WARNING - OLD ARCHIVES

This is an archived copy of the Xen.org mailing list, which we have preserved to ensure that existing links to archives are not broken. The live archive, which contains the latest emails, can be found at http://lists.xen.org/
   
 
 
Xen 
 
Home Products Support Community News
 
   
 

xen-devel

Re: [Xen-devel] [PATCH 1 of 2 V4] tools/libxc: Remus Checkpoint Compress

To: rshriram@xxxxxxxxx
Subject: Re: [Xen-devel] [PATCH 1 of 2 V4] tools/libxc: Remus Checkpoint Compression
From: George Dunlap <George.Dunlap@xxxxxxxxxxxxx>
Date: Thu, 20 Oct 2011 12:48:49 +0100
Cc: brendan@xxxxxxxxx, xen-devel@xxxxxxxxxxxxxxxxxxx, ian.jackson@xxxxxxxxxxxxx
Delivery-date: Thu, 20 Oct 2011 04:49:41 -0700
Dkim-signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=mime-version:sender:in-reply-to:references:date :x-google-sender-auth:message-id:subject:from:to:cc:content-type :content-transfer-encoding; bh=WknNQI53B6OZ+6xIwfTjY83mwgMXujD8FWKdzcnbuN4=; b=GlHcNE5SqJ1XOYM/H1j1TQ/NkP1f39lQPrSTx0F6xQ6MolbBIv3o06yyeZY7REZ0+9 Z+OAt/F3JLULsSelkPJAetANOpOlliA701AF0zZpAcpTdqXP5Lq2ncgCeQAMDCh1D1ok LeN7xmbfM/GjLVlrSP3yzV8YzkQ/XVVPr3ahQ=
Envelope-to: www-data@xxxxxxxxxxxxxxxxxxx
In-reply-to: <64d6b8a65a7ed4939fef.1319050207@xxxxxxxxxxxxxxxxxxx>
List-help: <mailto:xen-devel-request@lists.xensource.com?subject=help>
List-id: Xen developer discussion <xen-devel.lists.xensource.com>
List-post: <mailto:xen-devel@lists.xensource.com>
List-subscribe: <http://lists.xensource.com/mailman/listinfo/xen-devel>, <mailto:xen-devel-request@lists.xensource.com?subject=subscribe>
List-unsubscribe: <http://lists.xensource.com/mailman/listinfo/xen-devel>, <mailto:xen-devel-request@lists.xensource.com?subject=unsubscribe>
References: <patchbomb.1319050206@xxxxxxxxxxxxxxxxxxx> <64d6b8a65a7ed4939fef.1319050207@xxxxxxxxxxxxxxxxxxx>
Sender: xen-devel-bounces@xxxxxxxxxxxxxxxxxxx
On Wed, Oct 19, 2011 at 7:50 PM,  <rshriram@xxxxxxxxx> wrote:
> +    /* Without checkpoint compression, the dirty pages, pfn arrays
> +     * and tailbuf (vcpu ctx, shared info page, etc.)  are written
> +     * directly to outbuf. All of this is done while the domain is
> +     * suspended.
> +     *
> +     * When checkpoint compression is enabled, the dirty pages are
> +     * buffered, compressed "after" the domain is resumed and then
> +     * written to outbuf. Since tailbuf data are collected while a
> +     * domain is suspended, they cannot be directly written to the
> +     * outbuf as there is no dirty page data preceeding tailbuf.
> +     *
> +     * So,two output buffers are maintained. Tailbuf data goes into
> +     * ob_tailbuf. The dirty pages are compressed after resuming the
> +     * domain and written to ob_pagebuf. ob_tailbuf is then appended
> +     * to ob_pagebuf and finally flushed out.
> +     */
> +    struct outbuf ob_pagebuf, ob_tailbuf, *ob = NULL;

Thanks, that's very helpful.

I don't have any more objections / comments.

 -George

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel

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