Checkpointing Protocol Research Articles

A fully informed model-based checkpointing protocol for preventing useless checkpoints

Checkpointing and rollback recovery are widely used techniques for handling failures in distributed systems. When processes involved in a distributed computation are allowed to take checkpoints independently without any coordination with each other, some or all of the checkpoints taken may not be part of any consistent global checkpoint, and hence, are useless for recovery. Communication-induced checkpointing algorithms allow processes to take checkpoints independently and also ensure that each checkpoint taken is part of a consistent global checkpoint by forcing processes to take some additional checkpoints. It is well known that it is impossible to design an optimal communication-induced checkpointing algorithm (i.e. a checkpointing algorithm that takes minimum number of forced checkpoints). So, researchers have designed communication-induced checkpointing algorithms that reduce forced checkpoints using different heuristics. In this paper, we present a communication-induced checkpointing algorithm which takes less number of forced checkpoints when compared to some of the existing checkpointing algorithms in its class.

Unified model for assessing checkpointing protocols at extreme‐scale

SUMMARYIn this paper, we present a unified model for several well‐known checkpoint/restart protocols. The proposed model is generic enough to encompass both extremes of the checkpoint/restart space, from coordinated approaches to a variety of uncoordinated checkpoint strategies (with message logging). We identify a set of crucial parameters, instantiate them, and compare the expected efficiency of the fault tolerant protocols, for a given application/platform pair. We then propose a detailed analysis of several scenarios, including some of the most powerful currently available high performance computing platforms, as well as anticipated Exascale designs. The results of this analytical comparison are corroborated by a comprehensive set of simulations. Altogether, they outline comparative behaviors of checkpoint strategies at very large scale, thereby providing insight that is hardly accessible to direct experimentation. Copyright © 2013 John Wiley & Sons, Ltd.

Towards an energy estimator for fault tolerance protocols

Checkpointing protocols have different energy consumption depending on parameters like application features and platform characteristics. To select a protocol for a given execution, we propose an energy estimator that relies on an energy calibration of the considered platform and a user description of the execution settings.

Achieving Checkpointing Global Consistency Through a Hybrid Compile Time and Runtime Protocol

The execution times of large-scale parallel applications on modern multi/many-core systems are usually longer than their mean time between failures. Therefore, parallel applications must tolerate hardware failures to ensure that not all computation is lost on machine failures. Checkpointing and rollback recovery are very useful techniques to implement fault-tolerant applications. In parallel applications a checkpointing protocol is required to guarantee that individual checkpoints form a consistent global state. Coordinated approaches are the most popular solution to achieve global checkpointing consistency. However, their main drawback is their poor scalability due to the required runtime coordination. This work presents a new hybrid protocol that combines the detection of valid recovery lines at compile time with a light and asynchronous protocol at runtime to negotiate the closest valid recovery line. Experimental results prove the efficiency and scalability of the proposal.

Scalable Checkpointing-Based Rollback Recovery Protocol for Geographically Distributed Systems

Two opposite approaches were proposed to address some scalability problem resulting from coordinated checkpointing's synchronization during failure-free operation: minimizing the number of checkpointing participants and having the checkpointing process non-blocking. However, these previous approaches, oblivious to the underlying network, may not fundamentally provide any breakthrough for ensuring high scalability required in very large-scale P2P-based systems. This paper proposes a non-blocking coordinated checkpointing protocol to significantly reduce checkpointing synchronization overhead by structuring the peer-to-peer network into a set of groups according to a particular criterion. In this protocol, among processes in a group, one is designated as representative with the following special roles, intra-group and inter-group checkpointing coordination. Intra-group checkpointing coordination addresses the checkpointing procedure among processes within a group. On the other hand, inter-group checkpointing coordination is performed only among representatives. Thanks to this beneficial feature, the proposed protocol may considerably reduce the number of checkpointing control messages routed on core networks compared with the existing ones.

