Saved in:
Bibliographic Details
Main Authors: Qiu, Jiansheng, Yuan, Fangzhou, Gao, Mingyu, Zhang, Huanchen
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.02070
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916531659603968
author Qiu, Jiansheng
Yuan, Fangzhou
Gao, Mingyu
Zhang, Huanchen
author_facet Qiu, Jiansheng
Yuan, Fangzhou
Gao, Mingyu
Zhang, Huanchen
contents The multi-level design of Log-Structured Merge-trees (LSM-trees) naturally fits the tiered storage architecture: the upper levels (recently inserted/updated records) are kept in fast storage to guarantee performance while the lower levels (the majority of records) are placed in slower but cheaper storage to reduce cost. However, frequently accessed records may have been compacted and reside in slow storage. Existing algorithms are inefficient in promoting these ``hot'' records to fast storage, leading to compromised read performance. We present HotRAP, a key-value store based on RocksDB that can timely promote hot records individually from slow to fast storage and keep them in fast storage while they are hot. HotRAP uses an on-disk data structure (a specially-made LSM-tree) to track the hotness of keys and includes three pathways to ensure that hot records reach fast storage with short delays. Our experiments show that HotRAP outperforms state-of-the-art LSM-trees on tiered storage by up to 5.4$\times$ compared to the second best under read-only and read-write-balanced YCSB workloads with common access skew patterns, and by up to 1.9$\times$ compared to the second best under Twitter production workloads.
format Preprint
id arxiv_https___arxiv_org_abs_2402_02070
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle HotRAP: Hot Record Retention and Promotion for LSM-trees with Tiered Storage
Qiu, Jiansheng
Yuan, Fangzhou
Gao, Mingyu
Zhang, Huanchen
Databases
The multi-level design of Log-Structured Merge-trees (LSM-trees) naturally fits the tiered storage architecture: the upper levels (recently inserted/updated records) are kept in fast storage to guarantee performance while the lower levels (the majority of records) are placed in slower but cheaper storage to reduce cost. However, frequently accessed records may have been compacted and reside in slow storage. Existing algorithms are inefficient in promoting these ``hot'' records to fast storage, leading to compromised read performance. We present HotRAP, a key-value store based on RocksDB that can timely promote hot records individually from slow to fast storage and keep them in fast storage while they are hot. HotRAP uses an on-disk data structure (a specially-made LSM-tree) to track the hotness of keys and includes three pathways to ensure that hot records reach fast storage with short delays. Our experiments show that HotRAP outperforms state-of-the-art LSM-trees on tiered storage by up to 5.4$\times$ compared to the second best under read-only and read-write-balanced YCSB workloads with common access skew patterns, and by up to 1.9$\times$ compared to the second best under Twitter production workloads.
title HotRAP: Hot Record Retention and Promotion for LSM-trees with Tiered Storage
topic Databases
url https://arxiv.org/abs/2402.02070