Re: Patch to improve reliability of postgresql on linux nfs
От | Thom Brown |
---|---|
Тема | Re: Patch to improve reliability of postgresql on linux nfs |
Дата | |
Msg-id | CAA-aLv7-fWZuWYEch1ScZFFnktvRgfEjbAy4BFpw=uwN85Z=zA@mail.gmail.com обсуждение исходный текст |
Ответ на | Patch to improve reliability of postgresql on linux nfs (George Barnett <gbarnett@atlassian.com>) |
Список | pgsql-hackers |
On 9 September 2011 01:04, George Barnett <gbarnett@atlassian.com> wrote: > After looking through the code I found that when postgres calls write() it doesn't retry. In order to address the issuewith the PANIC in the WAL writer I set the sync method to o_sync which solved the issue in that part of the code, howeverI was still seeing failures in other areas of the code (such as the FileWrite function). Following this, I spoketo an NFS guru who pointed out that writes under linux are not guaranteed to complete unless you open up O_SYNC or similaron the file handle. Have you run the test with varying wal_sync_method values? On Linux the default is fdatasync because historically Linux hasn't supported O_DSYNC (a wal_sync_method value of open_datasync). But I believe as of Kernel 2.6.33 it does support it. Have you tried modifying this parameter in your tests? Are you even using Linux? (you haven't specified) -- Thom Brown Twitter: @darkixion IRC (freenode): dark_ixion Registered Linux user: #516935 EnterpriseDB UK: http://www.enterprisedb.com The Enterprise PostgreSQL Company
В списке pgsql-hackers по дате отправления: