CPU Allocation Research Articles

Dynamic Service Provisioning in the Edge-Cloud Continuum With Bounded Resources

We consider a hierarchical edge-cloud architecture in which services are provided to mobile users as chains of virtual network functions. Each service has specific computation requirements and target delay performance, which require placing the corresponding chain properly and allocating a suitable amount of computing resources. Furthermore, chain migration may be necessary to meet the services’ target delay. We model and formalize the problem of finding a feasible chain placement and resource allocation, while minimizing the migration, bandwidth, and computation costs. We tackle this problem by partitioning it into a (i) CPU allocation problem, and a (ii) placement problem. For the CPU allocation problem, we find an optimal solution. For the placement problem, we show that even finding a feasible solution is NP-hard, and envision an algorithm that is guaranteed to find a feasible solution while leveraging a bounded amount of resource augmentation. Our algorithms are incorporated into a solution framework that aims to minimize both the cost and the required resource augmentation. The results, obtained through trace-driven, large-scale simulations, show that our framework can provide a close-to-optimal solution while running several orders of magnitude faster than an ILP solver.

Autothrottle: Satisfying Network Performance Requirements for Containers

This paper investigates how to satisfy network performance requirements that are crucial in achieving the service level objectives (SLOs) in clouds. Traditional techniques for network performance management have a limited ability to satisfy the network SLOs. Our in-depth analysis reveals that the fundamental reason comes from decoupling of the CPU scheduler and the network traffic controller as the current CPU scheduler is not aware of such network requirements but only provides a fair-share amount of CPU to all containers. Thus, the container cannot perform the amount of network processing as needed to satisfy its SLO when the CPU allocation is insufficient. In this paper, we propose Autothrottle that dynamically adjusts the CPU allocation for the containers to satisfy their network SLOs. The key element of Autothrottle is a throttle algorithm that autonomously determines the amount of CPU for each container needed to satisfy the requirement. We implement Autothrottle in the Linux kernel and evaluate it with massive real-world workloads such as Apache Kafka. Our evaluation results show that Autothrottle successfully satisfies the given network SLO only with a 2% gap while the existing scheme achieves 20% less than the SLO. We further observe that Autothrottle also reduces the CPU overhead in network processing by 19%, improving the network throughput by 27% compared to the existing scheme.

Adapt Burstable Containers to Variable CPU Resources

In the age of the cloud-native, container technology, referred as OS-level virtualization, is increasingly adopted to deploy cloud applications. Compared with virtual machines, containers are lightweight and flexible in resource management. An important quality-of-service (QoS) class in container management is burstable container, whose resource limits are higher than the actual requests allowing a container to expand whenever demands ramp up and additional resources become available. However, efficiently managing burstable containers is challenging, especially for CPU resources. On the one hand, burstable containers should maintain sufficient concurrency, in the form of threads, to utilize extendable CPU resources. On the other hand, the degree of concurrency necessary for utilizing peak CPU resources leads to suboptimal performance when a container's CPU allocation is constrained. In this paper, we recommend that the number of threads in burstable containers should always be set to the CPU limit to guarantee extensibility. However, modern operating systems (OSes) fall short of efficiently managing thread oversubscription. First, the OS CPU scheduler is inefficient for scheduling excessive threads and lacks container awareness. Second, the existing blocking synchronization supported by the OS kernel is inefficient in handling the sleep and wakeup of excessive threads. Finally, the non-blocking synchronization may waste CPUs performing busy waiting when more than one thread in the run queue. To this end, we present a user-level adaptive container scheduler and two OS mechanisms, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">virtual blocking</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">busy-waiting detection</i> , to avoid inefficiency in managing burstable containers without requiring program code changes. Experimental results show that our approaches can keep burstable containers efficient while allowing the applications in containers to take advantage of additional CPUs. The performance gain under high system load is up to 29.7×.

