A survey of fault tolerance mechanisms and checkpoint/restart implementations for high performance computing systems
TLDR
The failure rates of HPC systems are reviewed, rollback-recovery techniques which are most often used for long-running applications on HPC clusters are discussed, and a taxonomy is developed for over twenty popular checkpoint/restart solutions.Abstract:
In recent years, High Performance Computing (HPC) systems have been shifting from expensive massively parallel architectures to clusters of commodity PCs to take advantage of cost and performance benefits. Fault tolerance in such systems is a growing concern for long-running applications. In this paper, we briefly review the failure rates of HPC systems and also survey the fault tolerance approaches for HPC systems and issues with these approaches. Rollback-recovery techniques which are most often used for long-running applications on HPC clusters are discussed because they are widely used for long-running applications on HPC systems. Specifically, the feature requirements of rollback-recovery are discussed and a taxonomy is developed for over twenty popular checkpoint/restart solutions. The intent of this paper is to aid researchers in the domain as well as to facilitate development of new checkpointing solutions.read more
Citations
More filters
Proceedings ArticleDOI
Running Resilient MPI Applications on a Dynamic Group of Recommended Processes
TL;DR: This work presents a new model to deal with fault-tolerance in HPC systems in which processes execute tests among themselves in orderto determine whether the processors (or cores) on which they are runningare recommended or non-recommended.
Book ChapterDOI
Analysis and Optimization of a Joint Redundancy and Inspection-Based Maintenance Strategy
TL;DR: The results indicate that this optimization method could find optimal redundancy as well as inspection rate in a joint redundancy and inspection-based maintenance strategy which is widely used in computing systems.
Journal ArticleDOI
ER-Store: A Hybrid Storage Mechanism with Erasure Coding and Replication in Distributed Database Systems
Zijian Li,Chuqiao Xiao +1 more
TL;DR: In this article, a data temperature recognition algorithm that can distinguish data tablets and divide data tablets into three types, cold, warm, and hot, according to the frequency of access is proposed.
Proceedings ArticleDOI
Communication Induced Checkpointing based Fault Tolerance Mechanism – A Review and CIAC-FTM Framework in IoT Environment
TL;DR: In this paper , a communication-induced adaptive checkpointing fault-tolerant mechanism (CIAC-FTM) is proposed to address software faults at application level in IoT. This mechanism places checkpoints at required nodes depending on the type of fault detected, in turn reducing checkpoints and storage overheads.
Proceedings ArticleDOI
Design and Study of Elastic Recovery in HPC Applications
TL;DR: In this article, the authors propose a mechanism to asynchronously store checkpoints into a self-descriptive file format and load the data upon recovery with a different number of processes.
References
More filters
Book ChapterDOI
Time, clocks, and the ordering of events in a distributed system
TL;DR: In this paper, the concept of one event happening before another in a distributed system is examined, and a distributed algorithm is given for synchronizing a system of logical clocks which can be used to totally order the events.
Journal ArticleDOI
Time, clocks, and the ordering of events in a distributed system
TL;DR: In this article, the concept of one event happening before another in a distributed system is examined, and a distributed algorithm is given for synchronizing a system of logical clocks which can be used to totally order the events.
Proceedings ArticleDOI
Live migration of virtual machines
Christopher Clark,Keir Fraser,Steven Hand,Jacob Gorm Hansen,Eric Jul,Christian Limpach,Ian Pratt,Andrew Warfield +7 more
TL;DR: The design options for migrating OSes running services with liveness constraints are considered, the concept of writable working set is introduced, and the design, implementation and evaluation of high-performance OS migration built on top of the Xen VMM are presented.
MPI: A Message-Passing Interface Standard
TL;DR: This document contains all the technical features proposed for the interface and the goal of the Message Passing Interface, simply stated, is to develop a widely used standard for writing message-passing programs.
Journal ArticleDOI
Distributed snapshots: determining global states of distributed systems
K. Mani Chandy,Leslie Lamport +1 more
TL;DR: An algorithm by which a process in a distributed system determines a global state of the system during a computation, which helps to solve an important class of problems: stable property detection.