关于Linux内核可抢占性方法研究与实现

标准Linux内核是不能被抢占的,致使调度延迟较大,这是导致Linux系统实时性不强的主要原因,对Linux内核不可抢占性进行了深入分析,阐述了两种降低调度延迟的方案：低延迟方案和内核抢占式方案,并对这两种方案进行了测试与分析。     

云环境下基于多属性层次分析的虚拟机部署与调度策略

针对云计算中物理服务器间的负载不均问题,提出一种基于多属性层次分析的虚拟机部署与调度策略。该算法将虚拟机按照资源的需求特点进行分类,主要由两方面构成:在虚拟机部署时,对虚拟机的资源进行热点分析并对其重要程度进行量化,根据量化后的权向量以及服务器资源的使用记录对各个服务器进行预测评价,选择最佳服务器进行部署;在虚拟机调度时,获得运行在超载服务器上的各个虚拟机的权向量,并按照一定次序对未超载服务器进行评价,查找是否有更适合的服务器,从而降低超负荷服务器的负载。与同类算法相比,该算法不仅实现了服务器各项资源的优化配置,而且降低了动态负载平衡导致的整体损耗。实验结果表明,当按同一次序在5台物理服务器上申请20台资源需求不等的虚拟机时,该算法到达平衡状态需要的平均动态迁移次数比随机均衡算法减少了80%,同时进入平衡状态后,各服务器的各项资源使用情况也更趋于平衡。     

数据中心的网络虚拟化方案研究

为解决数据中心多网络设备、多网络端口的问题,采用IRF将多台网络设备进行连接,“横向整合”起来组成一个“联合设备”,实现跨设备链路聚合,增加带宽并提高链路可靠性.为解决数据中心各个虚拟机的安全性问题,在虚拟机网络内部采用PVLAN技术隔离各个虚拟机,提高网络的安全性.将两种方案应用于实际的校园数据中心网络建设中.测试结果表明,该方案能扩展网络端口数量和交换能力、增强网络的可靠性和提高网络的安全性.     

VMware虚拟机在网络实验与教学中的应用

本文介绍了用VMware虚拟机软件构建虚拟机操作系统的方法。运用虚拟机,可在一台计算机中运行真实操作系统的同时运行多个虚拟机,并可模拟出一个局域网网络环境,极大地方便了网络实验与教学的开展。     

基于平均负载和空闲内存税率的虚拟机内存优化

提出了根据平均负载对内存动态按需调整和利用空闲内存税率在虚拟机间均衡内存分配相结合的优化方案。当内存资源充足时,通过平均负载预测虚拟机内存的需求,根据需求分配内存大小;当内存资源紧张时,从未完全使用内存的虚拟机中根据空闲内存税率回收部分内存,实现在虚拟机间内存的均衡分配。实验证明本方案的系统对访存密集型负载的标准测试程序的性能有很大提高,在单个虚拟机性能最多损失6.7%的前提下,所有虚拟机的平均性能提高了30.6%,说明了它的有效性。     

固定优先级延迟抢占分层调度

复杂实时系统常采用资源分区隔离软件子系统,分区结构的系统包含分区级和任务级2层调度。抢占需要消耗系统资源,过多地抢占会降低系统效率。针对该问题,文章提出了延迟抢占分区模型,在分区中设置不可抢占区,保证系统可调度性的同时减少了大量不必要抢占;建立了延迟抢占分区模型的可调度性判定条件,并给出了分区设计算法。仿真结果表明,延迟抢占分区可以显著减少运行中的抢占次数。     

改善计算机实验室实验能力的几种方法

介绍了应用型地方本科院校计算机实验室的现状,做了网络存储体系、集群与负载平衡、虚拟机与仿真器等技术的应用研究。结合计算机实验室网络环境和设备性能差的实际,提出了利用NAS网络存储技术、负载均衡技术、虚拟机与仿真器等"虚拟"技术优化改善计算机实验室网络系统性能的几种方法,旨在探索易用、可靠且廉价的实验室网络服务系统优化方案,提升计算机实验室的实验支持能力,提高实验效率。     

基于猫群优化算法的云计算虚拟机资源负载均衡调度

为了提高虚拟机资源调度的利用率, 实现虚拟机资源合理调度, 提出一种基于猫群优化算法的虚拟机资源调度优化方法. 首先根据虚拟机资源调度优化目标构建数学模型; 然后综合考虑最短时间与最优负载构建猫群优化算法的适应度函数, 并通过模拟猫的日常行为实现虚拟机资源调度最优方案的寻优; 最后在CloudSim平台上对该算法的有效性进行测试. 测试结果表明, 该算法能获得更优的虚拟机资源调度方案, 保证了虚拟机资源的负载均衡, 可以满足用户需求的偏好性.     

光接入网中低延迟高能效动态带宽分配算法研究

巨大的能源消耗以及高延迟已经成为阻碍无源光网络进一步发展的主要困难.为了解决这个问题,绿色动态带宽分配算法最近被广泛地研究.然而,这些所提出来的方案并不能在降低能耗的同时满足低延迟的要求.在本文中,一个高能效低延迟的动态带宽分配方案被提出,称之为"组合配对动态带宽分配算法"(Pair-Wise Combination,PWC).本文所提出的PWC动态带宽分配算法能够动态地改变轮询次序,以压缩周期长度,提高了延迟性能.不仅如此,该方案在同时考虑了上、下行数据传输的情况下,还能提高无源光网络的能耗效率.仿真结果表明,该方案能够极大地降低能耗,同时还能有效地降低业务延迟.仿真结果表明,在光网络单元的个数为16,上行网络负载为0.3时,PWC方案下的上行延迟为1.18ms,节能效率为91.1%;而与之对比的ECS能耗节约方案的上行延迟为2.33ms,节能效率为89%.提出的PWC方案优于已有的ECS节能方案.     

基于Remus的双机热备份优化机制研究

双机热备技术是虚拟化系统提高其高可用性的一种可靠的解决方案。双机热备技术一般都采用不断生成检查点的方法,将主节点上实时的状态更新传送到备份节点上面以实现主备份节点之间的状态同步。该系统在热备过程中如果遇到内存密集型应用时,传统的检查点技术会造成带宽的延迟,进而影响虚拟机双机热备的高可用性,或者在热备过程中心跳线失效而导致系统对主备虚拟机状态发生误判,从而导致系统不能正常运行。基于Remus系统的双机热备方式,提出了两种优化方案:第一是增量检查点压缩机制,第二是客户端辅助判断主虚拟机状态机制。实验测试表明,基于XOR-RLE的增量检查点压缩算法有效降低了内存密集型应用导致的带宽延迟,同时也验证了面向客户端的热备机制可大幅减少热备过程中系统误判的产生。     

VirtCO:Joint Coflow Scheduling and Virtual Machine Placement in Cloud Data Centers

Cloud data centers, such as Amazon EC2, host myriad big data applications using Virtual Machines(VMs). As these applications are communication-intensive, optimizing network transfer between VMs is critical to the performance of these applications and network utilization of data centers. Previous studies have addressed this issue by scheduling network flows with coflow semantics or optimizing VM placement with traffic considerations.However, coflow scheduling and VM placement have been conducted orthogonally. In fact, these two mechanisms are mutually dependent, and optimizing these two complementary degrees of freedom independently turns out to be suboptimal. In this paper, we present VirtCO, a practical framework that jointly schedules coflows and places VMs ahead of VM launch to optimize the overall performance of data center applications. We model the joint coflow scheduling and VM placement optimization problem, and propose effective heuristics for solving it. We further implement VirtCO with OpenStack and deploy it in a testbed environment. Extensive evaluation of real-world traces shows that compared with state-of-the-art solutions, VirtCO greatly reduces the average coflow completion time by up to 36.5%. This new framework is also compatible with and readily deployable within existing data center architectures.     

FlexCore: Dynamic Virtual Machine Scheduling Using VCPU Ballooning

As multi-core processors become the de-facto configuration in modern computers, the adoption of SMP Virtual Machines(VMs) has been increasing, allowing for more efficient use of computing resources. However,because of existence of schedulers in both the hypervisor and the guest VMs, this creates a new research problem,viz., double scheduling. Although double scheduling may cause many issues including lock-holder preemption,v CPU stacking, CPU fragmentation, and priority inversion, prior approaches have either introduced new problems and/or addressed the problem incompletely. In this paper, we describe the design and implementation of Flex Core,a new scheduling scheme using v CPU ballooning, which dynamically adjusts the number of v CPUs of a VM at runtime. This essentially eliminates unnecessary scheduling in the hypervisor layer, and thus, boosts performance significantly. An evaluation using a complete KVM-based implementation shows that the average performance improvement for PARSEC applications on a 12-core Intel machine is approximately 52.9%, ranging from 35.4% to79.6%.     

基于资源动态变化的桌面Linux交互性能测试方法

传统的性能测试方法或者仅关心操作系统或CPU的局部吞吐量性能,或者仅关注应用软件的使用性能,不能反映L inux系统对桌面交互应用的影响。该文提出了基于动态变化的系统资源环境,利用事件处理延迟时间对L inux桌面应用进行交互式性能测试的方法。建立了桌面应用的静态模型,改进了已有的动态模型,完成了在不同的内存负载下应用软件启动交互性能测试。基于该方法的测试结果表明L inux桌面应用交互性能在软件启动方面不佳,在桌面应用环境下的sw ap效率较低。由于L inux体系结构和算法源自传统U n ix,先天比较适合服务器。因而L inux要成为性能卓越的桌面操作系统,除了应用软件自身需要改进外,系统资源的管理调度也需要优化。     

vCerberus: A DRTM system based on virtualization technology

This paper presents vCerberus, a novel hypervisor to provide trusted and isolated code execution within virtual domains. vCerberus is considerably tiny, while allowing secure sensitive codes to be executed in an isolated circumstance from the virtual domain, and can be attested by a remote party in an efficient way. These properties will be guaranteed even if the guest operating system is malicious. This protects the secure sensitive codes against the malicious codes in the Guest OS, e.g., the kernel rootkits. We present an approach to dynamically measure and isolate the launch environment on the virtual machines based on the para-virtualization technology and a novel virtualization of trusted platform module (TPM). Our performance experiment result shows that the overhead introduced by vCerberus is minimized; the performance of the launch environment in vCerberus is as competitive as the guest OS running on mainstream hypervisors.     

Efficient Multi-Tenant Virtual Machine Allocation in Cloud Data Centers

Virtual Machine(VM) allocation for multiple tenants is an important and challenging problem to provide efficient infrastructure services in cloud data centers. Tenants run applications on their allocated VMs, and the network distance between a tenant's VMs may considerably impact the tenant's Quality of Service(Qo S). In this study, we define and formulate the multi-tenant VM allocation problem in cloud data centers, considering the VM requirements of different tenants, and introducing the allocation goal of minimizing the sum of the VMs' network diameters of all tenants. Then, we propose a Layered Progressive resource allocation algorithm for multi-tenant cloud data centers based on the Multiple Knapsack Problem(LP-MKP). The LP-MKP algorithm uses a multi-stage layered progressive method for multi-tenant VM allocation and efficiently handles unprocessed tenants at each stage. This reduces resource fragmentation in cloud data centers, decreases the differences in the Qo S among tenants, and improves tenants' overall Qo S in cloud data centers. We perform experiments to evaluate the LP-MKP algorithm and demonstrate that it can provide significant gains over other allocation algorithms.     

跨域虚拟网络环境下虚拟机Live的迁移机制

针对跨域虚拟网络环境下虚拟机的在线迁移机制, 设计了支持虚拟机跨域通信的虚拟网络路由协议和控制虚拟机在线迁移的路由更新协议, 以支持虚拟机的跨域动态管理, 并基于流行虚拟化环境Xen, 完成了原型实现, 从而解决了虚拟机跨域的在线迁移问题, 实现了利用广域网络环境搭建动态虚拟化平台.     

Discovering Attack Path Oriented-IP Traceback

The technique of IP traceback may effectively block DOS (Denial Of Service) and meet the requirement of the computer forensic, but its accuracy depends upon that condition that each node in the Internet must support IP packet marking or detected agents. So far, this requirement is not satisfied. On the basis of traditional traeeroute, this paper investigates the efficiency of diseovering path methods from aspects of the size and order of detecting packets, and the length of paths. It points out that the size of padding in probed packets has a slight effect on discovering latency, and the latency with the method of bulk sending-receiving is much smaller than one with the traditional tracemute. Moreover, the loss rate of packets with the technique of TTL (Time To Live) which increases monotonously is less than that with the technique of TTL which decreases monotonously. Lastly,OS (Operating System) passive fingerprint is used as heuristic to predict the length of the discovered path so as to reduce disturbance in network traffic.     

城市交通网络优化研究与进展

城市交通网络优化的重要性越来越明显,目前对城市交通网络优化已取得很大的进展。综述了城市交通网络优化的典型方法研究,对其优化算法进行了详细的分析比较,对进化多目标优化算法进行了深入的研究,给出其研究的现状及其前景。     

Applying File Information to Block-Level Content Addressable Storage

Content addressable storage (CAS) is a promising technology for improving storage efficiency as well as access throughput.Currently,many CAS products are implemented on the block level,which results in loss of file information.Thus,some sophisticated optimizations cannot be achieved,such as accurate fileprefetching.This paper presents a file-aware block-level storage system combined with the CAS function.In contrast with some existing file-level CAS,this system is transparent to upper-level applications,including the operating system and the file system.These features are achieved by using smart-disk technologies to help the storage system to learn the file-system layout.A prototype was implemented on an open-source virtual machine (VM) with the guest operating system being Windows XP.Tests show that this combination significantly reduces the size of the VM image file and improves the storage performance by discarding unused blocks and using a simple file-level prefetching strategy.     

A less resource-consumed security architecture on cloud platform

Traditional security framework in cloud platform usually brings self-vulnerability and considerable additional resource consumption. To solve these problems, we propose an external processes monitoring architecture for current popular cloud platform OpenStack with kernel-based virtual machine (KVM). With this architecture, we can monitor all active processes in online virtual machine (VMs) and scan them for their potential maliciousness in OpenStack with no agent, and can also detect hidden processes in offline VMs’ memory snapshots and notice the user to decide whether to kill them when VMs become active. Analysis and experimental results show that our architecture is able to reduce consumption of CPU, memory and bandwidth in cloud platform and can detect viruses and hidden processes effectively in VMs.