Storage Networks

Bigger Isn’t Always Better

by Scott Shimomura on ‎02-04-2016 01:52 PM (1,466 Views)

Does size matter in the data center? With Cisco’s launch of the 9718, I am reminded of what it’s like to shop at Costco. You are surrounded by enormous versions of products that you don’t necessarily want or need. Who needs a jar of mayonnaise when you can get a gallon vat of mayonnaise?  Why buy the king-sized bag of Cheetos when you can buy the jumbo seven pound sack? Or why buy six or even twelve rolls of toilet paper when you can buy thirty?


The problem is when you get home, where are you going to put this stuff? Will you ever use it? Buying bigger seemed right at first, but then you have the inevitable regrets that you didn’t buy smarter.


Costco… I mean Cisco added the MDS 9718 to its director product family to address a requirement that we don’t hear from storage customers. They aren’t asking us to build a larger chassis or massively increase port density. They are asking for technology that enables operation stability, predictable performance, and simple scalability. Cisco didn’t build that… they launched a monolithic chassis (based on a Nexus 7718 IP switch) designed to address high port density that comes at the expense of massive size and unbelievable energy consumption. Fun fact: a fully populated 9718 draws more energy than 11 average US homes. 


INFINIDAT Guest Post: Teaming Up to Stop Legacy Infrastructure Band-Aids

by ene ‎01-20-2016 02:23 PM - edited ‎01-20-2016 02:24 PM (1,955 Views)

Clients should not have to make choices between availability, scalability, and performance manageability. Enterprise Storage should be easy-to-deploy and seamless to manage. At INFINIDAT we believe in the importance of storage without compromise. To do so, we recommend pairing our revolutionary InfiniBox with a strong partner ecosystem to deliver best-in-class datacenter solutions for our clients.


The Network Matters for NVMe, Wait What?

by Scott Shimomura on ‎12-07-2015 06:00 AM (3,962 Views)

While all-flash and hybrid arrays are finally becoming mainstream in the data center, there is a new wave of innovation on the horizon that will enable even better application performance. Server-side storage isn’t new, however Non-Volatile Memory Express (NVMe) is emerging as a new storage platform that will drive massive performance gains.




Applications will see better random and sequential performance by reducing latency and enabling much more parallelism through an optimized PCI Express (PCIe) interface purpose-built for solid state storage.


So why does networking matter for host-based storage? On the surface, it would seem counterintuitive. However, what do you do when you want to share storage or want high availability functionality such as failover? Simple, you connect the storage over a fabric. The NVM Express over Fabrics initiative was started to begin to address these needs. While there are Ethernet with RDMA, Infiniband-based and Intel Omni-Path fabrics, they leverage networking technologies that are not widely deployed for enterprise storage. This means potential NVMe customers would have to deploy additional networks to support their storage.


Building the Edgeless Data Lake with EMC IsilonSD, Connectrix VDX, and the New IP

by jbleess ‎11-16-2015 09:45 AM - edited ‎11-18-2015 09:20 AM (4,278 Views)

The combination of a New IP architecture along with the launch of the Datalake 2.0 strategy by EMC, has added new tools to extend the traditional boundries of the datalake. Combining IsilonSD for remote or temporary locations with our VCS Fabric based Isilon core, allowed a reanalysis of the unstructured data we manage. 




Strategic partnership between Brocade and QLogic has resulted in co-developing a set of advanced features designed to streamline and reduce time for provisioning, increase the reliability of data transfers, and add resiliency and improved management visibility. The features leverage Fabric Vision and extend management functionality and simplicity for joint customer and further differentiates Brocades products in the storage market.


Brocade and Emulex Advance Gen 5 End-to-End Across The Network

by Tim Lustig ‎10-28-2015 05:01 AM - edited ‎10-28-2015 07:40 AM (2,474 Views)

Technology has been an enabler since the first hand tools and cultivation of agriculture begun. Continually improving life and increasing human productivity based on skills learned and passed down over generations and tens of thousands of years. The accumulation of knowledge and the ability to progress technology by sharing information accelerated with Johann Gutenberg’s invention of the printing press. The launch of the Internet in 1991 further facilitated the sharing of information and smart phones made accessing information much easier by placing it right in an individual’s palm. Due to this, we have seen an accelerated speed at which communication occurs and subsequently, over the years, an increase in technology development.


In 2014 Brocade and Emulex entered into a strategic relationship with a focus on advancing Fibre Channel technology.


