Does the incrementing of rx_over_errors/rx_dropped mean that the card cannot handle data at the rate it's receiving?
I am using the ConnectX - 3 Pro 10 Gigabit Ethernet card and receiving udp multicast data.
I have read the Mellanox post regarding rx_over_errors which states:
rx_over_errors: Number of received frames that were dropped due to on hardware port receive buffer overflow. This counter is increased at point (1) in the figure above. In most cases, rx_over_errors is equal to rx_dropped.
Following is my output from ethtool.
#ethtool -S ens2
NIC statistics:
rx_packets: 4036581952
rx_bytes: 468690115462
rx_multicast_packets: 4036581949
rx_broadcast_packets: 0
rx_errors: 0
rx_dropped: 7868070
rx_length_errors: 0
rx_over_errors: 7868070
rx_crc_errors: 0
rx_jabbers: 0
# ethtool --driver ens2
driver: mlx4_en
version: 2.4-1.0.0.1 (Jun 10 2015)
firmware-version: 2.33.5100
bus-info: 0000:15:00.0
supports-statistics: yes
supports-test: yes
supports-eeprom-access: no
supports-register-dump: no
supports-priv-flags: yes