LoboVault Home

Keeping checkpoint/restart viable for exascale systems


Please use this identifier to cite or link to this item: http://hdl.handle.net/1928/17473

Keeping checkpoint/restart viable for exascale systems

Show full item record

Title: Keeping checkpoint/restart viable for exascale systems
Author: Ferreira, Kurt
Advisor(s): Bridges, Patrick
Committee Member(s): Arnold, Dorian
Taufer, Michela
Crandall, Jed
Department: University of New Mexico. Dept. of Computer Science
Subject: Checkpoint/Restart, Reliability, Exascale, State-Machine Replication
LC Subject(s): Computer networks--Scalability.
Fault tolerant computing.
High performance computing.
Degree Level: Doctoral
Abstract: Next-generation exascale systems, those capable of performing a quintillion operations per second, are expected to be delivered in the next 8-10 years. These systems, which will be 1,000 times faster than current systems, will be of unprecedented scale. As these systems continue to grow in size, faults will become increasingly common, even over the course of small calculations. Therefore, issues such as fault tolerance and reliability will limit application scalability. Current techniques to ensure progress across faults like checkpoint/restart, the dominant fault tolerance mechanism for the last 25 years, are increasingly problematic at the scales of future systems due to their excessive overheads. In this work, we evaluate a number of techniques to decrease the overhead of checkpoint/restart and keep this method viable for future exascale systems. More specifically, this work evaluates state-machine replication to dramatically increase the checkpoint interval (the time between successive checkpoints) and hash-based, probabilistic incremental checkpointing using graphics processing units to decrease the checkpoint commit time (the time to save one checkpoint). Using a combination of empirical analysis, modeling, and simulation, we study the costs and benefits of these approaches on a wide range of parameters. These results, which cover of number of high-performance computing capability workloads, different failure distributions, hardware mean time to failures, and I/O bandwidths, show the potential benefits of these techniques for meeting the reliability demands of future exascale platforms.
Graduation Date: December 2011
URI: http://hdl.handle.net/1928/17473

Files in this item

Files Size Format View Description
dissertation.pdf 2.465Mb PDF View/Open Manuscript

This item appears in the following Collection(s)

Show full item record

UNM Libraries

Search LoboVault


My Account