We recently recorded a series of videos at VMworld US 2015 with a few of our partners to talk about why the network is important when it comes to storage. When going back and watching these videos one statement stands out. Jerimiah Dooley, Principal Architect for SolidFire, says “Of all the customers that use SolidFire today, how many of the end users, ones that are using the applications, know what switch vendor is providing connectivity? The answer is none of them.” He goes on to say they should never know because when everything is working properly they don’t care. However, as soon as something doesn’t work the way it’s supposed to everyone will know which vendor is to blame. This is one of the most important reasons programs like Brocade’s Solid State Ready program (SSR) are in place to make sure the integration between the storage and the network infrastructure is as seamless as possible and has been validated by both companies.


Storage, networking and virtual advances are driving a huge impact in places you might not expect. In the case of The Jim Henson Company, most notably known for Muppets and Sesame Street characters, these technologies are being leveraged to drive new programming and ventures.


In recent years, The Jim Henson Company has been developing new ways to take traditional puppetry to the digital animation space. It has developed advanced simulation capabilities driven by the company’s own animation software engine, a workstation using a joystick and a digital glove, and actors with body sensors enabling puppeteers to manipulate a digital puppet exactly like they would a physical puppet.


Recently a new infographic titled “What Happens in an Internet Minute? caught my attention, not because of the facts, but rather the questions it provoked. What is happening within my applications in the data center?


Today, flash technology and high-performance storage networks have changed the way we think about applications and their performance. The diagram below can easily be substituted with enterprise’s mixed mission-critical and non-critical applications.


Avoid Outages and Re-syncs with Extension Trunking

by Scott Shimomura on ‎08-24-2015 07:00 AM (2,179 Views)

In storage environments, reliable and resilient networks — to the point of no frame loss and in-order frame delivery — is necessary for error-free operation, high performance, and operational ease. This improves availability, reduces operating expenses and, most of all reduces the risk of data loss. Brocade addresses today’s important trends and requirements with the Brocade Extension Switches with Brocade Extension Trunking.


Extension Trunking is an advanced feature of the Brocade Extension platforms for both Fibre Channel and IP extension, enabling bandwidth aggregation and lossless failover for increased resiliency over IP WANs. It provides load balancing and network resilience to increase WAN utilization and protect against WAN link failures. This video details the operation and advantages of this technology in extended storage applications.


Best-In-Class Vendors Partner to Build A Best-In-Class VDI Solution

by Nanjunda Somyaji ‎08-18-2015 09:00 AM - edited ‎10-07-2015 07:22 AM (8,847 Views)

Few years back, enterprises were evaluating Virtual Desktop Infrastructure (VDI) to see whether VDI is a viable technology while reducing cost of operations. As proof-of-concept, they deployed VDI in a selected group to evaluate and understand the issues. During this time, VDI was still expensive, hard to manage and Enterprises did not see expected ROI.


Fast forward and VDI technologies have matured thanks to technologies that include: Virtual SAN, vRealize Operations and LogInsight, better networks and low-cost flash storage. These developments are pushing enterprises to deploy VDI across the organization’s infrastructure.


Today’s organizations depend on fast, reliable access to data wherever and whenever needed, regardless of location. The ramifications and potential business impact of an unreliable disaster recovery and data protection infrastructure are greater than ever.


The Brocade 7840 Extension Switch provides a suite of features — from pre-deployment validation to advanced network failure recovery technologies — to ensure a continuously available storage extension infrastructure. One unique feature is Adaptive Rate Limiting which dynamically adjusts bandwidth sharing between minimum and maximum rate limits to optimize bandwidth utilization and maintain maximum WAN performance during disruptions.


Sharing Isn’t Always a Good Thing

by Spencer Lail on ‎08-11-2015 05:00 AM (3,047 Views)

For many of us, preschool and kindergarten were all about learning how to share. But in the IT world, sharing isn’t always a good thing. You need to carefully identify when and where it makes sense to share if you want to operate as efficiently as possible.


Consider that just a few years ago IP storage was considered a departmental or “non-critical” storage solution—primarily for workloads that weren’t considered core elements to business success. The general lack of Tier 1 tools, performance, reliability, and scalability kept IP storage from being a truly “production-ready” solution for most organizations.


