One (storage) protocol to rule them all?

One of the questions posed to the “ask me anything” storage panel at this week’s TECHunplugged event was whether we will ever see a single storage protocol develop. This is an interesting idea and with the move to object storage, seems to have some merit. However, as always with technology, the answer “it depends” seems the …

[Trevor_Pott]

FCoTR is the future.

[Justin Clift]

Fibre Channel over Tolkien Ring? ;)

[The Beer Monster]

Preach it, brother.

[chris coreline]

FC_AL still works... if your a masochist.

[Anonymous Coward]

The problem with FCoE

Was mainly that it doesn't fit the 'tower' model of modern system administration. Either the network team needs to learn zoning so they can manage the converged ethernet/FCoE switches, or you need two teams with administrative access and authority to make changes to the same equipment. Inevitably this sort of thing will lead to turf wars and finger pointing.

That's why FCoE has been mainly used in hyperconverged environments like vBlock where the lines have to blur anyway and there is less need for post-install switch configuration like zoning in the first place.

[DWRandolph]

STANDARDS ?!?

sorry, but as a cynical old bastard, I am compelled to re-post this whenever I hear the word "standard", especially when they are talking about new / consolidate / simplify :}

https://xkcd.com/927/

[Yaron Haviv]

Everything is an Object

why not view everything as an object. Blocks, files, ..

today in storage we have a narrow vision of what Objects are (e.g. cannot be modified, need to be served via HTTP, ..) if we think of Objects like programmers and add the notions of properties, methods, & events and flexible yet fast Ethernet based protocol you would be able to map block sectors, files, records, or any other form of data to such "data objects" and without compromising on performance

My 2c

Yaron

SDSBlog.com

[chris coreline]

erm. FC is just a transport layer for SCSI anyway.

NVMe should replace SCSI for anything 'new' in 5 years, probably over RoCE but there is no accounting for

a) taste

b) expensive core Fibre Channel networks which will work fine with whatever fNVMe transport arises.

Object may replace CIFS/NFS in a similar timescale, but i doubt microsoft will react well to anything disturbing their CIFS protocol, which is tied into everything from cluster management to printer management....

[Alex McDonald 1]

To quote a colleague, if you've managed to get a file handle to an object, you're doing objects all wrong. Object protocols shouldn't support POSIX-like semantics. Files are for when you want to be stateful; objects are RESTful.

Anyhow, back to the question you were posed. There's a hashtag on Twitter for this; #QTWTAIN. It's short for "Questions To Which The Answer Is No".

[celticnomad]

The proposition is Nonsense.

For Protocol read transport and for mechanism read destination.

Mapping this to the physical human world I'd say a comparison is that we either travel everywhere by Space ship (even to the corner shop) , or foot (even to the moon) , complete bonkers .

The protocol/transport and destination/mechanism choices should be determined by what best fits the requirements of the data usage (application, latency requirements, etc) .. until we get the equivalent of instantaneous matter transfer for humans, multiple solutions will (and should) exist.