Telcos around the world have long recognized the value of Emulex I/O solutions but today, Emulex has announced planned advanced features that will enable them to more quickly develop and deliver quality network services to customers. The new features include packet processing enhancements and enhanced programmability for the Emulex OneConnect® OCe14000 series of 10Gb and 40Gb Ethernet (10/40GbE) Network and Converged Network Adapters (CNAs). The new features enable telecom equipment manufacturers (TEMs) and telecom operators to accelerate the deployment of Network Functions Virtualization (NFV) solutions. 6WIND and Emulex have partnered to develop the Emulex Poll Mode Driver (PMD) for increased packet processing and performance updates to the Data Plane Development Kit (DPDK), a set of data plane libraries and network interface controller drivers for fast packet processing on industry standard servers. These updates are based on the new Emulex open SURF application programming interface (API) which speeds performance and deployment of NFV workloads.
The Benefits for Telcos: Continue reading…
By Jeet Nagda
What is the right connectivity “tool” for the right job? We plan to explore this very question as it relates to Fibre Channel and its future for next generation data centers, with Ben Woo, managing director of Neuralytix.
It’s no secret that Fibre Channel is the handy wrench that people keep around for years to solve the real problems of storage. It is a mature technology, well understood by the industry and already implemented in low latency, high performance environments. And it’s still alive and well. An excerpt from the research note authored by Ben on behalf of Emulex, entitled “The Future of Fibre Channel” states:
“The design of modern storage systems, with its multi-protocol architectures and software-definition, does not eliminate the dependencies on underlying block storage devices. To meet the demands of massively parallel high-bandwidth applications, storage systems depend on an even higher performing underlying subsystem (Fibre Channel) to sustain the performance.” Ben Woo, Neuralytix.
As Fibre Channel ports continue to grow, with flash arrays becoming more prominent in today’s data centers, emphasis on scale-up databases, dense virtualization and ultra-fast solid state disk (SSD) makes Fibre Channel the clear choice for preferred enterprise storage network. Join us on Tuesday, April 22 at 11 a.m. PT to learn more, register now!
Today, I have the opportunity to walk the show floor at the National Association of Broadcasters (NAB) convention in Las Vegas with more than 90,000 others viewing the wares from more than 1,500 companies. Why would I do this to myself after I just spent three days doing much the same thing at Interop in Las Vegas last week? I’m there to witness the explosion of 4K video along with a number of Emulex partners, including CacheIO, Echostreams and Studio Network Solutions (SNS).
With new 4K video cameras capable of offering outputs of 4,000 pixels wide, media companies now have the ability to provide content at 4x the resolution of current high definition standards. In order to meet the high I/O, bandwidth and latency needs of the video production, post-production and streaming processes, storage companies are turning to Emulex LightPulse® Gen 5 (16GFC) Fibre Channel (FC) technology to achieve the best performance for their customers.
Today we announced that we are working with CacheIO, Echostreams and SNS to deliver high performance storage and caching appliances for 4K and 8K media production, post-production and streaming. These companies have leveraged the Emulex OneCoreTM Storage Software Development Kit (SDK), a comprehensive solution for independent hardware and software vendors (IHVs and ISVs) and system integrators to create target side drivers in a custom, high efficiency environment, for storage, flash/solid state disk (SSD) and applications that require low latency and high performance I/O connectivity. The Emulex OneCore Storage SDK offers the widest range of storage applications and comprehensive back-end support, as well as support for all Emulex I/O connectivity solutions, including FC Host Bus Adapters (HBAs) and the newly announced OneConnect® OCe14000 family of Ethernet and Converged Network Adapters (CNAs).
- CacheIO (booth #SL10810): With SSD bandwidth of up to 140Gbps, and scaling up to 48TB SSD capacity, the CacheIO Flash Array is ideal for 4K/8K media production. The CacheIO FA140 Flash Array now incorporates Emulex LightPulse Gen 5 FC HBAs for optimized target connectivity for production and post-production workflow. The form factor of the LightPulse Gen 5 FC HBAs enables production workstations to access up to nine simultaneous uncompressed 4K streams form a single 2RU CacheIO array.
