Re: [issue] pmwebd graphite api performance issue

[Ken McDonell <kenj@xxxxxxxxxxxxxxxx>]

On 28/07/15 08:23, Frank Ch. Eigler wrote:
> Thanks!  More caching (whether within pmwebd or libpcp) would likely
> help this case.  Will ponder it deeper once we have the problem child ^W
> archive in hand.
Does not necessarily require any additional cacheing ... I was suggest 
an algorithmic change, from
traverse pmns
        for each metric of interest found
        get the metadata (including indom)

to

traverse pmns
        salt away each metric of interest
foreach metric of interest
        skip metric if already done
        get metadata
        process this _and_ all other metrics with the same indom

If an indom is common to N metrics this reduces the pmGetInDomArchive() 
calls from N to 1 for all those metrics