In #publiccloud you presume that scale out is happening. I don't think any public cloud provider isn't using scale out tech under the covers in order to provide elasticity.
where often non-scale out products can be cheaper on a short term basis as their design cost has long been amortized. Think Networker sold for 99% off at times.
In the @IgneousIO view, we evangelize the need to deliver on-premises infrastructure as-a-Service and have strictly separated our data plane from our management plane.
achieving the scale and elasticity offered by most public cloud providers in the DC often requires underlying scale-out infrastructure, issue is having hw resources at the ready without over spending
As a developer today, you can make assumptions that the #publiccloud you are using can scale as you need it. You generally can't make that assumption in the #datacenter.
@johna_white Infinite scale isn't necessarily required, but the scaling increments may be very different - particularly as you deal with fault domains.
would also say that scaleout in #publiccloud is often designed/tested to scale far further with more automation than in the #datacenter . Just a matter of economics...
Most people don't need the ability to massively scale but ask a a developer if he prefers always having resources available when they need or for as long or short as they need it or if they prefer requesting resources from IT and waiting...
I'd call scale-out an interesting inflection point where products with older "design centers" will be overtaken overall by products that are built with scale out in their "design center".
I think that it starts with the software architecture - the algorithms - and that the architecture imposes constraints on the hardware. As Rickover said, "The devil is in the details, but so is salvation."
@fdmts Here you go then. Scale out = An innovative, game changing, and leading solution that leverages actionable synergies across unique, optimized paradigm shifts to deliver bottom line results that you can double click on.
At the compute and storage layer, it's mostly software. You can build some massive scale out systems using standard white boxes. For networking, there are benefits to using custom ASICS to minimize latencies.