Theory Comput Syst DOI 10.1007/s00224-014-9599-8 FNB: Fast Non-Blocking Coordinated Checkpointing Protocol for Distributed Systems Zohra Abdelhafidi · Mohamed Djoudi · Nasreddine Lagraa · Mohamed Bachir Yagoubi © Springer Science+Business Media New York 2015 Abstract This paper presents a Fast Non-Blocking coordinated checkpointing pro- tocol for distributed systems with the aim of minimizing the number of requests and mutable checkpoints while reducing the checkpointing latency. Our protocol relies on two mechanisms; the first one is piggybacking dependency information on computa- tion and reply message, thereby, tracking direct, transitive and hidden dependencies among processes. The second one is popular processes; due to the communication between processes, it is more desirable that the checkpointing procedure is initiated by popular processes having more dependency information. In fact, this way may reduce the checkpointing latency and the likelihood of checkpointing halting caused by fault occurrence. We also present a simulation study that compares our proto- col to CSNB protocol (Cao and Singhal Non-Blocking) and CSB.protocol (Cao and Singhal Blocking) Keywords Distributed systems · Fault tolerance · Coordinated checkpointing · Dependency · Popular process Z. Abdelhafidi () · M. Djoudi · N. Lagraa · M. B. Yagoubi Computer Science and Mathematic Laboratory, Amar Telidji University, Road of Ghardaia, BP 37G, Laghouat 03000, Algeria e-mail: z.abdelhafidi@mail.lagh-univ.dz M. Djoudi e-mail: m.djoudi@mail.lagh-univ.dz N. Lagraa e-mail: n.lagraa@mail.lagh-univ.dz M. B. Yagoubi e-mail: m.yagoubi@mail.lagh-univ.dz