• Journal of KIISE:Computer Systems and Theory
• /
• v.36 no.4
• /
• pp.259-273
• /
• 2009

Most of large-scale distributed file systems decouple a metadata operation from read and write operations for a file. In the distributed file systems, a certain server named a metadata server (MDS) maintains metadata information in file system such as access information for a file, the position of a file in the repository, the namespace of the file system, and so on. But, the existing systems used restrictive metadata management schemes, because most of the distributed file systems designed to focus on the distributed management and the input/output performance of data rather than the metadata. Therefore, in the existing systems, the metadata throughput and expandability of the metadata server are limited. In this paper, we propose a new non-shared metadata management scheme in order to provide the high metadata throughput and scalability for a cluster of MDSs. First, we derive a dictionary partitioning scheme as a new metadata distribution technique. Then, we present a load balancing technique based on the distribution technique. It is shown through various experiments that our scheme outperforms existing metadata management schemes in terms of scalability and load balancing.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.1
• /
• pp.32-39
• /
• 2015

The voice communications with wireless backbone based networks are evolving into a packet switching VoIP systems. In those networks, a call processing scheme is required for management of subscribers and connection between them. A VoIP service scheme for those systems requires reliable subscriber management and connection establishment schemes, but the conventional call processing schemes based on the centralized server has lack of reliability. Thus, the mutual-backup architecture of SIP-servers is required to ensure efficient subscriber management and reliable VoIP call processing capability, and the synchronization and call processing schemes should be changed as the architecture is changed. In this paper, a mutual-backup architecture of SIP-servers is proposed for wireless backbone based networks. A message format for synchronization and information exchange between SIP servers is also proposed in the paper. This paper also proposes a FSM scheme for the fast call processing in unreliable networks to detect multiple servers at a time. The performance analysis results show that the mutual backup server architecture increases the call processing success rates than conventional centralized server architecture. Also, the FSM scheme provides the smaller call processing times than conventional SIP, and the time is not increased although the number of SIP servers in the networks is increased.

• The KIPS Transactions:PartA
• /
• v.9A no.2
• /
• pp.137-146
• /
• 2002

In VOD server, in order to guarantee playback of continuous media, such as video, without hiccups for multiusers, the server has to manage its buffer sophisticatedly by prefeching a part of the data into the buffer As the continuous media data buffered by one user can be used again by the others, the number of disk accesses is reduced and then the latency time far the users is also reduced. In this paper, we propose a new buffer management technique for continuous media in VOD server. Our basic algorithm partitions the buffer into groups and then a group of buffer which has the lowest utilization is chosen and partitioned again for a new user. The basic algorithm is extended for supporting multiple streams and clip data and for providing VCR functions. Our proposed technique is able to increase in the number of concurrent users as increasing the utilization of the buffer and to minimize the average waiting time for multiuser accesses as the bandwidth of storage is slowly reached to the limit. In the simulation study for comparing the performance of our technique with that of the existing techniques, we show that the average waiting time is reduced mere than 50% and the number of concurrent users increases by 1 ∼5% as compared with those of the exiting techniques.

• The KIPS Transactions:PartD
• /
• v.9D no.2
• /
• pp.185-194
• /
• 2002

Most of mobile computing systems allow mostly read-only transactions from mobile clients for retrieving various types of Information such as stock data, traffic information and news updates. Since previous concurrence control protocols, however, do not consider such a particular characteristics, the performance degradation occurs when previous schemes are applied to the broadcast environment. In this paper, we propose OCC/UTF(Optimistic Concurrence Control with Update Transaction First) that is most appropriate for broadcast environment. OCC/UTF lets a query transaction, that has already read the data item which was invalidated by update transaction, read again the same data item without the abort of the query transaction due to non-serializability. Therefore, serializable order is maintained and the query transaction is committed safely regardless of commitment of update transactions. In OCC/UTF, Clients need not require server to commit their query transactions. Because of broadcasting the validation reports including values updated recently to clients, it reduces the overhead of requesting recent values from the server and the server need not also re-broadcast the newest values. As a result, OCC/UTF makes full use of the asymmetric bandwidth. It can also improve transaction throughput by increasing the commit ratio of query transactions as much as possible.

• The KIPS Transactions:PartA
• /
• v.12A no.5 s.95
• /
• pp.341-354
• /
• 2005

The main bottleneck for large scale VOD systems is bandwidth of storage or network I/O due to the large number of client requests simultaneously, and then efficient techniques are required to solve the bottleneck problem of the VOD system. Patching is one of the most efficient techniques to overcome the bottleneck of the VOD system through the use of multicast scheme. In this paper, we propose a new patching scheme, called P2P proxy patching, for improving the typical patching technique by jointly using the prefix caching and P2P proxy. In our proposed scheme, each client plays a role in a proxy to multicast a regular stream to other clients that request the same video stream. Due to the use of the P2P proxy and the prefix caching, the client requests that ive out of the patching window range can receive the regular stream from other clients in the previous patching group without allocating the new regular channels from the VOD server to the clients. In the performance study, we show that our patching scheme can reduce the server bandwidth requirement about $33\%$ less than that of the existing patching technique with respect to prefix size and request interval.

