Re: [dpdk-users] DPDK KNI Issue

["Pattan, Reshma" <reshma.pattan@intel.com>]

Hi Ilir,

Can you reiterate the test as suggested below. Because during KNI testing I observed one weird behavior that, If we keep running tcpdump on KNI device and try to terminate KNI application with cntl+c/ or by other means it doesn’t get terminated. In such case  we need to kill tcpdump first then KNI application. After doing this, for next round dpdk bounded ports are not receiving any traffic. So I suggest you to do below steps.

a)terminate tcpdump and KNI application
b)unbind DPDK ports from igb_uio.
c)bind back DPDK ports to igb_uio.
d)run test_pmd application and make sure traffic is been received on the ports.  If traffic is received ,
e)then run KNI application
d)run tcpdump on KNI device

Let me know how things goes.

Thanks,
Reshma
From: Ilir Iljazi [mailto:iljazi@gmail.com]
Sent: Friday, December 4, 2015 5:54 PM
To: Pattan, Reshma
Subject: Re: [dpdk-users] DPDK KNI Issue

Hi thanks again. I'm using the example application to create the interface:

./examples/kni/build/app/kni -n 4 -c 0xff -- -p 0x1 -P --config="(0,5,7)" &

The interface is created and I'm able to configure it just like any other linux interface via IP/subnet default route etc. I haven't written my application yet because I can't get basic functionality working such as connect and data xfer. Hence, the debug isn't expected to help since the routines posted are not called. Regarding the proc file system monitoring, same answer there is no application yet.

Thanks,
Ilir

On Fri, Dec 4, 2015 at 11:13 AM, Pattan, Reshma <reshma.pattan@intel.com<mailto:reshma.pattan@intel.com>> wrote:
Hi,

Are you using dpdk kni sample application? (Or) you have your own module with KNI implementation? If so please share the code will look into.

Can you also check by adding enough logging  to below functions .
a)kni_net_rx_normal and other kni_next_rx_* functions if they are invoked  by DPDK to push packets to TCPIP stack.
b)kni_net_tx being invoked by TCP/IP stack to push packets to DPDK.

Also, you can use app/proc_info app from DPDK  2.1 release to check packet statistics of DPDK ports, to see what is happening.

Thanks,
Reshma

> -----Original Message-----
> From: users [mailto:users-bounces@dpdk.org<mailto:users-bounces@dpdk.org>] On Behalf Of Pattan, Reshma
> Sent: Friday, December 4, 2015 12:28 PM
> To: Ilir Iljazi; users@dpdk.org<mailto:users@dpdk.org>
> Subject: Re: [dpdk-users] DPDK KNI Issue
>
> Hi,
>
> I had tried KNI ping testing on fedora ,  DPDK2.2 and using one loopback
> connection, it works fine and I tried without steps 9 and 10.
> I am not sure why steps 9 & 10 are needed in your case, but you can try without
> those 2 steps and see the results.
> Also, after you start the ping, make sure there is no core dump in dmesg for KNI
> module.
> If ur running tcpdump with icmp filter try running without filter and first see if
> ARP packets are reaching to KNI or not.
> Also can you check if packet drop stats of kni iface increasing?
>
> Thanks,
> Reshma
>
> > -----Original Message-----
> > From: users [mailto:users-bounces@dpdk.org<mailto:users-bounces@dpdk.org>] On Behalf Of Ilir Iljazi
> > Sent: Thursday, December 3, 2015 9:55 PM
> > To: users@dpdk.org<mailto:users@dpdk.org>
> > Subject: [dpdk-users] DPDK KNI Issue
> >
> > Hi,
> > I have been having an issue with dpdk kni whereby I cant send and
> > receive packets from the kni interface. I spent about a week trying to
> > figure it out the issue myself to no avail. Although I did find
> > articles with a similar signature to mine none of the proposed solutions helped
> solve the problem.
> >
> > Environment:
> > Ubuntu Server 14.04
> > DPDK Package 2.1.0 (Latest)
> > Network Card: (10Gbe ixgbe driver)
> >
> > 06:00.0 Ethernet controller: Intel Corporation 82599ES 10-Gigabit
> > SFI/SFP+ Network Connection
> > 06:00.1 Ethernet controller: Intel Corporation 82599ES 10-Gigabit
> > SFI/SFP+ Network Connection
> >
> > 06.00.0 (port 0 connected to switch)
> > 06:00.1 (port 1 not connected to switch)
> >
> > Configuration:
> > 1.) DPDK built without issue
> > 2.) Modules Loaded:
> >
> > insmod $RTE_TARGET/kmod/igb_uio.ko
> > insmod $RTE_TARGET/kmod/rte_kni.ko kthread_mode=multiple
> >
> >
> > 3.) Reserved Huge Pages:
> >
> > echo 4096 >
> > /sys/devices/system/node/node0/hugepages/hugepages-
> 2048kB/nr_hugepages
> > echo 4096 >
> > /sys/devices/system/node/node1/hugepages/hugepages-
> 2048kB/nr_hugepages
> >
> >
> > 4.) Mounted huge page partition
> >
> > echo ">>> Mounting huge page partition"
> > mkdir -p /mnt/huge
> > mount -t hugetlbfs nodev /mnt/huge
> >
> >
> > 5.) Interfaces 06:00.0/1 bound to igb uio module (option 19 on setup)
> >
> > Network devices using DPDK-compatible driver
> > ============================================
> > 0000:06:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection'
> > drv=igb_uio unused=
> > 0000:06:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection'
> > drv=igb_uio unused=
> >
> >
> > 6.) Started kni test application:
> >
> > Command: ./examples/kni/build/app/kni -n 4 -c 0xff -- -p 0x1 -P --
> > config="(0,5,7)" &
> >
> > Output:
> >
> > EAL: PCI device 0000:06:00.0 on NUMA socket -1
> > EAL:   probe driver: 8086:10fb rte_ixgbe_pmd
> > EAL:   PCI memory mapped at 0x7fcda5c00000
> > EAL:   PCI memory mapped at 0x7fcda5c80000
> > PMD: eth_ixgbe_dev_init(): MAC: 2, PHY: 18, SFP+: 5
> > PMD: eth_ixgbe_dev_init(): port 0 vendorID=0x8086 deviceID=0x10fb
> > EAL: PCI device 0000:06:00.1 on NUMA socket -1
> > EAL:   probe driver: 8086:10fb rte_ixgbe_pmd
> > EAL:   PCI memory mapped at 0x7fcda5c84000
> > EAL:   PCI memory mapped at 0x7fcda5d04000
> > PMD: eth_ixgbe_dev_init(): MAC: 2, PHY: 18, SFP+: 6
> > PMD: eth_ixgbe_dev_init(): port 1 vendorID=0x8086 deviceID=0x10fb
> > APP: Port ID: 0
> > APP: Rx lcore ID: 5, Tx lcore ID: 7
> > APP: Initialising port 0 ...
> > PMD: ixgbe_dev_rx_queue_setup(): sw_ring=0x7fcd5c1adcc0
> > sw_sc_ring=0x7fcd5c1ad780 hw_ring=0x7fcd5c1ae200
> dma_addr=0xe5b1ae200
> > PMD: ixgbe_dev_tx_queue_setup(): sw_ring=0x7fcd5c19b5c0
> > hw_ring=0x7fcd5c19d600 dma_addr=0xe5b19d600
> > PMD: ixgbe_set_tx_function(): Using simple tx code path
> > PMD: ixgbe_set_tx_function(): Vector tx enabled.
> > PMD: ixgbe_set_rx_function(): Vector rx enabled, please make sure RX
