Monitoring network performance and detecting network faults using round trip transmission times

摘要

A method of processing communications includes: receiving transmission data over a selected time interval for each of a plurality of communication paths between a host processor and a control unit configured to control at least one I/O device; calculating an average round-trip transmission time for each of the communication paths over the time interval; comparing an average round-trip transmission time for a communication path having the highest average round-trip transmission time to a threshold value and to a multiple of an average round-trip transmission time for a communication path having the lowest average round-trip transmission time; and determining, based on comparing the highest round-trip transmission time to the threshold value and to a multiple of the lowest round-trip transmission time, whether the time period indicates a delay in communication between the I/O subsystem and the control unit requiring at least one of a monitoring action and a recovery action.