March 31, 2015

Musing: Could We Replace Ethernet With PCIe?

oUc4nZF

Greg “EtherealMind” Ferro recently “mused” that it might be a good idea to replace PCI Express (PCIe) inside servers or rack-scale infrastructure with Ethernet. But this seems to be the exact opposite of the direction the industry is headed. Rather than replacing PCIe with Ethernet, companies like Intel seem set on replacing short-range Ethernet (in rack-scale systems) with PCIe!

vSphere 6: NFS 4.1 Finally Has a Use?

VMware has adopted NFS 4.1

Way back in the 1990’s, UNIX admins delighted in upgrading from NFSv2 to NFSv3. Then NFSv4 came around and … crickets. Now VMware has become the first major/useful/mainstream application for NFSv4.1, so the floodgates are open! But are they?

Why Big Disk Drives Require Data Integrity Checking

You might think RAID is for data protection, but it does nothing of the sort!

Hard disk drives keep getting bigger, meaning capacity just keeps getting cheaper. But storage capacity is like money: The more you have, the more you use. And this growth in capacity means that data is at risk from a very old nemesis: Unrecoverable Read Errors (URE).

The Rack Endgame: Open Compute Project

SAfa

On reading my thoughts about the evolution of enterprise storage, many pointed out that this looks an awful lot like the Facebook-led Open Compute Project (OCP). This is entirely intentional. But OCP is simply one expression of this new architecture, and perhaps not the best one for the enterprise.

Cisco’s Trojan Horse

Cisco's UCS C3160 is a "storage server" for the all-Cisco rack

Industry watchers like me have long wondered when Cisco will transform itself into a full-line IT infrastructure vendor. This strategy was tipped in 2009 as Cisco barged into the server market with UCS. But one leg of the stool is still missing: Storage remains the province of Cisco partners like EMC and NetApp.

The Rack Endgame: A New Storage Architecture For the Data Center

Top of rack flash, bottom of rack capacity, and software gluing everything together!

Top-of-rack flash and bottom-of-rack disk makes a ton of sense in a world of virtualized, distributed storage. It fits with enterprise paradigms yet delivers real architectural change that could “move the needle” in a way that no centralized shared storage system ever will. SAN and NAS aren’t going away immediately, but this new storage architecture will be an attractive next-generation direction!

Virtualized and Distributed Storage: This Time For Sure!

The principles of data physics suggest that data should be located closer to compute

We were never able to achieve storage virtualization in mainstream enterprise IT because we lacked the ability to identify and move data non-disruptively. This has been solved by caching and distributed storage solutions, and it’s only a matter of time before the legacy need for centralized storage falls away.

#VMEspresso with @SolarWinds at #VMworld: “Storage I/O is About to Get Crazy”

Join me for #VMEspresso at #VMworld courtesy of @SWI_Systems

Join me for “Storage I/O is About to Get Crazy”! I’ll be speaking on Tuesday morning, August 26, at 7:30 AM at Jillian’s San Francisco, right on the corner next to Moscone and the rest of VMworld. SolarWinds is sponsoring this talk and will provide breakfast (including gourmet coffee) to any and all registered VMworld attendees.

Cloud Without Virtualization

Gigaom Structure 2014

Lots of folks conflate cloud computing and virtualization, but these are not necessarily intrinsically related. Although most cloud servers today use a hypervisor like KVM or Xen to share compute hardware, there’s no reason it has to be this way. My takeaway from Gigaom Structure this week is that an alternative paradigm is emerging: Cloud without […]

Is Storage the Killer App for Software-Defined Networking?

onug_logo

Software Defined Networking (SDN) has always looked a bit like a solution in search of a problem, at least in the enterprise data center. But there are lots of potential applications that need a dynamic and scalable network. In my mind, storage is chief among these, since scalability and flexibility has always been extremely difficult to achieve.