[SPDK] clarifications on spdk-top

Hi,

I understand you are the author of this, I didn't find any
documentation on that in the spdk docs. Could you prepare a quick memo
and post it here and hopefully later have something more official?

For never-sleeping framework like spdk/dpdk there's always the kinda
critical question of the break-down to idle (we didn't get anything
new to process) vs busy (we have some work to do) %% (e.g portions of
a second when sampled repeatly) -- when I looked on the idle/busy
columns the numbers were in us but it seems they didn't sum to 1M. So
what is expected there?

Thanks,

Or.