xfs
[Top] [All Lists]

Re: [PATCH] Freeze bdevs when freezing processes.

To: David Chinner <dgc@xxxxxxx>
Subject: Re: [PATCH] Freeze bdevs when freezing processes.
From: Nigel Cunningham <ncunningham@xxxxxxxxxxxxx>
Date: Thu, 26 Oct 2006 19:18:57 +1000
Cc: "Rafael J. Wysocki" <rjw@xxxxxxx>, Pavel Machek <pavel@xxxxxx>, Andrew Morton <akpm@xxxxxxxx>, LKML <linux-kernel@xxxxxxxxxxxxxxx>, xfs@xxxxxxxxxxx
In-reply-to: <20061026085700.GI8394166@xxxxxxxxxxxxxxxxx>
References: <1161576735.3466.7.camel@xxxxxxxxxxxxxxxxxx> <200610251432.41958.rjw@xxxxxxx> <1161782620.3638.0.camel@xxxxxxxxxxxxxxxxxx> <200610252105.56862.rjw@xxxxxxx> <20061026073022.GG8394166@xxxxxxxxxxxxxxxxx> <1161850709.17293.23.camel@xxxxxxxxxxxxxxxxxx> <20061026085700.GI8394166@xxxxxxxxxxxxxxxxx>
Sender: xfs-bounce@xxxxxxxxxxx
Hi.

On Thu, 2006-10-26 at 18:57 +1000, David Chinner wrote:
> I didn't think we've ever done that - periodic or delayed operations
> are passed off to the kernel threads to execute. A stack trace
> (if you still have it) would be really help here.

I don't, but I know how to get it again. Will give it a go shortly.

> Hmmm - we have a couple of per-cpu work queues as well that are
> used on I/O completion and that can, in some circumstances,
> trigger new transactions. If we are only flush metadata, then
> I don't think that any more I/o will be issued, but I could be
> wrong (maze of twisty passages).

I can understand that. I'm trying to learn Xgl programming at the mo :)

Nigel


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