视频服务器存储子系统的I/O优化

视频服务器存储子系统的I／O性能决定了视频服务器的总体性能。本文提出的一种新的实时磁盘调度算法（LLF－Window)能有效地服务各种编码格式的视频流，并对传统的SCSI总线不均衡调度机制进行了改造，实验结果表明，新的磁盘调度算法和改造后的SCSI总线调度机制有效地改进了视频服务器存储子系统的I／O性能，保证了视频流的连续播放。     

多媒体服务器混合磁盘调度策略

基于多媒体服务器的性能要求，提出了一种自适应的混合磁盘调度策略DRT-window．它既能满足实时请求对实时性的要求，根据实时请求的截止期动态选择窗口大小；又能在其松弛度内尽努力(best-effort)地服务非实时请求，从而减少非实时请求的响应时间。DRT-window采用了两级层次调度方案：第一层为不同类型的请求采用各自适合的调度策略；第二层为混合请求调度嚣，混合调度第一层中的不同类型的请求。通过性能比较和理论证明，表明此混合磁盘调度策略能在保证实时请求无抖动执行的同时，尽量地减少非实时请求的响应时间。     

Disk scheduling in video editing systems

Modern video servers support both video-on-demand and nonlinear editing applications. Video-on-demand servers enable the user to view video clips or movies from a video database, while nonlinear editing systems enable the user to manipulate the content of the video database. Applications such as video and news editing systems require that the underlying storage server be able to concurrently record live broadcast information, modify prerecorded data, and broadcast an authored presentation. A multimedia storage server that efficiently supports such a diverse group of activities constitutes the focus of this study. A novel real-time disk scheduling algorithm is presented that treats both read and write requests in a homogeneous manner in order to ensure that their deadlines are met. Due to real-time demands of movie viewing, read requests have to be fulfilled within certain deadlines; otherwise, they are considered lost. Since the data to be written into disk is stored in main memory buffers, write requests can be postponed until critical read requests are processed. However, write requests still have to be processed within reasonable delays and without the possibility of indefinite postponement. This is due to the physical constraint of the limited size of the main memory write buffers. The new algorithm schedules both read and write requests appropriately, to minimize the amount of disk reads that do not meet their presentation deadlines, and to avoid indefinite postponement and large buffer sizes in the case of disk writes. Simulation results demonstrate that the proposed algorithm offers low violations of read deadlines, reduces waiting time for lower priority disk requests, and improves the throughput of the storage server by enhancing the utilization of available disk bandwidth     

Adaptive cycle management in soft real-time disk retrieval

The objective of this study is to determine the right cycle management policy to service periodic soft real-time disk retrieval. Cycle-based disk scheduling provides an effective way of exploiting the disk bandwidth and meeting the soft real-time requirements of individual I/O requests. It is widely used in real-time retrieval of multimedia data blocks. Interestingly, the issue of cycle management with respect to dynamically changing workloads has not been receiving proper attention despite its significant engineering implications on the system behavior. When cycle length remains constant regardless of varying I/O workload intensity, it may cause under-utilization of disk bandwidth capacity or unnecessarily long service startup latency. In this work, we present a novel cycle management policy which dynamically adapts to the varying workload. We develop pre-buffering policy which makes the adaptive cycle management policy robust against starvation. The proposed approach elaborately determines the cycle length and the respective buffer size for pre-buffering. Performance study reveals a number of valuable observations. Adaptive cycle length management with incremental pre-buffering exhibits superior performance to the other cycle management policies in startup latency, jitter and buffer requirement. It is found that servicing low playback rate contents such as video contents for 3G cellular network requires rather different treatment in disk subsystem capacity planning and call admission criteria because relatively significant fraction of I/O latency is taken up by plain disk overhead.     

