DenKv: Addressing Design Trade-offs of Key-value Stores for Scientific Applications

Safdar Jamil; Awais Khan; Kihyun Kim; Jae Kook Lee; Dosik An; Taeyoung Hong; Sarp Oral; Youngjae Kim

doi:10.1109/PDSW56643.2022.00009

DenKv: Addressing Design Trade-offs of Key-value Stores for Scientific Applications

Safdar Jamil, Awais Khan, Kihyun Kim, Jae Kook Lee, Dosik An, Taeyoung Hong, Sarp Oral, Youngjae Kim

Technology Integration

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

High-performance computing (HPC) facilities have employed flash-based storage tier near to compute nodes to absorb high I/O demand by HPC applications during periodic system-level checkpoints. To accelerate these checkpoints, proxy-based distributed key-value stores (PD-KVS) gained particular attention for their flexibility to support multiple backends and different network configurations. PD-KVS rely internally on monolithic KVS, such as LevelDB or RocksDB, to exploit the KV interface and query support. However, PD-KVS are unaware of the high redundancy factor in checkpoint data, which can be up to GBs to TBs, and therefore, tend to generate high write and space amplification on these storage layers. In this paper, we propose DenKv which is deduplication-extended node-local LSM-tree-based KVS. DenKv employs asynchronous partially inline dedup (APID) and aims to maintain the performance characteristics of LSM-tree-based KVS while reducing the write and space amplification problems. We implemented DenKv atop BlobDB and showed that our proposed solution maintains performance while reducing write amplification up to 2× and space amplification by 4× on average.

Original language	English
Title of host publication	Proceedings of PDSW 2022
Subtitle of host publication	7th International Parallel Data Systems Workshop, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	20-25
Number of pages	6
ISBN (Electronic)	9781665475624
DOIs	https://doi.org/10.1109/PDSW56643.2022.00009
State	Published - 2022
Event	7th IEEE/ACM International Parallel Data Systems Workshop, PDSW 2022 - Dallas, United States Duration: Nov 13 2022 → Nov 18 2022

Publication series

Name	Proceedings of PDSW 2022: 7th International Parallel Data Systems Workshop, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis

Conference

Conference	7th IEEE/ACM International Parallel Data Systems Workshop, PDSW 2022
Country/Territory	United States
City	Dallas
Period	11/13/22 → 11/18/22

Funding

This work was supported in part by the Korea Institute of Science and TechnologyInformation (Grant No.J-22-NB-C03-S01) and by the National Research Foundation of Korea(NRF) grant funded by the Korea government (MSIT) (No. NRF-2021R1A2C2014386). This manuscript has been authored by UT-Battelle, LLC under Contract No. DE-AC05-00OR22725 with the U.S. Department of Energy. The publisher, by accepting the article for publication, acknowledgesthat the U.S. Government retains a non-exclusive, paid up, irrevocable, world-wide license to publish or reproduce the published form of the manuscript, or allow others to do so, for United States Government purposes. The Department of Energy will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan (http://energy.gov/downloads/doe-public-access-plan)Y.. Kim is the corresponding author.

Keywords

Deduplication
High Performance Computing
Key-Value Stores
Log-Structures Merge Tree

Access to Document

10.1109/PDSW56643.2022.00009

Cite this

Jamil, S., Khan, A., Kim, K., Lee, J. K., An, D., Hong, T., Oral, S., & Kim, Y. (2022). DenKv: Addressing Design Trade-offs of Key-value Stores for Scientific Applications. In Proceedings of PDSW 2022: 7th International Parallel Data Systems Workshop, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis (pp. 20-25). (Proceedings of PDSW 2022: 7th International Parallel Data Systems Workshop, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/PDSW56643.2022.00009

Jamil, Safdar ; Khan, Awais ; Kim, Kihyun et al. / DenKv : Addressing Design Trade-offs of Key-value Stores for Scientific Applications. Proceedings of PDSW 2022: 7th International Parallel Data Systems Workshop, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 20-25 (Proceedings of PDSW 2022: 7th International Parallel Data Systems Workshop, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis).

@inproceedings{8b3a6624b8614952abb6cadd015e3e92,

title = "DenKv: Addressing Design Trade-offs of Key-value Stores for Scientific Applications",

abstract = "High-performance computing (HPC) facilities have employed flash-based storage tier near to compute nodes to absorb high I/O demand by HPC applications during periodic system-level checkpoints. To accelerate these checkpoints, proxy-based distributed key-value stores (PD-KVS) gained particular attention for their flexibility to support multiple backends and different network configurations. PD-KVS rely internally on monolithic KVS, such as LevelDB or RocksDB, to exploit the KV interface and query support. However, PD-KVS are unaware of the high redundancy factor in checkpoint data, which can be up to GBs to TBs, and therefore, tend to generate high write and space amplification on these storage layers. In this paper, we propose DenKv which is deduplication-extended node-local LSM-tree-based KVS. DenKv employs asynchronous partially inline dedup (APID) and aims to maintain the performance characteristics of LSM-tree-based KVS while reducing the write and space amplification problems. We implemented DenKv atop BlobDB and showed that our proposed solution maintains performance while reducing write amplification up to 2× and space amplification by 4× on average.",

keywords = "Deduplication, High Performance Computing, Key-Value Stores, Log-Structures Merge Tree",

