Shared System Resources Research Articles

REDB: Real-time enhancement of Docker containers via memory bank partitioning in multicore systems

Docker is a lightweight virtualization technology adopted by numerous companies to develop, deploy, and manage applications. However, All Docker containers running on the same system share system resources, leading to performance interference among them. This interference adversely affects the predictability of program response times within the containers. Thus, shared resource isolation between containers has become an important issue. Efforts have been made to improve isolation across various dimensions, such as file systems, I/O, etc. However, consideration of the effect of memory bank interference remains open. We propose a novel approach, REDB, as an effective solution to achieve memory isolation among containers, thereby enhancing the real-time performance of Docker containers. The fundamental strategy is partitioning DRAM banks and allocating specific banks to particular containers. The results reveal that the slowdown ratios of SPEC CPU2006 benchmarks show an average improvement of 7.7% (up to 18.4%) for Docker with REDB. We utilize the Cyclictest tool to characterize the Docker container latency, and our evaluations indicate that the maximum latency, a critical indicator of real-time performance, decreases significantly from 564 us for Docker without bank partitioning to just 26 us for Docker with REDB, resulting in an impressive reduction of 95.3%.

Fairness-aware data offloading of IoT applications enabled by heterogeneous UAVs

With the widespread application of IoT devices, some new scenarios with insufficient coverage of communication infrastructure have arisen, such as wildlife habit monitoring. For these IoT applications, how to efficiently backhaul data collected by IoT devices has become a key technology. As a new data collecting mode for environments lacking communication infrastructure, UAV-enabled data offloading has attracted increasing research interest. Nevertheless, the fairness of data offloading is rarely studied, which directly influences the quality of service. Therefore, we investigate the fairness-aware task scheduling for data offloading enabled by heterogeneous UAVs. To reduce the uncertainty of user status information caused by poor communication, a service time related data arrival rate estimation model is proposed. The fairness-aware heterogeneous UAV-enabled data offloading model is proposed to ensure that all users share system resources fairly. Then, we creatively propose a dynamic incentive-based coordinate descent optimization framework-DISCO, which can progressively improve resource utilization while maximizing service fairness. Besides, we theoretically analyze and experimentally demonstrate its convergence and low time complexity. The performance of DISCO is verified by a series of simulation experiments. Compared with four baseline algorithms, DISCO shows distinct advantages in terms of service fairness, energy efficiency, adaptability and data throughput.

Evaluating Controlled Memory Request Injection for Efficient Bandwidth Utilization and Predictable Execution in Heterogeneous SoCs

High-performance embedded platforms are increasingly adopting heterogeneous systems-on-chip (HeSoC) that couple multi-core CPUs with accelerators such as GPU, FPGA, or AI engines. Adopting HeSoCs in the context of real-time workloads is not immediately possible, though, as contention on shared resources like the memory hierarchy—and in particular the main memory (DRAM)—causes unpredictable latency increase. To tackle this problem, both the research community and certification authorities mandate (i) that accesses from parallel threads to the shared system resources (typically, main memory) happen in a mutually exclusive manner by design, or (ii) that per-thread bandwidth regulation is enforced. Such arbitration schemes provide timing guarantees, but make poor use of the memory bandwidth available in a modern HeSoC. Controlled Memory Request Injection (CMRI) is a recently-proposed bandwidth limitation concept that builds on top of a mutually-exclusive schedule but still allows the threads currently not entitled to access memory to use as much of the unused bandwidth as possible without losing the timing guarantee. CMRI has been discussed in the context of a multi-core CPU, but the same principle applies also to a more complex system such as an HeSoC. In this article, we introduce two CMRI schemes suitable for HeSoCs: Voluntary Throttling via code refactoring and Bandwidth Regulation via dynamic throttling. We extensively characterize a proof-of-concept incarnation of both schemes on two HeSoCs: an NVIDIA Tegra TX2 and a Xilinx UltraScale+, highlighting the benefits and the costs of CMRI for synthetic workloads that model worst-case DRAM access. We also test the effectiveness of CMRI with real benchmarks, studying the effect of interference among the host CPU and the accelerators.

