Howard Marks

Network Computing Blogger


Upcoming Events

Where the Cloud Touches Down: Simplifying Data Center Infrastructure Management

Thursday, July 25, 2013
10:00 AM PT/1:00 PM ET

In most data centers, DCIM rests on a shaky foundation of manual record keeping and scattered documentation. OpManager replaces data center documentation with a single repository for data, QRCodes for asset tracking, accurate 3D mapping of asset locations, and a configuration management database (CMDB). In this webcast, sponsored by ManageEngine, you will see how a real-world datacenter mapping stored in racktables gets imported into OpManager, which then provides a 3D visualization of where assets actually are. You'll also see how the QR Code generator helps you make the link between real assets and the monitoring world, and how the layered CMDB provides a single point of view for all your configuration data.

Register Now!

A Network Computing Webinar:
SDN First Steps

Thursday, August 8, 2013
11:00 AM PT / 2:00 PM ET

This webinar will help attendees understand the overall concept of SDN and its benefits, describe the different conceptual approaches to SDN, and examine the various technologies, both proprietary and open source, that are emerging. It will also help users decide whether SDN makes sense in their environment, and outline the first steps IT can take for testing SDN technologies.

Register Now!

More Events »

Subscribe to Newsletter

  • Keep up with all of the latest news and analysis on the fast-moving IT industry with Network Computing newsletters.
Sign Up

See more from this blogger

Nimbus Goes All-In For SSD

In the venture-driven, "grow-faster-or-go-home" storage world, it's gratifying when a company is run like the small business that it is. Nimbus Data systems has been selling iSCSI disk arrays and unified storage systems for about five years, and they've been making money despite their low profile. Now, like Cortez burning his ships upon his arrival in the New World, Nimbus data CEO Tom Iskovich is betting the company that the market is ready for all SSD storage systems, discontinuing their current models with spinning discs. I've written before how I thought an array of reasonably priced SSDs might be a better idea than a few STEC ZEUSiops at $10,000 or more a pop.  Now Nimbus has proven me right.

I haven't yet had a chance to bring an S-class -- which frankly sounds too much like a Mercedes-Benz for my taste -- into the lab to test Nimbus' claims of 500,000 IOPS for a base 2.5TB system and 1.3 million IOPS for the 100TB full rack version. But even if it turns out to be half as fast as Nimbus claims, that's still a bargain.

Nimbus is lowering the price by building their own solid state drives using Micron's extended-life MLC flash chips. While these devices don't deliver the 100,000 erase cycle lifetimes typical of the SLC flash typically used for enterprise storage, their 30,000 cycle projected lives are a big step up from the 10,000 cycles the MLC typically used in laptop SSds can deliver. To put things in perspective to run a 2.5TB S-class through 30,000 cycles a customer would have to write 41TB a day for five years. Nimbus further boosts flash-endurance by over provisioning the system by 28 percent to give wear-leveling algorithms in the controllers and their HALO OS some breathing room, as well as equipping the S-class with 48GB of RAM for caching so repeated writes never make it to the flash devices in the first place.

To put Nimbus's pricing in perspective, let's look at some of the other options that a mid-size company would consider. The base S-class costs $10/RAW GB or a nickel per IOP.  A Dell Equallogic PS600XV with 16 300GB 15K RPM drives costs about the same on a dollar per GB basis but delivers less than 1/10th the IOPS. Looking for flash performance?  $25,000 might get you three 200GB enterprise flash drives from EMC for your Clariion or an Equallogic PS6000s with eight 50GB SLC SSDs. Way less than 1/5th the capacity of the Nimbus.

But the S-class isn't just a dumb flash array. Nimbus's HALO OS -- shipping for years with spinning disks -- supports thin-provisioning, synchronous and async replication through a dedicated 1Gbps Ethernet port, multi-path I/O and all the IP storage protocols a sane person could want from CIFS and NFS to iSCSI. To top it all off, while Nimbus doesn't use ZFS they do include ZFS/WAFL data deduplication. Nimbus has even thought through the network interfaces, equipping the S-class with four 10Gbps Ethernet ports then providing 1000Base-T SFP+ transceivers so that users who haven't yet made the leap to 10Gbps Ethernet can use the system out of the box and just swap transceivers when they get a 10Gbps switch.


Related Reading


More Insights


Network Computing encourages readers to engage in spirited, healthy debate, including taking us to task. However, Network Computing moderates all comments posted to our site, and reserves the right to modify or remove any content that it determines to be derogatory, offensive, inflammatory, vulgar, irrelevant/off-topic, racist or obvious marketing/SPAM. Network Computing further reserves the right to disable the profile of any commenter participating in said activities.

 
Disqus Tips To upload an avatar photo, first complete your Disqus profile. | Please read our commenting policy.
 
Vendor Comparisons
Network Computing’s Vendor Comparisons provide extensive details on products and services, including downloadable feature matrices. Our categories include:

Research and Reports

Network Computing: April 2013



TechWeb Careers