Re: [pcp] pmchart + Some Archives == Sloooooow

[Ken McDonell <kenj@xxxxxxxxxxxxxxxx>]

On 06/01/15 09:31, Nathan Scott wrote:
> Should be enough info here already - Ken, I think the root cause here is using
> log-once for discrete metrics like hinv.ncpu and then using time windows which
> exclude that log-once sample.  We end up scanning the window for a value for
> the discrete metric IIRC... any way we could make libpcp peek outside the time
> window for this case?  (not going to be easy, I suspect)  Or any alternate way
> we could tackle this one?  Perhaps put a cap on the scan & returning novalues
> sooner than a full time window scan would?
Analysis looks robust.

Proper Fix (tm) is not that difficult.  For discrete metrics (we know 
the semantics) need to extend the search to the beginning of the archive 
(past the -S time) to try and find the lower (in time) bound ... this 
would be attempted at most once as per the existing logic.
I'm a bit time challenged at the moment, so don't expect a commit too soon.