Effect of Hyper-Threading in Latency-Critical Multithreaded Cloud Applications and Utilization Analysis of the Major System Resources

Multithreaded latency-critical applications represent an important subset of workloads running on public cloud systems. Most of these systems deploy powerful computing servers including Intel Hyper-Threading processors. Understanding how performance is affected by the consumption of the main system resources is a major concern for cloud providers in order to devise virtualization strategies that improve the system efficiency. With this aim, this paper first characterizes the impact of QPS on tail latency, analyzing different scenarios varying the number of threads and the thread-to-core allocation (single-task and multi-task execution) policy. The characterization study reveals that the performance of some applications does not scale with the number of threads, and the performance of some others is insensitive to the Hyper-Threading technology, so they can be allocated in less physical cores and improve system utilization. Identifying these applications, however, at run-time is challenging. Despite identifying these applications at run-time is challenging, this paper shows that they can be successfully detected at run-time by analyzing the utilization trend of the major system resources. In addition to CPU, we have also studied how assigning the share of each application of other major shared system resources impacts on performance. We outline considerations cloud providers should take into account to improve performance and resource utilization.

An Associative Optimizing Method on Reliability and Cost in Clouds

Cloud computing enables users to use shared system resources in an efficient pay-as-you-go manner. However, the reliability of cloud computing is a challenging proposition. Cloud users cannot improve the reliability of their cloud environment from the hardware and system level. On the other hand, due to the cost and complexity of the system, improving the reliability of specific users using practical methods is not straightforward for the operators of cloud systems. In this paper, we attempt to optimize the reliability of the cloud system by using the correlation between cost and reliability. We conduct a comprehensive and detailed analysis of the reliability of clouds, extract vital features that can be used to improve system reliability and consider cost constraints. We propose the reliability model and virtual machine (VM) provisioning/request model; based on this model, we propose an SLA-oriented reliability assurance scheme to continuously optimize the reliability of clouds. The experimental results not only indicate the validity of the model and schemes proposed in this paper but also provide a new perspective for the continuous optimization of cloud system reliability.

Techniques and Analysis for Mixed-criticality Scheduling with Mode-dependent Server Execution Budgets

In mixed-criticality systems, tasks of different criticality share system resources, mainly to reduce cost. Cost is further reduced by using adaptive mode-based scheduling arrangements, such as Vestal’s model, to improve resource efficiency, while guaranteeing schedulability of critical functionality. To simplify safety certification, servers are often used to provide temporal isolation between tasks. In its simplest form, a server is a periodically recurring time window, in which some tasks are scheduled. A server’s computational requirements may greatly vary in different modes, although state-of-the-art techniques and schedulability tests do not allow different budgets to be used by a server in different modes. This results in a single conservative execution budget for all modes, increasing system cost. The goal of this paper is to reduce the cost of mixed-criticality systems through three main contributions: (i) a scheduling arrangement for uniprocessor systems employing fixed-priority scheduling within periodic servers, whose budgets are dynamically adjusted at run-time in the event of a mode change, (ii) a new schedulability analysis for such systems, and (iii) heuristic algorithms for assigning budgets to servers in different modes and ordering the execution of the servers. Experiments with synthetic task sets demonstrate considerable improvements (up to 52.8%) in scheduling success ratio when using dynamic server budgets vs. static “one-size-fits-all-modes” budgets.

Applied On-Chip Machine Learning for Dynamic Resource Control in Multithreaded Processors

In this paper, we propose a machine learning algorithm to control instruction fetch bandwidth in a simultaneous multithreaded CPU. In a simultaneous multithreaded CPU, multiple threads occupy pools of hardware resources in the same clock cycle. Under some conditions, one or more threads may undergo a period of inefficiency, e.g., a cache miss, thereby inefficiently using shared resources and degrading the performance of other threads. If these inefficiencies can be identified at runtime, the offending thread can be temporarily blocked from fetching new instructions into the pipeline and given time to recover from its inefficiency, and prevent the shared system resources from being wasted on a stalled thread. In this paper, we propose a machine learning approach to determine when a thread should be blocked from fetching new instructions. The model is trained offline and the parameters embedded in a CPU, which can be queried with runtime statistics to determine if a thread is running inefficiently and should be temporarily blocked from fetching. We propose two models: a simple linear model and a higher-capacity neural network. We test each model in a simulation environment and show that system performance can increase by up to 19% on average with a feasible implementation of the proposed algorithm.

