forked from cisco-system-traffic-generator/trex-core
-
Notifications
You must be signed in to change notification settings - Fork 4
Open
Description
Description
- With multi core: I'm seeing some packet drops when running trex in ASTF mode with UDP protocol. I tried with 1M CPS which gave me around 1600 keepalive packet drops. I'm also seeing this when running at a higher CPS.
- With single core: I'm seeing half of the transmitted packets are getting dropped due to the keepalive issue. Upon investigation, realized that half of the packets are going into queue 1 and the other half are going into queue 0; however, they should all go to queue 0.
TRex Configuration
interfaces: ['0000:14:00.0', '0000:15:00.0']
rx_desc: 4096
port_info:
- ip: 1.1.1.1
default_gw: 2.2.2.2
- ip: 2.2.2.2
default_gw: 1.1.1.1
platform:
master_thread_id: 0
latency_thread_id: 10
dual_if:
- socket: 0
threads: [1,2,3,4,5,6,7,8,9,20,21,22,23,24,25,26,27,28,29]
Screenshots
To Reproduce
- Start trex on one terminal by using
./t-rex-64 -c 8 -i --astf - Start trex-console on another terminal using
./trex-console - Then using this command
start -f astf/udp1.py -m 10000000 -d 100in trex-console
Reactions are currently unavailable
Metadata
Metadata
Assignees
Labels
No labels
