Re: O_DIRECT on macOS
От | Thomas Munro |
---|---|
Тема | Re: O_DIRECT on macOS |
Дата | |
Msg-id | CA+hUKGLty89LL6G7buZDWO4wd5T=wcNPjTfUKd5LRJZzWcf8sw@mail.gmail.com обсуждение исходный текст |
Ответ на | Re: O_DIRECT on macOS (Andres Freund <andres@anarazel.de>) |
Ответы |
Re: O_DIRECT on macOS
|
Список | pgsql-hackers |
On Tue, Jul 13, 2021 at 1:56 PM Andres Freund <andres@anarazel.de> wrote: > On 2021-07-13 13:25:50 +1200, Thomas Munro wrote: > > I'm planning to go with that idea (#1), if there are no objections. > > The only other viable approach I see is to completely separate our > internal flag representation from the OS representation and do the whole > mapping inside fd.c - but that seems like a too big hammer right now. Agreed. Pushed! For the record, Solaris has directio() that could be handled the same way. I'm not planning to look into that myself, but patches welcome. Illumos (née OpenSolaris) got with the programme and added O_DIRECT. Of our 10-or-so target systems I guess that'd leave just HPUX (judging by an old man page found on the web) and OpenBSD with no direct I/O support.
В списке pgsql-hackers по дате отправления: