| 摘要 |
In a distributed computer system having components which may fail intermittently, a fault monitor, coupled to one component, detects whether that component is working. Whenever the fault monitor detects that the component has failed, i.e., changed from working to broken status, the status filter transmits without delay a "broken" signal. Whenever the fault monitor detects that the component has changed from broken to working status, however, the status filter transmits a "working" signal only after a recovery time interval corresponding to a computed skepticism level, and only if the component does not fail during that recovery time interval. The status filter increases the computed skepticism level, and redetermines the recovery time interval in accordance therewith, each time that the component fails after the status filter has transmitted a "working" signal. The status filter decreases the computed skepticism level, and redetermines the recovery time interval in accordance therewith, when, after the status filter has transmitted a "working" signal, the component does not fail for at least a defined interval of time. |
