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-ia64-devel

Re: [Xen-ia64-devel] [PATCH] work around for populate physmap hypercall

To: Isaku Yamahata <yamahata@xxxxxxxxxxxxx>
Subject: Re: [Xen-ia64-devel] [PATCH] work around for populate physmap hypercall
From: Alex Williamson <alex.williamson@xxxxxx>
Date: Mon, 20 Aug 2007 09:35:30 -0600
Cc: xen-ia64-devel@xxxxxxxxxxxxxxxxxxx
Delivery-date: Mon, 20 Aug 2007 08:37:21 -0700
Envelope-to: www-data@xxxxxxxxxxxxxxxxxx
In-reply-to: <20070820032324.GA25340%yamahata@xxxxxxxxxxxxx>
List-help: <mailto:xen-ia64-devel-request@lists.xensource.com?subject=help>
List-id: Discussion of the ia64 port of Xen <xen-ia64-devel.lists.xensource.com>
List-post: <mailto:xen-ia64-devel@lists.xensource.com>
List-subscribe: <http://lists.xensource.com/cgi-bin/mailman/listinfo/xen-ia64-devel>, <mailto:xen-ia64-devel-request@lists.xensource.com?subject=subscribe>
List-unsubscribe: <http://lists.xensource.com/cgi-bin/mailman/listinfo/xen-ia64-devel>, <mailto:xen-ia64-devel-request@lists.xensource.com?subject=unsubscribe>
Organization: HP OSLO R&D
References: <20070820032324.GA25340%yamahata@xxxxxxxxxxxxx>
Sender: xen-ia64-devel-bounces@xxxxxxxxxxxxxxxxxxx
On Mon, 2007-08-20 at 12:23 +0900, Isaku Yamahata wrote:
> Hi.
> This patch is work around for xencomm and the soft lockup message.
> However I need help before commit.
> 
> - It is necessary to test it before commit with much memory.
>   I haven't tested it with much memory because my environment doesn't have
>   such huge memory.
> - I defined MEMORYOP_MAX_EXTENTS based on the xencomm limitation.
>   Howver I'm not sure the value is small enough to avoid the soft lockup
>   message because I couldn't produce the message on my environment.
>   It is necessary to determine the value with expriments.

Hi Isaku,

   The defined MEMORYOP_MAX_EXTENTS is still a bit too big, I get soft
lockups with large domains.  Further testing shows dividing your
MEMORYOP_MAX_EXTENTS calculation by 4 gives me nearly 1 million extents,
and eliminates the soft lockup.  I've tested up to a 90G domain with no
problems on startup.  Here's the macro I end up with:

#define MEMORYOP_MAX_EXTENTS                                            \
                ((((((PAGE_SIZE - sizeof(struct xencomm_desc)) /        \
                   sizeof(uint64_t)) - 2) * PAGE_SIZE) /                \
                  sizeof(*xen_guest_handle(kern_op.extent_start))) / 4)

Thanks,

        Alex

-- 
Alex Williamson                             HP Open Source & Linux Org.


_______________________________________________
Xen-ia64-devel mailing list
Xen-ia64-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-ia64-devel

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