Improving data integrity in linux software RAID with protection information (T10-PI)

Baoquan Zhang; Raghunath Raja Chandrasekar; Alireza Haghdoost; Lance Evans; David Du

doi:10.1109/CCGRID.2018.00091

Improving data integrity in linux software RAID with protection information (T10-PI)

Baoquan Zhang, Raghunath Raja Chandrasekar, Alireza Haghdoost, Lance Evans, David Du

Computer Science and Engineering

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

Abstract

The T10 DIF (Data Integrity Field) and DIX (Data Integrity Extension) specifications provide mechanisms to guarantee end-to-end data integrity and protection in the face of silent data corruption in modern storage systems. However, the Multiple Devices (MD) software RAID driver in Linux does not fully leverage these capabilities to provide such end-to-end guarantees with widely-used RAID modes such as 5 and 6, thereby causing an 'integrity gap' in the Linux I/O stack. This paper describes the design and performance characteristics of a DIX-aware MD module that plugs this integrity gap with minimal overhead to client applications. A PI (Protection Information) operator is added in MD to handle the PI-related operations, and dedicated buffers for PI are allocated and managed in MD RAID-5/6 personality's stripe structures to generate, store, and verify the PI. This allows seamless exchange of PI information among end-applications running in user mode, file systems, the linux block layer, and PI-capable HBAs and drives. Our evaluations show that the DIX-aware MD module has the capability of detecting SDC with the tolerable performance penalty.

Original language	English (US)
Title of host publication	Proceedings - 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGRID 2018
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	609-615
Number of pages	7
ISBN (Electronic)	9781538658154
DOIs	https://doi.org/10.1109/CCGRID.2018.00091
State	Published - Jul 13 2018
Event	18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGRID 2018 - Washington, United States Duration: May 1 2018 → May 4 2018

Publication series

Name	Proceedings - 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGRID 2018

Other

Other	18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGRID 2018
Country/Territory	United States
City	Washington
Period	5/1/18 → 5/4/18

Bibliographical note

Funding Information:
This work is partially supported by a grant from CRAY and NSF awards 1305237, 1421913, 1439622 and 1525617. The authors also express their gratitude to Martin K. Petersen from Oracle, Chaitra Basappa from Broadcom and others who offer significant help during the experimental setup.

Publisher Copyright:
© 2018 IEEE.

Keywords

Linux kernel
Software RAID
T10 PI

Access

10.1109/CCGRID.2018.00091

OpenUrl availability

Full text

Cite this

Zhang, B., Raja Chandrasekar, R., Haghdoost, A., Evans, L., & Du, D. (2018). Improving data integrity in linux software RAID with protection information (T10-PI). In Proceedings - 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGRID 2018 (pp. 609-615). (Proceedings - 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGRID 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CCGRID.2018.00091

Improving data integrity in linux software RAID with protection information (T10-PI). / Zhang, Baoquan; Raja Chandrasekar, Raghunath; Haghdoost, Alireza et al.
Proceedings - 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGRID 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 609-615 (Proceedings - 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGRID 2018).

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

Zhang, B, Raja Chandrasekar, R, Haghdoost, A, Evans, L & Du, D 2018, Improving data integrity in linux software RAID with protection information (T10-PI). in Proceedings - 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGRID 2018. Proceedings - 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGRID 2018, Institute of Electrical and Electronics Engineers Inc., pp. 609-615, 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGRID 2018, Washington, United States, 5/1/18. https://doi.org/10.1109/CCGRID.2018.00091

Zhang B, Raja Chandrasekar R, Haghdoost A, Evans L, Du D. Improving data integrity in linux software RAID with protection information (T10-PI). In Proceedings - 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGRID 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 609-615. (Proceedings - 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGRID 2018). doi: 10.1109/CCGRID.2018.00091

Zhang, Baoquan ; Raja Chandrasekar, Raghunath ; Haghdoost, Alireza et al. / Improving data integrity in linux software RAID with protection information (T10-PI). Proceedings - 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGRID 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 609-615 (Proceedings - 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGRID 2018).

