xfs
[Top] [All Lists]

Re: patch: double freereq freeing

To: Russell Cattelan <cattelan@xxxxxxxxxxx>
Subject: Re: patch: double freereq freeing
From: Jens Axboe <axboe@xxxxxxx>
Date: Mon, 11 Dec 2000 00:31:52 +0100
Cc: linux-xfs@xxxxxxxxxxx
In-reply-to: <3A33F9C8.CD56A6CC@xxxxxxxxxxx>; from cattelan@xxxxxxxxxxx on Sun, Dec 10, 2000 at 03:46:49PM -0600
References: <20001210215635.E294@xxxxxxx> <3A33F25C.5E9FAB1C@xxxxxxxxxxx> <20001210222057.F294@xxxxxxx> <3A33F9C8.CD56A6CC@xxxxxxxxxxx>
Sender: owner-linux-xfs@xxxxxxxxxxx
On Sun, Dec 10 2000, Russell Cattelan wrote:
> > In any way, I can merge it into the xfs tree if there's an interest.
> 
> I have discovered a corruption problem when using kiobuf io.
> I occurs both in the XFS-test11 tree and with your elevator patch.
> So it does appear to be the fault of the patch,
> although it does occur sooner with the elevator patch in.

The most likely explanation is probably that blk-xx changes the
I/O generated and thus the pattern of how soon / when corruption
happens.

> Currently our doio test can completely starve out log requests,
> thus by blocking out any new file system activity.
> Your patch does a good job of clean up the starvation problem so
> yes we do want to incorporate it.

We can easily do a small patch that enables log writes to not be
rearranged by the elevator. That should completely fix such log
starvation issues.

> We do need to figure out were the corruption is coming from
> first.

Of course.

-- 
* Jens Axboe <axboe@xxxxxxx>
* SuSE Labs

<Prev in Thread] Current Thread [Next in Thread>