• Journal of Advanced Navigation Technology
• /
• v.13 no.5
• /
• pp.684-690
• /
• 2009

In this paper, we propose the acceleration method of the DDR-SSD RAID level 5. The DDR-SSD is the storage device of the Next Generation Storage(NGS) system. The DDR-SSD has different characteristics with HDD and Flash SSD. That's why the DDR-SSD RAID level 5 does not provide the best performance when the normal acceleration method is used. In this paper, to accelerate the DDR-SSD RAID level 5 operation, we propose the parity cache and the architecture of the parity cell. The parity cache stores only parity blocks. This acceleration method proposed in this paper reduce the number of the disk access and the overhead of parity operations.

• Journal of Advanced Navigation Technology
• /
• v.14 no.6
• /
• pp.916-927
• /
• 2010

In this paper, we analyze the performance of the parity cache enabled RAID level-5 via the simulation. This RAID system consists of the DDR memory-based storage devices. To do this, we develop the simulation model and suggest the basic performance analysis data which we want to get via the simulation. And we implement the simulator based on the simulation model and execute the simulator. From the result of the simulation, we expect that the parity cache enabled RAID level-5 configured by the DDR memory based storage devices has the positive effectiveness to the enhancing of the storage system performance if the storage access patterns of applications are tuned.

• Journal of the Korea Society of Computer and Information
• /
• v.4 no.2
• /
• pp.8-18
• /
• 1999

It is very important to recover data immediately at a single disk failure for critical applications such as multimedia storage systems. real-time systems and so on. As an efficient solution, this paper proposes that RAID level conversion scheme to improve the performance before a failed disk is replaced with a new disk. By using this scheme, it does not require an additional disk to recover data. Comparing with previous studies, this scheme is appropriate to low cost system that has not additional redundant device. The performance of proposed scheme is evaluated and analyzed with that of RAID level 5 for various requested sizes through the simulation. The results show that the performance of the proposed scheme is improved up to 20 percents compared with that of RAID level 5 at the failure mode and 80 percents at reconfigured mode.

• Journal of KIISE:Computer Systems and Theory
• /
• v.27 no.7
• /
• pp.675-683
• /
• 2000

For real time services of multimedia applications, storage systems should provide data without degrading their performance. Since it is very important to recover data immediately at a disk failure, the disk recovery system is required. This paper presents a hybrid recovery scheme which prevents degraded the performance on a single disk failure at RAID level 5 architecture until the failed disk is replaced with a new disk. The proposed scheme is very economical compared to previous spare disk schemes because it does not use extra disks. The performance of the proposed scheme is evaluated and analyzed with that of the RAID level 5 for various requested sizes through the simulation. The results show that the performance of the proposed scheme is improved up to 20 percents at the failure mode and 80 percents at the reconfigured mode. After a multimedia server system has been built with a RAID controller and hard disks, the data recovery performance of the propose scheme are compared with the results of simulation.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.6
• /
• pp.47-56
• /
• 2010

HDD-based RAIDs have been used in high-capacity storage systems for traditional data server. However, their data reliability are relatively low and they consume lots of power since hard disk drive is weak on shock and its power consumption is high due to frequent spindle motor operation. Therefore, this paper presents new SSD based RAID system architecture using various erasure codes. The proposed methode applys Reed-Solomon, EVENODD, and Liberation coding schemes onto file system level and device driver level, respectively. Besides, it uses data allocation method to minimize the side effect of reducing the lifespan of SSD. Detail experimental results show that Liberation code increase wear-leveling rates of SSD based RAID-6 more than other codes. The SSD based RAID system applying erasure codes at the device driver level shows better performance than that at the file system level. I/O performance of RAID-6 system using SSD is 4.5%~8.5% higher than that of using HDD and the power consumption of the RAID system using SSD is 18%~40% less than that of using HDD.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04a
• /
• pp.25-27
• /
• 2003

RAID 시스템에서 디스크 캐시는 시스템 성능 향상에 중요한 요소 중 하나이다. 2단계 캐시는 1단계 캐시에 비해 우수한 성능을 보이고 시간적, 공간적 지역성에도 효율적이다. 제안된 캐시 시스템은 2 단계로 구성되어 1단계 캐시는 작은 블록 크기로 구성되어 세트 연관 사상 방식을 이용하고 2단계 캐시는 큰 블록 크기로 구성되어 전 연관 사상 방식을 사용한다. 본 논문에서는 특히 대용량 디스크 캐시에서 디스크입출력 시간을 향상시키고 효율적으로 일관성을 유지할 수 있는 디스크 제어기 상에 위치하는 RAID 5 디스크 캐시의 모델을 제시하여 적중률을 향상시켜 수행속도를 개선시키고자 한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04a
• /
• pp.64-66
• /
• 2004

