Re: Changing WAL Header to reduce contention during ReserveXLogInsertLocation()

Поиск
Список
Период
Сортировка
От Pavan Deolasee
Тема Re: Changing WAL Header to reduce contention during ReserveXLogInsertLocation()
Дата
Msg-id CABOikdOFM9i906PMpuE7-a3N+xqjYFS=B-9C5Ozh9+wKA-onsQ@mail.gmail.com
обсуждение исходный текст
Ответ на Re: Changing WAL Header to reduce contention duringReserveXLogInsertLocation()  (Peter Eisentraut <peter.eisentraut@2ndquadrant.com>)
Ответы Re: Changing WAL Header to reduce contention during ReserveXLogInsertLocation()  (Simon Riggs <simon@2ndquadrant.com>)
Список pgsql-hackers
Дерево обсуждения


On Fri, Mar 9, 2018 at 8:49 PM, Peter Eisentraut <peter.eisentraut@2ndquadrant.com> wrote:
On 2/1/18 19:21, Simon Riggs wrote:
> If we really can't persuade you of that, it doesn't sink the patch. We
> can have the WAL pointer itself - it wouldn't save space but it would
> at least alleviate the spinlock.

Do you want to send in an alternative patch that preserves the WAL
pointer and only changes the locking?


Sorry for the delay. Here is an updated patch which now replaces xl_prev with xl_curr, thus providing similar safeguards against corrupted or torn WAL pages, but still providing benefits of atomic operations.

I repeated the same set of tests and the results are almost similar. These tests are done on a different AWS instance though and hence not comparable to previous tests. What we do in these tests is essentially call ReserveXLogInsertLocation() 1M times to reserve 256 bytes each time, in a single select statement (the function is exported and a SQL-callable routine is added for the purpose of the tests)

Patched:
======
#clients  #tps
1 34.195311
2 29.001584
4 31.712009
8 35.489272
16 41.950044

Master:
======
#clients  #tps
1 24.128004
2 12.326135
4 8.334143
8 16.035699
16 8.502794

So that's pretty good improvement across the spectrum.

Thanks,
Pavan

--
 Pavan Deolasee                   http://www.2ndQuadrant.com/
 PostgreSQL Development, 24x7 Support, Training & Services
Вложения

В списке pgsql-hackers по дате отправления:

Предыдущее
От: Kyotaro HORIGUCHI
Дата:
Сообщение: Re: Protect syscache from bloating with negative cache entries
Следующее
От: Alexander Korotkov
Дата:
Сообщение: Re: Prefix operator for text and spgist support