Re: pgsql: Allow to trigger kernel writeback after a configurable number of
От | Andres Freund |
---|---|
Тема | Re: pgsql: Allow to trigger kernel writeback after a configurable number of |
Дата | |
Msg-id | 20160312060832.szkhp4srs7vmqgy7@alap3.anarazel.de обсуждение исходный текст |
Ответ на | pgsql: Allow to trigger kernel writeback after a configurable number of (Andres Freund <andres@anarazel.de>) |
Ответы |
Re: pgsql: Allow to trigger kernel writeback after a configurable number of
|
Список | pgsql-committers |
Tom, On 2016-03-11 01:29:09 +0000, Andres Freund wrote: > Several operating systems allow some control over the kernel page > cache. Linux has sync_file_range(2), several posix systems have msync(2) > and posix_fadvise(2). sync_file_range(2) is preferable because it > requires no special setup, whereas msync() requires the to-be-flushed > range to be mmap'ed. For the purpose of flushing dirty data > posix_fadvise(2) is the worst alternative, as flushing dirty data is > just a side-effect of POSIX_FADV_DONTNEED, which also removes the pages > from the page cache. Thus the feature is enabled by default only on > linux, but can be enabled on all systems that have any of the above > APIs. This broke gaur: http://pgbuildfarm.org/cgi-bin/show_log.pl?nm=gaur&dt=2016-03-12%2005%3A44%3A25 I'm planning to add a #ifndef MAP_FAILED #define MAP_FAILED ((void*) (-1)). Unless HPPA simply has that defined elsewhere? Greetings, Andres Freund
В списке pgsql-committers по дате отправления: