PDS: An I/O-Efficient Scaling Scheme for Parity Declustered Data Layout

Li, Zhipeng; Xu, Yinlong; Tian, Chengjin; Bai, Youhui

doi:10.1109/icpp.2017.49

Cited by 1 publication

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This paper was presented in part at the 46th IEEE International Conference on Parallel Processing (ICPP), 2017 [14]. In the conference paper, we proposed an efficient scaling algorithm, PDS (Parity Declustering Scaling), to scale up disk arrays with parity declustered data layout.…”

Section: Acknowledgmentmentioning

confidence: 99%

A Fast Approach to Scale Up Disk Arrays With Parity Declustered Data Layout by Minimizing Data Migration

Li¹,

Xu²,

Tian³

et al. 2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

Parity declustering is widely deployed in erasure-coded storage systems so as to provide fast recovery and high data availability. However, to perform scaling on such redundant array of inexpensive disks (RAIDs), it is necessary to preserve parity declustered data layout so as to preserve the properties after scaling. Unfortunately, existing scaling algorithms fail to achieve this goal so they cannot be applied for scaling RAIDs with parity declustering. To address this challenge, we develop an efficient online scaling scheme called parity declustering scaling (PDS), which employs an auxiliary balanced incomplete block design to define the data migration so as to preserve parity declustered data layout. Furthermore, PDS can also be applied to scale RAIDs for improving reliability and/or storage efficiency as options by allocating more parity blocks and/or data blocks in stripes. We provide theoretical proofs to formally show that PDS preserves parity declustered data layout, and achieves uniform distributions of data and parity blocks after scaling while requiring only the minimal data migration. We implement PDS in Linux kernel 3.14.72 and evaluate its performance with real-world traces. The results show that PDS can reduce 82.37 percent of scaling time and 18.25 percent of user response time during scaling on average, compared with ''movingeverything'' round-robin approach adapted to achieve parity declustered data layout after scaling. INDEX TERMS Scaling, parity declustering, capacity expansion, reliability, data migration.

show abstract

Section: Acknowledgmentmentioning

confidence: 99%