Showing posts with label Data Center. Show all posts
Showing posts with label Data Center. Show all posts

Thursday, March 7, 2019

Source Photonics expands data center and routing portfolio

Source Photonics has expanded its portfolio of single-mode products for datacenter and routing applications. The new products leverage the company’s multi-year investment in 28Gbaud and 53Gbaud PAM4 developments and support applications such as the 400G DR4, FR4 and LR8, 100G DR/FR, and 50G LR and ER.

In addition, Source Photonics also announces the availability of its second-generation 100G QSFP28 CWDM4.

“Source Photonics led the market deployment of small form-factor 10 km products for several generations,” says Ed Ulrichs, Director of PLM at Source Photonics. “The performance of our advanced 50G, 100G and 400G PAM4 based products prove our technical and production capabilities to lead scale of the entire 500m to 40 km portfolio.”

Source Photonics’ portfolio of Datacenter and Routing products include:

  • 400G LR8 supporting 400GE links up to 10 km; the platform is expandable to support 400G-ER8 for 400G links up to 40 km by 2020
  • 400G DR4 supporting 400GE links for 500m as well as enhanced reach of up to 2 km; the platform supports breakout into 100G-DR/FR as well as high-density 100GE links
  • 400G FR4 supporting 400GE links up to 2 km over duplex single-mode fiber
  • 400G SR8 supporting 400GE links up to 100m (OM4) over multi-mode fiber
  • 100G DR/FR supporting single-channel 100G connectivity and supporting breakout from 400G DR4
  • 100G LR4 supporting 100GE links up to 10 km with support for Ethernet only and OTU4 as well as enhanced performance for E-temp and I-temp applications
  • 100G 4WDM-40 supporting 100GE links up to 40 km with Ethernet only and OTU4 support
  • 100G CWDM4 supporting 100GE links up to 2 km over duplex single-mode fiber
  • 100G SR4 supporting 100GE links up to 100m (OM4) over multi-mode fiber

http://sourcephotonics.com

Tuesday, January 15, 2019

AvidThink: Huawei’s CloudEngine 16800 switch based on Broadcom

Huawei's newly-announced CloudEngine 16800 data center switch is based on Broadcom’s merchant silicon, according to a published report from AvidThink's Roy Chua.

In terms of capacity, the Huawei CloudEngine 16800 data center switch boasts the industry’s highest density 48-port 400GE line card per slot, yielding an overall 768-port 400GE switching capacity.

AvidThink notes that the current top-of-line Broadcom Tomahawk 3 is capable of 32 400GbE ports for 12.8 Tbps switching capacity, less than the 48 400GbE ports on a single Huawei 16800 line card. The report also reveals that Huawei's 16800 will be available for early field trials in Q2 2019.

In addition, Huawei will incorporate its own AI silicon into the switching platform's design for fine-tuned traffic optimization.

https://avidthink.com/analysis/huawei-cloudengine-16800-ascend-ai/

  • AvidThink was formed in the fall of 2018 as an independent research and analysis company focused on technology infrastructure. Prior to that, AvidThink had operated as SDxCentral Research, part of SDxCentral.com, a leading technology media publication.

Huawei's CloudEngine 16800 data center switch boasts 768-port 400GE

Huawei unveiled its CloudEngine 16800 data center switch built for the Artificial Intelligence (AI) era.

The platform has three defining characteristics making it suitable for the AI era: an embedded AI chip, the capacity for a 48-port 400GE line cards per slot,, and the capability to evolve to the autonomous driving network.

Huawei said its embedded, high-performance AI chip will apply an innovative iLossless algorithm for the auto-sensing and auto-optimization of the traffic model. It promises lower latency and higher throughput based on zero packet loss. The company estimates its optimization will increase the AI computing power from 50 percent to 100 percent compared to traditional Ethernet, while improving the data storage Input/Output Operations Per Second (IOPS) by 30 percent. The CloudEngine 16800’s local intelligence and the centralized network analyzer FabricInsight creates a distributed AI O&M architecture capable of identifing faults -- a key goal of an autonomous driving network.

In terms of capacity, the Huawei CloudEngine 16800 data center switch boasts the industry’s highest density 48-port 400GE line card per slot, yielding an overall 768-port 400GE switching capacity. Huawei says power consumption per bit is reduced by 50% with the massive configuration. The company also claims to have overcome multiple technical challenges such as high-speed signal transmission, heat dissipation, and power supply.

http://e.huawei.com/topic/cloud-engine2019/en/index.html?ic_medium=hwdc&ic_source=ebg_banner_EEBGHQ179Q19W

Thursday, January 10, 2019

Huawei's CloudEngine 16800 data center switch boasts 768-port 400GE

Huawei unveiled its CloudEngine 16800 data center switch built for the Artificial Intelligence (AI) era.

