• Proceedings of the IEEK Conference
• /
• 2003.07d
• /
• pp.1327-1330
• /
• 2003

The internet SCSI(iSCSI) disk has been studied as a storage system which can be directly connected to TCP/IP network. We designed and implemented a shared disk following the iSCSI protocol and providing cache consistency. It is named as intelligent iSCSI(i$^2$SCSI) disk. The i$^2$SCSI disk provides cache consistency of all blocks that belong to the disk using a conventional lease method and it uses 'contiguous blocks-level locking' The prototype of the i$^2$SCSI disk emulator and its client is designed and implemented in Linux 2.4.

• Journal of Digital Convergence
• /
• v.11 no.11
• /
• pp.421-427
• /
• 2013

Disk Cache Manager(DCM), a functional server of microkernel based, to improve the I/O power of shared disks is designed and implemented in this work. DCM interfaces other different servers with message passing through ports by serving as a system actor the multi-thread mode on the Minix3 micro-kernel. DCM proposed in this paper uses the shared disk logically as a Seven Disk and Sodd Disk to enable parallel I/O. DCM enables the efficient placement of disk data because it raises disk cache hit-ratio by increasing the cache size when the utilization of the particular disk is high. Through experimental results, we show that DCM is quite efficient for a shared disk with higher utilization.

• Journal of KIISE:Databases
• /
• v.35 no.6
• /
• pp.469-480
• /
• 2008

A shared disk (SD) cluster couples multiple nodes for high performance transaction processing, and all the coupled nodes share a common database at the disk level. To reduce the number of disk accesses, each node caches database pages in its memory buffer. Since a particular page may be cached simultaneously in different nodes, cache consistency should be maintained to ensure that nodes can always access the most recent version of database pages. Most cache consistency schemes proposed in the SD cluster adopted LRU as a buffer replacement algorithm. In this paper, we first present four buffer replacement algorithms that consider the characteristics of the SD cluster. Then we compare the performance of the buffer replacement algorithms. We perform the experiments on a variety of cluster configurations and database workloads. The experiment results show that the proposed algorithms achieve performance improvement up to 5 times of LRU algorithm.

• Journal of KIISE:Computer Systems and Theory
• /
• v.30 no.1
• /
• pp.33-49
• /
• 2003

Recently, there have been large storage demands for manipulating multimedia data. To solve the tremendous storage demands, one of the major researches is the SAN(Storage Area Network) that provides the local file requests directly from shared-disk storage and also eliminates the server bottlenecks to performance and availability. SAN also improve the network latency and bandwidth through new channel interface like FC(Fibre Channel). But to manipulate the efficient storage network like SAN, traditional local file system and distributed file system are not adaptable and also are lack of researches in terms of a metadata structure for large-scale inode object such as file and directory. In this paper, we describe the architecture and design issues of our shared-disk file system and provide the efficient bitmap for providing the well-formed block allocation in each host, extent-based semi flat structure for storing large-scale file data, and two-phase directory structure of using Extendible Hashing. Also we describe a detailed algorithm for implementing the file system's device driver in Linux Kernel and compare our file system with the general file system like EXT2 and shard disk file system like GFS in terms of file creation, directory creation and I/O rate.

• Journal of KIISE:Databases
• /
• v.30 no.6
• /
• pp.629-640
• /
• 2003

A shared disk (SD) cluster couples multiple nodes for high performance transaction processing, and all the coupled nodes share a common database at the disk level. In the SD cluster, a transaction routing corresponds to select a node for an incoming transaction to be executed. An affinity-based routing can increase local buffer hit ratio of each node by clustering transactions referencing similar data to be executed on the same node. However, the affinity-based routing is very much non-adaptive to the changes in the system load, and thus a specific node will be overloaded if transactions in some class are congested. In this paper, we propose a dynamic transaction routing scheme that can achieve an optimal balance between affinity-based routing and dynamic load balancing of all the nodes in the SD cluster. The proposed scheme is novel in the sense that it can improve the system performance by increasing the local buffer hit ratio and reducing the buffer invalidation overhead.