Joint VNF Placement, CPU Allocation, and Flow Routing for Traffic Changes

The emerging network-softwarization technologies, such as software-defined networking and network function virtualization play important roles in 5G communication and future networks. One of the critical challenges of the practical application of the softwarized networks is to appropriately place virtual network functions (VNFs). The underlying resources and traffic requirements are often factored in the previous works of VNF placement. However, VNFs’ dynamic abilities of changing traffic are usually ignored. Resources allocated to VNFs can vary their traffic-change ratios, and the adjustment of resource volumes should be provisioned to support traffic changes. In this work, we pay attention to the joint optimization problem of VNF Placement, CPU Allocation, and flow Routing (VNFPAR) in the scenarios consisting of VNFs that can dynamically change traffic. We employ the logarithmic functions to approximate VNFs’ traffic change relations and formulate VNFPAR as a mixed-integer nonlinear programming (MINLP) problem. We demonstrate that this problem is highly nonconvex and involves highly coupled variables. For small-scale VNFPAR problems, we propose an optimal algorithm based on relaxation and programming to consume the minimum bandwidth resources. Because VNFPAR is NP-hard, to quickly find near-optimal solutions for large-scale VNFPAR problems, we present heuristic algorithms based on multistage greedy and simulated annealing, respectively. Besides, to achieve a tradeoff between solution quality and execution time, we decompose VNFPAR into subproblems and design an alternating optimization-based method. We evaluate our algorithms on real-work topologies and traffic patterns. Extensive simulations show that our proposed heuristic algorithms are convergent, stable, and effective in terms of solving VNFPARs. The proposed algorithms have small optimality gaps within 7.4%–26.3%. Meanwhile, they save 39.3%–48.4% bandwidth resources compared with relevant baseline technologies.

Sustainable MapReduce: Optimizing Security and Efficiency in Hadoop Clusters with Lightweight Cryptography-based Key Management

The exponential growth of big data has led to a significant increase in the volume and complexity of data being generated and stored. This trend has created a huge demand for secure storage and processing of big data. Cryptography is a widely used technique for securing data, but traditional cryptography algorithms are often too resource-intensive for big data applications. To address this issue, light weight cryptography algorithms have been developed that are optimized for low computational overhead and low memory utilization. This research paper explores the use of a new sustainable algorithm that utilizes a lightweight cryptographybased key management scheme to optimize MapReduce security and computational efficiency in Hadoop clusters. The proposed sustainable MapReduce algorithm aims to reduce memory and CPU allocation, thereby significantly reducing the energy consumption of Hadoop clusters. The paper emphasizes the importance of reducing energy consumption and enhancing environmental sustainability in big data processing and highlights the potential benefits of using sustainable lightweight cryptography algorithms in achieving these goals. Through rigorous testing and evaluation, the paper demonstrates the effectiveness of the proposed sustainable MapReduce algorithm in improving the energy efficiency and computational performance of Hadoop clusters, making it a promising solution for sustainable big data processing.

DSTS: A hybrid optimal and deep learning for dynamic scalable task scheduling on container cloud environment

Containers have grown into the most dependable and lightweight virtualization platform for delivering cloud services, offering flexible sorting, portability, and scalability. In cloud container services, planner components play a critical role. This enhances cloud resource workloads and diversity performance while lowering costs. We present hybrid optimum and deep learning approach for dynamic scalable task scheduling (DSTS) in container cloud environment in this research. To expand containers virtual resources, we first offer a modified multi-swarm coyote optimization (MMCO) method, which improves customer service level agreements. Then, to assure priority-based scheduling, we create a modified pigeon-inspired optimization (MPIO) method for task clustering and a rapid adaptive feedback recurrent neural network (FARNN) for pre-virtual CPU allocation. Meanwhile, the task load monitoring system is built on a deep convolutional neural network (DCNN), which allows for dynamic priority-based scheduling. Finally, the presentation of the planned DSTS methodology will be estimated utilizing various test vectors, and the results will be associated to present state-of-the-art techniques.

Minimum Overhead Beamforming and Resource Allocation in D2D Edge Networks

Device-to-device (D2D) communications is expected to be a critical enabler of distributed computing in edge networks at scale. A key challenge in providing this capability is the requirement for judicious management of the heterogeneous communication and computation resources that exist at the edge to meet processing needs. In this paper, we develop an optimization methodology that considers the network topology jointly with device and network resource allocation to minimize total D2D overhead, which we quantify in terms of time and energy required for task processing. Variables in our model include task assignment, CPU allocation, subchannel selection, and beamforming design for multiple-input multiple-output (MIMO) wireless devices. We propose two methods to solve the resulting non-convex mixed integer program: semi-exhaustive search optimization, which represents a “best-effort” at obtaining the optimal solution, and efficient alternate optimization, which is more computationally efficient. As a component of these two methods, we develop a novel coordinated beamforming algorithm which we show obtains the optimal beamformer for a common receiver characteristic. Through numerical experiments, we find that our methodology yields substantial improvements in network overhead compared with local computation and partially optimized methods, which validates our joint optimization approach. Further, we find that the efficient alternate optimization scales well with the number of nodes, and thus can be a practical solution for D2D computing in large networks.

