Is there a way to override it to set 9216 instead at runtime? Or would I need to modify and recompile pktgen/dpdk?
Looking at another interface using the kernel driver, the max mtu reported is 9216 so I’m also not sure where the 9618 comes from or why it’s being used instead of 9216. Perhaps I’m misunderstanding
what should work out-of-the-box and what needs to be tweaked during compilation time.
I’m using pktgen 21.05.0 and dpdk 21.08.
Copyright(c) <2010-2021>, Intel Corporation. All rights reserved. Powered by DPDK
EAL: Detected 72 lcore(s)
EAL: Detected 2 NUMA nodes
EAL: Detected shared linkage of DPDK
EAL: Multi-process socket /var/run/dpdk/rte/mp_socket
EAL: Selected IOVA mode 'PA'
EAL: No available 1048576 kB hugepages reported
EAL: VFIO support initialized
EAL: Device 0000:00:05.0 is not NUMA-aware, defaulting socket to 0
EAL: Device 0000:00:06.0 is not NUMA-aware, defaulting socket to 0
EAL: Probe PCI driver: net_ena (1d0f:ec20) device: 0000:00:06.0 (socket 0)
EAL: Device 0000:00:07.0 is not NUMA-aware, defaulting socket to 0
TELEMETRY: No legacy callbacks, legacy socket not created
**** Jumbo Frames of 9618 enabled.
*** Copyright(c) <2010-2021>, Intel Corporation. All rights reserved.
*** Pktgen created by: Keith Wiles -- >>> Powered by DPDK <<<
Port: Name IfIndex Alias NUMA PCI
0: net_ena 0 0 1d0f:ec20/00:06.0
Initialize Port 0 -- TxQ 6, RxQ 1
Ethdev port_id=0 max_rx_pkt_len 9618 > max valid value 9216
!PANIC!: Cannot configure device: port=0, Num queues 1,6 (22)Invalid argument
PANIC in pktgen_config_ports():
Cannot configure device: port=0, Num queues 1,6 (22)Invalid argument
6: [pktgen(+0xa8de) [0x55d0401ef8de]]
5: [/lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0xf3) [0x7ffb0b4ab0b3]]
4: [pktgen(+0xa454) [0x55d0401ef454]]
3: [pktgen(+0x31a2e) [0x55d040216a2e]]
2: [/usr/local/lib/x86_64-linux-gnu/librte_eal.so.21(__rte_panic+0xcd) [0x7ffb0b869e9f]]
1: [/usr/local/lib/x86_64-linux-gnu/librte_eal.so.21(rte_dump_stack+0x32) [0x7ffb0b88f602]]
Aborted
Thanks,
Josh