author = "Safdar Jamil and Awais Khan and Kihyun Kim and Lee, {Jae Kook} and Dosik An and Taeyoung Hong and Sarp Oral and Youngjae Kim",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 7th IEEE/ACM International Parallel Data Systems Workshop, PDSW 2022 ; Conference date: 13-11-2022 Through 18-11-2022",

year = "2022",

doi = "10.1109/PDSW56643.2022.00009",

language = "English",

series = "Proceedings of PDSW 2022: 7th International Parallel Data Systems Workshop, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "20--25",

booktitle = "Proceedings of PDSW 2022",

}

Jamil, S, Khan, A, Kim, K, Lee, JK, An, D, Hong, T, Oral, S & Kim, Y 2022, DenKv: Addressing Design Trade-offs of Key-value Stores for Scientific Applications. in Proceedings of PDSW 2022: 7th International Parallel Data Systems Workshop, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis. Proceedings of PDSW 2022: 7th International Parallel Data Systems Workshop, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis, Institute of Electrical and Electronics Engineers Inc., pp. 20-25, 7th IEEE/ACM International Parallel Data Systems Workshop, PDSW 2022, Dallas, United States, 11/13/22. https://doi.org/10.1109/PDSW56643.2022.00009

DenKv: Addressing Design Trade-offs of Key-value Stores for Scientific Applications. / Jamil, Safdar; Khan, Awais; Kim, Kihyun et al.
Proceedings of PDSW 2022: 7th International Parallel Data Systems Workshop, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis. Institute of Electrical and Electronics Engineers Inc., 2022. p. 20-25 (Proceedings of PDSW 2022: 7th International Parallel Data Systems Workshop, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - DenKv

T2 - 7th IEEE/ACM International Parallel Data Systems Workshop, PDSW 2022

AU - Jamil, Safdar

AU - Khan, Awais

AU - Kim, Kihyun

AU - Lee, Jae Kook

AU - An, Dosik

AU - Hong, Taeyoung

AU - Oral, Sarp

AU - Kim, Youngjae

PY - 2022

Y1 - 2022

N2 - High-performance computing (HPC) facilities have employed flash-based storage tier near to compute nodes to absorb high I/O demand by HPC applications during periodic system-level checkpoints. To accelerate these checkpoints, proxy-based distributed key-value stores (PD-KVS) gained particular attention for their flexibility to support multiple backends and different network configurations. PD-KVS rely internally on monolithic KVS, such as LevelDB or RocksDB, to exploit the KV interface and query support. However, PD-KVS are unaware of the high redundancy factor in checkpoint data, which can be up to GBs to TBs, and therefore, tend to generate high write and space amplification on these storage layers. In this paper, we propose DenKv which is deduplication-extended node-local LSM-tree-based KVS. DenKv employs asynchronous partially inline dedup (APID) and aims to maintain the performance characteristics of LSM-tree-based KVS while reducing the write and space amplification problems. We implemented DenKv atop BlobDB and showed that our proposed solution maintains performance while reducing write amplification up to 2× and space amplification by 4× on average.

AB - High-performance computing (HPC) facilities have employed flash-based storage tier near to compute nodes to absorb high I/O demand by HPC applications during periodic system-level checkpoints. To accelerate these checkpoints, proxy-based distributed key-value stores (PD-KVS) gained particular attention for their flexibility to support multiple backends and different network configurations. PD-KVS rely internally on monolithic KVS, such as LevelDB or RocksDB, to exploit the KV interface and query support. However, PD-KVS are unaware of the high redundancy factor in checkpoint data, which can be up to GBs to TBs, and therefore, tend to generate high write and space amplification on these storage layers. In this paper, we propose DenKv which is deduplication-extended node-local LSM-tree-based KVS. DenKv employs asynchronous partially inline dedup (APID) and aims to maintain the performance characteristics of LSM-tree-based KVS while reducing the write and space amplification problems. We implemented DenKv atop BlobDB and showed that our proposed solution maintains performance while reducing write amplification up to 2× and space amplification by 4× on average.

KW - Deduplication

KW - High Performance Computing

KW - Key-Value Stores

KW - Log-Structures Merge Tree

UR - http://www.scopus.com/inward/record.url?scp=85148005481&partnerID=8YFLogxK

U2 - 10.1109/PDSW56643.2022.00009

DO - 10.1109/PDSW56643.2022.00009

M3 - Conference contribution

AN - SCOPUS:85148005481

T3 - Proceedings of PDSW 2022: 7th International Parallel Data Systems Workshop, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis

SP - 20

EP - 25

BT - Proceedings of PDSW 2022

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 13 November 2022 through 18 November 2022

ER -

Jamil S, Khan A, Kim K, Lee JK, An D, Hong T et al. DenKv: Addressing Design Trade-offs of Key-value Stores for Scientific Applications. In Proceedings of PDSW 2022: 7th International Parallel Data Systems Workshop, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis. Institute of Electrical and Electronics Engineers Inc. 2022. p. 20-25. (Proceedings of PDSW 2022: 7th International Parallel Data Systems Workshop, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis). doi: 10.1109/PDSW56643.2022.00009

DenKv: Addressing Design Trade-offs of Key-value Stores for Scientific Applications

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this