important, especially in data center networks, where the applications have stringent bandwidth and latency requirements. However, some congestion control schemes employ In-band Network Telemetry (INT), which introduces nontrivial bandwidth overhead. In this paper, we propose an efficient congestion control scheme: Precise ECN Encoding (PEE). PEE refactors the Explicit Congestion Notification (ECN) marking logic and proposes a novel ECN-based multi-packet joint encoding/decoding mechanism to enable more precise congestion perception. Compared with the state-of-the-art schemes, PEE achieves precise congestion control without introducing extra bandwidth overhead, achieving high throughput and low latency simultaneously. Comprehensive experimental results show that, compared to TIMELY, DCQCN, and HPCC, PEE reduces the average Flow Completion Time (FCT) by 102.1%, 26.8%, and 16.6% respectively under 80% network load.

A variety of model representation methods have been used in recent works to translate machine learning models into programmable switch rules to address network classification tasks at line-speed, i.e., in-network classification. These works generally deploy a complete but heavy model on a switch with limited hardware resources, causing both network-wide waste of resources and unsatisfactory accuracy. Therefore, we propose In-Forest, a general distributed in-network classification framework. Firstly, to improve accuracy with limited resources, we develop a Lightweight Ensemble Generic Optional Model (LEGO), which can be further enhanced into multiple enhanced base models with full functionality. Each switch only needs to deploy a simple base model, rather than the complete ensemble model. Thus, hardware resources required for both switches and the entire network can be significantly reduced. Secondly, as traffic traverses multiple switches, In-Forest aggregates the classification results from different enhanced base models for higher accuracy. Furthermore, we design a two-phase resource-aware model allocation strategy that assigns enhanced base models to switches under different scenarios. We use stable deep reinforcement learning to respond to dynamic traffic changes. Experimental results show that when compared to SwitchTree, Planter, and Netbeacon in two real network topologies, In-Forest can increase accuracy by up to 19.31%, while reducing the number of switch rules by 89.98%.

The data center network (DCN) is a key component of cloud computing. With the rapid expansion of cloud computing, the scale of DCN grows bigger and bigger. However, lacking proper engineering management method, engineers may miswire some links while building DCN, which is called “miswiring problem”. And these miswiring links lead to differences between physical topology and design blueprint graph of DCN, resulting in communication error in DCN. The previous works (DAC [1] and ETAC [2]) only detect devices with miswiring links. DAC can not let the network work until engineers fix miswiring links manually, which is a time-consuming and error-prone task. And ETAC only utilize the devices without miswiring links, it excludes devices with miswiring links from working, which wastes link resource and drops down network throughput. In this paper, we focus on miswiring problem in Clos-based DCN network, and an effective algorithm is introduced to detect and correct miswiring links. Moreover, we propose a miswiring tolerant routing protocol (MTR) to embrace miswiring links, increasing the network throughput in the presence of miswiring links. The simulation results show that for a Fat-Tree network with 128,000 servers, our design can efficiently detect and correct miswiring links (at most 20% miswiring links) in less than 120 milliseconds. And in a 32-array Fat-Tree network, compared with ECMP, MTR can reduce the data transmission completion time by 2.5%, 5.43%, 8.74%, and 11.66% when the percentage of miswiring links is 5%, 10%, 15%, and 20%, respectively.

TCP has been widely adopted in current data centers to ensure reliable data delivery. However, recently TCP Incast was found to occur in many-to-one communications with barrier-synchronized requirement, where the TCP goodput drops dramatically. Previous solutions to TCP Incast either require updating the OS/hardware to support fine-grained timers, or smartly control utilization of the switch buffer to reduce the probability of buffer overflow and packet loss. In this paper we explore a different approach to support many-to-one communication in data center networks, which we call LTTP (LT-code based Transport Protocol). LTTP improves LT (Luby Transform) code to achieve reliable UDP-based transmission by exploiting data redundancy, and employs TFRC (TCP Friendly Rate Control) to adjust the traffic sending rates at servers. NS-2 based simulation shows that the goodput of LTTP never degrades with the increase of the number of servers in many-to-one communications, and LTTP significantly outperforms DCTCP when the number of servers is large. Simulation results also demonstrate that LTTP flows can fairly share bandwidth with TCP flows.