Hello all,
I am trying to operate RSS in X710 NIC.
In order to do so, I use l3fwd example.
I added a printf in l3fwd_lpm.c, right after rte_eth_rx_burst to print the
lcore, queueid and nb_rx.
In my server I have 2 NICs. X520 and X710. From each NIC I connect to a switch,
and another connection t
Hello all,
I am trying to operate RSS in X710 NIC.
In order to do so, I use l3fwd example.
I added a printf in l3fwd_lpm.c, right after rte_eth_rx_burst to print the
lcore, queueid and nb_rx.
In my server I have 2 NICs. 82599 and X710. From each NIC I connect to a
switch, and another connection
Hi all,
I want to use both PF and VF bound to igb_uio.
However, when doing so, VF init fails:
EAL: PCI device :04:10.1 on NUMA socket 0
EAL: probe driver: 8086:10ed rte_ixgbevf_pmd
PMD: eth_ixgbevf_dev_init(): VF Initialization Failure: -100
EAL: Error - exiting with code: 1
Cause: Reques
Hi all,
I want to use both PF and VF bound to igb_uio.
However, when doing so, VF init fails:
EAL: PCI device :04:10.1 on NUMA socket 0
EAL: probe driver: 8086:10ed rte_ixgbevf_pmd
PMD: eth_ixgbevf_dev_init(): VF Initialization Failure: -100
EAL: Error - exiting with code: 1
Caus
I also encountered the same issue.
It seems the NIC doesn't report it's up fast enough for that code. For me it
sometimes worked and sometimes didn't.
I just pushed a sleep command before checking it's up (before calling to
app_ports_check_link, in init.c).
---
Hello,
In librte_eal, in eal_ivshmem.c, in function map_all_segments, there is mapping
of segments from the metadata to the same virtual address as written in the
metadata.
Is there a method to guarantee that this mapping won't fail, even for different
processes, that might have large code or c