Re: Speed up Clog Access by increasing CLOG buffers

Поиск
Список
Период
Сортировка
От Amit Kapila
Тема Re: Speed up Clog Access by increasing CLOG buffers
Дата
Msg-id CAA4eK1J70Aj6Pvt31LYMD8ptMv7+9WFN0cQLq1LGhCYPFM9njw@mail.gmail.com
обсуждение исходный текст
Ответ на Re: Speed up Clog Access by increasing CLOG buffers  (Robert Haas <robertmhaas@gmail.com>)
Ответы Re: Speed up Clog Access by increasing CLOG buffers  (Robert Haas <robertmhaas@gmail.com>)
Список pgsql-hackers
Дерево обсуждения
On Sun, Feb 21, 2016 at 12:02 PM, Robert Haas <robertmhaas@gmail.com> wrote:
On Sun, Feb 21, 2016 at 10:27 AM, Amit Kapila <amit.kapila16@gmail.com> wrote:

Client_Count/Patch_Ver164128256
HEAD(481725c0)963281452859326447
Patch-1938281523170329402


We can see 10~11% performance improvement as observed
previously.  You might see 0.02% performance difference with
patch as regression, but that is just a run-to-run variation.

Don't the single-client numbers show about a 3% regresssion?  Surely not 0.02%.


Sorry, you are right, it is ~2.66%, but in read-write pgbench tests, I
could see such fluctuation.  Also patch doesn't change single-client
case.  However, if you still feel that there could be impact by patch,
I can re-run the single client case once again with different combinations
like first with HEAD and then patch and vice versa.


With Regards,
Amit Kapila.
EnterpriseDB: http://www.enterprisedb.com

В списке pgsql-hackers по дате отправления:

Предыдущее
От: Robert Haas
Дата:
Сообщение: Re: Speed up Clog Access by increasing CLOG buffers
Следующее
От: Fabien COELHO
Дата:
Сообщение: Re: checkpointer continuous flushing - V18