On Thu, Apr 11, 2013 at 5:45 PM, Hefty, Sean <sean.he...@intel.com> wrote:
[...]
>> but lets get there after hopefully agreeing what is RSS QP group.

> So far, this is what I think it is:
> - a collection of related receive queues
> - each queue is configured somewhat separately - i.e. sized, CQ, sge size, 
> etc.
> - receives are posted to the queues separately
> - the queues are allocated together
>
> This is where it gets confusing.  They're allocated together, but through 
> separate API
> calls.
> I'm not sure if they share states or not.  Can all of them but one go into 
> the error state > and still receive data?  Do packets get routed to whichever 
> queue actually works, or do > packets sometimes get dropped, but sometimes 
> don't, depending on some local rules > which have been programmed into the 
> HCA?  Can the queues really be destroyed
> independently?

We only require (== implemented that) for the verbs level to mandate
for the RSS parent not to be destroyed before ANY of the RSS childs is
destroyed and be placed to action only after ALL RSS childs are
created. The queues (RSS childs can be destroyed independently after
the parent is destroyed, yes.

RSS child QPs are plain UD or RAW Packet QPs that only have
consecutive QPNs which is common requirement of HW for configuring the
RSS parent which in networking is called the RSS indirection or
dispatching QP. You can send and receive on them.

If an RSS child goes to the error state it will not receive data.

Packets are routed to RSS childs only per the hash function output,
not per the state of that child.

This design doesn't allow for an app to do DoS attack on the HW either
if they try that out or just have a bug, but does require them to
think out their code (design/review/test) - fair enough. RSS exists in
almost any Ethernet NIC you take from the shelf, and works in the
manner I explained here, e.g if one of the Ethernet RSS child queues
isn't functional packets hashed to it will not be received

> Is it even necessary to treat the receive queues as being independent?  What 
> happens > if they're allocated, destroyed, and modified as a single entity?
[...]

can you elaborate/explain the question a little more?

Or.
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Reply via email to