Validate the Health of the HSS

About xtcheckhss and its series of HSS tests.

The xtcheckhss command initiates a series of tests that validate the health of the HSS by gathering and displaying information supplied by scripts located on blade controllers (BCs) and cabinet controllers (CCs). xtcheckhss includes the following tests:
  • Version Checker: Reads the current version running on the L0C, QLOC, L0Ds, BC micro, CC micro, CC FPGA, CHIA FPGAs, Tolapai BIOSes, and Node BIOS. The version that is read from each device is compared to the currently installed versions on the SMW.
  • Sensor Checker: Reads environment sensors including temperatures, voltages, currents, and other data.
  • SEEP Checker: Reads serial electrically erasable PROMs (SEEPs) in the system. This test can report any un-initialized, zeroed, or unreadable SEEPs.
  • AOC Checker: Reads all active optical cable (AOC) data. This test displays any outliers relative to the average data calculated by previous runs.
  • ITP Checker: Validates the embedded ITP path
  • NTP Checker: Reads system time on all controllers and compares them with the SMW time; displays any mismatches.
  • Control Checker: Examines and modifies system controls.
  • Configuration Information Checker: Reads the system hardware configuration and reports the system setup, including the blade type, daughter card type, CPU type and count, and the CPU and PDC mask.
  • PCI checker: Checks for missing or degraded PCIe connectivity on add-in cards on an IBB. This test requires that the nodes be powered up and bounced. Any cards that do not train to the PCIe Gen or Width specified in the Link Capability register are flagged. Any cards that are reported as physically present but not seen by the node are flagged.

For complete information, see the xtcheckhss(8) man page.