cvs commit: src/sys/kern kern_poll.c

[Scott Long]

Nate Lawson wrote:
> Scott Long wrote:
> 
>> Nate Lawson wrote:
>>
>>> For the case of storage, you actually have a better model since all 
>>> transactions are initiated from the host (as opposed to packet 
>>> arrivals).  This gives an easy metric for a dynamic polling threshold 
>>> -- if you have a deep queue of outstanding requests and one 
>>> completes, you should poll a little more than normal.
>>>
>>
>> Except for target mode.
> 
> 
> Never heard of that before.
> 

Take my wife, please!

Bada-bum-chink

Seriously though, I mention it because it is a very important component
for storage applicances, bith in it's ability to work and work well.
It's an area where we still have a significanlt lead of Linux.

Scott