> I have a function in pgsql language, this function do some select to some
> tables for verify some conditions and then do one insert to a table with
> NO
> index. Update are not performed in the function
>
> When 1 client connected postgres do 180 execution per second
> With 2 clients connected postgres do 110 execution per second
> With 3 clients connected postgres do 90 execution per second
>
> Finally with 6 connected clients postgres do 60 executions per second
> (totally 360 executions per second)
>
> While testing, I monitor disk, memory and CPU and not found any overload.
There's always a bottleneck - otherwise the system might run faster (and
hit another bottleneck eventually). It might be CPU, I/O, memory, locking
and maybe some less frequent things.
> I know that with this information you can figure out somethigns, but in
> normal conditions, Is normal the degradation of performance per connection
> when connections are incremented?
> Or should I spect 180 in the first and something similar in the second
> connection? Maybe 170?
>
>
> The server is a dual xeon quad core with 16 GB of ram and a very fast
> storage
> The OS is a windows 2008 R2 x64
Might be, but we need more details about how the system works. On Linux
I'd ask for output from 'iostat -x 1' and 'vmstat 1' but you're on Windows
so there are probably other tools.
What version of PostgreSQL is this? What are the basic config values
(shared_buffers, work_mem, effective_cache_size, ...)? Have you done some
tuning? There's a wiki page about this:
http://wiki.postgresql.org/wiki/Tuning_Your_PostgreSQL_Server
Have you tried to log slow queries? Maybe there's one query that makes the
whole workload slow? See this:
http://wiki.postgresql.org/wiki/Logging_Difficult_Queries
Tomas
