There are error frames on the 10G Ethernet port

seek_scholars · ‎09-11-2020

Hello,

I'm using an LS1046A-RDB board with LSDK-18.06-V4.14.

There is a 10 Gigabit Ethernet port on the development board. Ethernet frame errors will occur when using the iperf3 tool to test the bandwidth.

CAT.7 network cable used to connect 2 board network ports

On first board:

# fmc -c /etc/fmc/config/private/ls1046ardb/config_1133.xml -p /etc/fmc/config/private/ls1046ardb/policy_ipv4.xml -a

# ifconfig fm1-mac9 192.168.2.152

# iperf3 -s

On second board:

# fmc -c /etc/fmc/config/private/ls1046ardb/config_1133.xml -p /etc/fmc/config/private/ls1046ardb/policy_ipv4.xml -a

# ifconfig fm1-mac9 192.168.2.181

# iperf3 -c 192.168.2.152 -t 100 -i 1

Test Results

Connecting to host 192.168.2.152, port 5201
[ 4] local 192.168.2.181 port 41786 connected to 192.168.2.152 port 5201
[ ID] Interval Transfer Bandwidth Retr Cwnd
[ 4] 0.00-1.00 sec 805 MBytes 6.75 Gbits/sec 0 857 KBytes

[ 4] 1.00-2.00 sec 811 MBytes 6.80 Gbits/sec 1 643 KBytes
^C[ 4] 2.00-2.89 sec 715 MBytes 6.78 Gbits/sec 2 933 KBytes
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval Transfer Bandwidth Retr
[ 4] 0.00-2.89 sec 2.28 GBytes 6.78 Gbits/sec 3 sender
[ 4] 0.00-2.89 sec 0.00 Bytes 0.00 bits/sec receiver
iperf3: interrupt - the client has terminated

USDPAA policy file:policy_ipv4.xml

/etc/fmc/config/private/ls1046ardb/policy_ipv4.xml is a soft link to /etc/fmc/config/private/ls1046ardb/RR_FFSSPPPH_1133_5559/policy_ipv4.xml.

USDPAA config file : config_1133.xml

<?xml version="1.0" encoding="utf-8"?>
<cfgdata>
<config>
<engine name="fm0">
<port type="MAC" number="3" policy="fm_policy_3"/>
<port type="MAC" number="4" policy="fm_policy_4"/>
<port type="MAC" number="6" policy="fm_policy_6"/>
<port type="MAC" number="9" policy="fm_policy_7"/>
<port type="MAC" number="10" policy="fm_policy_8"/>

</engine>
</config>
</cfgdata>

Enter the command on the 192.168.2.181 board

root@localhost:~# ifconfig fm1-mac9
fm1-mac9: flags=4163<UP,BROADCAST,RUNNING,MULTICAST> mtu 1500
inet 192.168.2.181 netmask 255.255.255.0 broadcast 192.168.2.255
inet6 fe80::24b0:38ff:fe0d:5edc prefixlen 64 scopeid 0x20<link>
ether 26:b0:38:0d:5e:dc txqueuelen 1000 (Ethernet)
RX packets 183917 bytes 9566221 (9.5 MB)
RX errors 7 dropped 0 overruns 0 frame 0
TX packets 16993628 bytes 25681206376 (25.6 GB)
TX errors 0 dropped 0 overruns 0 carrier 0 collisions 0
device memory 0x1af0000-1af0fff

There is an error data frame

root@localhost:~# ethtool -S fm1-mac9
NIC statistics:
interrupts [CPU 0]: 247642
interrupts [CPU 1]: 334337
interrupts [CPU 2]: 333466
interrupts [CPU 3]: 344804
interrupts [TOTAL]: 1260249
rx packets [CPU 0]: 151803
rx packets [CPU 1]: 13695
rx packets [CPU 2]: 18417
rx packets [CPU 3]: 8
rx packets [TOTAL]: 183923
tx packets [CPU 0]: 13459185
tx packets [CPU 1]: 1684122
tx packets [CPU 2]: 1658997
tx packets [CPU 3]: 191328
tx packets [TOTAL]: 16993632
tx recycled [CPU 0]: 0
tx recycled [CPU 1]: 0
tx recycled [CPU 2]: 0
tx recycled [CPU 3]: 0
tx recycled [TOTAL]: 0
tx confirm [CPU 0]: 3337150
tx confirm [CPU 1]: 4475639
tx confirm [CPU 2]: 4516475
tx confirm [CPU 3]: 4664368
tx confirm [TOTAL]: 16993632
tx S/G [CPU 0]: 13459147
tx S/G [CPU 1]: 1684098
tx S/G [CPU 2]: 1658982
tx S/G [CPU 3]: 191320
tx S/G [TOTAL]: 16993547
rx S/G [CPU 0]: 0
rx S/G [CPU 1]: 0
rx S/G [CPU 2]: 0
rx S/G [CPU 3]: 0
rx S/G [TOTAL]: 0
tx error [CPU 0]: 0
tx error [CPU 1]: 0
tx error [CPU 2]: 0
tx error [CPU 3]: 0
tx error [TOTAL]: 0
rx error [CPU 0]: 1
rx error [CPU 1]: 2
rx error [CPU 2]: 1
rx error [CPU 3]: 3
rx error [TOTAL]: 7
bp count [CPU 0]: 85
bp count [CPU 1]: 97
bp count [CPU 2]: 79
bp count [CPU 3]: 120
bp count [TOTAL]: 381
rx dma error: 0
rx frame physical error: 7
rx frame size error: 0

I each restart board Linux OS, the value of Retr will be different. Please help me how to solve the 10G network retransmission problem?

Thanks