基于层次化请求过滤的SonD无盘Windows

按需服务无盘Windows通过在Windows2K/XP内核中虚拟小型计算机系统接口(SCSI)设备,将SCSI设备的读写请求转化为网络磁盘的读写请求与服务器端通信,实现远程无盘启动Windows的软件解决方案。该技术有效地将存储资源和计算资源分离后动态结合,实现存储资源的统一管理和计算资源的合理分配。基于Windows的分层驱动模型,还提出了层次化请求过滤技术。     

Dynamic real-time scheduling strategies for interactive continuous media servers

In this paper, we propose and study a dynamic approach to schedule real-time requests in a video-on-demand (VOD) server. Providing quality of service in such servers requires uninterrupted and on-time retrieval of motion video data. VOD services and multimedia applications further require access to the storage devices to be shared among multiple concurrent streams. Most of the previous VOD scheduling approaches use limited run-time,0 information and thus cannot exploit the potential capacity of the system fully. Our approach improves throughput by making use of run-time information to relax admission control. It maintains excellent quality of service under varying playout rates by observing deadlines and by reallocating resources to guarantee continuous service. It also reduces start-up latency by beginning service as soon as it is detected that deadlines of all real-time requests will be met. We establish safe conditions for greedy admission, dynamic control of disk read sizes, fast initial service, and sporadic services. We conduct thorough simulations over a wide range of buffer capacities, load settings, and over varying playout rates to demonstrate the significant improvements in quality of service, throughput and start-up latency of our approach relative to a static approach.     

双头镜像磁盘的实时调度算法及性能评价

本文对双头镜像磁盘系统模型进行实时扩展,并提出了三种实时调度算法：最早截止期优先算法（ＥＤＦ）,可满足的最早截止期优先算法（Ｆ－ＥＤＦ）和忽视超时限请求算法（ＩＧＭ－ＥＤＦ）．这三种算法充分考虑了Ｉ／Ｏ请求的截止期限,使双头镜像磁盘系统能更好地满足实时需求．在进行了性能模拟后,发现实时调度算法比非实时算法能更好地满足实时Ｉ／Ｏ请求的时限要求．三种实时调度算法中,适用于硬实时应用的ＩＧＭ－ＥＤＦ的性能最好,Ｆ－ＥＤＦ算法的性能次之,它适用于软实时环境．     

Issues in the design of a storage server for video-on-demand

We examine issues related to the design of a storage server for video-on-demand (VOD) applications. The storage medium considered is magnetic disks or arrays of disks. We investigate disk scheduling policies, buffer management policies and I/O bus protocol issues. We derive the number of sessions that can be supported from a single disk or an array of disks and determine the amount of buffering required to support a given number of users. Furthermore, we propose a scheduling mechanism for disk accesses that significantly lowers the buffer-size requirements in the case of disk arrays. The buffer size required under the proposed scheme is independent of the number of disks in the array. This property allows for striping video content over a large number of disks to achieve higher concurrency in access to a particular video object. This enables the server to satisfy hundreds of independent requests to the same video object or to hundreds of different objects while storing only one copy of each video object. The reliability implications of striping content over a large number of disks are addressed and two solutions are proposed. Finally, we examine various policies for dealing with disk thermal calibration and the placement of videos on disks and disk arrays.     

Dynamic batching policies for an on-demand video server

In a video-on-demand environment, continuous delivery of video streams to the clients is guaranteed by sufficient reserved network and server resources. This leads to a hard limit on the number of streams that a video server can deliver. Multiple client requests for the same video can be served with a single disk I/O stream by sending (multicasting) the same data blocks to multiple clients (with the multicast facility, if present in the system). This is achieved by batching (grouping) requests for the same video that arrive within a short time. We explore the role of customer-waiting time and reneging behavior in selecting the video to be multicast. We show that a first come, first served (FCFS) policy that schedules the video with the longest outstanding request can perform better than the maximum queue length (MQL) policy that chooses the video with the maximum number of outstanding requests. Additionally, multicasting is better exploited by scheduling playback of the most popular videos at predetermined, regular intervals (hence, termed FCFS-). If user reneging can be reduced by guaranteeing that a maximum waiting time will not be exceeded, then performance of FCFS- is further improved by selecting the regular playback intervals as this maximum waiting time. For an empirical workload, we demonstrate a substantial reduction (of the order of 60%) in the required server capacity by batching.     

