QsNetII Interconnect

Cannot Use telnet With Quadrics Switch Controller Firmware Version 44-5032399

Due to a known firmware bug, you cannot use the telnet command to access the Quadrics switch controller if the switch controller is running firmware version 44-5032399.

However, you can log in to the switch controller using ssh if you enable ssh access and disable telnet access on the switch controller.

Refer to Appendix D in the HP XC System Software Installation Guide for instructions on how to configure the telnet and ssh access settings.

ELAN4 Diagnostic Tools Fail on Systems With ELAN3 Interconnect

This release note applies only to systems with an ELAN3 interconnect.

The /opt/hptc/etc/gconfig.d/C30swmlogger gconfigure script, which is run by the cluster_config utility, fails on an ELAN3 system because the swmlogger service and the qsnet diagnostic database are supported only on ELAN4 systems.

On ELAN3 systems, enter the following commands on the head node to stop the swmlogger service from running and to disable the swmlogger service from starting at boot time. You must run these two commands any time you rerun the cluster_config utility:

# service swm stop
# chkconfig --del swm

Possible Conflict with Use of SIGUSR2

The Quadrics QsNet^II software internally uses SIGUSR2 to manage the interconnect. This can conflict with any user applications that use SIGUSR2, including for debugger use.

To work around this conflict, set the environment variable LIBELAN4_TRAPSIG for the application to a different signal number other than the default value 12 that corresponds to SIGUSR2. Doing this instructs the Quadrics software to use the new signal number, and SIGUSR2 can be once again used by the application. Signal numbers are define in the /usr/include/asm/signal.h file.

The qsnet Database May Contain Entries to Nonexistent Switch Modules

Depending on your system topology, the qsnet diagnostics database may contain entries to nonexistent switches.

This issue is manifested as errors reported by the /usr/bin/qsctrl utility similar to the following:

# qsctrl
qsctrl: failed to initialise module QR0N03: no such module (-7)
...

In the previous example, the switch_modules table in the qsnet database is populated with QR0N03 even though the QR0N03 module is not physically present. This problem has been reported to Quadrics, Ltd.

To work around this problem, delete the QR0N03 entry (and any other nonexistent switch entries) from the switch_modules table, and restart the swmlogger service:

# mysql -u root -p qsnet
mysql> delete from switch_modules where name="QR0N03";
mysql>quit# service swm restart

In addition to the previous problem, the IP address of a switch module may be incorrectly populated in the switch_modules table, and you might see the following message:

# qsctrl
qsctrl: failed to parse module name 172.20.66.2
...

Resolve this issue by deleting the IP address from the switch_modules table and restarting the swmlogger service:

# mysql -u root -p qsnet
mysql> delete from switch_modules where name="172.20.66.2";
mysql>quit
# service swm restart

	Note: You must repeat the previous procedure if you rerun the cluster_config utility and you choose to recreate the qsnet database during the cluster_config operation.