[vpp-dev] a bug at jvppgen @ stable18.10, java enum type's ordinal <-> value

2018-11-14 Thread wangchuan...@163.com
Hi all, The Flags show (0 1 2 3 4) by printf at 'vl_api_bridge_flags_t_handler' when calling java api(bridgeFlags). It seems to be that the ordinal of the java enum type was passed into the c function('vl_api_bridge_flags_t_handler'), not the value of the java enum type(1 2 4 8 16) . I c

Re: [vpp-dev] MemIf with non-VPP userspace appliation

2018-11-14 Thread satish . gundu
Thanks Damjan for the quick response. In fact, delighted to see a response from you ( all these days, I was watching your videos ). We have a non-VPP-App which acts as a control plane entity. This will  send  session installation onto data-plane-VPP. For this communication, if we use plain UDS c

Re: [vpp-dev] ip4-load-balance

2018-11-14 Thread Dave Barach via Lists.Fd.Io
+1, "vpp# show hardware" and "$ cat /proc/cpuinfo" to make sure that the selected cores are on the right NUMA socket... HTH... Dave -Original Message- From: vpp-dev@lists.fd.io On Behalf Of Vratko Polak -X (vrpolak - PANTHEON TECHNOLOGIES at Cisco) via Lists.Fd.Io Sent: Wednesday, Nove

Re: [vpp-dev] ip4-load-balance

2018-11-14 Thread Vratko Polak -X (vrpolak - PANTHEON TECHNOLOGIES at Cisco) via Lists.Fd.Io
> Any clues as to what might causing the delta? >> using FD.io VPP 18.07 If you are still using that, the performance might depend on the NUMA node used. There was a placement bug, and the fix [1] has been merged just before 18.10. Vratko. [1] https://gerrit.fd.io/r/15483 -Original Message-

Re: [vpp-dev] ip4-load-balance

2018-11-14 Thread Ray Kinsella
CSIT is measuring roughly 12mpps on HSW. When I measure with an equivalent system I get 10.5mpps on HSW. What I am finding is that DPDK is more efficient on CSIT HSW. CSIT Graph Node Clocks/Vector dpdk-input 6.07e1 TenGigabitEtherneta/0/0-tx 4.09e1

Re: [vpp-dev] API changes to trigger email

2018-11-14 Thread Vratko Polak -X (vrpolak - PANTHEON TECHNOLOGIES at Cisco) via Lists.Fd.Io
> email = f...@project1.io > email = f...@project2.io I think it would be easier to sent only one e-mail to a fd.io mailing list created specifically for announcing VPP api changes. Similarly to how we created csit-report [0] for announcing perform

Re: [vpp-dev] Multi threaded vpp

2018-11-14 Thread Damjan Marion via Lists.Fd.Io
> On 14 Nov 2018, at 14:31, ko wrote: > > Hi, > > > I'm trying to set up a multi-thread vpp middlebox with 2 NICs, dpdk+RSS. I > allocated 14 worker threads and defined 7 rx-queues per interface. I see them > with #show threads, and in $top, but how can i be sure that they are placed > cor

[vpp-dev] Multi threaded vpp

2018-11-14 Thread ko
Hi, I'm trying to set up a multi-thread vpp middlebox with 2 NICs, dpdk+RSS. I allocated 14 worker threads and defined 7 rx-queues per interface. I see them with #show threads, and in $top, but how can i be sure that they are placed correctly on my interfaces/queues as it looks that # sh dpd

Re: [vpp-dev] Regarding IP Fragmentation

2018-11-14 Thread Xuekun
Hi, Ole Is there a general rule to set the MTU in overlay networks to avoid fragmentation? Currently I saw the interface's MTU is 9000 in VPP by default. So can we assume the intermedia router/switch to the tunnel end point can handle the jumbo frame correctly? Thus even the mtu of tunnel end

Re: [vpp-dev] Regarding IP Fragmentation

2018-11-14 Thread Ole Troan
Prashant, > Imagine a usecase where I am getting IP packets on my graph node. > I encapsulate them into an outer IP and send them out. > So let's say in my example, I get IP1 and IP2. IP1 is max mtu size and > IP2 is a shorter one. Perhaps they themselves are part of a fragmented > flow. > I now e

Re: [vpp-dev] Regarding IP Fragmentation

2018-11-14 Thread Prashant Upadhyaya
Thanks Ole. Imagine a usecase where I am getting IP packets on my graph node. I encapsulate them into an outer IP and send them out. So let's say in my example, I get IP1 and IP2. IP1 is max mtu size and IP2 is a shorter one. Perhaps they themselves are part of a fragmented flow. I now encapsulate

