Dell Brocade 6520 Administrator's Guide Supporting Fabric OS 7.1.0 - Page 388

13 Advanced bottleneck detection settings Switch-wide alerting parameters: Alerts - Yes Latency threshold for alert - 0.200 Congestion threshold for alert - 0.700 Averaging time for alert - 200 seconds Quiet time for alert - 150 seconds Adjusting the frequency of bottleneck alerts Depending on the circumstances, a problematic switch or port might be triggering alerts more frequently than desired. The -qtime parameter can be used to throttle alerts by specifying the minimum number of seconds between consecutive alerts. Thresholds are configured separately for each type of bottleneck and statistical data are collected independently for each condition. This parameter applies individually to each type of bottleneck detection; so there can be one latency alert and one congestion alert in one quiet time. Example of setting quiet time This example sets a latency threshold of 0.8 for a time window of 30 seconds, and specifies that an alert should be sent when 80% (0.8) of the one-second samples over any period of 30 seconds were affected by latency bottleneck conditions; the system then waits 60 seconds before issuing the next alert (assuming that there is one). switch:admin> bottleneckmon --enable -lthresh 0.8 -time 30 -qtime 60 -alert=latency switch:admin> Notes • Alert-related parameters can only be specified with --config when -alert is specified. This is because -noalert is assumed if -alert is not specified, and -noalert cancels all alert-related parameters. As long as you want alerts, you must include the exact form of alert (-alert, -alert=congestion, or -alert=latency) in every --config operation, even if alerts are already enabled. • The retention of settings applies only to the --config command, not to --enable. An --enable operation behaves as if there is no preexisting user configuration, so if the --enable command does not include -alert, but does specify alert-related parameters, that command will fail. Advanced bottleneck detection settings Bottleneck detection uses the concept of an affected second when determining whether a bottleneck exists on a port. Each second is marked as being affected or unaffected by a latency or congestion bottleneck, based on certain criteria. You can use the sub-second latency criterion parameters to refine the criterion for determining whether a second is marked as affected by latency bottlenecks. For example, you might want to use the sub-second latency criterion parameters in the following cases: • You notice an under-performing application, but do not see any latency bottlenecks detected. You can temporarily increase the sub-second sensitivity of latency bottleneck detection on the specific F_Ports for this application. 388 Fabric OS Administrator's Guide 53-1002745-02