How to Drive High-Throughput Over Distance

by Scott Shimomura on ‎08-10-2015 07:00 AM (3,624 Views)

The advanced performance and network optimization features of the Brocade 7840 Extension Switch enable replication and backup applications to send more data over metro and WAN links in less time, and optimize available WAN bandwidth. Supporting up to 250ms Round-Trip Time (RTT) latency, the Brocade Extension Switch enables cost-effective extension solutions over distances up to 37,500 kilometers (23,400 miles).


Never Disrupt Your Replication Again with Firmware Updates

by Scott Shimomura ‎08-03-2015 07:00 AM - edited ‎08-03-2015 01:50 PM (2,702 Views)

Hot Code Load (HCL), also known as Non-Disruptive Firmware Upgrades, have been available for Fibre Channel platforms for a long time, but not for the extension platforms. With the recently announced Brocade 7840 Extension Switch, HCL is now available for extension switches. This feature is critical for replication in mission critical environments where companies cannot afford to take their infrastructure down while they upgrade. With the higher data rates everyone is dealing with, even a short window of disruption can cause you to fall behind and open yourself up for risk.


Many organizations have converged various disparate networks over time into a common IP/Ethernet network. The business reasons for consolidation are certainly there as this approach should reduce capital costs and fewer networks to manage should reduce complexity, management and operational costs. And if you need to segment the network, it can be done with VLANs, virtual routing and forwarding instances or overlays on the single shared IP/Ethernet network, right?


The benefits do sound compelling, but in practice most organizations seldom take this approach for various business and technical reasons. This also is the case with IP storage networks.


Unexpected consequences. They’re everywhere in life. All the time, all over the world, someone is making a plan to solve a problem. Unfortunately, it’s difficult for most of us to envision the full impact or range of tradeoffs associated with that plan.


For example, think about a family moving to a bigger house. With a home twice the size of their old one, they now have more room for the kids, additional space to grow, and a solution to key problems (like not having enough bathrooms). But did the parents properly plan for all the costs this new home entails? Are they ready for double the cost of heating and cooling bills? Have they braced for the higher taxes and additional maintenance work?


Move over Godzilla. There is a new sheriff in town.


EMC unleashed “The Beast” this week at EMC World, which is their new aptly named software upgrade for XtremIO 3.X all-flash storage that more than doubles supported all-flash capacity to 40TB, with the ability to cluster eight of these monsters together with consistent and predictable sub-millisecond performance.


EMC World 2015: More About IP Extension

by mdetrick ‎05-06-2015 08:00 AM - edited ‎05-06-2015 11:55 AM (5,095 Views)

IPEX is based on 5 pillars. These tenants are distinctly different, crucial to many environments, and made up the design criteria for Brocade Extension Engineering. To review, they are:


  • High Performance (covered in part 2 of 3 in this series)
  • Operational Excellence
  • Superior Availability
  • Strong Security
  • Easy Deployment 

Today, we will discuss the remaining four pillars.


Saturday’s Fight of the Century in Las Vegas elevated Floyd Mayweather to global prominence as the world’s best welterweight boxer. 48-0; one shy of Rocky Marciano’s undefeated career record. Mayweather turned in a vintage performance as he outboxed Manny Pacquiao in a brilliant display to win a unanimous decision in one of the biggest fights in boxing history.


Like Saturday’s epic event, EMC made history today on the global Las Vegas stage at EMC World by bringing its heavyweight, high-end storage systems to the EMC VSPEX family, further strengthening its position as the undisputed, world champion of reference architectures sold exclusively through channel partners. Brocade is proud to be in the same corner as EMC for this new VSPEX solution, as the storage networking foundation, connecting EMC VMAX3 100K storage with high-performance servers.


EMC World 2015: It’s all about Performance!

by mdetrick on ‎05-05-2015 08:00 AM (2,706 Views)

Welcome back to the second installment on Brocade 7840 IPEX. Today’s blog is all about improving performance of IP storage applications between data centers, a cornerstone of IPEX. There is A LOT to this pillar, so, I’ve devoted today’s entire blog to just to this subject. Here is a list of pertinent Brocade technologies implemented in IPEX that enhance native IP storage performance:


  • Purpose built hardware and software
  • Intolerant IP storage applications
  • WAN Optimized TCP
  • TCP Acceleration
  • End-to-End Flow Control
  • Data batching
  • Jumbo Frames
  • Adaptive Rate Limiting (ARL)
  • QoS (Enforcement and Marking)
  • Compression
  • Scalability

EMC World 2015: Take Control with IP Extension

by mdetrick on ‎05-04-2015 07:30 AM (4,854 Views)

Good morning EMC World 2015! Here we are again in Las Vegas pursuing the latest technological advancements for our storage and cloud environments.