> > burst size no less than 32.
> > KNI: pci: 06:00:00  8086:10fb
> >
> >
> > Checking link status
> > done
> > Port 0 Link Up - speed 10000 Mbps - full-duplex
> > APP: Lcore 1 has nothing to do
> > APP: Lcore 2 has nothing to do
> > APP: Lcore 3 has nothing to do
> > APP: Lcore 4 has nothing to do
> > APP: Lcore 5 is reading from port 0
> > APP: Lcore 6 has nothing to do
> > APP: Lcore 7 is writing to port 0
> > APP: Lcore 0 has nothing to do
> >
> >
> > 7.) KNI interface configured and brought up:
> >
> > root@l3sys2-acc2-3329:~/dpdk-2.1.0#<mailto:root@l3sys2-acc2-3329:~/dpdk-2.1.0#> ifconfig vEth0 192.168.13.95
> > netmask
> > 255.255.248.0 up
> > APP: Configure network interface of 0 up
> > PMD: ixgbe_set_rx_function(): Vector rx enabled, please make sure RX
> > burst size no less than 32.
> >
> > root@l3sys2-acc2-3329:~/dpdk-2.1.0#<mailto:root@l3sys2-acc2-3329:~/dpdk-2.1.0#> ifconfig vEth0
> >
> > vEth0     Link encap:Ethernet  HWaddr 90:e2:ba:55:fd:c4
> >           inet addr:192.168.13.95  Bcast:192.168.15.255  Mask:255.255.248.0
> >           inet6 addr: fe80::92e2:baff:fe55:fdc4/64 Scope:Link
> >           UP BROADCAST RUNNING MULTICAST  MTU:1500  Metric:1
> >           RX packets:0 errors:0 dropped:0 overruns:0 frame:0
> >           TX packets:0 errors:0 dropped:8 overruns:0 carrier:0
> >           collisions:0 txqueuelen:1000
> >           RX bytes:0 (0.0 B)  TX bytes:0 (0.0 B)
> >
> > Note also that dmesg is clean not pointing to any issues:
> > [ 1770.113952] KNI: /dev/kni opened
> > [ 1770.561957] KNI: Creating kni...
> > [ 1770.561973] KNI: tx_phys:      0x0000000e5b1ca9c0, tx_q addr:
> > 0xffff880e5b1ca9c0
> > [ 1770.561974] KNI: rx_phys:      0x0000000e5b1c8940, rx_q addr:
> > 0xffff880e5b1c8940
> > [ 1770.561975] KNI: alloc_phys:   0x0000000e5b1c68c0, alloc_q addr:
> > 0xffff880e5b1c68c0
> > [ 1770.561976] KNI: free_phys:    0x0000000e5b1c4840, free_q addr:
> > 0xffff880e5b1c4840
> > [ 1770.561977] KNI: req_phys:     0x0000000e5b1c27c0, req_q addr:
> > 0xffff880e5b1c27c0
> > [ 1770.561978] KNI: resp_phys:    0x0000000e5b1c0740, resp_q addr:
> > 0xffff880e5b1c0740
> > [ 1770.561979] KNI: mbuf_phys:    0x000000006727dec0, mbuf_kva:
> > 0xffff88006727dec0
> > [ 1770.561980] KNI: mbuf_va:      0x00007fcd8627dec0
> > [ 1770.561981] KNI: mbuf_size:    2048
> > [ 1770.561987] KNI: pci_bus: 06:00:00
> > [ 1770.599689] igb_uio 0000:06:00.0: (PCI Express:5.0GT/s:Width x8) [
> > 1770.599691] 90:e2:ba:55:fd:c4 [ 1770.599777] igb_uio 0000:06:00.0
> > (unnamed
> > net_device) (uninitialized):
> > MAC: 2, PHY: 0, PBA No: E68793-006
> > [ 1770.599779] igb_uio 0000:06:00.0 (unnamed net_device) (uninitialized):
> > Enabled Features: RxQ: 1 TxQ: 1
> > [ 1770.599790] igb_uio 0000:06:00.0 (unnamed net_device) (uninitialized):
> > Intel(R) 10 Gigabit Network Connection
> >
> >
> > 8.) ethtool vEth0 link is detected:
> >
> > root@l3sys2-acc2-3329:~/dpdk-2.1.0#<mailto:root@l3sys2-acc2-3329:~/dpdk-2.1.0#> ethtool vEth0 Settings for vEth0:
> > Supported ports: [ FIBRE ]
> > Supported link modes:   10000baseT/Full
> > Supported pause frame use: No
> > Supports auto-negotiation: No
> > Advertised link modes:  10000baseT/Full Advertised pause frame use: No
> > Advertised auto-negotiation: No
> > Speed: 10000Mb/s
> > Duplex: Full
> > Port: Other
> > PHYAD: 0
> > Transceiver: external
> > Auto-negotiation: off
> > Supports Wake-on: d
> > Wake-on: d
> > Current message level: 0x00000007 (7)
> >       drv probe link
> > Link detected: yes
> >
> >
> > 9.) kernel started with: iommu=pt intel_iommu=on
> >
> > GRUB_CMDLINE_LINUX="iommu=pt intel_iommu=on console=tty1
> > console=ttyS1,115200n8"
> >
> >
> > 10.) Disabled virtualization in BIOS per forum recommendation
> >
> >
> > Situation:
> > Despite doing everything seemingly correct I cant ssh or ping to and
> > from this interface. I tried starting tcpdump on the interface but didn't notice
> any traffic.
> > I'm not sure what I'm doing wrong here, if I could get some support
> > I'd appreciate it. I can provide additional details from the system if needed.
> >
> > Thanks!