FAIRIO: A Throughput-oriented Algorithm for Differentiated I/O Performance

Providing differentiated service in a consolidated storage environment is a challenging task. To address this problem, we introduce FAIRIO, a cycle-based I/O scheduling algorithm that provides differentiated service to workloads concurrently accessing a consolidated RAID storage system. FAIRIO enforces proportional sharing of I/O service through fair scheduling of disk time. During each cycle of the algorithm, I/O requests are scheduled according to workload weights and disk-time utilization history. Experiments, which were driven by the I/O request streams of real and synthetic I/O benchmarks and run on a modified version of DiskSim, provide evidence of FAIRIO’s effectiveness and demonstrate that fair scheduling of disk time is key to achieving differentiated service in a RAID storage system. In particular, the experimental results show that, for a broad range of workload request types, sizes, and access characteristics, the algorithm provides differentiated storage throughput that is within 10% of being perfectly proportional to workload weights; and, it achieves this with little or no degradation of aggregate throughput. The core design concepts of FAIRIO, including service-time allocation and history-driven compensation, potentially can be used to design I/O scheduling algorithms that provide workloads with differentiated service in storage systems comprised of RAIDs, multiple RAIDs, SANs, and hypervisors for Clouds.     

The Analysis and Performance of Multi-Rate Service in Distributed Video-on-Demand Systems

In this paper, we develop an end-to-end analysis of a distributed Video-on-Demand (VoD) system that includes an integrated model of the server and the network subsystems with analysis of its impact on client operations. The VoD system provides service to a heterogeneous client base at multiple playback rates. A class-based service model is developed where an incoming video request can specify a playback rate at which the data is consumed on the client. Using an analytical model, admission control conditions at the server and the network are derived for multi-rate service. We also develop client buffer requirements in presence of network delay bounds and delay jitter bounds using the same integrated framework of server and network subsystems. Results from an extensive simulation show that request handling policies based on limited redirection of blocked requests to other resources perform better than load sharing policies. The results also show that downgrading the service for blocked requests to a lower bitrate improves VoD system performance considerably. Combining the downgrade option with restrictions on access to high bitrate request classes is a powerful tool for manipulating an incoming request mix into a workload that the VoD system can handle.     

Block I/O Scheduling on Storage Servers of Distributed File Systems

This paper presents a new scheme of I/O scheduling on storage servers of distributed/parallel file systems, for yielding better I/O performance. To this end, we first analyze read/write requests in the I/O queue of storage server (we name them block I/Os), by using our proposed technique of horizontal partition. Then, all block requests are supposed to be divided into multiple groups, on the basis of their offsets. This is to say, all requests related to the same chunk file will be grouped together, and then be satisfied within the same time slot between opening and closing the target chunk file on the storage server. As a result, the time resulted by completing block I/O requests can be significantly decreased, because of less file operations on the corresponding chunk files at the low-level file systems of server machines. Furthermore, we introduce an algorithm to rate a priority for each group of block I/O requests, and then the storage server dispatches groups of I/Os by following the priority order. Consequently, the applications having higher I/O priorities, e.g. they have less I/O operations and small size of involved data, can finish at a earlier time. We implement a prototype of this server-side scheduling in the PARTE file system, to demonstrate the feasibility and applicability of the proposed scheme. Experimental results show that the newly proposed scheme can achieve better I/O bandwidth and less I/O time, compared with the strategy of First Come First Served, as well as other server-side I/O scheduling approaches.     

基于透明计算模式的I/O Server的设计

设计并实现了一个基于透明计算模式的I/O Server系统，I/O Server和I/O Client是一个在透明计算环境下，支持多操作系统远程启动和运行的网络存储访问服务I/O Manager的2个软件模块，I/O Server工作在服务器端，I/O Client工作在客户端。在透明计算模式中，各客户机硬件与操作系统分离，用户需要的操作系统的应用程序存储在服务器端。在客户机启动时，I/O Server和启动协议将I/O Client下载到端系统上运行，然后I/O Client向I/O Server发出I/O请求，I/O Server对收到的I/O请求加以分析，进行优先级分类，在优先级分时轮转调度I/O请求、操作服务器上的虚拟硬盘文件，并通过预取和缓存策略减少磁盘I/O操作，将处理结果返回给客户端，支持操作系统的远程启动，并为系统运行时的各种请求提供服务。     

