Re: Overhead for stats_command_string et al, take 2

Tom Lane wrote:
> Stefan Kaltenbrunner <stefan(at)kaltenbrunner(dot)cc> writes:
>> This is what I get on a fast AMD Dual Opteron box(Running Debian
>> Sarge/AMD64):
>
>> 8.1.4 HEAD
>> 1000000 SELECT 1; 74,74,73 77,76,77
>> stats_command_string=1; 105,99,106 78,79,78
>> log_min_duration_statement=100 79,80,81 75,80,76
>> statement_timeout=100 78,79,78 75,79,77
>> all 3 104,108,107 82,81,81
>
>> all values in seconds with 3 consecutive runs of one million "SELECT 1;"
>> queries. It takes about 48 seconds to run the same test without
>> stat-collection btw.
>
> I'm confused. Isn't your first table row for the case of no stat collection?
> Or do you mean that you have stats_row_level and/or stats_block_level on
> in all four cases?

yes - stats_row_level and stats_block_level on in all cases (sorry for
the confusion) - I can easily redo the tests without those - but that's
what I had in the running conf and I only remember that after I was
nearly done with all the testing :-)

Stefan