- Echostreams (booth #SL10810): The FlacheSAN2 is a 2U high performance SSD flash storage appliance. With dense storage capacity and numerous I/O expansion slots, it is ideally suited for digital content streaming at the network edge. Emulex Gen 5 FC technology, using the Emulex OneCore SDK, provides an extremely high performance, low latency target for Echostreams.
- Studio Network Solutions (SNS) (booth #SL10827): SNS EVO is a complete, networked storage server solution for video/film/TV, graphics, visual effects, animation, audio, and broadcast production environments. SNS EVO shared media storage server is a blend of simplicity and performance. By integrating a NAS and a SAN into one system, customers get the benefits of both file sharing and volume sharing. Emulex Gen 5 FC technology brings the latency and performance requirements to meet the needs of these diverse customers.
This is the best bet you can make in Las Vegas today! Avoid busting in black jack, rolling snake eyes at the craps table and seeing that random line of apples, grapes and cherries, which result in you not getting that 95 percent payout the casino advertised on its slot machines. With Emulex and the storage partners who utilize our technology, you are going to make top dollar back on your investment.
…For data centers built on Open Compute Project (OCP) designs that is! The Open Compute Project Foundation is a rapidly growing community of engineers around the world whose mission is to design and enable the delivery of the most efficient server, storage and data center hardware designs for scalable computing. The OCP designs are maximized for total cost of ownership (TCO), energy efficiency, and reduced complexity in the scalable computing space. To that end, Emulex has released the OCm14000-OCP series of Ethernet and Converged Network Adapters (CNAs) for data centers utilizing OCP-based server designs.
By taking a quick look at the chart below, you will see that Emulex has packaged up some very nice advanced features for cloud and enterprise network use as well as for converged data centers–features that are above and beyond what you’ll find in other competitive products.
- Open Enablement of Software-defined Networking (SDN): The recently introduced Emulex SURF open API, provides the tools needed to implement SDN technology that can be optimized for next generation applications and new industry standards, such as OpenStack, CloudStack and OpenFlow.
- High-Performance Virtualization: OCm14000-OCP adapters uses highly efficient and scalable hardware offload technology to transfer the overhead of virtual networking, providing up to 50 percent better CPU utilization1 compared to standard NICs when used for VMware VirtualWire connection, thereby increasing the number of VMs that can be supported per server. In addition, the OCm14000-OCP adapters deliver a fundamental 4x performance increase in small packet network performance,2 which is required to scale transaction-heavy and clustered applications.
- Rapid, Secure and Scalable Cloud Connectivity: Emulex Virtual Network Exceleration™ (VNeX) offload technology provides up to 70 percent better performance1 vs. software-only implementations of emerging overlay network standards such as Network Virtualization using Generic Routing Encapsulation (NVGRE) used by Microsoft Hyper-V Network Virtualization and Virtual Extensible LAN (VXLAN) used in VMware NSX. These overlay network standards enable virtual and cloud environments to scale beyond the limitations of Layer 2 networks and support seamless migration from anywhere to anywhere.
- Optimized Application Delivery with Advanced RDMA over Converged Ethernet (RoCE) Architecture: The OCm14000-OCP adapters are based on a low-latency RoCE architecture that help enterprise IT and cloud data centers optimize unstructured and file-based storage environments, which are based on Windows Server SMB Direct and Linux NFS protocols.
- Increased Block Protocol Performance: The OCm14000-OCP adapters increase total block protocol I/O operations per second (IOPS) by 50 percent over previous generation CNAs2 and build upon the proven history of enterprise-class storage reliability at Emulex.
Available configurations include single and dual-port 10GbE SFP+ Ethernet Network Adapter models and a single-port 40GbE Ethernet[KL3] Network Adapter model, as well as a dual-port 10GbE QSFP+ CNA model. The OCm14000-OCP- series of adapters adhere to the mezzanine card specification for OCP v2.0 motherboards.
