[Bloat] great interview on the scale conference wifi successes

[David Lang]

On Tue, 10 Mar 2015, Dave Taht wrote:

> On Tue, Mar 10, 2015 at 1:44 PM, David Lang <david at lang.hm> wrote:
>> On Tue, 10 Mar 2015, Dave Taht wrote:
>>
>>> https://www.youtube.com/watch?v=UXvGbEYeWp0&t=4795
>>>
>>> (takes a bit to get to the wifi part)
>>>
>>> H/T to david lang for getting it so right!
>>
>>
>> Thanks, for those interested in what I did, you can see the presentation I
>> gave on the topic at LISA '12
>> https://www.usenix.org/conference/lisa12/technical-sessions/presentation/lang_david_wireless
>> and the ;login article I wrote as a follow-up
>> https://www.usenix.org/publications/login/april-2013-volume-38-number-2/wireless-means-radio
>>
>> This year I deployed 53 APs. I'll make an updated map showing where they
>> were deployed.
>
> So far as I know all the APs were fq-codeled, but the firewall/gw was
> not. Had I not been too sick to make it to the conference, might have
> got that done. As it was, david ran some netperf-wrapper tests on the
> firewall on the last day, and, well, that data was miserable. Next
> year! we'll get that right.

Next year we are moving to a new location (arguably we outgrew the current 
location quite a while ago, and this year we had people sitting on the floor in 
rooms, hanging out at the doorway, and filling the overflow rooms where we 
live-streamed the talk as well)

the new location is considerably larger (~2x the space), so we will have to buy 
a lot more APs. The WNDR3800 is not available in these sorts of quantities, so 
we will have to buy something new. We are looking at two major options

1. going with something similar to what we've been running (say the 3700v4)

2. switching to ac/mimo APs

since we will be needing ~120 APs for next year, the cost of the different 
options will be significant. At this point we are just starting to look and 
figure out what's available, what sort of price difference there will be, and 
what the advantages of the better APs would be.

I'll probably purchase some samples to experiment over the next few months, but 
we won't make the mass purchase of whatever until late in the year.

David Lang