Toward Consistent State Management of Adaptive Programmable Networks Based on P4

P4Resilience: Scalable Resilience for Multi-failure Recovery in SDN with Programmable Data Plane

The massive energy usage of data centers may be traced in part to the growing number of data centers and workstations because of economies of scale for cloud computing. It does, though, indicate wasteful power usage. Consequently, researching ways to improve the energy efficiency of datacenter equipment is now a crucial aspect in reducing datacenter power consumption. In this study, we describe methodologies and algorithms for flexible, energy-efficient, and effective load balancing in data centers, resulting in lower energy consumption by systems. Because of difficulties related with energy consumption, such as capital expenditure, operational costs, and environmental effect, renewable energy is becoming an increasing major consideration in data centers. With the rise in environmental consequences around the world, data centers must consider energy efficiency as one of the most critical factors. Cloud computing techniques have made a huge impact all over the world. Green DC is a concept that has been tested. We suggested an algorithm in this paper based on certain current algorithm limitations that will help to reduce environmental effect. We investigated the efficiency of our program further and used a load balancing method to improve its performance.

Distributed randomized in-network localised load-balancing (DRILL) is one of the most commonly used protocols and relies on the “power of two choices” algorithm. However, this is a sub-optimal load balancing solution due to under-sampling and high number of candidate ports. Along with per-packet granularity, this sub-optimality increases the occurrence of out-of-order packets. Therefore, in this paper, we proposes a novel power of two choices-based load balancing protocol to overcome these shortcomings. Designated as state aware multiple-choice routing (SAMCR) for load balancing in data centers, it builds a Kalman filtering algorithm; to approximate queue length states using the developed processes and measurement models. Furthermore, it uses the estimated queue length states in an adaptive threshold-based covariance matrix to track the most optimal decision in the system. Mathematical simulations as well as an NS-3 discrete event network simulator were used to evaluate the superior performance of SAMCR over other state-of the art approaches in terms of system load, flow completion time and throughput for most types of flows.

This paper presents the network load balancing problem, a challenging real-world task for multi-agent reinforcement learning (MARL) methods. Traditional heuristic solutions like Weighted-Cost Multi-Path (WCMP) and Local Shortest Queue (LSQ) are less flexible to the changing workload distributions and arrival rates, with a poor balance among multiple load balancers. The cooperative network load balancing task is formulated as a Dec-POMDP problem, which naturally induces the MARL methods. To bridge the reality gap for applying learning-based methods, all methods are directly trained and evaluated on an emulation system from moderate-to large-scale. Experiments on realistic testbeds show that the independent and "selfish" load balancing strategies are not necessarily the globally optimal ones, while the proposed MARL solution has a superior performance over different realistic settings. Additionally, the potential difficulties of MARL methods for network load balancing are analysed, which helps to draw the attention of the learning and network communities to such challenges.

Virtualization is the key technology of cloud computing, by which the physical resources in data center can be abstracted as a virtual resource pool for flexible resource allocation. To make full use of the data center resources, efficient virtual network embedding (VNE) is both an efficient and challenging solution. Traditional VNE algorithms focused on the generic topology in the Internet, while the data center network topology is regular and symmetric. In this paper, the most widely used fat-tree topology is considered, and a proximal adaptive VNE algorithm based on multi-dimensional load balancing is proposed. In this VNE algorithm, the bandwidth resource cost is reduced by proximal mapping, and the joint balancing of computation and communication loads is taken into account to achieve multi-dimension resource allocation balance. Simulation results show that the proposed algorithm can increase the resource utilization, and keep both the load balance of each single-dimension resource and the joint balance of different dimensions of resources.

Entropy-based approaches have been shown to aid a wide variety of network measurement applications such as load balancing, anomaly detection, traffic classification. Existing entropy estimation methods require frequent interaction between forwarding and control planes which increases the burden on the network and causes unnecessary delay. In this paper, we present Filter-Sketch, a two-layer sketch that supports frequency estimation with small and static memory allocation. Based on Filter-Sketch, we propose a new generation of mechanisms to calculate entropy at a line rate which completely executes in programmable data plane. The trace-driven evaluation shows that Filter-Sketch achieves higher accuracy than the existing data plane algorithm in entropy estimation where the relative error decreases 0.65 in average.

Software-Defined Networking (SDN) promises the vision of more flexible and manageable networks, but requires certain level of programmability in the data plane. Such a flexible, programmable data plane implementation is OpenFlow (OF) which these days is seen as primary model of SDN data plane. In this paper we focus on the limitations of OF in packet switching performance. We share some measurement results we collected using an OF 1.3 prototype based on Intel's Data Plane Development Kit (DPDK) and we also describe some optimization ideas. While OF 1.0 can be implemented on high-speed Ethernet switch hardware it has certain disadvantages in the area of flexibility. On the other hand OF 1.3 offers good-enough flexibility, but the poor performance of OF 1.3 implementations seems to represent a roadblock to SDN adoption. In this paper we argue that contrast to the common view, the overhead of flexibility is relatively low. We also argue that the apparent difference between a programmable data plane and a state of the art layered data plane is not primarily due to flexibility itself, but because the lack of optimization in case of flexible implementations.

Recently, Programmable Data Plane (PDP) has been leveraged to offload Network Functions (NFs). Due to its high processing capabilities, programmable data plane can improve the performance of NFs to more than one order of magnitude. However, the coarse-grained NF orchestration granularity on the PDP makes it hard to fulfill the dynamic service chain demands. In this paper, we propose the Flexible Network Function (FlexNF) Deployment on the programmable data plane. We first design an NF Selection Framework which leverages labels and the pipeline re-enter operation to support Selective Serving Mechanism for flexible NF orchestration. We then design a two-stage service path construction algorithm to provide on-path service based on SSM with load balancing taken into account. We implement 7 types of real network functions in the commodity P4 switch, based which we construct the comprehensive experiments. The results show that FlexNF can reduce the traffic routing delay by about 42.6% while increasing service chain acceptance rate by 5 times compared with current solutions.

Software-Defined Networking (SDN) switch vendors are interested in extending switch data planes to support new and continuously evolving network protocols (e.g., NVGRE, VXLAN). Numerous commercial programmable data plane devices already enable a programmer to specify various aspects of the data plane including packet parsing, actions, and the layout of packet processing on the hardware device itself. Unlike OpenFlow-based devices, which only expose a series of fixed match-action table (MAT) abstraction, these specialized devices provide a more flexible abstraction for packet processing. Despite the increased programmability that these devices offer, however, the architecture of the target restricts the features that can be exposed to the programmer. Similarly, existing languages for programming the data planes in such devices (e.g., P4) assume a specific computational model, resembling the architecture of the device for which they are targeted for. Unfortunately, this model leads to similar limitations as in OpenFlow, where the high-level specification is coupled to the underlying device model.In this paper, we introduce NetASM, an intermediate representation for programmable data planes. NetASM is a device-independent language that is expressive enough to act as the target language for compilers for high-level languages, yet low-level enough to be efficiently assembled on various device architectures. It enables conventional compiler optimization techniques to significantly improve the performance and resource utilization of custom packet-processing pipelines on a variety of targets.

This paper describes the design and implementation of a general-purpose compile-time sandbox for P4 data plane programs. Our mechanism allows a supervisor to interpose on another program's interaction with the forwarding device. The sandboxing technique we use provides also a powerful new program structuring model, allowing a data plane developer to combine crosscutting program modules in a safe way. To demonstrate the capabilities of our construct, we describe the implementation of a data plane security kernel that enforces end host isolation policies on top of a programmable data plane.

Network attacks show a trend of increased attack intensity, enhanced diversity, and more concealed attack methods, which put forward higher requirements for the performance of network security equipment. Unlike the SDN (software defined network) switch with a fixed-function data plane, switches with programmable data planes can help users realize more network protocols. Programming Protocol-independent Packet Processors (P4) is proposed to define the operations of the data plane and to implement user’s applications, e.g., data center networks, security, or 5G. This paper provides a review of research papers on solving network security problems with P4-based programmable data plane. The work can be organized into two parts. In the first part, the programming language P4, P4 program, architectures, P4 compilers, P4 Runtime, and P4 target are introduced according to the workflow model. The advantages of P4-based programmable switching in solving network security are analyzed. In the second part, the existing network security research papers are divided into four parts according to the perspectives of passive defense, active defense, and combination of multiple technologies. The schemes in each category are compared, and the core ideas and limitations are clarified. In addition, a detailed comparison is made for the research on the performance of P4 targets. Finally, trends and challenges related to the P4-based programmable data plane are discussed.

