Abstract
Peer to peer (P2P) grid systems consist of nodes present in multiple organizations and spread across different physical locations. These resources join and leave P2P grid depending upon their determination. Therefore, availability of grid resource cannot be guaranteed at all times. Moreover, failure in network infrastructure, hardware and software of resource can force it to leave grid without any early warnings. Many authors have proposed decentralized scheduling algorithms for P2P grid. In this paper, we have proposed a fault tolerant decentralized scheduling algorithm for P2P grid, which reschedules jobs of grid resource when node failure happens. This mechanism handles node failure in fully decentralized manner. Key feature of this fault tolerant approach is that, it reschedules jobs depending upon communication and computation cost associated with jobs.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
