Re: stored procedure stats in collector - Mailing list pgsql-hackers

From Martin Pihlak
Subject Re: stored procedure stats in collector
Date
Msg-id 46F7EEF4.7090102@gmail.com
Whole thread Raw
In response to Re: stored procedure stats in collector  (Tom Lane <tgl@sss.pgh.pa.us>)
List pgsql-hackers
>> It seems that the overhead is unnoticeable if disabled, very visible
>> for lightweight functions and heavy callers. Almost unnoticeable for
>> more compute intensive functions.
> 
> The very high system times seem odd.  Maybe you have a machine with
> slow gettimeofday()?
> 

So it seems (on Ubuntu 7.04). Reran the benchmark on another system and
got more reasonable results:

"none"  usr      sys    total
dummy   15.9     0.68   16.58
rfact   39.37    0.07   39.44
ifact   12.89    0.01   12.9

"all"   usr      sys    total    diff x
dummy   20.82    4.44   25.26    1.52
rfact   45.17    4.17   49.34    1.25
ifact   12.92    0.03   12.96    1.00

Regards,
Martin


pgsql-hackers by date:

Previous
From: Simon Riggs
Date:
Subject: Re: GUC variable renaming, redux
Next
From: Tom Lane
Date:
Subject: Re: GUC variable renaming, redux