Shahram Ghandeharizadeh

Staggered striping in multimedia information systems

Multimedia information systems have emerged as an essential component of many application domains ranging from library information systems to entertainment technology. However, most implementations of these systems cannot support the continuous display of multimedia objects and suffer from frequent disruptions and delays termed hiccups. This is due to the low I/O bandwidth of the current disk technology, the high bandwidth requirement of multimedia objects, and the large size of these objects that almost always requires them to be disk resident. One approach to resolve this limitation is to decluster a multimedia object across multiple disk drives in order to employ the aggregate bandwidth of several disks to support the continuous retrieval (and display) of objects. This paper describes staggered striping as a novel technique to provide effective support for multiple users accessing the different objects in the database. Detailed simulations confirm the superiority of staggered striping.

Continuous retrieval of multimedia data using parallelism

Most implementations of workstation-based multimedia information systems cannot support a continuous display of high resolution audio and video data and suffer from frequent disruptions and delays termed hiccups. This is due to the low I/O bandwidth of the current disk technology, the high bandwidth requirement of multimedia objects, and the large size of these objects, which requires them to be almost always disk resident. A parallel multimedia information system and the key technical ideas that enable it to support a real-time display of multimedia objects are described. In this system, a multimedia object across several disk drives is declustered, enabling the system to utilize the aggregate bandwidth of multiple disks to retrieve an object in real-time. Then, the workload of an application is distributed evenly across the disk drives to maximize the processing capability of the system. To support simultaneous display of several multimedia objects for different users, two alternative approaches are described. The first approach multitasks a disk drive among several requests while the second replicates the data and dedicates resources to each individual request. The trade-offs associated with each approach are investigated using a simulation model. >

On configuring a single disk continuous media server

The past decade has witnessed a proliferation of repositories that store and retrieve continuous media data types, e.g., audio and video objects. These repositories are expected to play a major role in several emerging applications, e.g., library information systems, educational applications, entertainment industry, etc. To support the display of a video object, the system partitions each object into fixed size blocks. All blocks of an object reside permanently on the disk drive. When displaying an object, the system stages the blocks of the object into memory one at a time for immediate display. In the presence of multiple displays referencing different objects, the bandwidth of the disk drive is multiplexed among requests, introducing disk seeks. Disk seeks reduce the useful utilization of the disk bandwidth and result in a lower number of simultaneous displays (throughput).This paper characterizes the impact of disk seeks on the throughput of the system. It describes REBECA as a mechanism that maximizes the throughput of the system by minimizing the time attributed to each incurred seek. A limitation of REBECA is that it increases the latency observed by each request. We quantify this throughput vs latency tradeoff of REBECA and, develop an efficient technique that computes its configuration parameters to realize the performance requirements (desired latency and throughput) of an application.

A performance analysis of alternative multi-attribute declustering strategies

During the past decade, parallel database systems have gained increased popularity due to their high performance, scalability and availability characteristics. With the predicted future database sizes and the complexity of queries, the scalability of these systems to hundreds and thousands of processors is essential for satisfying the projected demand. Several studies have repeatedly demonstrated that both the performance and scalability of a paralel database system is contingent on the physical layout of data across the processors of the system. If the data is not declustered properly, the execution of an operator might waste resources, reducing the overall processing capability of the system. With earlier, single attribute declustering strategies, such as those found in Tandem, Teradata, Gamma, and Bubba parallel database systems, a selection query including a range predicate on any attribute other than the partitioning attribute must be sent to all processors containing tuples of the relation. By directing a query with minimal resource requirements to processors that contain no relevant tuples, the system wastes CPU cycles, communication bandwidth, and I/O bandwidth, reducing its overall processing capability. As a solution, several multi-attribute declustering strategies have been proposed. However, the performance of these declustering techniques have not previously been compared to one another nor with a single attribute partitioning strategy. This paper, compares the performance of Multi-Attribute GrId deClustering (MAGIC) strategy and Bubbas Extended Range Declustering (BERD) strategy with one another and with the range partitioning strategy. Our results indicate that MAGIC outperforms both range and BERD in all experiments conducted in this study.

Mitra: A Scalable Continuous Media Server

Mitra is a scalable storage manager that supports the display of continuous media data types, e.g., audio and video clips. It is a software based system that employs off-the-shelf hardware components. Its present hardware platform is a cluster of multi-disk workstations, connected using an ATM switch. Mitra supports the display of a mix of media types. To reduce the cost of storage, it supports a hierarchical organization of storage devices and stages the frequently accessed objects on the magnetic disks. For the number of displays to scale as a function of additional disks, Mitra employs staggered striping. It implements three strategies to maximize the number of simultaneous displays supported by each disk. First, the EVEREST file system allows different files (corresponding to objects of different media types) to be retrieved at different block size granularities. Second, the FIXB algorithm recognizes the different zones of a disk and guarantees a continuous display while harnessing the average disk transfer rate. Third, Mitra implements the Grouped Sweeping Scheme (GSS) to minimize the impact of disk seeks on the available disk bandwidth.In addition to reporting on implementation details of Mitra, we present performance results that demonstrate the scalability characteristics of the system. We compare the obtained results with theoretical expectations based on the bandwidth of participating disks. Mitra attains between 65% to 100% of the theoretical expectations.

