[nova] Persistent memory resource tracking model
jaypipes at gmail.com
Mon Jan 7 14:02:40 UTC 2019
On 01/07/2019 05:05 AM, Sean Mooney wrote:
> i think i share jays preference here in increasing the granularity and eiter tracking
> the allocation in MiBs or Bytes. i do somewhat agree that bytes is likely to fine grained
> hence my perference for mebibytes.
Actually, that's not at all my preference for PMEM :) My preference is
to use custom resource classes like "CUSTOM_PMEM_NAMESPACE_1TB" because
the resource is the namespace, not the bunch of blocks/bytes of storage.
With regards to the whole "finest-grained unit" thing, I was just
responding to Alex Xu's comment:
"The point of the initial design is avoid to encode the `size` in the
resource class name. If that is ok for you(I remember people hate to
encode size and number into the trait name), then we will update the
design. Probably based on the namespace configuration, nova will be
responsible for create those custom RC first. Sounds works."
More information about the openstack-discuss