A Performance Evaluation and Examination of Open-Source Erasure Coding Libraries for Storage

By James S. Plank, Jianqiang Luo, Catherine D. Schuman, Lihao Xu, Zooko Wilcox-O'Hearn. USENIX Conference on File and Storage Technologies, 2009

301 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Rethinking erasure codes for cloud file systems: minimizing I/O for recovery and degraded reads (2012, background): “Performance Metrics: Erasure codes have been evaluated historically on a variety of metrics, such as the CPU impact of encoding and decoding [3, 11, 37], the penalty of updating small amounts of data [5, 26, 52] and the ability to reconfigure systems without re-encoding [3, 7, 26].”
FTI: High performance Fault Tolerance Interface for hybrid systems (2011, background): “Diskless checkpoint [14, 15, 19, 28, 29, 30] was proposed by Plank et al. as a solution to avoid the I/O bottleneck; however several challenges, such as how to optimize the encoding algorithms and how to improve the time and memory efﬁciency of that technique, were important points against its…”
HAIL: a high-availability and integrity layer for cloud storage (2009, methodology): “As noticed from Figure 5, time spent performing dispersal code application using Jerasure is the dominant factor in .le encoding speed (at least 50% of the total encoding cost, excluding I/O).”