Gartner predicted 75% of databases in the cloud by 2022. The industry debate focused on migration – but not on the question that mattered most: what happens to performance?
Blog
Don’t Call It A Comeback
flashdba returns from retirement to ask the question nobody in the cloud conversation was asking: when 75% of databases move to the cloud, what actually happens to performance?
The Final Post: Hardware Is Dead
Seven years in the all-flash storage industry ends with one conclusion: hardware has lost the battle. The real competition now is in software, cloud and the economics of abstraction.
Flash Debrief: The End (part 1)
A retrospective on seven years in the All-Flash storage industry – from Violin Memory’s $2bn valuation to Chapter 11, through acquisitions and consolidation, to the conclusion that the flash wars had only one winner: cloud.
Oracle ASM and Thin Provisioning – How To Reclaim Space
Thin provisioning lets storage arrays report more capacity than they physically have – but Oracle ASM doesn't automatically return space when data is deleted. Here's how to reclaim it.
All Flash Arrays: Scale Up vs Scale Out (Part 2)
Scale-out adds performance by adding controller pairs, but forces unnecessary hardware spend when only capacity is needed. Combining independent scale-up and scale-out is the architecture that makes composable storage possible.
All Flash Arrays: Scale Up vs Scale Out (Part 1)
Enterprise storage has two independent requirements: capacity and performance. Scale-up-only architectures struggle to address both – hitting metadata and DRAM ceilings before either dimension is adequately satisfied.
The Flash Insider: To POC or Not To POC?
Guest Post I'm excited announce another guest blog written by my good friend and funny-talking American cousin Nathan Fuzi. Like me, Nate comes from a database background but joined the all-flash storage revolution back in its infancy. Which means, like me, Nate how has a little tombstone on his résumé marked Violin Memory. But even though he … Continue reading The Flash Insider: To POC or Not To POC?
All Flash Arrays: Active/Active versus Active/Passive
Active/passive architecture limits a storage array to 50% of its available controller performance – and costs more per unit of throughput than a true active/active design.
All Flash Arrays: Controllers Are The New Bottleneck
When flash eliminated mechanical latency, the bottleneck moved – from the persistence layer to the controllers. Deduplication and data reduction now place crushing demands on controller CPU and DRAM.







