Assigning a single SND CPU to service a 10 Gbps+ interface will only get you to 4-5Gbps at best before the single CPU is saturated. What you need to do is enable Multi-Queue for the busy interfaces and possibly reduce the number of firewall workers in your CoreXL split so there are more SNDs available to keep up with your busy interfaces. This assumes that your firewall NIC hardware supports Multi-Queue, what model is your gateway? Also to echo Chris we will need to see Super Seven outputs.
Incidentally, in R81 and later all supported interfaces automatically have Multi-Queue enabled, and the CoreXL split is adjusted dynamically which would almost certainly completely avoid the issue you are experiencing.
Attend my 60-minute "Be your Own TAC: Part Deux" Presentation
Exclusively at CPX 2025 Las Vegas Tuesday Feb 25th @ 1:00pm