Re: RFC: filtered metrics

[fche@xxxxxxxxxx (Frank Ch. Eigler)]

nathans wrote:

> [...]  Thinking system wide filters like "when looking at
> per-process metrics, this system is expected to have N million
> insts, so force a system wide filter for all access to per-process
> metrics via a specified cgroup". [...]

Would this be a administrative preference for security/load-limiting?
If so, it's bound to be ineffective.

Is it for a user's convenience, to automagically limit system view to
her own context (if she's stuck within a cgroup)?  That could be done
by extending our use of the unix-socket SO_PEERCRED system to also
pass the incoming pid to the pmdas, which could then (if desired - ie.
in some PMNS subhierarchy) govern themselves accordingly.

- FChE