Cross-Rack-Aware Updates in Erasure-Coded Data Centers
Refereed conference paper presented and published in conference proceedings


引用次數
替代計量分析
.

其它資訊
摘要The update performance in erasure-coded data centers is often bottlenecked by the constrained cross-rack bandwidth. We propose CAU, a cross-rack-aware update mechanism that aims to mitigate the cross-rack update traffic in erasure-coded data centers. CAU builds on three design elements: (i) selective parity updates, which select the appropriate parity update approach based on the update pattern and the data layout to reduce the cross-rack update traffic; (ii) data grouping, which relocates and groups updated data chunks in the same rack to further reduce the cross-rack update traffic; and (iii) interim replication, which stores a temporary replica for each newly updated data chunk. We evaluate CAU via trace-driven analysis, local cluster experiments, and Amazon EC2 experiments. We show that CAU enhances state-of-the-arts by mitigating the cross-rack update traffic as well as maintaining high update performance in both local cluster and geo-distributed environments.
著者Zhirong Shen, Patrick P. C. Lee
會議名稱47th International Conference on Parallel Processing (ICPP 2018)
會議開始日13.08.2018
會議完結日16.08.2018
會議地點Eugene, Oregon
會議國家/地區美國
會議論文集題名Proceedings of the 47th International Conference on Parallel Processing (ICPP 2018)
出版年份2018
月份8
出版社ACM
文章號碼80
語言美式英語

上次更新時間 2021-19-09 於 00:57