[vpp-dev] Unit test failures in master

2018-11-14 Thread Juraj Linkeš
Hi vpp-devs, There are a couple of make test failures in master: *IPv4 Reassembly - https://jira.fd.io/browse/VPP-1475 o Just one test fails - random order reassembly, there are missing packets *L2 FIB - https://jira.fd.io/browse/VPP-1476 o Multiple failures - the first tes

Re: [vpp-dev] how to set cb for keepalive of vapi-connection @ 18.10

2018-11-14 Thread Klement Sekera via Lists.Fd.Io
it's shared memory, unless vpp dies there is no reason for the connection to go down. if required, I would suggest you send periodic control pings. Quoting wangchuan...@163.com (2018-11-14 02:12:07) >worried that the connection might break. > >-

Re: [vpp-dev] Regarding IP Fragmentation

2018-11-14 Thread Ole Troan
Prashant, > I have a usecase where I have two IP Datagrams, let's call them IP1, > IP2. Each contains UDP Payload. > IP1 size is bigger than mtu. > IP2 size is lesser than mtu. > > I ship these both one after the other in that order to ip4-lookup. > > IP1 gets fragmented, as expected, to IP1.1 a

[vpp-dev] how to gen new plugin‘s java api jar file @vpp stable/18.10

2018-11-14 Thread wangchuan...@163.com
hi all, I add 1 pluin "wcg", and the wcg.api.vapi.h was compiled out, but no jvpp-wcg.jar. Help please! DETAILS: 1、 I writed the extras/japi/java/jvpp-wcg/jvpp_hc.h and jvpp_hc.c refferring to gtpu plugin. 2、and add into extras/japi/java/Makefile.am: # # WCG Plugin # if ENABLE_WCG_PLUGIN

[vpp-dev] Regarding IP Fragmentation

2018-11-14 Thread Prashant Upadhyaya
Hi, I have a usecase where I have two IP Datagrams, let's call them IP1, IP2. Each contains UDP Payload. IP1 size is bigger than mtu. IP2 size is lesser than mtu. I ship these both one after the other in that order to ip4-lookup. IP1 gets fragmented, as expected, to IP1.1 and IP1.2 and the fragm

Re: [vpp-dev] how can i change interface name.

2018-11-14 Thread Damjan Marion via Lists.Fd.Io
-- Damjan > On 14 Nov 2018, at 09:54, abbas ali chezgi via Lists.Fd.Io > wrote: > > hi vpp developers, > > how can i change device name in vpp with vppctl or api? You cannot without modifying the code -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Re

[vpp-dev] how can i change interface name.

2018-11-14 Thread abbas ali chezgi via Lists.Fd.Io
hi vpp developers, how can i change device name in vpp with vppctl or api? thanks. -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#11238): https://lists.fd.io/g/vpp-dev/message/11238 Mute This Topic: https://lists.fd.io/mt/28133826/21656 Group Owner:

Re: [vpp-dev] ipsec support for chained buffers.

2018-11-14 Thread Xuekun
Thanks. So any plan to support IP fragmentation/reassembly in IPSec? Like fragmentation before encryption? (Sorry for off the email thread 😊 ) From: vpp-dev@lists.fd.io On Behalf Of Damjan Marion via Lists.Fd.Io Sent: Wednesday, November 14, 2018 4:12 PM To: Hu, Xuekun Cc: vpp-dev@lists.fd.io

Re: [vpp-dev] ip4-load-balance

2018-11-14 Thread Neale Ranns via Lists.Fd.Io
Hi Ray, By way of explanation.. without the interface the route is recursive, i.e. 20.20.20.20/24 is sent via 1.1.1.2. So the forwarding can be thought of as happening in two stages, firstly the lookup for the packet’s destination that matches 20.20.20.20/24 then the ‘lookup’ on the result of 1

Re: [vpp-dev] ipsec support for chained buffers.

2018-11-14 Thread Damjan Marion via Lists.Fd.Io
Chained buffers are used when packet size is bigger than buffer size (2K). Also in some cases chained buffers may be used when packets are replicated to avoid copy of the whole payload -- Damjan > On 14 Nov 2018, at 02:24, Xuekun wrote: > > What is the chained buffer used for? For IP frag

Re: [vpp-dev] MemIf with non-VPP userspace appliation

2018-11-14 Thread Damjan Marion via Lists.Fd.Io
What kind of communication exactly you need? Memif is universal packet shared memory interface, and can be used with non-vpp applications. we have lightweight library doing exactly that. See extras/libmemif in vpp repo -- Damjan > On 13 Nov 2018, at 11:52, satish.gu...@gmail.com wrote: >