On 10.01.2020 23:21, Andrew Doran wrote: > The second is pulling in efficient tracking of page clean/dirty status from > the yamt-pagecache branch. This reduces the amount of work fsync() needs to > do, which should be of benefit to the DBMS. > We probably should adapt DBMS to use fsync_range(), at least there where Linux uses sync_file_range(). We might need to implement more semantics if needed, but there is need to someone with expertise in DBMS to speak up.
Attachment:
signature.asc
Description: OpenPGP digital signature