Publications
Detailed Information
Re-architecting distributed block storage system for improving random write performance
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Oh, Myoungwon | - |
dc.contributor.author | Park, Jiwoong | - |
dc.contributor.author | Park, Sung Kyu | - |
dc.contributor.author | Choi, Adel | - |
dc.contributor.author | Lee, Jongyoul | - |
dc.contributor.author | Choi, Jin-Hyeok | - |
dc.contributor.author | Yeom, Heon Young | - |
dc.date.accessioned | 2022-06-24T00:25:52Z | - |
dc.date.available | 2022-06-24T00:25:52Z | - |
dc.date.created | 2022-05-09 | - |
dc.date.issued | 2021-07 | - |
dc.identifier.citation | Proceedings - International Conference on Distributed Computing Systems, Vol.2021-July, pp.104-114 | - |
dc.identifier.uri | https://hdl.handle.net/10371/183733 | - |
dc.description.abstract | © 2021 IEEE.In cloud ecosystems, distributed block storage systems are used to provide a persistent block storage service, which is the fundamental building block for operating cloud native services. However, existing distributed storage systems performed poorly for random write workloads in an all-NVMe storage configuration, becoming CPU-bottlenecked. Our roofline-based approach to performance analysis on a conventional distributed block storage system with NVMe SSDs reveals that the bottleneck does not lie in one specific software module, but across the entire software stack; (1) tightly coupled I/O processing, (2) inefficient threading architecture, and (3) local backend data store causing excessive CPU usage. To this end, we re-architect a modern distributed block storage system for improving random write performance. The key ingredients of our system are (1) decoupled operation processing using non-volatile memory, (2) prioritized thread control, and (3) CPU-efficient backend data store. Our system emphasizes low CPU overhead and high CPU efficiency to efficiently utilize NVMe SSDs in a distributed storage environment. We implement our system in Ceph. Compared to the native Ceph, our prototype system delivers more than 3x performance improvement for small random write I/Os in terms of both IOPS and latency by efficiently utilizing CPU cores. | - |
dc.language | 영어 | - |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | - |
dc.title | Re-architecting distributed block storage system for improving random write performance | - |
dc.type | Article | - |
dc.identifier.doi | 10.1109/ICDCS51616.2021.00019 | - |
dc.citation.journaltitle | Proceedings - International Conference on Distributed Computing Systems | - |
dc.identifier.wosid | 000728379200010 | - |
dc.identifier.scopusid | 2-s2.0-85117161066 | - |
dc.citation.endpage | 114 | - |
dc.citation.startpage | 104 | - |
dc.citation.volume | 2021-July | - |
dc.description.isOpenAccess | N | - |
dc.contributor.affiliatedAuthor | Yeom, Heon Young | - |
dc.type.docType | Conference Paper | - |
dc.description.journalClass | 1 | - |
- Appears in Collections:
- Files in This Item:
- There are no files associated with this item.
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.