The reliability and high performance of metadata service is crucial to the store architecture. A novel design of a two-level metadata server file system （TTMFS） is presented, which behaves high reliability and perfo...The reliability and high performance of metadata service is crucial to the store architecture. A novel design of a two-level metadata server file system （TTMFS） is presented, which behaves high reliability and performance. The merits both centralized management and distributed management are considered simultaneously in our design. In this file system, the advanced-metadata server is responsible for manage directory metadata and the whole namespace. The double-metadata server is responsible for maintaining file metadata. And this paper uses the Markov return model to analyze the reliability of the two-level metadata server. The experiment data indicates that the design can provide high throughput.展开更多
Distribution of metadata in a metadata server cluster is important in mass storage system. A good distribution algorithm has a significant influence on the system performance, availability and scalability. Subtree par...Distribution of metadata in a metadata server cluster is important in mass storage system. A good distribution algorithm has a significant influence on the system performance, availability and scalability. Subtree partition and hash are two traditional metadata distribution algorithms used in distributed file systems. They both have a defect in system scalability. This paper proposes a new directory hash （DH） algorithm. By treating directory as the key value of hash function, implementing concentrated storage of metadata, pipelining operations and prefetching technology, DH algorithm can enhance the system scalability on the premise without sacrificing system performance.展开更多
基金Supported by the Industrialized Foundation ofHebei Province (F020501)
文摘The reliability and high performance of metadata service is crucial to the store architecture. A novel design of a two-level metadata server file system （TTMFS） is presented, which behaves high reliability and performance. The merits both centralized management and distributed management are considered simultaneously in our design. In this file system, the advanced-metadata server is responsible for manage directory metadata and the whole namespace. The double-metadata server is responsible for maintaining file metadata. And this paper uses the Markov return model to analyze the reliability of the two-level metadata server. The experiment data indicates that the design can provide high throughput.
基金Project supported by the National Grand Fundamental Research 973 Program of China （Grant No.2004CB318203）, and the National Natural Science Foundation of China （Grant No.60603074）
文摘Distribution of metadata in a metadata server cluster is important in mass storage system. A good distribution algorithm has a significant influence on the system performance, availability and scalability. Subtree partition and hash are two traditional metadata distribution algorithms used in distributed file systems. They both have a defect in system scalability. This paper proposes a new directory hash （DH） algorithm. By treating directory as the key value of hash function, implementing concentrated storage of metadata, pipelining operations and prefetching technology, DH algorithm can enhance the system scalability on the premise without sacrificing system performance.
