HP Fabric OS 7.1.0, Administrator'S Manual

Page: 389 / 666

Fabric OS Administrator’s Guide 389
53-1002745-02
Excluding a port from bottleneck detection
13
•
You want greater-than-default (sub-second) latency sensitivity on your fabric, so you set
sub-second latency criterion parameters at the time you enable bottleneck detection.
•
You want to reduce the number of alerts you are receiving about known latency bottlenecks in
the fabric, so you temporarily decrease the sub-second latency sensitivity on these ports.
•
You have a latency bottleneck on an ISL that is not at the edge of the fabric.
The sub-second latency criterion parameters are always applicable. These parameters affect alerts
and, even if alerting is not enabled, they affect the history of bottleneck statistics.
The sub-second latency criterion parameters are the following, with default values in parentheses:
•
-lsubsectimethresh (0.8) is similar to the -lthresh alerting parameter, except on a sub-second
level. The default value of 0.8 means that at least 80% of a second must be affected by latency
for the second to be marked as affected.
•
-lsubsecsevthresh (50) specifies the factor by which throughput must drop in a second for that
second to be considered affected by latency. The default value of 50 means that the observed
throughput in a second must be no more than 1/50th the capacity of the port for that second
to be counted as an affected second. 1/50th of capacity means 2% of capacity, which means
98% loss of throughput.
Sub-second latency criterion parameters apply only to latency bottlenecks and not congestion
bottlenecks.
When you enable bottleneck detection, you can specify switch-wide sub-second latency criterion
parameters. After you enable bottleneck detection, you can change the sub-second latency
criterion parameters only on a per-port basis. You cannot change them on the entire switch, as you
can with alerting parameters, unless you disable and then re-enable bottleneck detection.
Changing the sub-second latency criterion parameters on specific ports causes an interruption in
the detection of bottlenecks on those ports, which means the history of bottlenecks is lost on these
ports. Also note the following behaviors if you change the sub-second latency criterion parameters:
•
Traffic through these ports is not affected.
•
History of latency bottlenecks and congestion bottlenecks is lost on these ports. Other ports
are not affected, however.
•
The interruption occurs whether you set or clear per-port overrides on the sub-second latency
criterion parameters.
•
Because of the interruption, you can never have an alert for a port such that the alert spans
periods of time with different sub-second latency criteria on that port.
Excluding a port from bottleneck detection
When you exclude a port from bottleneck detection, no data is collected from the port and no alerts
are generated for the port. All statistics history for the port is discarded.
Alerting parameters for the port are preserved, so if you later include the port for bottleneck
detection, the alerting parameters are restored.
Per-port exclusions might be needed if, for example, a long-distance port is known to be a
bottleneck because of credit insufficiency. In general, however, per-port exclusions are not
recommended.