The platform has three defining characteristics making it suitable for the AI era: an embedded AI chip, the capacity for a 48-port 400GE line cards per slot,, and the capability to evolve to the autonomous driving network.

Huawei said its embedded, high-performance AI chip will apply an innovative iLossless algorithm for the auto-sensing and auto-optimization of the traffic model. It promises lower latency and higher throughput based on zero packet loss. The company estimates its optimization will increase the AI computing power from 50 percent to 100 percent compared to traditional Ethernet, while improving the data storage Input/Output Operations Per Second (IOPS) by 30 percent. The CloudEngine 16800’s local intelligence and the centralized network analyzer FabricInsight creates a distributed AI O&M architecture capable of identifing faults -- a key goal of an autonomous driving network.

In terms of capacity, the Huawei CloudEngine 16800 data center switch boasts the industry’s highest density 48-port 400GE line card per slot, yielding an overall 768-port 400GE switching capacity. Huawei says power consumption per bit is reduced by 50% with the massive configuration. The company also claims to have overcome multiple technical challenges such as high-speed signal transmission, heat dissipation, and power supply.

http://e.huawei.com/topic/cloud-engine2019/en/index.html?ic_medium=hwdc&ic_source=ebg_banner_EEBGHQ179Q19W



Thursday, December 13, 2018

Data center land in Hong Kong sells for US$697 million

The last remaining plot of land designated for development into a data centre sold for a higher-than-expected HK$5.45 billion ((US$697 million), according to the South China Morning Post. There were nine bidders for the 295,405 square foot property. The buyer is listed as Sunevision Holdings.

https://www.scmp.com/business/article/2177665/hong-kongs-biggest-and-last-data-centre-site-fetches-hk545-billion


Tuesday, November 20, 2018

Google plans EUR 600 million data center in Denmark

Google confirmed plans for a new data center in western Denmark, just outside Fredericia.

The new facility represents an investment of EUR 600 million. Google is securing Power Purchase Agreements with renewable energy sources in Denmark. Construction is expected to be completed in late 2021. This will be Google's fifth data center in Europe, joining sites in Ireland, Finland, the Netherlands and Belgium.

https://www.blog.google/inside-google/infrastructure/breaking-ground-googles-first-data-center-denmark/

Thursday, September 6, 2018

Vantage Data Centers completes Santa Clara data center -- 75MW

Vantage Data Centers completed construction of its final data center at its Santa Clara, California campus, known as V5. The new four-story addition adds 15MW of critical IT load, bringing the campus total to 75MW. This campus is the largest in Silicon Valley. The addition also features a new cooling system that uses a combination of outside air and a chilled water loop, which uses recycled water and modular chiller and dry-cooler technology designed to minimize water usage while maintaining ultra-low PUEs. The water loop also utilizes non-potable grey water, further reducing impact on local water resources. The facility also supports both traditional and high-density data center designs.

“Silicon Valley continues to be a vital and strategic market for our customers,” said Vantage President and Chief Executive Officer Sureel Choksi. “With the final facility on our first Santa Clara campus complete, and construction of our 69MW Matthew Street campus also in Santa Clara well underway, Vantage can support the growth of enterprises, cloud and hyperscale customers well into the future.”

Vantage is also building a new 42-acre, 108MW campus in Ashburn, Virginia. The first 24MW building, which will provide 6MW of initial capacity on this completely new campus, is scheduled to be completed in early 2019.

The new expansion contains several features designed to enhance sustainability while maintaining a low total cost of ownership.

Monday, July 16, 2018

Arrcus builds Network OS for white box data center infrastructure

Arrcus, a start-up based in San Jose, California, emerged from stealth to unveil its software-driven, hardware agnostic network operating system for white boxes.

Arrcus said it sees an opportunity to help enterprises transform the way they manage their networks, liberating them from vertically integrated proprietary solutions and opening the door to horizontally diversified choices of best-in-class silicon and hardware systems.

The company's new ArcOS networking operating system has been ported to both Broadcom’s StrataDNX Jericho+ and StrataXGS Trident 3 switching silicon platforms.

ArcOS is built on a modular micro-services paradigm and offers advanced Layer 3 routing capabilities. Key elements include a hyper-performance resilient control plane, an intelligent, programmable Dataplane Adaptation Layer (DPAL), a data-Model Driven Telemetry for Control Plane, Data Planes and Environmental, and a consistent YANG/OpenConfig APIs for easy programmatic access.  These capabilities in conjunction with Broadcom’s StrataDNX Jericho+ platform enable the support for the full BGP internet routing table.

Arrcus cites the following use cases:

  • Spine-Leaf Clos for Datacenter workloads
  • Internet Peering for CDN providers and ISPs
  • Resilient Routing to the Host
  • Massively Scalable Route-Reflector clusters in physical/container form-factors

Arrcus also announced $15 million in Series A funding from General Catalyst and Clear Ventures. Advisors include include Pankaj Patel, former EVP and CDO of Cisco; Amarjit Gill, serial entrepreneur who founded and sold companies to Apple, Broadcom, Cisco, EMC, Facebook, Google, and Intel; Farzad Nazem, former CTO of Yahoo; Randy Bush, Internet Hall of Fame, founder Verio (basis of NTT’s DataCenter Business); Fred Baker, former Cisco Fellow, IETF Chair and Co-Chair of the IPv6 Working Group; Nancy Lee, ex-VP of People at Google, and Shawn Zandi, Director, Network Engineering at LinkedIn.

“We use ‘network different’ as our fundamental approach to enable the freedom of choice through our product innovation and challenging the status quo.  Arrcus has assembled the world’s best networking technologists, is bringing new capabilities, and changing the business model to make it easier to design, deploy, and manage large scale networking solutions for our customers,” stated Arrcus co-founder and CEO Devesh Garg.

  • Arrcus is headed by Devesh Garg, who previously was president of EZchip (acquired by Tilera) and founding CEO of Tilera (acquired by EZchip). He also served at Bessemer Venture Partners and Broadcom. Other Arrcus co-founders include Keyur Patel, who was a Distinguished Engineer at Cisco; and Derek Yeung, a former Principal Engineer at Cisco.

Thursday, August 24, 2017

Apple picks Iowa for $1.3 billion data center

Apple will build a 400,000-square-foot, state-of-the-art data center in Waukee, Iowa, a town with a population of about 14,000 located in the center of the state, near Des Moines.

The investment is valued at $1.3 billion. Construction is expected to start early next year and be completed in 2020.

The new facility will run entirely on renewable energy from day one.

“At Apple, we’re always looking at ways to deliver even better experiences for our customers. Our new data center in Iowa will help serve millions of people across North America who use Siri, iMessage, Apple Music and other Apple services — all powered by renewable energy,” said Tim Cook, Apple’s CEO. “Apple is responsible for 2 million jobs in all 50 states and we’re proud today’s investment will add to the more than 10,000 jobs we already support across Iowa, providing even more economic opportunity for the community.”

“At Apple, we’re always looking at ways to deliver even better experiences for our customers. Our new data center in Iowa will help serve millions of people across North America who use Siri, iMessage, Apple Music and other Apple services — all powered by renewable energy,” said Tim Cook, Apple’s CEO. “Apple is responsible for 2 million jobs in all 50 states and we’re proud today’s investment will add to the more than 10,000 jobs we already support across Iowa, providing even more economic opportunity for the community.”

https://www.apple.com/newsroom/2017/08/apples-next-us-data-center-will-be-built-in-iowa/


  • Google operates a major data center in Council Bluffs, Iowan


Facebook Plans 4th Expansion of Iowa Data Center


Facebook announced the fourth major expansion of its hyper-scale data center campus in Altoona, Iowa. Specifically, Facebook will add cold storage capabilities to the complex.  The expansion will add more than 100,000 square feet to building 3. Cold storage of Facebook photos and other archival media is currently done at Facebook data centers in Prineville, Oregon and Forest City, North Carolina. 

Wednesday, March 8, 2017

Radisys Announces DCEngine Release 1.0 Management Software

Radisys announced its DCEngine Management Software Release 1.0 for optimizing resources for hyperscale data centers,

The software is now available and shipping integrated with Radisys’ DCEngine product line, which is an open hardware platform based on the Open Compute Project (OCP) CG-OpenRack-19 specification. The specification is a scalable carrier-grade rack level system that integrates high performance compute, storage and networking in a standard 19 inch rack. Future DCEngine Management Software releases will extend these capabilities with a focus on facilitating the deployment and integration of the DCEngine hyperscale data center solution into existing SDN-enabled ecosystems.

Highlights of DCEngine Management Software Release 1.0

  • Intel Rack Scale Design APIs to enable dynamic composition of resources based on workload specific demands
  • Modules for leading data center orchestration frameworks, such as Ansible, to make firmware updates easy and convenient
  • Redfish Interface 1.0 protocol support


“CSPs are evolving their virtualization strategies and deploying data center infrastructure to support high availability applications such as virtualized network functions and real-time data analytics,” said Bryan Sadowski, vice president, FlowEngine and DCEngine, Radisys. “Our new management software for DCEngine delivers essential hardware resource management capabilities that are increasingly needed in this new ecosystem. We’ve reduced the operational pain points for rack scale deployments and operations by building a suite of tools that enable automated and convenient configuration as well as resource management to meet CSPs’ evolving requirements.”

http://www.radisys.com

Tuesday, November 1, 2016

Cisco Brings on Roland Acra as SVP/GM, Data Center Business Group

Cisco announced the appointment of Roland Acra as SVP/GM, Data Center Business Group. He will be responsible for defining the next phase of Cisco data center strategy and driving development for its data center portfolio, including all data center switching products – NX2/4/5/6K, NX3K, NX7K, and NX9K, UCS, SAN, and associated products and programs.

As a long-standing industry expert in Internet routing, software engineering and communication protocol development, Roland fits right in – once again. He

Acra is a Cisco veteran having held several general management and executive leadership positions from 1991 – 2003. In 2010, he came back to Cisco as Vice President in the Smart Grid Business Unit, following the acquisition of Arch Rock , a developer of IPv6-based wireless sensor networks where he served as President and CEO. Prior to Arch Rock, he was the President and CEO of Procket Networks.

http://www.cisco.com

Wednesday, June 8, 2016

HPE Expands its Cloud Portfolio

Hewlett Packard Enterprise rolled out a set of major updates to its cloud portfolio, including:

  • HPE Helion Cloud Suite, a new software suite enabling customers to deliver and manage their full spectrum of applications -- from traditional, virtualized, cloud native and containers -- across a broad range of infrastructure environments. HPE Helion Cloud Suite includes full-stack automation to enable rapid delivery of IT services and applications, and provides a common simplified, self-service storefront for IT and developers. It also includes a complete development environment supporting DevOps processes for traditional and cloud-native applications.
  • HPE Helion CloudSystem 10, an engineered hardware and software solution to build and rapidly deploy an enterprise grade cloud environment for a full range of workloads and offering a deep integration with HPE OneView 3.0 for automatic provisioning of cloud resources from bare metal infrastructure. It delivers hosting, automation and orchestration of traditional and cloud-native workloads. This pre-integrated solution, brings together HPE hardware, storage, networking, software and services into one package.
  • HPE Helion Stackato 4.0, a complete and open application development platform-as-a-service (PaaS) solution, powered by Cloud Foundry, designed to speed the delivery of cloud native applications.
  • HPE Cloudline 3100 Server, offering industry leading economics for service providers. The CL3100 meets cloud service providers' dense storage requirements for Hadoop/Cassandra/compute workloads. The CL3100 (1U) storage server is 75 percent smaller than the CL5200 storage server (4U), requiring a smaller footprint.
  • New HPE Technology Services offerings for IT transformation and workload migration

"No enterprise has a one size fits all approach to cloud -- every customer wants solutions that help them drive their business faster and cut costs across their full spectrum of applications," said Bill Hilf, senior vice president and general manager, HPE Cloud. "Organizations require their own right mix of traditional IT, private, managed and public clouds and the flexibility to support applications spanning different technologies, architectures and delivery models. The HPE Helion portfolio gives customers a simple, powerful set of options, offering the breadth and coverage they need."

http://www.hpe.com

Sunday, June 5, 2016

Cavium's 64-Bit ARM ThunderX2 Packs up to 54 Cores

Cavium unveiled its 64-bit ARM-based ThunderX2 processor for servers in cloud data centers used for workloads such as compute, security, storage, data analytics, network function virtualization (NFV) and distributed databases.

The second generation ARM processor from Cavium, which offers a number of on-board accelerators and advanced capabilities, packs up to 54 cores, enabling it to deliver two to three times the performance across a wide range of standard benchmarks and applications compared to ThunderX. It is built in 14nm FinFET process and is compliant with ARMv8.2 architecture as well as ARM's Server Base System Architecture (SBSA) standard.

Key ThunderX2 features will include:

  • 2nd generation of full custom Cavium ARM core: 2.4 to 2.8GHz in normal mode, Up to 3 GHz in Turbo mode; > 2X single thread performance compared to ThunderX.
  • Up to 54 cores per socket delivering 2-3X socket level performance compared to ThunderX.
  • Cache: 40K I-Cache and 64K D-cache, highly associative; 32MB shared Last Level Cache (LLC).
  • Single and dual socket configuration support using 2nd generation of Cavium Coherent Interconnect with > 2.5X coherent bandwidth compared to ThunderX.
  • System Memory: 6 DDR4 memory controllers per socket; Dual DIMM per memory controller, for a total of 12 DIMMs per socket.
  • Full system virtualization for low latency from virtual machine to IO enabled through Cavium virtSOC technology.
  • Integrated 10/25/40/50/100GbE network connectivity.
  • Multiple integrated SATAv3 interfaces.
  • Integrated PCIe Gen3 interfaces, x1, x4, x8 and x16 support.
  • Integrated Hardware Accelerators: OCTEON style packet parsing, shaping, lookup, QoS and forwarding; Virtual Switch (vSwitch) offload; Virtualization, storage and NITROX V security.

Four versions of the ThunderX2 will be offered:

  • ThunderX2_CP:  Optimized for cloud compute workloads such as private and public clouds, web serving, web caching, web search, commercial HPC workloads such as computational fluid dynamics (CFD) and reservoir modeling. This family supports multiple 10/25/40/50/100 GbE network Interfaces and PCIe Gen3 interfaces. It also includes accelerators for virtualization and vSwitch offload.
  • ThunderX2_ST: Optimized for big data, cloud storage, massively parallel processing (MPP) databases and Data warehousing workloads. This family supports multiple 10/25/40/50/100 GbE network interfaces, PCIe Gen3 interfaces and SATAv3 interfaces. It also includes hardware accelerators for data protection/ integrity/security, user to user efficient data movement.
  • ThunderX2_SC:  Optimized for secure web front-end, security appliances and cloud RAN type workloads. This family supports multiple 10/25/40/50/100 GbE interfaces and PCIe Gen3 interfaces. Integrated hardware accelerators include Cavium’s industry leading, 5th generation NITROX security technology with acceleration for IPSec, RSA and SSL.
  • ThunderX2_NT: Optimized for media servers, scale-out embedded applications and NFV type workloads. This family supports multiple 10/25/40/50/100 GbE interfaces. It also includes OCTEON style hardware accelerators for packet parsing, shaping, lookup, QoS and forwarding.

"ThunderX2 combines our next generation core that will deliver significantly higher single thread performance with next generation IO and hardware accelerators to provide a compelling value proposition for the server market and greatly expand the serviceable server TAM," said Syed Ali, President and CEO of Cavium. "ThunderX2 will enable flexible, scalable and fully optimizable servers for next generation software defined data centers."

http://www.cavium.com


Cavium Unleashes 64-bit ARM-based OCTEON TX

Cavium unveiled its OCTEON TX family, a line of 64-bit ARM based SOCs for control plane and data plane applications in networking, security, and storage.

The OCTEON TX combines Cavium's data plane architecture with its optimized ARMv8.1 cores (the company continues to produce its OCTEON III processors, which are based on MIPS).

The new processors expand the addressability of Cavium’s embedded products into control plane application areas within enterprise, service provider, data center networking and storage that need support of extensive software ecosystem and virtualization features. This product line is also optimized to run multiple concurrent data and control planes simultaneously for security and router appliances, NFV and SDN infrastructure, service provider CPE, wireless transport, NAS, storage controllers, IOT gateways, printer and industrial applications.

Cavium said the control planes of next gen platforms will need to run commercial software distributions and operating systems (e.g., RHEL, Canonical and Java SE), support open source applications (e.g., OpenStack, OpenFlow and Quagga), launch services dynamically and run customer specific services. Multiple types of high performance data plane applications also need to be supported for firewall, content delivery, routing, and traffic management. While current OCTEON SOCs are used in applications for data plane as well as control plane with embedded software, control plane applications requiring wider software ecosystem and support traditionally have been addressed by the x86 architecture. The ARM architecture is able to service these critical needs.

Wednesday, March 9, 2016

Here's what Happened at Open Compute Project Summit

In the five years since its launch, the Open Compute Project (OCP) has chalked up dozens of innovations and technical specification contributions that have been implemented by hyperscale data center operators. The ambitions have now expanded beyond rack hardware to include switching, storage, silicon photonics,  a telemetry framework, an open-source analytics platform and new domain of solutions adapted for telecom operators.

Here are some highlights from this week's OCP Summit in San Jose, California:

  • Hundreds of companies and thousands of developers are now participating in Open Compute
  • Facebook estimates it has saved several billion dollars thanks to OCP
  • The OCP Board of Directors includes Jason Taylor (Facebook), Bill Laing (Microsoft), Don Duet (Goldman Sachs), Mark Roenick (Rackspace), Jason Waxman (Intel), Andy Bechtolsheim, and Frank Frankovsky.
  • OCP has big ambitions for the telecom world which needs efficient infrastructure too. OCP has launched a Telecom Infrastructure Project that includes initial participation from AT&T, DT, EE, Equinix, Nokia, SK Telecom and Verizon.
  • Facebook is moving quickly to bring 100G technology into the network backbone of its hyperscale data centers
  • Intel said its OCP Rack Scale Architecture, with compute shelves, NVMe storage shelves, and network shelves has gained traction from a robust ecosystem of partners.
  • OCP rack servers are moving to a standard 19" design.  This enables system to pack up to 256GB of DDR4 DIMMs on a single motherboard.
  • OCP foresees that specialized workloads, such as security or SDN, will benefit from acceleration boards based on FPGAs.
  • Silicon photonics will soon be a requirement in hyperscale data centers, especially when backbones eventually upgrade beyond 100G.
  • OCP is developing an open telemetry framework for data centers.
  • OCP open telemetry will be matched by an OCP open analytics platform.
  • Microsoft highlighted its role in developing an open switch abstraction interface (SAI) to remove complexity in hyperscale data centers
  • Microsoft's next OCP contribution is Software for Open Networking in the Cloud (SONiC), which allows sharing of the same software stack across hardware from multiple switch vendors. With its modular architecture and lean stack, SONiC allows data center operators to debug, fix, and test software bugs much faster. It also allows the flexibility to scale down the software and develop features that are required for datacenter and networking needs.
  • Artificial Intelligence applications will require highly efficient and massively scalable hardware blocks.  Facebook is bringing these AI requirements to OCP. Its Big Sur AI hardware assembly has already deployed thousands of machines in just a few months. Big Sur is Open Rack-compatible and incorporates eight high-performance GPUs of up to 300 watts each, with the flexibility to configure between multiple PCI-e topologies. It uses NVIDIA's Tesla Accelerated Computing Platform.

  • Google has just joined OCP. The biggest cloud participants also include Facebook, Microsoft and Rackspace.  (still missing Amazon, Alibaba, Apple, LinkedIn, etc).
  • Google's first contribution to OCP is its design for a 48v data center rack.  Google said its design is 30% more energy efficient, in part by minimizing AC-DC conversions.
  • Equinix has announced it is adopting Facebook’s Wedge network switch design and open-source architecture.
  • Goldman Sachs announced that more than 80% of servers that the company has acquired since last summer are based on OCP standards.
  • OCP is introducing Lightning, which is  flexible NVMe JBOF (just a bunch of flash). It is designed to provide a PCIe gen 3 connection from end to end (CPU to SSD). It leverages the existing Open Vault (Knox) SAS JBOD infrastructure to provide a faster time to market, maintain a common look and feel, enable modularity in PCIe switch solutions, and enable flexibility in SSD form factors. 

http://www.opencompute.org/


Thursday, February 11, 2016

CoreSite Posts 25% YoY Rise in Revenue for Data Center Services

CoreSite reported Q4 2015 revenue of $90.9 million, a 25.4% increase year over year and an increase of 5.3% on a sequential-quarter basis. CoreSite reported fourth-quarter net income attributable to common shares of $9.3 million, or $0.32 per diluted share.

Tom Ray, CoreSite’s Chief Executive Officer, commented, “We're pleased to report continued execution of our business plan in the fourth quarter, delivering solid growth and finishing out 2015 as another strong year for our company.” Mr. Ray continued, “In addition to our solid financial results for the fourth quarter, we finished 2015 and began 2016 with positive leasing momentum.

Some highlights:

  • CoreSite executed 155 new and expansion data center leases representing $8.9 million of annualized GAAP rent during the fourth quarter, comprised of 42,089 NRSF at a weighted-average GAAP rental rate of $211 per NRSF.
  • CoreSite’s fourth-quarter data center lease commencements totaled 54,329 NRSF at a weighted average GAAP rental rate of $172 per NRSF, which represents $9.3 million of annualized GAAP rent.
  • CoreSite’s renewal leases signed in the fourth quarter totaled $10.1 million in annualized GAAP rent, comprised of 49,561 NRSF at a weighted-average GAAP rental rate of $204 per NRSF, reflecting a 3.8% increase in rent on a cash basis and 6.7% increase on a GAAP basis. The fourth-quarter rental churn rate was 2.3%.


http://www.coresite.com

Thursday, January 28, 2016

Nokia Incorporates Open Compute Designs into AirFrame Portfolio

Nokia plans to incorporate Open Compute Project (OCP) designs into its AirFrame Data Center Portfolio, aiming to offer greater efficiency, density, cooling and power usage effectiveness.

OCP-based variants for computing, network and storage will be developed in line with OCP specifications, but taking into account the specific needs of the telco domain such as regulatory requirements, Direct Current (DC) power feeding and electromagnetic shielding.