Conflict-Based Search for the Virtual Network Embedding Problem

In emerging network virtualization architectures, service providers will be able to create many heterogeneous virtual networks and offer customized end-to-end services by leasing shared resources from infrastructure providers. The Virtual Network Embedding (VNE) problem is central to such technology. It involves the proper allocation of CPU and bandwidth resources available in a physical substrate network to meet the demands of multiple virtual networks. Combinatorially, the VNE problem is a problem in resource management that is NP-hard to solve. In this paper, we present a novel version of the Conflict-Based Search (CBS) algorithm for solving the VNE problem. Our approach, called VNE-CBS, is inspired by the success of the CBS framework in the Multi-Agent Path Finding domain. We successfully address the unique challenges in applying the CBS framework to the VNE problem, and, in doing so, we pave the way for overcoming a crucial issue in Internet ossification via heuristic search methods. On the theoretical front, we show that, unlike many existing algorithms, our algorithm is complete and optimal. On the experimental front, we show that our algorithm significantly outperforms other state-of-the-art methods on various benchmark instances for both the offline and online versions of the VNE problem.

A containerized task clustering for scheduling workflows to utilize processors and containers on clouds

Recent advancements of virtualization technologies for parallel processing involve scheduling containerized tasks in a workflow. Since a container can include multiple tasks, it can be reused or shared among applications. If every task in a workflow uses its dedicated container without sharing among any tasks, each container image must be downloaded for each task. As a result, many computational resources are required to process and the communication latency related to container image downloading can become a bottleneck for the makespan. In task scheduling algorithms for workflows, this characteristic produces a new challenging issue that how effectively shares containers among tasks to avoid redundant container image download processes and redundant task allocations. One of the fundamental problems is that no policy has been established for simultaneously satisfying effective container sharing, maintaining the degree of task parallelism, and effective computational resource utilization. In this paper, we propose a clustering-based containerized task scheduling algorithm for clouds, namely, shareable functional task clustering for utilizing virtualized resources (SF-CUV). The objective of SF-CUV is to minimize the makespan with less computational resources and containers than other algorithms by clustering tasks and sharing each container among tasks. SF-CUV consists of two phases: (i)task clustering and pre-virtual CPU (vCPU) allocation phase to derive an accurate scheduling priority, and (ii)task ordering and actual task reallocation phase. Experimental results obtained via simulation and in a real environment show that SF-CUV can utilize both vCPUs and containers with a shorter makespan compared with other approaches.

Benchmarking and Performance Evaluations on Various Configurations of Virtual Machine and Containers for Cloud-Based Scientific Workloads

Cloud computing manages system resources such as processing, storage, and networking by providing users with multiple virtual machines (VMs) as needed. It is one of the rapidly growing fields that come with huge computational power for scientific workloads. Currently, the scientific community is ready to work over the cloud as it is considered as a resource-rich paradigm. The traditional way of executing scientific workloads on cloud computing is by using virtual machines. However, the latest emerging concept of containerization is growing more rapidly and gained popularity because of its unique features. Containers are treated as lightweight as compared to virtual machines in cloud computing. In this regard, a few VMs/containers-associated problems of performance and throughput are encountered because of middleware technologies such as virtualization or containerization. In this paper, we introduce the configurations of VMs and containers for cloud-based scientific workloads in order to utilize the technologies to solve scientific problems and handle their workloads. This paper also tackles throughput and efficiency problems related to VMs and containers in the cloud environment and explores efficient resource provisioning by combining four unique methods: hyperthreading (HT), vCPU cores selection, vCPU affinity, and isolation of vCPUs. The HEPSCPEC06 benchmark suite is used to evaluate the throughput and efficiency of VMs and containers. The proposed solution is to implement four basic techniques to reduce the effect of virtualization and containerization. Additionally, these techniques are used to make virtual machines and containers more effective and powerful for scientific workloads. The results show that allowing hyperthreading, isolation of CPU cores, proper numbering, and allocation of vCPU cores can improve the throughput and performance of virtual machines and containers.

