[Most Recent Entries] [Calendar View]
Monday, March 13th, 2017
| Time | Event |
| 3:00p | Can Your Company Endure an AWS-size Outage? Whether hackers worm their way into key data center systems and cause an outage, or a technical mishap takes down multiple servers, human error is usually to blame. As you know, outages can be extremely costly to businesses due to loss of customers, reputation, and revenue. Most companies today rely on digital information sharing and connectivity as critical elements in their business model. When this function breaks, business grinds to a halt. The most recent example happened when an engineer for Amazon Web Services accidentally mistyped a command while debugging the company’s billing system for its cloud storage service, S3. The right command would have removed just a small numbers of servers running on one of the S3 subsystems. “Unfortunately, one of the inputs to the command was entered incorrectly and a larger set of servers was removed than intended,” according to an Amazon blog that also apologized for the ramifications. This proverbial pushing of the wrong button resulted in a four-hour outage that brought down or compromised web services across the internet and cost AWS customers and others reliant on third-party services hosted by AWS hundreds of millions of dollars. They included: Coursera, Medium, Quora, Slack, Docker, Expedia, and more. Take a look at all 11 sessions in Data Center World’s Security, Data Sovereignty and Risk Management track. Cyence, a company that estimates the economic impact of cyber risk, told Data Center Knowledge that the outage caused S&P 500 companies to lose $150 million and US financial services another $160 million as a result. That number could easily exceed $160 million because it doesn’t include many other types of companies, such as credit unions, that host mobile applications on Amazon’s cloud. An international study by the Business Continuity Institute showed that IT and telecom outages were the top three sources of disruption for financial services, IT and communications, transport and storage, and government. Fourteen percent of those surveyed estimated that a previous disruptive incident cost their businesses between $1.3 million and $13 million. John Parker, who is responsible for disaster recovery and global data center operations management for ESRI, thought AWS handled the outage efficiently. “I was impressed with the AWS Root Cause Analysis (RCA) report, but even more impressed that they also looked at other processes during the incident that may have slowed down the resolution process,” he said. “Every company should not only determine the RCA but look at opportunities to improve all processes during an incident, thus reducing the amount of downtime.” Parker is speaking at the Data Center World conference next month in Los Angeles. Details below. AWS is taking precautions to prevent similar and future outages by modifying its tool for removing capacity to prevent it from removing too much capacity too quickly and to prevent capacity from being removed when any subsystem reaches its minimum required capacity. The team also reprioritized work to partition one of the affected subsystems into smaller ‘cells,’ which was planned for later this year but will now begin right away. Of course, developing a plan to restore systems and business as soon as possible goes hand-in-hand with preventing outages from the get-go. That’s just not always realistic, considering the nature of humans and unpredictability of natural disasters. “No company is immune to outages as long as humans are involved as human error is the leading cause of outages,” Parker concurred. “That’s why having Solid Incident Management processes in place is so critical for companies: Companies can recover much faster with them.” Data Center World Keynote Speaker and professional hacker Kevin Mitnick blames humans for cybersecurity weaknesses in corporate America as well. “My presentation will clearly illustrate why people are the weakest link in the security chain,” Mitnick says. “Attendees will see real demonstrations of some of the most current combinations of hacking, social engineering and cutting-edge technical exploits my team and I actually use to penetrate client systems, with a 100 percent success rate. They will also gain strategies to protect their organizations, and themselves, from harm and to help mitigate the risks they face.” Parker will be part of a two-hour panel discussion, “Will the Cloud Replace the Need for Data Centers?” on Wednesday, April 5 from 9:30 to 11:45 a.m. He will also present, “Cloud Computing 101: A Primer” as part of the All Access Pass Workshop series on Monday, April 3 from 8 a.m. to 11:30 a.m. This article originally appeared at AFCOM. |
