Re: [vpp-dev] N-queue node input

Ah, thank you. That seems much more logical. (Still familiarizing myself with tools in this toolbox. Haven't found the 10mm socket yet.) -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#12620): https://lists.fd.io/g/vpp-dev/message/12620 Mute This

Re: [EXT] [vpp-dev] 128 byte cache line support

From: Damjan Marion Sent: Friday, March 22, 2019 3:59 PM To: Nitin Saxena Cc: vpp-dev@lists.fd.io; Narayana Prasad Raju Athreya Subject: Re: [EXT] [vpp-dev] 128 byte cache line support On 22 Mar 2019, at 09:35, Nitin Saxena mailto:nsax...@marvell.com>> wrote: Hi Damjan, >> Can we

Re: [vpp-dev] Status of PPPoE Plugin

This part of the code mentioned let any MAC address with mcast bit through: > + /*if (!ethernet_address_cast (e0->dst_address) && > (hi->hw_address != 0) && > !eth_mac_equal ((u8 *) e0, hi->hw_address)) > error0 = ETHERNET_ERROR_L3_MAC_MISMATCH;

Re: [vpp-dev] Status of PPPoE Plugin

Thanks Damjan. Will look into it and find some way to resolve it. Thanks, Hongjun From: Damjan Marion [mailto:dmar...@me.com] Sent: Friday, March 22, 2019 3:41 PM To: Ni, Hongjun Cc: l...@cisco.com; vpp-dev@lists.fd.io Subject: Re: [vpp-dev] Status of PPPoE Plugin On 22 Mar 2019, at 07:34,

Re: [EXT] [vpp-dev] 128 byte cache line support

> On 22 Mar 2019, at 09:35, Nitin Saxena wrote: > > Hi Damjan, > > >> Can we conclude that there is no technical arguments? > > On technical aspects: > Changing VLIB structure to 128 byte from current 256 byte (for our target) > In case of forwarding we only use single Dcache line till

[vpp-dev] DHCPv6 proxy not working over VLAN interface

Hi all, I am trying to assign v6 address to clients using DHCP PD. I have ISC Bind configured to provide v6 prefixes and configured dhcpv6 proxy using the following command. vppctl set dhcpv6 proxy server 2001:xxx::10d::1 src-address 2001:xxx::10d::700 It is working for clients from non

Re: [EXT] [vpp-dev] 128 byte cache line support

Hi Damjan, >> Can we conclude that there is no technical arguments? On technical aspects: 1. Changing VLIB structure to 128 byte from current 256 byte (for our target) * In case of forwarding we only use single Dcache line till ipv4-input (because of packet parsing info in second 64B

Re: [EXT] [vpp-dev] 128 byte cache line support

— Damjan > On 22 Mar 2019, at 01:37, Nitin Saxena wrote: > > > From: Damjan Marion > Sent: Friday, March 22, 2019 12:35 AM > To: Nitin Saxena > Cc: vpp-dev@lists.fd.io; Narayana Prasad Raju Athreya > Subject: Re: [EXT] [vpp-dev] 128 byte cache line support > > > >> On 21 Mar 2019, at

Re: [vpp-dev] Status of PPPoE Plugin

> On 22 Mar 2019, at 07:34, Ni, Hongjun wrote: > > Hi John, > > For first PADI packet, its destination MAC is broadcast address. > Not sure it is accepted by ethernet-input node? Sure it does, otherwise arp, dhcp, ... will not work. > Do we need special process to handle it? > 5.1 The

Re: [vpp-dev] Status of PPPoE Plugin

Hi John, For first PADI packet, its destination MAC is broadcast address. Not sure it is accepted by ethernet-input node? Do we need special process to handle it? 5.1 The PPPoE Active Discovery Initiation (PADI) packet The Host sends the PADI