Re: Performance issue with 8.2.3 - "C" application

От: Karl Denninger
Тема: Re: Performance issue with 8.2.3 - "C" application
Дата: ,
Msg-id: 46A7BA28.5030203@denninger.net
(см: обсуждение, исходный текст)
Ответ на: Re: Performance issue with 8.2.3 - "C" application  (Karl Denninger)
Список: pgsql-performance

Скрыть дерево обсуждения

Performance issue with 8.2.3 - "C" application  (Karl Denninger, )
 Re: Performance issue with 8.2.3 - "C" application  (Tom Lane, )
  Re: Performance issue with 8.2.3 - "C" application  (Karl Denninger, )
   Re: Performance issue with 8.2.3 - "C" application  ("Merlin Moncure", )
    Re: Performance issue with 8.2.3 - "C" application  (Karl Denninger, )
     Re: Performance issue with 8.2.3 - "C" application  (Tom Lane, )
      Re: Performance issue with 8.2.3 - "C" application  (Karl Denninger, )
       Re: Performance issue with 8.2.3 - "C" application  (Karl Denninger, )
 Re: Performance issue with 8.2.3 - "C" application  (Nis Jørgensen, )
 Re: Performance issue with 8.2.3 - "C" application  (Gregory Stark, )

Looks like that was the problem - got a day under the belt now with the
8.2.4 rev and all is back to normal.

Karl Denninger ()
http://www.denninger.net




Karl Denninger wrote:
> Aha!
>
> BIG difference.  I won't know for sure until the biz day tomorrow but
> the "first blush" look is that it makes a HUGE difference in system
> load, and I no longer have the stats collector process on the top of
> the "top" list......
>
> Karl Denninger ()
> http://www.denninger.net
>
>
>
>
> Tom Lane wrote:
>> Karl Denninger <> writes:
>>
>>> Hmmmmm..... now that's interesting.  Stats collector IS accumulating
>>> quite a bit of runtime..... me thinks its time to go grab 8.2.4.
>>>
>>
>> I think Merlin might have nailed it --- the "stats collector bug" is
>> that it tries to write out the stats file way more often than it
>> should.  So any excessive userland CPU time you see is just the tip
>> of the iceberg compared to the system and I/O costs incurred.
>>
>>             regards, tom lane
>>
>> ---------------------------(end of broadcast)---------------------------
>> TIP 1: if posting/reading through Usenet, please send an appropriate
>>        subscribe-nomail command to  so that your
>>        message can get through to the mailing list cleanly
>>
>>
>> %SPAMBLOCK-SYS: Matched [hub.org+], message ok
>>
>
>
> %SPAMBLOCK-SYS: Matched [@postgresql.org+], message ok
>
> ---------------------------(end of broadcast)---------------------------
> TIP 6: explain analyze is your friend
>
>
> %SPAMBLOCK-SYS: Matched [hub.org+], message ok


%SPAMBLOCK-SYS: Matched [@postgresql.org+], message ok


В списке pgsql-performance по дате сообщения:

От: Tom Lane
Дата:
Сообщение: Re: User concurrency thresholding: where do I look?
От: angga erwina
Дата:
Сообщение: performance of postgresql in replication using slony