Hello I am using iperf3. Specifically, I am running a test between two systems, with the following options: -c <target_ip> -t 60 -i 10 -P 2
My source and target VMs both have 2 CPU cores each. The output of lscpu from the source VM (is identical on the target as well): # lscpu Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Byte Order: Little Endian CPU(s): 2 On-line CPU(s) list: 0,1 Thread(s) per core: 1 Core(s) per socket: 2 I have 2 questions: a. I want to ensure that when -P 2 is in effect, the load should be uniformly distributed across both the cores. However, I find that on the client side, cpu 0 does more work compared to cpu 1, and on the server, its vice -versa. 1. Is there an option to ensure uniform distribution of load across the cpu cores? 2. Also, in the absence of a uniform distribution, I would expect only cpu 0 to do more work. But cpu 1 appears to be working more on the server side. Any thoughts on this? Thanks in advance, - Rajarshi _______________________________________________ Iperf-users mailing list Iperf-users@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/iperf-users