This year EMC and Brocade are proud to present something entirely new: IPEX (IPEX = IP Extension) on the Brocade 7840 (EMC Connectrix MP-7840B). You say, Hummm… Why do I need extension for IP? I’m sure you’re thinking, can’t I just handoff my IP storage flows to the network? Of course, I hope the Network Admins meet their SLAs (Service Level Agreements) so I can meet mine! Who out there wants to have SLA responsibility that in turn relies on the network SLA, of which you have no control? Yep, that’s what I thought… No One!


Redefine Networking for IP Storage

by Scott Shimomura ‎04-29-2015 10:00 PM - edited ‎05-26-2015 09:32 AM (10,194 Views)

Traditional Ethernet networks were never designed to address the needs of IP storage.


When was the last time you thought about the network connecting your IP storage? Was it when you had to wait for a few weeks to get ports provisioned for new storage? Was it when the network was taken down for routine maintenance and you had to plan for an outage? Or when you had a network outage and waited for hours for it to come back up in order to recover the storage?


Unlike your Fibre Channel SAN, you probably don’t own or manage the network for your IP storage. If you are like many of the customers we have met with over the last year, you are looking for better ways to manage growth, mitigate risk, and reduce costs. It’s clear that shared networks simply cannot handle the growth of business-critical workloads on IP storage.


Traditional Ethernet networks were never designed to address the needs of IP storage.


Don’t Get Caught with Data Security Gaps

by Jim Rapoza on ‎04-27-2015 12:01 AM (4,172 Views)

When important people need protection, how does it usually work? For example, a president, prime minister or other world leader? Typically, if there’s any kind of expected threat, it’s full protection round the clock, everywhere and with no margin for error.


Now imagine that, instead of this kind of protection, a world leader under threat had multiple locations that were very secure but, when they moved between locations, instead of armored cars and lots of bodyguards, they had to run alone through the streets to get to their destination?


(Dateline: A major enterprise data center, in the year 2020) Running an enterprise storage network sure is a lot different than it used to be. Back in the old days (circa 2015) we were mainly concerned with our traditional data center, keeping the big iron storage up and running and ensuring our networks were fast enough to handle regular backup and restore requests.


Now those days look like the stone-age. Software defined? Forget about it. The storage infrastructures of 2020 are way beyond that, pulling in massive amounts of data in real-time, making it constantly accessible to a variety of analytics tools and applications, and doing so across locations and geographies on fast and flexible networks and virtual storage infrastructures.


Businesses have come to recognize that the combination of big data technologies, new data sources and evolving analytic approaches present an opportunity to drive competitive advantage and accelerate innovation. But many are struggling with where to start to begin taking advantage of the business value that these new technologies promise.


Today’s launch of EMC’s Federation Business Data Lake (FBDL) changes that. With the FBDL, IT can quickly and easily clear the path for more timely and informed business decisions. The solution provides a fully engineered, enterprise-grade data lake tuned to the strategic priorities of a business that can help to quickly realize the value of big data analytics.



If you ask someone in a given field of endeavor "What is critical to success?" they'll most likely focus on one or two key elements. For instance, in Hollywood, someone might point to the director and the stars as critical. A football fan might mention the head coach and the quarterback. In the IT world, a discussion of enterprise applications will likely turn to critical systems such as ERP and CRM.


Your Own IP Storage Network? It's Time to Drive Change

by AJ Casamento on ‎03-13-2015 10:00 AM (101,077 Views)

I know, I know. There's a world of difference between managing a storage network and running a fleet of 18-wheelers.


Or is there?

Bear with me, and imagine for a moment that you’re the boss of a freight shipping company.


To Prevent Data Gridlock, You Need a Smarter Highway

by Jim Rapoza on ‎03-11-2015 12:54 PM (54,205 Views)

Have you ever noticed how, just when you need to be somewhere fast, a traffic jam suddenly appears?




Making sure that there are an adequate number of buffer credits on a link, particularily an ISL link, is difficult when one is doing it by hand. The attachment provided here uses Microsoft Excel to provide a fairly robust, in-the-ballpark capability to determine the number of buffer credits necessary on a link of any speed, any average frame size, any distance and which also includes the user's capability to compress and/or encrypt the data in-flight.



This is an updated spreadsheet with just a minor change to how buffer credits get calculated.


How can we improve the Community?