| 3:42p | Ascent Acquires Data Centers in Atlanta and Toronto Data center provider Ascent recently shifted its growth strategy to Greater Atlanta and Toronto with the acquisition of two enterprise-grade facilities made possible by a partnership with TowerBrook Capital Partners and raising $3.3 million, according to the St. Louis Business Journal. The newest additions to the St. Louis-based company’s portfolio are aimed at cloud and edge deployments with plug-and-play data center space the company says is immediately available. “Similar to other data center owners, this customer was reevaluating its real estate portfolio and operational needs,” CEO Phil Horstmann said in a statement. The Atlanta data center (ATL1) currently offers up to 8.1 MW of critical power and can be expanded to 14 MW. The Toronto facility (TOR1) is expected to have up to 4.8 MW of critical power available in the second quarter of this year with the overall site capable of expanding up to 75 MW. In Dallas, the threats of severe weather and the need for impenetrable facilities forced Ascent to create facilities in that market capable of withstanding EF5 tornadoes with up to 360 mph winds. That called for 15-inch reinforced concrete walls, a 13.5-inch reinforced concrete roof and an 8,000-pound blast door at the dock area. While Atlanta may not be in tornado country, it’s certainly vulnerable to hurricanes and will require a similar environment. While demand remains steady in the Atlanta market, the area is seeing slower overall growth than other top US markets, according to a recent report from CBRE. However, the report suggested that demand from non-local companies for wholesale space to support secondary and disaster-recovery deployments will likely remain steady, which fits right into Ascent’s wheelhouse. Meanwhile, as the business and financial hub of Canada, home to the Toronto Internet Exchange, base for nearly 90,000 businesses, and home to five of the nation’s largest banks, Toronto is fast becoming a data center mecca. See also: 2016 Was a Record Year for Data Center Acquisitions, but 2017 Will Be off the Charts |
| 4:12p | Equinix Opens Its Third São Paulo Data Center Equinix has added more Latin flavor to its data center menu with the recent opening of SP3, a new $69 million facility located in São Paulo—the company’s third in the key financial hub near the Bovespa stock exchange and fifth across Latin America. Equinix says its São Paulo operations serve some 1,000 companies, including 270 cloud and IT services firms and more than 70 telecommunications carriers. From there, companies can also set up direct links to new submarine cable systems, including the Seabras-1 cable between Brazil and the US. SP3 will add 725 cabinets in the first phase with an expected total capacity at full build-out of 2,775 cabinets and 13.3 MW of power. Although its three data centers in São Paulo and two in Rio De Janeiro give Equinix a strong Brazilian presence, the company plans another in São Paulo upon closing of the agreement with Verizon, announced in December 2016, to acquire 29 data centers across 15 metro areas in North and South America. “All of our data centers around the world are interconnected and redundant,” Yuri Fiaschi, country manager of Brazil, Infopip, one of the new facility’s 30 first customers, said in a statement. “This allows us to ensure business continuity – and Equinix is an important part of this strategy. In addition, having a local facility will help us expand operations in the region, especially among companies within the financial market, which is also one of Equinix’s main ecosystems.” |
| 4:30p | Strategic IT Infrastructure in 2017 Matt Kixmoeller is VP of Products for Pure Storage. Data is rising at an unprecedented clip, and companies are struggling with how much to store, how much can be analyzed, etc. – compromises no one wants to (or should have to) make. That’s precisely why data management has become the topic du jour and why the perception of IT infrastructure has shifted: What was once considered a commodity has become a platform where businesses build applications and derive insights from mission-critical data. While an all-cloud future continues to dominate headlines, the reality is quite different. As we continue to move into 2017, we expect to see the conversation shifting from the all-out hype and push to public cloud to a more nuanced discussion of optimizing infrastructure to fit the specific needs of each customer. Here are the top IT infrastructure trends I believe will be top of mind for the balance of 2017: Renewed Focus on Hybrid CloudContrary to popular belief, the public cloud has not swallowed the majority of workloads and applications with only 20 percent of workloads today in the public cloud. And according to IDC, growth is expected to slow after 2017 as businesses begin to pull back from experimentation and optimize storage strategies. Multiple factors will contribute to the slowdown, including concerns over vendor lock-in, security, accessibility and cost. In my view, public and private clouds will co-exist in the long term, and most data centers will be a mix of public cloud (IaaS/PaaS platforms like AWS and Azure) and private cloud. While the public cloud can often offer more cost-effective elasticity, experimentation, archival, and disaster recovery, private cloud will excel for more predictable, performance-critical workloads (latency is higher in public cloud, and bandwidth is expensive) as well as when there are security concerns with using proprietary algorithms or data in the public cloud. Many customers have had almost blind directives to move some element of IT infrastructure to the public cloud without a real understanding of cost and operational implication. I think we will continue to see a better inspection of public cloud realities, resulting in the first wave of “best