Nokia said it plans to offer a full end-to-end data center solution for telco, IT and enterprise customers, with cloud wise services supporting design and deployment. The OCP-based variants will complement the already available AirFrame rackmount servers launched in June 2015, offering complete flexibility, scalability and reliability for smaller and more distributed data center deployments.

“Nokia’s vast experience, competence and scale will redefine OCP specifications for carrier-grade performance, and we are delighted to extend our collaboration with Facebook and the Open Compute Project. This will ensure that our customers fully benefit from OCP solution efficiencies and performance, as well as the OCP ecosystem, for what is seen as the industry benchmark in hyperscale data center deployments. We see our input into OCP as being vital to ensure data centers can handle the most demanding of workloads,” stated Henri Tervonen, head of Mobile Broadband Architecture at Nokia.

http://networks.nokia.com/news-events/press-room/press-releases/Nokia-AirFrame-portfolio-enhanced-for-hyperscale-data-center-deployments-MWC16

Nokia Launches its AirFrame Data Center Servers and Switches

Nokia unveiled its AirFrame Data Center Solution for combining the benefits of cloud computing technologies with the stringent requirements of the core and radio in the telco world.


The Nokia AirFrame Data Center Solution is the company's foundation for meeting the latency and data processing requirements of the future, including 5G and distributed cloud applications. The portfolio is build around highly integrated, Intel-based servers and switches that are optimized for low-latency, scalability, flexibility and business agility.

Key advantages of AirFrame:

  • Offers significant efficiency gains when running data-demanding telco applications like mobile network Virtual Network Functions (VNFs)
  • Fully compliant with IT standards and able to run the most common IT cloud applications in parallel to telco cloud
  • Enables operators to implement not only their NFV strategy, but also expand into new business models, such as renting data center capacity for customers' IT applications
  • Implements the most advanced telco cloud security practices, which have been tested and approved at the Nokia Security Center in Berlin
  • Adheres to Nokia Networks' open standards approach as well as complies with ETSI NFV, ensuring the success of telco cloud deployments
  • Ready for 5G, with an advanced cloud management solution to handle the telco cloud architecture (centralized / distributed), including security orchestration which automates and manages the lifecycle of security policies and security functions
  • Ready to support several Nokia VNFs, including OSS/CEM and the company's recently announced Radio Cloud architecture

AirFrame components include:

  • Nokia AirFrame Cloud Servers and Switches - Pre-integrated racks with ultra-dense servers, high performance switches and software defined storage, including Nokia Networks specific enhancements that make it more efficient than other solutions to run demanding VNFs
  • Data center services - AirFrame is complemented by a suite of professional services provided by the company's services experts and geared to implement, monitor and operate telco cloud data centers

Wednesday, November 18, 2015

Vapor IO Releases Open Source Platform for Server and Rack Mgt

Vapor IO, a start-up offering a hyper modular data center solution, introduced its Open Data Center Runtime Environment (DCRE) - an open source platform for data center rack and server management.

Vapor IO, which earlier this year introduced its hyper collapsed, disaggregated  data center solution, developed this new OpenDCRE software to simplify data center infrastructure communication. The solution exposes current generation interfaces to data center operators, system and devops administrators, thereby simplifying the programming needed to start automating the physical infrastructure itself.

Vapor IO said OpenDCRE is being released as an open source alternative to proprietary interfaces and custom silicon. This ensures that when a user interacts with their data center, they are communicating over a community owned interface and standard. OpenDCRE is designed to support all data center environments supporting HPE Cloudline and other OCP platforms. OpenDCRE replaces the need for out of band management networks saving users thousands of dollars per rack. Additional features of the product include SSL support, analog sensor and power control support and a simple RESTful API running on Raspberry Pi.

“Data centers have proven to be nothing short of problematic,” said Cole Crawford, founder and CEO of Vapor IO. ”This is primarily due to poorly integrated systems, legacy software and hardware, and the disjointed approach the industry takes to building out data center environments. As IT prepares to support edge based computing, it is imperative we manage and orchestrate our infrastructure as a whole with no prejudice as to where or how many data centers are employed to support our workloads. This is a large feat and we’re thrilled to have support from partners like Future Facilities and Romonet as we move forward.”
OpenDCRE is now available for download and has already generated support from partners such as Future Facilities and Romonet.
 
http://www.vapor.io/products/open-dcre/

Monday, November 2, 2015

Mellanox Open Ethernet Gains Acceptance by Open Compute Project

The Open Compute Project (OCP) has accepted Mellanox Technologies' 10GbE and 40GbE switch systems. This includes:

  • the MSX1710OCP spine switch system, with 36 QSFP+ interfaces
  • the MSX1410OCP leaf / top-of-rack (ToR) switch system, with 48 SFP+ interfaces and 12 QSFP+ interfaces

Both switch systems are based on the company's SwitchX-2 silicon, which is designed for non-blocking 2.56 Tbps full wire speed forwarding with cut-through latency and deterministic zero packet loss performance. Mellanox is a co-author of the Switch Abstraction Interface (SAI), which enables applications and Ethernet protocol stacks to operate seamlessly over any Open Ethernet compatible switch hardware platform. Mellanox was the first to integrate the SAI layer and to offer its free download as an open-source.

