Re: Correction to comment regarding atomicity of an operation

Поиск
Список
Период
Сортировка
От Noah Misch
Тема Re: Correction to comment regarding atomicity of an operation
Дата
Msg-id 20120912200813.GA10429@tornado.leadboat.com
обсуждение исходный текст
Ответ на Re: Correction to comment regarding atomicity of an operation  (Gurjeet Singh <singh.gurjeet@gmail.com>)
Ответы Re: Correction to comment regarding atomicity of an operation  (Gurjeet Singh <singh.gurjeet@gmail.com>)
Список pgsql-hackers
On Wed, Sep 12, 2012 at 06:44:37AM -0400, Gurjeet Singh wrote:
> Thinking a bit more about the need for locks, I guess even the shared
> variables whose read/write ops are considered atomic need to be protected
> by locks so that the effects of NUMA architectures can be mitigated.

src/backend/storage/lmgr/README.barrier has nice coverage of such issues.

NUMA does not change the picture.  CPU architecture specifications define
ordering constraints for instructions that touch memory.  NUMA is a property
of specific system implementations that changes performance characteristics,
but not functional guarantees, of those instructions.



В списке pgsql-hackers по дате отправления:

Предыдущее
От: Nathan Wagner
Дата:
Сообщение: Re: ossp-uuid Contrib Patch
Следующее
От: Gurjeet Singh
Дата:
Сообщение: Re: Correction to comment regarding atomicity of an operation