• KIISE Transactions on Computing Practices
• /
• v.21 no.8
• /
• pp.561-566
• /
• 2015

Hadoop is becoming widely adopted in scientific and commercial areas as an open-source distributed data processing framework. Recently, for real-time processing and analysis of data, an attempt to apply high-performance computing technologies to Hadoop is being made. In this paper, we have expanded the Hadoop Filesystem library to support Lustre, which is a popular high-performance parallel distributed filesystem, and implemented the Hadoop MapReduce execution environment over the Lustre filesystem. We analysed Hadoop MapReduce over Lustre by using Hadoop standard benchmark tools. We found that Hadoop MapReduce over Lustre execution has a performance 2-13 times better than a typical Hadoop MapReduce execution.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2014.07a
• /
• pp.329-332
• /
• 2014

클라우드 컴퓨팅이 활성화 됨에 따라 기존의 파일 시스템과는 다른 대용량 파일 처리에 효율적인 분산파일시스템의 요구가 대두 되었다. 그 중에 하둡 분산 파일 시스템(Hadoop Distribute File System, HDFS)은 기존의 분산파일 시스템과는 달리 가용성과 내고장성을 보장하고, 데이터 접근 패턴을 스트리밍 방식으로 지원하여 대용량 파일을 효율적으로 저장할 수 있다. 이러한 장점 때문에, 클라우드 컴퓨팅의 파일시스템으로 대부분 채택하고 있다. 하지만 실제 HDFS 데이터 집합에서 대용량 파일 보다 소용량 파일이 차지하는 비율이 높으며, 이러한 다수의 소 용량 파일은 데이터 처리에 있어 높은 처리비용을 초래 할 뿐 만 아니라 메모리 성능에 악영향을 끼친다. 하지만 소 용량 파일을 프리패칭 함으로서 이러한 문제점을 해결 할 수 있다. HDFS의 데이터 프리페칭은 기존의 데이터 프리페칭의 기법으로는 적용하기 어려워 HDFS를 위한 데이터 프리패칭 기법을 제안한다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.10 no.10
• /
• pp.1115-1122
• /
• 2015

Hadoop framework was designed to be suitable for processing very large files. On the other hand, when processing the Small Files, it waste the resource of a distributed system, and occur performance degradation. It is shown noticeable the more the Small Files. This problem is caused by the Small Files, it can be solved through the merging of associated Small Files. But a way of merging of Small Files has some limited point. in this paper, examines existing limit of merging method, design merging method Small Files for effective process.

• Journal of Internet Computing and Services
• /
• v.13 no.5
• /
• pp.55-64
• /
• 2012

Nowadays, as Cloud computing becomes popular, a need for a DFS(distributed file system) is increased. But, in the current Cloud computing environments, there is no DFS framework that is sufficient to protect sensitive private information from attackers. Therefore, we designed and proposed a secure scheme for distributed file systems. The scheme provides confidentiality and availability for a distributed file system using a secret sharing method. In this paper, we measured the speed of encryption and decryption for our proposed method, and compared them with that of SEED algorithm which is the most popular algorithm in this field. This comparison showed the computational efficiency of our method. Moreover, the proposed secure read/write model is independent of Hadoop DFS structure so that our modified algorithm can be easily adapted for use in the HDFS. Finally, the proposed model is evaluated theoretically using performance measurement method for distributed secret sharing model.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.23 no.5
• /
• pp.831-847
• /
• 2013

The various types of data are being created in large quantities resulting from the spread of social media and the mobile popularization. Many companies want to obtain valuable business information through the analysis of these large data. As a result, it is a trend to integrate the big data technologies into the company work. Especially, Hadoop is regarded as the most representative big data technology due to its terabytes of storage capacity, inexpensive construction cost, and fast data processing speed. However, the authentication token system of Hadoop Distributed File System(HDFS) for the user authentication is currently vulnerable to the replay attack and the datanode hacking attack. This can cause that the company secrets or the personal information of customers on HDFS are exposed. In this paper, we analyze the possible security threats to HDFS when tokens or datanodes are exposed to the attackers. Finally, we propose the secure authentication protocol in HDFS based on hash chain.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.23 no.5
• /
• pp.803-813
• /
• 2013

