LDPLFS: Improving I/O performance without application modification

S. A. Wright; S. D. Hammond; S. J. Pennycook; I. Miller; J. A. Herdman; S. A. Jarvis

doi:10.1109/IPDPSW.2012.172

LDPLFS: Improving I/O performance without application modification

S. A. Wright^*, S. D. Hammond, S. J. Pennycook, I. Miller, J. A. Herdman, S. A. Jarvis

^*Corresponding author for this work

Engineering and Physical Sciences

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

5 Citations (Scopus)

Abstract

Input/Output (I/O) operations can represent a significant proportion of run-time when large scientific applications are run in parallel and at scale. In order to address the growing divergence between processing speeds and I/O performance, the Parallel Log-structured File System (PLFS) has been developed by EMC Corporation and the Los Alamos National Laboratory (LANL) to improve the performance of parallel file activities. Currently, PLFS requires the use of either (i) the FUSE Linux Kernel module, (ii) a modified MPI library with a customised ROMIO MPI-IO library, or (iii) an application rewrite to utilise the PLFS API directly. In this paper we present an alternative method of utilising PLFS in applications. This method employs a dynamic library to intercept the low-level POSIX operations and retarget them to use the equivalents offered by PLFS. We demonstrate our implementation of this approach, named LDPLFS, on a set of standard UNIX tools, as well on as a set of standard parallel I/O intensive mini-applications. The results demonstrate almost equivalent performance to a modified build of ROMIO and improvements over the FUSE-based approach. Furthermore, through our experiments we demonstrate decreased performance in PLFS when ran at scale on the Lustre file system.

Original language	English
Title of host publication	Proceedings of the 2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2012
Pages	1352-1359
Number of pages	8
DOIs	https://doi.org/10.1109/IPDPSW.2012.172
Publication status	Published - 2012
Event	2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2012 - Shanghai, China Duration: 21 May 2012 → 25 May 2012

Publication series

Name	Proceedings of the 2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2012

Conference

Conference	2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2012
Country/Territory	China
City	Shanghai
Period	21/05/12 → 25/05/12

Keywords

Data Storage Systems
File Systems
High Performance Computing
I/O

ASJC Scopus subject areas

Software

Access to Document

10.1109/IPDPSW.2012.172

Cite this

Wright, S. A., Hammond, S. D., Pennycook, S. J., Miller, I., Herdman, J. A., & Jarvis, S. A. (2012). LDPLFS: Improving I/O performance without application modification. In Proceedings of the 2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2012 (pp. 1352-1359). Article 6270802 (Proceedings of the 2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2012). https://doi.org/10.1109/IPDPSW.2012.172

Wright, S. A. ; Hammond, S. D. ; Pennycook, S. J. et al. / LDPLFS : Improving I/O performance without application modification. Proceedings of the 2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2012. 2012. pp. 1352-1359 (Proceedings of the 2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2012).

@inproceedings{ca84bd13fea3423e85bdb728051f3565,

title = "LDPLFS: Improving I/O performance without application modification",

abstract = "Input/Output (I/O) operations can represent a significant proportion of run-time when large scientific applications are run in parallel and at scale. In order to address the growing divergence between processing speeds and I/O performance, the Parallel Log-structured File System (PLFS) has been developed by EMC Corporation and the Los Alamos National Laboratory (LANL) to improve the performance of parallel file activities. Currently, PLFS requires the use of either (i) the FUSE Linux Kernel module, (ii) a modified MPI library with a customised ROMIO MPI-IO library, or (iii) an application rewrite to utilise the PLFS API directly. In this paper we present an alternative method of utilising PLFS in applications. This method employs a dynamic library to intercept the low-level POSIX operations and retarget them to use the equivalents offered by PLFS. We demonstrate our implementation of this approach, named LDPLFS, on a set of standard UNIX tools, as well on as a set of standard parallel I/O intensive mini-applications. The results demonstrate almost equivalent performance to a modified build of ROMIO and improvements over the FUSE-based approach. Furthermore, through our experiments we demonstrate decreased performance in PLFS when ran at scale on the Lustre file system.",

keywords = "Data Storage Systems, File Systems, High Performance Computing, I/O",

author = "Wright, {S. A.} and Hammond, {S. D.} and Pennycook, {S. J.} and I. Miller and Herdman, {J. A.} and Jarvis, {S. A.}",

year = "2012",

doi = "10.1109/IPDPSW.2012.172",

language = "English",

isbn = "9780769546766",

series = "Proceedings of the 2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2012",

pages = "1352--1359",

booktitle = "Proceedings of the 2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2012",

note = "2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2012 ; Conference date: 21-05-2012 Through 25-05-2012",

