- Архив списков рассылки pgsql-performance

Поиск
Список
Период
Сортировка
От Orhan Aglagul
Тема
Дата
Msg-id 868BCE5A6576F44A862F1FBBC3E14A01042559C3@ms17.mse9.exchange.ms
обсуждение исходный текст
Ответы Re:  (Dan Harris <fbsd@drivefaster.net>)
Re:  (Scott Marlowe <smarlowe@g2switchworks.com>)
Re:  (Scott Marlowe <smarlowe@g2switchworks.com>)
Re:  (Greg Smith <gsmith@gregsmith.com>)
Список pgsql-performance

Hi Everybody,

I was trying to see how many inserts per seconds my application could handle on various machines.

Those are the machines I used to run my app:

 

1)       Pentium M 1.7Ghz

2)       Pentium 4 2.4 Ghz

3)       DMP Xeon 3Ghz

 

Sure, I was expecting the dual Zeon to outperform the Pentium M and 4. But the data showed the opposite.

So, I wrote a simple program (in C) using the libpq.so.5 which opens a connection to the database (DB in localhost),

Creates a Prepared statement for the insert and does a 10,000 insert. The result did not change.

 

Only after setting fsync to off in the config file, the amount of time to insert 10,000 records was acceptable.

 

Here is the data:

           

Time for 10000 inserts

Fsync=on

Fsync=off

Pentium M 1.7

~17 sec

~6 sec

Pentium 4 2.4

~13 sec

~11 sec

Dual Xeon

~65 sec

~1.9 sec

 

I read that postgres does have issues with MP Xeon (costly context switching). But I still think that with fsync=on 65 seconds is ridiculous.

 

Can anybody direct me to some improved/acceptable  performance with fsync=on?

 

Thx,

 

Orhan a.

В списке pgsql-performance по дате отправления:

Предыдущее
От: david@lang.hm
Дата:
Сообщение: Re: Throttling PostgreSQL's CPU usage
Следующее
От: Dan Harris
Дата:
Сообщение: Re: