[dpdk-users] How to test l3fwd?

Vincent Li vincent.mc.li at gmail.com
Wed Jul 27 22:42:43 CEST 2016
Previous message: [dpdk-users] How to test l3fwd?
Next message: [dpdk-users] pdump help
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
I figured it out too. just for the sake of future reference if anyone
running into same kind of issue.  I used DPDK pktgen as packet
generator and my set up as below:

syn flood flow: pktgen box Port0 ( random source ip, destination ip
2.1.1.1) -> DPDK Port0 (1.1.1.0) ..(l3fwd)..DPDK Port1 (2.1.1.0) ->
pktgen box linux driver nic (ip 2.1.1.1)

1,

pktgen box (used mTCP DPDK port so there is actual dpdk0 interface in
Linux,everything else is same as upstream DPDK, have or not have dpdk0
in linux does not matter here):

21: dpdk0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast
state UNKNOWN group default qlen 1000
    link/ether 00:1b:21:50:bc:38 brd ff:ff:ff:ff:ff:ff
    inet 10.0.0.126/24 brd 10.0.0.255 scope global dpdk0
       valid_lft forever preferred_lft forever
    inet6 fe80::21b:21ff:fe50:bc38/64 scope link
       valid_lft forever preferred_lft forever

8: p1p2: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc mq state UP
group default qlen 1000
    link/ether 00:1b:21:50:bc:39 brd ff:ff:ff:ff:ff:ff
    inet 2.1.1.1/24 scope global p1p2
       valid_lft forever preferred_lft forever
    inet6 fe80::21b:21ff:fe50:bc39/64 scope link
       valid_lft forever preferred_lft forever

relevant pktgen load test file config:

set ip dst 0 2.1.1.1
set mac 0 a0:36:9f:a1:4d:6c # <====this should be the l3fwd DPDK port 0 mac

dst.ip start 0 2.1.1.1
dst.ip min 0 2.1.1.1
dst.ip max 0 2.1.1.1
dst.ip inc 0 0.0.0.1


start pktgen

#./app/app/x86_64-native-linuxapp-gcc/pktgen -c 0x6ff  -- -m [2:2-15].0

Pktgen> load <the load test file>

Pktgen> start 0

Pktgen> page range
Pktgen> page main

- Ports 0-0 of 1   <Main Page>  Copyright (c) <2010-2016>, Intel Corporation
  Flags:Port    :   ------R--------:0
Link State      :        <UP-1000-FD>       ----TotalRate----
Pkts/s Max/Rx   :                 0/0                     0/0
       Max/Tx   :     1488234/1488196         1488200/1488196
MBits/s Rx/Tx   :               0/952                   0/952
Broadcast       :                   0


2

l3fwd dpdk

root at r210:/home/dpdk/mtcp/dpdk-16.04# ./tools/dpdk_nic_bind.py --status

Network devices using DPDK-compatible driver
============================================
0000:01:00.0 'I350 Gigabit Network Connection' drv=igb_uio unused=
0000:01:00.1 'I350 Gigabit Network Connection' drv=igb_uio unused=

start l3fwd

 #./build/l3fwd -c 0xf -- -p 0x3  --config="(0,0,0),(0,1,1),(1,0,2),(1,1,3)"

try more complete run example if above does not work

#./build/l3fwd -c 0xf -- -p 0x3 --eth-dest=<dpdk port 0>,<mac of dpdk
port 1> --eth-dest=<dpdk port 1>,<target dest mac> -P
--config="(0,0,0),(0,1,1),(1,0,2),(1,1,3)"
......................
L3FWD: LPM or EM none selected, default LPM on
Initializing port 0 ... Creating queues: nb_rxq=2 nb_txq=4...
Address:A0:36:9F:A1:4D:6C, Destination:02:00:00:00:00:00, Allocated
mbuf pool on socket 0
LPM: Adding route 0x01010100 / 24 (0)
LPM: Adding route 0x02010100 / 24 (1)
LPM: Adding route IPV6 / 48 (0)
LPM: Adding route IPV6 / 48 (1)
txq=0,0,0 PMD: eth_igb_tx_queue_setup(): sw_ring=0x7f21258be940
hw_ring=0x7f21258c0980 dma_addr=0x5a88c0980
txq=1,1,0 PMD: eth_igb_tx_queue_setup(): sw_ring=0x7f21258ac7c0
hw_ring=0x7f21258ae800 dma_addr=0x5a88ae800
txq=2,2,0 PMD: eth_igb_tx_queue_setup(): sw_ring=0x7f212589a640
hw_ring=0x7f212589c680 dma_addr=0x5a889c680
txq=3,3,0 PMD: eth_igb_tx_queue_setup(): sw_ring=0x7f21258884c0
hw_ring=0x7f212588a500 dma_addr=0x5a888a500

Initializing port 1 ... Creating queues: nb_rxq=2 nb_txq=4...
Address:A0:36:9F:A1:4D:6D, Destination:02:00:00:00:00:01, txq=0,0,0
PMD: eth_igb_tx_queue_setup(): sw_ring=0x7f2125876240
hw_ring=0x7f2125878280 dma_addr=0x5a8878280
txq=1,1,0 PMD: eth_igb_tx_queue_setup(): sw_ring=0x7f21258640c0
hw_ring=0x7f2125866100 dma_addr=0x5a8866100
txq=2,2,0 PMD: eth_igb_tx_queue_setup(): sw_ring=0x7f2125851f40
hw_ring=0x7f2125853f80 dma_addr=0x5a8853f80
txq=3,3,0 PMD: eth_igb_tx_queue_setup(): sw_ring=0x7f212583fdc0
hw_ring=0x7f2125841e00 dma_addr=0x5a8841e00