The OCm14000-OCP series of adapters will be available starting in calendar Q3 2014.
- Based on Emulex Implementers Lab blog
- Based on Emulex Labs testing
By: Rick Trujilio, product marketing manager, Endace division of Emulex (blog cross posted from Endace on Network Visibility blog)
I just love this time of year. Not only is it finally warming up outside after this unseasonably cold winter, but we are in full swing with March Madness and the Final Four is shaping up for a thrilling conclusion. Yeah, and my NCAA tournament bracket picks didn’t make me a billionaire either, but there is still a chance to win big as I just happen to be heading to Las Vegas. Yes, that’s right, it’s that time again for Interop, where there is an opportunity to learn about the latest IT technology innovations.
We are exhibiting at Interop in booth #1158, scheduled from Tuesday, April 1 through Thursday, April 3 at the Mandalay Bay Convention Center in Las Vegas.
We will be giving presentations in our booth theatre every hour on the half hour on a variety of topics, including our OneConnect® network connectivity products and Endace® network visibility products. Learn about how Emulex products are used in overlay networks, software-defined networking (SDN), as well as improving response times for security incidents. And, just for listening to our presentations, all of our attendees will receive a promotional giveaway and a chance to win an iPad Air. Don’t miss out!
Here is a rundown of the sessions we’ll be presenting:
Tuesday, April 1, 2014
2:30 p.m.: Emulex OneConnect Open Compute Project (OCP) 10 & 40GbE Adapters, Barbara Porter, Sr. Product Marketing Manager, Emulex
3:30 p.m. : What? Who? When? How Network Visualization Can Help You Answer the Difficult Questions that Arise from Security Breaches, Sonny Singh, Channel Marketing & Alliances Manager, Emulex
4:30 p.m. : Overlay Networks, Brandon Hoff, Director of Product Marketing, Emulex
5:30 p.m. : Emulex OneConnect Open Compute Project (OCP) 10 & 40GbE Adapters, Barbara Porter, Sr. Product Marketing Manager, Emulex
6:30 p.m. : What? Who? When? How Network Visualization Can Help You Answer the Difficult Questions that Arise from Security Breaches, Sonny Singh, Channel Marketing & Alliances Manager, Emulex
Wednesday, April 2, 2014
11:00 a.m : Overlay Networks, Brandon Hoff, Director of Product Marketing, Emulex
12:00 p.m. : Software Defined SANs, Scott Ruple, Marketing, Jeda Networks
1:00 p.m. : What? Who? When? How Network Visualization Can Help You Answer the Difficult Questions that Arise from Security Breaches, Sonny Singh, Sr. Channel Marketing & Alliances Manager, Emulex
2:00 p.m.: Emulex OneConnect Open Compute Project (OCP) 10 & 40GbE Adapters, Barbara Porter, Sr. Product Marketing Manager, Emulex
3:00 p.m. : Software Defined SANs, Scott Ruple, Marketing, Jeda Networks
4:00 p.m. : Next Generation EndaceDAG™ Data Capture Card, Rick Trujillo, Product Marketing Manager, Emulex
Thursday, April 3, 2014
11:00 a.m.: 12:00pm: Software Defined SANs, Scott Ruple, Marketing, Jeda Networks
12:00 p.m.: Next Generation EndaceDAG Data Capture Card, Rick Trujillo, Product Marketing Manager, Emulex
1:00 p.m.: Emulex OneConnect Open Compute Project (OCP) 10 & 40GbE Adapters, Barbara Porter, Sr. Product Marketing Manager, Emulex
1:00 p.m.: What? Who? When? How Network Visualization Can Help You Answer the Difficult Questions that Arise from Security Breaches, Sonny Singh, Channel Marketing & Alliances Manager, Emulex
In addition, for the second year running, Emulex has been selected to provide its EndaceProbe™ Intelligent Network Recorders (INRs) to record all of the activity on the Interop network, otherwise known as InteropNet (read our related blog here for all of the details). We are proud to provide a critical service to such a modern and cutting-edge network!