• Journal of KIISE:Software and Applications
• /
• v.26 no.10
• /
• pp.1178-1178
• /
• 1999

A spatial join has the property that its execution time exponentially increases in proportion to the number of spatial objects. Recently, there have been many attempts for improving the performance of the spatial join by using parallel processing schemes, In the case of executing parallel spatial join using the parallel machine with shared disk architecture, the disk bottleneck of parallel processing of spatial join worsens in comparison with sequential spatial join. This paper presents the algorithms of task creation and assignment to reduce the disk bottleneck caused by accessing the shared disk at the same time, and to minimize message passing between processors, This paper proposes object caching which is a higher level of abstraction than page caching, and uses it to do creation and assignment of tasks according to temporal and spatial localities for minimizing disk access time. The object caching shows the performance improvement of 50%. The task creation and assignment using localities gives the gain of 30% and 20%. Overall performance evaluation of the proposed algorithms shows 7.2 times speed up than those of sequential execution of spatial joins.

• Spatial Information Research
• /
• v.10 no.1
• /
• pp.93-106
• /
• 2002

The traditional file system are designed to store and manage fur small size files. So. we cannot process the huge files related with geographic information data using the traditional file system such as unix file system or linux file system. In this paper, we propose new metadata structures and management mechanisms for the large file system in geographic information system. The proposed mechanisms use dynamic multi-level mode for large files and dynamic bitmap for huge file system. We implement the proposed mechanisms in the metadata structures of SANtopia is shared disk huge file system for storage area networks(SAN).

• Proceedings of the IEEK Conference
• /
• 2003.07d
• /
• pp.1633-1636
• /
• 2003

In this paper, we developed the scheme to grow to use newly added disk space without having to kill the application, unmount file system. This scheme, called online resizing, can resize the file system layout with the advent of Logical Volume Manager. The online resizing scheme is designed and implemented in linux cluster system where multiple hosts share the disk data in storage area network environment. It is incorporated with SANfs shared file system and can perform resizing technique with SANfs-VM volume manager. The experimental result shows that it can maximize the availability and capacity of the SANfs system which are important for modem servers where must not lose their customer.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.12 no.4
• /
• pp.71-79
• /
• 2016

This study proposes a performance model of a shared bus multi-processor system and analyzes the effect of input/output types on system performance and overload of shared resources. This system performance model reflects the memory reference time in relation to the effect of input/output types on shared resources and the input/output processing time in relation to the input/output processor, disk buffer, and device standby places. In addition, it demonstrates the contribution of input/output types to system performance for comprehensive analysis of system performance. As the concept of workload in the probability theory and the presented model are utilized, the result of operating and analyzing the model in various conditions of processor capability, cache miss ratio, page fault ratio, disk buffer hit ratio (input/output processor and controller), memory access time, and input/output block size. A simulation is conducted to verify the analysis result.

• Journal of KIISE:Databases
• /
• v.31 no.2
• /
• pp.108-121
• /
• 2004

In this paper, we propose an enhanced snapshot technique that solves performance degradation when snapshot is initiated for the storage cluster system. However, traditional snapshot technique has some limits adapted to large amount storage shared by multi-hosts in the following aspects. As volume size grows, (1) it deteriorates crucially the performance of write operations due to additional disk access to verify COW is performed. (2) Also it increases excessively the blocking time of write operation performed during the snapshot creation time. (3)Finally, it deteriorates the performance of write operations due to additional disk I/O for mapping block caused by the verification of COW. In this paper, we propose an efficient snapshot technique for large amount storage shared by multi-hosts in SAN Environments. We eliminate the blocking time of write operation caused by freezing while a snapshot creation is performing. Also to improve the performance of write operation when snapshot is taken, we introduce First Allocation Bit(FAB) and Snapshot Status Bit(SSB). It improves performance of write operation by reducing an additional disk access to volume disk for getting snapshot mapping block. We design and implement an efficient snapshot technique, while the snapshot deletion time, improve performance by deallocation of COW data block using SSB of original mapping entry without snapshot mapping entry obtained mapping block read from the shared disk.