Programmable Data Plane (PDP) has been leveraged to offload Network Functions (NFs). Due to its high processing capability, the PDP improves the performance of NFs by more than one order of magnitude. However, the coarse-grained NF orchestration on the PDP makes it hard to fulfill the dynamic service chain demands and unreasonable network function deployment causes long end-to-end delays. In this paper, we propose the Flexible Network Function (FlexNF) deployment on the PDP. First, we design an NF Selection Framework, leveraging the service selection label and re-entering operations for flexible NF orchestration. Second, to support runtime NF reconfiguration to meet the dynamic flow demands, we propose the Per-Flow On-Demand servicing mechanism, where one Match-Action Table with multiple mixed NFs works as different NFs for different flows. Third, to ensure the QoS of flows, on the one hand, we design an SP-aware NF Placement Algorithm to find a near-optimal placement solution that accommodates peak traffic volume while minimizing the overall routing path lengths of all the requests, on the other hand, we design a Two-Stage Service Path Construction Algorithm to provide on-path service while considering load balancing. We implement 15 types of network functions on the P4 switch, based on which we construct the comprehensive experiments. FlexNF reduces the traffic delay by 42.6% while increasing the service chain acceptance rate by five times compared with current solutions. Besides, when switching functions, the FlexNF improves the throughput by 2.04Gbps and reduces the packet loss by 8.269% compared with current solutions.

Flow-based load balancing exploits the parallelism of network traffic to improve forwarding performance. However, in programmable data planes, the concept of “flow” has been changed, which undermines the premise of hashing-based load balancing. The current network hashing algorithms such as Toeplitz and CRC16 cannot recognize the flow containing different packets, may resulting in forwarding performance degradation. In this study, we introduced an approach based on the locality sensitive hashing to the failure at flow recognition. We proved that bit sampling achieves a higher probability that packets belonging to the same flow are mapped to the same queue than Toeplitz and random algorithm. To guarantee the load balancing performance of bit sampling, we proposed a method for bits selection. The experimental results showed that bit sampling could improve the probability by at least 55% over current network hashing algorithms while maintaining competitive load-balancing performance.

We highlight the advantages of dynamic wavelength allocation and path rerouting in hybrid optical flow-switched data center networks compared with static electronic packet-switched data center networks. Current electronic packet-switched networks perform routing based on lookup tables and shortest path routing over high speed optical connections. However, load balancing and path rerouting are not designed in coordination with the optical data plane. In this work, we design and analyze the performance of load balancing and resource allocation in hybrid flow data center architectures. In the hybrid flow architecture, the transport layer and control plane are responsible for load balancing, congestion control and reliable data delivery in wavelength division multiplexed networks. The transport layer abstracts the underlying network and data link layers from user applications. Applications are unaware of whether flows are transmitted via the electronic data plane, optical data plane, or both, where the relevant metric for applications is transaction delay. We show that the data center architecture that minimizes delay in the presence of elephant flows and dynamic loads is the hybrid flow architecture with dynamic resource allocation.

Network virtualization allows multiple logical networks to coexist on the same physical infrastructure. However, existing virtualization techniques do not work well for data plane. Software-based virtualization techniques suffer from poor performance due to high virtualization overhead while hardware-based virtualization techniques are not flexible due to limited programmability. In this paper, we present Virtualizing Programmable Data Plane (VirtPDP), an architecture to achieve scalability, flexibility, and isolation simultaneously. Specifically, VirtPDP proposes a parallel pipeline structure by extending programmable data plane to parallelly execute multiple virtual networks on a programmable switch. With VirtPDP, each virtual network runs independently to guarantee performance isolation. Additionally, VirtPDP uses a multi-controller control plane structure to independently manage virtual networks on the programmable switch. We implement the VirtPDP prototype both on BMv2 target and Tofino target. The experimental results show that compared to existing work, VirtPDP not only realizes parallel operation of multiple virtual networks with low performance loss, but also provides better flexibility and scalability. Meanwhile, Tofino-based VirtPDP performs much better than DPDK-based NativeP4 while realizing the coexistence of multiple virtual networks.