Don’t gamble on your network visibility infrastructure (or your network connectivity, for that matter!). Come by and learn how we can help you gain full visibility into your network and help you resolve your most critical network and security issues while reducing your network downtime and outages.
By Jeet Nagda
Today, we announced the newest release of our OneCore Storage Software Development Kit (SDK). Our OneCore Storage SDK is a comprehensive solution for independent hardware and software vendors to create target side drivers. Developers can continue to hit the target of custom software efficiently, with 100% accuracy every time. Bullseye!
What goodies did we add into this major release?
• Improved compatibility with back-end environments including RHEL 6.4 and FreeBSD 9.2
• Linux-iscsi.org (LIO) Preview (now called Target Core Module or TCM)
• Support for our recently launched OneConnect® OCe14000 family of Ethernet Network Adapters and Converged Network Adapters (CNAs). Support for our blazing fast 40Gb Ethernet (40GbE) speeds will be coming in the next update!
• Support for N_Port Identification Virtualization (NPIV)
• Challenge Handshake Authentication Protocol (CHAP) for iSCSI and MC/S (Multiple Connections per Session) for iSCSI failover
• Continued support for SCST, RAMD
This means our SDK is now compatible with nearly all of the protocols you could imagine using, including Fibre Channel over Ethernet (FCoE), iSCSI, and, of course, Fibre Channel. Professionals who use the SDK now have a modularly designed kit that supports most back-end interfaces and protocols.
Additionally, the aforementioned NPIV support allows implementation of T10 Protection Information (T10PI) which provides enhanced data protection against silent data corruption. So keep your eyes peeled for an invite to our webcast on March 4, where we will be giving out some prizes and revealing the full details of the latest features.
In my previous blog, “Great Migrations in IT – Cloud, Big Data and the Race for Web-Scale IT. It’s All About Business Agility!”- I talked about the efforts of enterprises to capture some of the cost and agility benefits, which are inherent in cloud service providers. Today, I would like to focus on another topic – the need for high performance I/O in the data center and what Emulex is doing to conquer those high peaks (performance requirements) that confront us in some of the world’s largest enterprise data centers (and increasingly, in much smaller data centers too).
In the world of mountain climbing, there is a list of mountains known as the seven summits representing the peaks on each continent with the highest prominence. There are very few people who have conquered all seven of these peaks; in fact, www.7summits.com lists 348 people as of the end of 2011 who were known to have accomplished this feat.
To scale these peaks, one must possess a mix of traits, including strength, agility, adaptability, stamina and determination. These peaks, or the challenges represented by them, remind me of the challenges many data centers encounter to meet the ever-growing demands of their user population. Explosive growth in data that is available to the organization, which must be analyzed to provide real time business intelligence, sounds like a Mount Everest-sized feat. Increasing virtual density of servers needed to provide on-demand services to customers, while controlling both capital expenditure (CAPEX) and operational expenditures (OPEX), sounds like the effort it takes to scale Mount Aconcagua. And don’t even get me started on the high performance I/O requirements it takes to scale the application performance needs of my customers on Mount McKinley. Okay, too far, but you get my meaning.
Recently, Emulex announced its new line of Ethernet Network Adapters and Converged Network Adapters (CNAs). This new line of products, the OCe14000 family, is based on the Emulex Engine (XE) 100 series of I/O controllers. A key capability of this controller is the ability to accelerate applications using Remote Direct Memory Access (RDMA) over Converged Ethernet (RoCE).
RoCE is a networking protocol and standard that directly addresses two key limitations of current compute and networking architectures, namely overhead created by data copies between user (application) and kernel memories and latencies introduced by the TCP/IP protocol.
RDMA is fundamentally an accelerated I/O delivery mechanism. It introduces the concept of “zero-copy” data placement, which allows specially designed RDMA (Network Interface Cards (NICs) on both ends of a transaction (also called an R-NIC) to transfer data directly from the user memory of the source server to the user memory of the destination server bypassing the operating system (OS) kernel.
Bypassing the kernel lets applications issue commands to the NIC without having to execute a kernel call. The RDMA request is issued from user space to the source (local) R-NIC and over the Ethernet network to the destination (remote) R-NIC without requiring any kernel involvement. This reduces the number of context switches between kernel space and user space, while handling network traffic.
Because the RDMA data transfer is performed by the DMA engine on the R-NIC, the CPU is not used for the memory movement, freeing it to perform other tasks, such as hosting more virtual workloads.
RDMA reduces latency and improves throughput by bypassing the host TCP/IP stack, relying instead on high performance InfiniBand (IB) protocols at Layer 3 (L3) and higher layers in combination with industry-standard Ethernet at the Link Layer (L2) and Physical Layer (L1). RoCE leverages Converged Ethernet, also known as Data Center Bridging or Converged Enhanced Ethernet as a lossless physical layer networking medium. RoCE can especially benefit from DCB Priority Flow Control (PFC) for lossless transmission, Enhanced Transmission Selection for class of services and 802.1Q Congestion Notification (QCN) for congestion avoidance. This bypass of the TCP/IP stack in favor of IB protocols implemented in adapter hardware is the fundamental differentiator, and improvement with RoCE, when compared with the older Internet Wide Area RDMA Protocol (iWARP).
A simplified architecture of RoCE architecture with zero-copy data placement is shown below. The removal of the TCP/IP stack and a data copy step reduce overall latency to deliver accelerated applications performance.
As this feature is deployed in coming months, we plan to provide explicit support for protocols such as Microsoft Windows Server’s Server Message Block (SMB) 3.0 Direct and Linux Network File System (NFS). These protocols represent use cases and applications in our customer base, which are ripe for high performance I/O capabilities.
With Microsoft Windows Server 2012 R2, Microsoft enabled Hyper-V live migration to leverage SMB Direct. This allows the Hyper-V files to travel more efficiently to the destination server during the migration, effectively accelerating the act of migrating a virtual machine across the network. Due to the CPU efficiency of RDMA, this is accomplished without imposing a huge CPU tax on the server during the migration. According to Microsoft, additional SMB Direct acceleration capabilities include:
File storage for virtualization (Hyper-V™ over SMB). Hyper-V can store virtual machine (VM) files, such as configuration, virtual hard disk (VHD) files, and snapshots, in file shares over the SMB 3.0 protocol. This can be used for both standalone file servers and clustered file servers that use Hyper-V together with shared file storage for the cluster.
Microsoft SQL Server over SMB. SQL Server can store user database files on SMB file shares. Currently, this is supported with SQL Server 2008 R2 for stand-alone SQL servers. Upcoming versions of SQL Server will add support for clustered SQL servers and system databases.
Traditional storage for end user data. The SMB 3.0 protocol provides enhancements to the Information Worker (or client) workloads. These enhancements include reducing the application latencies experienced by branch office users when accessing data over wide area networks (WAN) and protecting data from eavesdropping attacks.
As you can see, traditional Microsoft shops have plenty of opportunities to leverage the high performance I/O capabilities of an R-NIC using SMB Direct. Truly a McKinley-esque need.
Similar to Microsoft’s SMB, NFS is used as a standard access protocol by many Network Attached Storage (NAS) appliances to provide remote file sharing to multiple diverse clients. Performance is a primary consideration when large files are moved around networks, hence the need for high performance I/O via RDMA.
Increasingly, NAS and NFS are also being considered for relational databases, such as Oracle, which have traditionally been housed on Storage Area Network (SAN) connected arrays. With native RDMA support, NFS becomes a stronger option for Oracle databases. Due to their mission-critical nature, databases demand high performance storage capabilities with low latency. This need increases the pressure on the storage and I/O community to provide this robust and high performance capability.
With NFS, the client (e.g., the Oracle database server) controls the file system and the NAS device appears as local storage. Due to this, vendors have been able to optimize I/O for their specific needs, greatly enhancing performance. However, the one area which cannot be optimized by the application is the network.
