deploy scenario os-nosdn-ovs-ha by fuel, but instance can not reachable by ip. interface dpdk0 Cannot allocate memory.

asked 2016-10-12 08:57:29 -0700

wu.zhihui gravatar image

updated 2016-10-12 19:57:13 -0700

I installed OPNFV with scenario os-nosdn-ovs-ha on my pod. The version of OPNFV is a latest daily version based on fuel. The deployment was successful. But health check test case "Check network connectivity from instance with DPDK via floating IP" was failed. Because instance can not reachable by ip.

here are some info from my pod.

port was binded by dpdk.

 root@node-2:/usr/share/dpdk/tools# dpdk_nic_bind --status
 Network devices using DPDK-compatible driver
 0000:81:00.0 '82599 10 Gigabit Dual Port Backplane Connection' drv=igb_uio unused=

ovs bridge on compute node.

root@node-2:~# ovs-vsctl show
Bridge br-int
    fail_mode: secure
    Port int-br-prv
        Interface int-br-prv
            type: patch
            options: {peer=phy-br-prv}
    Port br-int
        Interface br-int
            type: internal
Bridge br-floating
    Port br-floating
        Interface br-floating
            type: internal
    Port "p_ff798dba-0"
        Interface "p_ff798dba-0"
            type: internal
Bridge br-prv
    Port "dpdk0"
        Interface "dpdk0"
            type: dpdk
            error: "could not open network device dpdk0 (Cannot allocate memory)"
    Port br-prv
        Interface br-prv
            type: internal
    Port phy-br-prv
        Interface phy-br-prv
            type: patch
            options: {peer=int-br-prv}
ovs_version: "2.5.90"

hugepage memory

root@node-2:~#  cat /proc/meminfo
MemTotal:       131645440 kB
MemFree:        125060932 kB
AnonHugePages:    749568 kB
HugePages_Total:    1152
HugePages_Free:     1024
HugePages_Rsvd:        0
HugePages_Surp:        0
Hugepagesize:       2048 kB

why device dpdk0 can not allocate memory? The value of MemFree and Hugepages_Free is not zero. Any ideas about this issue? Thanks in advance.

By the way, I found that this scenario os-nosdn-ovs-ha ci jenkins job on branch master was successful only on lf-pod2 and failed on the other pods.

edit retag flag offensive close merge delete


Even I am having same error with 'Openvswitch with NSH/DPDK plugin'. VMs do net get any IP address

siddharthgogar ( 2016-10-19 18:29:50 -0700 )edit