Abstract: Embodiments of a system that adjusts a checkpointing frequency in a distributed computing system that executes multiple jobs are described. During operation, the system receives signals associated with the operation of the computing nodes. Then, the system determines risk metrics for the computing nodes using a pattern-recognition technique to identify anomalous signals in the received signals. Next, the system adjusts a checkpointing frequency of a given checkpoint for a given computing node based on a comparison of a risk metric associated with the given computing node and a threshold, thereby implementing holistic fault tolerance, in which prediction and prevention of potential faults occurs across the distributed computing system.

Abstract: Embodiments of a system that adjusts a checkpointing frequency in a distributed computing system that executes multiple jobs are described. During operation, the system receives signals associated with the operation of the computing nodes. Then, the system determines risk metrics for the computing nodes using a pattern-recognition technique to identify anomalous signals in the received signals. Next, the system adjusts a checkpointing frequency of a given checkpoint for a given computing node based on a comparison of a risk metric associated with the given computing node and a threshold, thereby implementing holistic fault tolerance, in which prediction and prevention of potential faults occurs across the distributed computing system.

Abstract: A method for use in a computer system provides a dynamic, “self tuning” soft-error-rate-discrimination (SERD) method and apparatus. Specially designed SRAMs or other circuits are “tuned” in a manner that gives them extreme susceptibility to cosmic neutron events (soft errors), higher than that of the “regular” SRAM components, memory modules or other components in the computer system. One such specially designed SRAM is deployed per server. An interface algorithm continuously sends read/write traffic to the special SRAM to infer the soft error rate (SER), which is directly proportional to cosmic neutron flux. The inferred cosmic neutron flux rate is employed in a Poisson SPRT algorithmic approach that dynamically compensates the soft error discrimination sensitivity in accordance with the instantaneous neutron flux for all of the regular SRAM components in the server.

Abstract: A method for checkpointing a system that includes receiving a stop command by an executing thread from a master, wherein the executing thread executes an operating system, continuing execution of the executing thread until a checkpoint is reached after receiving the stop command, halting execution of the executing thread at the checkpoint, and checkpointing the system by storing a state and a snapshot of memory.

Abstract: A method for safepointing a system that includes receiving a stop command by an executing thread from a master, wherein the executing thread executes an operating system, continuing execution of the executing thread until a safepoint is reached after receiving the stop command, halting execution of the executing thread at the safepoint; and evaluating a response from the executing thread to diagnosis the system.

Abstract: One embodiment of the present invention provides a system that facilitates aligning a first signal with a second signal in a manner that optimizes a correlation between the first signal and the second signal. The system starts by receiving a set of signals, including the first signal and the second signal. The system then determines a correlation between the first signal and the second signal. Next, the system adjusts an alignment between the first signal and again determines a correlation between the first signal and the second signal. If the correlation is greater with the alignment adjustment, the system adjusts the alignment between the first signal and the second signal. This process of adjusting the alignment is repeated for different alignments to find an optimal alignment. Hence, the present invention operates effectively for signal sources which may be independently speeding up and slowing down with respect to each other while under surveillance.

Abstract: Methods, systems, and articles of manufacture consistent with the present invention train a real-time health-monitor for a computer-based system while simultaneously monitoring the health of the system. A plurality of signals that each describe an operating condition of a subject data processing system are monitored in real-time. It is determined whether there is a problem with the subject data processing system by comparing at least one of the monitored signals to a corresponding at least one signal in a known signal dataset. The known signal dataset includes a signal value for at least one signal that describes an operating condition of one of a plurality of subject data processing systems. A new signal dataset having an entry for each monitored signal and a corresponding signal value is prepared simultaneously with monitoring the plurality of signals and determining whether there is a problem.

Abstract: One embodiment of the present invention provides a system that detects a failure sequence that leads to undesirable computer system behavior and that subsequently takes a corresponding remedial action. During operation, the system receives instrumentation signals from the computer system while the computer system is operating. The system then uses these instrumentation signals to determine if the computer system is in a failure sequence that is likely to lead to undesirable system behavior, such as a system crash, wherein the determination involves considering predetermined multivariate correlations between multiple instrumentation signals and a failure sequence that is likely to lead to undesirable system behavior. Next, if the computer system is in a failure sequence that is likely to lead to undesirable system behavior, the system takes a remedial action.

Abstract: One embodiment of the present invention provides a system that facilitates determining the effects of a temperature variation in a computer system. The system operates by systematically varying the flow of a coolant through the computer system to produce a temperature variation in the computer system while the computer system is operating. While this temperature variation is taking place, the system monitors the computer system to determine effects of the temperature variation on the computer system.