Bug 1892815
| Summary: | [OVS-DPDK][bnxt] Ping failed over OVS-dpdk/bnxt using openvswitch-2.9.7-1.el7fdn under 7.9 | ||
|---|---|---|---|
| Product: | Red Hat Enterprise Linux Fast Datapath | Reporter: | Jean-Tsung Hsiao <jhsiao> |
| Component: | openvswitch | Assignee: | Timothy Redaelli <tredaelli> |
| openvswitch sub component: | ovs-dpdk | QA Contact: | Jean-Tsung Hsiao <jhsiao> |
| Status: | NEW --- | Docs Contact: | |
| Severity: | unspecified | ||
| Priority: | unspecified | CC: | ctrautma, gcase, jhsiao, ktraynor, qding, tli, tredaelli |
| Version: | RHEL 7.7 | Flags: | jhsiao:
needinfo?
(tredaelli) |
| Target Milestone: | --- | ||
| Target Release: | --- | ||
| Hardware: | Unspecified | ||
| OS: | Unspecified | ||
| Whiteboard: | |||
| Fixed In Version: | Doc Type: | If docs needed, set a value | |
| Doc Text: | Story Points: | --- | |
| Clone Of: | Environment: | ||
| Last Closed: | Type: | Bug | |
| Regression: | --- | Mount Type: | --- |
| Documentation: | --- | CRM: | |
| Verified Versions: | Category: | --- | |
| oVirt Team: | --- | RHEL 7.3 requirements from Atomic Host: | |
| Cloudforms Team: | --- | Target Upstream Version: | |
| Embargoed: | |||
|
Description
Jean-Tsung Hsiao
2020-10-29 17:47:41 UTC
I also run pvp ovs dpdk performance case failed on bnxt_en card. beaker job: https://beaker.engineering.redhat.com/jobs/4694206 https://beaker.engineering.redhat.com/jobs/4692789 This same issue happened again under 2.9.9.
It can be reproduced easily using the following loop:
[root@netqe10 home]# for i in {1..5}; do echo Test $i; date; systemctl stop openvswitch; systemctl start openvswitch; sh ovs-dpdk.sh; done
Test 1
Fri Apr 16 15:21:12 EDT 2021
default via 10.19.15.254 dev em3 proto dhcp metric 100
10.19.15.0/24 dev em3 proto kernel scope link src 10.19.15.47 metric 100
192.168.9.0/24 dev ovsbr0 proto kernel scope link src 192.168.9.106
192.168.122.0/24 dev virbr0 proto kernel scope link src 192.168.122.1
link_state : down
PING 192.168.9.105 (192.168.9.105) 56(84) bytes of data.
From 192.168.9.106 icmp_seq=1 Destination Host Unreachable
From 192.168.9.106 icmp_seq=2 Destination Host Unreachable
From 192.168.9.106 icmp_seq=3 Destination Host Unreachable
From 192.168.9.106 icmp_seq=4 Destination Host Unreachable
64 bytes from 192.168.9.105: icmp_seq=5 ttl=64 time=0.526 ms
64 bytes from 192.168.9.105: icmp_seq=6 ttl=64 time=0.071 ms
64 bytes from 192.168.9.105: icmp_seq=7 ttl=64 time=0.134 ms
64 bytes from 192.168.9.105: icmp_seq=8 ttl=64 time=0.089 ms
64 bytes from 192.168.9.105: icmp_seq=9 ttl=64 time=0.131 ms
64 bytes from 192.168.9.105: icmp_seq=10 ttl=64 time=0.129 ms
--- 192.168.9.105 ping statistics ---
10 packets transmitted, 6 received, +4 errors, 40% packet loss, time 9000ms
rtt min/avg/max/mdev = 0.071/0.180/0.526/0.156 ms, pipe 4
Test 2
Fri Apr 16 15:21:32 EDT 2021
default via 10.19.15.254 dev em3 proto dhcp metric 100
10.19.15.0/24 dev em3 proto kernel scope link src 10.19.15.47 metric 100
192.168.9.0/24 dev ovsbr0 proto kernel scope link src 192.168.9.106
192.168.122.0/24 dev virbr0 proto kernel scope link src 192.168.122.1
link_state : up
PING 192.168.9.105 (192.168.9.105) 56(84) bytes of data.
