On the 23rd of February, Nimble Storage announced their new Predictive Flash platform as an extension of their current product portfolio. It uses the same trusted software, but leverages the speed of flash and advanced analytics to offer higher performance storage. A customer expects data to be available instantly and without delays. Nimble Storage makes sure this is the case based on a three-pronged approach: high density solid-state storage, cloud based management and big data analytics to proactively solve issues before they cause a problem for the business.
I first met the Nimble Storage team at Storage Field Day 6. Back then they impressed mightily with InfoSight: Nimble’s cloud based management platform for their storage arrays. It offered proactive failure detection by gathering statistics from all Nimble Storage arrays and using that intel to automatically resolve issues before they could become a hassle for the customer. It also allowed the Nimble engineering teams to blacklist upgrade paths, making sure that a known faulty software upgrade did not inadvertedly cause downtime on other storage arrays. Now, a year later, Nimble is celebrating its fifth birthday and I can’t help but notice: it’s come far since the start-up phase.
NexGen has been building hybrid storages for several years: systems with spinning disks for capacity and flash for performance. This is a skill set that will not go away with the onset of all-flash Arrays. There are many types of flash available and each type of non-volatile memory will have advantages and disadvantages in capacity, performance, cost, power draw, etc. Mixing those characteristics properly inside one array allows a vendor to leverage the strengths of each technology. Say Hi to the hybrid all-flash arrays!
Reliability of a system is usually expressed as a percentage of uptime. A system that has an uptime of at least 99,9% should typically not exceed an unplanned downtime of roughly 8 hours and 45 minutes each year. ‘Five nines’ or 99,999% of availability is often used in IT: this equates to roughly 5 minutes of downtime on a yearly basis. For Infinidat this wasn’t good enough, so they built the Infinibox with a reliability of 99,99999%. That’s only 3.2 seconds of downtime per year. Yikes!
I can’t hide the fact I was looking forward to the Qumulo presentation at Storage Field Day 8: I love scale-out NAS systems, with all the advantages they bring in terms of performance, scalability, manageability and upgradeability. I quickly learned that the founders of Qumulo previously worked on Isilon and OneFS. I work with Isilons in the field, so my interest was peaked
Back to Qumulo: they build a data-aware, scale-out, primary storage system. And it’s software defined. Meaning you’ll have full flexibility in the hardware you want to use and how big/fast/expensive you want to make the system. Plus it also gives you real-time insight into the data on the Qumulo system. Interested? Read on!