Date: Thu, 4 Dec 2008 11:45:44 -0500 (EST)
From: Mikulas Patocka <mpatocka@redhat.com>
To: Andi Kleen <andi@firstfloor.org>
cc: linux-kernel@vger.kernel.org, xfs@oss.sgi.com,
       Alasdair G Kergon <agk@redhat.com>,
       Andi Kleen <andi-suse@firstfloor.org>, Milan Broz <mbroz@redhat.com>
Subject: Re: Device loses barrier support (was: Fixed patch for simple
 barriers.)
In-Reply-To: <20081204145810.GR6703@one.firstfloor.org>
Message-ID: <Pine.LNX.4.64.0812041139200.2434@hs20-bc2-1.build.redhat.com>
References: <Pine.LNX.4.64.0812040009340.15169@hs20-bc2-1.build.redhat.com>
 <20081204100050.GN6703@one.firstfloor.org> <Pine.LNX.4.64.0812040836480.6118@hs20-bc2-1.build.redhat.com>
 <20081204142015.GQ6703@one.firstfloor.org> <Pine.LNX.4.64.0812040913510.6118@hs20-bc2-1.build.redhat.com>
 <20081204145810.GR6703@one.firstfloor.org>
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1692
Lines: 50

> > > > finished after the 2nd write) and you are in an interrupt context, where 
> > > > you can't reissue -EOPNOTSUPP request. So what do you want to do?
> > > 
> > > The barrier aware file systems I know of just resubmit synchronously when 
> > > a barrier fails.
> > 
> > ... and produce structure corruption for certain period in time, because 
> > the writes meant to be ordered are submitted unordered.
> 
> No there is nothing unordered. The file system path typically looks like
> 
> commit of a transaction
> 	if (i have never seen a barrier failing) 
> 		write block with barrier
> 		if (EOPNOTSUPP) {
> 			record failure
> 			submit synchronously
> 		}
> 	} else
> 		submit synchronously
> 

If you view this as a "right" way of using barriers, then you can drop 
barrier support at all and replace this code sequence with:

 flush disk cache
 submit write synchronously
 flush disk cache

--- because synchronous barriers bring you no performance advantage over 
the above sequence.

> So if a pvmove barrier fails it will just submit synchronously.
> 
> The write block with barrier bit varies, jbd/gfs2 do it synchronously
> too and xfs does it asynchronously (with io done callbacks), but

And how does xfs preserve write ordering, if the barrier asynchronously 
fails with -EOPNOTSUPP and there are other writes submitted after the 
barrier?

> in both cases they handle an EOPNOTSUPP comming out in the final
> io done.

Mikulas
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/