NCSA's World Wide Web server: design and performance

Kwan, T.T.; McGrath, Robert E.; Reed, Daniel A.

doi:10.1109/2.471181

Cited by 147 publications

(49 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lastly, load-balancing server resource usage has been an active area of research for over a decade, since early work on web servers [Kwan et al 1995]. In the storage domain, disk striping and replication [Patterson et al 1988;Ganger et al 1993] to distribute disk accesses across a set of drives has been popular for quite some time.…”

Section: Related Workmentioning

confidence: 99%

Workload-based generation of administrator hints for optimizing database storage utilization

2008

View full text Add to dashboard Cite

Database storage management at data centers is a manual, time-consuming, and error-prone task. Such management involves regular movement of database objects across storage nodes in an attempt to balance the I/O bandwidth utilization across disk drives. Achieving such balance is critical for avoiding I/O bottlenecks and thereby maximizing the utilization of the storage system. However, manual management of the aforesaid task, apart from increasing administrative costs, encumbers the greater risks of untimely and erroneous operations. We address the preceding concerns with STORM, an automated approach that combines low-overhead information gathering of database access and storage usage patterns with efficient analysis to generate accurate and timely hints for the administrator regarding data movement operations. STORM's primary objective is minimizing the volume of data movement required (to minimize potential down-time or reduction in performance) during the reconfiguration operation, with the secondary constraints of space and balanced I/O-bandwidth-utilization across the storage devices. We analyze and evaluate STORM theoretically, using a simulation framework, as well as experimentally. We show that the dynamic data layout reconfiguration problem is NP-hard and we present a heuristic that provides an approxi-where M is the number of storage devices and N is the total number of database objects residing in the storage devices. A simulation study shows that the heuristic converges to an acceptable solution that is successful in balancing storage utilization with an accuracy that lies within 7% of the ideal solution. Finally, an experimental study demonstrates that the STORM approach can improve the overall performance of the TPC-C benchmark by as much as 22%, by reconfiguring an initial random, but evenly distributed, placement of database objects.

show abstract

Section: Related Workmentioning

confidence: 99%

Workload-based generation of administrator hints for optimizing database storage utilization

2008

View full text Add to dashboard Cite

show abstract

“…It is often assumed that the service time of a request is proportional to the size of its requested file. Simple strategies, like random and round-robin algorithms, are good enough when the requests are uniform in size and independent (Kwan, McGrath, & Reed, 1995). To take advantage of temporal locality in requests, locality-aware distribution strategies make server selection based on the requested content (Pai et al, 1998).…”

Section: Web Applicationsmentioning

confidence: 99%

“…The simplest DNS-based load-balancing approach in a Web cluster is round robin (Kwan et al, 1995). In this approach, the DNS server assigns the IP addresses of the cluster servers in a round-robin manner to the clients' address-mapping requests.…”

Section: State-blind Load Balancingmentioning

confidence: 99%

Load Balancing on the Internet

Jiang

Zhou

2004

The Internet Encyclopedia

View full text Add to dashboard Cite

This chapter gives a survey of state‐of‐the‐art load‐balancing strategies on the Internet. Internet services must be scalable, available, and responsive to handle large traffic volumes and support up to millions of concurrent clients. This scalability requirement goes beyond the capability of any single machine servers. Cluster server architecture is gaining momentum in support of scalable Internet services. The servers in a cluster can be either distributed locally at the same site or globally distributed in different geographical locations. Load balancing is a key integration technology at both layers for performance. This chapter presents a characterization of Web services and gives a classification of load balancing strategies according to their deployment locations (server, network, and client sides), information taken into account (state‐blind, client‐state aware, and server‐state aware), and implementation levels (network and application layers). Representative load balancing strategies in each category are reviewed.

show abstract

“…Moreover, users expect to receive responses in a short period of time, regardless of the number of requests that web servers must process at a given time. This new scenario introduces several challenges to the client/server model used on the Internet, considering that the level of scalability of a single web server is relatively low (Kwan et al, 1995;Colajanni and Yu, 1997).…”

Section: Introductionmentioning

confidence: 99%

Flow Based Load Balancing: Optimizing Web Servers Resource Utilization

Bays

Marcon

2012

jacr

View full text Add to dashboard Cite

Abstract. The expansion of the Internet has caused a growth on the number of users requesting services through the network, as well as the number of servers and the amount of services they offer. In order to minimize this problem, web servers have started to use a distributed architecture implementation, however with only one external interface for receiving requests from users. In this paper, we propose an approach towards flow-oriented load balancing, using the OpenFlow technology. Thus, each data flow is directed to a server, according to the policy being employed. We evaluate three load balancing techniques: random choice, time slice based choice and weighted balancing, each of them with its advantages and disadvantages. Through our measurements, weighted balancing achieved the best results over the other policies. Moreover, random choice and time slice based choice are capable of distributing the load in an acceptable way among nodes, considering the average load of each server.

show abstract

NCSA's World Wide Web server: design and performance

Cited by 147 publications

References 5 publications

Workload-based generation of administrator hints for optimizing database storage utilization

Workload-based generation of administrator hints for optimizing database storage utilization

Load Balancing on the Internet

Flow Based Load Balancing: Optimizing Web Servers Resource Utilization

Contact Info

Product

Resources

About