Re: We really ought to do something about O_DIRECT and data=journalled on ext4
From:
Andres Freund <andres(at)anarazel(dot)de>
To:
pgsql-hackers(at)postgresql(dot)org
Cc:
Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>,
Josh Berkus <josh(at)agliodbs(dot)com>
Subject:
Re: We really ought to do something about O_DIRECT and data=journalled on ext4
Date:
2010-12-01 18:41:46
Message-ID:
201012011941.46965.andres@anarazel.de (view raw or flat )
Thread:
2010-12-01 02:55:58 from Josh Berkus <josh(at)agliodbs(dot)com>
2010-12-01 03:09:01 from Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
2010-12-01 03:13:11 from Josh Berkus <josh(at)agliodbs(dot)com>
2010-12-01 05:31:34 from Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
2010-12-01 10:35:50 from Dimitri Fontaine <dimitri(at)2ndQuadrant(dot)fr>
2010-12-01 11:46:45 from Marti Raudsepp <marti(at)juffo(dot)org>
2010-12-01 13:50:36 from Robert Haas <robertmhaas(at)gmail(dot)com>
2010-12-01 17:58:24 from Josh Berkus <josh(at)agliodbs(dot)com>
2010-12-01 18:09:05 from Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
2010-12-01 18:19:40 from Josh Berkus <josh(at)agliodbs(dot)com>
2010-12-01 18:53:09 from Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
2010-12-01 19:00:25 from Josh Berkus <josh(at)agliodbs(dot)com>
2010-12-01 18:41:46 from Andres Freund <andres(at)anarazel(dot)de>
2010-12-01 19:03:38 from Andrew Dunstan <andrew(at)dunslane(dot)net>
2010-12-01 22:48:05 from Greg Smith <greg(at)2ndquadrant(dot)com>
2010-12-06 20:53:42 from Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
2010-12-06 23:56:26 from Greg Smith <greg(at)2ndquadrant(dot)com>
2010-12-07 00:43:15 from Steve Singer <ssinger(at)ca(dot)afilias(dot)info>
2010-12-07 02:00:24 from Josh Berkus <josh(at)agliodbs(dot)com>
2010-12-07 18:16:57 from Steve Singer <ssinger(at)ca(dot)afilias(dot)info>
2010-12-07 01:34:33 from Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
2010-12-08 15:14:18 from Marti Raudsepp <marti(at)juffo(dot)org>
2010-12-08 15:36:21 from Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
2010-12-07 02:04:02 from Josh Berkus <josh(at)agliodbs(dot)com>
2010-12-07 02:05:28 from Robert Haas <robertmhaas(at)gmail(dot)com>
2010-12-07 02:10:13 from Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
2010-12-07 02:12:25 from Josh Berkus <josh(at)agliodbs(dot)com>
2011-03-11 01:25:52 from Bruce Momjian <bruce(at)momjian(dot)us>
2010-12-07 02:32:48 from Josh Berkus <josh(at)agliodbs(dot)com>
2010-12-01 03:25:22 from Andrew Dunstan <andrew(at)dunslane(dot)net>
2010-12-01 04:17:05 from Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
2010-12-01 14:00:13 from Andrew Dunstan <andrew(at)dunslane(dot)net>
2010-12-02 23:58:36 from Bruce Momjian <bruce(at)momjian(dot)us>
2010-12-03 19:55:23 from Josh Berkus <josh(at)agliodbs(dot)com>
2010-12-03 20:02:24 from Heikki Linnakangas <heikki(dot)linnakangas(at)enterprisedb(dot)com>
Lists:
pgsql-hackers
On Wednesday 01 December 2010 19:09:05 Tom Lane wrote:
> Josh Berkus <josh(at)agliodbs(dot)com> writes:
> > It's a bug and it's our bug.
>
> No, it's a filesystem bug that this particular filesystem doesn't
> support a perfectly reasonable combination of options, and doesn't
> even fail gracefully as it could easily do. But assigning blame
> doesn't help much.
I wouldnt call it a reasonable combination - promising fs-level data-
journaling (data=journal) and O_DIRECT are not really compatible with each
other...
Andres
In response to
Responses
pgsql-hackers by date
Next :From: Heikki LinnakangasDate: 2010-12-01 18:51:19Subject : Re: Hot Standby: too many KnownAssignedXidsPrevious :From : Josh BerkusDate : 2010-12-01 18:19:40Subject : Re: We really ought to do something about O_DIRECT and
data=journalled on ext4
