• Journal of Korea Society of Industrial Information Systems
• /
• v.12 no.3
• /
• pp.10-18
• /
• 2007

According to the recent growth of the internet commercialization and differentiated QoS(quality of service), statistical traffic modeling is necessary for forecasting and controlling future network capacity. This paper reviews tile essential components in web workloads. And I propose adjusted internet traffic modeling using heavy-tailed distributions and intervention techniques.

• ETRI Journal
• /
• v.31 no.2
• /
• pp.173-181
• /
• 2009

The growth of the World Wide Web and web-based applications is creating demand for high performance web servers to offer better throughput and shorter user-perceived latency. This demand leads to widely used cluster-based web servers in the Internet infrastructure. Load balancing algorithms play an important role in boosting the performance of cluster web servers. Previous load balancing algorithms suffer a significant performance drop under dynamic and database-driven workloads. We propose an estimation-based load balancing algorithm with admission control for cluster-based web servers. Because it is difficult to accurately determine the load of web servers, we propose an approximate policy. The algorithm classifies requests based on their service times and tracks the number of outstanding requests from each class in each web server node to dynamically estimate each web server load state. The available capacity of each web server is then computed and used for the load balancing and admission control decisions. The implementation results confirm that the proposed scheme improves both the mean response time and the throughput of clusters compared to rival load balancing algorithms and prevents clusters being overloaded even when request rates are beyond the cluster capacity.

• The Journal of Korean Association of Computer Education
• /
• v.18 no.3
• /
• pp.115-124
• /
• 2015

In this paper, we introduce a web-based scheduling toolkit(GridTool2), which can run simulation of scheduling algorithm in grid system. And we suggest new algorithms which apply additional communication costs to the existing MinMin and Suffrage scheduling algorithms. Since GridTool2 runs in web environment using server and database, it does not require a separate compiler or runtime environment. The GridTool2 allows variables such as communication costs on the web for performance evaluation, and shows simulation results on the web page. The new algorithm with communication costs was tested using GridTool2 to check for performance improvements. The results revealed that the new algorithm showed better performance as more workloads were incorporated to the system.

• The KIPS Transactions:PartA
• /
• v.8A no.3
• /
• pp.261-268
• /
• 2001

With the rapid growth of the Internet, various web-based businesses are creating a new environment in an imaginary space. However, this expanding Internet and user increase cause an overflow of transmission and numerous subordinate problems. To solve these problems, a parallel cluster system is produced using different methods. This thesis recommends a multi0distribution cluster group. It constructs a MPP dynamic distribution sub-cluster group using numerous low-priced and low-speed systems. This constructed sub-cluster group is then connected with a singular virtual IP to finally serve the needs of clients (users). This multi-distribution cluster group consists of an upper structure based on LVS and a dynamic serve cluster group centered around an SC-server. It conducts the workloads required from users in a parallel process. In addition to the web service, this multi-distribution cluster group can efficiently be utilized for the calculations which require database controls and a great number of parallel calculations as well as additional controls with result from the congestion of service.

• Journal of KIISE:Computer Systems and Theory
• /
• v.29 no.6
• /
• pp.346-353
• /
• 2002

The explosive increase of World Wide Web usage has incurred significant amount of network traffic and server load. To overcome these problems, web proxy caching replicates frequently requested documents in the web proxy closer to the users. Cache utilization depends on the replacement policy which tries to store frequently requested documents in near future. Temporal locality and Zipf frequency distribution, which are commonly observed in web proxy workloads, are considered as the important properties to predict the popularity of documents. In this paper, we propose a novel cache replacement policy, called Adaptive LFU (ALFU), which incorporates 1) Zipf frequency distribution by utilizing LFU and 2) temporal locality adaptively by measuring the amount of the popularity reduction of documents as time passed efficiently. We evaluate the performance of ALFU by comparing it to other policies via trace-driven simulation. Experimental results show that ALFU outperforms other policies.

