On Wed, 2005-11-02 at 21:16 +1100, Gavin Sherry wrote: > connections are updating the branches table heavily. As an aside, did you > initialise with a scaling factor of 10 to match your level of concurrency? Yep, I did. > that. The hackers list archive also contains links to the testing Mark > Wong has been doing at OSDL with TPC-C and TPC-H. Taking a look at the > configuration file he is using, along with the annotated postgresql.conf, > would be useful, depending on the load you're antipating and your > hardware. I will look into that project. > Well, two things may be at play. 1) if you are using write caching on your > controller/disks then at the point at which that cache fills up > performance will degrade to roughly that you can expect if write through > cache was being used. Secondly, we checkpoint the system periodically to > ensure that recovery wont be too long a job. Running for pgbench for a few > seconds, you will not see the effect of checkpointing, which usually runs > once every 5 minutes. I still think it is strange. Simple tests with tar suggest that I could easily do 600-700 tps at 50.000 KB/second ( as measured by iostat), a test with bonnie++ measured throughputs > 40.000 KB/sec during very long times, with 1723 - 2121 operations per second. These numbers suggest that PostgreSQL is not using all it could from the hardware. Processor load however is negligible during the pgbench tests. As written before, I will look into the OSDL benchmarks. Maybe they are more suited for my needs: *understanding* performance determinators. > > Hope this helps. You certainly did, thanks. -- Groeten, Joost Kraaijeveld Askesis B.V. Molukkenstraat 14 6524NB Nijmegen tel: 024-3888063 / 06-51855277 fax: 024-3608416 e-mail: J.Kraaijeveld@xxxxxxxxxx web: www.askesis.nl
