Re: [vpp-dev] the source_and_port_range_check and the URPF support ipv6?

2018-04-12 Thread Neale Ranns
Hi Xyxue, There’s no plan to support IPv6 uRPF. However, a simple cut-n-paste of the IPv4 code (ip/ip4_source_check.c) and some refactoring of common parts would be the way to go. Regards, neale From: on behalf of xyxue Date: Thursday, 12 April 2018 at 02:49 To: otroan Cc: vpp-dev Subject

Re: [vpp-dev] [csit-dev] VPP 18.04-RC2 release milestone

2018-04-12 Thread Dave Wallace
+vpp-dev Forwarded Message Subject:Re: [csit-dev] VPP 18.04-RC2 release milestone Date: Thu, 12 Apr 2018 10:10:20 -0400 From: Dave Wallace To: csit-...@lists.fd.io Chris, As discussed at yesterday's CSIT weekly meeting, the CSIT team is working to produce a

Re: [vpp-dev] [csit-dev] VPP 18.04-RC2 release milestone

2018-04-12 Thread Chris Luke
Thanks Dave, I look forward to it. Chris. From: csit-...@lists.fd.io On Behalf Of Dave Wallace Sent: Thursday, April 12, 2018 10:10 To: csit-...@lists.fd.io Subject: Re: [csit-dev] VPP 18.04-RC2 release milestone Chris, As discussed at yesterday's CSIT weekly meeting, the CSIT team is working

[vpp-dev] need help regarding ipsec performance improvement

2018-04-12 Thread Meng Maggie
Hi all, I am trying to do some ipsec performance testing on vpp 17.10 (DPDK-17.08). I was getting optimum performance with vector size 64. following is the snippet of show run command output --- TenGigabitEthernet3/0/1-output active 21070 1348480

[vpp-dev] need help regarding ipsec performance improvement

2018-04-12 Thread Meng Maggie
Hi all, I am trying to do some ipsec performance testing on vpp 17.10 (DPDK-17.08). I was getting optimum performance with vector size 64. following is the snippet of show run command output --- TenGigabitEthernet3/0/1-output active 21070 1348480

[vpp-dev] vec_new() vs. vec_validate()

2018-04-12 Thread Bly, Mike
Hello, After some digging, near as I can tell, for a new pointer to a new entity, it would seem that vec_new() is pretty much providing the same results as vec_validate(), albeit, with one less memset(bob, o, sizeof(*bob)) being performed. However, I see a 10:1 usage (preference?) of vec_valida

Re: [vpp-dev] vec_new() vs. vec_validate()

2018-04-12 Thread Chris Luke
Vec_new always allocates storage, vec_validate ensures that an existing allocation is at least a certain size, or create a new one if the pointer is NULL. The latter is typically used when the storage will be used as an array and you want to make sure it's large enough to store element N. See

Re: [vpp-dev] vec_new() vs. vec_validate()

2018-04-12 Thread John Lo (loj)
As noted by Billy, vec_validate would call vec_resize and then call memset() to clear unused area to 0. This call is required to make sure, if vector is expanded by vec_resize without having to allocate new memory, any unused memory with stale content is cleared. For new vectors, calling vect_