Revisiting I/O Behavior in Large-Scale Storage Systems: The Expected and the Unexpected

被引：32

作者：

Patel, Tirthak ^{[1
]}

Byna, Surendra ^{[2
]}

Lockwood, Glenn K. ^{[2
]}

Tiwari, Devesh ^{[1
]}

机构：

[1] Northeastern Univ, Boston, MA 02115 USA

[2] Lawrence Berkeley Natl Lab, Berkeley, CA USA

来源：

PROCEEDINGS OF SC19: THE INTERNATIONAL CONFERENCE FOR HIGH PERFORMANCE COMPUTING, NETWORKING, STORAGE AND ANALYSIS | 2019年

基金：

美国国家科学基金会;

关键词：

D O I：

10.1145/3295500.3356183

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

Large-scale applications typically spend a large fraction of their execution time performing I/O to a parallel storage system. However, with rapid progress in compute and storage system stack of large-scale systems, it is critical to investigate and update our understanding of the I/O behavior of large-scale applications. Toward that end, in this work, we monitor, collect and analyze a year worth of storage system data from a large-scale production parallel storage system. We perform temporal, spatial and correlative analysis of the system and uncover surprising patterns which defy existing assumptions and have important implications for future systems.

引用

页数：13

共 59 条

[11]

[Anonymous], 2017, NETW ARCH STOR NAS 2

[12]

[Anonymous], 2015, I O PERFORMANCE ANAL

[13]

[Anonymous], 2018, STEM CELLS INT

[14]

Austin B., 2014, NERSC 2014 WORKLOAD

[15]

Bhimji W, 2016, ACCELERATING SCI NER

[16] HPC global file system performance analysis using a scientific-application derived benchmark [J].

Borrill, Julian ;

Oliker, Leonid ;

Shalf, John ;

Shan, Hongzhang ;

Uselton, Andrew .

PARALLEL COMPUTING, 2009, 35 (06) :358-373

[17]

Brinkmann A., 2017, TECHNICAL REPORT

[18] Understanding and Improving Computational Science Storage Access through Continuous Characterization [J].

Carns, Philip ;

Harms, Kevin ;

Allcock, William ;

Bacon, Charles ;

Lang, Samuel ;

Latham, Robert ;

Ross, Robert .

ACM TRANSACTIONS ON STORAGE, 2011, 7 (03)

[19]

Chien S. W., 2019, ARXIV190304364

[20] Characterizing Deep-Learning I/O Workloads in TensorFlow [J].

Chien, Steven W. D. ;

Markidis, Stefano ;

Sishtla, Chaitanya Prasad ;

Santos, Luis ;

Herman, Pawel ;

Narasimhamurthy, Sai ;

Laure, Erwin .

PROCEEDINGS OF 2018 IEEE/ACM 3RD JOINT INTERNATIONAL WORKSHOP ON PARALLEL DATA STORAGE & DATA INTENSIVE SCALABLE COMPUTING SYSTEMS (PDSW-DISCS), 2018, :54-63

← 1 2 3 4 5 6 →