Moooo-re Siloes Please!

I have received a few private comments that I was unduly critical of tagging mechanisms in my recent post about the VN-Tag/VN-Link debate between Cisco and HP.  I don't have a problem with tagging mechanisms, in fact I am a fan of them - however, I have an issue with too many tagging mechanisms.  There ends up being a tag for about everything - we have Security Group Tags, MPLS Tags, VLAN Tags, QoS Tags at L2 and separate ones at L3, we also now have tags that identify the Virtual Machine or the NIC on the Virtual Machine so we can create new NICs in software.

Let's just own up to it for a second that there are way too many tags; however, the problem is not always the industry and companies that want to create a new tag. Now before I go offering a solution that is highly likely to not be flame-retardant let me get on my proverbial soapbox for a second, so bear with me...

I think a root cause problem is that there is a schism in the relevant standards bodies.  I have to go to one standards group for Ethernet (IEEE), another to work at the IP layers (IETF), yet a third if I want to carry storage traffic (ANSI T.11) - and this is the tip of the iceberg.  It is hard enough to shepherd a great idea through the bureaucratic morass that are created anytime you put that many strongly opinionated, diametrically opposed, and discretely compensated individuals on a board/council/committee and try to get them working together but now with things getting 'blurry' between the once rigid lines between siloed standards bodies it is near impossible.

So while I often catch the brunt of 'why isn't this done in the standards bodies' question and have fielded it for years I don't think we have done a fair job of analyzing how efficient the standards bodies are and whether they should look at reorganizing around how their customers use the technologies they ratify.  The world is changing from 20 years ago - are the standards bodies changing with it?  Are they part of the legacy of siloed information technology that needs to change with the new world order where lines are crossed, borders are blurred, and service is more important than boxes?

As far as how to solve this embedded multi-vectored tagging problem I don't think there is one 'right' answer.  But one thing I always with was available was a single extensible tagging structure, that could be layered/embedded, that could be re-purposed for different functions and the first few bits (say 8 or so) delimited what 'kind' of tag it is (QoS, App Descriptor, Segmentation, Forwarding, Cloud Storage Access Rights, etc), and the next 16-24 bits were used to delimit something relevant within that kind of tag.  Done in an extensible fashion we could keep the extended header short of 128-256 bits which would mean it could pretty easily be parsed with one of the more advanced stream processing methods on the market.

One standard to rule them all, one to bind them...

Yes, it is sort of 'too simple' and is probable a bit like Dark Lord Sauron forging the 'One Ring to Rule them All, One Ring to Bind Them' (and the fact that I am doing that from memory should be a strong signal that I missed ComicCon)  but a tagging construct that 'crossed party lines' between IEEE, IETF, ANSI, ISO, W3C, etc could be quite interesting.  It's a shame there is not standards body to run it through....

dg