Diminishing Returns and Deep Learning for Adaptive CPU Resource Allocation of Containers

Containers provide a lightweight runtime environment for microservices applications while enabling better server utilization. Automatic optimal allocation of CPU pins to the containers serving specific workloads can help to minimize the completion time of jobs. Most of the existing state-of-the-art focused on building new efficient scheduling algorithms for placing the containers on the infrastructure, and the resources to the containers are allocated manually and statically. An automatic method to identify and allocate optimal CPU resources to the containers can help to improve the efficiency of the scheduling algorithms. In this article, we introduce a new deep learning-based approach to allocate optimal CPU resources to the containers automatically. Our approach uses the law of diminishing marginal returns to determine the optimal number of CPU pins for containers to gain maximum performance while maximizing the number of concurrent jobs. The proposed method is evaluated using real workloads on a Docker-based containerized infrastructure. The results demonstrate the effectiveness of the proposed solution in reducing the completion time of the jobs by 23% to 74% compared to commonly used static CPU allocation methods.

Cooperative Game-Based Virtual Machine Resource Allocation Algorithms in Cloud Data Centers

With the growing demand of cloud services, cloud data centers (CDCs) can provide flexible resource provisioning in order to accommodate the workload demand. In CDCs, the virtual machine (VM) resource allocation problem is an important and challenging issue to provide efficient infrastructure services. In this paper, we propose a unified resource allocation scheme for VMs in the CDC system. To provide a fair-efficient solution, we concentrate on the basic concept of Shapley value and adopt its variations to effectively allocate CDC resources. Based on the characteristics of value solutions, we develop novel CPU, memory, storage, and bandwidth resource allocation algorithms. To practically implement our algorithms, application types are assumed as cooperative game players, and different value solutions are applied to optimize the resource utilization. Therefore, our four resource allocation algorithms are jointly combined as a novel fourfold game model and take various benefits in a rational way through the cascade interactions while solving comprehensively some control issues. To ensure the growing demand of cloud services, this feature can leverage the full synergy of different value solutions. To check the effectiveness and superiority of our proposed scheme, we conduct extensive simulations. The simulation results show that our algorithms have significant performance improvement compared to the existing state-of-the-art protocols. Finally, we summarize our cooperative game-based approach and discuss possible major research issues for the future challenges about the cloud-assisted DC resource allocation paradigm.

Efficient Privacy Preserving Data Collection and Computation Offloading for Fog-Assisted IoT

The property of performing data processing near the source of data (i.e., at the edge of the network) enables fog computing that can effectively reduce computation latency, bandwidth and energy consumption, especially for big data network scenarios. For the sake of achieving efficient and secure big sensory data collection in fog-assisted Internet of Things (IoT), this paper proposes an efficient privacy preserving data collection and computation offloading scheme. In the proposed scheme, first, the designed layer-aware fog computing architecture provides effective support for efficient and secure data collection and fog computation offloading. Then the proposed sampling perturbation encryption method protects data privacy against eavesdroppers and active attackers without sacrificing data correlation, and it also facilitates the simultaneous execution of decrypting and decompressing operations on encrypted sampling data. Furthermore, the developed data processing method at fog nodes reduces the amount of redundant data transmissions significantly, and the formulated optimization model for the measurement matrix ensures the high precision of data reconstruction at the end user. Particularly, a completion time minimization problem is formulated for fog computation offloading, and an efficient offloading decision algorithm is developed to find the minimum completion time by determining the optimal offloading proportion with joint optimal allocation of local CPU, external CPU and channel bandwidth resources. Finally, the illustrative results reveal that the proposed scheme is an efficient data collection and computation offloading scheme with a strong privacy preservation property. For example, when the temporal compression ratio is 0.5, the redundant data can be reduced by 65 percent at fog node with a low relative recovery error 0.0139. At the same time when the task size is 9 Mb, the completion time of compression computation task at fog node can be reduced by 14.6 percent compared with other computation offloading method.

Chronological and exponential based Lion optimisation for optimal resource allocation in cloud

Cloud computing is a service-oriented architecture, which has a pool of resources. This paper introduces the resource allocation scheme for cloud computing by introducing an optimisation algorithm named Chronological E-Lion algorithm. The proposed Chronological E-Lion algorithm is developed by integrating the chronological concept to the EWMA-based Lion algorithm. The fitness function of the proposed Chronological E-Lion algorithm considers various parameters, like cost, profit, CPU allocation, memory allocation, MIPS, and frequency scaling, for optimally allocating the resources. The performance of the proposed method is analysed using three different problem instances based on the evaluation metrics, profit, CPU allocation rate, and memory allocation rate. From the simulation results, it can be concluded that the proposed Chronological E-Lion algorithm achieved improved performance with the values of 45.93, 0.16, and 0.0093, for profit, CPU utilisation rate, and memory utilisation rate.

