Scheduling real-time disk transfers for continuous media applications

Long, Darrell D. E.; Thakur, M.N.

doi:10.1109/mass.1993.289755

Cited by 14 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many early systems work on a single-server [7,25,34], or for a specific kind of workloads, such as media recording and streaming [23,46,47] or virtual machines [10].…”

Section: Related Workmentioning

confidence: 99%

ASCAR: Automating contention management for high-performance storage systems

Miller

et al. 2015

2015 31st Symposium on Mass Storage Systems and Technologies (MSST)

View full text Add to dashboard Cite

Abstract-High-performance parallel storage systems, such as those used by supercomputers and data centers, can suffer from performance degradation when a large number of clients are contending for limited resources, like bandwidth. These contentions lower the efficiency of the system and cause unwanted speed variances. We present the Automatic Storage Contention Alleviation and Reduction system (ASCAR), a storage traffic management system for improving the bandwidth utilization and fairness of resource allocation. ASCAR regulates I/O traffic from the clients using a rule based algorithm that controls the congestion window and rate limit. The rule-based client controllers are fast responding to burst I/O because no runtime coordination between clients or with a central coordinator is needed; they are also autonomous so the system has no scale-out bottleneck. Finding optimal rules can be a challenging task that requires expertise and numerous experiments. ASCAR includes a SHAred-nothing Rule Producer (SHARP) that produces rules in an unsupervised manner by systematically exploring the solution space of possible rule designs and evaluating the target workload under the candidate rule sets. Evaluation shows that our ASCAR prototype can improve the throughput of all tested workloadssome by as much as 35%. ASCAR improves the throughput of a NASA NPB BTIO checkpoint workload by 33.5% and reduces its speed variance by 55.4% at the same time. The optimization time and controller overhead are unrelated to the scale of the system; thus, it has the potential to support future large-scale systems that can have millions of clients and thousands of servers. As a pure client-side solution, ASCAR needs no change to either the hardware or server software.

show abstract

“…Many early systems work on a single-server [7,25,34], or for a specific kind of workloads, such as media recording and streaming [23,46,47] or virtual machines [10].…”

Section: Related Workmentioning

confidence: 99%

ASCAR: Automating contention management for high-performance storage systems

Miller

et al. 2015

2015 31st Symposium on Mass Storage Systems and Technologies (MSST)

View full text Add to dashboard Cite

show abstract

“…Besides offline algorithms, there are also a few online algorithms. Long [18] used examples to show that no deterministic online algorithm can achieve good performance if there is no restrictions on jobs. Lipton [19] proposed a randomized online algorithm that is strongly 2-competitive for the case in which intervals must be one of two possible lengths.…”

Section: Previous Workmentioning

confidence: 99%

Maximizing Throughput for Optical Burst Switching Networks

Qiao

et al. 2007

IEEE/ACM Trans. Networking

View full text Add to dashboard Cite

Abstract-A key problem in Optical Burst Switching (OBS) is to schedule as many bursts as possible on wavelength channels so that the throughput is maximized and the burst loss is minimized. Currently, most of the research on OBS (e.g., burst scheduling and assembly algorithms) has been concentrated on reducing burst loss in an "average-case" sense. Little effort has been devoted to understanding the worst-case performance. Since OBS itself is an open-loop control system, it may often exhibit a worst-case behavior when adversely synchronized, thus a poor worst-case performance can lead to an unacceptable system-wide performance. In this paper, we use competitive analysis to analyze the worstcase performance of a large set of scheduling algorithms, called best-effort online scheduling algorithms, for OBS networks, and establish a number of interesting upper and lower bounds on the performance of such algorithms. Our analysis shows that the performance of any best-effort online algorithm is closely related to a few factors, such as the range of offset time, burst length ratio, scheduling algorithm, and number of data channels. A surprising discovery is that the worst-case performance of any best-effort online scheduling algorithm is primarily determined by the maximum to minimum burst length ratio, followed by the range of offset time. Furthermore, if all bursts have the same burst length and offset time, all best-effort online scheduling algorithms generate the same optimal solution, regardless how different they may look like. Our analysis can also be extended to some non-besteffort online scheduling algorithms, such as the well-known Horizon algorithm, and establish similar bounds. Based on the analytic results, we give guidelines for several widely discussed OBS problems, including burst assembly, offset time setting and scheduling algorithm design, and propose a new channel reservation protocol called VFO to improve the worst-case performance. Our simulation shows that it is quite often for an online scheduling algorithm to exhibit its (near) worst-case performance. Thus improving the worst-case performance is essential. Our simulation also suggests that VFO reduces the average burst loss rate by as much as 35%.

show abstract

“…Swift [2] is a distributed storage system that also stripes objects across different storage nodes. A QoS mechanism for Swift was proposed [10]. However, this mechanism differs in that it provides reservation through admission control for storage tasks that are known a priori, instead of global level sharing between classes where the loads may not be known in advance.…”

Section: Related Workmentioning

confidence: 99%