• Journal of KIISE:Computing Practices and Letters
• /
• v.6 no.4
• /
• pp.441-447
• /
• 2000

In this paper, we design and implement an Internet GIS based on ObjectWeb, which makes to use various distributed services and object paradigm. We use CORBA, which is the standard of distributed object middleware and supports interoperability and reusability regardless of the execution environment and the implementation language of a distributed code, so that it easily extends established systems in networking environment and accesses distributed heterogeneous spatial data. Our method distributes parts of user interactive tasks to clients to reduce and to improve the system performance while existing approaches concentrate all workloads on a server. We implement a travel information system on the developed IGIS. Users receive services from remote servers employing a Java client system running on a web browser.

• The KIPS Transactions:PartD
• /
• v.13D no.2 s.105
• /
• pp.165-174
• /
• 2006

As new database systems are developed or new functions are added to existing database systems, database developers or users would like to evaluate new database systems or new functions. This paper presents an integrated database benchmark suite. The integrated suite offers genetic benchmarks, custom benchmark, and hybrid benchmarks to users on a unified Web user interface. With regard to text data generation, the integrated suite supports eight data distributions with three data types. The integrated suite can also generate XML data in three different ways. Users can run benchmarks in realistic environments by performing the workload generation facility of the integrated suite, which generates composite workloads similar to real-world workloads. Using supporting tools, users can easily implement new generic and custom benchmarks in the integrated suite. An illustrative demonstration to add a new custom benchmark into the integrated suite is presented.

• ETRI Journal
• /
• v.30 no.4
• /
• pp.621-623
• /
• 2008

We propose a novel input pointing device called the multimodal mouse (MM) which uses two modalities: face recognition and speech recognition. From an analysis of Microsoft Office workloads, we find that 80% of Microsoft Office Specialist test tasks are compound tasks using both the keyboard and the mouse together. When we use the optical mouse (OM), operation is quick, but it requires a hand exchange delay between the keyboard and the mouse. This takes up a significant amount of the total execution time. The MM operates more slowly than the OM, but it does not consume any hand exchange time. As a result, the MM shows better performance than the OM in many cases.

• Journal of Computing Science and Engineering
• /
• v.11 no.3
• /
• pp.92-99
• /
• 2017

Memcached, commonly used to speed up the data access in big-data and Internet-web applications, is a system software of the distributed-cache mechanism. But it is subject to the severe challenge of the loss of recently uncommitted updates in the case where the Memcached servers crash due to some reason. Although the replica scheme and the disk-log-based replay mechanism have been proposed to overcome this problem, they generate either the overhead of the replica synchronization or the persistent-storage overhead that is caused by flushing related logs. This paper proposes a scheme of backing up the write requests (i.e., set and add) on the Memcached client side, to reduce the overhead resulting from the making of disk-log records or performing the replica consistency. If the Memcached server fails, a timestamp-based recovery mechanism is then introduced to replay the write requests (buffered by relevant clients), for regaining the lost-data updates on the rebooted Memcached server, thereby meeting the data-consistency requirement. More importantly, compared with the mechanism of logging the write requests to the persistent storage of the master server and the server-replication scheme, the newly proposed approach of backing up the logs on the client side can greatly decrease the time overhead by up to 116.8% when processing the write workloads.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.7
• /
• pp.2815-2839
• /
• 2020

In a cloud computing paradigm, allocation of various virtualized ICT resources is a complex problem due to the presence of heterogeneous application (MapReduce, content delivery and networks web applications) workloads having contentious allocation requirements in terms of ICT resource capacities (resource utilization, execution time, response time, etc.). This task of resource allocation becomes more challenging due to finite available resources and increasing consumer demands. Therefore, many unique models and techniques have been proposed to allocate resources efficiently. However, there is no published research available in this domain that clearly address this research problem and provides research taxonomy for classification of resource allocation techniques including strategic, target resources, optimization, scheduling and power. Hence, the main aim of this paper is to identify open challenges faced by the cloud service provider related to allocation of resource such as servers, storage and networks in cloud computing. More than 70 articles, between year 2007 and 2020, related to resource allocation in cloud computing have been shortlisted through a structured mechanism and are reviewed under clearly defined objectives. Lastly, the evolution of research in resource allocation techniques has also been discussed along with salient future directions in this area.