Coordinated Checkpointing Algorithm Research Articles

Anti-message Logging based Check pointing Algorithm for Mobile Distributed Systems

Checkpointing is one of the commonly used techniques to provide fault tolerance in distributed systems so that the system can operate even if one or more components have failed. However, mobile computing systems are constrained by low bandwidth, mobility, lack of stable storage, frequent disconnections and limited battery life. Hence checkpointing protocols which have fewer checkpoints are preferred in mobile environment. In this paper, we propose a minimum-process coordinated Checkpointing algorithm for checkpointing deterministic distributed applications on mobile systems. We eliminate useless checkpoints as well as blocking of processes during checkpoints at the cost of logging anti-messages of very few messages during Checkpointing. We also try to minimize the loss of checkpointing effort.

A Checkpointing Algorithm Based Unreliable Non-FIFO Channels

We propose a coordinated checkpointing algorithm based unreliable non-FIFO channel. In unreliable non-FIFO channel, the system can lose, duplicate, or reorder messages. The processes may not compute some messages because of message losses; the processes may compute some messages twice or more because of message duplicate; the processes may not compute messages according to their sending order because of message reordering. The above-mentioned problems make processes produce incorrect computation result, consequently, prevent processes from taking consistent global checkpoints. Our algorithm assigns each message a sequence number in order to resolve above-mentioned problems. During the establishing of the checkpoint, the consistency of checkpoint can be determined by the sequence number of sending and receiving messages. We can identify the lost messages, reordering messages and duplicate messages by checking the sequence number of sending and receiving messages. We resolve above-mentioned problems by resending the lost messages, buffering the reordering messages and dropping the duplicate messages. Our algorithm makes processes take consistent global checkpoints.

A Non-blocking Checkpointing Algorithm for Distributed Systems

The technology of checkpointing and rollback recovery as an effective method of fault tolerance, has been used widely on the parallel or distributed computer systems. We have presented a nonblocking coordinated checkpointing algorithm for distributed systems, which are differ from the conventional approach of taking first temporary checkpoints and then converting them to permanent ones by processes. The proposed checkpointing algorithm allows processes to take permanent checkpoints directly, without taking temporary checkpoints. The character of the algorithm contributes to its speed of execution. The orphan messages are eliminated by sender processes and the in-transit messages are eliminated by checkpointing interval and retransmission mechanism. While reducing the complexity of control message during gain checkpoints from O(n) to O(n), the algorithm’s controlling messages are reduced to n-1.

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.

Coordinated Checkpointing Algorithms for Mobile Agent Environments

Mobile agent execution environments have many features that are different from traditional distributed execution environments such as: mobility, autonomy and limited data size. If a failure occurs in an application where mobile agents cooperate and there is no appropriate method to protect it, more cost will be wasted for restarting the program. This investigation proposes checkpointing algorithms based on four mobile agent coordination models: direct coordination, blackboard-based coordination, meeting-oriented coordination and Linda-like coordination models. These algorithms consider the influence of spatial and temporal coupling on mobile agent coordination, and are easy to implement. Therefore, the checkpointing overhead can be reduced when mobile agents cooperate to complete a task in a multi-agent system. Finally, the experiments and our findings suggest the appropriate coordination algorithms for different applications.

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 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 LOW OVERHEAD MINIMUM PROCESS GLOBAL SNAPSHOT COLLECTION ALGORITHM FOR MOBILE DISTRIBUTED SYSTEM

Coordinated checkpointing is an effective fault tolerant technique in distributed system as it avoids the domino effect and require minimum storage requirement. Most of the earlier coordinated checkpoint algorithms block their computation during checkpointing and forces minimum-process or non-blocking but forces all nodes to takes checkpoint even though many of them may not be necessary or non-blocking minimum-process but takes useless checkpoints or reduced useless checkpoint but has higher synchronization message overhead or has high checkpoint request propagation time. Hence in mobile distributed systems there is a great need of minimizing the number of communication message and checkpointing overhead as it raise new issues such as mobility, low bandwidth of wireless channels, frequently disconnections, limited battery power and lack of reliable stable storage on mobile nodes. In this paper, we propose a minimum-process coordinated checkpointing algorithm for mobile distributed system where no useless checkpoints are taken, no blocking of processes takes place and enforces a minimum-number of processes to take checkpoints. Our algorithm imposes low memory and computation overheads on MH's and low communication overheads on wireless channels. It avoids awakening of an MH if it is not required to take its checkpoint and has reduced latency time as each process involved in a global checkpoint can forward its own decision directly to the checkpoint initiator.

A synchronous checkpointing protocol for mobile distributed systems: probabilistic approach

Coordinated checkpointing is a method that minimises number of processes to checkpoint for an initiation. It may require blocking of processes, extra synchronisation messages or useless checkpoints. We propose a minimum process coordinated checkpointing algorithm where the number of useless checkpoints and blocking are reduced using a probabilistic approach that computes an interacting set of processes on checkpoint initiation. A process checkpoints if the probability that it will get a checkpoint request in current initiation is high. A few processes may be blocked but they can continue their normal computation and may send messages. We also modified methodology to maintain exact dependencies.

A Hybrid Coordinated Checkpointing Protocol for Mobile Computing Systems

Minimum-process coordinated checkpointing is a suitable approach to introduce fault tolerance in mobile distributed systems transparently. The approach is domino-free, requires at most two checkpoints of each process and only minimum number of processes to checkpoint. At times, it requires piggybacking of some information with normal messages, blocking of the underlying computation or taking some checkpoints more than the minimum required. In minimum-process checkpointing, some processes, which are not part of minimum set, may not take checkpoints for several checkpoint initiations, and thus may starve to checkpoint. In case of recovery after a fault, this may lead to their rollback to far earlier checkpointed states and thus may cause greater loss of computation. In coordinated checkpointing, where all processes checkpoint, the recovery line is advanced for each process but the checkpointing overhead may be exceedingly high, especially in mobile environments; because, all mobile nodes need to checkpoint even if some may be disconnected or in doze mode operation. To balance the checkpointing overhead and the loss of computation on recovery, we propose a hybrid coordinated checkpointing algorithm, where an all-process coordinated checkpointing is forced after the execution of minimum-process coordinated checkpointing algorithm for a fixed number of times. Thus, the Mobile nodes with low activity or in doze mode operation may not be disturbed during minimum-process checkpointing and the recovery line is advanced for all processes after an all-process checkpoint. Additionally, we also optimize the piggybacked information, avoid blocking and minimize the number of useless checkpoints.

A novel min-process checkpointing scheme for mobile computing systems

In distributed computing systems, processes in different hosts take checkpoints to survive failures. For mobile computing systems, due to certain new characteristics such as mobility, low bandwidth, disconnection, low power consumption and limited memory, conventional distributed checkpointing schemes need to be reconsidered. In this paper, a novel min-process coordinated checkpointing algorithm that makes full use of the computation ability and power of mobile support stations is proposed. During normal computation message transmission, the checkpoint dependency information among mobile hosts is recorded in the corresponding mobile support stations. When a checkpointing procedure begins, the initiator concurrently informs relevant mobile hosts, which minimizes the identifying time. Moreover, compared with the existing coordinated checkpointing schemes, our algorithm blocks the minimum number of mobile support stations during the identifying procedure, which leads to the improvement of the system performance. In addition, the proposed algorithm is a min-process, domino-free checkpointing algorithm, which is especially desirable for mobile computing systems. Quantitative analysis and experimental simulation show that our algorithm outperforms other coordinated checkpointing schemes in terms of the identifying time and the number of blocked mobile support stations and then can provide a better system performance for mobile computing systems.

Checkpointing MPI applications on symmetric multi-processor machines using SMPCkpt

Researchers from many different areas have requirements for computational power to solve their specific problems. Symmetric multi-processor (SMP) machines are also widely available and their processing capacity is in demand particularly for applications in areas such as virtual reality and multimedia. Checkpointing provides the backbone for rollback recovery (fault-tolerance), playback debugging, process migration and job swapping. Numerous checkpointing tools have been designed and implemented but few are based on SMP machines for MPI applications. This work designs, develops, and implements SMPCkpt, a checkpointing system for symmetric multi-processor environments. SMPCkpt supports a range of facilities, including transparent checkpointing, fault detection, and rollback recovery. Two coordinated checkpointing algorithms, barrier and non-barrier, are developed and implemented in SMPCkpt that can be used to reduce the execution down time in the presence of failures.

A checkpoint-based high availability run-time system for Windows NT clusters

This paper presents a high availability run-time system----ChaRM-NT, a Checkpoint-based Rollback recovery system for parallel applications on a cluster of computers (COCs) based on Windows NT. ChaRM-NT implements an insert-mode, reduced coordinated checkpointing and rollback recovery (CRR) mechanism. Owing to the above techniques, ChaRM-NT can recover parallel applications from the checkpointing file upon system failures. In addition we have implemented a new coordinated checkpointing algorithm that only requires O(n) control messages where n is the number of participating processes. Independent on message passing environments (MPEs) ChaRM-NT implements a portable single process CRR library. Therefore it is very easy to adapt to different MPEs and it supports PVM and MPI for NT now.

On coordinated checkpointing in distributed systems

Coordinated checkpointing simplifies failure recovery and eliminates domino effects in case of failures by preserving a consistent global checkpoint on stable storage. However, the approach suffers from high overhead associated with the checkpointing process. Two approaches are used to reduce the overhead: first is to minimize the number of synchronization messages and the number of checkpoints, the other is to make the checkpointing process nonblocking. These two approaches were orthogonal in previous years until the Prakash-Singhal algorithm combined them. In other words, the Prakash-Singhal algorithm forces only a minimum number of processes to take checkpoints and it does not block the underlying computation. However, we found two problems in this algorithm. In this paper, we identify these problems and prove a more general result: there does not exist a nonblocking algorithm that forces only a minimum number of processes to take their checkpoints. Based on this general result, we propose an efficient algorithm that neither forces all processes to take checkpoints nor blocks the underlying computation during checkpointing. Also, we point out future research directions in designing coordinated checkpointing algorithms for distributed computing systems.

Adaptive checkpointing in message passing distributed systems

Determining consistent global checkpoints is common to many distributed problems such as fault-tolerance, distributed debugging, properties detection, etc. Uncoordinated and coordinated checkpointing algorithms have been traditionally used for such determinations. This paper addresses a third technique, namely adaptive checkpointing, that has recently emerged. This technique assumes processes take local checkpoints independently and requires them to take additional local checkpoints in order that all local checkpoints be members of some consistent global checkpoint. We first study the characteristics of such adaptive algorithms. Then, a general adaptive checkpointing algorithm is designed from a condition, first stated by Netzer and Xu, that answers the following question: ‘does a given local checkpoint belong to a consistent global checkpoint’' (such a local checkpoint is not useless). The resulting algorithm has the nice property to reduce the number of additional local checkpoints taken to ensure the property ‘no local checkpoint is useless’. Futhermore, it provides each local checkpoint with a consistent global checkpoint to which it belongs. Compared to uncoordinated and coordinated checkpointing algorithms, this algorithm combines the advantages of both without inheriting their drawbacks.