Re: POC: Cache data in GetSnapshotData()

Поиск
Список
Период
Сортировка
От Robert Haas
Тема Re: POC: Cache data in GetSnapshotData()
Дата
Msg-id CA+TgmoapMXzCGFvjRYRoYAnCwpYf+d2itXx0nA-oSg+rGNOOFQ@mail.gmail.com
обсуждение исходный текст
Ответ на Re: POC: Cache data in GetSnapshotData()  (Mithun Cy <mithun.cy@enterprisedb.com>)
Ответы Re: POC: Cache data in GetSnapshotData()  (Mithun Cy <mithun.cy@enterprisedb.com>)
Список pgsql-hackers
On Thu, Mar 3, 2016 at 6:20 AM, Mithun Cy <mithun.cy@enterprisedb.com> wrote:

On Tue, Mar 1, 2016 at 12:59 PM, Amit Kapila <amit.kapila16@gmail.com> wrote:
>Don't we need to add this only when the xid of current transaction is valid?  Also, I think it will be better if we can explain why we need to add the our >own transaction id while caching the snapshot.
I have fixed the same thing and patch is attached.

Some more tests done after that

pgbench write tests: on 8 socket, 64 core machine.

/postgres -c shared_buffers=16GB -N 200 -c min_wal_size=15GB -c max_wal_size=20GB -c checkpoint_timeout=900 -c maintenance_work_mem=1GB -c checkpoint_completion_target=0.9

./pgbench -c $clients -j $clients -T 1800 -M prepared postgres

Inline image 3

A small improvement in performance at 64 thread.

What if you apply both this and Amit's clog control log patch(es)?  Maybe the combination of the two helps substantially more than either one alone.

Or maybe not, but seems worth checking.

--
Robert Haas
EnterpriseDB: http://www.enterprisedb.com
The Enterprise PostgreSQL Company
Вложения

В списке pgsql-hackers по дате отправления:

Предыдущее
От: Robert Haas
Дата:
Сообщение: Re: pgbench small bug fix
Следующее
От: Masahiko Sawada
Дата:
Сообщение: Re: Support for N synchronous standby servers - take 2