Harmonia: A Globally Coordinated Garbage Collector for Arrays of Solid-state Drives
Abstract
Solid-State Drives (SSDs) offer significant performance improvements over hard disk drives (HDD) on a number of workloads. The frequency of garbage collection (GC) activity is directly correlated with the pattern, frequency, and volume of write requests, and scheduling of GC is controlled by logic internal to the SSD. SSDs can exhibit significant performance degradations when garbage collection (GC) conflicts with an ongoing I/O request stream. When using SSDs in a RAID array, the lack of coordination of the local GC processes amplifies these performance degradations. No RAID controller or SSD available today has the technology to overcome this limitation. This paper presents Harmonia, a Global Garbage Collection (GGC) mechanism to improve response times and reduce performance variability for a RAID array of SSDs. Our proposal includes a high-level design of SSD-aware RAID controller and GGC-capable SSD devices, as well as algorithms to coordinate the global GC cycles. Our simulations show that this design improves response time and reduces performance variability for a wide variety of enterprise workloads. For bursty, write dominant workloads response time was improved by 69% while performance variability was reduced by 71%.
- Authors:
-
- ORNL
- Publication Date:
- Research Org.:
- Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States). National Center for Computational Sciences (NCCS)
- Sponsoring Org.:
- USDOE Office of Science (SC)
- OSTI Identifier:
- 1017325
- DOE Contract Number:
- DE-AC05-00OR22725
- Resource Type:
- Conference
- Resource Relation:
- Conference: IEEE Symposium on Massive Storage Systems and Technologies (MSST), Denver, CO, USA, 20110523, 20110527
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE; ALGORITHMS; DESIGN; PERFORMANCE; STORAGE; Flash Memory; Solid-state Drive; RAID; Garbage Collection; Scheduling
Citation Formats
Kim, Youngjae, Oral, H Sarp, Shipman, Galen M, Lee, Junghee, Dillow, David A, and Wang, Feiyi. Harmonia: A Globally Coordinated Garbage Collector for Arrays of Solid-state Drives. United States: N. p., 2011.
Web.
Kim, Youngjae, Oral, H Sarp, Shipman, Galen M, Lee, Junghee, Dillow, David A, & Wang, Feiyi. Harmonia: A Globally Coordinated Garbage Collector for Arrays of Solid-state Drives. United States.
Kim, Youngjae, Oral, H Sarp, Shipman, Galen M, Lee, Junghee, Dillow, David A, and Wang, Feiyi. 2011.
"Harmonia: A Globally Coordinated Garbage Collector for Arrays of Solid-state Drives". United States.
@article{osti_1017325,
title = {Harmonia: A Globally Coordinated Garbage Collector for Arrays of Solid-state Drives},
author = {Kim, Youngjae and Oral, H Sarp and Shipman, Galen M and Lee, Junghee and Dillow, David A and Wang, Feiyi},
abstractNote = {Solid-State Drives (SSDs) offer significant performance improvements over hard disk drives (HDD) on a number of workloads. The frequency of garbage collection (GC) activity is directly correlated with the pattern, frequency, and volume of write requests, and scheduling of GC is controlled by logic internal to the SSD. SSDs can exhibit significant performance degradations when garbage collection (GC) conflicts with an ongoing I/O request stream. When using SSDs in a RAID array, the lack of coordination of the local GC processes amplifies these performance degradations. No RAID controller or SSD available today has the technology to overcome this limitation. This paper presents Harmonia, a Global Garbage Collection (GGC) mechanism to improve response times and reduce performance variability for a RAID array of SSDs. Our proposal includes a high-level design of SSD-aware RAID controller and GGC-capable SSD devices, as well as algorithms to coordinate the global GC cycles. Our simulations show that this design improves response time and reduces performance variability for a wide variety of enterprise workloads. For bursty, write dominant workloads response time was improved by 69% while performance variability was reduced by 71%.},
doi = {},
url = {https://www.osti.gov/biblio/1017325},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Sat Jan 01 00:00:00 EST 2011},
month = {Sat Jan 01 00:00:00 EST 2011}
}