• Journal of the Semiconductor & Display Technology
• /
• v.19 no.3
• /
• pp.61-67
• /
• 2020

This paper is to propose a hybrid memory adaptor using next-generation nonvolatile memory devices such as phase-change memory to improve the performance limitations of OpenStack-based object storage systems. The proposed system aims to improve the performance of the account and container servers for object metadata management. For this, the proposed system consists of locality-based dynamic page buffer, write buffer, and nonvolatile memory modules. Experimental results show that the proposed system improves the hit rate by 5.5% compared to the conventional system.

• Journal of the Korea Convergence Society
• /
• v.8 no.7
• /
• pp.29-37
• /
• 2017

Compared to the commercial networks, R&E networks have the strength such as flexible network engineering and design. Based on those features of R&E networks, we propose our storage cloud service model which supports general-purpose network users in a central region and experimental network users in distributed regions simultaneously. We prototype our service model utilizing multiple proxy controllers of OpenStack Swift service in order to deploy several regions via experimental backbone networks. Our experiments on the influence of the network latency and the size of data to be transmitted show that the bigger size of data is preferable to the smaller size of data in an experimental backbone network where the network latency increases within 10ms because the rate of throughput decline in the bigger object is comparatively small. It means that our service model is appropriate for experimental network users who directly access the service in order to move intermittently high volume of data as well as normal users in the central region who access the service frequently.

• KIISE Transactions on Computing Practices
• /
• v.22 no.6
• /
• pp.296-301
• /
• 2016

Object-based storage is an efficient storage solution that can handle unstructured data and shows better security and scalability than traditional block-based storage. However, in terms of power management, Object-based storage writes multiple copies in storage cluster, hence many servers consume unnecessary power in idle state. In order to resolve this problem, it is necessary to apply power management strategy by adjusting power mode of servers in idle state according to their workloads. In this paper, we proposed a new dynamic power management (DPM) method to transform power mode of storage servers dynamically according to workload information sent from proxy server. The experimental result shows that the proposed power management technic reduces total power consumption by 12% in the OpenStack based Swift object storage.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.05a
• /
• pp.12-15
• /
• 2018

비정형 데이터를 효율적으로 처리하기 위한 대표적인 오브젝트 스토리지로 OpenStack Swift가 있다. 하지만, 오브젝트 스토리지의 일관성 지원은 동기화 지연을 발생시키고 전체 성능에 영향을 미친다. 이런 문제는 기존 시스템에서 발생하는 페이지 스왑, 데이터 중복을 비휘발성 메모리를 사용함으로써 제거할 수 있고 오브젝트 서버의 성능 하락을 완화할 수 있다. 하지만, 비휘발성 메모리를 효율적으로 사용하기 위해서는 비휘발성 메모리 장치별 특성을 고려한 효율적인 데이터 배치가 필요하고 본 논문에서는 이를 위한 마이그레이션 기법을 제안한다. 마이그레이션 기법에서 사용하는 점수식은 First In First Out (FIFO)보다 정확도를 약 11% 향상시켰고, 기존 기법들보다 실행 시간은 42% 감소, 마이그레이션 횟수는 최대 24배 감소, 에너지 소비량은 9% 정도 절약하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.284-286
• /
• 2015

최근 첨단과학응용 분야에서 클라우드 기반의 실험 환경을 구축하는 사례가 늘어가고 있다. 이러한 연구 환경의 패러다임 변화와 관련하여 연구망에서도 고성능 백본 망을 활용한 데이터 공유 서비스에 대한 필요성이 대두되고 있다. 본 논문에서는 데이터 공유 모델의 설계에 앞서 실험적 연구로 공개 소프트웨어 클라우드 운영체제인 OpenStack의 Swift 서비스를 이용하여 오브젝트 스토리지 실험 테스트 베드를 구축하고, 대용량의 데이터 전송 시 발생하는 트래픽을 분석한다. 분석 결과, 리플리카의 생성, 배치 및 선택 등에 따른 유의한 트래픽 발생의 변화를 관찰할 수 있었고, 이러한 결과는 광역 규모의 분산된 데이터 공유 모델 설계 및 망에 대한 요구사항 등으로 활용될 수 있다.

• KIPS Transactions on Computer and Communication Systems
• /
• v.4 no.9
• /
• pp.297-306
• /
• 2015

Cloud computing has been increasingly used in various fields due to its flexibility, scalability, cost effectiveness, etc. Recently, many scientific communities have been attempting to use cloud computing as a way to deal with difficulties in constructing and operating a research infrastructure. Especially, since they need various collaborations based on networking, such as sharing experimental data, redistributing experimental results, and so forth, cloud computing environment that supports high performance networking is required for scientific communities. To address these issues, we propose RealLab, a high performance cloud platform for collaborative research that provides virtual experimental research environment and data sharing infrastructure over KREONET/GLORIAD. Additionally, we describe some RealLab use cases for showing the swift creation of experimental environment and explain how massive experimental data can be transferred and shared among the community members.