Gary Orenstein, Fusion-io, at PerconaLive 2014 with John Furrier and Jeff Kelly @thecube #PerconaLive Broadcasting from PerconaLive : MySQL Conference and Expo, theCUBE co-hosts John Furrier and Jeff Kelly invite Gary Orenstein, Fusion-io CMO, who takes the opportunity to announce some new features around his company's flashware applications. Orenstein begins with some background on Fusion-io, describing how it started with a basic question: If we want to optimize the entire stack, what's the path? Fusion-io believes that path begins with optimizations around flash memory. With that mantra in mind, perhaps the most notable of Fusion-io's announcements this week is the new NMV Compression, a flash-aware interface that can double the usable capacity of Fusion-ioMemory while eliminating the performance impact associated with disk-era compression algorithms common in flash SSDs. Orenstein says NMV can deliver up to 4x more flash endurance by streamlining commands to optimize MySQL databases for persistent flash memory architectures when integrated with Atomic Writes interface. The end result is a diminishing overhead for using compression with MySQL. Another big news item the hosts asked Orenstein about was WebScaleSQL. This week Google, Facebook, LinkedIn, and Twitter launched project WebScaleSQL, in which engineers of four companies will come together to solve the problems of information processing in massive databases. As the name implies, WebScaleSQL is a fork of MySQL (right now, that's MySQL 5.6), optimized for large scale databases. WebScaleSQL will broaden existing activities in the MySQL community. Orenstein quotes in their words, "A branch of MySQL that will be optimized for the type of web transactions that they're working on." An interesting takeaway from the announcement for Orenstein is that these are four companies we inherently trust with our data. Additionally, they didn't go and build something net-new, but instead built on improving an already existent technology. A quarter of multi-DMSs already run on MySQL, Orenstein notes, reminding that we've already seen very successful models for sharding, or partitioning the database to grow it. So MySQL has proved it can scale, it just scales differently. Companies are becoming increasingly reliant on their ability to capture, process, and present information. In essence, ingest what you can ingest, run analytics and queries, then deliver actionable insights. One thing Fusion-io did was instead of using storage protocols on flash memory, it exposed flash natively to the CPU in the operation system so that it could perform quickly, as opposed to protocols designed for rotating spinning media. That philosophy of thinking about new memory in terms of its potential for the future as opposed to just thinking about it as how it would fit with the past was a huge differentiator for Fusion-io. Applications and databases that rely on storage, previously needed disc drives and DRAM. But now, flash memory is a great new memory tier that is in between, according to Orenstein. It takes the best of disc (persistent) and combines it with the best of DRAM (really, really fast). Fusion-io took a look at compression, recognizing its business appeal. MySQL compression was a no brainer. But why wasn't the community using it? In talking with Fusion-io clients, Orenstein says the feedback they got was that the overhead and cost of a slight performance penalty was turning people off. Fusion-io knew they had a win that was just waiting to be tackled, compressing data and gaining more usable space. So Fusion-io went to work. By exposing APIs from flash memory to MySQL, and with a few minor tweaks to MySQL, Fusion-io has been able to essentially eliminate the overhead impact. Its clients are now able to utilize the compression that's built into MySQL. Users are seeing a huge gain in usable capacity. Fusion-io takes a very workload specific view. That means that with topline performance, they want to get as close to the end user as far as that performance is possible. In their research, they're noticing that latency consistency is fast becoming a performance must. Orenstein stresses that companies need to seek out what works for them. Topline performance, dollar costs, space costs, power costs...companies should come up with the right equation that works for their specific workload. Kelly chimed in that it sounds a lot like mapping business requirements to the technology. Orenstein and Furrier agree — in some cases flash is going to be relevant, same for SQL and MySQL. But it's a workload specific question and there is no silver bullet. "The good news is that while the scale of those problems might be different between one of these web giants and a smaller company, the nature of the problems is not that different," says Orenstein.