“It is exciting to see organizations such as Mellanox take an active role in shaping the future of open networking through not only its open collaboration and participation in the OCP Networking Project, but through its willingness to open the specs and designs around in its SwitchX-2 product line,” said Amber Graner, operations director for the Open Compute Project Foundation. “The Mellanox switch contributions are another great example of how OCP through member participation is accelerating the future of open hardware in the networking ecosystem.”

http://www.opencompute.org/wiki/Networking/SpecsAndDesigns#Accepted_Hardware
http://www.mellanox.com/

Thursday, June 4, 2015

HP and Arista Offer Data Center Reference Architectures

HP announced a new partnership with Arista Networks to provide verified reference architectures for data centers.

The HP Converged Architecture with Arista is designed to support private, public and hybrid cloud applications across compute and storage, including all-flash solutions with HP 3PAR StoreServ. The companies said their open and flexible solutions deliver simplified provisioning and ongoing maintenance, via the application of Arista Extensible Operating System (EOS) and network programmable platforms, with HP OneView integration at its core.

“The joint reference architectures from HP and Arista will deliver a dramatically simplified path to convergence and cloud-efficiency for our joint customers,” said Ed Chapman, vice president of business development and alliances, Arista Networks, Inc. “This will allow customers to rapidly realize the benefits of a converged infrastructure to accelerate their business and improve time to value while remaining flexible for future business needs.”

In addition, HP announced enhancements to its OneView 2.0 management platform, which unifies processes, user interfaces (UI’s) and the application programming interfaces (APIs) across HP server, storage, and Virtual Connect networking devices. The enhancements include new server automation tools for defining firmware and driver baselines as well as server, LAN and SAN settings in one place and consistently provision or update those settings multiple times. Additionally, new profile mobility makes it possible to migrate and recover of workloads across server platform types, configurations, and generations.

http://www.hp.com/go/convergedsystem

Wednesday, May 27, 2015

ECI Announces ElastiCLOUD DCI Solution

ECI announced its ElastiCLOUD data center interconnect solution.

The company said its platform will support more than 25T on a single fiber, offer low power consumption at less than 85W/100G,  and offer a mix of packet and optical interfaces in the same platform with extremely high density. ElastiCLOUD also support ECI’s LightApps SDN applications for dynamic bandwidth allocation, service scheduling and network automation.

“Data traffic continues to grow exponentially. In fact, according to industry reports, the amount of data traveling between data centers is expected to quadruple between 2013 and 2018. Clearly the cloud connectivity infrastructure, as we know it today, must evolve.  This is the main reason why ElastiCLOUD is a key addition to the ECI family of solutions. It is also extremely important as it supports ECI’s current focus on the US market, which is home to many cloud service providers and data center operators,” said Mr. Andreas Hegers, Head of Marketing at ECI.

http://www.ecitele.com

Wednesday, May 13, 2015

CenturyLink Opens Hydro-electric-powered Data Center

CenturyLink inaugurated a new data center in central Washington, adding hydro-electric-powered data center services to its hybrid IT services portfolio.

The data center, located in Moses Lake, Washington, will ultimately support up to 30 megawatts of IT load on the site, with an initial ramp to 8 megawatts. It offers data center and network services, and includes access to cloud, colocation and managed services available through CenturyLink's global data center footprint. The site also has a seismic rating of 2B, the lowest rating in the western United States, making it a key location for disaster recovery solutions.

"CenturyLink's new low-cost power data center services provide many benefits to our customers, including a highly resilient solution coupled with power costs and efficiency metrics that rank among the best in the industry, and the facility serves as an excellent disaster recovery location," said David Meredith, senior vice president, CenturyLink. "Enterprises enjoy global access to CenturyLink's portfolio of cloud and managed hybrid IT services, and we continue to extend the reach of our data center footprint to new markets to meet from the needs of our customers."

The property is owned by Server Farm Realty and leased to CenturyLink.

http://news.centurylink.com/news/centurylink-adds-hydro-electric-powered-data-center-services-in-central-washington

See also