Sorry, I could not read the content fromt this page.
Showing posts with label center. Show all posts
Showing posts with label center. Show all posts
Friday, 30 August 2013
Tuesday, 27 August 2013
VMworld 2013: Networking and storage take center stage
VMware opens the VMworld 2013 conference in San Francisco this morning with a flurry of product announcements that both underscore the company's leadership in virtualization and help to flesh out its concept of the software-defined data center (SDDC). Along with updates of the vSphere virtualization platform and the vCloud Suite for managing vSphere-based private clouds, VMware is unveiling a new software-defined storage solution called Virtual SAN and a new network virtualization solution called NSX.
Virtual SAN turns the local storage of multiple vSphere hosts into highly available, shared storage that supports SSD for read caching and policy-based provisioning of virtual machines based on performance and availability requirements. VMware says a public beta will be available in Q3 2013.
NSX is based largely on the network virtualization solution that VMware acquired with Nicira last year. Although optimized for vSphere in a number of ways, NSX also supports the KVM and Xen hypervisors (with Hyper-V on the road map) and works with third-party cloud management systems such as OpenStack and CloudStack. Aimed at large enterprises and service providers -- organizations with a significant stake in making network provisioning faster and easier -- NSX will be available in Q4 2013.
The Version 5.5 releases of vSphere with Operations Management and the vCloud Suite, both expected to be available in Q3 2013, incorporate a lengthy list of new features and improvements. These start with the new abilities to leverage flash in vSphere hosts for read caching and to bring high availability to certain monitored applications and extend to improvements in backup, replication, single sign-on, network troubleshooting, the Web client, and host hardware support.
Some of the improvements are designed to make virtualization more suitable for applications that continue to cling to bare metal. For instance, a new latency-sensitivity setting for virtual machines helps make the case for virtualizing low-latency applications such as stock trading, while new Hadoop virtualization extensions simplify the virtualization of Hadoop workloads and bring high availability to the entire Hadoop stack.
Incremental changes
The vSphere 5.5 release introduces incremental changes and updates across the board. At the VM level, virtual hardware Version 10 brings a number of new features. New AHCI (Advanced Host Controller Interface) support enables multiple SATA devices on the same controller. New graphics features include support for Intel and AMD GPUs on Windows and Linux guests, along with support for OpenGL Version 2.1 for Linux guests. At the processor level you'll find new support for CPU-C states, which make it possible both to increase scale and conserve power. New hardware support includes hot-pluggable SSD PCIe memory devices, which now can be added or removed without taking the machine offline.
The new latency-sensitivity setting changes how the hypervisor handles the allocation of physical resources to the virtual machine, reserving memory, increasing vCPU ownership of the physical CPU, and bypassing CPU scheduling at the virtualization layer. This feature can significantly improve the response time of a typical virtual machine in order to meet the demands of latency sensitive applications.
VMware shows Microsoft Cluster Services some love in this release. Windows Server 2012 fail-over clustering is supported in vSphere 5.5 in the form of round robin path policy plus Fibre Channel over Ethernet (FCoE) and iSCSI protocol support.
The vCenter Server has seen a number of incremental changes as well. The vCenter Server Appliance now supports as many as 500 vSphere hosts and 5,000 virtual machines. The vSphere Web Client has been updated to support OS X for VM Console access, deploying OVF templates, and attaching client devices. On all supported Web browsers, the Web Client adds new drag-and-drop capability along with the ability to filter search list items and quickly access the 10 most recently accessed objects. VMware has also ironed out a number of wrinkles in vCenter Single Sign-On. The improvements include tighter integration with Microsoft Active Directory and a simplified installation process.
This new release of vSphere also brings the inevitable scalability increases to the ESXi hypervisor. Host configuration maximums increase from 160 physical CPUs to 320, 2TB of memory to 4TB, eight NUMA nodes to 16, and 2,048 virtual CPUs to 4,096.
Networking enhancements
VMware has placed a special emphasis on networking enhancements in this release. Some of them probably won't make headlines or turn many heads, but they will definitely make a difference to the people getting the job done. Diagnosing network problems often requires an analysis of the actual traffic on the wire. This takes both troubleshooting skill and the tools to get at the packets of interest. VMware vSphere 5.5 includes new packet capture functionality and a customized version of TCPDUMP to allow you to access host network traffic at the virtual NIC, virtual switch, or uplink level.
VMware adds networking, storage to its virtual data center stack
At the kick-off of its annual VMworld user conference, being held this week in San Francisco, VMware will fill in more layers of its software stack for running its envisioned software defined data center (SDDC).
“IT should be able to provision a production environment in minutes,” said Peter Wei, a VMware senior director of product marketing. “People want things very quickly, so you have to abstract the [IT infrastructure]. Otherwise it is not possible.”