• Journal of KIISE:Computer Systems and Theory
• /
• v.30 no.12
• /
• pp.708-713
• /
• 2003

For many years clustered heterogeneous web server architecture has been formed on the internet because the explosive internet services and the various quality of requests. The critical point in cluster environment is the mapping schemes of request to server. and recently this is the main issue of internet architecture. The topic of previous mapping methods is to assign equal loads to servers in cluster using the number of requests. But recent growth of various services makes it hard to depend on simple load balancing to satisfy appropriate latency. So mapping based on requested content to decrease response time and to increase cache hit rates on entire servers - so called “content-based” mapping is highly valuated on the internet recently. This paper proposes Prioritized Highest Random Weight mapping(PHRW mapping) that improves content-based mapping to properly fit in the heterogeneous environment. This mapping scheme that assigns requests to the servers with priority, is very effective on heterogeneous web server cluster, especially effective on decreasing latency of reactive data service which has limit on latency. This paper have proved through algorithm and simulation that proposed PHRW mapping show higher-performance by decrease in latency.

• Journal of the Korean Geophysical Society
• /
• v.3 no.4
• /
• pp.235-244
• /
• 2000

We studied basic ideas of a network based Gravity/Magnetic data processing server/client system which provides functions of data processing, forward modeling, inversion and data process on Data Base. This Java technology was used to provide facilities, socket communication and JDBC(Java Database Connectivity) technology to produce an effective and practical client application. The server computers are linked by network to process the MPI parallelized computing. This can provide useful devices of the geophysical process and modeling that usually require massive computing performance and time. Since this system can be accessed by lots of users, it can provides the consistent and confident results through the verified processing programs. This system also makes it possible to get results and outputs through internet when their local machines are connected to the network. It can help many users who want to omit the jobs of system administration and to process data during their field works.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.12
• /
• pp.67-73
• /
• 2010

In SIP(Session Initiation Protocol) environment, the presence event notification operation makes presence service user to recognize presence information status changes of the other party. In conventional method, the user should send each SIP SUBSCRIBE message containing the address of the other party to the presence server. Furthermore each presence subscription requires refresh messages, and the amount of notification messages from the other party becomes large. These facts increases network traffic and the load of presence server. In this paper, to solve these problems a new presence list service has been suggested. It uses a presence list consists of URI of the other party and make it possible to subscribe by using one SUBSCRIBE message. So this method decreases the amount of SUBSCRIBE messages and refresh messages, and it also decreases the amount processing event notification messages from the subscribed the other party. And to increase the efficiency, a presence filtering method which enables to include some parts of selected presence information into the notification message body has been also suggested. The implemented system can reduce SIP message related network traffic and message processing time of the presence server. The performance of this proposed system has been evaluated by experiments, and the results showed decreasing of server processing time.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.2B
• /
• pp.36-43
• /
• 2005

This paper suggests a method to effectively apply an application model of fuzzy-neural network to the optimal load distribution algorithm, considering the complication and non-linearity of the web server environment. We use the clustering web server in the linux system and it consists of a load balancer that distributes the network loads and some of real servers that processes the load and responses to the client. The previous works considered only with the scrappy decision information such as the connections. That is, since the distribution algorithm depends on the input of the whole network throughput, it was proved inefficient in terms of performance improvement of the web server. With the proposed algorithm, it monitors the whole states of both network input and output. Then, it infers CPU and memory states of each real server and effectively distributes the requests of the clients. In this paper, the proposed model is compared with the previous method through simulations and we analysis the results to develop the optimal and intelligent load balancing model.

• The KIPS Transactions:PartA
• /
• v.15A no.4
• /
• pp.227-238
• /
• 2008

Recently, as network environment has broadened, the demands on VOD have been increased. The VOD services can be categorized into two types, RVOD and NVOD. Practical VOD services adopt one of them exclusively. Since a method using only one of RVOD and NVOD is not able to deal with frequently variable demand of clients, it leads to a result of overload on a server and a waste of server bandwidth. The efficiency of the network resource usage becomes lower. Hence this paper presents a study on the protocol for efficient VOD services. We propose a new protocol appliable for the existing VOD service algorithm, analyze its performance through simulation, and developed server/client systems applying the new protocol. We propose a mode switching protocol combined with protocols used in RVOD and NVOD. The proposed protocol is not able only to control both RVOD and NVOD but also to change the mode between RVOD and NVOD. As a result of using the proposed protocol to meet frequently variable demand, server bandwidth can be used efficiently. Especially, it can be applied to the existing VOD service algorithms. Therefore, we expect that the proposed protocol in this paper will be widely used in emerging VOD markets.