Highly accurate timing services are critical to ensure data integrity over wireless networks where data from multiple sensors needs to be processed with precise synchronization. The IEEE 1588 standard Precision Time Protocol (PTP) is typically used to meet the timing accuracy requirements of modern wireless networks; however, implementing PTP is becoming a challenge as telecommunication equipment companies replace fixed function designs with cost-effective General-Purpose Processor (GPP) based designs. One example is the Virtual Radio Access Networks (vRAN) design, where fixed-function appliances are replaced with Commercial-Off-The-Shelf (COTS) servers. To maintain consistent clock service management while implementing PTP on a GPP system, the Operating System (OS) manages the respective clock operations. Kernel-based PTP clock provisioning presents a unified interface for all the network services running in the same computer node. Still, it does not adequately address network services inside a Virtual Machine (VM) where the guest OS resides in a different clock domain. In addition, a software-based PTP clock provisioning service is subject to system jitters, which results in non-deterministic clock accuracy. To address these VM provisioning requirements, we devised a CPU clock-based cross-timestamping technique, ptp4sdn. In this design, we developed a new analytical equation to correlate TimeStamp Counts (TSC) between the PTP clock (available from an IO device) and the CPU clock. In addition, a new algorithm was also developed to remove inherent system jitters introduced with software-based cross-timestamping implementations. Finally, we empirically demonstrate that ptp4sdn can achieve sub-100 ns clock synchronization accuracy, previously only achievable with HW-based implementations.

With the rapid deployment of cloud services and the transformation of traditional on-prem services, e.g., infrastructure, platform, and security, to cloud platforms, the demand for High Availability for cloud services is essential. The growth of compute services through cloud platforms can no longer be met via standard resource provisioning techniques, which includes resources such as compute devices, network devices, etc. Device virtualization is key for cloud resource allocation. Even with the continued adoption of workload containerization, the requirement of domain isolation and the flexibility of service provisioning, containerization within a Virtual Machine is the preferred cloud deployment model. In this paper, we present the design of a live network device update mechanism, e.g., driver and firmware, through a host managed device emulation interface for services deployed on a cloud compute platform. This design does not require scheduled shutdowns of the cloud server, nor does it require hardware redundancy for a system administrator to perform driver and/or firmware maintenance updates. The innovative design presented in this paper enables dynamic resource sharing based upon the service requirements, e.g., failover switching time and network throughput, between the target devices to be updated along with other network devices either in service or on standby. A live networking device mechanism reduces compute service interruption and provides a transparent network function transition between the target interfaces and the failover interfaces.

Network function virtualization (NFV) allows net-work functions executed on general-purpose servers or virtual machines (VMs) instead of proprietary hardware, greatly improving the flexibility and scalability of network services. Recent trends in using programmable accelerators to speed up NFV performance introduce challenges in flow scheduling in a dynamic NFV environment. Reinforcement learning (RL) trains machine learning models for decision making to maximize returns in uncertain environments such as NFV. In this paper, we study the allocation of heterogeneous processors (CPUs and FPGAs) to minimize the delays of flows in the system. We conduct extensive simulations to evaluate the performance of reinforcement learning based scheduling algorithms such as Advantage Actor Critic (A2C), Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO), and compare with greedy policies. The results show that RL based schedulers can effectively learn from past experiences and converge to the optimal greedy policy. We also analyze in-depth how the policies lead to different processor utilization and flow processing time, and provide insights into these policies.

As SDN-based networking infrastructure continues to evolve, an increasing number of traditional network functions are deployed over virtualized networks. Similar to fixed function switching networks, traffic monitoring in a Software Defined Network is critical in order to ensure the security and performance of the underlying infrastructure. In the context of virtualized networks, deployment of a virtualized TAP service has been reported as an effective VNF that can provide the same monitoring capabilities as a physical TAP. For most virtual switch implementations, e.g., OvS, network device virtualization is based upon a para-virtualization technology, i.e., VIRTIO. One of the primary use cases for port mirroring is inter-VM communication, i.e., packet streams that exist between virtual network devices, which remains prohibitively expensive for TAP devices. Specifically, it has been observed that virtual TAPs can contribute up to 70% performance degradation to the source VNF(s). With reference to prior work, we previously presented a feasibility study that included a novel approach towards the reduction of port-mirroring overhead. In this paper we present our latest contributions, in which we integrate our design into OvS and develop a VLAN based filtering scheme to pass traffic from a source device to a monitoring device. In this case, both devices may reside either within the same or different switch domains. Furthermore, we present an improvement over RSPAN and discuss its feasibility in delivering mirrored traffic across switch domains, which, in contrast to ERSPAN, does not require an L3 overlay network.

As network bandwidth consumption continues to grow exponentially, real-time traffic data analysis becomes increasingly challenging and expensive. In many cases, network traffic monitoring can only be achieved via hardware Test Access Point (TAP) devices. Due to the intrusiveness and inflexibility of deploying hardware devices, this approach is intractable within an SDN environment where dynamic network resource allocation is key to the orchestration of network services. This paper presents a novel mirror tunnel design to achieve near hardware level TAP-as-a-Service (TaaS) performance through network device mirror offloading, while retaining resource reconfigurability. Mirror tunneling is a hybrid approach whereby a software TAP transports traffic from a source device to a mirror tunnel device. Traffic is then mirrored in place and sent to the destination device. The combination of a software TAP with the mirroring capabilities of the underlying hardware empowers system administrators to create a dynamically reconfigurable multi-path traffic mirroring system. As demonstrated in the benchmark results, this approach is efficient in terms of network bandwidth consumption and computational resources. In addition, this methodology is designed to mirror traffic in high-throughput environments with minimal to no impact on the source Virtual Network Functions (VNFs).

As SDN-based networking infrastructure continues to evolve, an increasing number of traditional network functions are deployed over virtualized network. Like traditional networks, traffic monitoring in a Software Defined Network is critical in order to ensure security and performance of the underlying infrastructure. In the context of virtualized networks, deployment of a virtualized TAP service has been reported as an effective VNF that can provide the same monitoring capabilities as a physical TAP. Unfortunately, over a para-virtualization environment, e.g. OVS, where inter-VM communication is expensive it has been observed that virtual TAPs can contribute up to 70% performance degradation. In this paper, we present a hybrid approach that allows network administrators to mirror VIRTIO port traffic to another VF (SR-IOV) via NIC hardware offloading. As a result, the mirrored traffic can be viewed through a monitoring VNF in a separate VM. Through this approach, the throughput overhead can be reduced by as much as 50%.

Network measurement tools must support the collection of fine-grain flow statistics and scale well to the increasing line rates. However, conventional network measurement software tools are inadequate in high-speed network at the current scale. In this paper, we present Ares, a scalable high-performance passive network measurement tool to collect accurate per-flow metrics. Ares is built on a multicore platform, consisting of an effective hierarchical core assignment strategy, an efficient hash table for keeping flow statistics, a novel lockless flow statistics management scheme, as well as cache friendly prefetching. Our extensive performance evaluation shows that Ares brings about 19x speedup for 64-byte packets over existing approaches and can sustain up to a line rate of 100Gbps, while delivering the same level of fine-grained flow metrics.

Network measurement is critical in network management such as performance monitoring, diagnosis, and traffic engineering. However, conventional network measurement solutions are limited by simple and fixed functionalities as well as coarse-grained statistics which often fail to precisely illustrate network conditions. In this paper, we propose an event-driven declarative query language, EQuery, for programmable network management in order to design sophisticated measurement tasks and enable event mechanism to avoid human intervene. Furthermore, we design a compiler to support the query language on the EQuery Controller, which drives the chaining query workflow with nondeterministic finite automaton (NFA), and translates measurement jobs into low-level rules/states on the physical devices. Finally, we evaluate the effectiveness of our EQuery framework on a nation-wide operational network with real-time network statistics.