Design and implementation of scalable continuous media servers

Abstract During the past decade, the information technology has evolved to store and retrieve continuous media data types, e.g., audio and video clips. Unlike the traditional data types (e.g., text), continuous media consists of a sequence of quanta, either audio samples or video frames, that convey meaning when presented at a pre-specified rate. A challenging task when implementing these servers is to guarantee retrieval and delivery of a clip at its pre-specified rate. Continuous media servers are expected to play a major role in many application domains including library information systems, entertainment technology, educational applications, etc. The focus of this study is on the disk subsystem of a server and techniques that both enhance its performance and ensure its scalability. By scalable, we mean that the system can grow incrementally as the requirements of an application grows in order to avoid a degradation in performance. This study details data placement techniques across both (1) the zones of a disk in order to trade bandwidth for storage, and (2) multiple disks to enable the system to scale. In addition, we describe scheduling techniques to (1) trade memory for disk bandwidth and vice versa, and (2) merge multiple requests referencing a single clip in order to increase the number of simultaneous displays supported by the system. We present performance results from Mitra, an experimental prototype that realizes an implementation of the presented techniques. These results demonstrate the feasibility of a scalable server.

On multimedia repositories, personal computers, and hierarchical storage systems

The past decade has witnessed a proliferation of personal computers at homes, businesses, classrooms, libraries, etc. Most often, these systems are used to disseminate information. Recently, multimedia repositories have added to the excitement of this information age by allowing a user to retrieve and manipulate continuous media data types (audio and video objects). The design and implementation of these systems is challenging due to both the large size of objects that constitute this media type and their continuous bandwidth requirement. Compression in combination with the availability of fast CPUs (for real-time decompression) provide effective support for a continuous display of those objects with high bandwidth requirement. Hierarchical storage structures (consisting of RAM, disk and tertiary storage devices) provide a cost-effective solution for the large size of their repositories. The focus of this study is on personal computers (single user, single display) that employ fast CPUs, compression and hierarchical storage structures to support multimedia applications. Its goals are to ensure a continuous display of audio and video objects while minimizing the latency time observed by the user. Its contributions include a novel pipelining mechanism and PIRATE as a technique to manage the disk resident objects.

Heraclitus: elevating deltas to be first-class citizens in a database programming language

Traditional database systems provide a user with the ability to query and manipulate one database state, namely the current database state. However, in several emerging applications, the ability to analyze “what-if” scenarios in order to reason about the impact of an update (before committing that update) is of paramount importance. Example applications include hypothetical database access, active database management systems, and version management, to name a few. The central thesis of the Heraclitus paradigm is to provide flexible support for applications such as these by elevating deltas, which represent updates proposed against the current database state, to be first-class citizens. Heraclitus[Alg,C] is a database programming language that extends C to incorporate the relational algebra and deltas. Operators are provided that enable the programmer to explicitly construct, combine, and access deltas. Most interesting is the when operator, that supports hypothetical access to a delta: the expression E when &sgr; yields the value that side effect free expression E would have if the value of delta expression &sgr; were applied to the current database state. This article presents a broad overview of the philosophy underlying the Heraclitus paradigm, and describes the design and prototype implementation of Heraclitus[Alg, C]. A model-independent formalism for the Heraclitus paradigm is also presented. To illustrate the utility of Heraclitus, the article presents an in-depth discussion of how Heraclitus[Alg, C] can be used to specify, and thereby implement, a wide range of execution models for rule application in active databases; this includes both prominent execution models presented in the literature, and more recent “customized” execution models with novel features.

Pipelining mechanism to minimize the latency time in hierarchical multimedia storage managers

An emerging area of database system research is to provide support for continuous media data types (digital audio and video). These data types are expected to play a major role in applications such as library information systems, scientific databases, entertainment technology, etc. They require both a high volume of storage and a high bandwidth requirement for their continuous display. The storage organization of systems that support these data types is expected to be hierarchical, consisting of one or more tertiary storage devices, several disk drives, and some memory. The database resides permanently on the tertiary storage device. The disk drives store a number of frequently accessed objects, while the memory is used to stage a small fraction of a referenced object for immediate display. When a user references an object that is tertiary resident, if the system elects to materialize the object on the disk drives in its entirety before initiating its display then the user would observe a high latency time. This paper describes a general purpose pipelining mechanism that overlaps the display of an object with its materialization on the disk drives in order to minimize the latency time of the system. The pipelining mechanism is novel because it ensures a continuous retrieval of an object to a display station (in order to support its continuous display).

Placement of continuous media in wireless peer-to-peer networks

This paper investigates a novel streaming architecture consisting of home-to-home online (H2O) devices that collaborate with one another to provide on-demand access to large repositories of continuous media such as audio and video clips. An H2O device is configured with a high bandwidth wireless communication component, a powerful processor, and gigabytes of storage. A key challenge of this environment is how to place data across H2O devices in order to enhance startup latency, defined as the delay observed from when a user requests a clip, to the onset of its display. Our primary contribution is a novel replication technique that enhances startup latency, while minimizing the total storage space required from an environment consisting of N H2O devices. This technique is based on the following intuition: The first few blocks of a clip are required more urgently than its last few blocks, and should be replicated more frequently in order to minimize startup latency. We develop analytical models to quantify the number of replicas required for each block. In addition, we describe two alternative distributed implementation of our replication strategy. When compared with full replication, our technique provides on average greater than 97% (i.e., several orders of magnitude) savings in storage space, while ensuring zero startup latency and a hiccup-free reception.