Independent checkpointing in a heterogeneous grid environment

Abstract

Abstract-The EU-funded XtreemOS project implements an open-source grid operating system based on Linux. In order to provide fault tolerance and migration for grid applications, it integrates a distributed grid-checkpointing service called XtreemGCP. This service is designed to support different checkpointing protocols and to address the underlying gridnode checkpointers (e.g. BLCR, LinuxSSI, OpenVZ, etc.) in a transparent manner through a uniform interface. In this paper, we present the integration of an independent checkpointing and rollback-recovery protocol into the XtreemGCP. The solution we propose is not checkpointer bound and thus can be transparently used on top of any grid-node checkpointer.To evaluate the prototype we run it within a heterogeneous environment composed of single-PC nodes and a Single System Image (SSI) cluster. The experimental results demonstrate the capability of the XtreemGCP service to integrate different checkpointing protocols and independently checkpoint a distributed application within a heterogeneous grid environment. Moreover, the performance evaluation also shows that our solution outperforms the existing coordinated checkpointing protocol in terms of scalability.

Optimization of checkpointing/recovery strategy in cloud computing with adaptive storage management

“…There are generally three types of protocols. Coordinated Checkpointing: This protocol requires processes to coordinate the establishment of their checkpoints to form a coherent global state. Independent checkpointing: This protocol avoids the synchronization phase by allowing each process to save its local state Independently of the others. The advantage of this type of checkpointing is that the overhead is reduced and it can be controlled. Checkpointing induced by communication: In this protocol, the processes take two kinds of checkpoints, local and forced .…”

“…• Independent checkpointing 5,8,9 : This protocol avoids the synchronization phase by allowing each process to save its local state Independently of the others. The advantage of this type of checkpointing is that the overhead is reduced and it can be controlled.…”

“…If we take as an example the grid computing, in the work of Boccia et al, the authors used a coordinated checkpointing in parallel applications. In other works, the checkpointing was also used to ensure the fault tolerance. The replication also is exploited in fault tolerance in grid .…”

HOPE: A Hybrid Optimistic checkpointing and selective Pessimistic mEssage logging protocol for large scale distributed systems

“…Kovcs et al [32] described the TotalCheckpoint tool, which integrate library-level checkpointer with the application, for software-heterogeneous ClusterGrid infrastructures. Feller et al [33] designed and implemented an extended version of the XtreemOS grid checkpointer, which supports the independent checkpointing protocol. And their results showed that independent checkpointing is more suited than coordinated checkpointing in a heterogeneous grid environment.…”