Architecture Support for Behavior-based Adaptive Checkpointing

2008

The utilization of new generation computing platforms like computational grids or desktop grids introduces new challenging problems. In particular, due to the huge number of the involved processors, security and fault-tolerance aspects are key issues that must be taken into account. Coordinated checkpointing is one of the most popular technique to deal with failures in such platforms. The approach of application-directed checkpointing in fault-tolerance puts an incredible strain on the storage system and the communications. This results in large overheads on the execution times of applications that severely impact the performance and the scalability. This work presents a new model of coordinated checkpoint/restart mechanism for several types of computing platforms. Its main feature is that it is independent from the failure law which makes it very flexible. We will show that such a model may be used to determine the optimal periodic checkpoint interval and to reduce the checkpoint overhead through mathematical analysis of reliability. Moreover, unlike most of the existing checkpointing models, the proposed model is able to take into account a variable checkpoint cost. Finally, we report some experiments based on simulations for random failure distributions corresponding to the two most popular laws, namely, the Poisson's process and Weibull's law.

International Journal of Cloud Applications and Computing, 2011

Cloud computing refers to both the applications delivered as services over the Internet and the hardware and systems software in the datacenters that provide those services. Failures of any type are common in current datacenters, partly due to the number of nodes. Fault tolerance has become a major task for computer engineers and software developers because the occurrence of faults increases the cost of using resources and to meet the user expectations, the most fundamental user expectation is, of course, that his or her application correctly finishes independent of faults in the node. This paper proposes a fault tolerant architecture to Cloud Computing that uses an adaptive Checkpoint mechanism to assure that a task running can correctly finish in spite of faults in the nodes in which it is running. The proposed fault tolerant architecture is simultaneously transparent and scalable.

The International Journal of High Performance Computing Applications, 2005

As high performance clusters continue to grow in size and popularity, issues of fault tolerance and reliability are becoming limiting factors on application scalability. To address these issues, we present the design and implementation of a system for providing coordinated checkpointing and rollback recovery for MPI-based parallel applications. Our approach integrates the Berkeley Lab BLCR kernel-level process checkpoint system with the LAM implementation of MPI through a defined checkpoint/restart interface. Checkpointing is transparent to the application, allowing the system to be used for cluster maintenance and scheduling reasons as well as for fault tolerance. Experimental results show negligible communication performance impact due to the incorporation of the checkpoint support capabilities into LAM/MPI.

Abstract—Middleware for parallel computing systems incorporate checkpointing to achieve fault tolerance. Most traditional checkpointing approaches tend to be less dynamic in large scale parallel computing environments. Hence, there arises a need for an adaptive and dynamic approach. The work reported in this paper, proposes a multi-agent based approach for fault tolerance.

2008

As the scale of high performance computing (HPC) continues to grow, application fault resilience becomes crucial. To address this problem, we are working on the design of an adaptive fault tolerance system for HPC applications.

1998

Checkpointing and rollback recovery is a very effective technique to tolerate transient faults and preventive shutdowns. In the past, most of the checkpointing schemes published in the literature were supposed to be transparent to the application programmer and implemented at the operating-system level. In the recent years, there has been some work on higher-level forms of checkpointing. In this second approach, the user is responsible for the checkpoint placement and is required to specify the checkpoint contents.

15th International Conference on Advanced Computing and Communications (ADCOM 2007), 2007

This paper presents an autonomic Web Service Resource Framework (WSRF) container that enables selfconfiguration using IBM's autonomic computing (AC) architecture and resolves Quality of Service (QoS) problems through service migration. The migration manager bases its decisions on an overall health status metric (H-metric). The H-metric characterises the health of a service container. A unified AC sensor/effector interface, protocol, and metric summarization allows us to build up a hierarchical WSRF container structure to create a virtualized WSRF container.

Computer, 2000

distributed system consists of autonomous computing modules that interact with each other using messages. Designing distributed systems is more difficult than designing centralized systems for several reasons. Physical separation and the use of heterogeneous computers complicate interprocessor communication, management of resources, synchronization of cooperating activities, and maintenance of consistency among multiple copies of information. The main advantages of distributed systems include increased fault-tolerance capabilities through the inherent redundancy of resources, improved performance by concurrently executing a single task on several computing modules, resource sharing, and the ability to adapt to a changing environment (extensibility).'

Future Generation Computer Systems, 2010

In recent years there has been a significant effort to develop middleware that facilitates the execution of applications on Grid infrastructures. However, support for fault-tolerant execution continues to be scarce. The CPPC-G framework is a service-based architecture designed to provide efficient faulttolerant mechanisms for the execution of sequential and parallel applications on grids. Applications to be managed by CPPC-G are expected to be preprocessed with CPPC (ComPiler for Portable Checkpointing), a tool for automatically inserting portable checkpoint instrumentation into the code of parallel applications. Built on top of existing Globus services, CPPC-G services are in charge of submitting and monitoring CPPC applications, managing generated checkpoint files, detecting failures and automatically restarting failed executions. In this paper the feasibility of this approach is assessed by measuring the performance of CPPC-G, quantitatively addressing its impact on application performance. Results show that the increase in overall throughput and availability comes with minor performance degradation. (G. Rodríguez), pardo@udc.es (X.C. Pardo), mariam@udc.es (M.J. Martín), pglez@udc.es (P. González). range of different machines. Portability in this context means to provide the following fundamental features:

The Journal of Supercomputing

Due to the increase and complexity of computer systems, reducing the overhead of fault tolerance techniques has become important in recent years. One technique in fault tolerance is checkpointing, which saves a snapshot with the information that has been computed up to a specific moment, suspending the execution of the application, consuming I/O resources and network bandwidth. Characterizing the files that are generated when performing the checkpoint of a parallel application is useful to determine the resources consumed and their impact on the I/O system. It is also important to characterize the application that performs checkpoints, and one of these characteristics is whether the application does I/O. In this paper, we present a model of checkpoint behavior for parallel applications that performs I/O; this depends on the application and on other factors such as the number of processes, the mapping of processes and the type of I/O used. These characteristics will also influence sc...