Re: LWLOCK_STATS

Поиск
Список
Период
Сортировка
От Simon Riggs
Тема Re: LWLOCK_STATS
Дата
Msg-id CA+U5nMJJOX4AuASRaumXyfcXwnsj+r59AG-v62=VeH6GSib5fA@mail.gmail.com
обсуждение исходный текст
Ответ на Re: LWLOCK_STATS  (Jim Nasby <jim@nasby.net>)
Ответы Re: LWLOCK_STATS  (Merlin Moncure <mmoncure@gmail.com>)
Re: LWLOCK_STATS  (Jim Nasby <jim@nasby.net>)
Список pgsql-hackers
On Tue, Jan 10, 2012 at 12:24 AM, Jim Nasby <jim@nasby.net> wrote:

> IIRC, pg_bench is *extremely* write-heavy. There's probably not that many systems that operate that way. I suspect
thatmost OLTP systems read more than they write, and some probably have as much as a 10-1 ratio. 

IMHO the main PostgreSQL design objective is doing a flexible, general
purpose 100% write workload. Which is why Hot Standby and
LISTEN/NOTIFY are so important as mechanisms for offloading read
traffic to other places, so we can scale the total solution beyond 1
node without giving up the power of SQL.

So benchmarking write-heavy workloads and separately benchmarking
read-only workloads is more representative.

--
 Simon Riggs                   http://www.2ndQuadrant.com/
 PostgreSQL Development, 24x7 Support, Training & Services


В списке pgsql-hackers по дате отправления:

Предыдущее
От: Joel Jacobson
Дата:
Сообщение: Re: Generate call graphs in run-time
Следующее
От: Benedikt Grundmann
Дата:
Сообщение: Re: Page Checksums