practices” that define which services and workloads should remain on highly optimized, resilient on-premise technology, specialized SaaS or secure private cloud, and which should be in public cloud. More and more businesses will begin to see strategic infrastructure as a competitive advantage. The differentiation will lie in having your own private data center to analyze data faster, discover new insights, and deliver new products and experiences. AFAs Take Another Leap with NVMeNVM Express, a next-generation memory-class protocol for CPU-to-flash communication, is poised to drive a shift across the storage industry to NVMe architectures. Analysts forecast that NVMe, which is enabling the next generation of flash performance and density, will become the leading interface protocol for flash by 2019. A critical mass of consumer devices has already shifted to NVMe, and the enterprise will not be far behind. Current storage systems use the legacy SCSI or SAS protocol, which present a bottleneck and cause performance delays when communicating to flash. The NVMe protocol holds the promise of eliminating the SCSI bottleneck, bringing massive parallelism with up to 64K queues and lockless connections that can provide each CPU core with dedicated queue access to each SSD. Storage arrays with internal NVMe also provide better performance, with increases in bandwidth and lower latency, as well as higher density and greater consolidation – all amounting to lower-per-workload costs. Today, legacy disk vendors are finally on board the all-flash train, but to play catch up with purpose-built AFAs, most have adopted a retrofit strategy. Unfortunately for customers, retrofit arrays aren’t designed for NVMe – or any new, flash-native innovations – which means another expensive refresh cycle and painful forklift upgrades are on the horizon for anyone investing in a retrofit array today. The massive parallelism unlocked by NVMe will be required by any business who wants to take advantage of their data, as well as capitalize on future technological advances such as super-dense SSDs, modern multi-core CPUs, new memory technologies and high-speed interconnects. Cost Uncertainty Could Impede Cloud AdoptionAlthough public cloud can offer cost effective elasticity – short bursts of workload activity can be quickly and easily spun up in AWS – in the long term, public clouds will not be able to offer the cost certainty that CIOs need. The simplicity gained in managing public cloud deployments from an IT perspective has been almost eradicated by the added complexity of cost management. Essentially, the time admins recouped has been replaced with managing budgets. This trend is made evident by the sheer number of fiscal management tools available for the cloud. And more and more, CFOs are attending conferences like AWS’ re:Invent, eager to understand where and how their IT budgets are being spent. One thing is for certain: Data will continue to grow at an unprecedented rate in 2017 and beyond, making IT infrastructure and data management a boardroom issue for major corporations worldwide. It’s an exciting time to be in the space. Opinions expressed in the article above do not necessarily reflect the opinions of Data Center Knowledge and Penton. Industry Perspectives is a content channel at Data Center Knowledge highlighting thought leadership in the data center arena. See our guidelines and submission process for information on participating. View previously published Industry Perspectives in our Knowledge Library. |
| 7:37p | Why Microsoft Says ARM Chips Can Replace Half of Its Data Center Muscle Recent years’ relative quiet on the ARM server front, the scarcity of large-scale IBM Power deployment news, and the consistent growth reported by Intel’s Data Center Group may in totality create an impression that the data center chip wars have subsided, with Intel enjoying a massive – and secure – lead. A few announcements that came out of last week’s Open Compute Summit in Santa Clara and the Google Cloud Next conference in San Francisco however showed that while Intel’s lead may be massive, it’s under bigger threat than may have appeared. The biggest news out of the Open Compute event was that Microsoft had been working with ARM chip makers Cavium and Qualcomm on ARM server designs to run many of its cloud services (Qualcomm’s processors are in a big but reportedly waning share of the world’s smartphones). This was not an announcement like the ones we’ve heard in the past from Facebook and Google –non-committal revelations that they had been testing ARM servers here and there, and that they were really always testing everything on the market, just in case. Microsoft thinks there’s real potential for ARM servers to eventually provide more than half of its cloud data center capacity. Coming from the world’s second-largest cloud provider, that kind of announcement should give Intel a lot to think about. As more and more corporate applications are headed for the cloud, the number of servers traditional hardware vendors sell to enterprises is on a gradual decline, while cloud providers are buying more and more processors to support those migrating workloads. The prospect of ARM servers working out the way Microsoft is picturing they may for its Azure cloud threatens Intel’s biggest source of revenue growth.
The same week, speaking on stage at Google’s big cloud event, Raejeanne Skillern, leader of Intel’s Cloud Service Provider Group, confirmed what Google had announced earlier, that Intel had sold to Google its latest-generation Skylake server chips before it would let any other company have them, giving Google’s cloud platform a temporary performance advantage over its competitors. Timing of both announcements may be a coincidence, but one reason Microsoft has been working with ARM server vendors is to avoid putting all its eggs in one basket, especially if that basket is a supplier that’s not required to provide all its customers with a level playing field. Read more: Google Expands Cloud Data Center Plans, Asserts Hardware, Connectivity Leadership In order to avoid having to rewrite much of the software that powers its cloud services, Microsoft has ported Windows Server 2016 to ARM, Leendert van Doorn, distinguished engineer for Azure, announced from stage at the summit. The company envisions using ARM servers to power its cloud storage, Big Data, Machine Learning, search, index, and other workloads. “Those properties together actually represent over half of our data center capacity, so there’s quite a lot of potential for different kinds of servers there,” he said, adding that the workload that for now is safely in the x86 corner is running customers’ cloud VMs, also known as infrastructure-as-a-service. “We work closely with our x86 partners too, so one of the key things here for us is choice,” van Doorn said in an interview with Data Center Knowledge. Besides Intel, those x86 partners also include AMD, which is staging a “comeback” to the data center market, leading with its upcoming high-performance Naples chip. Project Olympus, Microsoft’s effort to leverage the open source hardware design community of the Open Compute Project to create its next cloud server, includes motherboards for Intel, AMD chips, as well as the ARM variants by Cavium and Qualcomm. The ARM server ecosystem has to a great extent benefited from the massive scale of the high-end smartphone market, van Doorn wrote in a blog post. The developer ecosystem that has grown around ARM-powered smartphones has “significantly helped Microsoft in porting its cloud software to ARM servers.” Van Doorn cited throughput-oriented ARM designs as a key reason Microsoft is getting so heavily involved with the architecture. “Those are things with high-performance IO, high IPCs (instructions per cycle), lots of cores and threads, large numbers of them, and lots of interesting connectivity options, especially with some of the newer bus standards, which are very interesting from an accelerator perspective,” he said. Simpler hardware compatibility is another factor. Because ARM chipsets and motherboards are built on open standards, there’s absolutely no difference between Cavium and Qualcomm versions of Windows Server 2016 for ARM, van Doorn said. A single generic ARM ACPI driver will enable the OS to discover and onboard peripherals and such instead of different drivers for different chipsets, as explained by The Register. Another trend that’s playing out in Microsoft’s ARM and AMD announcements is the new opportunity to optimize cloud hardware for specific workloads. That opportunity is in the economies of scale the cloud has made possible. From van Doorn’s blog post: “Due to the scale required for certain cloud services, i.e. the number of machines allocated to them, it becomes more economically feasible to optimize the hardware to the workload instead of the other way around, even if that means changing the Instruction Set Architecture.” A bigger variety of chipmakers in theory makes that kind of optimization easier. |
| << Previous Day |
2017/03/13 [Calendar] |
Next Day >> |