• Journal of Industrial Technology
• /
• v.27 no.B
• /
• pp.215-219
• /
• 2007

For Web server implementations, there are 4 main schemes: process-per-request (PPR), thread-per-request (TPR), worker thread pool (WTP), and worker thread pool with buffers (WTPB). This paper compares performance of the schemes in response time point of view. WTPB shows the best performance. The appropriate number of worker threads for WTPB depends on the request service time. For short requests, the number can be very small. But for longer requests, it is about 1/6 of the number of simultaneous connections.

• Journal of Communications and Networks
• /
• v.17 no.2
• /
• pp.118-125
• /
• 2015

In this paper, we propose a method to reduce mobile social network services (SNSs) traffic using a mobile integrated SNS gateway (MISG) to improve network communication performance between the mobile client and SNS servers. The gateway connects the client and SNS servers using the contents adapter and the web service adapter and helps to improve communication performance using its cache engine. An integrated SNS application, the user's client, communicates with the gateway server using integrated SNS protocol. In addition, the gateway can alert the client to new SNS contents because of the broker server implemented by the message queuing telemetry transport protocol. We design and develop the modules of the gateway server and the integrated SNS application. We then measure the performance of MISG in terms of content response time and describe the result of the experiment.

• Journal of KIISE:Computer Systems and Theory
• /
• v.32 no.1
• /
• pp.21-28
• /
• 2005

Web servers or web application servers, in general, adopt multi-thread model for efficient handling of many user requests. However, the multi -thread model always does not show the better performance than multi -process model. Sometimes, in a certain specific case, it can show worse performance than multi -process model. In this paper, to trace the cause of the decreased performance of multi -thread model, we experiment and analyze the performance of the multi-thread model by using two approaches. At first, we compare the performance of the multi-process model and multi-thread model for various application environments. Second, we observe the effects of variations of web server's dynamic directives, which are used to increase the flexibility of the web server for various system environments. For the experiments, we integrated a web client simulator, which was written by us, with the Apache 2.0 web server. This paper shows and analyze the results of the experiments.

• Journal of the Korea Society for Simulation
• /
• v.15 no.2
• /
• pp.23-29
• /
• 2006

This paper studies the Internet stream server which serves multimedia stream services such as VoD and MoD. The Internet multimedia stream server is developed to provide 50 users with continuous multimedia stream contents simultaneously. This paper focuses on introducing design concepts, operation details and on evaluating system performance and doing sensitivity analysis with respect to the change of the system components. The performance evaluation is performed using simulation in order to identify the system component that mostly affects the system performance. The sensitivity analysis shows the service delay rates of the multimedia stream server depending on the user's service request pattern. Also, the analysis is made on the utilization rates of the core system components such as the PCI bus and the Ethernet card, and on the system performance change by adding more system components.

• The Journal of Information Systems
• /
• v.4
• /
• pp.85-104
• /
• 1995

In a loosely-coupled distributed database server system, a server failure and/or a communication failure can be masked by a resiliency mechanism. Recognizing that a distributed transaction executes at several servers during its lifetime, we propose a resiliency mechanism which allows continuous transaction processing in distributed database server systems in the presence of a server failure. The resiliency mechanism for transaction processing is achieved by keeping redundant information using a primary/backup approach. The purpose of this paper is to analyze the performance improvement opportunities with the resiliency mechanism and to present the design of the proposed system.

• International Journal of Contents
• /
• v.4 no.1
• /
• pp.16-19
• /
• 2008

In this paper, we propose to new dispatcher method, which doesn't depend on an operating system of the server, and the direct routing method, by which a server answers a client's request at first hand. And, propose new web clustering scheme based on the contents on the web where web servers composed of cluster, with each different contents, answer client's request. The other purposes are to reduce overhead of the dispatcher through load balance, and to minimize the time to take in responding to a client's request. The performance of new web cluster scheme was improved by about 39% than that of the existing RR method. It was identified that the performance of the proposed web cluster method was extraordinary improved comparing with that of the existing RR method as a whole.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.4B
• /
• pp.411-423
• /
• 2004

This paper defines test methodologies and performance indices for SIP server system, and describes elements that can have influence on the test of SIP network equipments. Moreover, we implement a tester to evaluate the performance of SIP Servers such as Registrar and Proxy server. The performance indices for testing SIP servers are message processing rate, transaction delay, and call success probability. The parameters that can have an effect on the performance of SIP servers are user population, transport protocol, method of database access, method of DNS, call creation pattern, definition of transactions, and size of packets. We tested several SIP servers that act as Registrar, Proxy, and Redirect server using the implemented SIP tester, and, as a result, verified functions of the tester and performance indices and input parameters defined in this paper. Performance indices and methodologies presented in this paper can be used to evaluate SIP servers in NGN

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.8 no.4
• /
• pp.43-52
• /
• 2008

The paper presents the problem definition of video placement and efficient methods for placing video data on a cluster of video servers. The video placement is to place each of video replicas on one of the servers where the number and location of the servers are already determined. The rejection ratio of user requests is one of most important user-perceive performance measures, so it has been used as a performance criteria in many researches on the VOD system. The objective of our video placement is to achieve the load balancing among servers and the minimization of total network loads. To our experiment, the presented methods show better performance in terms of the rejection ratio of user requests than the methods for video placements in which only either server load balancing or network load minimization is considered. Also, it is observed that considerations on server load balancing is especially important in video placement. To our survey, little research has been published on video placement in which server and network load are considered together in a video server cluster environment.

• The KIPS Transactions:PartC
• /
• v.10C no.1
• /
• pp.87-94
• /
• 2003

As the number of the Internet users increases explosively, a solution for this problem is web caching. So, many techniques on improving cache server performance have been suggested. In this paper, we analyze the cause of the bottleneck in cache servers, and propose an arbitral thread and delayed caching mechanism as a solution. We use an arbitral thread in order to provide a quick service to user requests through eliminating the ready multi-thread search problem in case of disk writing operation. We also use delayed caching in order to provide stable system operation through avoiding overloaded disk operation and queue threshold. Proposed cache server is implemented through modification on SQUlD cache server, and we compare its performance with the original SQUID cache server.

• Proceedings of the KSME Conference
• /
• 2004.11a
• /
• pp.1472-1475
• /
• 2004

Current processor power consumption has dramatically increased and already reached 115 Watts. Therefore, Heat sink design needs more high accuracy in 1U server. The target performance of heat sink is very dependent of fin geometry and it is also seriously affected by design conditions such as fan type, air duct shape and heatsink design parameters. The present paper investigates the behavior of heat sink performance under various conditions. The present work addresses pressurized type plane fin heat sinks having dimension of 40 mm by 40 mm by 56 mm fan.