Research and implementation on high-speed transmission performance optimization technology of ten gigabit firewall UDP multicast

Under the development trend of high throughput, large capacity and strong time effective data security transmission of the second generation data relay system in China, the high-performance processing requirements for the firewall of the backbone network security protection equipment are constantly improving. Focusing on the characteristics of the second generation data relay system, the key technologies of the transmission processing of the 10 Gigabit firewall based on the x86 architecture for different data flows are researched, the optimization design of the CPU allocation and scheduling mode, the function judgment mechanism of the network card characteristics and the kernel state write operation function of the 10 Gigabit firewall are completed. The test results show that the optimized 10 Gigabit firewall gives full play to its maximum transmission performance, and provides a better security transmission service guarantee for the integrated data relay users.

Energy efficient partition allocation in mixed-criticality systems.

This paper addresses the problem of energy management of mixed criticality applications in a multi-core partitioned architecture. Instead of focusing on new scheduling algorithms to adjust frequency in order to save energy, we propose a partition to CPU allocation that takes into account not only the different frequencies at which the CPU can operate but the level of criticality of the partitions. The goal is to provide a set of pre-calculated allocations, called profiles, so at run time the system can switch to different modes depending on the battery level. These profiles achieve different levels of energy saving and performance applying different strategies. We also present a comparison in terms of energy saving of the most used bin-packing algorithms for partition allocation. As this is an heuristic, it is not possible to ensure that our results involve the minimum energy consumption. For this reason, we also provide a comparison with a exact method, such as constraint programming.

D-Simplexed: Adaptive Delaunay Triangulation for Performance Modeling and Prediction on Big Data Analytics

Big Data processing systems (e.g., Spark) have a number of resource configuration parameters, such as memory size, CPU allocation, and the number of running nodes. Regular users and even expert administrators struggle to understand the mutual relation between different parameter configurations and the overall performance of the system. In this paper, we address this challenge by proposing a performance prediction framework, called d-Simplexed, to build performance models with varied configurable parameters on Spark. We take inspiration from the field of Computational Geometry to construct a d-dimensional mesh using Delaunay Triangulation over a selected set of features. From this mesh, we predict execution time for various feature configurations. To minimize the time and resources in building a bootstrap model with a large number of configuration values, we propose an adaptive sampling technique to allow us to collect as few training points as required. Our evaluation on a cluster of computers using WordCount, PageRank, Kmeans, and Join workloads in HiBench benchmarking suites shows that we can achieve less than 5% error rate for estimation accuracy by sampling less than 1% of data.

Analysis of the allocation of classes, threads and CPU used in embedded systems for Java applications

In order to analyze the volume of classes and threads allocated by Java applications, as well as the CPU used in embedded systems, we performed a comparative study to follow the behavior of several simple applications of different categories and in two VMs. different. After collecting data through monitoring tools, we found that with the VMZ more classes and threads are created, and more CPU is consumed, so more collections are made to free up memory space. This is due to the fact that VMZ is based on Oracle’s Open JDK, it takes a little more memory and CPU to load all the libraries used.

Energy efficient partition allocation in partitioned systems

This paper addresses the problem of energy management of applications in a multi-core partitioned architecture. Instead of focusing on new scheduling algorithms to adjust frequency in order to save energy, we propose a partition to CPU allocation that takes into account the different frequencies at which the CPU can operate. The goal of this paper is to provide a set of solutions to energy minimization problem. Each solution will supply feasible workload’s allocation to cores with a different energy level and system utilization. We also present a comparison in terms of energy saving of the most used bin-packing algorithms for partition allocation.

Provenance-aware optimization of workload for distributed data production

Distributed data processing in High Energy and Nuclear Physics (HENP) is a prominent example of big data analysis. Having petabytes of data being processed at tens of computational sites with thousands of CPUs, standard job scheduling approaches either do not address well the problem complexity or are dedicated to one specific aspect of the problem only (CPU, network or storage). Previously we have developed a new job scheduling approach dedicated to distributed data production – an essential part of data processing in HENP (preprocessing in big data terminology). In this contribution, we discuss the load balancing with multiple data sources and data replication, present recent improvements made to our planner and provide results of simulations which demonstrate the advantage against standard scheduling policies for the new use case. Multi-source or provenance is common in computing models of many applications whereas the data may be copied to several destinations. The initial input data set would hence be already partially replicated to multiple locations and the task of the scheduler is to maximize overall computational throughput considering possible data movements and CPU allocation. The studies have shown that our approach can provide a significant gain in overall computational performance in a wide scope of simulations considering realistic size of computational Grid and various input data distribution.