Chew analyzer: Workload-aware data management across differentiated storage pools

Xiongzi Ge; Xuchao Xie; David H.C. Du; Pradeep Ganesan; Dennis Hahn

doi:10.1109/MASCOTS.2018.00017

Chew analyzer: Workload-aware data management across differentiated storage pools

Xiongzi Ge, Xuchao Xie, David H.C. Du, Pradeep Ganesan, Dennis Hahn

Computer Science and Engineering

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

3 Scopus citations

Abstract

In multi-Tier storage systems, moving data from one tier to the next can be inefficient. And because each type of storage device has its own idiosyncrasies with respect to the workloads that it can best support, unnecessary data movement might result. In this paper, we explore a fully connected storage architecture in which data can move from any storage pool to another. We propose a Chunk-level storage-Aware workload Analyzer framework, abbreviated as ChewAnalyzer, to facilitate efficient data placement. Access patterns are characterized in a flexible way by a collection of I/O accesses to a data chunk. ChewAnalyzer employs a Hierarchical Classifier [1] to analyze the chunk patterns step by step. In each classification step, the Chunk Placement Recommender suggests new data placement policies according to the device properties. Based on the analysis of access pattern changes, the Storage Manager can adequately distribute or migrate the data chunks across different storage pools. Our experimental results show that ChewAnalyzer improves the initial data placement and that it migrates data into the proper pools directly and efficiently.

Original language	English (US)
Title of host publication	Proceedings - 26th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2018
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	94-101
Number of pages	8
ISBN (Electronic)	9781538668863
DOIs	https://doi.org/10.1109/MASCOTS.2018.00017
State	Published - Nov 7 2018
Event	26th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2018 - Milwaukee, United States Duration: Sep 25 2018 → Sep 28 2018

Publication series

Name	Proceedings - 26th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2018

Other

Other	26th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2018
Country/Territory	United States
City	Milwaukee
Period	9/25/18 → 9/28/18

Bibliographical note

Funding Information:
We would like to thank the anonymous MASCOTS reviewers for their helpful comments to improve the previous draft of this paper. We also thank Al Andux, Ajay Bakre, Jerry Fredin, and Art Harkin from NetApp and all the members in the CRIS group for their suggestions and support. This work was partially supported by NSF awards 1305237, 1812537, 1421913, 1439622 and 1525617.

Publisher Copyright:
© 2018 IEEE.

Keywords

Data movement
Data placement
Fully connected storage
Hierarchical Classifier
Storage

Access

10.1109/MASCOTS.2018.00017

OpenUrl availability

Full text

Cite this

Ge, X., Xie, X., Du, D. H. C., Ganesan, P., & Hahn, D. (2018). Chew analyzer: Workload-aware data management across differentiated storage pools. In Proceedings - 26th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2018 (pp. 94-101). Article 8526875 (Proceedings - 26th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MASCOTS.2018.00017

Chew analyzer: Workload-aware data management across differentiated storage pools. / Ge, Xiongzi; Xie, Xuchao; Du, David H.C. et al.
Proceedings - 26th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 94-101 8526875 (Proceedings - 26th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2018).

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

Ge, X, Xie, X, Du, DHC, Ganesan, P & Hahn, D 2018, Chew analyzer: Workload-aware data management across differentiated storage pools. in Proceedings - 26th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2018., 8526875, Proceedings - 26th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2018, Institute of Electrical and Electronics Engineers Inc., pp. 94-101, 26th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2018, Milwaukee, United States, 9/25/18. https://doi.org/10.1109/MASCOTS.2018.00017

Ge X, Xie X, Du DHC, Ganesan P, Hahn D. Chew analyzer: Workload-aware data management across differentiated storage pools. In Proceedings - 26th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 94-101. 8526875. (Proceedings - 26th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2018). doi: 10.1109/MASCOTS.2018.00017

Ge, Xiongzi ; Xie, Xuchao ; Du, David H.C. et al. / Chew analyzer : Workload-aware data management across differentiated storage pools. Proceedings - 26th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 94-101 (Proceedings - 26th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2018).

