Re: checkpointer continuous flushing - V18
От | Fabien COELHO |
---|---|
Тема | Re: checkpointer continuous flushing - V18 |
Дата | |
Msg-id | alpine.DEB.2.10.1603102332220.18837@sto обсуждение исходный текст |
Ответ на | Re: checkpointer continuous flushing - V18 (Andres Freund <andres@anarazel.de>) |
Ответы |
Re: checkpointer continuous flushing - V18
|
Список | pgsql-hackers |
[...] > I had originally kept it with one context per tablespace after > refactoring this, but found that it gave worse results in rate limited > loads even over only two tablespaces. That's on SSDs though. Might just mean that a smaller context size is better on SSD, and it could still be better per table space. > The number of pages still in writeback (i.e. for which sync_file_range > has been issued, but which haven't finished running yet) at the end of > the checkpoint matters for the latency hit incurred by the fsync()s from > smgrsync(); at least by my measurement. I'm not sure I've seen these performance... If you have hard evidence, please feel free to share it. -- Fabien.
В списке pgsql-hackers по дате отправления: