[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

RE: [Xen-users] "Memory squeeze in netback driver"


  • To: "Petersson, Mats" <Mats.Petersson@xxxxxxx>, <xen-users@xxxxxxxxxxxxxxxxxxx>
  • From: "Marlier, Ian" <ian.marlier@xxxxxxxxxxxxxxxxxxx>
  • Date: Thu, 19 Oct 2006 16:41:18 -0400
  • Delivery-date: Thu, 19 Oct 2006 13:42:55 -0700
  • List-id: Xen user discussion <xen-users.lists.xensource.com>
  • Thread-index: Acbyx0BJO5HZCGkVS7O00pwajpVJ4wA1C3mAAABfjhAAB9RakA==
  • Thread-topic: [Xen-users] "Memory squeeze in netback driver"

 

> -----Original Message-----
> From: Petersson, Mats [mailto:Mats.Petersson@xxxxxxx] 
> Sent: Thursday, October 19, 2006 1:09 PM
> To: Marlier, Ian; xen-users@xxxxxxxxxxxxxxxxxxx
> Subject: RE: [Xen-users] "Memory squeeze in netback driver"
> 
>  
> 
> > -----Original Message-----
> > From: xen-users-bounces@xxxxxxxxxxxxxxxxxxx
> > [mailto:xen-users-bounces@xxxxxxxxxxxxxxxxxxx] On Behalf Of 
> Marlier, 
> > Ian
> > Sent: 19 October 2006 17:28
> > To: Marlier, Ian; xen-users@xxxxxxxxxxxxxxxxxxx
> > Subject: RE: [Xen-users] "Memory squeeze in netback driver"
> > 
> > Anyone have thoughts on this?  I've googled around, and 
> haven't come 
> > up with anything that I haven't tried already.
> > 
> > And, it severely limits the effectiveness of the Xen environment, 
> > because I'm now running a machine that appears unable to 
> use more than 
> > 25% of the available resources...
> 
> If you look at linux-<ver>-xen/drivers/xen/netback/netback.c 
> around line
> 572 (this isn't the latest source, but I don't think it's 
> changed much in the last week or so), you'll see where the 
> error message comes from.
> I'm not sure what the code does tho' - it's got something to 
> do with the hypercall XENMEM_increase_reservation, but I 
> haven't got time to look at what that does. 
> 
> dom0_mem shouldn't be added to the vmlinuz line, but to the 
> xen.gz line
> - which I think is the reason your dom0 is showing 12GB. Not 
> sure if that's got anything to do with the above problem tho'. 

Mats, perfect!  Moving the dom0_mem parameter to the kernel line in my
grub config was all that was needed.  I feel a little silly for not
having figured that one out myself, though... :-/

I'm not going to pretend that I understand what the code you pointed to
is doing -- I know a bit of C, but it would take me a good long while to
walk that back.  I would bet, though, that it has to do with the chunk
of memory allocated to Dom0 by the balloon driver when a new machine is
created (for what, I dunno, but...).  We started seeing problems when
the total amount of memory allocated was at or just above 4GB, so maybe
Dom0 just didn't have DMA-able memory available to allocate itself?

Or, at least, that makes sense to my growing-but-not-yet-grown
understanding, and seems to fit with the symptoms and the solution.


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


 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.