Information Processing and Security Analysis of Shared System Resource Based Architectures

Background: Nowadays, service-oriented architectures and cloud-based infrastructures are widely used in manufacturing industries and IT organizations. These architectures and infrastructures are based on shared system resources. In some organizations, system resources like a printer, photocopy machines, and scanners are also shared among the members of the organization. The purpose of the proposed work is to model various types of shared system resources, shared system resources based architecture/infrastructure and analyze the model to identify the possible security risk associated with shared system resources and shared system resources based architecture/infrastructure. Design Approach: To model shared system resources and shared system resources based architecture/Infrastructure, Petri net and its variations are used. For security analysis of the Petri net based model of the shared system resource, Petri net algebra based concepts are applied. Results: The present paper successfully demonstrates that the proposed Petri net based modeling approach can be used for quantitative and qualitative security analysis of shared system resources and shared system resources based architecture/infrastructure. For quantitative analysis of security risk associated with shared system resources, information theoretic concepts are used. To demonstrate the effectiveness of the proposed method, case studies are also incorporated in the present paper. The proposed approach can take various security risk factors like timing analysis attack, information leakage due to confidentiality policy violation and power analysis attack into the consideration while analyzing the security of shared system resources in the industrial environment.

IOFollow: Improving the performance of VM live storage migration with IO following in the cloud

VM live migration becomes critical to deployment in the Cloud, as to enable fast and transparent workload rescheduling among unevenly utilized physical nodes, aimed at high performance and energy efficient utilization of computer server resources. Nevertheless, VM I/O intensity can significantly impact the performance of VM live storage migration due to contention for the shared disk bandwidth and system resources. Based on this observation, this paper proposes the IOFollow scheme to improve simultaneously the VM performance and migration performance. IOFollow mitigates the I/O interference between VM I/O requests and migration I/O requests, by scheduling the migration sequence according to the access pattern of VM I/O requests. In addition, it improves the cache management efficiency by exploiting the semantic information from the VMs and migration threads. Results obtained from trace-based experiments on a lightweight prototype implementation of IOFollow indicate that IOFollow system is highly competitive, improving both the VM performance and migration performance significantly when compared to existing design.

Dynamic Transaction Management for System Level Quality-of-Service in Mobile APs

Recent consumer devices with high-quality multimedia support heavily rely on high performance application processors, each of which contain many masters (or processing units) such as CPUs, GPUs, and DSPs connected by high-bandwidth interconnection networks and share the memory. Each master running multimedia applications requires a specific amount of bandwidth from system resources to provide quality-of-service (QoS) capability. However, it is sometimes difficult to satisfy such bandwidth requirement of a master due to unpredictable conflicts on limited shared system resources. This is a problem that needs to be addressed in consumer multimedia devices in order to provide seamless services within limited performance boundaries. In this paper, we propose a novel system-level QoS management scheme called dynamic transaction management (DTM) to address this anomaly. The proposed scheme collects the real-time bandwidth demand of masters, evaluates the gravity of their operations, and orchestrates their bandwidth consumption based on necessity. The evaluation results show that DTM effectively support bandwidth allocation by regulating the over-consumption of system resources by less urgent masters.

