How to reset mlnx_qos settings

Hi all,

I’ve seen mlnx_qos working properly to limit the traffic with sk_prio.

If I want to reset all the qos settings, how to do that ? Even after rebooting the system, the traffic without sk_prio was limited. I’ve set all queue unlimited, but it did not work for no sk_proio.

How to clear qos settings?

*** here is logs running rate limit

$ mlnx_qos -i enp182s0f0 -p 0,1,2,3,4,5,6,7 -r 6,6,6,6,6,6,6,6

DCBX mode: OS controlled

Priority trust state: dscp

dscp2prio mapping:

prio:0 dscp:07,06,05,04,03,02,01,00,

prio:1 dscp:15,14,13,12,11,10,09,08,

prio:2 dscp:23,22,21,20,19,18,17,16,

prio:3 dscp:31,30,29,28,27,26,25,24,

prio:4 dscp:39,38,37,36,35,34,33,32,

prio:5 dscp:47,46,45,44,43,42,41,40,

prio:6 dscp:55,54,53,52,51,50,49,48,

prio:7 dscp:63,62,61,60,59,58,57,56,

Receive buffer size (bytes): 262016,0,0,0,0,0,0,0,

Cable len: 7

PFC configuration:

priority 0 1 2 3 4 5 6 7

enabled 0 0 0 0 0 0 0 0

buffer 0 0 0 0 0 0 0 0

tc: 0 ratelimit: 6.0 Gbps, tsa: vendor

priority: 0

tc: 1 ratelimit: 6.0 Gbps, tsa: vendor

priority: 1

tc: 2 ratelimit: 6.0 Gbps, tsa: vendor

priority: 2

tc: 3 ratelimit: 6.0 Gbps, tsa: vendor

priority: 3

tc: 4 ratelimit: 6.0 Gbps, tsa: vendor

priority: 4

tc: 5 ratelimit: 6.0 Gbps, tsa: vendor

priority: 5

tc: 6 ratelimit: 6.0 Gbps, tsa: vendor

priority: 6

tc: 7 ratelimit: 6.0 Gbps, tsa: vendor

priority: 7

[root@vm1 ~]# iperf -c 1.1.1.112 -i 1


Client connecting to 1.1.1.112, TCP port 5001

TCP window size: 45.0 KByte (default)


[ 3] local 1.1.1.111 port 38774 connected with 1.1.1.112 port 5001

[ ID] Interval Transfer Bandwidth

[ 3] 0.0- 1.0 sec 488 MBytes 4.09 Gbits/sec

[ 3] 1.0- 2.0 sec 488 MBytes 4.09 Gbits/sec

[ 3] 2.0- 3.0 sec 557 MBytes 4.67 Gbits/sec

[ 3] 3.0- 4.0 sec 539 MBytes 4.52 Gbits/sec

[ 3] 0.0- 4.0 sec 2.04 GBytes 4.35 Gbits/sec

*** after rebooting the system, I’ve seen the default value, but vm traffic was limited by 1Gbps

$ mlnx_qos -i enp182s0f0

DCBX mode: OS controlled

Priority trust state: pcp

Receive buffer size (bytes): 262016,0,0,0,0,0,0,0,

Cable len: 7

PFC configuration:

priority 0 1 2 3 4 5 6 7

enabled 0 0 0 0 0 0 0 0

buffer 0 0 0 0 0 0 0 0

tc: 0 ratelimit: unlimited, tsa: vendor

priority: 1

tc: 1 ratelimit: unlimited, tsa: vendor

priority: 0

tc: 2 ratelimit: unlimited, tsa: vendor

priority: 2

tc: 3 ratelimit: unlimited, tsa: vendor

priority: 3

tc: 4 ratelimit: unlimited, tsa: vendor

priority: 4

tc: 5 ratelimit: unlimited, tsa: vendor

priority: 5

tc: 6 ratelimit: unlimited, tsa: vendor

priority: 6

tc: 7 ratelimit: unlimited, tsa: vendor

[root@vm1 ~]# iperf -c 1.1.1.112 -i 1


Client connecting to 1.1.1.112, TCP port 5001

TCP window size: 45.0 KByte (default)


[ 3] local 1.1.1.111 port 41298 connected with 1.1.1.112 port 5001

[ ID] Interval Transfer Bandwidth

[ 3] 0.0- 1.0 sec 80.9 MBytes 678 Mbits/sec

[ 3] 1.0- 2.0 sec 108 MBytes 903 Mbits/sec

[ 3] 2.0- 3.0 sec 105 MBytes 882 Mbits/sec

[ 3] 3.0- 4.0 sec 122 MBytes 1.03 Gbits/sec

[ 3] 4.0- 5.0 sec 110 MBytes 926 Mbits/sec

[ 3] 5.0- 6.0 sec 114 MBytes 959 Mbits/sec

[ 3] 6.0- 7.0 sec 118 MBytes 990 Mbits/sec

[ 3] 7.0- 8.0 sec 116 MBytes 971 Mbits/sec

[ 3] 8.0- 9.0 sec 123 MBytes 1.03 Gbits/sec

[ 3] 9.0-10.0 sec 132 MBytes 1.11 Gbits/sec

[ 3] 0.0-10.0 sec 1.10 GBytes 948 Mbits/sec

Best Regrads,

Jiho Jung

Hi Jiho Jung,

You can reset mlnx_qos settings by either changing them manually back to default, restart the driver or reboot the server.

There are 2 ways to set qos parameters:

  1. Using mlnx_qos

  2. Using LLDP DCBX

There could be some conflicts if both of them are used.

Note: If you are using mlnx_qos to enable PFC, please ensure all firmware LLDP and DCBX parameters are disabled in the firmware.

mlxconfig -d /dev/mst/mt4115_pciconf0 set LLDP_NB_DCBX_P1=FALSE LLDP_NB_TX_MODE_P1=0 LLDP_NB_RX_MODE_P1=0 LLDP_NB_DCBX_P2=FALSE LLDP_NB_TX_MODE_P2=0 LLDP_NB_RX_MODE_P2=0

Regards,

Chen