But make no mistake: while marketing slides and vendor presentations suggest that everything "SD" is magic and easy, this is certainly not the case! "SD" at its best may enhance flexibility (customer choice of common hardware building blocks) and provide lower TCO, but the underlying mechanics and infrastructure still needs to provide the functions and performance levels of today's specialized products! So -as always- there's no free lunch here!
Point in case: read this article about the claimed TCO's for the CISCO ACI solution!
Good old Ethernet -as a protocol- is currently undergoing a major boost in terms of standardized speeds and -as a result- increased number of use cases. One of them is the new segment of "Ethernet disk drives". A very promising way of providing access to HDDs directly attached to standard Ethernet (thus no SATA, SAS, ...) as "The Register" writes in this article about a recent Seagate announcement here: "Kinetic is the object storage platform Seagate has built to make it possible to so useful work with its Ethernet-equipped disk drives. Seagate's ambition is to cut arrays out of the loop, allowing software to talk directly to disks. By cutting arrays and file systems out of the loop, Seagate reckons it can save users some cash and also speed things up."
To accommodate the increasing performance requirements of today's networks, the Ethernet Alliance has recently issued an updated roadmap including native 25 Gb/s which is supposed to be productized as early as 2015!
"The Ethernet Alliance recently released its 2015 roadmap, which outlines Ethernet’s response to the ongoing desire for more bandwidth in data centers by adding new speeds for both in-rack and backbone connections. The roadmap calls for some eye-popping speeds in the future, but also charts out a plan for the low end of the market, representing an unprecedented level of activity for Ethernet."
Read the complete article here!
With my longterm Fibre Channel background, I was wondering of course where this leaves the storage protocol which is still dominating most of the datacenter connectivity between compute and storage: For a number of agreeable reasons, as outlined in this great article here, you may argue that FC has a somehow limited future: "Pundits have long predicted the demise of Fibre Channel, but this time it's real. In fact, the decline has already begun and now that RoCE is routable, this decline will accelerate. The last years Dell’ Oro SAN report highlighted a 3% year over year decline in Fibre Channel revenues, citing the need for “distributed scale-out and object-based storage” and a preference for "Ethernet speeds and converged infrastructure.""
Would you agree?
Posts
No comments:
Post a Comment