Performance evaluation of parallel file systems for PC clusters and ASCI red

Garg, Sharad; Mache, Jens

doi:10.1109/clustr.2001.959973

Cited by 6 publications

(1 citation statement)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A micro-benchmark, similar to the one used in [1,[18][19][20][21][22][23], was used to measure the aggregate read and write performance. In this benchmark, each client concurrently opens a common file, then reads or writes disjoint portions of this file, and finally closes it.…”

Section: Experiments Environments and Evaluation Benchmarksmentioning

confidence: 99%

Exploiting redundancy to boost performance in a RAID-10 style cluster-based file system

et al. 2006

View full text Add to dashboard Cite

While aggregating the throughput of existing disks on cluster nodes is a cost-effective approach to alleviate the I/O bottleneck in cluster computing, this approach suffers from potential performance degradations due to contentions for shared resources on the same node between storage data processing and user task computation. This paper proposes to judiciously utilize the storage redundancy in the form of mirroring existed in a RAID-10 style file system to alleviate this performance degradation. More specifically, a heuristic scheduling algorithm is developed, motivated from the observations of a simple cluster configuration, to spatially schedule write operations on the nodes with less load among each mirroring pair. The duplication of modified data to the mirroring nodes is performed asynchronously in the background. The read performance is improved by two techniques: doubling the degree of parallelism and hot-spot skipping. A synthetic benchmark is used to evaluate these algorithms in a real cluster environment and the proposed algorithms are shown to be very effective in performance enhancement.

show abstract