A Resilient Framework for Fault Handling in Web Service Oriented Systems
11
Citation
21
Reference
10
Related Paper
Citation Trend
Abstract:
Resilience is an important factor in designing web service oriented systems due to frequent failures arising in runtime. These failures derive from the stochastic and uncertainty nature of a composite web service. Service providers need to rapidly address issue when a fault occurs in system running. But it is not easy to locate and fix the faults only using the log generated by the system. In this paper, we propose a resilient framework to automatically generate a fault handling strategy for each failed service to improve the efficiency of fault handling. In the framework, we design and implement three components including exception analyzer, decision maker, and strategy selector. First, The exception analyzer builds a record, derived from the system log generated by an application, for each failed service. Next, the decision maker adopts a k-means clustering approach to construct a decision including the fault handling to each failed service in a scope. Then, the strategy selector uses an integer program solver to generate the solution to strategy selection problem that is boiled down to the optimization problem. The experiment shows that the framework can improve resilience of Web service-oriented systems under acceptable overheads, and meanwhile the accuracy of fault handling strategy is over 95%.Keywords:
Resilience
Scope (computer science)
Solver
Roughing has been simulated with the Finite element software Abaqus TM to replicate an industrial-scale process. The model has been made to be as close as possible to its real counterpart. For this purpose, an automated controlling logic has been created to simulate the multiple passes as well as inter-pass times for roughing. Simulating multiple passes with FEM is computationally very demanding, so new methods to reduce computing times are worth considering. During a roll pass an explicit solver is necessary due to high deformation amounts and rates. An explicit solver is tied to a very small time increment, so it takes a long time. On the other hand, inter-pass periods do not include any deformation or roller contact, so an implicit solver is quite capable of computing this portion of the simulation. An implicit solver can speed up the time increment considerably when compared to the explicit solver, so using it potentially saves a significant amount of computing time. Unfortunately, Abaqus does not include any methods to change the solver during a single simulation. Instead it is possible to communicate between the two solver types by manually importing data from a completed simulation to a new simulation model. A new method to change solvers automatically using a self-made Python code is proposed in this paper.
Solver
Python
Problem solver
Cite
Citations (2)
The Border Profile LU (BPLU) linear equation solver is the default solver for newer versions of RELAP5-3D. It can significantly reduce execution time compared to the previous default solver, MA18. Particularly for 3D cases, it can reduce run time by one to two orders of magnitude over MA18. However, because of some user reported failures, the MA18 solver currently must be used for coupled analyses. Over one dozen User Problems (UP) have been reported between 1999 and 2011 that involve the BPLU solver in RELAP5-3D. These issues can be combined into two categories of problems with the solver: (1) It fails when running multidimensional components with the nearly-implicit hydrodynamics advancement scheme. (2) It fails with some input models where the MA18 sparse solver does not fail. The sources of these UP have been found and corrected. The modified coding has been thoroughly tested with over 3000 test cases and on two different compute platforms. The updates are incorporated in RELAP5-3D, version 3.0.2.
Solver
Cite
Citations (0)
Solver
Cite
Citations (131)
Solver
Problem solver
Scope (computer science)
Microsoft excel
Cite
Citations (0)
The Border Profile LU (BPLU) linear equation solver is the default solver for newer versions of RELAP5-3D. It can significantly reduce execution time compared to the previous default solver, MA18. Particularly for 3D cases, it can reduce run time by one to two orders of magnitude over MA18. However, because of some user reported failures, the MA18 solver currently must be used for coupled analyses. Over one dozen User Problems (UP) have been reported between 1999 and 2011 that involve the BPLU solver in RELAP5-3D. These issues can be combined into two categories of problems with the solver: • It fails when running multidimensional components with the nearly-implicit hydrodynamics advancement scheme. • It fails with some input models where the MA18 sparse solver does not fail. The sources of these UP have been found and corrected. The modified coding has been thoroughly tested with over 3000 test cases and on two different compute platforms. The updates are incorporated in RELAP5-3D, version 3.0.2.
Solver
Cite
Citations (0)
In this paper, we present a resilience analysis of the impact of soft errors on CLAMR, a hydrodynamics miniapp for high performance computing (HPC). Leveraging the conservation of mass law, we design a fault detection mechanism and checkpoint/restart fault tolerance approach to enhance the resilience of CLAMR. Overall, our approach can detect up to 88.3% of faults that propagate into SDC or crashes with minimal (less than 1%) overhead for the optimal configuration. We show that CLAMR's fault-tolerance depends on when a fault is injected into the simulation and we also evaluate the frequency of detection and checkpointing on performance.
Resilience
Soft error
Fault injection
Transient (computer programming)
Software fault tolerance
Cite
Citations (12)
Solver
Cite
Citations (27)
A procedure for the experimental convergence evaluation of a hydraulic-network solver is proposed, based on using genetic algorithms to search for network parameter values that maximize the number of iterations of the hydraulic-network solver under test. The efficiency of the method is demonstrated by the example of convergence evaluation for the EPANET hydraulic simulator. Examples of a pipe network and of combinations of parameter values for which the static solver of the simulator fails to converge in a reasonable number of iterations are given. The features of the EPANET 2.00.12 solver responsible for loss of convergence are discussed. New criteria for the automatic start of solution damping aimed at improving the convergence of the solver are proposed. The better convergence of the EPANET solver modified in accordance with these criteria is confirmed by the random and the proposed search-based testing method.
Solver
Cite
Citations (3)
Abstract In this paper the accuracy, efficiency and stability of two hybrid solvers are compared to FDTD in several complex scattering cases. The explicit hybrid solver, FD‐FV, combines an unstructured FVTD solver with FDTD, and the explicit–implicit solver, FD‐FE, combines an unstructured FETD solver with FDTD. The results show that the two hybrid solvers are much more efficient than FDTD for complex objects where a Cartesian grid is not able to capture the geometry properly. Furthermore, they show that the FD‐FE solver is a better choice than the FD‐FV solver. Mainly because it is stable as long as the time step satisfies the CFL condition in the FDTD region, while the FD‐FV solver may suffer from late time instabilities. But the FD‐FE solver is also more efficient since the iterative method used to solve the matrix–vector system arising in FETD converges fast and the FVTD solver is heavily penalized by having to take shorter time steps to satisfy its CFL condition. Copyright © 2002 John Wiley & Sons, Ltd.
Solver
Cite
Citations (31)