I have heard something like this before
"There is nothing new to be discovered in physics now. All that remains is more and more precise measurement." - Lord Kelvin, shortly before quantum mechanics and general relativity.
Despite my enthusiasm about recent upgrade announcements, there’s a part of me that wonders: who really cares about arrays these days? The announcements from IBM, HDS, NetApp and the inevitable EMC announcement later in the year just leave me cold. The storage array is nearly done as a technology: are we going to see much more …
That's going to be interesting, For synchronous replication we have got to have the two ( or more) storage devices at the same" data point" before we signal to the server that the data is on the media. The further you go, the longer it takes the signal to return from the remote unit that it is on the media - anyone got any ideas on how we we increase the speed of light?
This is a serious and possibly fatal weakness in VSAN strategies. Vendors seem to extoll the virtues of storage mashups without getting into the detail of achieving no single point of failure. That makes VSANs a retrograde step.
This is consistent with the new instance storage mentality, whereby a local SSD is used to boost performance n an instance. That approach abandons virtualization, since loss of a node can cause actual data loss, given the no repair mentality of CSPs. The result is that jobs are in essence running in a hosted services model rather than a true virtualization model.
VSAN advocates blithely assume that "flexibility" is good, but the concept ignores too many real world constraints. Power efficiency and cooling, efficient networking, and ease of management are all understood in traditional storage, while it's still hard to see any thought of this behind all the VSAN and SDN hype.
here is a diagram on how 3PAR does this(since 2009 anyway), I believe a few others do it too
http://www.techopsguys.com/wp-content/uploads/2012/12/3par-sync-longdistance-replication.png
pdf that talks about it
http://h20195.www2.hp.com/V2/GetPDF.aspx%2F4AA3-8318ENW.pdf
Synchronous replication over long distance?
But the techops link (diagram) clearly shows Synchronous on short distance only and Asynchronous (and periodic) for long distance.
Within the HP Technical white paper it says:
"...HP 3PAR Remote Copy can help limit these costs with our Synchronous Long Distance topology where data is replicated to a nearby data center in synchronous replication mode while simultaneously being replicated asynchronously with Periodic Asynchronous mode...".
Keywords: Synchronous for nearby and Asynchronous for long distance. A good feature to do both from a single source but certainly not Synchronous over long distance. Can we agree?