From 192.168.9.106 icmp_seq=1 Destination Host Unreachable
From 192.168.9.106 icmp_seq=2 Destination Host Unreachable
From 192.168.9.106 icmp_seq=3 Destination Host Unreachable
From 192.168.9.106 icmp_seq=4 Destination Host Unreachable
From 192.168.9.106 icmp_seq=5 Destination Host Unreachable
From 192.168.9.106 icmp_seq=6 Destination Host Unreachable
From 192.168.9.106 icmp_seq=7 Destination Host Unreachable
From 192.168.9.106 icmp_seq=8 Destination Host Unreachable
64 bytes from 192.168.9.105: icmp_seq=9 ttl=64 time=0.554 ms
64 bytes from 192.168.9.105: icmp_seq=10 ttl=64 time=0.089 ms
--- 192.168.9.105 ping statistics ---
10 packets transmitted, 2 received, +8 errors, 80% packet loss, time 9001ms
rtt min/avg/max/mdev = 0.089/0.321/0.554/0.233 ms, pipe 4
Test 3
Fri Apr 16 15:21:51 EDT 2021
default via 10.19.15.254 dev em3 proto dhcp metric 100
10.19.15.0/24 dev em3 proto kernel scope link src 10.19.15.47 metric 100
192.168.9.0/24 dev ovsbr0 proto kernel scope link src 192.168.9.106
192.168.122.0/24 dev virbr0 proto kernel scope link src 192.168.122.1
link_state : up
PING 192.168.9.105 (192.168.9.105) 56(84) bytes of data.
64 bytes from 192.168.9.105: icmp_seq=1 ttl=64 time=1001 ms
64 bytes from 192.168.9.105: icmp_seq=2 ttl=64 time=2.33 ms
64 bytes from 192.168.9.105: icmp_seq=3 ttl=64 time=0.154 ms
64 bytes from 192.168.9.105: icmp_seq=4 ttl=64 time=0.070 ms
64 bytes from 192.168.9.105: icmp_seq=5 ttl=64 time=0.160 ms
64 bytes from 192.168.9.105: icmp_seq=6 ttl=64 time=0.083 ms
64 bytes from 192.168.9.105: icmp_seq=7 ttl=64 time=0.082 ms
64 bytes from 192.168.9.105: icmp_seq=8 ttl=64 time=0.083 ms
64 bytes from 192.168.9.105: icmp_seq=9 ttl=64 time=0.068 ms
64 bytes from 192.168.9.105: icmp_seq=10 ttl=64 time=0.083 ms
--- 192.168.9.105 ping statistics ---
10 packets transmitted, 10 received, 0% packet loss, time 9000ms
rtt min/avg/max/mdev = 0.068/100.508/1001.968/300.487 ms, pipe 2
Test 4
Fri Apr 16 15:22:11 EDT 2021
default via 10.19.15.254 dev em3 proto dhcp metric 100
10.19.15.0/24 dev em3 proto kernel scope link src 10.19.15.47 metric 100
192.168.9.0/24 dev ovsbr0 proto kernel scope link src 192.168.9.106
192.168.122.0/24 dev virbr0 proto kernel scope link src 192.168.122.1
link_state : up
PING 192.168.9.105 (192.168.9.105) 56(84) bytes of data.
