route/arp lifetime (Re: it's the output, not ack coalescing (Re: TSO and FreeBSD vs Linux))

[Andre Oppermann]

On 25.08.2013 16:42, Adrian Chadd wrote:
> On 24 August 2013 10:09, Andre Oppermann <andre at freebsd.org <mailto:andre at freebsd.org>> wrote:
>
>     On 24.08.2013 19:04, Adrian Chadd wrote:
>
>         I'm very close to starting an mbuf batching thing to use in a few places like receive,
>         transmit and
>         transmit completion -> free path. I'd be interested in your review/feedback and testing as
>         it sounds
>         like something you can easily stress test there. :)
>
>
>     I'd strongly recommend fixing a number of other places and collect
>     lower hanging fruit before starting with mbuf batching.
>
>
> I'm open to suggestions.
>
> Scott killed our high hanging fruit (VM / buffer page lifecycle) and what's left is not very low. If
> you have any recommendations, I'd love to hear them.

1. lle lock to rmlock.

2. if_addr and IN_ADDR locks to rmlocks.

3. routing table locking (rmlocks, and by doing away with rtentry locks and refcounting
    through copy-out on lookup and prohibition of having any pointers into the rtable).

-- 
Andre