System Progress Estimation in Time based Coordinated Checkpointing Protocols

A mobile computing system consists of mobile and stationary nodes. Checkpointing is an efficient fault tolerant technique used in distributed systems. Checkpointing in mobile systems faces many new challenges such as low wireless bandwidth, frequent disconnections and lack of stable storage on mobile nodes. Coordinated Checkpointing that minimizes the number of processes to take useless checkpoints is a suitable approach to introduce fault tolerance in such systems. The time-based checkpointing protocol eliminates communication overheads by avoiding extra control messages and useless checkpoints. Such protocols directly accesses stable storage when checkpoints are saved. In this paper a new probabilistic approach for evaluation of the system progress is devised which is suitable for the mobile distribution applications. The system behavior is observed by varying some system parameters such as fault rate, clock drift rate, saved checkpoint time, checkpoint intervals. A validation regarding system progress is made via a simulation technique. The simulation results show that the proposed probabilistic model is well suited for the mobile computing systems. General Terms Checkpointing, System progress, Simulation

A multi-cycle checkpointing protocol that ensures strict 1-rollback

In this paper, a checkpointing protocol based on loose synchronization is proposed. The protocol enables processes to take checkpoints at different frequencies so that each process can control its rollback distance. In traditional asynchronous and quasi-synchronous checkpointing protocols, the checkpoints that are not up-to-date may be used for recovery. As a result, the rollback distance is often difficult to control. In the proposed protocol, the checkpoint cycle of each process is dynamically adjusted using a pessimistic scheme so that strict 1-rollback is achieved; namely, one of the last two checkpoints of each process can be utilized for recovery.

An Efficient Coordinated Checkpointing Approach for Distributed Computing Systems with Reliable Channels

In distributed systems, likelihood of failure increases with increase in the number of processes and a single failure often renders the entire system state useless. Checkpointing and rollback recovery is a common technique used for increasing the system reliability against various anticipated and unanticipated failures. Checkpointing can be independent, quasi-synchronous and coordinated. Coordinated checkpointing can be blocking or non-blocking. Also, either all the processes in the distributed system may need to checkpoint or only a minimum number of processes may be required to checkpoint. Minimizing the number of processes to checkpoint may introduce blocking. The non-blocking checkpointing protocols introduce overhead of piggybacking some information for non-intrusiveness. Minimization of this piggybacked information is the objective of our work. We have designed a non-blocking coordinated checkpointing protocol for distributed systems with reliable communication channels that minimize piggybacked information on each message.

Message efficient global snapshot recording using a self stabilizing spanning tree in a MANET

Distributed snapshots are a significant paradigm for distributed systems. These are applied for constructing checkpoint protocols, apart from investigating, testing, or proving properties in distributed executions such as deadlocks and termination. Though a number of snapshot algorithms exist for traditional distributed systems, they cannot be directly applied to mobile ad hoc networks due to the constraints of topology and hostile conditions in which the MANETs operate. The paper presents an algorithm for recording the global state of a clustered and multi-hop mobile ad hoc network. The proposed algorithm imposes a self stabilizing spanning tree upon the network topology to reduce the message overhead in the system due to the algorithm and to deal with the dynamic nature of MANETs. Moreover, the protocol handles concurrent snapshot initiation and does not require FIFO channels. The message complexity of snapshot recording is O(n-1) where n is the number of clusters in the system

Independent checkpointing in a heterogeneous grid environment

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 various checkpointing protocols and different checkpointer packages (e.g. BLCR, LinuxSSI, OpenVZ, etc.) in a transparent manner through a uniform checkpointer interface. In this paper, we present the integration of a backward error recovery protocol based on independent checkpointing into the XtreemGCP service. The solution we propose is not checkpointer bound and thus can be transparently used on top of any checkpointer package. 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.

Theoretical and experimental evaluation of communication-induced checkpointing protocols in [formula omitted] and [formula omitted] families

Communication-induced checkpointing (CIC) protocols help in bounding rollback propagation by ensuring that each checkpoint taken is useful, while at the same time allowing each process to take checkpoints independently. In this paper, we focus on the evaluation of CIC protocols belonging to two families, namely, the F E family and F Lazy - E family. We present both theoretical and experimental evaluation of the protocols belonging to these two families. The results of our experimental evaluation not only confirm the theoretical comparison but also reveals the fine differences between these protocols.