}

Wright, SA, Hammond, SD, Pennycook, SJ, Miller, I, Herdman, JA & Jarvis, SA 2012, LDPLFS: Improving I/O performance without application modification. in Proceedings of the 2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2012., 6270802, Proceedings of the 2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2012, pp. 1352-1359, 2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2012, Shanghai, China, 21/05/12. https://doi.org/10.1109/IPDPSW.2012.172

LDPLFS: Improving I/O performance without application modification. / Wright, S. A.; Hammond, S. D.; Pennycook, S. J. et al.
Proceedings of the 2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2012. 2012. p. 1352-1359 6270802 (Proceedings of the 2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2012).

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

TY - GEN

T1 - LDPLFS

T2 - 2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2012

AU - Wright, S. A.

AU - Hammond, S. D.

AU - Pennycook, S. J.

AU - Miller, I.

AU - Herdman, J. A.

AU - Jarvis, S. A.

PY - 2012

Y1 - 2012

N2 - Input/Output (I/O) operations can represent a significant proportion of run-time when large scientific applications are run in parallel and at scale. In order to address the growing divergence between processing speeds and I/O performance, the Parallel Log-structured File System (PLFS) has been developed by EMC Corporation and the Los Alamos National Laboratory (LANL) to improve the performance of parallel file activities. Currently, PLFS requires the use of either (i) the FUSE Linux Kernel module, (ii) a modified MPI library with a customised ROMIO MPI-IO library, or (iii) an application rewrite to utilise the PLFS API directly. In this paper we present an alternative method of utilising PLFS in applications. This method employs a dynamic library to intercept the low-level POSIX operations and retarget them to use the equivalents offered by PLFS. We demonstrate our implementation of this approach, named LDPLFS, on a set of standard UNIX tools, as well on as a set of standard parallel I/O intensive mini-applications. The results demonstrate almost equivalent performance to a modified build of ROMIO and improvements over the FUSE-based approach. Furthermore, through our experiments we demonstrate decreased performance in PLFS when ran at scale on the Lustre file system.

AB - Input/Output (I/O) operations can represent a significant proportion of run-time when large scientific applications are run in parallel and at scale. In order to address the growing divergence between processing speeds and I/O performance, the Parallel Log-structured File System (PLFS) has been developed by EMC Corporation and the Los Alamos National Laboratory (LANL) to improve the performance of parallel file activities. Currently, PLFS requires the use of either (i) the FUSE Linux Kernel module, (ii) a modified MPI library with a customised ROMIO MPI-IO library, or (iii) an application rewrite to utilise the PLFS API directly. In this paper we present an alternative method of utilising PLFS in applications. This method employs a dynamic library to intercept the low-level POSIX operations and retarget them to use the equivalents offered by PLFS. We demonstrate our implementation of this approach, named LDPLFS, on a set of standard UNIX tools, as well on as a set of standard parallel I/O intensive mini-applications. The results demonstrate almost equivalent performance to a modified build of ROMIO and improvements over the FUSE-based approach. Furthermore, through our experiments we demonstrate decreased performance in PLFS when ran at scale on the Lustre file system.

KW - Data Storage Systems

KW - File Systems

KW - High Performance Computing

KW - I/O

UR - http://www.scopus.com/inward/record.url?scp=84867427930&partnerID=8YFLogxK

U2 - 10.1109/IPDPSW.2012.172

DO - 10.1109/IPDPSW.2012.172

M3 - Conference contribution

AN - SCOPUS:84867427930

SN - 9780769546766

T3 - Proceedings of the 2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2012

SP - 1352

EP - 1359

BT - Proceedings of the 2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2012

Y2 - 21 May 2012 through 25 May 2012

ER -

Wright SA, Hammond SD, Pennycook SJ, Miller I, Herdman JA, Jarvis SA. LDPLFS: Improving I/O performance without application modification. In Proceedings of the 2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2012. 2012. p. 1352-1359. 6270802. (Proceedings of the 2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2012). doi: 10.1109/IPDPSW.2012.172

LDPLFS: Improving I/O performance without application modification

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this