As the developments of smart devices and social network services, the amount of data has been exploding. The world is facing Big data era. For these reasons, the Big data processing technology which is a new technology that can handle such data has attracted much attention. One of the most representative technologies is Hadoop. Hadoop Distributed File System(HDFS) designed to run on commercial Linux server is an open source framework and can store many terabytes of data. The initial version of Hadoop did not consider security because it only focused on efficient Big data processing. As the number of users rapidly increases, a lot of sensitive data including personal information were stored on HDFS. So Hadoop announced a new version that introduces Kerberos and token system in 2009. However, this system is vulnerable to the replay attack, impersonation attack and other attacks. In this paper, we analyze these vulnerabilities of HDFS security and propose a new protocol which complements these vulnerabilities and maintains the performance of Hadoop.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.12 no.2
• /
• pp.367-374
• /
• 2017

This paper discusses management problems of Hadoop distributed node, which is a platform for big data processing, and proposes a novel technique for enabling flexible node management of Hadoop Distributed File System. Hadoop cannot configure Hadoop cluster dynamically because it judges temporarily unavailable nodes as a failure. Delayed block replication scheme proposed in this paper delays the removal of unavailable node as much as possible so as to be easily rejoined. Experimental results show that the proposed scheme increases flexibility of node management with little impact on distributed processing performance when the cluster size changes.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2014.07a
• /
• pp.337-340
• /
• 2014

클라우드 시스템이 큰 이슈로 떠오르면서 그 기반이 되는 분산 파일 시스템에 관한 연구가 계속되고 있다. 최근 제안된 분산파일 시스템은 대부분 확장 가능하며 신뢰성이 있는 시스템으로 구성되어 있으며 내고장성(Fault tolerance)과 높은 가용성을 위해 데이터 복제 기법을 사용하며 하둡 분산 파일 시스템에서는 블락의 복제수를 기본3개로 지정한다. 그러나 이 정책은 복제수가 많아지면 많아질수록 가용성은 높아지지만 스토리지 또한 증가한다는 단점이 있다. 본 논문에선 이러한 문제점을 해결하기 위해 최소한의 블락 복제수와 복제된 블락을 효율적으로 배치하여 더 좋은 성능과 부하분산(Load Balancing)하기 위한 기법을 제안한다.

• Annual Conference of KIPS
• /
• 2017.11a
• /
• pp.45-47
• /
• 2017

하둡은 대표적인 빅데이터 처리 프레임워크로 널리 사용되고 있지만 하둡 어플리케이션은 고성능컴퓨팅 환경에서 하둡 분산파일시스템이 아닌 러스터 병렬 파일시스템 위에서도 수행될 수 있다. 그러나 이를 위해서 추가적으로 러스터 병렬파일시스템을 구축하고 관리하는 것은 시간 소모적인 업무가 될 수 있다. 본 연구는 러스터 병렬파일시스템의 오토 프로비저닝을 위한 암바리 서비스의 설계 방안에 대해서 제안한다. 암바리는 하둡 클러스터의 프로비저닝, 관리, 모니터링을 위한 운영 관리 프레임워크이며 운영자의 필요에 따라서 확장할 수 있는 서비스 프레임워크를 제공한다. 본 연구에서는 암바리를 통해서 러스터 병렬파일시스템을 오토 프로비저닝하고 관리하기 위한 확장 서비스를 설계하였으며 서비스를 위한 컴포넌트와 각 컴포넌트별 중요한 기능 사항에 대해서 논하였다.

• Journal of Advanced Navigation Technology
• /
• v.18 no.4
• /
• pp.401-408
• /
• 2014

Hadoop is composed with MapReduce programming model for distributed processing and HDFS distributed file system. Hadoop is suitable framework for big data processing, but processing of mass small files have many problems. The processing of mass small file in hadoop have problems to created one mapper per one file, and it have problems to needed many memory for store of meta information of file. This paper have comparison evaluation processing method of mass small file with various method in hadoop platform. The processing of general compression format is inadequate because of processing by one mapper regardless of data size. The processing of sequence and hadoop archive file is removed memory problem of namenode by compress and combine of small file. Hadoop archive file is faster then sequence file about combine time of small file. The processing using CombineFileInputFormat class is needed not combine of small file, and it have similar speed big data processing method.