[dpdk-dev] testpmd crashes with Invalid NUMA socket, default to 0

[Kenvish Butani]

Thanks a lot Anatoly for your inputs !

*This got fixed by reserving total of "512" hugepages.*

Thanks a lot :)
Appreciate.

Thanks,
--Kenvish

On Mon, Oct 22, 2018 at 3:16 PM Burakov, Anatoly <anatoly.burakov at intel.com>
wrote:

> On 22-Oct-18 10:28 AM, Kenvish Butani wrote:
> > Thanks a lot for your prompt reply !
> >
> > JFYI, The invalid NUma socket was resolved by manually changing the
> > entry to 0
> >
> > echo 0 > /sys/bus/pci/devices/0000\:01\:00.0/uio/uio0/device/numa_node
> > echo 0 > /sys/bus/pci/devices/0000\:01\:00.1/uio/uio1/device/numa_node
> >
> > # ./testpmd-cc-on-local -c 0xF -n 1 --log-level=eal,8
> > EAL: Detected lcore 0 as core 0 on socket 0
> > EAL: Detected lcore 1 as core 0 on socket 1
> > EAL: Detected lcore 2 as core 1 on socket 0
> > EAL: Detected lcore 3 as core 1 on socket 1
> > EAL: Detected lcore 4 as core 2 on socket 0
> > EAL: Detected lcore 5 as core 2 on socket 1
> > EAigb_uio 0000:01:00.0: uio device registered with irq 44
> > L: Detected lcore 6 as core 8 on socket 0
> > EAL: Detected lcore 7 as core 8 on socket 1
> > EAL: Detected lcore 8 as core 9 on socket 0
> > EAL: Detected lcore 9 as core 9 on socket 1
> > EAL: Detected lcore 10 as core 10 on socket 0
> > EAL: Detected lcore 11 as core 10 on socket 1
> > EAL: Detected lcore 12 as core 0 on socket 0
> > EAL: Detected lcore 13 as core 0 on socket 1
> > EAL: Detected lcore 14 as core 1 on socket 0
> > EAL: Detected lcore 15 as core 1 on socket 1
> > EAL: Detected lcore 16 as core 2 on socket 0
> > EAL: Detected lcore 17 as core 2 on socket 1
> > EAL: Detected lcore 18 as core 8 on socket 0
> > EAL: Detected lcore 19 as core 8 on socket 1
> > EAL: Detected lcore 20 as core 9 on socket 0
> > EAL: Detected lcore 21 as core 9 on socket 1
> > EAL: Detected lcore 22 as core 10 on socket 0
> > EAL: Detected lcore 23 as core 10 on socket 1
> > EAL: Support maximum 128 logical core(s) by configuration.
> > EAL: Detected 24 lcore(s)
> > EAL: Detected 2 NUMA nodes
> > EAL: Multi-process socket /var/run/dpdk/rte/mp_socket
> > EAL: DPAA Bus not present. Skipping.
> > EAL: Module /sys/module/vfio_pci not found! error 2 (No such file or
> > directory)
> > EAL: VFIO PCI modules not loaded
> > EAL: Probing VFIO support...
> > EAL: Module /sys/module/vfio not found! error 2 (No such file or
> directory)
> > EAL: VFIO modules not loaded, skipping VFIO support...
> > EAL: Ask a virtual area of 0x2e000 bytes
> > EAL: Virtual area found at 0x7fdf72c49000 (size = 0x2e000)
> > EAL: Setting up physically contiguous memory...
> > EAL: Ask a virtual area of 0x61000 bytes
> > EAL: Virtual area found at 0x7fdf72be8000 (size = 0x61000)
> > EAL: Memseg list allocated: 0x800kB at socket 0
> > EAL: Ask a virtual area of 0x400000000 bytes
> > EAL: Virtual area found at 0x7fdb70c00000 (size = 0x400000000)
> > EAL: Ask a virtual area of 0x61000 bytes
> > EAL: Virtual area found at 0x7fdf72b87000 (size = 0x61000)
> > EAL: Memseg list allocated: 0x800kB at socket 0
> > EAL: Ask a virtual area of 0x400000000 bytes
> > EAL: Virtual area found at 0x7fd770a00000 (size = 0x400000000)
> > EAL: Ask a virtual area of 0x61000 bytes
> > EAL: Virtual area found at 0x7fdf72b26000 (size = 0x61000)
> > EAL: Memseg list allocated: 0x800kB at socket 0
> > EAL: Ask a virtual area of 0x400000000 bytes
> > EAL: Virtual area found at 0x7fd370800000 (size = 0x400000000)
> > EAL: Ask a virtual area of 0x61000 bytes
> > EAL: Virtual area found at 0x7fdf72ac5000 (size = 0x61000)
> > EAL: Memseg list allocated: 0x800kB at socket 0
