Using cliques of nodes to store desktop grid checkpoints

Authors

Filipe Araujo
Patricio Domingues
Derrik Kondo
Luís Silva

Abstract

Checkpoints that store intermediate results of computation have a fundamental
impact on the computing throughput of Desktop Grid systems, like BOINC.
Currently, BOINC workers store their checkpoints locally. A major limitation
of this approach is that whenever a worker leaves unﬁnished computation, no
other worker can proceed from the last stable checkpoint. This forces tasks to be
restarted from scratch when the original machine is no longer available.

To overcome this limitation, we propose to share checkpoints between nodes.
To organize this mechanism, we arrange nodes to form complete graphs (cliques),
where nodes share all the checkpoints they compute. Cliques function as sur-
vivable units, where checkpoints and tasks are not lost as long as one of the
nodes of the clique remains alive. To simplify construction and maintenance of
the cliques, we take advantage of the central supervisor of BOINC. To evaluate
our solution, we combine simulation with some real data to answer the most
fundamental question: what do we need to pay for increased throughput?

Subject

Desktop Grid

Conference

Coregrid Integration Workshop, April 2008

PDF File

Cited by

Year 2012 : 1 citations

Ahmad Al-Shishtawy, ”Self-Management for Large-Scale Distributed Systems”, PhD Thesis, KTH School of Information and Communication Technology, Stockholm, Sweden, 2012.

Year 2010 : 1 citations

Fedak, G., “Recent Advances and Research Challenges in Desktop Grid and Volunteer Computing", Grids, P2P and Services Computing, pp. 171-185, 2010

Year 2009 : 1 citations

Hóglund, J. and Al-Shishtawy, A. and Parlavantzas, N., “D1. 5: Full Specification & Final Prototypes of Overlay Services”, 2009

Year 2008 : 2 citations

Ahmad Al-Shishtawy, Joel Höglund, Konstantin Popov, Nikos Parlavantzas, Vladimir Vlassov, Per Brand, "Enabling Self-Management Of Component Based Distributed Applications?, From Grids to Service and Pervasive Computing, pp 163 174, Thierry Priol and Marco Vanneschi (eds), Springer-Verlag, ISBN: 978-0-387-09454-0, 2008

[PDF] D1. 5: Full Specification & Final Prototypes of Overlay Servicesgrid4all.eu [PDF]
D Level - grid4all.eu
Page 1. Project no. 034567 Grid4All Specific Targeted Research Project (STREP) Thematic
Priority 2: Information Society Technologies D1.5: Full Specification & Final Prototypes of
Overlay Services Due date of deliverable: 1st December 2008. ...
Related articles - View as HTML