Enter Emulex and our high performance I/O. By providing an enterprise-class solution which optimizes the balance between I/O operations per second (IOPS), throughput and latency, Emulex is building on our foundation of providing the highest performing, most reliable connectivity solutions for our customers. The Emulex EngineTM (XE)100 controller, and the OCe14000 family of adapters which will be built using it, establish a base camp for conquering the highest peaks.
When combined with features such as storage protocol offload for FCoE and iSCSI and overlay networks offload for optimizing the efficiency of software-defined networking (SDN), the OCe14000 family of Ethernet Network Adapters will provide data centers with the tools necessary to scale their challenging peaks, much like mountain climbers use belay devices, crampons, and pitons to traverse dangerous terrain.
Great Migrations in IT – Cloud, Big Data and the Race for Web-Scale IT. It’s All About Business Agility!Posted January 22nd, 2014 by Mike Jochimsen
Okay, these are not new terms. Cloud computing and big data, are both concepts and specific products that have been around for years. We keep hearing every year that “this is year of the cloud,” or “this is the year that big data will take off.” That’s not typically the way things happen in IT though. There is no magical switch that, when turned on, creates a new market. New paradigms are adopted gradually – people migrate.
That is exactly what we see happening in IT right now. For example, in cloud computing, the race isn’t over and cloud computing hasn’t won. However, the adoption of cloud computing technologies in the
enterprise data center are far enough along the curve to claim there is a definite trend that is unlikely to reverse. According to Cisco (Cisco Global Cloud Index: Forecast and Methodology, 2012–2017), the migrati
on from traditional data center workloads to cloud workloads crosses the 50% threshold in 2014 and total IP traffic from those workloads passed over that threshold two years ago.
According to the Enterprise Strategy Group (ESG), 72% of Global 2000 companies are beginning to use big data analytics to make decisions (ESG, The Impact of Big Data on Analytics). That seems like a true testament to the value of big data and the business intelligence that can be gained from it. In addition, IDG, in their 2014 IDG Big Data research, reported that that big data initiatives continue to be a high/critical priority for 60% of enterprise organizations (1,000+ employees) and 46% of SMBs (<1,000 employees). They also report that data measured will grow by 76% in the next 18 months.
The IDG survey also indicates that customer investments in big data will largely be for infrastructure to storage and analyze their big data.
More recently, Gartner (Gartner, Use Web-Scale IT to Make Enterprise IT Competitive with the Cloud, May 13, 2013) stated that “by 2017, 25% of Global 2000 e-commerce applications will be supported by a Web-scale IT approach.” “Gartner defines Web-scale IT as “a system-oriented architectural pattern that enables the rapid and scalable development and delivery of Web-based IT services leveraging agile, lean and continuous principles. Web-scale IT is a pattern of global-class computing that delivers the capabilities of large cloud services providers within an enterprise IT setting by rethinking positions across several dimensions.” In a nutshell, this means that CIOs, who are under constant pressure to cut cost and deliver service faster, are looking for examples of world-class data centers who are doing this effectively today and they are seeing Amazon, Facebook and Google leading the charge. These are companies who ignored existing paradigms when they built their data centers and decided to create new ones.
Enterprises are already running cloud workloads in their data centers and analyzing big data to make business decisions. Now, they are also beginning to transform their data centers to resemble those of successful cloud service providers.
- A self-service infrastructure which can rapidly provision services, enables portability of workloads, allows for multi-tenancy and is simple to manage.
- A high performance network which is scalable and provides the right balance of bandwidth, throughput I/O operations per second (IOPS) and latency to meet the diverse performance needs of all of the enterprise applications.
- Data processing and analytics capabilities which support the new data repositories and applications required to get the most value out of new data that is available to the enterprise.
To help enterprises achieve these goals and meet the challenges on their migration to a Web-scale IT operation, Emulex announced today the next generation of its Ethernet technology, the XE100 I/O controller and the OCe14000 family of Ethernet Network Adapters and Converged Network Adapters (CNAs). The XE100 controller provides the following features:
- Support for both 10Gb and 40Gb Ethernet (10GbE and 40GbE) networking with storage protocol offload, offering a balance between high throughput and high IOPS. It also provides fast, efficient storage connectivity for Hadoop clusters and NoSQL databases.
- Virtual Network Fabric and software-defined network support with Emulex Virtual Network Exceleration™ (VNeX) offload technology and concurrent stateless TCP offload support. Emulex VNeX supports emerging industry standards such as Network Virtualization using Generic Routing Encapsulation (NVGRE) used by Microsoft Hyper-V and Virtual Extensible LAN (VXLAN) used in VMware’s NSX.
- RDMA over Converged Ethernet (RoCE) delivers application and storage acceleration through faster I/O operations with upcoming support for Windows Server SMB Direct and Linux NFS protocols. In addition to microsecond-class latency performance for applications such as solid state disk (SSD) access, database clusters, clustered file systems and Hyper-V live migration, the XE100 series enables end users to fully realize the benefits from the consolidation of multiple networking services on a single high-speed Ethernet adapter platform.
The new OCe14000 line of adapters will ship in Q1 and the great IT migration will…continue. We just hope we can make it go a little quicker and smoother for all concerned.
Today, we announced our latest round of partners who have certified our Gen 5 16Gb Fibre Channel (16GFC) Host Bus Adapters (HBAs) for interoperability with their software or storage. The latest round of endorsements come from our friends at ATTO, Bloombase, Imation, Permabit and Violin Memory. This great cross section of the industry further represents that Emulex’s leading position in Gen 5 FC is continuing to roll right along.
Okay, that’s all well and good, but as a customer, you are rightfully asking “why should I care?” I’ve got one word for you – growth. If you aren’t experiencing growth in your data storage capacity needs, then you aren’t yet aware of all of the sources of data generation that are snowballing in front of you.
The fact is that storage growth is continuing rapidly. According to Gartner (Market Trends – Evolving HDD and SSD Storage Landscapes, 30 Oct 2013) storage will ONLY grow between 35%-50% annually through 2016, and that low number is due primarily to storage efficiency products. Storage growth is due to data generation growth. That is coming from your normal enterprise application growth (financial applications, order management, supply chain, etc.) as well as the numerous sources of big data that touch your company in increasing numbers every day.
Back to your primary concern – “why should I care?” Your employees, customers and suppliers are all part of the problem. They allparticipate in this massive proliferation of data that needs to be stored, secured, compressed, deduplicated, backed up and analyzed! Emulex and its partners participate in helping you to minimize the impact of this massive tsunami of data.
Imation: The Imation Nexsan E-Series™ SAN storage system is targeted at midsized organizations needing an extremely dense and highly reliable solution. Imation’s expertise in capacity-optimized storage has led to leading efficiencies at the lowest possible cost-per-terabyte for applications like disk backup and bulk storage, tailored to fit in any environment whether traditional, virtual or cloud.
Imation has certified the Emulex Gen 5 FC HBAs with the Nexsan E-Series so that customers can benefit from the increased bandwidth, I/O operations per second (IOPS) and reduced latency.
Violin Memory: Violin Memory flash memory arrays accelerate business critical applications and enabling fully virtualized and optimized IT infrastructures. Designed for sustained performance with high reliability, Violin flash memory arrays scale to hundreds of terabytes and millions of IOPS with low, spike-free latency. Violin Memory has certified the Emulex LPe16000 Gen 5 FC HBAs as initiators against its 6000 Series flash memory arrays. This configuration was used in the recently published Storage Switzerland report on designing a two million IOPS architecture.
ATTO Technology: ATTO provides end-to-end solutions to help customers better store, manage, and deliver their data. ATTO has certified the Emulex LPe16000 Gen 5 FC HBAs with its FastStream storage controllers, FibreBridge 6500 bridge and FibreConnect 8GFC and 16GFC switches, providing low latency, guaranteed bandwidth for time-sensitive applications, streaming media, virtualized, backup and recovery applications.
