Advantages in Scalability of Softriqs versus Tasklets

I am curious about reading through LKD, when to start using softriqs other tasklets in terms of when the limit of scalability of tasklets are hit. I am assuming after reading LKD it seems to happen when multiple cores would be of great advantage in scaling the bottom half of my or our people's code. In addition in seems to also happen when timing of interrupts needs to be in the range of under milliseconds to process the bottom half and this seems very important for the networking subsystem. Cheers and Thanks for Any Answers, Nick