> > EAL: Ask a virtual area of 0x400000000 bytes
> > EAL: Virtual area found at 0x7fcf70600000 (size = 0x400000000)
> > EAL: Ask a virtual area of 0x61000 bytes
> > EAL: Virtual area found at 0x7fdf70d30000 (size = 0x61000)
> > EAL: Memseg list allocated: 0x800kB at socket 1
> > EAL: Ask a virtual area of 0x400000000 bytes
> > EAL: Virtual area found at 0x7fcb70400000 (size = 0x400000000)
> > EAL: Ask a virtual area of 0x61000 bytes
> > EAL: Virtual area found at 0x7fdf70ccf000 (size = 0x61000)
> > EAL: Memseg list allocated: 0x800kB at socket 1
> > EAL: Ask a virtual area of 0x400000000 bytes
> > EAL: Virtual area found at 0x7fc770200000 (size = 0x400000000)
> > EAL: Ask a virtual area of 0x61000 bytes
> > EAL: Virtual area found at 0x7fdf70c6e000 (size = 0x61000)
> > EAL: Memseg list allocated: 0x800kB at socket 1
> > EAL: Ask a virtual area of 0x400000000 bytes
> > EAL: Virtual area found at 0x7fc370000000 (size = 0x400000000)
> > EAL: Ask a virtual area of 0x61000 bytes
> > EAL: Virtual area found at 0x7fdf70c0d000 (size = 0x61000)
> > EAL: Memseg list allocated: 0x800kB at socket 1
> > EAL: Ask a virtual area of 0x400000000 bytes
> > EAL: Virtual area found at 0x7fbf6fe00000 (size = 0x400000000)
> > EAL: TSC frequency is ~2394274 KHz
> > EAL: Master lcore 0 is ready (tid=72c7ec00;cpuset=[0])
> > EAL: lcore 1 is ready (tid=6f5fe700;cpuset=[1])
> > EAL: lcore 2 is ready (tid=6edfd700;cpuset=[2])
> > EAL: lcore 3 is ready (tid=6e5fc700;cpuset=[3])
> > EAL: Trying to obtain current memory policy.
> > EAL: Setting policy MPOL_PREFERRED for socket 0
> > EAL: Restoring previous memory policy: 0
> > EAL: request: mp_malloc_sync
> > EAL: Heap on socket 0 was expanded by 2MB
> > EAL: PCI device 0000:01:00.0 on NUMA socket 0
> > EAL:   probe driver: 8086:10a7 net_e1000_igb
> > EAL:   PCI memory mapped at 0x7fdf72aa5000
> > EAL:   PCI memory mapped at 0x7fdf72aa1igb_uio 0000:01:00.1: uio device
> > registered with irq 45
> > 000
> > EAL: PCI device 0000:01:00.1 on NUMA socket 0
> > EAL:   probe driver: 8086:10a7 net_e1000_igb
> > EAL:   PCI memory mapped at 0x7fdb70be0000
> > EAL:   PCI memory mapped at 0x7fdf72a9d000
> > EAL: Module /sys/module/vfio not found! error 2 (No such file or
> directory)
> > EAL: Trying to obtain current memory policy.
> > EAL: Setting policy MPOL_PREFERRED for socket 0
> > EAL: alloc_seg(): allocation happened on wrong socket (wanted 0, got 1)
> > EAL: attempted to allocate 45 segments, but only 31 were allocated
> > EAL: Restoring previous memory policy: 0
> > EAL: Trying to obtain current memory policy.
> > EAL: Setting policy MPOL_PREFERRED for socket 1
> > EAL: alloc_seg(): allocation happened on wrong socket (wanted 1, got 0)
> > EAL: attempted to allocate 45 segments, but only 32 were allocated
> > EAL: Restoring previous memory policy: 0
> > EAL: Error - exiting with code: 1
> >    Cause: rte_zmalloc(32 struct rte_port) failed
>
> This looks like you don't have enough memory. What probably happened is,
> you've reserved some huge pages but they were spread across sockets, so
> you don't have enough on any given socket, even though technically you
> may have enough memory as  far as total amount is concerned.
>
> My advice would be to increase the total number of reserved hugepages.
>
> >
> >
> > Is vfio driver mandatory ? i see few error messages related to it.
>
> These errors are harmless.
>
> >
> > Also, I see few error messages related to memory allocation, but I am
> > not sure how to fix this. Can you please help me out here.
> >
> > Thanks,
> > --Kenvish
>
> --
> Thanks,
> Anatoly
>