@inproceedings{1e804907a1cf488f86f551b46d0d37b2,

title = "Improving data integrity in linux software RAID with protection information (T10-PI)",

abstract = "The T10 DIF (Data Integrity Field) and DIX (Data Integrity Extension) specifications provide mechanisms to guarantee end-to-end data integrity and protection in the face of silent data corruption in modern storage systems. However, the Multiple Devices (MD) software RAID driver in Linux does not fully leverage these capabilities to provide such end-to-end guarantees with widely-used RAID modes such as 5 and 6, thereby causing an 'integrity gap' in the Linux I/O stack. This paper describes the design and performance characteristics of a DIX-aware MD module that plugs this integrity gap with minimal overhead to client applications. A PI (Protection Information) operator is added in MD to handle the PI-related operations, and dedicated buffers for PI are allocated and managed in MD RAID-5/6 personality's stripe structures to generate, store, and verify the PI. This allows seamless exchange of PI information among end-applications running in user mode, file systems, the linux block layer, and PI-capable HBAs and drives. Our evaluations show that the DIX-aware MD module has the capability of detecting SDC with the tolerable performance penalty.",

keywords = "Linux kernel, Software RAID, T10 PI",

author = "Baoquan Zhang and {Raja Chandrasekar}, Raghunath and Alireza Haghdoost and Lance Evans and David Du",

note = "Funding Information: This work is partially supported by a grant from CRAY and NSF awards 1305237, 1421913, 1439622 and 1525617. The authors also express their gratitude to Martin K. Petersen from Oracle, Chaitra Basappa from Broadcom and others who offer significant help during the experimental setup. Publisher Copyright: {\textcopyright} 2018 IEEE.; 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGRID 2018 ; Conference date: 01-05-2018 Through 04-05-2018",

year = "2018",

month = jul,

day = "13",

doi = "10.1109/CCGRID.2018.00091",

language = "English (US)",

series = "Proceedings - 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGRID 2018",

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

pages = "609--615",

booktitle = "Proceedings - 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGRID 2018",

}

TY - GEN

T1 - Improving data integrity in linux software RAID with protection information (T10-PI)

AU - Zhang, Baoquan

AU - Raja Chandrasekar, Raghunath

AU - Haghdoost, Alireza

AU - Evans, Lance

AU - Du, David

N1 - Funding Information: This work is partially supported by a grant from CRAY and NSF awards 1305237, 1421913, 1439622 and 1525617. The authors also express their gratitude to Martin K. Petersen from Oracle, Chaitra Basappa from Broadcom and others who offer significant help during the experimental setup. Publisher Copyright: © 2018 IEEE.

PY - 2018/7/13

Y1 - 2018/7/13

N2 - The T10 DIF (Data Integrity Field) and DIX (Data Integrity Extension) specifications provide mechanisms to guarantee end-to-end data integrity and protection in the face of silent data corruption in modern storage systems. However, the Multiple Devices (MD) software RAID driver in Linux does not fully leverage these capabilities to provide such end-to-end guarantees with widely-used RAID modes such as 5 and 6, thereby causing an 'integrity gap' in the Linux I/O stack. This paper describes the design and performance characteristics of a DIX-aware MD module that plugs this integrity gap with minimal overhead to client applications. A PI (Protection Information) operator is added in MD to handle the PI-related operations, and dedicated buffers for PI are allocated and managed in MD RAID-5/6 personality's stripe structures to generate, store, and verify the PI. This allows seamless exchange of PI information among end-applications running in user mode, file systems, the linux block layer, and PI-capable HBAs and drives. Our evaluations show that the DIX-aware MD module has the capability of detecting SDC with the tolerable performance penalty.

AB - The T10 DIF (Data Integrity Field) and DIX (Data Integrity Extension) specifications provide mechanisms to guarantee end-to-end data integrity and protection in the face of silent data corruption in modern storage systems. However, the Multiple Devices (MD) software RAID driver in Linux does not fully leverage these capabilities to provide such end-to-end guarantees with widely-used RAID modes such as 5 and 6, thereby causing an 'integrity gap' in the Linux I/O stack. This paper describes the design and performance characteristics of a DIX-aware MD module that plugs this integrity gap with minimal overhead to client applications. A PI (Protection Information) operator is added in MD to handle the PI-related operations, and dedicated buffers for PI are allocated and managed in MD RAID-5/6 personality's stripe structures to generate, store, and verify the PI. This allows seamless exchange of PI information among end-applications running in user mode, file systems, the linux block layer, and PI-capable HBAs and drives. Our evaluations show that the DIX-aware MD module has the capability of detecting SDC with the tolerable performance penalty.

KW - Linux kernel

KW - Software RAID

KW - T10 PI

UR - http://www.scopus.com/inward/record.url?scp=85050983027&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050983027&partnerID=8YFLogxK

U2 - 10.1109/CCGRID.2018.00091

DO - 10.1109/CCGRID.2018.00091

M3 - Conference contribution

AN - SCOPUS:85050983027

T3 - Proceedings - 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGRID 2018

SP - 609

EP - 615

BT - Proceedings - 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGRID 2018

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGRID 2018

Y2 - 1 May 2018 through 4 May 2018

ER -

Improving data integrity in linux software RAID with protection information (T10-PI)

Abstract

Publication series

Other

Bibliographical note

Keywords

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this