Soft-Checkpointing Based Hybrid Synchronous Checkpointing Protocol for Mobile Distributed Systems

Minimum-process coordinated checkpointing is a suitable approach to introduce fault tolerance in mobile distributed systems transparently. In order to balance the checkpointing overhead and the loss of computation on recovery, the authors propose a hybrid checkpointing algorithm, wherein an all-process coordinated checkpoint is taken after the execution of minimum-process coordinated checkpointing algorithm for a fixed number of times. In coordinated checkpointing, if a single process fails to take its checkpoint; all the checkpointing effort goes waste, because, each process has to abort its tentative checkpoint. In order to take the tentative checkpoint, an MH (Mobile Host) needs to transfer large checkpoint data to its local MSS over wireless channels. In this regard, the authors propose that in the first phase, all concerned MHs will take soft checkpoint only. Soft checkpoint is similar to mutable checkpoint. In this case, if some process fails to take checkpoint in the first phase, then MHs need to abort their soft checkpoints only. The effort of taking a soft checkpoint is negligibly small as compared to the tentative one. In the minimum-process coordinated checkpointing algorithm, an effort has been made to minimize the number of useless checkpoints and blocking of processes using probabilistic approach.

Fault tolerance for data parallel programs

The main issues when supporting fault tolerance based on checkpointing and rollback recovery for High-Performance applications are related to the scalability of the introduced support, the possibility of analyzing the induced overhead and, in more general terms, the optimization of the trade-off between failure-free and recovery performances. In this paper we describe our contribution in fault tolerance for high-level structured parallelism models. We take a different viewpoint w.r.t. existing contributions, by introducing a methodology to derive interesting properties to support fault tolerance. We show how to apply this methodology to a general data parallel model, deriving useful properties to introduce a class of checkpointing protocols. Thanks to this methodology, this class of protocols is not affected by the described issues. We exemplify two checkpointing protocols and the related rollback recovery techniques. For each protocol we also derive cost models statically describing the failure-free performance, which can be used for performance tuning or to target some Quality of Service parameter. To assess the innovation of the results we analytically and experimentally compare the introduced protocols with two literature protocols. Results show that while the protocols introduced in this paper permit the definition of cost models and have a good scalability, the literature protocols do not always have these properties. Copyright © 2010 John Wiley & Sons, Ltd.

Design and Performance Analysis of Coordinated Checkpointing Algorithms for Distributed Mobile Systems

Checkpointing is an efficient fault tolerance technique used in distributed systems. Mobile computing raises many new issues, such as high mobility, lack of stable storage on mobile hosts (MHs), low bandwidth of wireless channels, limited battery life and disconnections that make the traditional checkpointing protocols unsuitable for such systems. Several checkpointing algorithms have been reported in the literature. In this paper, we analyze some of existing coordinated checkpointing algorithms on the basic of blocking time, synchronization message overhead, number of processes required to checkpoint, number of useless checkpoint, piggybacked information messages onto computation messages and concurrent execution. We also proposed an efficient checkpointing algorithm to reduce the checkpointing overheads. Our checkpoint algorithm does not have any synchronization message overhead as it uses time to indirectly coordinate to create the consistent cut in distributed mobile system without increasing the number of checkpoints..

A Review of Fault Tolerant Checkpointing Protocols for Mobile Computing Systems

A distributed system is a collection of independent entities that cooperate to solve a problem that cannot be individually solved. A mobile computing system is a distributed system where some of processes are running on mobile hosts (MHs), whose location in the network changes with time. Mobile distributed systems raise new issues such as mobility, low bandwidth of wireless channels, disconnections, limited battery power and lack of reliable stable storage on mobile nodes. This paper addresses the problem of fault tolerant computing in mobile distributed systems. The techniques described are based on checkpointing and roll back recovery.

