Search

Advancements in storage technology along with the fast deployment of high-speed networks has allowed the storage, transmission, and manipulation of multimedia information such as text, graphics, still images, video, and audio to be feasible. Our study focused on the performance of the mass storage system for a large-scale video-on-demand server. Different video file striping schemes, such as application level striping and device driver level striping, were examined in order to study scalability and performance issues. To study the impact of different concurrent access patterns on the performance of a server, experimental results were obtained on group access on a single video file and multiple group accesses on multiple video files. All of our experiments were conducted on a fully configured Silicon Graphics Inc. Onyx computer system. The Onyx machine was connected to 31 SCSI-2 channels which have 496 GBytes disk storage, 20 MIPS R4400 processors, and 768 MBytes main memory. From the experimental results, the storage system of Onyx machine can potentially provide about 360 concurrent video accesses with guaranteed quality of service.

In this paper we look at the performance characteristics of three tools used to move large data sets over dedicated long distance networking infrastructure. Although performance studies of wide area networks have been a frequent topic of interest, performance analyses have tended to focus on network latency characteristics and peak throughput using network traffic generators. In this study we instead perform an end-to-end long distance networking analysis that includes reading large data sets from a source file system and committing the data to a remote destination file system. An evaluation of end-to-end data movement is also an evaluation of the system configurations employed and the tools used to move the data. For this paper, we have built several storage platforms and connected them with a high performance long distance network configuration. We use these systems to analyze the capabilities of three data movement tools: BBcp, GridFTP, and XDD. Our studies demonstrate that existing data movement tools do not provide efficient performance levels or exercise the storage devices in their highest performance modes.

In this project we look at the performance characteristics of three tools used to move large data sets over dedicated long distance networking infrastructure. Although performance studies of wide area networks have been a frequent topic of interest, performance analyses have tended to focus on network latency characteristics and peak throughput using network traffic generators. In this study we instead perform an end-to-end long distance networking analysis that includes reading large data sets from a source file system and committing large data sets to a destination file system. An evaluation of end-to-end data movement is also an evaluation of the system configurations employed and the tools used to move the data. For this paper, we have built several storage platforms and connected them with a high performance long distance network configuration. We use these systems to analyze the capabilities of three data movement tools: BBcp, GridFTP, and XDD. Our studies demonstrate that existing data movement tools do not provide efficient performance levels or exercise the storage devices in their highest performance modes. We describe the device information required to achieve high levels of I/O performance and discuss how this data is applicable in use cases beyond data movement performance.

Obtaining consistent bandwidth with predictable latency from disk-based storage systems has proven difficult due to the storage system's inability to understand quality of service (QoS) requirements. In this paper, we present a feasibility study of QoS with the object-based storage device (OSD) specification. We look at OSD's ability to provide QoS guarantees for consistent bandwidth with predictable latency. Included in this paper is a description of QoS requirements of a sample application and how these requirements are translated into parameters that are then communicated to, and interpreted by, the OSD. Implementation problems lead to the failure of a hard real-time QoS model, but this failure is not due to the OSD protocol. The paper concludes with a description of how well the revision 9 OSD standard (OSDR9) is able to accommodate QoS. We provide suggestions for improving the OSD specification and its ability to communicate QoS requirements.

The bandwidth performance of a Fibre Channel Arbitrated Loop (FCAL) is roughly defined to be 100 MegaBytes (100 bytes) per second. Furthermore, FCAL is capable of a theoretical peak of 40,000 I/O operations (transactions) per second. These performance levels, however, are largely not realized by the applications that use Fibre Channel as an interface to disk subsystems. The bandwidth and transaction performance of an Arbitrated Loop is sensitive to both the number of devices on the loop as well as the physical length of the loop. This study focuses on the effects of these two factors on the observed performance of Fibre Channel Arbitrated Loop as the number of nodes is scaled from 2 to 97 devices and as the physical length of the loop is scaled from 50 meters to several kilometers in length. To summarize, this study shows that the performance decreases significantly for very long loops and explains how this can be partially avoided. Also, the loop propagation delay on loops with many devices has only a moderate affect on performance. Finally, the effects of length tend to dominate the effects of population for very long, highly populated loops.

Advancements in storage technology along with the fast deployment of high-speed networks has allowed the storage, transmission and manipulation of multimedia information such as text, graphics, still images, video and audio to be feasible. Our study focused on, the performance of the mass storage system for a large-scale video-on-demand server. Different video file striping schemes, such as application level striping and device driver level striping, were examined in order to study scalability and performance issues. To study the impact of different concurrent access patterns on the performance of a server, experimental results were obtained on group access on a single video file and multiple group accesses on multiple video files.

With the growing popularity of storage area networks (SANs) and clustered, shared file systems, the file system is becoming a distinct and critical part of a system environment. Because the file system mitigates access to data on a mass storage subsystem, it has certain behavioral and functional characteristics that affect I/O performance from an application and/or system point of view. Measuring file system performance is significantly more complicated than that of the underlying disk subsystem because of the many types of higher-level operations that can be performed (allocations, deletions, directory searches, ...etc.). The tasks of measuring and characterizing the performance of a file system is further complicated by SANs and emerging clustering technologies that add a distributed aspect to the file systems themselves. Similarly, as the cluster/SAN grows in size, so does the task of performance measurement. The objective of this study is to identify some of the more significant issues involved with file system benchmarking in a highly scalable clustered environment.

The primary objectives of this project were to evaluate the performance of the SGI CXFS File System in a Storage Area Network (SAN) and compare/contrast it to the performance of a locally attached XFS file system on the same computer and storage subsystems. The University of Minnesota participants were asked to verify that the performance of the SAN/CXFS configuration did not fall below 85% of the performance of the XFS local configuration. There were two basic hardware test configurations constructed from the following equipment: Two Onyx 2 computer systems each with two Qlogic-based Fibre Channel/XIO Host Bus Adapter (HBA); One 8-Port Brocade Silkworm 2400 Fibre Channel Switch; and Four Ciprico RF7000 RAID Disk Arrays populated Seagate Barracuda 50GB disk drives. The Operating System on each of the ONYX 2 computer systems was IRIX 6.5.6. The first hardware configuration consisted of directly connecting the Ciprico arrays to the Qlogic controllers without the Brocade switch. The purpose for this configuration was to establish baseline performance data on the Qlogic controllers / Ciprico disk raw subsystem. This baseline performance data would then be used to demonstrate any performance differences arising from the addition of the Brocade Fibre Channel Switch. Furthermore, the performance of the Qlogic controllers could be compared to that of the older, Adaptec-based XIO dual-channel Fibre Channel adapters previously used on these systems. It should be noted that only raw device tests were performed on this configuration. No file system testing was performed on this configuration. The second hardware configuration introduced the Brocade Fibre Channel Switch. Two FC ports from each of the ONYX2 computer systems were attached to four ports of the switch and the four Ciprico arrays were attached to the remaining four. Raw disk subsystem tests were performed on the SAN configuration in order to demonstrate the performance differences between the direct-connect and the switched configurations. After this testing was completed, the Ciprico arrays were formatted with an XFS file system and performance numbers were gathered to establish a File System Performance Baseline. Finally, the disks were formatted with CXFS and further tests were run to demonstrate the performance of the CXFS file system. A summary of the results of these tests is given.