Thread (1 message) 1 message, 1 author, 2015-01-16

Re: Does I210 NIC support Flow director filters?

From: Bruce Richardson <hidden>
Date: 2015-01-16 17:31:59

On Fri, Jan 16, 2015 at 11:42:42AM -0500, Kamraan Nasim wrote:
Hi Bruce,
Perhaps this can be worked around by setting  rx_drop_en in the
rte_eth_rxconf <http://dpdk.org/doc/api/structrte__eth__rxconf.html> and
using small values for number of rx descripters so that the NIC drops when
it is out of RX descriptors for that queue?

As long as NIC can still provide q_ipackets/q_errors then this might be
faster than doing a RX in software and drop.

--Kam
Yes, so long as packets dropped for that queue are counted against that queue,
then yes.

/Bruce
On Fri, Jan 16, 2015 at 5:56 AM, Bruce Richardson <
bruce.richardson-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org> wrote:
quoted
On Thu, Jan 15, 2015 at 08:06:52PM -0500, Kamraan Nasim wrote:
quoted
quoted
quoted
quoted
update the RSS RETA table so that traffic doesn't get sent
to that queue via RSS. Is that what you are asking?
Thanks Bruce, that's exactly it.  Basically each filter will forward
traffic to a unique RSS queue which can allow me to calculate filter
match
quoted
statistics for that queue(or filter). At that point I would like to drop
the filtered packet. Is there any way to drop the filtered packet in the
RSS queue without doing a rte_eth_rx_burst() and dropping it then?

--Kam
I don't believe there is any other way to drop them from the queue other
than
RX and drop. It's not the most efficient way to do so (since you have to
allocate,
fill and free an mbuf), but it's the only way that an app can do so without
adding new functions to the driver(s).

/Bruce
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help