Artifact for ELECT: Enabling Erasure Coding Tiering for LSM-tree-based Storage (FAST 2024)
Artifact Description:
This is the artifact for the FAST '24 paper "ELECT: Enabling Erasure Coding Tiering for LSM-tree-based Storage". ELECT is a distributed tiered KV store that enables replication and erasure coding tiering.
For more detailed documentation, please refer to the README of the ELECT repository.
Paper:
Link to the USENIX FAST'24: https://www.usenix.org/conference/fast24/presentation/ren
Citation:
@INPROCEEDINGS{fast24elect,
TITLE = "{ELECT}: Enabling Erasure Coding Tiering for LSM-tree-based Storage",
AUTHOR = "Yanjing Ren and Yuanming Ren and Xiaolu Li and Yuchong Hu and Jingwei Li and Patrick P.C. Lee",
NOTE = "To appear, won all 3 Artifact-Evaluation badges",
BOOKTITLE = "Proceedings of the 22nd USENIX Conference on File and Storage Technologies (FAST '24)",
ADDRESS = "Santa Clara, CA",
MONTH = "February",
YEAR = "2024",
PUBLISHER = "USENIX Association"
}
Reproducibility status:
This artifact was evaluated by USENIX FAST 2024 Artifact Evaluation Committee members and awarded all 3 Artifact-Evaluation badges: Artifacts Available, Artifacts Functional, and Results Reproduced.
Experiment:
Testbed
As a distributed KV store, ELECT requires a cluster of machines to run. With the default erasure coding parameters (i.e., [n,k]==[6,4]), ELECT requires a minimum of 6 machines as the storage nodes. In addition, we require a server node as the cold tier to store the cold data. We also need a client node to run the YCSB benchmark tool. Therefore, we require at least eight machines to reproduce the evaluations.
Detailed Instructions
Please refer to our artifact evaluation instructions to run the evaluations as in our paper.
Support:
For any support, please email Yanjing Ren (yjren22@cse.cuhk.edu.hk) or create an issue at the GitHub repository.
Launching this artifact will open it within Chameleon’s shared Jupyter experiment environment, which is accessible to all Chameleon users with an active allocation.
Download ArchiveDownload an archive containing the files of this artifact.
Download with git
Clone the git repository for this artifact, and checkout the version's commit
git clone https://github.com/adslabcuhk/elect
# cd into the created directory
git checkout f5299a7114bfebb074ff19d708520a0199cfa2ac
Submit feedback through GitHub issues