DroidAuditor: A framework for auditing covert communication on Android

SummaryExploitation of covert channels in smartphone operating systems may lead to furtive data transmission between applications with different permissions, which might threaten users' privacy. Restricting the access to shared system resources can effectively prevent the exploitation of known covert channels. However, it inevitably limits the normal usage of those resources. In this paper, we propose a general method that detects covert channel attack at runtime without impacting the accessibility of shared resources in the system. The main idea of the method is to track and audit the use of system resources known as potential covert channel variables and impose interferences on those channels to reduce their capacity once violations are detected. We implement a prototype framework, which is able to audit and interfere covert communication both in the application layer and in the native layer of Android. The experimental results demonstrate that our method can effectively reduce the data rate of user‐defined covert channels while the overhead is negligible.

Isoefficiency in Practice

Task-based programming offers an elegant way to express units of computation and the dependencies among them, making it easier to distribute the computational load evenly across multiple cores. However, this separation of problem decomposition and parallelism requires a sufficiently large input problem to achieve satisfactory efficiency on a given number of cores. Unfortunately, finding a good match between input size and core count usually requires significant experimentation, which is expensive and sometimes even impractical. In this paper, we propose an automated empirical method for finding the isoefficiency function of a task-based program, binding efficiency, core count, and the input size in one analytical expression. This allows the latter two to be adjusted according to given (realistic) efficiency objectives. Moreover, we not only find (i) the actual isoefficiency function but also (ii) the function one would yield if the program execution was free of resource contention and (iii) an upper bound that could only be reached if the program was able to maintain its average parallelism throughout its execution. The difference between the three helps to explain low efficiency, and in particular, it helps to differentiate between resource contention and structural conflicts related to task dependencies or scheduling. The insights gained can be used to co-design programs and shared system resources.

An efficient chaotic based PSO for earliness/tardiness optimization in a batch processing flow shop scheduling problem

The flow shop is a well-known class of manufacturing system for production process planning. The need for scheduling approaches arises from the requirement of most systems to implement more than one process at a moment. Batch processing is usually carried out to load balance and share system resources effectively and gain a desired quality of service level. A flow shop manufacturing problem with batch processors (BP) is discussed in current paper so as to minimize total penalty of earliness and tardiness. To address the problem, two improved discrete particle swarm optimization (PSO) algorithms are designed where most important properties of basic PSO on velocity of particles are enhanced. We also employ the attractive properties of logistic chaotic map within PSO so as to investigate the influence of chaos on search performance of BP flow shop problem. In order to investigate the suggested algorithms, a comprehensive computational study is carried out and performance of algorithms is compared with (1) a commercial optimization solver, (2) a well-known algorithm from PSO’s literature and (3) three algorithms from BP’s literature. The experimental results demonstrate the superiority of our algorithm against others.

Research of Access Control Models in Personal Networks

How to prevent illegal users from sharing system resources was one of the main purposes for MAGNET Security Group. This paper introduced some major access control models such as traditional access control models, role-based access control model (RBAC), task-based access control model (TBAC) and role-task-based access control model (T-RBAC). In the end, a feasible scheme PN_T-RBAC was proposed at the base of the T-RBAC model in existence, which was suitable for the coalition environment of personal networks.

An Efficient Scheduling Method for Grid Systems Based on a Hierarchical Stochastic Petri Net

This paper addresses the problem of resource scheduling in a grid computing environment. One of the main goals of grid computing is to share system resources among geographically dispersed users, and schedule resource requests in an efficient manner. Grid computing resources are distributed, heterogeneous, dynamic, and autonomous, which makes resource scheduling a complex problem. This paper proposes a new approach to resource scheduling in grid computing environments, the hierarchical stochastic Petri net (HSPN). The HSPN optimizes grid resource sharing, by categorizing resource requests in three layers, where each layer has special functions for receiving subtasks from, and delivering data to, the layer above or below. We compare the HSPN performance with the Min-min and Max-min resource scheduling algorithms. Our results show that the HSPN performs better than Max-min, but slightly underperforms Min-min.

