Am 14.02.21 um 10:57 schrieb Matthias Petermann:
Most likely it's interrupt processing under Xen, or something along those lines.You mean something like what is discussed here:http://www.owlnet.rice.edu/~kevinaboos/docs/interrupt-coalescing-presentation.pdf?
However, I am still a bit surprised... Interrupts are sent in the case of the Dom0, nevertheless, mainly from the hardware in the direction of the kernel(?) If - as in the test with iperf on localhost (loopback) - no physical I/O hardware is involved at all - how can it be that the difference in this test is so clear?
Kind regards Matthias