Horton

Re: We really ought to do something about O_DIRECT and data=journalled on ext4

Tom Lane <tgl@sss.pgh.pa.us>

View thread
From: Tom Lane <tgl@sss.pgh.pa.us>
To: Robert Haas <robertmhaas@gmail.com>
Cc: Josh Berkus <josh@agliodbs.com>, Greg Smith <greg@2ndquadrant.com>, PostgreSQL-development <pgsql-hackers@postgresql.org>
Date: 2010-12-07T02:10:13Z
Lists: pgsql-hackers 
Robert Haas <robertmhaas@gmail.com> writes:
> On Mon, Dec 6, 2010 at 9:04 PM, Josh Berkus <josh@agliodbs.com> wrote:
>> Actually, on OSX 10.5.8, o_dsync and fdatasync aren't even available.
>> From my run, it looks like even so regular fsync might be better than
>> open_sync.

> But I think you need to use fsync_writethrough if you actually want durability.

Yeah.  Unless your laptop contains an SSD, those numbers are garbage on
their face.  So that's another problem with test_fsync: it omits
fsync_writethrough.

			regards, tom lane