Real-time disk scanning for timely retrieval of continuous media objects

In recent years, demands for multimedia applications have rapidly grown with the advances in computing power and network technology. To fulfill the demands, it is crucial to establish the multimedia information systems supporting continuous media (CM) streams without hiccups. Many useful methods have been proposed in the past so that CM steams with VCR-quality can be supported. Although these earlier approaches can be used for the service of VCR-quality streams, they cannot provide a good system performance for the CM streams with various playback rates and rather short durations of playback. In the paper, we propose a new CM playback method that consists of bulk-scanning and an earliest-deadline-first style scheduling algorithm. Our proposed method provides both good response times and high I/O utilization using the efficient disk scheduling. In addition, our mechanism for admission control makes CM streams never experience hiccups until the ends of playback. Through experimental analyses, we show the performance advantages of the proposed method over the earlier methods.     

A new real time disk-scheduling method based on GSR algorithm

Disk scheduling has an important role in QOS guarantee of soft real-time environments such as video-on-demand and multimedia servers. Since now, some disk-scheduling algorithms have been proposed to schedule real-time disk requests. One of the most recent algorithms is global seek-optimizing real-time (GSR) that schedules the disk requests with different ready times by a global regrouping scheme. In the present paper, we propose a real-time disk-scheduling algorithm based on GSR that is called IGSR (improved GSR). IGSR creates the scan-groups of the requests and tries to find a good feasible schedule by optimized grouping with considering another chance for tasks that miss their deadlines at initial grouping. With regard to the admission policy of tasks, two different version of proposed method are presented: the first one has been designed for the case that all the disk requests available simultaneously and second one has been designed for the case that requests are admitted dynamically (GSR does not support the second one). It means that in the second case, the request queue may change when a task is running but in the first one it does not change. Simulation results showed IGSR outperformed GSR and some other related works in terms of maximum supportable streams, number of missed deadlines, and disk throughput.     

Scheduling on-demand data broadcast in mixed-type request environments

In many on-demand broadcast environments, there can be a mix of requests, in which some of the requests have real-time constraints, while other requests have no time constraints associated with them. We refer to such environments as mixed-type environments. Existing strategies for on-demand data in broadcast systems typically only consider how to minimize the wait time of the requests, while scheduling strategies for real-time requests typically only consider how to minimize the number of deadlines missed. How to satisfy both of these constraints is a challenging problem whose solution can benefit many applications. In this paper, we present an on-demand broadcast cost model that is more general than existing broadcast cost models because it considers both response time and number of deadlines missed. An analysis of the system is presented as a Markov decision process to ascertain the feasibility of an optimal policy. We propose two scheduling strategies for mixed-type broadcast systems that are based on our cost model: maximum paid cost first and maximum value gained first. The simulation results show that both of our strategies always achieve the best result, when compared to existing broadcast strategies, for varying request arrival rates, real-time to non-real-time request ratios, missed deadline weight values, wait-time bounds on the non-real-time requests, and varying broadcast rates.     

影响多媒体服务器性能的关键因素研究

在构建大规模视频服务系统时 ,基于层次型多服务器群的体系结构在吞吐率、可扩展性、经济性等方面都有其突出的优势 ,尤其适合于在因特网上的应用 .但是 ,要充分发挥和提高视频服务系统的性能 ,还要针对一些主要的瓶颈(如服务器磁盘 I/ O带宽与网络带宽 ) ,解决好一系列的问题 .本文分析了影响多媒体视频服务器性能的一些主要因素 ,如视频服务器的体系结构、服务器与客户端之间的数据传送方式、媒体数据在视频服务器存储子系统中的分布与放置方式、对磁盘访问请求的调度、单服务器中的缓存及多服务器间协同缓存的管理、接入控制策略、流调度策略等 ,这些因素对视频服务器的性能与吞吐率有着极大的影响 .本文还介绍了一些适用于大规模视频服务系统的性能优化技术 ,如广播、批处理等流调度策略 .在构建视频服务器系统时 ,只有综合考虑这些因素 ,才能真正提高服务器乃至整个视频服务系统的吞吐率 ,并较好地满足客户的 Qo S要求     

一种新颖的带模糊截止时限的磁盘调度算法

设计了一种新的基于截止时限的磁盘调度算法，该算法支持带多优先级的请求。对于某些实时要求，其截止时限是不确定的或者不精确的，该算法采用模糊集来描述这类不确定性，模糊截止时限的隶属度函数表示对请求完成时间的满意程度。调度的目的是最优的指定优先级，使得截止时限的满意程度最大化。根据请求截止时限的不同，把满意程度划分为若干连续的区间。在每个不同的区间内，每个请求都对应有修正的截止时限，把请求按照其修正的截止时限非减的顺序分配优先级，才能实现请求优先级的最优配置。仿真结果表明该算法能有效的分配请求的优先级，降低请求的丢失率，保证了更多的请求得到满足。     

Multicast Pull Scheduling: When Fairness Is Fine

We investigate server scheduling policies to minimize average user perceived latency in pull-based client-server systems (systems where multiple clients request data from a server) where the server answers requests on a multicast/ broadcast channel. We first show that there is no O(1) -competitive algorithm for this problem. We then give a method to convert any nonclairvoyant unicast scheduling algorithm A to nonclairvoyant multicast scheduling algorithm B . We show that if A works well, when jobs can have parallel and sequential phases, then B works well if it is given twice the resources. More formally, if A is an s -speed c -approximation unicast algorithm, then its counterpart algorithm B is a 2s -speed c -approximation multicast algorithm. It is already known [5] that Equi-partition, which devotes an equal amount of processing power to each job, is a (2 + ε) -speed O(1 + 1/ε) -approximation algorithm for unicast scheduling of such jobs. Hence, it follows that the algorithm {BEQUI}, which broadcasts all requested files at a rate proportional to the number of outstanding requests for that file, is a (4 + ε) -speed O(1 + 1/ε) -approximation algorithm. We give another algorithm BEQUI-EDF and show that BEQUI-EDF is also a (4 + ε) -speed O(1 + 1/ε) -approximation algorithm. However, BEQUI-EDF has the advantage that the maximum number of preemptions is linear in the number of requests, and the advantage that no preemptions occur if the data items have unit size.     

DVDs: Much Needed “Shot in the Arm” for Video Servers

The release of DVD-ROMs (Digital Versatile Disk—Read Only Memory), capable of storing an entire 133 minute MPEG-2 movie, coupled with the gradual deployment of high speed networks will give a much needed impetus to Video-on-Demand systems, especially movie-on-demand services. Various memory components such as DVD-ROMs, magnetic RAID towers, and RAM are available, each with different storage and bandwidth capabilities, and each with different costs. To design a video server, we need to optimize the cost factor, yet meet the massive storage, high bandwidth and continuity requirements of video stream delivery.In the first part of this paper we compare DVD-ROM and RAID systems on the basis of two factors—a storage factor and a bandwidth factor. We work out relations to calculate capacity requirements and costs, of these systems given the demands of video delivery. We then propose an architecture for a video server where we deploy three layers of memory functioning as video pumps: DVD-ROM towers, RAID towers, and RAM. We then work out expressions to determine the migration strategy of a movie between these layers of storage so as to optimize on the cost of storage while satisfying the performance requirements. We then show the method by which the amount of storage required for each type of memory in the three layers can be fixed, knowing the usage pattern.In the second part of the paper, we discuss the implementation of a video pump where there is a need to integrate scheduling, admission control, VBR stream management, and handling of VCR-like requests such as fast-forward, fast-reverse and pause. We first work out general relations for calculation of the service time of a request knowing the seek overheads and playback rates. We then show that, surprisingly, the C-SCAN algorithm, which incurs the least amount of seek overhead and therefore has a lesser cycle time, is twice as efficient as SCAN in terms of buffer space requirements. We then propose a full-load admission control and scheduling algorithm that operates on a constant cycle time basis. We test the validity of this scheme though a the simulator which we have built based on our disk model and use it to extract parameters such as disk bandwidth utilization factor and buffer sizes needed for a VBR load scenario.