[openib-general] Re: QoS RFC

[Caitlin Bestler]

openib-general-bounces at openib.org wrote:
> Roland
> 
> This thread also indirectly brings up the issue of
> OpenFabrics, RNIC, and QoS.
> 
> The RNIC devices don't have to be, but are typically unified
> wire devices, i.e. have simultaneous support for regular
> Ethernet NIC functions such as LSO/TSO and checksum offloads;
> iSCSI HBA initiator and/or target functionality; RNIC
> functionality; and TCP/IP offload.
> 
> All the usual Ethernet TCP/IP management and configuration
> tools work as expected for such a device, e.g. for the
> purpose of this discussion QoS configuration with DiffServ, etc.
> 
> At the same time: if there's an OpenFabrics QoS API, then
> this API needs to be transport agnostic, such that RNIC QoS
> can be configured through this same OpenFabrics QoS API.
> 
> To be clear: the QoS requirements presented in the RFC look
> quite reasonable for an RNIC device, but the initial proposal
> didn't abstract out non-essential (to QoS) IB detail.
> 
> Regards,
> 
> Asgeir Eiriksson
> CTO
> Chelsio Communications Inc.
> 
> 

For the reasons Asgeir cites, I believe that any QoS
solution that is compatible with a "unified wire" 'NIC'
would be something so inclusive that the proper forum
for its discussion would be netdev.

Creating specialized controls to deal with a portion
of the network traffic will not be generally useful.
I have no opinion as to how well defined the proposal
is for dealing specifically with InfiniBand traffic,
but I do not think it represents a generalized approach
to RDMA QoS for the simple reason that on an IP network
there is no such thing as QoS for *one* type of traffic.
QoS needs to cover all traffic to be of value.