@inproceedings{e89bbd45cfbd4950a0e9eb65712e74bf,

title = "Chew analyzer: Workload-aware data management across differentiated storage pools",

abstract = "In multi-Tier storage systems, moving data from one tier to the next can be inefficient. And because each type of storage device has its own idiosyncrasies with respect to the workloads that it can best support, unnecessary data movement might result. In this paper, we explore a fully connected storage architecture in which data can move from any storage pool to another. We propose a Chunk-level storage-Aware workload Analyzer framework, abbreviated as ChewAnalyzer, to facilitate efficient data placement. Access patterns are characterized in a flexible way by a collection of I/O accesses to a data chunk. ChewAnalyzer employs a Hierarchical Classifier [1] to analyze the chunk patterns step by step. In each classification step, the Chunk Placement Recommender suggests new data placement policies according to the device properties. Based on the analysis of access pattern changes, the Storage Manager can adequately distribute or migrate the data chunks across different storage pools. Our experimental results show that ChewAnalyzer improves the initial data placement and that it migrates data into the proper pools directly and efficiently.",

keywords = "Data movement, Data placement, Fully connected storage, Hierarchical Classifier, Storage",

author = "Xiongzi Ge and Xuchao Xie and Du, {David H.C.} and Pradeep Ganesan and Dennis Hahn",

note = "Funding Information: We would like to thank the anonymous MASCOTS reviewers for their helpful comments to improve the previous draft of this paper. We also thank Al Andux, Ajay Bakre, Jerry Fredin, and Art Harkin from NetApp and all the members in the CRIS group for their suggestions and support. This work was partially supported by NSF awards 1305237, 1812537, 1421913, 1439622 and 1525617. Publisher Copyright: {\textcopyright} 2018 IEEE.; 26th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2018 ; Conference date: 25-09-2018 Through 28-09-2018",

year = "2018",

month = nov,

day = "7",

doi = "10.1109/MASCOTS.2018.00017",

language = "English (US)",

series = "Proceedings - 26th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2018",

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

pages = "94--101",

booktitle = "Proceedings - 26th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2018",

}

TY - GEN

T1 - Chew analyzer

T2 - 26th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2018

AU - Ge, Xiongzi

AU - Xie, Xuchao

AU - Du, David H.C.

AU - Ganesan, Pradeep

AU - Hahn, Dennis

N1 - Funding Information: We would like to thank the anonymous MASCOTS reviewers for their helpful comments to improve the previous draft of this paper. We also thank Al Andux, Ajay Bakre, Jerry Fredin, and Art Harkin from NetApp and all the members in the CRIS group for their suggestions and support. This work was partially supported by NSF awards 1305237, 1812537, 1421913, 1439622 and 1525617. Publisher Copyright: © 2018 IEEE.

PY - 2018/11/7

Y1 - 2018/11/7

N2 - In multi-Tier storage systems, moving data from one tier to the next can be inefficient. And because each type of storage device has its own idiosyncrasies with respect to the workloads that it can best support, unnecessary data movement might result. In this paper, we explore a fully connected storage architecture in which data can move from any storage pool to another. We propose a Chunk-level storage-Aware workload Analyzer framework, abbreviated as ChewAnalyzer, to facilitate efficient data placement. Access patterns are characterized in a flexible way by a collection of I/O accesses to a data chunk. ChewAnalyzer employs a Hierarchical Classifier [1] to analyze the chunk patterns step by step. In each classification step, the Chunk Placement Recommender suggests new data placement policies according to the device properties. Based on the analysis of access pattern changes, the Storage Manager can adequately distribute or migrate the data chunks across different storage pools. Our experimental results show that ChewAnalyzer improves the initial data placement and that it migrates data into the proper pools directly and efficiently.

AB - In multi-Tier storage systems, moving data from one tier to the next can be inefficient. And because each type of storage device has its own idiosyncrasies with respect to the workloads that it can best support, unnecessary data movement might result. In this paper, we explore a fully connected storage architecture in which data can move from any storage pool to another. We propose a Chunk-level storage-Aware workload Analyzer framework, abbreviated as ChewAnalyzer, to facilitate efficient data placement. Access patterns are characterized in a flexible way by a collection of I/O accesses to a data chunk. ChewAnalyzer employs a Hierarchical Classifier [1] to analyze the chunk patterns step by step. In each classification step, the Chunk Placement Recommender suggests new data placement policies according to the device properties. Based on the analysis of access pattern changes, the Storage Manager can adequately distribute or migrate the data chunks across different storage pools. Our experimental results show that ChewAnalyzer improves the initial data placement and that it migrates data into the proper pools directly and efficiently.

KW - Data movement

KW - Data placement

KW - Fully connected storage

KW - Hierarchical Classifier

KW - Storage

UR - http://www.scopus.com/inward/record.url?scp=85058310566&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85058310566&partnerID=8YFLogxK

U2 - 10.1109/MASCOTS.2018.00017

DO - 10.1109/MASCOTS.2018.00017

M3 - Conference contribution

AN - SCOPUS:85058310566

T3 - Proceedings - 26th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2018

SP - 94

EP - 101

BT - Proceedings - 26th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2018

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 25 September 2018 through 28 September 2018

ER -

Chew analyzer: Workload-aware data management across differentiated storage pools

Abstract

Publication series

Other

Bibliographical note

Keywords

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this