[dpdk-dev] running l2fwd with endless error message: PMD: Unhandled Msg 00000006
Hi, Recently I try to run l2fwd. When I try to ifconfig the VF created by igb_uio based PF in the VMs, The l2fwd will print out endless error as follow: PMD: Unhandled Msg 0006 PMD: Unhandled Msg 0008 --- And the VM will also print out endless error message as follow: --- [ 447.339765] ixgbevf: eth1: ixgbevf_watchdog_task: NIC Link is Up, 10 Gbps [ 447.748556] ixgbevf: eth1: ixgbevf_watchdog_task: NIC Link is Up, 10 Gbps [ 447.844914] ixgbevf: eth1: ixgbevf_watchdog_task: NIC Link is Up, 10 Gbps I have one Intel X520 with two ports. I bind the two PF to igb_uio and then create one VF per PF. I bind each VF to one VM and start the two VM in the same physical server. I run the l2fwd in the host to take over the PF. When I ifconfig in the VM then the above errors accur. I use DPDK 1.5.0r0 version in the host with 3.6.10-4.fc18.x86_64. In the virtual machine I use ixgbevf V2.11.3. Anyone has the some problems? Or I have any wrong step to run the l2fwd? Any advises are appreciated. Cheng Luo.
[dpdk-dev] DPDK failed to handle intialize VF
Hi, I am using DPDK for SRIOV. I have one Intel X520 with two PFs. After binding the two PFs to igb_uio, I create two VFs and assign them to a virtual machine. I found that to wake up VF, the VF will send some message to PF such as IXGBE_VF_SET_MACVLAN(0x06) and IXGBE_VF_API_NEGOTIATE(0x08) for the initialization. However, DPDK's PMD driver does not handle this messgae. In the source code /lib/librte_pmd_ixgbe/ixgbe_pf.c the function ixgbe_rcv_msg_from_vf only handle the following message: IXGBE_VF_SET_MAC_ADDR (0x02) IXGBE_VF_SET_MULTICAST (0x03) IXGBE_VF_SET_LPE (0x04) IXGBE_VF_SET_VLAN (0x05) and take other message as error message and take no operation. Therefore, if take DPDK to control the PF, I can not use VF with ixgbevf driver in the VMs. The PMD driver will endless print error message as follow: - PMD: Unhandled Msg 0006 PMD: Unhandled Msg 0008 --- And in the VMs, it also prints endless error message - [ 447.339765] ixgbevf: eth1: ixgbevf_watchdog_task: NIC Link is Up, 10 Gbps [ 447.748556] ixgbevf: eth1: ixgbevf_watchdog_task: NIC Link is Up, 10 Gbps [ 447.844914] ixgbevf: eth1: ixgbevf_watchdog_task: NIC Link is Up, 10 Gbps While I also read the code in ixgbe, and found that it can handle message 0x06 and 0x08. Is this a bug for DPDK ? Or any step is wrong for my configuration? I think DPDK should be ok to run in the host while with VF in the VM uses normal driver such as ixgbevf.
[dpdk-dev] fail to run with testpmd, EAL fail to bind socket
Dear all, I am a beginner with DPDK. I just install it in fedora18 with two X540 Enthercards. After compile it and run the testpmd I got the following message: [root at localhost test-pmd]# ./testpmd -c7 -n3 -- -i --nb-cores=2 --nb-ports=2 EAL: Detected lcore 0 as core 0 on socket 0 EAL: Detected lcore 1 as core 1 on socket 0 EAL: Detected lcore 2 as core 2 on socket 0 EAL: Setting up hugepage memory... EAL: Ask a virtual area of 0x2097152 bytes EAL: Virtual area found at 0x2a80 (size = 0x20) EAL: Ask a virtual area of 0x2143289344 bytes EAL: Virtual area found at 0x2aaa2aa0 (size = 0x7fc0) EAL: Ask a virtual area of 0x2097152 bytes EAL: Virtual area found at 0x7fc6aec0 (size = 0x20) EAL: Requesting 1024 pages of size 2MB from socket 0 EAL: TSC frequency is ~1795673 KHz EAL: Master core 0 is ready (tid=af35b880) EAL: Core 2 is ready (tid=ad7f1700) EAL: Core 1 is ready (tid=adff2700) EAL: PCI device :02:00.0 on NUMA socket -1 EAL: probe driver: 8086:1528 rte_ixgbe_pmd EAL: PCI memory mapped at 0x7fc6af128000 EAL: PCI memory mapped at 0x7fc6af361000 EAL: PCI device :02:00.1 on NUMA socket -1 EAL: probe driver: 8086:1528 rte_ixgbe_pmd EAL: PCI memory mapped at 0x7fc6aef28000 EAL: PCI memory mapped at 0x7fc6aef24000 Interactive-mode selected Configuring Port 0 (socket -1) Configuring Port 1 (socket -1) Checking link statuses... Port 0 Link Up - speed 1 Mbps - full-duplex Port 1 Link Up - speed 1 Mbps - full-duplex Done testpmd> Although I can get into the testpmd command mode, but it seems EAL fails to bind the socket on the PCI device. Therefore, when I run start tx_first and stp, no package forwarding as follow = testpmd> start tx_first io packet forwarding - CRC stripping disabled - packets/burst=16 nb forwarding cores=2 - nb forwarding ports=2 RX queues=1 - RX desc=128 - RX free threshold=0 RX threshold registers: pthresh=8 hthresh=8 wthresh=4 TX queues=1 - TX desc=512 - TX free threshold=0 TX threshold registers: pthresh=36 hthresh=0 wthresh=0 TX RS bit threshold=0 - TXQ flags=0x0 testpmd> stop Telling cores to stop... Waiting for lcores to finish... -- Forward statistics for port 0 -- RX-packets: 0 RX-dropped: 0 RX-total: 0 TX-packets: 16 TX-dropped: 0 TX-total: 16 -- Forward statistics for port 1 -- RX-packets: 0 RX-dropped: 0 RX-total: 0 TX-packets: 16 TX-dropped: 0 TX-total: 16 +++ Accumulated forward statistics for all ports+++ RX-packets: 0 RX-dropped: 0 RX-total: 0 TX-packets: 32 TX-dropped: 0 TX-total: 32 Done. Can anyone tell me how to fix this? Thank you very much.
[dpdk-dev] /sys/bus/pci/devices/[interface]/numa_node is -1
Hi, I try to run DPDMK testpmd and failed. I found that EAL will read /sys/bus/pci/devices/[interface]/numa_node file and initilize the PCI devices. My PC does not support NUMA, it has only one processor. However, initial value of numa_node of the device is -1. I found some suggestion that BIOS should support the proper ACPI features to detect PCI devices affinity to CPU. Otherwise, the numa_node will be -1. However, I can not find the proper option in the BIOS. Does anyone have the same problem or can give some suggestion? Thank you. Cheng Luo.