Anti-message Logging Based Coordinated Checkpointing Protocol for Deterministic Mobile Computing Systems

Anti-message Logging Based Coordinated Checkpointing Protocol for Deterministic Mobile Computing Systems

A Low-overhead Minimum Process Coordinated Checkpointing Algorithm for Mobile Distributed System

A distributed system is a collection of independent entities that cooperate to solve a problem that cannot be individually solved. A mobile computing system is a distributed system where some of processes are running on mobile hosts (MHs), whose location in the network changes with time. The number of processes that take checkpoints is minimized to 1) avoid awakening of MHs in doze mode of operation, 2) minimize thrashing of MHs with checkpointing activity, 3) save limited battery life of MHs and low bandwidth of wireless channels. In minimum-process checkpointing protocols, some useless checkpoints are taken or blocking of processes takes place. In this paper, we propose a minimum-process coordinated checkpointing algorithm for non-deterministic mobile distributed systems, where no useless checkpoints are taken. An effort has been made to minimize the blocking of processes and synchronization message overhead. We try to reduce the loss of checkpointing effort when any process fails to take its checkpoint in coordination with others.

Real Time Snapshot Collection Algorithm for Mobile Distributed Systems with Minimum Number of Checkpoints

Checkpointing is an efficient way of implementing fault tolerance in distributed systems. Mobile computing raises many new issues, such as high mobility, lack of stable storage on mobile hosts (MHs), low bandwidth of wireless channels, limited battery life and disconnections that make the traditional checkpointing protocols unsuitable for such systems. Minimum process non-blocking coordinated checkpointing may be useful for mobile distributed system as this approach is domino-free, requires at most two checkpoints of each process on stable storage, forces only interacting processes to checkpoint and does not suspend their underlying computation during checkpointing. Sometimes, it also requires piggybacking of information onto normal messages, blocking of the underlying computation or taking some useless checkpoints. In this paper, we propose a non-blocking minimum process coordinated checkpointing algorithm that requires minimum bandwidth over wireless channels and does not requires any induced/forced or mutable checkpoints and reduce the height of checkpointing tree without taking any extra overhead in real time.

A weighted checkpointing protocol for mobile distributed systems

Here, we propose a weighted checkpointing approach for Mobile Distributed Computing Systems (MDCSs) that significantly reduces checkpointing overheads on mobile nodes. Checkpointing protocols can be coordinated, log-based or quasi-synchronous. Coordinated checkpointing requires extra synchronisation messages and may block the underlying computation. In quasi-synchronous approach, processes have limited autonomy in checkpointing but all nodes need not checkpoint concurrently. Such protocols guarantee consistent global state but results in dynamic checkpointing overheads. To minimise these overheads, we propose a weighted checkpointing protocol that requires no synchronisation messages, reduces the checkpointing overheads at mobile nodes but requires logging for mobile nodes. Simulation results show that the new approach is better than quasi-synchronous approach.

HIERARCHICAL REPLICATION TECHNIQUES TO ENSURE CHECKPOINT STORAGE RELIABILITY IN GRID ENVIRONMENT

An efficient and reliable fault tolerance protocol plays a key role in High Performance Computing. Rollback recovery is the most common fault tolerance technique used in High Performance Computing and especially in MPI applications. This technique relies on the reliability of the checkpoint storage. Most of the rollback recovery protocols assume that the checkpoint servers machines are reliable. However, in a grid environment any unit can fail at any moment, including components used to connect different administrative domains. Such failures lead to the loss of a whole set of machines, including the more reliable machines used to store the checkpoints in this administrative domain. Thus it is not safe to rely on the high Mean Time Between Failures of specific machines to store the checkpoint images.This paper introduces a new coordinated checkpoint protocol, which tolerates checkpoint server failures and clusters failures, and ensures a checkpoint storage reliability in a grid environment. To provide this reliability the protocol is based on a replication process. We propose new hierarchical replication strategies that exploit the locality of checkpoint images in order to minimize inter-cluster communication.We evaluate the effectiveness of our two hierarchical replication strategies through simulations against several criteria such as topology and scalability.