단일 입출력 디스크(SDIO)는 클러스터 환경에서 빠르고 신뢰성 있는 분산 저장장치를 제공한다. 단일 입출력 디스크는 주로 RAID 레벨 0이나 레벨 1을 사용하는데, RAID 레벨 5를 사용함으로써 좋은 성능과 좋은 신뢰도 그리고 높은 디스크 용량 사용률을 얻을 수 있다. 그러나 RAID 레벨 5를 사용함으로써 네트웍 오버헤드 문제, 작은 데이터의 기록 성능 문제, 동시 기록 문제가 발생한다. 위의 새 가지 문제를 해결하거나 최소화하기 위하여 본 논문에서는 Parity Cumulating이라는 접근방법을 제시한다. Parity Cumulating은 패리티의 계산을 두 개의 노드로 분산시킴으로써 네트웍 오버헤드를 줄이고, 패리티를 버퍼에 저장하고 디스크에 작업이 없을 때 처리함으로써 작은 데이터의 기록 성능을 높이며 동시 기록시 일관성을 지킨다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.04a
• /
• pp.3-5
• /
• 2000

RAID 레벨 5는 쓰기 시에 패리티 갱신을 위한 4번의 디스크 접근으로 인하여 OLTP와 같이 상대적으로 빈번한 디스크 접근을 가지고 데이터 크기가 작으며 쓰기의 횟수가 많은 작업환경에서 성능이 떨어지게 된다. 데이터와 패리티에 대한 캐싱은 OLTP환경에서의 쓰기에 대한 문제를 해결하기 위한 기법이다. 본 논문에서는 리눅스 운영체제의 파일 데이터 구조에 변화를 주고, 커널에서 얻어진 정보를 디스크 캐쉬의 운영에 이용한다. 스트라입 크기(G)를 가지는 RAID 레벌 5에서 패리티 캐쉬의 크기가 전체 캐쉬 크기의 1/G 이하 일 경우 데이터 패리티 캐쉬 크기 변화에 영향을 받지 않고 캐쉬의 그룹 단위 운영과 그에 따른 패리티의 미리 읽기를 가능하게 하여 패리티에 대한 추가적인 읽기를 최소화하는 기법을 제안한다. 본 논문의 실험 결과는 초당 디스크에 도착하는 평균 디스크 접근 요구 개수에 변화를 주어 시뮬레이션 방법으로 입증하였으며, OLTP 환경에서 데이터와 패리티 캐쉬를 독립적으로 운영하는 일반적인 캐쉬 운영 방법에 비해 평균 응답시간을 단축시킬 수 있음을 알 수 있다.

• Proceedings of the IEEK Conference
• /
• 2000.06c
• /
• pp.47-50
• /
• 2000

In this paper, we propose a new destage algorithms, called the Dynamic Adaptive Threshold which determines turn-on and turn-off thresholds dynamically depending on the current write cache occupancy level and the differential rate of the host write requests. For performance evaluation, the proposed algorithm is compared with the wellknown High-Low Water Mark (HLWM) algorithm. Performance tests are fulfilled with our cached RAID 5 simulator. The simulation results show that the proposed algorithm outperforms the HLWM algorithm in terms of response time of host reads and write cache hit ratio under various workloads.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.2
• /
• pp.305-311
• /
• 2010

iATA (Internet Advanced Technology Attachment) is a block-level protocol developed to transfer ATA commands over TCP/IP network, as an alternative network storage solution to address insufficient storage problem in mobile devices. This paper employs RAID5 distributed storage servers concept into iATA, in which the idea behind is to combine several machines with relatively inexpensive disk drives into a server array that works as a single virtual storage device, thus increasing the reliability and speed of operations. In the case of one machine failed, the server array will not destroy immediately but able to function in a degradation mode. Meanwhile, information can be easily recovered by using boolean exclusive OR (XOR) logical function with the bit information on the remaining machines. We perform I/O measurement and benchmark tool result indicates that additional fault tolerance feature does not delay read/write operations with reasonable file size ranged in 4KB-2MB, yet higher data integrity objective is achieved.