Thomas,
If I use hugetlbfs the VM does not crash and it works as
expected. This is good enough and unblocks me. Thanks for the help.
Regards,
Srini
echo 1024 > /proc/sys/vm/nr_hugepages
mkdir /huge
mount -t hugetlbfs nodev /huge
rmmod virtio_net
./build/app/testpmd -c 0x3 -n 1 --use-device 0000:00:0a.0 -d
./librte_pmd_virtio.so -- --disable-hw-vlan --disable-rss -i --rxq=1
--txq=1 --rxd=256 --txd=256
.....
EAL: Skip lcore 54 (not detected)
EAL: Skip lcore 55 (not detected)
EAL: Skip lcore 56 (not detected)
EAL: Skip lcore 57 (not detected)
EAL: Skip lcore 58 (not detected)
EAL: Skip lcore 59 (not detected)
EAL: Skip lcore 60 (not detected)
EAL: Skip lcore 61 (not detected)
EAL: Skip lcore 62 (not detected)
EAL: Skip lcore 63 (not detected)
EAL: Setting up memory...
EAL: cannot open /proc/self/numa_maps, consider that all memory is in
socket_id 0
EAL: Ask a virtual area of 0x734003200 bytes
EAL: Virtual area found at 0x8a800000 (size = 0x2bc00000)
EAL: Ask a virtual area of 0x339738624 bytes
EAL: Virtual area found at 0x76000000 (size = 0x14400000)
EAL: Requesting 256 pages of size 4MB from socket 0
EAL: TSC frequency is ~2379255 KHz
EAL: WARNING: cpu flags constant_tsc=yes nonstop_tsc=no -> using
unreliable clock cycles !
librte_pmd_virtio version 1.1
Copyright 2013 6WIND S.A. provided without warranty.
EAL: Master core 0 is ready (tid=b7753800)
EAL: Core 1 is ready (tid=b6d1fb40)
EAL: PCI device 0000:00:0a.0 on NUMA socket -1
EAL: probe driver: 1af4:1000 rte_virtio_net_pmd
start = d060
end = d07f
Interactive-mode selected
Configuring Port 0 (socket -1)
PMD: rte_eth_dev_config_restore: port 0: MAC address array not supported
Checking link statuses...
Port 0 Link Up - speed 100 Mbps - full-duplex
Done
testpmd>
On Thu, Dec 5, 2013 at 9:00 PM, Thomas Monjalon
<thomas.monjalon at 6wind.com> wrote:
> 05/12/2013 16:19, Srinivasan J :
>> tried executing testpmd, but the entire VM crashed.
>
> Booting a VM, removing virtio_net module and following the doc should work:
> http://dpdk.org/doc/virtio-net-pmd
>
> If it doesn't work, we need some logs to understand your problem.
> --
> Thomas
