https://bugs.dpdk.org/show_bug.cgi?id=193
Bug ID: 193
Summary: symmetric_mp example application crashes for Amazon
ENA in multiple process mode
Product: DPDK
Version: 18.11
Hardware: x86
OS: Linux
Status: CONFIRMED
Severity: critical
Priority: Normal
Component: ethdev
Assignee: dev@dpdk.org
Reporter: s...@paloaltonetworks.com
Target Milestone: ---
I have a Amazon AWS vm c5.xLarge instance with 3 ENA interface attached.
The first is management interface and the other two interfaces are data
interfaces.
I binded the data interfaces with igb_uio driver and enabled huge page as well.
I want to run symmetric_mp example with one as primary and the other as
secondary following this document
https://doc.dpdk.org/guides/sample_app_ug/multi_process.html.
When I launch the primary process, it is ok. However, as soon as I launch the
secondary process, both primary and secondary processes crashes.
Primary process:
(gdb) r -l 1 -n 4 --proc-type=auto -- -p 3 --num-procs=4 --proc-id=0
Starting program: /root/symmetric_mp -l 1 -n 4 --proc-type=auto -- -p 3
--num-procs=4 --proc-id=0
[Thread debugging using libthread_db enabled]
Using host libthread_db library "/lib64/libthread_db.so.1".
EAL: Detected 4 lcore(s)
EAL: Detected 1 NUMA nodes
EAL: Auto-detected process type: PRIMARY
[New Thread 0x7ffff6ed8700 (LWP 5663)]
EAL: Multi-process socket /var/run/dpdk/rte/mp_socket
[New Thread 0x7ffff66d7700 (LWP 5664)]
EAL: No free hugepages reported in hugepages-1048576kB
EAL: Probing VFIO support...
EAL: PCI device 0000:00:05.0 on NUMA socket -1
EAL: Invalid NUMA socket, default to 0
EAL: probe driver: 1d0f:ec20 net_ena
EAL: PCI device 0000:00:06.0 on NUMA socket -1
EAL: Invalid NUMA socket, default to 0
EAL: probe driver: 1d0f:ec20 net_ena
EAL: PCI device 0000:00:07.0 on NUMA socket -1
EAL: Invalid NUMA socket, default to 0
EAL: probe driver: 1d0f:ec20 net_ena
# Initialising port 0... # Initialising port 1...
Checking link statusdone
Port0 Link Up. Speed 0 Mbps - full-duplex
Port1 Link Up. Speed 0 Mbps - full-duplex
APP: Finished Process Init.
Lcore 1 using ports 0 1
lcore 1 using queue 0 of each port
Thread 1 "symmetric_mp" received signal SIGSEGV, Segmentation fault.
0x0000000000705155 in ena_com_rx_pkt ()
Secondary process:
(gdb) r -l 2 -n 4 --proc-type=auto -- -p 3 --num-procs=4 --proc-id=1
Starting program: /root/symmetric_mp -l 2 -n 4 --proc-type=auto -- -p 3
--num-procs=4 --proc-id=1
[Thread debugging using libthread_db enabled]
Using host libthread_db library "/lib64/libthread_db.so.1".
EAL: Detected 4 lcore(s)
EAL: Detected 1 NUMA nodes
EAL: Auto-detected process type: SECONDARY
[New Thread 0x7ffff6ed8700 (LWP 5777)]
EAL: Multi-process socket /var/run/dpdk/rte/mp_socket_5773_105ae7c1b74
[New Thread 0x7ffff66d7700 (LWP 5778)]
EAL: Probing VFIO support...
EAL: PCI device 0000:00:05.0 on NUMA socket -1
EAL: Invalid NUMA socket, default to 0
EAL: probe driver: 1d0f:ec20 net_ena
EAL: PCI device 0000:00:06.0 on NUMA socket -1
EAL: Invalid NUMA socket, default to 0
EAL: probe driver: 1d0f:ec20 net_ena
EAL: PCI device 0000:00:07.0 on NUMA socket -1
EAL: Invalid NUMA socket, default to 0
EAL: probe driver: 1d0f:ec20 net_ena
APP: Finished Process Init.
Lcore 2 using ports 0 1
lcore 2 using queue 1 of each port
Thread 1 "symmetric_mp" received signal SIGSEGV, Segmentation fault.
0x00000000007013e8 in eth_ena_recv_pkts ()
The same procedure works for ixgbevf instance with m4.2xLarge instances.
Could you help?
Thanks.
Suyang
--
You are receiving this mail because:
You are the assignee for the bug.
