OPERATIONAL DEFECT DATABASE
...
...
Document Version Release Date Details 2 03/19/2018 Updated Resolution with permanent fix, Superdome Flex firmware version 2.4.98. 1 12/19/2017 Original Document Release When the Board Management Controller (BMC) is under stress, power on of the partition may result in one or more chassis to miss NL (NUMA Link) rendezvous. The cause of stress is believed to orphan processes left behind by root shell access to the embedded Rack Management Controller (eRMC) or Board Management Controller (BMC). This issue is rare, because firmware blocks root access from external interfaces. Use the integrated event log (SHOW LOGS IEL) to look for NUMA link (NL) port link failure: NL_PORT_LINK_FAIL. This is a level 3 alert and all 4 quads of the HARP will show failure for both the monarch chassis and the expansion chassis. For example: 19342 2017-12-08 22:13:23Z MFW r001i06b 0 *WARN (3) FFFF100106FF0054 NL_PORT_LINK_FAIL [rack1/chassis_u6/harp0/quad0/port1(G0)] 19343 2017-12-08 22:13:23Z MFW r001i06b 0 *WARN (3) FFFF200106FF0054 NL_PORT_LINK_FAIL [rack1/chassis_u6/harp0/quad0/port2(P0)] 19344 2017-12-08 22:13:23Z MFW r001i06b 0 *WARN (3) FFFF300106FF0054 NL_PORT_LINK_FAIL [rack1/chassis_u6/harp0/quad0/port3(F0)] 19345 2017-12-08 22:13:23Z MFW r001i06b 0 *WARN (3) FFFF010106FF0054 NL_PORT_LINK_FAIL [rack1/chassis_u6/harp0/quad1/port0(N0)] 19346 2017-12-08 22:13:23Z MFW r001i06b 0 *WARN (3) FFFF120106FF0054 NL_PORT_LINK_FAIL [rack1/chassis_u6/harp0/quad2/port1(H0)] 19347 2017-12-08 22:13:23Z MFW r001i06b 0 *WARN (3) FFFF220106FF0054 NL_PORT_LINK_FAIL [rack1/chassis_u6/harp0/quad2/port2(B0)] 19357 2017-12-08 22:13:23Z MFW r001i06b 0 *WARN (3) FFFF030106FF0154 NL_PORT_LINK_FAIL [rack1/chassis_u6/harp1/quad3/port0(C1)] 19602 2017-12-08 22:13:39Z MFW r001i01b 0 *WARN (3) FFFF300101FF0054 NL_PORT_LINK_FAIL [rack1/chassis_u1/harp0/quad0/port3(F0)] 19603 2017-12-08 22:13:39Z MFW r001i01b 0 *WARN (3) FFFF010101FF0054 NL_PORT_LINK_FAIL [rack1/chassis_u1/harp0/quad1/port0(N0)] 19604 2017-12-08 22:13:39Z MFW r001i01b 0 *WARN (3) FFFF120101FF0054 NL_PORT_LINK_FAIL [rack1/chassis_u1/harp0/quad2/port1(H0)] 19607 2017-12-08 22:13:39Z MFW r001i01b 0 *WARN (3) FFFF030101FF0054 NL_PORT_LINK_FAIL [rack1/chassis_u1/harp0/quad3/port0(C0)]
Any HPE Superdome Flex server.
This issue is corrected in Superdome Flex firmware version 2.4.98, available here: Superdome Flex firmware version 2.4.98. As a workaround, if the error described above is seen, perform the following to recover from the error: 1. If the OS is booted, login to the OS as root and shut down the operating system: # shutdown -h 2. Log into the RMC/eRMC and power off the system by running: RMC CLI> POWER OFF NPAR pnum=0 3. Then, power on the system again: RMC CLI> POWER ON If the problem persists, power-cycle the chassis that missed NL rendezvous via the CLI command, POWER CYCLE BMC <GEOID>, and repeat the power-on. This advisory will be updated when additional solutions become available. RECEIVE PROACTIVE UPDATES : Receive support alerts (such as Customer Advisories), as well as updates on drivers, software, firmware, and customer replaceable components, proactively via e-mail through HPE Subscriber's Choice. Sign up for Subscriber's Choice at the following URL: Proactive Updates Subscription Form. NAVIGATION TIP : For hints on navigating HPE.com to locate the latest drivers, patches, and other support software downloads for ProLiant servers and Options, refer to the Navigation Tips document . SEARCH TIP : For hints on locating similar documents on HPE.com, refer to the Search Tips Document .
Click on a version to see all relevant bugs
Hewlett Packard Enterprise Integration
Learn more about where this data comes from
Bug Scrub Advisor
Streamline upgrades with automated vendor bug scrubs
BugZero Enterprise
Wish you caught this bug sooner? Get proactive today.