Collecting Distributed Performance Data with Dataheap: Generating and Exploiting a Holistic System View

The task of performance analysis and optimization grows more and more challenging with the increasing scale and complexity of large computing systems. The need for a holistic system analysis becomes apparent when traditional approaches do not collect the information that is required to investigate performance penalties caused by shared system resources. We have developed a distributed approach that is able to collect and process performance data from shared system resources. We call our software implementation of this approach Dataheap and have integrated it with a traditional program tracing facility. In this paper we describe the needs that have driven this development as well as connections to related projects. Dataheap is based on a threaded server, distributed agents that collect performance data, a storage backend that makes use of different databases, and access libraries that allow external systems to retrieve current and historic performance data. The server subsequently processes incoming performance data and allows to create secondary metrics on the fly which helps to transform individual system characteristics to standard performance metrics. Finally, we briefly illustrate how this approach has enhanced our performance debugging capabilities as well as our research on energy effcient computing.

Analysis and modeling of service impacts on system activities, resource workloads and service performance on computer and network systems

Various services running on computer and network systems compete for shared system resources. Impacts of services on system activities, workloads and performance need to be understood, modeled and used in many system planning and control activities. Due to complex interactions of many system resources e.g., CPU, memory and network and sharing of system resources by various services running at the same time, it is challenging to uncover and model relations of services with their resource workloads and resulting service performance. This paper presents our methodology that uses statistical analysis techniques to analyze empirical data of computer and network dynamics and uncover significant variables of system activities, resource workloads and service performance that are affected by services. Statistical modeling techniques are also employed in our methodology to build quantitative models of service impacts on system resource workloads and service performance. The methodology is illustrated and tested on three services of voice data communication, motion detection, and data encryption.

A Novel User Authentication Scheme Based on QR-Code

User authentication is one of the fundamental procedures to ensure secure communications and share system resources over an insecure public network channel. Thus, a simple and efficient authentication mechanism is required for securing the network system in the real environment. In general, the password-based authentication mechanism provides the basic capability to prevent unauthorized access. Especially, the purpose of the one-time password is to make it more difficult to gain unauthorized access to restricted resources. Instead of using the password file as conventional authentication systems, many researchers have devoted to implement various one-time password schemes using smart cards, time-synchronized token or short message service in order to reduce the risk of tampering and maintenance cost. However, these schemes are impractical because of the far from ubiquitous hardware devices or the infrastructure requirements. To remedy these weaknesses, the attraction of the QR - code technique can be introduced into our one-time password authentication protocol. Not the same as before, the proposed scheme based on QR code not only eliminates the usage of the password verification table, but also is a cost effective solution since most internet users already have mobile phones. For this reason, instead of carrying around a separate hardware token for each security domain, the superiority of handiness benefit from the mobile phone makes our approach more practical and convenient.

Fair Adaptive Bandwidth and Subchannel Allocation in the WiMAX Uplink

In some modern communication systems, as it is the case of WiMAX, it has been decided to implement Demand Assignment Multiple Access (DAMA) solutions. End-users request transmission opportunities before accessing the system, which provides an efficient way to share system resources. In this paper, we briefly review the PHY and MAC layers of an OFDMA-based WiMAX system, and we propose to use a Network Utility Maximization (NUM) framework to formulate the DAMA strategy foreseen in the uplink of IEEE 802.16. Utility functions are chosen to achieve fair solutions attaining different degrees of fairness and to further support the QoS requirements of the services in the system. Moreover, since the standard allocates resources in a terminal basis but each terminal may support several services, we develop a new decomposition technique, the coupled-decompositions method, that obtains the optimal service flow allocation with a small number of iterations (the improvement is significant when compared to other known solutions). Furthermore, since the PHY layer in mobile WiMAX has the means to adapt the transport capacities of the links between the Base Station (BS) and the Subscriber Stations (SSs), the proposed PHY-MAC cross-layer design uses this extra degree of freedom in order to enhance the network utility.

System load model for the OFDMA network

In this letter we introduce our system load model for the orthogonal frequency division multiple access (OFDMA) network. We formulate the requirements to the system load model and present its definition. The system load model comprises the uplink load, the downlink load, the sector load, and the network load. We describe our approach to combine the time-frequency and power shared system resources in the OFDMA network