Permabit: As a leader in data efficiency technology, Permabit delivers Albireo, an embedded high performance OEM data optimization software to storage, application, and integrated IT vendors. Permabit has certified the Emulex LPe16000 Gen 5 FC HBAs with Albireo, which enables storage vendors to deliver high speed data deduplication for primary, archive or backup storage tiers that utilize either traditional hard disk drive (HDD) or flash based storage.
Bloombase: Bloombase delivers application-transparent data at-rest encryption security for next-generation data centers. Bloombase has certified the Emulex LPe16000 Gen 5 FC HBA in servers with Bloombase StoreSafe, an all-in-one storage security software-appliance to lock down sensitive enterprise data stored in SAN for any business applications from ERP, content management, to big data analytics, etc with least infrastructure change
And finally, the Emulex advantage:
- Industry Leading FC Performance: up to 1.2 million IOPS on a single-port to meet today’s performance hungry applications, PCIe 3.0 servers, SSDs and backup application demands.
- Better for Database Applications:
- Three times faster for Oracle Database*
- Two times faster for Microsoft SQL Server*
- 4.6 times faster in 8Gb Mode*
- Greater IT Productivity: twice the management tools and takes half the time to install and manage versus other HBAs.
- Maximum Uptime to Meet SLAs: Highest published reliability data with more than 10 million hours mean time between failure (MTBF) on the LightPulse family of HBAs. LightPulse HBAs run cooler than others and utilize passive heat sinks for optimum realiability.
- Advanced Data Integrity: Protection against silent data corruption with T10 Protection Information (T10 PI) on 8GFC and Gen 5 HBAs.
- Market Leadership in Gen 5 FC HBAs: deployed by more OEMs than any other Gen 5 FC (16GFC) HBA brand.
*Demartek HBA Evaluation (Dec. 2012)
By Mark Jones, director, technical marketing, Emulex, and president of the Fibre Channel Industry Association
The FCIA (Fibre Channel Industry Association) just announced that the INCITS T11 standards committee has completed the physical specification that will be the maximum speed for the next generation of Fibre Channel (FC) products. 32GFC is now the fastest serial lane technology designed for transporting storage data. It effectively doubles the throughput of a single link to 3,200 MB/s in each direction. This announcement is the trigger point by which Fibre Channel vendors can now begin to design their 32GFC capable offerings. It is expected that an ecosystem of 32GFC adapters and switches will begin to emerge commercially during 2015.
New standards don’t come about by accident, a coalition of technology companies make up the INCITS T11 standards committee that contribute and guide the technical language to make up a technology standard. The FCIA is the nonprofit marketing organization that creates and manages the Fibre Channel speed roadmap, the timetable of where Fibre Channel has come from, and the future of where it is going. The roadmap goals are purposeful, increase the speed in modest steps that match the typical data center equipment refresh cycle of 3-5 years. To complement this timetable, the FCIA has maintained a requirement that all new specifications have a backward compatibility requirement of at least two generations. Together, this means that data centers that invest in Fibre Channel can adopt the latest Host Bus Adapters (HBAs) with higher speeds and maintain compatibility to current switch/storage investments, a window of compatibility of between 9-12 years in theory.
All Fibre Channel speeds up to this point have been serial lane technologies, using only a single pair of signals and associated components which helps to keep costs low. You may hear of faster technologies such as 40Gb Ethernet (40GbE) or 56 Gb InfiniBand (56GIB), but these are multi-lane technologies made up of slower base speed lanes. Multi-lanes add more components which leads to greater costs and complexity, with that comes backward compatibility and connectivity challenges.
Also, for the first time, FC-PI-6 uses Forward Error Correction (FEC), which improves the reliability of Fibre Channel links through the recovery from bit errors that occur in high speed networks. FEC helps minimize or avoid data stream errors that can lead to application performance degradation or outages.
Now that INCITS T11 has finished FC-PI-6 they will begin work on the next step. We will likely next see a parallel version of 32GFC called 128GFCp next year which will be ideally suited to reduce switch frontplate space by reducing port counts for interswitch links. Will 64GFC be the next base speed for Fibre Channel?