Re: [pcp] Derived Metrics with rate()

[Marko Myllynen <myllynen@xxxxxxxxxx>]

Hi,

On 2015-06-29 08:54, Marko Myllynen wrote:
> On 2015-06-28 00:59, Ken McDonell wrote:
> 
>> I don't think avqsz is correct.  read_rawactive and write_rawactive measure
>> time during which  disk requests are being serviced  ... these are in units
>> of milliseconds, so you need to divide by 1000 to get close to the sar
>> numbers.
> 
> I couldn't figure out how to match exactly with sar numbers and this was
> at least reacting the same way as sar's avgqu-sz (I should mentioned
> this in my earlier email).

I tried this one more time and I think the earlier mentioned formula is
as close as possible to sar numbers, there's a bit of deviation but the
same can be seen with pmiostat as well, dividing by 1000 would be wrong.

Thanks,

-- 
Marko Myllynen