Cross-layer optimizations in solid-state drives

Jia Hao Wang, Hsin Hung Chen, Wei Jian Su, Da-Wei Chang

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Solid-state drives (SSDs) utilize parallel architectures to improve their IO throughput. Although log buffer based flash translation layers (FTLs) are widely employed in SSDs, little has been addressed on the issue of placing pages under a parallel architecture in such FTLs. In this letter, we evaluate three possible page placement policies and show that there is no best policy due to the tradeoff between the degree of parallelism and the garbage collection overhead. To achieve high performance SSDs, cross-layer optimization techniques involving the cooperation between the buffer management layer and the FTL are proposed in this letter to maximize the degree of parallelism while keeping a low garbage collection overhead. The basic idea is to let the FTL keep the garbage collection overhead low by eliminating high-cost cross-channel live page copying, while making the buffer management layer responsible for maximizing the degree of parallelism. Simulation results on five realistic or benchmark based workloads show that the proposed techniques reduce the response time of the SSD by up to 79%.

Original languageEnglish
Article number6024440
Pages (from-to)109-112
Number of pages4
JournalIEEE Embedded Systems Letters
Volume3
Issue number4
DOIs
Publication statusPublished - 2011 Dec 1

Fingerprint

Parallel architectures
Copying
Throughput
Costs

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Computer Science(all)

Cite this

Wang, Jia Hao ; Chen, Hsin Hung ; Su, Wei Jian ; Chang, Da-Wei. / Cross-layer optimizations in solid-state drives. In: IEEE Embedded Systems Letters. 2011 ; Vol. 3, No. 4. pp. 109-112.
@article{dd591fadfece43268bba17be57e61053,
title = "Cross-layer optimizations in solid-state drives",
abstract = "Solid-state drives (SSDs) utilize parallel architectures to improve their IO throughput. Although log buffer based flash translation layers (FTLs) are widely employed in SSDs, little has been addressed on the issue of placing pages under a parallel architecture in such FTLs. In this letter, we evaluate three possible page placement policies and show that there is no best policy due to the tradeoff between the degree of parallelism and the garbage collection overhead. To achieve high performance SSDs, cross-layer optimization techniques involving the cooperation between the buffer management layer and the FTL are proposed in this letter to maximize the degree of parallelism while keeping a low garbage collection overhead. The basic idea is to let the FTL keep the garbage collection overhead low by eliminating high-cost cross-channel live page copying, while making the buffer management layer responsible for maximizing the degree of parallelism. Simulation results on five realistic or benchmark based workloads show that the proposed techniques reduce the response time of the SSD by up to 79{\%}.",
author = "Wang, {Jia Hao} and Chen, {Hsin Hung} and Su, {Wei Jian} and Da-Wei Chang",
year = "2011",
month = "12",
day = "1",
doi = "10.1109/LES.2011.2168941",
language = "English",
volume = "3",
pages = "109--112",
journal = "IEEE Embedded Systems Letters",
issn = "1943-0663",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

Cross-layer optimizations in solid-state drives. / Wang, Jia Hao; Chen, Hsin Hung; Su, Wei Jian; Chang, Da-Wei.

In: IEEE Embedded Systems Letters, Vol. 3, No. 4, 6024440, 01.12.2011, p. 109-112.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Cross-layer optimizations in solid-state drives

AU - Wang, Jia Hao

AU - Chen, Hsin Hung

AU - Su, Wei Jian

AU - Chang, Da-Wei

PY - 2011/12/1

Y1 - 2011/12/1

N2 - Solid-state drives (SSDs) utilize parallel architectures to improve their IO throughput. Although log buffer based flash translation layers (FTLs) are widely employed in SSDs, little has been addressed on the issue of placing pages under a parallel architecture in such FTLs. In this letter, we evaluate three possible page placement policies and show that there is no best policy due to the tradeoff between the degree of parallelism and the garbage collection overhead. To achieve high performance SSDs, cross-layer optimization techniques involving the cooperation between the buffer management layer and the FTL are proposed in this letter to maximize the degree of parallelism while keeping a low garbage collection overhead. The basic idea is to let the FTL keep the garbage collection overhead low by eliminating high-cost cross-channel live page copying, while making the buffer management layer responsible for maximizing the degree of parallelism. Simulation results on five realistic or benchmark based workloads show that the proposed techniques reduce the response time of the SSD by up to 79%.

AB - Solid-state drives (SSDs) utilize parallel architectures to improve their IO throughput. Although log buffer based flash translation layers (FTLs) are widely employed in SSDs, little has been addressed on the issue of placing pages under a parallel architecture in such FTLs. In this letter, we evaluate three possible page placement policies and show that there is no best policy due to the tradeoff between the degree of parallelism and the garbage collection overhead. To achieve high performance SSDs, cross-layer optimization techniques involving the cooperation between the buffer management layer and the FTL are proposed in this letter to maximize the degree of parallelism while keeping a low garbage collection overhead. The basic idea is to let the FTL keep the garbage collection overhead low by eliminating high-cost cross-channel live page copying, while making the buffer management layer responsible for maximizing the degree of parallelism. Simulation results on five realistic or benchmark based workloads show that the proposed techniques reduce the response time of the SSD by up to 79%.

UR - http://www.scopus.com/inward/record.url?scp=84555191900&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84555191900&partnerID=8YFLogxK

U2 - 10.1109/LES.2011.2168941

DO - 10.1109/LES.2011.2168941

M3 - Article

VL - 3

SP - 109

EP - 112

JO - IEEE Embedded Systems Letters

JF - IEEE Embedded Systems Letters

SN - 1943-0663

IS - 4

M1 - 6024440

ER -