64 bytes from 192.168.9.105: icmp_seq=1 ttl=64 time=1001 ms
64 bytes from 192.168.9.105: icmp_seq=2 ttl=64 time=2.32 ms
64 bytes from 192.168.9.105: icmp_seq=3 ttl=64 time=0.150 ms
64 bytes from 192.168.9.105: icmp_seq=4 ttl=64 time=0.087 ms
64 bytes from 192.168.9.105: icmp_seq=5 ttl=64 time=0.096 ms
64 bytes from 192.168.9.105: icmp_seq=6 ttl=64 time=0.082 ms
64 bytes from 192.168.9.105: icmp_seq=7 ttl=64 time=0.082 ms
64 bytes from 192.168.9.105: icmp_seq=8 ttl=64 time=0.095 ms
64 bytes from 192.168.9.105: icmp_seq=9 ttl=64 time=0.085 ms
64 bytes from 192.168.9.105: icmp_seq=10 ttl=64 time=0.083 ms
--- 192.168.9.105 ping statistics ---
10 packets transmitted, 10 received, 0% packet loss, time 9000ms
rtt min/avg/max/mdev = 0.082/100.481/1001.736/300.419 ms, pipe 2
Test 5
Fri Apr 16 15:22:31 EDT 2021
default via 10.19.15.254 dev em3 proto dhcp metric 100
10.19.15.0/24 dev em3 proto kernel scope link src 10.19.15.47 metric 100
192.168.9.0/24 dev ovsbr0 proto kernel scope link src 192.168.9.106
192.168.122.0/24 dev virbr0 proto kernel scope link src 192.168.122.1
link_state : up
PING 192.168.9.105 (192.168.9.105) 56(84) bytes of data.
64 bytes from 192.168.9.105: icmp_seq=1 ttl=64 time=1002 ms
64 bytes from 192.168.9.105: icmp_seq=2 ttl=64 time=3.51 ms
64 bytes from 192.168.9.105: icmp_seq=3 ttl=64 time=0.149 ms
64 bytes from 192.168.9.105: icmp_seq=4 ttl=64 time=0.137 ms
64 bytes from 192.168.9.105: icmp_seq=5 ttl=64 time=0.142 ms
64 bytes from 192.168.9.105: icmp_seq=6 ttl=64 time=0.065 ms
64 bytes from 192.168.9.105: icmp_seq=7 ttl=64 time=0.080 ms
64 bytes from 192.168.9.105: icmp_seq=8 ttl=64 time=0.094 ms
64 bytes from 192.168.9.105: icmp_seq=9 ttl=64 time=0.085 ms
64 bytes from 192.168.9.105: icmp_seq=10 ttl=64 time=0.084 ms
--- 192.168.9.105 ping statistics ---
10 packets transmitted, 10 received, 0% packet loss, time 9000ms
rtt min/avg/max/mdev = 0.065/100.714/1002.787/300.692 ms, pipe 2
*** ovs-dpdk.sh ***
[root@netqe10 home]# cat ovs-dpdk.sh
ovs-vsctl set Open_vSwitch . other_config={}
ovs-vsctl --no-wait set Open_vSwitch . other_config:dpdk-lcore-mask=0x002002
ovs-vsctl --no-wait set Open_vSwitch . other_config:dpdk-socket-mem="4096,4096"
ovs-vsctl --no-wait set Open_vSwitch . other_config:pmd-cpu-mask=0xa00a00
ovs-vsctl --no-wait set Open_vSwitch . other_config:dpdk-init=true
ovs-vsctl --if-exists del-br ovsbr0
ovs-vsctl add-br ovsbr0 -- set bridge ovsbr0 datapath_type=netdev
ovs-vsctl add-port ovsbr0 dpdk-10 -- set interface dpdk-10 type=dpdk ofport_request=10 \
options:dpdk-devargs=0000:83:00.0 options:n_rxq=4
ip a a 192.168.9.106/24 dev ovsbr0
ip lin set ovsbr0 up
ip r
ovs-vsctl list interface dpdk-10 | grep link_state
ping 192.168.9.105 -c 10
[root@netqe10 home]#
Please let me know if we need to have Broadcom take a look at this bug. |