Hi,
VPP provides the ARP functionality, However does it share the L2 tables
with kernel ?
When ARP input is processed then below functions are called -
vnet_arp_set_ip4_over_Ethernet
vl_api_rpc_call_main_thread
vl_msg_api_send_shmem_nolock
What is the purpose rpc_call_
Hey,
vnet_buffer_opaque_t data structure is very useful to delivery information
between graph nodes.
But seems that it is not clear for the following points:
(1). What rules need to be followed when using it?
(2). What is the limitation when using it?
(3). What usages are not allowed?
We need
I have found generally found that having features that can only be configured
at software startup almost inevitably causes problems. There are rare cases
where there is no choice, but in general it is much better if configuration can
be done for all features during operation.
Having said that,
On 11/10/16, gannega wrote:
> Hi,
>
> One question for Keith first:
>
> The flowtable currently uses the first opaque field as a buffer to store
> the data associated to the flow, but Andrew told me today that you
> advised against this kind of behavior.
Yeah - Keith, that was my impression from
Hi,
One question for Keith first:
The flowtable currently uses the first opaque field as a buffer to store
the data associated to the flow, but Andrew told me today that you
advised against this kind of behavior.
The idea is that the flowtable is configured to redirect packets to a
working node
Thanks for this input. That’s helpful.
Jerome
De : "murali Venkateshaiah (muraliv)"
Date : jeudi 10 novembre 2016 Ã 16:15
À : Jerome Tollet , "Frank Brockners (fbrockne)"
, "Maros Marsalek -X (mmarsale - PANTHEON TECHNOLOGIES at
Cisco)"
Cc : vpp-dev
Objet : Re: [vpp-dev] Interface bonding (bi
Quick FYI., atleast from our experience with Nfvi customers, where bonding is
enabled, the runtime changes aren't a requirement.
VPP bonding at startup has been good enough.
From: mailto:vpp-dev-boun...@lists.fd.io>> on
behalf of "Jerome Tollet (jtollet)"
mailto:jtol...@cisco.com>>
Date: Thurs
Frank,
I am not aware of customers changing their bonding configuration at runtime. Of
course, we could always imagine scenario but nothing concrete. It would be good
to get inputs from real users on this topic.
Anyway, my email below was just pointing design differences.
Jerome
De : "Frank Broc
Jerome,
quick question: In which case do you see customers changing the configuration
for link-aggregation/interface-bonding at runtime? I would typically see that
as an install-time feature, which is why even with OVS things are done through
the installer.
Thanks, Frank
From: Jerome Tollet (
Thanks! I had to do the following hacks to get DPDK .so files generated and
also the vpp libraries referring to them. Please let me know if it can
break something.
1. Enable RTE_TIMER (which is disabled by VPP)
2. Do a couple of symbol hacks in dpdk/drivers/net/bonding/rte_8023ad files
3. Change s
Frank, Maros,
One important difference I see between OVS-DPDK and VPP is that VPP Bonding
supports relies on DPDK. AFAIK, all DPDK parameters are set at startup and it
is then impossible to modify them.
On the other side, OVS-DPDK provides its own implementation of bonding and
LCAP. So it is pos
If I remember correctly I tested this only with manually built DPDK.
It was also working fine with .so files coming from ubuntu packages.
> On 9 Nov 2016, at 17:42, Nagaprabhanjan Bellaru wrote:
>
> Hi,
>
> I want to know if we can build dpdk as .so files? I tried enabling the
> CONFIG_RTE_S
12 matches
Mail list logo
