Re: pcp updates: pmdaproc, cgroups, books

[Nathan Scott <nathans@xxxxxxxxxx>]

----- Original Message -----
> > ----- Original Message -----
> > [...]  Either I'm missing something, or you're missing what is
> > happening in proc_refresh - it doesn't matter how many PMIDs get
> > thrown at a single fetch, it will refresh each cluster only once per
> > fetch...  so it has to be the fetch batching that triggers the leak,
> > right?
> 
> Did you run the test I posted?  I included results (taken before and
> after the fd-leak patch) that speak for themselves, and don't rely on
> speculation about what internal behaviors should have or not have
> triggered the bug.

There was no question about the end result (the problem is how the end
point was reached), and no speculation on my part.

Let me know when a new version of the change incorporating the review
comments is available, otherwise I can take those on when I'm back in
the office.

cheers.

--
Nathan