Skip to navigation
ReferenceCheck Catalog

CPU Checks

View as Markdown

CPU covers host processor inventory and availability signals.

System CPU Count

cpu_count

Verifies every logical CPU in the Linux kernel’s possible mask is online and available for scheduling.

PropertyValue
Provenancenvidia
Condition scopeNODE
Execution classPASSIVE
Scheduling cadenceCONTINUOUS
Maturitystable
Execution contextsOPERATOR_INFRA, TENANT_GUEST
Required signalspossible_cpu_count, online_cpu_count

Rules

  • CRITICAL when online_cpu_count != possible_cpu_count
    • Message: Expected all {possiblecpucount}possiblelogicalCPUstobeonline;found\{possible_cpu_count\} possible logical CPUs to be online; found {online_cpu_count} online.

Recommended action: operational state drain, then reset_gpu → restart_os → service_required

NUMA Node Count

numa_node_count

Verifies a node brought online the expected number of NUMA nodes for its architecture.

PropertyValue
Provenancenvidia
Condition scopeNODE
Execution classPASSIVE
Scheduling cadenceCONTINUOUS
Maturitystable
Execution contextsOPERATOR_INFRA, TENANT_GUEST
ArchitecturesGB200, GB300
Required signalsnuma_node_count

Thresholds

NameValueUnitCategoryDescription
expected_numa_node_countGB200: 34, GB300: 34, other: 34countDEFAULTExpected number of NUMA nodes online. GB200 and GB300 at 34. Override per fleet.

Rules

  • CRITICAL when numa_node_count != expected_numa_node_count
    • Message: Expected {expectednumanodecount}NUMAnodesonline,found\{expected_numa_node_count\} NUMA nodes online, found {numa_node_count}.

Recommended action: operational state drain, then reset_gpu → restart_os → service_required