iOS 7 update traffic

Nick Wolff nwolff at oar.net
Thu Sep 19 21:32:09 UTC 2013


In my experience just having a Akamai cache wasn't enough to handle this.
Our local cache was doing 15 out of 20gbps usage and seemed pegged at
that. One of our customers had a local Akamai cache on there end crash and
we were mostly filling a 10gbps pipe to a datacenter with limelight cdn's
at it. This was just the CDN spike and not the one's over our peering and
commodity traffic. 

Yes apple might not of forced people to upgrade exactly at the time they
released but they can at least do an enforced role out like google does(on
much smaller updates of course).

Our core handled it all with not much more then amazement from our staff
but a majority of customers pipes were pegged at whatever bandwidth they
were paying for(I'm talking between 200mbps-5gbps with a few as big as
10gbps customer connections)

--Nick




On 9/19/13 4:18 PM, "Stephen Fulton" <sf at lists.esoteric.ca> wrote:

>+1
>
>If you do not/cannot have an Akamai cache, connect to an IX that does,
>and make sure you've got the capacity.  My own rule of thumb is have 2x
>the capacity of your average *peak* traffic on an IX.  When big events
>happen, whether it is news, sporting or a major software update, that
>extra capacity will be sorely needed.
>
>At TorIX, most peers traffic jumped by the same percentage that others
>have bandied about on this thread.  One peer jumped almost 100%, but
>they had the right port speed and thus no issues (at least on the
>Exchange).
>
>Compared to transit in Canada, IX peering is dirt cheap, and pays
>dividends.
>
>-- Stephen
>
>On 19/09/2013 3:07 PM, Jared Mauch wrote:
>> The attitude in this email I have encountered elsewhere.  Apple pays
>>for bandwidth, customers pay for access. Not sure why their release
>>strategy is so highly critiqued. Microsoft and others have their own
>>strategies for incremental downloads, caching, etc.. Apple has theirs.
>>
>> Seems like most consumers want the update and are actively fetching it
>>vs having older software live forever and not be updated. Overall I see
>>this as a win.
>>
>> Jared Mauch
>>
>>> On Sep 19, 2013, at 2:11 PM, Warren Bailey
>>><wbailey at satelliteintelligencegroup.com> wrote:
>>>
>>> I don't see how operators could tolerate this, honestly. I can't think
>>>of a single provider who does not oversubscribe their access
>>>platform... Which leads me to this question :
>>>
>>> Why does apple feel it is okay to send every mobile device an update
>>>on a single day?
>>
>





More information about the NANOG mailing list