Cost Model

Поиск
Список
Период
Сортировка
От neto brpr
Тема Cost Model
Дата
Msg-id CALhhvc3MVe59VavoeE3ahrMeO6dh6fh9fkEzOT-tf-Vfp6qm-g@mail.gmail.com
обсуждение исходный текст
Ответы Re: Cost Model  ("David G. Johnston" <david.g.johnston@gmail.com>)
Список pgsql-hackers
Hello All

Anyone know if there is a patch that changes the PostgreSQL cost model in some way?
I'm working with an tuning technique, based in hybrid storage environments (HDDs and SSDs).

I need to know if exist any patches that allow postgresql to differentiate, for example, I/O costs of read and write and also costs of sequential read and random read.

This is because the read and write speeds of SSDs are asynchronous. On SSDs the read speed can be 340 times faster than writing.
In Hard Disks the sequential reading and writing values are almost the same. Also in HDDs the random reading is much slower than the sequential reading. 
In the SSDs the sequential and random reading are practically the same, due to being a purely electronic device.
I would like to know if there is any solution related to this that I said, because I would not need to develop this if something similar already exists.

It would be interesting if there is a patch that inserts new parameters in the postgresql.conf file to: 

- sequencial read page cost
- random read page cost
- sequencial write page cost
- random write page cost

Any comment, hint about it or something, please inform me.

Regards, 
Neto. 


Livre de vírus. www.avast.com.

В списке pgsql-hackers по дате отправления:

Предыдущее
От: David Fetter
Дата:
Сообщение: Schema-qualify function calls in information_schema
Следующее
От: Tom Lane
Дата:
Сообщение: Re: Schema-qualify function calls in information_schema