redfish: skip NVMe bay probe for non-storage chassis types (Module/Component/Zone)
On Supermicro HGX systems (SYS-A21GE-NBRT) ~35 sub-chassis (GPU, NVSwitch, PCIeRetimer, ERoT/IRoT, BMC, FPGA) all carry ChassisType=Module/Component/Zone and expose empty /Drives collections. shouldAdaptiveNVMeProbe returned true for all of them, triggering 35 × 384 = 13 440 HTTP requests → ~22 min wasted per collection (more than half of total 35 min collection time). Fix: chassisTypeCanHaveNVMe returns false for Module, Component, Zone. The candidate selection loop in collectRawRedfishTree now checks the parent chassis doc before adding a /Drives path to the probe list. Enclosure (NVMe backplane), RackMount, and unknown types are unaffected. Tests: - TestChassisTypeCanHaveNVMe: table-driven, covers excluded and storage-capable types - TestNVMePostProbeSkipsNonStorageChassis: topology integration, GPU chassis + backplane with empty /Drives → exactly 1 candidate selected (backplane only) Docs: - ADL-018 in bible-local/10-decisions.md - Candidate-selection test matrix in bible-local/09-testing.md - SYS-A21GE-NBRT baseline row in docs/test_server_collection_memory.md Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -999,6 +999,17 @@ func (c *RedfishConnector) collectRawRedfishTree(ctx context.Context, client *ht
|
||||
if !shouldAdaptiveNVMeProbe(doc) {
|
||||
continue
|
||||
}
|
||||
// Skip chassis types that cannot contain NVMe storage (e.g. GPU modules,
|
||||
// RoT components, NVSwitch zones on HGX systems) to avoid probing hundreds
|
||||
// of Disk.Bay.N URLs against chassis that will never have drives.
|
||||
chassisPath := strings.TrimSuffix(normalized, "/Drives")
|
||||
if chassisDocAny, ok := out[chassisPath]; ok {
|
||||
if chassisDoc, ok := chassisDocAny.(map[string]interface{}); ok {
|
||||
if !chassisTypeCanHaveNVMe(asString(chassisDoc["ChassisType"])) {
|
||||
continue
|
||||
}
|
||||
}
|
||||
}
|
||||
driveCollections = append(driveCollections, normalized)
|
||||
}
|
||||
sort.Strings(driveCollections)
|
||||
@@ -1316,6 +1327,21 @@ func shouldAdaptiveNVMeProbe(collectionDoc map[string]interface{}) bool {
|
||||
return !redfishCollectionHasExplicitMembers(collectionDoc)
|
||||
}
|
||||
|
||||
// chassisTypeCanHaveNVMe returns false for Redfish ChassisType values that
|
||||
// represent compute/network/management sub-modules with no storage capability.
|
||||
// Used to skip expensive Disk.Bay.N probing on HGX GPU, NVSwitch, PCIeRetimer,
|
||||
// RoT and similar component chassis that expose an empty /Drives collection.
|
||||
func chassisTypeCanHaveNVMe(chassisType string) bool {
|
||||
switch strings.ToLower(strings.TrimSpace(chassisType)) {
|
||||
case "module", // GPU SXM, NVLinkManagementNIC, PCIeRetimer
|
||||
"component", // ERoT, IRoT, BMC, FPGA sub-chassis
|
||||
"zone": // HGX_Chassis_0 fabric zone
|
||||
return false
|
||||
default:
|
||||
return true
|
||||
}
|
||||
}
|
||||
|
||||
func redfishCollectionHasNumericMemberRefs(memberRefs []string) bool {
|
||||
for _, memberPath := range memberRefs {
|
||||
if redfishPathTailIsNumeric(memberPath) {
|
||||
|
||||
Reference in New Issue
Block a user