Self-refined Fault Tolerance in HPC Using Dynamic Dependent Process Groups

SummaryCheckpoint‐based fault‐tolerant (FT) methods have been widely used to enhance the reliability of stream processing systems, but a checkpointing process usually introduces considerable overhead. It is a critical issue to choose the optimal checkpoint interval (OCI) that maximizes the processing efficiency. Traditional OCI models consider the recovery time equals to the execution time from the last checkpoint to the failure moment. However, for stream processing jobs, the recovery time is related to reprocessing workloads, depending on the real‐time input data before a failure. A new model is needed to choose the OCI for stream processing applications. Moreover, the input data rate of a stream processing job fluctuates over time. To solve these problems, we present a novel DSPS OCI (DOCI) model in this paper. We prove that it maximizes the processing efficiency for a given time. We propose an approach to dynamically adjust the OCI for an application to accommodate the workload fluctuations. We conduct simulation experiments to verify the effectiveness of our DOCI model and the efficiency of the online OCI adjustment algorithm. Experimental results with a real‐world dataset show that DOCI achieves an improvement on system efficiency by up to 32%, compared with existing FT approaches.

Optimal checkpointing interval of a communication system with rollback recovery

As computer communication technology has developed, system control mechanisms have been realized by a number of processors, and, hence, it has become necessary to carry out processing distributively and rapidly. Also, as the system mechanisms have become increasingly complicated, the problems of improving reliability and increasing capabilities have become important. In this paper, we consider a control system which is roughly divided into one mark processor and a group of other processors, and formulate a stochastic model by taking notice of only communications between two processors. We perform scheduled checkpointing and execute rollback recovery to restore the consistency of a whole system when two faults of processor failures and communication errors have occurred. The expected cost is obtained and an optimal checkpoint interval which minimizes it is discussed. © 2001 Scripta Technica, Electron Comm Jpn Pt 3, 84(9): 49–55, 2001

Efficient modeling and optimizing of checkpointing in concurrent component-based software systems

Processor Allocation and Checkpoint Interval Selection in Cluster Computing Systems

In this paper, we study how to provide dependable network processing through multi-core based network processors (NPs). We present the performance analysis results of an NP based network system and motivate our research. We propose to use the redundant cores available in an NP to handle faults. We outline a fault-tolerant (FT) task model specifically for NP based applications and describe our implementation taking advantage of hardware features of an Intel IXP2xxx NP. A set of experiments are conducted to evaluate the performance and effectiveness of a FT-enabled NP system. The experiment results show that our fault- tolerant design can effectively improve the schedulability of the system.

The engagement of life history and the life review among the aged: A research case study

In quiescent Swiss 3T3 cells, metabolic flux through phosphoribosyl pyrophosphate into nucleotides increased within 1 h when various growth factors were added (S. Ishijima, K. Kita, N. Kinoshita, T. Ishizuka, N. Suzuki, and M. Tatibana. J. Biochem. 104: 570-575, 1988). The divalent cation ionophore A23187 mimicked the stimulatory effect of epidermal growth factor plus insulin, thereby suggesting involvement of divalent cation mobilization in signaling the stimulation by the growth factors. The stimulation induced by the growth factors was nil in medium devoid of added Mg2+ but was not affected by the omission of Ca2+. The dependency on external Mg2+ was also observed with the stimulations by bombesin plus insulin, fibroblast growth factor, and A23187. In contrast, the mitogenic stimulation of glycolysis was observed irrespective of the presence or absence of Mg2+, indicating that initial events in the signaling process, including mitogen binding to receptors, took place in the absence of exogenous Mg2+. These results suggest that a Mg2(+)-dependent process, subsequent to growth factor binding to receptors, plays an essential role in signaling the early mitogenic stimulation of nucleotide synthesis.

The article analyses the methods of enhancing the combat capability of small police tactical groups, in particular, with regard to their participation in hostilities during martial law in Ukraine. The main attention is paid to the importance of the optimal location of the commander in a small tactical group, which ensures the efficiency of performance of service and combat tasks, prompt decision-making, mobility and security of the group. The paper uses a scientific approach to improving the combat capability and tactics of small tactical groups. The following methods are used in the article: analysis, analysis of primary sources, comparative analysis, statistical and mathematical analysis, survey, expert survey, optimisation and approximation, graphical method of formations and method of optimisation of the commander’s location in a small tactical group, and method of experimental research. Different types of combat formations are studied, in particular, such as line, column, wedge, rhombus, star, snake and others, which are basic tactical elements. For each type of formation, experiments were conducted to determine the optimal location of the commander. In particular, the speed of command transmission and the risks of information loss depending on the commander’s position and the distance between the soldiers were analysed. It is established that the most optimal location of the commander is in the centre of the formation, as this ensures fast communication and minimises the risk of losses during an attack. The criterion-based approach is proposed, which includes quantitative, spatial and tactical criteria for choosing the commander’s location. The main criteria include the commander’s personal safety, efficiency of command transfer, reduction of command transformations, and minimisation of movements during re-arrangements. The empirical results confirm the importance of a comprehensive consideration of these factors to increase the combat capability of a small tactical group. The practical significance of the study lies in its possible use in the training system of the National Police of Ukraine, which will help to ensure the smooth performance of service and combat tasks and reduce personnel losses. Based on the results obtained, recommendations aimed at optimising the location of the commander in different types of combat formations have been developed.

Modeling hydrolysis processes considering intracellular storage

Reliability consideration of a mobile communication system with network congestion

Ensuring fault tolerance of robotic systems is a challenge for factory automation. This paper focuses on multi-robot manipulation and maintenance for fault-tolerant systems. For this purpose, a manipulation strategy of multiple mobile robots, that enables a system to continue operating even if a working robot undergoes preventive maintenance or fails and undergoes corrective maintenance, is implemented. In addition, a robot failure and a maintenance policy for preventive and corrective maintenance activities are mathematically modeled on the basis of reliability engineering. Thus, working robots are allowed to undergo preventive maintenance at an optimal interval and corrective maintenance each time they fail. Finally, through simulation experiments, the effectiveness of an integrated multi-robot manipulation and maintenance in industrial applications is shown.

Titanium matrix composite (TMC) is a candidate material for application in gas turbines. For this reason it is necessary to know which parameters influence its high temperature strength. In the present investigation modelling of the high temperature strength (from room temperature up to 1000°C) of SCS-6-fibre reinforced IMI834 is performed and compared with experimental results. Modelling is done in two steps. Firstly, three dimensional finite element (FE) calculations are performed to determine the stress distribution around a broken fibre. TMC is a composite with a low fibre/matrix bond strength, so that stress transfer at the fibre/matrix interface mainly takes place as a result of frictional shear stresses. For this reason in the FE calculation two non-linear effects reducing the stress concentration in fibres neighbouring a broken fibre are considered: interfacial sliding and matrix ductility. The stress distribution determined this way is used in a Monte Carlo simulation of the global composite behaviour based on a Weibull strength distribution determined on single fibres. In this simulation influence functions are incorporated to describe the interfering stress fields of fibre breaks. The main reason for a reduction of the tensile strength at increasing test temperature is found to be the strength loss of the matrix. A smaller contribution to the strength reduction results from the reduced stress transfer (leading to a larger ineffective fibre length) at increased test temperature.

Joint optimization of maintenance and spares inventory policy for a series-parallel system considering dependent failure processes

Modeling dynamic environment effects on dependent failure processes with varying failure thresholds