Re: Overhead for stats_command_string et al, take 2

Tom Lane wrote:

> The bad news is that except in the stats_command_string cases, HEAD
> is noticeably slower than 8.1 on the machine with slow gettimeofday.
> In the single-transaction test this might be blamed on the addition
> of statement_timestamp support (which requires a gettimeofday per
> statement that wasn't there in 8.1) ... but in the one-transaction-
> per-statement tests that doesn't hold water, because each branch is
> doing a gettimeofday per statement, just in different places.
>
> Can anyone else reproduce this slowdown? It might be only an artifact
> of these particular builds, but it's a bit too consistent in my x86 data
> to just ignore.

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.

Stefan