[Openib-windows] Added ability to change IPoIB mtu size

[Yossi Leybovich]

> -----Original Message-----
> From: Alex Estrin [mailto:alex.estrin at qlogic.com] 
> Sent: Wednesday, November 29, 2006 6:45 PM
> To: Yossi Leybovich; Yossi Leybovich
> Cc: openib-windows at openib.org
> Subject: RE: [Openib-windows] Added ability to change IPoIB mtu size
> 
> Hi,
> 
> > -----Original Message-----
> > From: Yossi Leybovich [mailto:sleybo at dev.mellanox.co.il]
> > Sent: Wednesday, November 29, 2006 11:11 AM
> > To: Alex Estrin; Yossi Leybovich
> > Cc: openib-windows at openib.org
> > Subject: RE: [Openib-windows] Added ability to change IPoIB mtu size
> > 
> > 
> > Hi
> > 
> > Why do we need that?
> > Just update the inf and the driver will load. ( or you can fake the 
> > registry key ...).
> 
> - no updated INF file handy. 
> - Intentionally removed key.

That is true for developers and there are also quick ways to solve the
problems for developers
Do you think user use driver from one revision and inf from another?
Do you think user will delete the registry keys ?
(I assume that we have some keys that we must have so I don't think we can
be totally foolproof)

> 
> > If we go to this direction we should give default values 
> for all the 
> > registry keys why just to the payload ?
> Yes,I think that would be the best to have all default values 
> for all the keys.
> I assume almost all other IB stack capabilities depend on 
> IPoIB functionality, so it wouldn't be too much to expect it 
> to be as foolproof as possible.
> What do you think?
It will be nice to have this.

> 
> > Thanks
> > Yossi
> > 
> > > -----Original Message-----
> > > From: openib-windows-bounces at openib.org 
> > > [mailto:openib-windows-bounces at openib.org] On Behalf Of 
> Alex Estrin
> > > Sent: Wednesday, November 29, 2006 6:05 PM
> > > To: Yossi Leybovich
> > > Cc: openib-windows at openib.org
> > > Subject: Re: [Openib-windows] Added ability to change 
> IPoIB mtu size
> > > 
> > > Hi Yossi,
> > > 
> > > This patch would allow IPoIB to run even if for any 
> reason payload 
> > > mtu parameter is missing.
> > > Please review.
> > > 
> > > Thanks,
> > > Alex
> > > 
> > > Index: ipoib_driver.c
> > > 
> ===================================================================
> > > --- ipoib_driver.c	(revision 552)
> > > +++ ipoib_driver.c	(working copy)
> > > @@ -533,9 +533,13 @@
> > >  	{
> > >  		IPOIB_PRINT_EXIT( TRACE_LEVEL_ERROR, IPOIB_DBG_ERROR,
> > >  			("PayloadMtu parameter missing. Use the
> > > default.\n") );
> > > -		return status;
> > > +		p_adapter->params.payload_mtu = MAX_PAYLOAD_MTU;
> > > +		status = NDIS_STATUS_SUCCESS;
> > >  	}
> > > -	p_adapter->params.payload_mtu = 
> > > p_param->ParameterData.IntegerData;
> > > +	else
> > > +	{
> > > +		p_adapter->params.payload_mtu =
> > > p_param->ParameterData.IntegerData;
> > > +	}
> > >  	p_adapter->params.xfer_block_size = (sizeof(eth_hdr_t)
> > > + p_adapter->params.payload_mtu);
> > >  	NdisReadNetworkAddress( &status, &mac, &len, h_config );
> > > 
> > > > -----Original Message-----
> > > > From: openib-windows-bounces at openib.org 
> > > > [mailto:openib-windows-bounces at openib.org]On Behalf Of
> > > Yossi Leybovich
> > > > Sent: Wednesday, November 22, 2006 3:29 AM
> > > > To: Fabian Tillier; Anatoly Lisenko
> > > > Cc: openib-windows at openib.org
> > > > Subject: Re: [Openib-windows] Added ability to change
> > IPoIB mtu size
> > > > 
> > > > 
> > > >  
> > > > 
> > > > > -----Original Message-----
> > > > > From: Fabian Tillier [mailto:ftillier.sst at gmail.com]
> > > > > Sent: Wednesday, November 22, 2006 9:13 AM
> > > > > To: Anatoly Lisenko
> > > > > Cc: Yossi Leybovich; openib-windows at openib.org
> > > > > Subject: Re: [Openib-windows] Added ability to change
> > > IPoIB mtu size
> > > > > 
> > > > > Hi folks,
> > > > > 
> > > > > On 11/19/06, Anatoly Lisenko <anatolyl at voltaire.com> wrote:
> > > > > >
> > > > > > Hi Yossi,
> > > > > >
> > > > > > This patch add the ability to change MTU size in IPoIB.
> > > > > >
> > > > > > Please review.
> > > > > >
> > > > > > Thanks,
> > > > > >
> > > > > > Anatoly
> > > > > 
> > > > > It would be nice to have an explanation of what problem
> > > patches are
> > > > > trying to solve.  I assume this is done to enable
> > virtualization
> > > > > over IPoIB, which requires network packets to be ethernet
> > > MTU-sized.
> > > > > 
> > > > > I didn't have a chance to look at the patch, but have these
> > > > thoughts.
> > > > > Limiting the MTU reported to the OS works fine for
> > > outbound packets,
> > > > > but care must be exercised for inbound packets.
> > > > > 
> > > > > 1. The buffers posted to the receive queue must be the full
> > > > > 2048 byte IB MTU so that the IPoIB driver can receive
> > any packets
> > > > > sent to it without hitting a protection error due to
> > > overrunning the
> > > > > receive buffers.
> > > > > 2. If a buffer larger than the configured MTU is
> > > received, it must
> > > > > be reported to the OS somehow.  I don't know what's
> > > required to do
> > > > > this, whether you create a new IP header for the data
> > beyond the
> > > > > first, or whatnot, but it must be done in such a way that
> > > subsequent
> > > > > packets don't cause issues with sequence numbers.  This
> > > doesn't seem
> > > > > like a simple thing to do right, let alone in a 
> performant way.
> > > > > 
> > > > Cant we just drop the packets and add that to the statiscs
> > > of packet
> > > > discards?
> > > > Wny how I will check that in the code.
> > > > 
> > > > > Cheers,
> > > > > 
> > > > > - Fab
> > > > > 
> > > > 
> > > > _______________________________________________
> > > > openib-windows mailing list
> > > > openib-windows at openib.org
> > > > http://openib.org/mailman/listinfo/openib-windows
> > > > 
> > > > 
> > > 
> > 
> > 
>