mellanox kernel bypass(LD_preload) TCP/IP Socket write performance optimization

we are doing some profiling with socket send time and found out the “send” takes around 5-7us, the packet size is 215 bytes.

Profiling code
enter image description here

using VMA_stat, we confirm that everything sent are already “offloaded”, so, I assume the

send(xxx,xxx,xxx,xxx)

are using mellanox library instead of <sys/socket.h> ?

question

1. Any optimization techniques to reduce the socket transmission time?
2. Any obvious problem with how we use LD_preload?

we are using VMA_SPEC=latency and running on CentOS