2026-09-19T06:30:55Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1447642022-08-30T03:02:10Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Kraska, Tim
Markakis, Markos
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2022-08-29T16:10:09Z
2022-08-29T16:10:09Z
2022-05
2022-06-21T19:25:38.185Z
https://hdl.handle.net/1721.1/144764
https://orcid.org/ 0000-0003-2851-8840
Several widely-used key-value stores, like RocksDB, are designed around log-structured merge trees (LSMs). Optimizing for the performance characteristics of HDDs, LSMs provide good write performance by emphasizing sequential access to storage. However, this approach negatively impacts read performance: LSMs must employ expensive compaction jobs and memory-consuming Bloom filters in order to achieve reasonably fast reads. In the era of NVMe SSDs, we argue that this trade-off between read performance and write performance is sub-optimal. With enough parallelism, modern storage media have comparable random and sequential access performance, making update-in-place designs, which traditionally provide high read performance, a viable alternative to LSMs.
In this thesis, based on a research paper currently under submission, we close the gap between log-structured and update-in-place designs on modern SSDs by taking advantage of data and workload patterns. Specifically, we explore three key ideas: (A) record caching for efficient point operations, (B) page grouping for high-performance range scans, and (C) insert forecasting to reduce the reorganization costs of accommodating new records. We evaluate these ideas by implementing them in a prototype update-in-place key-value store called TreeLine. On YCSB, we find that TreeLine outperforms RocksDB and LeanStore by 2.18× and 2.05× respectively on average across the point workloads, and by up to 10.87× and 7.78× overall.
S.M.
Massachusetts Institute of Technology
In Copyright - Educational Use Permitted
Copyright retained by author(s)
https://rightsstatements.org/page/InC-EDU/1.0/
Rethinking Update-in-Place Key-Value Stores for Modern
Storage
Thesis
application/pdf
Master
Master of Science in Electrical Engineering and Computer Science
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="f3e91e48-9b61-4cb0-bee2-6863505c335e">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Title>Rethinking Update-in-Place Key-Value Stores for Modern
Storage</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2022-05</PublicationDate>
<Authors>
<Author>
<DisplayName>Markakis, Markos</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>https://rightsstatements.org/page/InC-EDU/1.0/</License>
<Abstract>Several widely-used key-value stores, like RocksDB, are designed around log-structured merge trees (LSMs). Optimizing for the performance characteristics of HDDs, LSMs provide good write performance by emphasizing sequential access to storage. However, this approach negatively impacts read performance: LSMs must employ expensive compaction jobs and memory-consuming Bloom filters in order to achieve reasonably fast reads. In the era of NVMe SSDs, we argue that this trade-off between read performance and write performance is sub-optimal. With enough parallelism, modern storage media have comparable random and sequential access performance, making update-in-place designs, which traditionally provide high read performance, a viable alternative to LSMs.
In this thesis, based on a research paper currently under submission, we close the gap between log-structured and update-in-place designs on modern SSDs by taking advantage of data and workload patterns. Specifically, we explore three key ideas: (A) record caching for efficient point operations, (B) page grouping for high-performance range scans, and (C) insert forecasting to reduce the reorganization costs of accommodating new records. We evaluate these ideas by implementing them in a prototype update-in-place key-value store called TreeLine. On YCSB, we find that TreeLine outperforms RocksDB and LeanStore by 2.18× and 2.05× respectively on average across the point workloads, and by up to 10.87× and 7.78× overall.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>