Re: some longer, larger pgbench tests with various performance-related patches

On Wed, Jan 25, 2012 at 12:00 PM, Jeff Janes <jeff(dot)janes(at)gmail(dot)com> wrote:
> On Tue, Jan 24, 2012 at 12:53 PM, Robert Haas <robertmhaas(at)gmail(dot)com> wrote:
>> Early yesterday morning, I was able to use Nate Boley's test machine
>> do a single 30-minute pgbench run at scale factor 300 using a variety
>> of trees built with various patches, and with the -l option added to
>> track latency on a per-transaction basis.  All tests were done using
>> 32 clients and permanent tables.  The configuration was otherwise
>> identical to that described here:
>>
>> http://archives.postgresql.org/message-id/CA+TgmoboYJurJEOB22Wp9RECMSEYGNyHDVFv5yisvERqFw=6dw@mail.gmail.com
>
> Previously we mostly used this machine for CPU benchmarking.  Have you
> previously described the IO subsystem?  That is becoming relevant for
> these types of benchmarks.   For example, is WAL separated from data?

I actually don't know much about the I/O subsystem, but, no, WAL is
not separated from data. I believe $PGDATA is on a SAN, but I don't
know anything about its characteristics.

>> By doing this, I hoped to get a better understanding of (1) the
>> effects of a scale factor too large to fit in shared_buffers,
>
> In my hands, the active part of data at scale of 300 fits very
> comfortably into 8GB shared_buffers.
>
> Indeed, until you have run a very long time so that pgbench_history
> gets large, everything fits in 8GB.

Hmm, my mistake. Maybe I need to crank up the scale factor some more.
This is why good benchmarking is hard.

--
Robert Haas
EnterpriseDB: http://www.enterprisedb.com
The Enterprise PostgreSQL Company