Fleetscale Memory Fault Management
Fleetscale Memory Fault Management (FMFM) is a Workstream within the OCP Hardware Management Project focused on standardizing memory fault management at fleet scale. It is proposing a vendor-agnostic architecture for memory error handling, with modular inputs from different hardware vendors, standard APIs between modules, and defined outputs such as failure cause, health information, and RAS actions. It is also standardizing memory error telemetry for better fleet-scale RAS management, troubleshooting, and FRU replacement policies, and coordinating with the broader OCP community to ensure a path for the architecture. The specification is developed on GitHub.
Get involved
Steering Committee Representative
Project Leads
About This Workstream
Fleetscale Memory Fault Management (FMFM) is a Workstream within the OCP Hardware Management Project.
The workstream is about standardization of fleet-scale memory fault management: a vendor-agnostic architecture for memory error handling, standardized memory error telemetry, and a path for that architecture across the broader OCP community.
Get Involved
Proposal and framework requirements are shared as working documents; the specification is developed on GitHub.
FMFM Workstream ProposalSpecification Repository on GitHubMailing List: OCP-HWMgt-FMFM
Scope
The FMFM Workstream focuses on standardization of fleet-scale memory fault management. Proposed topics:
- Vendor-Agnostic Architecture : standardize a vendor-agnostic architecture for memory error handling : modularization of inputs from different hardware vendors; APIs and connections between modules from different vendors; defined outputs for each module (failure cause, health information, RAS actions, etc.)
- Memory Error Telemetry : standardize memory error telemetry : format content for better fleet-scale RAS management, troubleshooting, FRU replacement policies, etc.
- OCP Alignment : coordinate with the broader OCP group to make sure there is a path for this general architecture