Understanding the Impact of BPRAM on Incremental Checkpoint

Xu LI; Kai LU; Xiaoping WANG; Bin DAI; Xu ZHOU

doi:10.1587/transinf.E96.D.663

Understanding the Impact of BPRAM on Incremental Checkpoint

Xu LI, Kai LU, Xiaoping WANG, Bin DAI, Xu ZHOU

Full Text Views

0

Cite this

Summary :

Existing large-scale systems suffer from various hardware/software failures, motivating the research of fault-tolerance techniques. Checkpoint-restart techniques are widely applied fault-tolerance approaches, especially in scientific computing systems. However, the overhead of checkpoint largely influences the overall system performance. Recently, the emerging byte-addressable, persistent memory technologies, such as phase change memory (PCM), make it possible to implement checkpointing in arbitrary data granularity. However, the impact of data granularity on the checkpointing cost has not been fully addressed. In this paper, we investigate how data granularity influences the performance of a checkpoint system. Further, we design and implement a high-performance checkpoint system named AG-ckpt. AG-ckpt is a hybrid-granularity incremental checkpointing scheme through: (1) low-cost modified-memory detection and (2) fine-grained memory duplication. Moreover, we also formulize the performance-granularity relationship of checkpointing systems through a mathematical model, and further obtain the optimum solutions. We conduct the experiments through several typical benchmarks to verify the performance gain of our design. Compared to conventional incremental checkpoint, our results show that AG-ckpt can reduce checkpoint data amount up to 50% and provide a speedup of 1.2x-1.3x on checkpoint efficiency.

Publication: IEICE TRANSACTIONS on Information Vol.E96-D No.3 pp.663-672

Publication Date: 2013/03/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1587/transinf.E96.D.663

Type of Manuscript: PAPER

Category: Dependable Computing

Cite this

Copy

Xu LI, Kai LU, Xiaoping WANG, Bin DAI, Xu ZHOU, "Understanding the Impact of BPRAM on Incremental Checkpoint" in IEICE TRANSACTIONS on Information, vol. E96-D, no. 3, pp. 663-672, March 2013, doi: 10.1587/transinf.E96.D.663.
Abstract: Existing large-scale systems suffer from various hardware/software failures, motivating the research of fault-tolerance techniques. Checkpoint-restart techniques are widely applied fault-tolerance approaches, especially in scientific computing systems. However, the overhead of checkpoint largely influences the overall system performance. Recently, the emerging byte-addressable, persistent memory technologies, such as phase change memory (PCM), make it possible to implement checkpointing in arbitrary data granularity. However, the impact of data granularity on the checkpointing cost has not been fully addressed. In this paper, we investigate how data granularity influences the performance of a checkpoint system. Further, we design and implement a high-performance checkpoint system named AG-ckpt. AG-ckpt is a hybrid-granularity incremental checkpointing scheme through: (1) low-cost modified-memory detection and (2) fine-grained memory duplication. Moreover, we also formulize the performance-granularity relationship of checkpointing systems through a mathematical model, and further obtain the optimum solutions. We conduct the experiments through several typical benchmarks to verify the performance gain of our design. Compared to conventional incremental checkpoint, our results show that AG-ckpt can reduce checkpoint data amount up to 50% and provide a speedup of 1.2x-1.3x on checkpoint efficiency.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E96.D.663/_p

Copy

@ARTICLE{e96-d_3_663,
author={Xu LI, Kai LU, Xiaoping WANG, Bin DAI, Xu ZHOU, },
journal={IEICE TRANSACTIONS on Information},
title={Understanding the Impact of BPRAM on Incremental Checkpoint},
year={2013},
volume={E96-D},
number={3},
pages={663-672},
abstract={Existing large-scale systems suffer from various hardware/software failures, motivating the research of fault-tolerance techniques. Checkpoint-restart techniques are widely applied fault-tolerance approaches, especially in scientific computing systems. However, the overhead of checkpoint largely influences the overall system performance. Recently, the emerging byte-addressable, persistent memory technologies, such as phase change memory (PCM), make it possible to implement checkpointing in arbitrary data granularity. However, the impact of data granularity on the checkpointing cost has not been fully addressed. In this paper, we investigate how data granularity influences the performance of a checkpoint system. Further, we design and implement a high-performance checkpoint system named AG-ckpt. AG-ckpt is a hybrid-granularity incremental checkpointing scheme through: (1) low-cost modified-memory detection and (2) fine-grained memory duplication. Moreover, we also formulize the performance-granularity relationship of checkpointing systems through a mathematical model, and further obtain the optimum solutions. We conduct the experiments through several typical benchmarks to verify the performance gain of our design. Compared to conventional incremental checkpoint, our results show that AG-ckpt can reduce checkpoint data amount up to 50% and provide a speedup of 1.2x-1.3x on checkpoint efficiency.},
keywords={},
doi={10.1587/transinf.E96.D.663},
ISSN={1745-1361},
month={March},}

Copy

TY - JOUR
TI - Understanding the Impact of BPRAM on Incremental Checkpoint
T2 - IEICE TRANSACTIONS on Information
SP - 663
EP - 672
AU - Xu LI
AU - Kai LU
AU - Xiaoping WANG
AU - Bin DAI
AU - Xu ZHOU
PY - 2013
DO - 10.1587/transinf.E96.D.663
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E96-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2013
AB - Existing large-scale systems suffer from various hardware/software failures, motivating the research of fault-tolerance techniques. Checkpoint-restart techniques are widely applied fault-tolerance approaches, especially in scientific computing systems. However, the overhead of checkpoint largely influences the overall system performance. Recently, the emerging byte-addressable, persistent memory technologies, such as phase change memory (PCM), make it possible to implement checkpointing in arbitrary data granularity. However, the impact of data granularity on the checkpointing cost has not been fully addressed. In this paper, we investigate how data granularity influences the performance of a checkpoint system. Further, we design and implement a high-performance checkpoint system named AG-ckpt. AG-ckpt is a hybrid-granularity incremental checkpointing scheme through: (1) low-cost modified-memory detection and (2) fine-grained memory duplication. Moreover, we also formulize the performance-granularity relationship of checkpointing systems through a mathematical model, and further obtain the optimum solutions. We conduct the experiments through several typical benchmarks to verify the performance gain of our design. Compared to conventional incremental checkpoint, our results show that AG-ckpt can reduce checkpoint data amount up to 50% and provide a speedup of 1.2x-1.3x on checkpoint efficiency.
ER -