[dpdk-dev] [PATCH v2 3/6] mk: Ensure correct detection of SSE4.2 on FreeBSD

Add a special case to the native target makefile, where we check if -march=native shows SSE4.2 support. If it does not, then not everything may build, so we check if the hardware supports SSE4.2, and use a corei7 target explicitly to get the SSE4.2 support. New in V2: * Re-enable ACL library for F

[dpdk-dev] Access to open flow table using DPDK libraries

Hi, > > I would like to know is there a way for the application using DPDK > libraries to access the openflow table in the SDN controller . Also please > let me know is there an API available for this access. > > Regards > Shankari.V >

[dpdk-dev] [PATCH 5/6] mk: add toolchain for clang and linuxapp target

> -Original Message- > From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com] > Sent: Thursday, July 17, 2014 3:23 AM > To: Richardson, Bruce > Cc: dev at dpdk.org > Subject: Re: [dpdk-dev] [PATCH 5/6] mk: add toolchain for clang and linuxapp > target > > 2014-07-08 00:36, Bruce Richa

[dpdk-dev] Access to open flow table using DPDK libraries

-Original Message- From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Shankari Vaidyalingam Sent: Thursday, July 17, 2014 9:15 AM To: dev at dpdk.org Subject: Re: [dpdk-dev] Access to open flow table using DPDK libraries Hi, > > I would like to know is there a way for the application usi

[dpdk-dev] [PATCH v2] kni: use netif_rx instead of netif_receive_skb in which ocurr deallock on userpace contex

On Thu, Jul 17, 2014 at 3:02 PM, Thomas Monjalon wrote: > Hi, > > 2014-07-11 23:37, Yao-Po Wang: >> Per netif_receive_skb function description, it may only be called from >> interrupt contex, but KNI is run on kthread that like as user-space >> contex. It may occur deallock, if netif_receive_skb c

[dpdk-dev] [PATCH 3/6] mk: Ensure correct detection of SSE4.2 on FreeBSD

On Thu, Jul 17, 2014 at 11:35:46AM +0200, Thomas Monjalon wrote: > Hi Bruce, > > 2014-07-08 00:36, Bruce Richardson: > > Add a special case to the native target makefile, where we check if > > -march=native shows SSE4.2 support. If it does not, then not everything may > > build, so we check if the

[dpdk-dev] DPDK causing Soft lockup on XEN ?

Hi, Maybe this is a config issue.. need some help. I have a situation where xen is reporting a cpu is stuck after the ip_fragmentation example hangs setting up memory. Sys log: Message from syslogd at port22 at Jul 17 14:27:32 ... kernel:[180294.724037] BUG: soft lockup - CPU#7 stuck for 22s! [

[dpdk-dev] [PATCH 3/6] mk: Ensure correct detection of SSE4.2 on FreeBSD

> -Original Message- > From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com] > Sent: Thursday, July 17, 2014 3:26 AM > To: Richardson, Bruce > Cc: dev at dpdk.org > Subject: Re: [dpdk-dev] [PATCH 3/6] mk: Ensure correct detection of SSE4.2 on > FreeBSD > > 2014-07-08 00:36, Bruce Ric

[dpdk-dev] Problem with popcnt in librte_acl and ixgbe vector code

I noticed a build issue trying to build 1.7.0 on a (old) laptop of mine. Problem is the same with either 'default' or 'native' machine. [grrr at glop dpdk]$ make install T=x86_64-native-linuxapp-gcc V=99 [...] == Build lib/librte_pmd_ixgbe gcc -Wp,-MD,./.ixgbe_rxtx_vec.o.d.tmp -m64 -pthread -m

[dpdk-dev] [PATCH v2] kni: use netif_rx instead of netif_receive_skb in which ocurr deallock on userpace contex

Hi, 2014-07-11 23:37, Yao-Po Wang: > Per netif_receive_skb function description, it may only be called from > interrupt contex, but KNI is run on kthread that like as user-space > contex. It may occur deallock, if netif_receive_skb called from kthread, > so it should be repleaced by netif_rx or ad

[dpdk-dev] Setup script for xen ?

I'm back on it.. Thanks for the help.. testpmd works as it should, it reports packets sent and received on two ports. I'm still having issues with the other examples. testpmd works cmdline works helloworld works All other programs in the examples directory hang in a similar way setting up memo

[dpdk-dev] [PATCH 3/6] mk: Ensure correct detection of SSE4.2 on FreeBSD

2014-07-08 00:36, Bruce Richardson: > Add a special case to the native target makefile, where we check if > -march=native shows SSE4.2 support. If it does not, then not everything may > build, so we check if the hardware supports SSE4.2, and use a corei7 target > explicitly to get the SSE4.2 suppor

[dpdk-dev] [PATCH 5/6] mk: add toolchain for clang and linuxapp target

2014-07-08 00:36, Bruce Richardson: > --- /dev/null > +++ b/mk/toolchain/clang/rte.vars.mk [...] > +ifeq ($(KERNELRELEASE),) > +CC= $(CROSS)clang > +else > +CC= $(CROSS)gcc > +endif Why not use clang for FreeBSD modules? This page seems to encourage clang: https://wiki.free

[dpdk-dev] phantom old packets received in new mbuf

Just to update, root cause is found... the problem is not at the dpdk rx side but at the transmit side (using sendto app). when transmitting through NICs models 82575 or 82576 (sendto app), the receiver reads it well using the DPDK rx program. however when using NIC 82541gi as transmitter (sendto

[dpdk-dev] [PATCH 3/6] mk: Ensure correct detection of SSE4.2 on FreeBSD

Hi Bruce, 2014-07-08 00:36, Bruce Richardson: > Add a special case to the native target makefile, where we check if > -march=native shows SSE4.2 support. If it does not, then not everything may > build, so we check if the hardware supports SSE4.2, and use a corei7 target > explicitly to get the SS

[dpdk-dev] MEMNIC error at EAL : [undefined symbol :per_lcore__lcore_id]

Hi, 2014-07-17 07:29, Srinivas Reddi: > I compiled my testapp using this command > > cc testapp.c -lrte_eal -lrte_mbuf -lrte_cmdline -lrte_timer -lrte_mempool > -lrte_pmd_ring -lethdev -lrte_malloc -ldl -lpthread -lrte_ring > -I/home/utils/dpdk-1.7.0/x86_64-native-linuxapp-gcc/include > -L/ho

[dpdk-dev] MEMNIC error at EAL : [undefined symbol :per_lcore__lcore_id]

Hi, I compiled my testapp using this command cc testapp.c -lrte_eal -lrte_mbuf -lrte_cmdline -lrte_timer -lrte_mempool -lrte_pmd_ring -lethdev -lrte_malloc -ldl -lpthread -lrte_ring -I/home/utils/dpdk-1.7.0/x86_64-native-linuxapp-gcc/include -L/home/utils/dpdk-1.7.0/x86_64-native-linuxapp

[dpdk-dev] MEMNIC error at EAL : [underined symbol : per_lcore__lcore_id]

Hi , Trying to write a test app for MEMNIC ... At the EAL init I got the error while loading the memnic driver .. .. EAL: /usr/local/lib/librte_pmd_memnic_copy.so: undefined symbol: per_lcore__lcore_id EAL arguments are : ./my_memnic_app --no-hpet -c 7 -n 4 --porc-type=auto -d /u