Saved in:
Bibliographic Details
Main Authors: Casaletto, Holly, Lefevre, Jeff, Montana, Aldrin, Alvaro, Peter
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.08923
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915335471366144
author Casaletto, Holly
Lefevre, Jeff
Montana, Aldrin
Alvaro, Peter
author_facet Casaletto, Holly
Lefevre, Jeff
Montana, Aldrin
Alvaro, Peter
contents Compaction is a necessary, but often costly background process in write-optimized data structures like LSM-trees that reorganizes incoming data that is sequentially appended to logs. In this paper, we introduce Transformation-Embedded LSM-trees (TE-LSM), a novel approach that transparently embeds a variety of data transformations into the compaction process. While many others have sought to reduce the high cost of compaction, TE-LSMs leverage the opportunity to embed other useful work to amortize IO costs and amplification. We illustrate the use of a TE-LSM in Mycelium, our prototype built on top of RocksDB that extends the compaction process through a cross-column-family merging mechanism. Mycelium enables seamless integration of a transformer interface and aims to better prepare data for future accesses based on access patterns. We use Mycelium to explore three types of transformations: splitting column groups, converting data formats, and index building. In addition to providing a cost model analysis, we evaluate Mycelium's write and read performance using YCSB workloads. Our results show that Mycelium incurs a 20% write throughput overhead - significantly lower than the 35% to 60% overhead observed in naive approaches that perform data transformations outside of compaction-while achieving up to 425% improvements in read latency compared to RocksDB baseline.
format Preprint
id arxiv_https___arxiv_org_abs_2506_08923
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Mycelium: A Transformation-Embedded LSM-Tree
Casaletto, Holly
Lefevre, Jeff
Montana, Aldrin
Alvaro, Peter
Distributed, Parallel, and Cluster Computing
Compaction is a necessary, but often costly background process in write-optimized data structures like LSM-trees that reorganizes incoming data that is sequentially appended to logs. In this paper, we introduce Transformation-Embedded LSM-trees (TE-LSM), a novel approach that transparently embeds a variety of data transformations into the compaction process. While many others have sought to reduce the high cost of compaction, TE-LSMs leverage the opportunity to embed other useful work to amortize IO costs and amplification. We illustrate the use of a TE-LSM in Mycelium, our prototype built on top of RocksDB that extends the compaction process through a cross-column-family merging mechanism. Mycelium enables seamless integration of a transformer interface and aims to better prepare data for future accesses based on access patterns. We use Mycelium to explore three types of transformations: splitting column groups, converting data formats, and index building. In addition to providing a cost model analysis, we evaluate Mycelium's write and read performance using YCSB workloads. Our results show that Mycelium incurs a 20% write throughput overhead - significantly lower than the 35% to 60% overhead observed in naive approaches that perform data transformations outside of compaction-while achieving up to 425% improvements in read latency compared to RocksDB baseline.
title Mycelium: A Transformation-Embedded LSM-Tree
topic Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2506.08923