Over the past few years, VMware has been expanding its core focus from virtualizing servers to a much broader task of virtualizing all the operations in a data center, using an architecture it calls SDDC. With SDDC, all of an organization’s infrastructure is virtualized, allowing data center administrators, in theory, to easily automate operations.
This year’s VMworld conference will provide more details about the products and protocols that could make SDDC a reality.
“People got the concept of SDDC, so some of the focus this year is how do we make it real,” Wei said. He noted that internal company surveys showed that 77 percent of VMware customers are thinking about expanding their virtualization strategy to storage and networking. To this end, the company is introducing new virtualization technologies for networking and storage.
Perhaps the most buzz for this year’s show is around network virtualization. At the conference, VMware will introduce products for its Network Virtualization Platform, NSX. Borrowing technology from VMware’s 2012 acquisition of Nicira, NSX virtualizes the networking layers of the OSI (Open Systems Interconnection) communications model.
VMwareVMworld’s network virtualization model, NSX
With NSX, administrators could execute and automate a wide variety of network configuration tasks, including the provisioning of switches, routers, load balancers, and virtual private networks.
“NSX is about speed, speed, speed,” Wei said. “NSX has a control plane that basically abstracts the hardware.” This abstraction allows the administrator to script actions, such as defining a new virtual local area network (VLAN), without the need to understand the protocols of each vendor’s hardware.
VMware is also extending its virtualization expertise to the storage layer. This week, the company will also introduce a beta of its Virtual Storage Area Network (VSAN), which the company unveiled at last year’s VMworld under the name of Distributed Storage.
Using VSAN software, an administrator can pool direct attached storage (DAS) hard drives across multiple servers to make one virtual SAN.
On the computing side, VMware is updating its vSphere software for managing virtual machines (VMs) to handle larger workloads. Virtual disks can now be as large as 64TB each—twice the size allowed in the previous edition. Release 5.5 of vSphere also includes a new connector for deploying Hadoop jobs, or other big data-style deployments, which can involve invoking hundreds or even thousands of virtual servers.
Joab Jackson covers enterprise software and general technology breaking news for the IDG News Service.
More by Joab Jackson
Monday, 5 August 2013
Rapidly growing DigitalOcean opens second NYC data center
Continuing its rapid expansion, cloud service provider DigitalOcean has opened a second facility in the greater New York metropolitan area -- a data center located in Google's gargantuan Manhattan facility.
The additional location is another sign of the fast-growing success the company has had in offering a low-cost, easy-to-use IaaS (infrastructure as a service).
"There's a huge market for developers out there who just want a server online as fast as possible, and that is what DigitalOcean provides," said Mitch Wainer, a co-founder and the chief marketing officer of DigitalOcean.
Although Wainer disputed that DigitalOcean's first New York City-area data facility, actually located in northern New Jersey, ran out of space, new users who have signed up in the past month or so were instructed that they could not host their accounts there, and were instructed to choose DigitalOcean's outlets in Amsterdam or San Francisco.
In any case, the company's user base is growing quickly. The company has accrued more than 35,000 customers since its launch in 2011, and its revenue is increasing by about 30 percent to 50 percent per month, Wainer said.
Internet service market analysis firm Netcraft noted that in June 2013 DigitalOcean had more than 7,000 Web-facing servers, a dramatic increase from the prior December when Netcraft counted only 100 DigitalOcean Web-facing servers.
This newest set of servers is being colocated with the Telx data center company, which leases space in Google's 3 million-square-foot building. The building takes up an entire block on 8th Avenue, in the Chelsea district of Manhattan.
DigitalOcean was founded with the idea of offering cloud hosting that would be easier to set up than what was offered by the market leader, Amazon Web Services (AWS).
"There was a huge void in the market," Wainer said. Amazon and Rackspace are focused on enterprise-scaled businesses, but businesses in the lower-tier to midlevel market, which don't require advanced feature sets and don't have full engineering teams to manage infrastructure, are completely ignored, he said.
With its wide range of services, Amazon Web Services recently launched a series of tutorials that can guide users into setting up virtual machines.
In contrast, DigitalOcean keeps its deployment options relatively simple -- and inexpensive. Accounts are billed either on a monthly or an hourly basis. The least expensive "droplet," which is what DigitalOcean calls a virtual machine, costs US$5 a month, or about $0.007 cents per minute, and features a single CPU core between 2GHz and 3GHz, 512MB of working memory, 20GB of storage and 1 terabyte of data transfers.
In contrast, the least expensive month-to-month option on AWS, a T1.micro image running Linux, would run about $14.96 per month, and does not come with any storage.
The company claims that users can set up a droplet, or resize it to another pricing tier, in less than a minute. It offers virtual machine images running basic versions of either the Ubuntu, Debian, CentOS, Arch or Fedora Linux distributions.
The company is using a number of new technologies for competitive performance, including SSDs (solid state drives), which can boost I/O performance. For virtualization, DigitalOcean uses Red Hat's KVM hypervisor.
Just as Microsoft is doing with its Windows Azure service, DigitalOcean is initially pursuing the market of developers who need modestly priced machines to develop and test code.
Wainer points to the rapidly growing user base of GitHub, an online source-code repository, as proof of the potential size of the developer market. Founded in 2008, GitHub now hosts 7.7 million repositories from 3.3 million users.
"You can see from that market size alone, that this is a billion-dollar market opportunity," Wainer said.
While DigitalOcean has been courting the developer market, it is also suited for startup businesses as well, Wainer said. For instance, one startup using DigitalOcean is the RSS reader service NewsBlur, which has accrued a significant user base after Google shut down its own RSS reader.
Not that the company hasn't had a few bumps. Last month, one user found that the service was using identical SSH fingerprints for multiple Ubuntu droplets generated within a single account, which was a significant security vulnerability. The company has since fixed the problem.
"That's one of the things about being a startup -- you can't be perfect from the get-go," Wainer said, though adding, "Whenever there is an issue, we've been responsive."
DigitalOcean, which is based in New York City, now has 30 employees, though it is looking to hire network engineers and Linux system administrators. It is also expecting to get a significant investment from an outside party shortly, which will be used "to drive new features and acquire capacity in additional regions," Wainer said.
The company is planning to offer virtual private networking and object storage, similar to Amazon's Simple Storage Service (S3). It will also broaden its array of off-the-shelf virtual machines, including those with WordPress or other popular applications installed and ready for use.
Joab Jackson covers enterprise software and general technology breaking news for The IDG News Service. Follow Joab on Twitter at @Joab_Jackson. Joab's e-mail address is Joab_Jackson@idg.com
Joab Jackson covers enterprise software and general technology breaking news for the IDG News Service.
More by Joab Jackson
Data center innovator Ken Brill dies at 68
Ken Brill, founder of the Uptime Institute and a forward thinker in data center design and operations, died this week at the age of 68, the Institute said on Thursday. The cause was cancer, a spokesman said.
Brill was known for his work creating the Uptime Institute's data center tiering system, which provides a way to rate and compare the reliability of computing facilities. It's used by many large companies for their data center planning and selection.
He was also a big proponent of data center energy efficiency, which has become a vital concern as computing services become more powerful and widespread. In particular, Brill pushed for better communication between IT staff and the engineering teams that run data centers, which he believed was the only way to get the most from operations.
"I think that will be a big part of his legacy: bringing together different disciplines to speak a common language for the betterment of the enterprise and its use of IT resources," said Julian Kudritzki, the Uptime Institute's chief operating officer, who worked with Brill for almost a decade.
Brill is also credited with technical innovations, including the introduction of dual power supplies for servers, which ensures a server keeps running if one power supply fails. He was awarded a patent for the invention in 2000 but never sought to profit from it, according to Kudritzki.
"He was motivated by the desire for constant improvement," he said. "That's what drove him."
That passion could make him combative at times, and Brill wasn't known for pulling his punches at the data center conferences where he spoke. In its statement, the Uptime Institute called him "a brilliant and bristly individual."
"He could be cantankerous, that wasn't a secret," Kudritzki said. "If you've ever been on a panel with Ken, you'll know it's rather a sporting adventure. It was all in pursuit of his principles; he believed the industry could do better."
Brill began his data center career as a manufacturer of power supply equipment in the 1970s. "By the mid-eighties I had made and lost a million dollars and nearly went bankrupt," he said in accepting an award from DataCenter Dynamics in 2009, according to a transcript.
"While I was licking my wounds and deciding what to do next, I realized my career needed to have a higher purpose beyond me and just making money. I settled on ensuring uninterruptible uptime."
Brill also founded the Uninterruptible Uptime Users Group, now known as 7X24 Exchange International, which gave him a lifetime achievement award. In 2009, Network World named him in a list of "10 people you should know in tech."
He earned an undergraduate degree in electrical engineering from the University of Redlands in California, and an MBA from Harvard Business School.
Kudritzki said he visited Brill at his home in Maine last week, and although he was ill, they still discussed improvements that the data center industry needs to make. "Part of the pleasure of seeing him, even in that state, is that the light was still shining," he said.
Brill stopped managing the Uptime Institute in 2009, when it was bought by research firm The 451 Group. Since then, he had been focused on expanding the Institute's operations in Asia and setting its general vision.
"Of course it's a great loss; in many people's minds there's an equals sign between Ken Brill and the Uptime Institute, and vice-versa, but we'll continue to drive on," Kudritzki said.
James Niccolai covers data centers and general technology news for IDG News Service. Follow James on Twitter at @jniccolai. James's e-mail address is james_niccolai@idg.com
Subscribe to:
Posts (Atom)