Containment Domains: A Scalable, Efficient and Flexible Resilience Scheme for Exascale Systems

Chung, Jinsuk; Lee, Ikhwan; Sullivan, Michael; Ryoo, Jee Ho; Kim, Dong Wan; Yoon, Doe Hyun; Kaplan, Larry; Erez, Mattan

doi:10.1155/2013/473915

Cited by 24 publications

(22 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Formalizations targeting resilience can be found in [17,32]. Containment domains for encapsulating failures within a hierarchical scope are discussed in [13]. Modeling and prediction of failures is addressed in [8,13].…”

Section: Other Important Studies and Discussionmentioning

confidence: 99%

Fault tolerance for remote memory access programming models

Besta

Hoefler

2014

Proceedings of the 23rd International Symposium on High-Performance Parallel and Distributed Computing

View full text Add to dashboard Cite

Remote Memory Access (RMA) is an emerging mechanism for programming high-performance computers and datacenters. However, little work exists on resilience schemes for RMA-based applications and systems. In this paper we analyze fault tolerance for RMA and show that it is fundamentally different from resilience mechanisms targeting the message passing (MP) model. We design a model for reasoning about fault tolerance for RMA, addressing both flat and hierarchical hardware. We use this model to construct several highly-scalable mechanisms that provide efficient low-overhead in-memory checkpointing, transparent logging of remote memory accesses, and a scheme for transparent recovery of failed processes. Our protocols take into account diminishing amounts of memory per core, one of the major features of future exascale machines. The implementation of our fault-tolerance scheme entails negligible additional overheads. Our reliability model shows that inmemory checkpointing and logging provide high resilience. This study enables highly-scalable resilience mechanisms for RMA and fills a research gap between fault tolerance and emerging RMA programming models.

show abstract

Section: Other Important Studies and Discussionmentioning

confidence: 99%

Fault tolerance for remote memory access programming models

Besta

Hoefler

2014

Proceedings of the 23rd International Symposium on High-Performance Parallel and Distributed Computing

View full text Add to dashboard Cite

show abstract

“…The protection domain of the pattern extends to the scope of the primary system, i.e., the scope for which the recovery block is created. Examples of the recovery block pattern in HPC include the Containment Domains (CD) [14] programming construct, which provides a recovery routine initiated upon detection of an error in the execution of the block of code encapsulated by the CD. This enables the CD to constrain the detection and correction of errors to the boundary of the domain.…”

Section: Recovery Block Patternmentioning

confidence: 99%

Resilience Design Patterns: A Structured Approach to Resilience at Extreme Scale

Hukerikar

Engelmann

2017

JSFI

View full text Add to dashboard Cite

Reliability is a serious concern for future extreme-scale high-performance computing (HPC) systems. Projections based on the current generation of HPC systems and technology roadmaps suggest the prevalence of very high fault rates in future systems. While the HPC community has developed various resilience solutions, application-level techniques as well as system-based solutions, the solution space remains fragmented. There are no formal methods and metrics to integrate the various HPC resilience techniques into composite solutions, nor are there methods to holistically evaluate the adequacy and efficacy of such solutions in terms of their protection coverage, and their performance & power efficiency characteristics. Additionally, few of the current approaches are portable to newer architectures and software environments that will be deployed on future systems. In this paper, we develop a structured approach to the design, evaluation and optimization of HPC resilience using the concept of design patterns. A design pattern is a general repeatable solution to a commonly occurring problem. We identify the problems caused by various types of faults, errors and failures in HPC systems and the techniques used to deal with these events. Each well-known solution that addresses a specific HPC resilience challenge is described in the form of a pattern. We develop a complete catalog of such resilience design patterns, which may be used by system architects, system software and tools developers, application programmers, as well as users and operators as essential building blocks when designing and deploying resilience solutions. We also develop a design framework that enhances a designer's understanding the opportunities for integrating multiple patterns across layers of the system stack and the important constraints during implementation of the individual patterns. It is also useful for defining mechanisms and interfaces to coordinate flexible fault management across hardware and software components. The resilience patterns and the design framework also enable exploration and evaluation of design alternatives and support optimization of the cost-benefit trade-offs among performance, protection coverage, and power consumption of resilience solutions. The overall goal of this work is to establish a systematic methodology for the design and evaluation of resilience technologies in extreme-scale HPC systems that keep scientific applications running to a correct solution in a timely and cost-efficient manner despite frequent faults, errors, and failures of various types.

show abstract

“…In the case of memory, a DUE indicates that some data has been lost. This loss of data could be acknowledged and tolerated (by an error tolerant application), it may be corrected by some higher-level protection mechanism (such as checkpoint and restart or a hierarchical state preservation and restoration runtime system [26]), or it may indicate a fail-stop condition where forward progress is halted (but no silent data corruption occurs). Section 5 evaluates Bamboo ECC in the context of machines with high-level state recovery facilities, as many highperformance and high-availability machines have system-level recovery mechanisms in place.…”

Section: Reliabilitymentioning

confidence: 99%