Dell POWEREDGE M1000E - Manual (Page 109)

Fabric OS Command Reference 81
53-1002746-01
bottleneckMon
2
Per-port overrides for alert parameters
Custom configuration for the above mentioned alert parameters. The
abbreviations "C" and "L" indicate "congestion" and "latency" alerts. "Y" means
alerts are enabled for both types, and "N" means alerts are disabled.
Excluded ports
List of ports excluded from bottleneck detection.
Credit recovery on backend ports
Use the --cfgcredittools commands to enable or disable credit recovery of backend ports and to display
the configuration. When this feature is enabled, credit is recovered on backend ports (ports connected to
the core blade or core blade backend ports) when credit loss has been detected on these ports. If
complete loss of credit on a Condor2 backend port causes frame timeouts, a link reset will be performed
on that port regardless of the configured setting, even if that setting is -recover off. When used with the
-recover onLrOnly option, the recovery mechanism takes the following escalating actions:
•
When it detects credit loss, it performs a link reset and logs a RASlog message (RAS Cx-1014).
•
If the link reset fails to recover the port, the port reinitializes. A RASlog message is generated (RAS
Cx-1015). Note that the port reinitialization does not fault the blade.
•
If the port fails to reinitialize, the port is faulted. A RASlog message (RAS Cx-1016) is generated.
•
If a port is faulted and there are no more online backend ports in the trunk, the core blade is faulted.
(Note that the port blade will always be faulted). A RASlog message is generated (RAS Cx-1017).
When used with the -recover onLrThresh option, recovery is attempted through repeated link resets
and a count of the link resets is kept. If the threshold of more than two link resets per hour is reached, the
blade is faulted (RAS Cx-1018). Note that regardless of whether the link reset occurs on the port blade or
on the core blade, the port blade is always faulted.
If you suspect complete credit loss on a particular virtual channel (VC) on a particular backend port, use
the -check option to examine that particular backend port and VC for credit loss. If the command detects
complete credit loss, it reports the information. If, in addition, you have enabled link resets on backend
ports, this command will perform a link reset on the link in an attempt to recover from the problem. You
must explicitly initiate this check and it is a one-time operation. In other words, this command does not
continuously monitor for credit loss in the background. Detection of credit loss takes 2-7 seconds, after
which the results of the operation are displayed. A Link Reset also generates a RASlog message.
For more information on the RASlog messages, refer to the Fabric OS Message Reference.
NOTES Command syntax predating Fabric OS v.6.4.0 is no longer supported as of Fabric OS v.7.0.0.
The execution of this command is subject to Virtual Fabric or Admin Domain restrictions that may be in
place. Refer to Chapter 1, "Using Fabric OS Commands" and Appendix A, "Command Availability" for
details.
The bottleneck detection commands are supported on F_Ports, FL_Ports, E_Ports, and EX_Ports.
The credit recovery commands are supported only on backend ports of Condor, Condor 2, and Condor
3-based blades in the Brocade DCX 8510-8 and DCX 8510-4 chassis.
The -check option is supported only on modular switches, and only on links between Condor 2 core
blades and Condor 2 port blades. AP blades are not supported.
OPERANDS Bottleneck detection commands
The following operands support bottleneck detection:
slot
On bladed systems only, specifies the slot number of the ports to be configured,
followed by a slash (/).