3,

pktgen box linux driver port

# tcpdump -nn -i p1p2 -c 10
tcpdump: verbose output suppressed, use -v or -vv for full protocol decode
listening on p1p2, link-type EN10MB (Ethernet), capture size 65535 bytes
13:37:07.166150 IP 216.145.81.59.26391 > 2.1.1.1.80: Flags [S], seq
3699016466:3699016472, win 8192, length 6
13:37:07.166152 IP 21.170.7.19.11344 > 2.1.1.1.80: Flags [S], seq
3254728108:3254728114, win 8192, length 6
13:37:07.166152 IP 62.211.26.25.5831 > 2.1.1.1.80: Flags [S], seq
2610626014:2610626020, win 8192, length 6
13:37:07.166153 IP 138.128.151.152.16368 > 2.1.1.1.80: Flags [S], seq
301380038:301380044, win 8192, length 6
13:37:07.166153 IP 254.40.13.171.30996 > 2.1.1.1.80: Flags [S], seq
1583422545:1583422551, win 8192, length 6
13:37:07.166154 IP 153.32.214.3.11340 > 2.1.1.1.80: Flags [S], seq
519927713:519927719, win 8192, length 6
13:37:07.166155 IP 167.247.215.107.21169 > 2.1.1.1.80: Flags [S], seq
3713824255:3713824261, win 8192, length 6
13:37:07.166155 IP 236.183.249.37.2446 > 2.1.1.1.80: Flags [S], seq
2407370042:2407370048, win 8192, length 6
13:37:07.166156 IP 64.57.152.132.5826 > 2.1.1.1.80: Flags [S], seq
1338723318:1338723324, win 8192, length 6
13:37:07.166156 IP 245.146.158.211.2438 > 2.1.1.1.80: Flags [S], seq
210449720:210449726, win 8192, length 6

On Wed, Jul 27, 2016 at 10:51 AM, Vincent Li <vincent.mc.li at gmail.com> wrote:
> could you please share how you figured out your problem?  it appears I
> am having same kind of  network link setup and  no packet being
> forwarded, there must be something I am missing, wondering if your
> solution would apply to my setup.
>
> Thanks!
>
> Vincent
>
> On Fri, Jul 22, 2016 at 6:18 PM, Charlie Li <charlie.li at gmail.com> wrote:
>> Never mind - I figured it out.
>>
>> On Wed, Jul 20, 2016 at 3:06 PM, Charlie Li <charlie.li at gmail.com> wrote:
>>
>>> I am also attaching the full logs from l3fwd and l2fwd.
>>>
>>> On Wed, Jul 20, 2016 at 3:02 PM, Charlie Li <charlie.li at gmail.com> wrote:
>>>
>>>> Hello,
>>>>
>>>> My setup is dpdk-2.2.0 on Fedora 23 Server with kernel 4.5.7.
>>>>
>>>> I have been testing L2 throughput with l2fwd and an Ixia traffic
>>>> generator. It works as expected.
>>>>
>>>> Command: ./l2fwd -c 0xf -n 4 -- -p 0x3
>>>> Ixia traffic: MAC (Ethernet frames)
>>>>
>>>>
>>>> Now I am moving to test L3 throughput with l3fwd, but cannot start
>>>> traffic from Ixia
>>>>
>>>> Command: ./l3fwd -c 0xf -n 4 -- -p 0x3 --config="(0,0,2)(1,0,3)"
>>>> Ixia traffic: IPv4 (IP packets)
>>>>
>>>> My question is:
>>>>
>>>> What are the IP addresses of the two ports?
>>>>
>>>> "LPM: Adding route 0x01010100 / 24 (0)
>>>> LPM: Adding route 0x02010100 / 24 (1)"
>>>>
>>>> Does it mean the IP addresses are 1.1.1.0 (netmask 255.255.255.0) for
>>>> port0 and 2.1.1.0 (netmask 255.255.255.0) for port1?
>>>>
>>>> I set up the following two flows, but Ixia complains "unreachable"
>>>>
>>>> Flow1: Ixia PortA (1.1.1.100) -> DPDK Port0 (1.1.1.0) .........(l3fwd)
>>>> ........ DPDK Port1 (2.1.1.0) -> Ixia PortB (2.1.1.100)
>>>>           Src IP: 1.1.1.100; Dst IP: 2.1.1.100; Gateway: 1.1.1.0
>>>>
>>>> Flow2: Ixia PortB (2.1.1.100) -> DPDK Port1 (2.1.1.0) .........(l3fwd)
>>>> ........ DPDK Port0 (1.1.1.0) -> Ixia PortA (1.1.1.100)
>>>>           Src IP: 2.1.1.100; Dst IP: 1.1.1.100; Gateway: 2.1.1.0
>>>>
>>>> Thanks,
>>>> Charlie
>>>>
>>>>
>>>
Previous message: [dpdk-users] How to test l3fwd?
Next message: [dpdk-users] pdump help
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
More information about the users mailing list