The code provides an example implementation of the idea shown in the paper "RapidCDC: Leveraging Duplicate Locality to Accelerate Chunking in CDC-based Deduplication Systems", which will appear in SoCC 2019.
Cite the paper like below,
@inproceedings{10.1145/3357223.3362731,
author = {Ni, Fan and Jiang, Song},
title = {RapidCDC: Leveraging Duplicate Locality to Accelerate Chunking in CDC-Based Deduplication Systems},
year = {2019},
isbn = {9781450369732},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3357223.3362731},
doi = {10.1145/3357223.3362731},
booktitle = {Proceedings of the ACM Symposium on Cloud Computing},
pages = {220–232},
numpages = {13},
keywords = {deduplication, locality, storage systems, CDC, content-defined chunking},
location = {Santa Cruz, CA, USA},
series = {SoCC ’19} }
or
Fan Ni and Song Jiang. 2019. RapidCDC: Leveraging Duplicate Locality to Accelerate Chunking in CDC-based Deduplication Systems. In Proceedings of the ACM Symposium on Cloud Computing (SoCC ’19). Association for Computing Machinery, New York, NY, USA, 220–232. DOI:https://doi.org/10.1145/3357223.3362731