Skip to content

Extraction of node I/O metadata #2

@vsoch

Description

@vsoch

Not sure the extent to which ior will be used, but I want to put notes here for how we can eventually automate generation of the subsystem metadata for nodes.

  • Take in user request for names to parse from /proc/mounts or some other filtering method
  • Parse /proc/mounts to find names and get mount points (and other featresu0
  • For each mount point, we need quota (can use IOR) but...
    • Parallelism is based on the controller. We can look up device specs (and maybe find them represented somewhere online?) Aside from checking a website.

Ping @hariharan-devarajan just for future discussion - I'm going to manually create this for now so I can develop the rainbow plumbing. 🚽

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions