“Rack n’ Roll” – Refresh Your Network with Minimum Investment and Downtime

- Elyse Ge Hylander, product line manager of enterprise solutions at CommScope (http://www.commscope.com/), says:

As data centers face ever-increasing growth, IT demands, and evolving technologies, IT administrators and facility and data center managers are challenged with responding to the rapid growth of their facilities and the businesses they support. Furthermore, rising operating expenses are driving data center operators to maximize their utilization of space, power and cooling through higher density server deployments, which introduces the challenge of managing larger bundles of cabling within the server cabinet.

It is safe to say that the data center is the heart that pumps the blood throughout an enterprise, and a new data center presents the unique opportunity to design a network that maximizes the best of today’s technology while providing a clear path to the future. Increased bandwidth demand is an overall priority for data center capacity; however, choosing the right way to evolve a data center encompasses a wide range of opinions.

To further add to these challenges, most network infrastructure is incapable of adapting to growth demands and evolving technologies with minimal investment and downtime. Traditionally, patch panels are installed inside the server cabinet and connected to the network via permanent horizontal cables. Servers are then loaded one at a time. As such, data center managers face the lack of agility to quickly deploy server racks and the associated cabling required accommodating growth needs. They are also challenged with the ability to accommodate upgrades to their existing infrastructure.

To address these issues, CommScope developed the InstaPATCH® ZERO server cabinet solution—the first pre-terminated server cabinet solution on the market. The cabinet features up to six cord cassettes that are pre-installed and configured in the zero U space of a 42U 600-mm wide and 1200-mm deep customized server cabinet jointly developed by Rittal and CommScope. It provides connectivity in an integrated, modular system that enables rapid, plug-and-play server cabinet deployment and facilitates best practices in intra-cabinet cable management. Positioned above the cabinet is a short, 4U equipment rack mounted to the overhead pathway. It segregates permanent cabling from cabinet and save space for active equipment by placing patch panels or interconnect equipment above the cabinet or rack.

InstaPATCH ZERO expedites server deployment by simply rolling in the loaded cabinet and plugging it into the network infrastructure. For non-greenfield data centers, customers dramatically reduce downtime during a technology refresh while preserving their investment in the network infrastructure. Connecting servers is a matter of pulling the cords from the cassettes and plugging them into the servers. The built-in patch cords are always the right length for server connections. Any cord slack stores neatly inside the cassette.

The data center network infrastructure generally lasts between seven and 10 years; however, the refresh cycle for servers and switches are every two to four years. Given the “connectivity-bus” like architecture along with the “roll in and plug-in” capability offered by the InstaPATCH ZERO solutions, customers no longer need to choose between minimizing downtime and preserving investment.

InstaPATCH ZERO Server Cabinet Solution instantly turns static equipment into a Living Infrastructure—an approach to designing, deploying and evolving data centers that encompasses a comprehensive portfolio of structured cabling solutions and planning tools. These solutions and tools can help customers drive efficiency through flexibility in addressing unanticipated changes in network design and priorities.

What makes this ideal is that there is no similar product on the market. The current method is to order patch panels, patch cords, patch cord managers and install all these parts in the production data center. The InstaPATCH ZERO cabinet is orderable with two, four, or the maximum of six cord cassettes pre-installed at the factory, simplifying ordering and installation since there is only one package and one part number.

Data center managers now have access to a turn-key solution designed for rapid server deployment and change management. By helping them with rapid deployment, CommScope helps them realize a higher investment value by saving time, money, space while also enabling them to plan for tomorrow’s growth.

Virtualized Data Centers Need VM-Aware Networking

- Dan Tuchler, vice president of product management with IBM System Networking (www.ibm.com), says:

Server virtualization brings both benefits and drawbacks to the data center: it can maximize underutilized resources and minimize infrastructure spending—but add complexity and administrative overhead for the network administrator. In order to fulfill the promise of a dynamic environment, VMs need to be supported by an intelligent network. What’s needed is a Virtual Machine-aware approach to network virtualization that can automatically migrate network policies along with Virtual machines (VMs) as they migrate across different physical servers. While many vendors are talking about this concept, IBM System Networking is actively delivering solutions to the problem—for all server virtualization technologies.

Virtualization promises to make significant contributions to data center and cloud computing for the foreseeable future. It provides the ability to create multiple compute environments in a single bare-metal host, minimizing idle processor cycles and maximizing the return per physical server. New Virtual Machines can be quickly added to the environment so that revenue opportunities are quickly realized. IBM’s VMready provides the simplicity, flexibility and power to manage the network in these dynamic, highly virtualized data centers.

IBM’s switch-resident VMready with Virtual Vision is a unique solution that enables the network to be Virtual Machine aware, so that the network can be configured and managed for 1000s of virtual ports (v-ports), rather than just a few physical ports. With VMready, as VMs migrate across physical hosts, so do their network attributes automatically, retaining the same ACLs, QoS and VLAN attributes. VMready works with all major hypervisors, including VMware, Microsoft’s Hyper-V, Xen and KVM.

An increasingly important part of data center infrastructure is what is sometimes referred to as the “virtual edge” – where physical and virtual infrastructures overlap, and where the virtualized network extends into the virtual server. Edge Virtual Bridging (EVB) technologies now being defined by the IEEE 802.1Qbg working group can make it easier for businesses to achieve large-scale server-network edge virtualization in the data center. In addition to the benefits of automation and open standards, the EVB approach also helps preserve existing IT investments by allowing migration to new, modern systems without having to replace current equipment.

Until recently, many data center administrators hesitated to take advantage of mobile VMs because of the time demands of managing the related networking requirements. Now automated solutions can safely create and move VMs, freeing network administrators from those responsibilities and bringing the full potential of virtualization to the data center.

Tackling the Physical Limitations of the Server – PCIe Sharing

Stephen Spellicy, 

VP of Marketing & Business Development at 

Virtensys (www.virtensys.com), says:

The challenge in the data center today
All too often in today’s data centers, administrators are running out of server resources: CPU, memory or I/O (storage & network) resources are all in high demand. A common problem is that the server has no ability to upgrade or move beyond its physical constraints. Smart data center administrators plan the best they can; buying servers that will meet the performance/scale demands of their applications. However, with the rapid growth in server virtualization, the traditional approach to planning your physical data center needs have changed dramatically. Now administrators are sizing servers not just for a single application, rather for many applications, running concurrently with a variety of resource needs that range in complexity.
Server virtualization platforms such as VMware vSphere® have taken the lead in dynamic virtual server resource management for the data center. However there still remains the challenge of improving resource management at the physical layer.

An acknowledged goal for the next generation data center (based on a heavier use of server virtualization and the promise of “hyper-consolidation”) is to minimize the overall physical infrastructure. From a networking perspective, this means reducing the number of switches per row; from a storage perspective, consolidating and reducing physical storage resources to the minimum, leveraging technologies such as compression, de-duplication, and high-density hard drives.

Blade server architecture is a successful and proven solution to help achieve this. Another solution, and an administrator favorite, is the rack mount server. Many administrators are deploying smaller (1U and 2U) physical server footprints to achieve a reduced cost (for example: power, cooling, physical space) within their densely populated rack. Especially as many customers and providers migrate towards a more commodity server driven model (vis-a-vis Cloud computing and/or Infrastructure as a Service – IaaS) this makes better business sense.
However this also raises some questions. If you plan to reduce the physical size of the server:

• What happens to the resource needs for your application?
• What if the server requires access to a high-speed network, using 10 Gigabit Ethernet (10GbE) and a high-performance SAN using an 8 Gbps Fibre Channel (FC) HBA?
• What if you also require access to the highest performance storage in the market today – PCIe based SSDs (solid-state drives)?

The question isn’t why would you want all of those capabilities in the same server, but rather how will you fit them inside a densely populated 1U physical server footprint?

Enter PCIe Sharing
The constraints are obvious. Smaller physical server hosts are “PCIe” slot constrained. Adding more slots to the motherboard is not an option. This means you will not be able to have all the interfaces available simultaneously. Furthermore if you require redundancy (multiple adapters for higher levels of availability), you are completely out of luck.

These types of server I/O peripherals are PCIe (PCI Express) based and allow servers to connect to high-speed networks and high performance storage. PCIe is an industry standard, well-known, well-understood and universally accepted server-based technology. Implementing a PCIe sharing solution that virtualizes multiple physical PCIe I/O adapter peripherals (10 GbE NICs, 8 Gbps FC HBA, RAID controllers and PCIe based SSDs) and shares them across multiple servers overcomes these constraints.

Virtensys PCIe sharing appliance is a proven solution that allows the sharing of physical I/O adapter resources. These types of I/O adapter resources are typically high cost, high demand I/O resources. Sharing them across multiple servers makes sense when you want to lower the TCO and improve resource utilization.

Virtensys’ PCIe sharing solution makes this possible without sacrificing the native capabilities of the I/O resource, retaining its initial value to the administrator:

• Offloading compute intensive checksum operations through hardware acceleration.
• Improving how the adapters buffer information when sharing resources amongst virtualized servers.

How PCIe sharing works
Utilizing Virtensys’ PCIe sharing technology, servers gain access to a virtualized instance of a traditional physical I/O resource (such as Micron Technology’s P320h PCIe SSD adapter). Sharing the physical I/O resource means that communications between connected servers can achieve higher performance, improved resource utilization and drastically lowers the total cost of ownership (TCO).

Another advantage of the shared resource model is the possibility of centralized provisioning and management. Each server now has access to a range of I/O resources –-- previously not possible, which has dramatic economic and logistical consequences.

Provisioning each server in your data center with its own physical PCIe based SSD adapter would ordinarily be cost prohibitive. However, imagine pooling two or even four of these same resources in a centralized appliance, and then sharing them as a virtualized PCIe-based SSD to multiple server hosts! Now any server can have its own portion of an “in-demand” resource, and depending on the configuration, all server hosts can see the resource as a shared pool, though connected via PCIe.

With the shared resource model, the performance benefit alone is a huge improvement; for example, block copies within a shared logical device or data store, to support operations within a clustered database or virtual machine live migration between server hosts. The operation can be achieved at local speeds/feeds as if the storage resource was directly attached and local to the server host itself.

Utilizing PCIe sharing – smaller physical servers together with more densely populated racks gain the full advantages of fewer physical cables to manage, and fewer adapters in each server, but with all the right capabilities, in the amounts/types needed to provide appropriate performance/scale.

PCIe “Slot” constrained servers benefit from technology like Virtensys’ PCIe Sharing technology in the following ways:

• Physical Layer Consolidation PCIe sharing addresses the need to remove the physical and logical layer complexity, providing management agility.
• I/O Density Providing server hosts with greater amounts of bandwidth and differing types of I/O resources for densely populated server hypervisor hosts.
• I/O Diversity Servers become “agnostic” to the storage protocol used, as they can support all native environments and can easily migrate between them.
• Hardware Acceleration Server-to-server communication remains within the “zone” and I/O communications happen at the lowest latency and highest performance/bandwidth possible.
• Resource Extension I/O resources, such as traditional SSDs and PCIe SSDs can be leveraged through virtualization as an extension of memory capability; e.g. “host cache”.

Servers not only need access to the right type and number of I/O resources but also additional resource can come at a cost from an overhead perspective. The last thing an administrator needs is a server fully loaded with high performance interfaces that can’t keep up due to CPU/memory utilization.

The cost of processing traffic for a high performance network or SAN may mean sacrificing needed CPU cycles to be shared across virtual machines. With Virtensys’ PCIe Sharing technology, much of the PCIe “control” related traffic is offloaded from the server. This means that traffic related to processing communications at the PCIe layer is hardware accelerated within the Virtensys architecture.

Virtensys’ architecture consists of two key components: the IOVE (I/O Virtualization Engine) and the VPC (Virtual Proxy Controller):

• The IOVE provide a 16 port PCIe multi-root aware switch; a high-speed switching fabric that provides 64 lanes of up to 320Gb/s of non-blocking bandwidth, fully compliant to the PCI-SIG MR-IOV specification. The IOVE handles the separation of the control and data planes. This enables each I/O device to access multiple host memory spaces, effectively separating direct memory access (DMA) to data buffers and control structures.
• The VPC operates on the control path to provide the virtualization of multiple physical devices, and is a proxy between the I/O device and the connected server. The VPC can pre-fetch data from host memory in anticipation of a read operation from a device, or from device registers anticipating a read operation from a host. Since the VPC is implemented as a hardware state machine rather than through software and context switching, register access latency on a virtualized I/O device is comparable a physical I/O device, and in some cases can even improve the throughput of a virtual I/O device, compared to a physical device.

When the virtualized version of a physical device is presented to a server, it’s as if the device were physically installed in the server. For example, a virtualized 10GbE adapter will be seen as a PCIe device in a server’s BIOS, and a virtualized Fibre Channel HBA will go through its normal initialization processes during server boot – just like a physically installed adapter. In addition, these virtualized adapters require no additional Virtensys-proprietary drivers, nor is it necessary to boot into the hosts operating system or hypervisor to be able to operate the adapters. This makes features such as PXE (preboot execution) or boot from SAN a possibility.

Summary
Sharing in the data center has been proven technology approach for decades, seen as a better way to achieve scale, resource utilization and even improve performance. As we progress beyond what can already be shared (server, network, and storage) to other areas of the data center, we recognize that the time has arrived to leverage sharing for PCIe based resources.
Utilizing Virtensys’ PCIe sharing technology – administrators no longer need to choose between physical server form factor. They can leverage smaller server footprints and gain the benefits of hyper-consolidation, without sacrificing I/O performance and scale. Furthermore they gain the benefits of I/O density and I/O diversity, with the added advantage of hardware acceleration and improved physical resource management.

For more information on Virtensys and how PCIe Sharing can work for you, check out: www.virtensys.com, www.facebook.com/virtensys or follow Virtensys on Twitter: @virtensys.

Server Failure? Not Here.

- Brad Rupp, senior software engineer, SuperLumin Networks (www.superlumin.com), says:

Today’s businesses are searching for ways to reduce costs, yet maintain reliable access to critical Web and cloud-based applications—even in the event of server hardware failure. Recently, SuperLumin Networks, a leading provider of scalable, high-performance media proxy and acceleration solutions, announced support for bypass NICs from Interface Masters.

Designed to provide maximum uptime for networks, SuperLumin Nemesis’ new fault tolerance capability offers a lower-cost alternative to expensive layer 4 switches and routers. Specifically, SuperLumin supports the Niagara n22xxed series NICs in SuperLumin Nemesis version 2.2, build 3446 and later.

Our partnership with Interface Masters allows SuperLumin to provide a low cost, high availability solution to our small business customers. In a nutshell, the Niagara NIC provides bypass capabilities in the event of a power failure, loss of heartbeat or other general server failure. If the server fails for any reason, the Niagara NIC will go into bypass mode, allowing all Ethernet traffic to flow through the NIC. While customers lose the caching capabilities that the SuperLumin Nemesis software provides, end users will see no loss of service.

As an example, assume I have a SuperLumin Nemesis server configured to provide caching of YouTube videos. This service alone provides a significant reduction in bandwidth usage, while allowing my end users to receive a better experience. Videos are delivered faster and at a higher bit rate, all while reducing upstream bandwidth usage to my ISP.

Now, suppose the server running SuperLumin Nemesis fails. In most cases, the end user’s ability to access YouTube would fail as well. With the addition of a Niagara NIC, this is not the case. The Niagara NIC will automatically go into bypass mode which connects the two ports of the NIC together, allowing all Ethernet traffic to continue to flow. End users can continue to access YouTube, although the service would be degraded due to the loss of caching provided by SuperLumin Nemesis.

We all know there are many ways to provide high availability. Each solution is a tradeoff between cost and the number of ‘9's we get of uptime. With the inclusion of a Niagara NIC in a SuperLumin Nemesis server, I can continue to provide access to my end users even if the server fails.

Far beyond the fault tolerance capability of SuperLumin Nemesis, we are recognized as one of the leaders within the caching market. SuperLumin Nemesis provides a rich feature set of access control rules, firewall and packet filter support, and authentication to LDAP, RADIUS, and NTLM back ends.

Those interested in a 45 day trial of SuperLumin Nemesis can download the ISO, documentation and a trial license at http://www.superlumin.com/knowledge_center/.

Simplifying Data Center Management with Converged Network Fabrics

- Matt Theurer, senior vice president, solutions architecture for Virtustream (www.virtustream.com), says:

Two disruptive trends have recently dramatically increased the data protection challenge: massive growth of digital data and the adoption of virtualization technologies that are driving server consolidation. Massive growth in data storage and processing and a decrease in physical server counts with virtualization technologies.

With the amount of data ever-increasing, the storage target and storage fabric (together, traditionally known as a Storage Area Network or SAN) is exploding in an almost exponential fashion. This massive increase in storage requirements, along with the need to access, manipulate and backup the data in ever shrinking time windows is stressing the SAN – putting data at risk and creating pressure on IT budgets.

Implementing a virtualization layer is now the norm. The high compute densities fostered by virtualization have placed similar stresses on the Local Area Network or LAN similar to the stresses placed on the SAN. Before virtualization the LAN traffic generated by a physical server was measured at a few hundred kilobits per second (Kbs) up to a few tens of megabits per second (Mbps). Modern physical hardware can have tens of processors processor cores and hundreds of gigabytes of RAM. This hardware supports tens and hundreds of virtual machines (vms) running on a single physical server with the concomitant network traffic now being measured in hundreds or even thousands of Mbps .

Fortunately, a new type of data center networks is emerging –converged networks – which shows great potential for handling scaled-up IT environments and streamlining data center operations.

Benefits of Convergence

Most traditional IT environments consist of two separate infrastructures – SAN and LAN – each with its own distinct architecture. This type of environment can be difficult to manage when scaling up and often requires two separate administrative groups to maintain. However, there is an alternative type of environment that is ideal for streamlining storage in data-intensive environments: a Converged Network Fabric. By merging SAN and LAN into one infrastructure, Converged Network Fabric merge can increase throughput, reduce cabling and redundant switches and adapters and lower administrative costs.

Because of their ability to simplify data center management, Converged Network Fabrics are ideal for enterprises considering migrating to a cloud computing environment. Data centers in traditional IT environments often have complicated communication networks, underutilized capacity and too many resources dedicated to managing both SAN and LAN infrastructures. But with a converged network, managers can strategically align SAN and LAN under one single administrative group, reducing management oversight and costs. In addition, converged network fabrics greatly reduce the number of physical connections per host. By reducing the physical infrastructure and simplifying data center management, converged network fabrics can help position enterprises for a smooth transition to the cloud.

Steps Toward Convergence

Prior to implementing a Converged Network Fabric it is important to understand the workload requirements of the existing communications and storage networks. You must assess the data transfer rates (typically measured in Kbps) for both storage and traditional network communications and you must understand the packets per second on the communications side and the input/output operations per second (IOPS) on the storage side.

Once you understand the storage and network traffic that will be crossing your converged fabric you must examine both the transit devices and the end point devices to verify that they can handle load. Your transit devices (switches) must be able to provide full point to point bandwidth as well as handle all of the packets traversing the interfaces. You will experience a larger mix of packets sizes from the traditional 1500 byte Ethernet frame to 2148 byte Fiber channel frames to 9000 byte Jumbo Ethernet frames. You absolutely do NOT want the ASICS in your switches to be oversubscribed. Beware of the inexpensive switch; it may cost you more in the long run.

Storage devices especially can put “back pressure” on the fabric and source load devices. By calculating IOPS (I/O per second) and the read/write ratio of those IOs, you can accurately design your backed storage system. Ensure your backend storage system(s) have sufficient I/O capacity to support the I/O being generated by the host(s). All of this data will help you determine the end benefit for your particular IT environment.

Avoiding Missteps

The most common mistake when implementing this type of convergence is not understanding the underlying traffic patterns. It is vitally important to size not only for bandwidth but also for packets per second on the communications side and IOPS on the storage side. Understanding how these types of traffic flow and interact is key to a successful implementation.

Another common mistake is not designing for high availability. On a converged fabric all data is flowing through a relatively small number of devices. Ensuring a sound, redundant design is critical.

The third most common issue is not sizing for growing workloads. This is especially true in virtualized and cloud infrastructures. Virtual server sprawl compounds this issue. Even in cases where the virtual infrastructure was properly sized and configured for network and disk I/O during the initial deployment, most organizations see dramatic growth in their virtual infrastructure over time. Typically additional network and storage resources are not added as new virtual machines are deployed. As new virtual machines appear, they are placed on existing disk pools and network volumes – often without consideration for the current communications and storage loads. Virtual machines use the same resources for a given workload as a physical server. It is important to have a good understanding of your requirements for both network and storage capacity and plan for growth accordingly.

Conclusion

Every day businesses are faced with massive data growth and flat IT budgets. Data centers in traditional IT environments often have complicated communication networks, underutilized capacity and high management costs. Converged networks, however, have the ability to increase data center efficiency and reduce management costs. By consolidating data center administration and streamlining throughput Converged Network Fabrics can help be a valuable solution for enterprises preparing for a move to the cloud.

For Additional Information

Two YouTube videos are available taking a closer look at Converged Fabrics:

Converged Fabrics



Converged Fabrics: Part 2 - Calculating IOPs –

Are Your Data Center Monitoring Practices Putting Critical Operations At Risk?

- Kurt Crisman, marketing manager with Network Technologies, Inc.(www.networktechinc.com), says:

Temperature, humidity, and other factors can impact data centers, telecom switching sites, and other POP sites. In a many businesses, three groups monitor environmental threats to data center and switching site equipment: network administrators or operations managers, security personnel, and maintenance employees. Often, particularly in a small or mid-sized business, monitoring of equipment may be performed by staff onsite or visiting equipment in remote locations. However, these monitoring practices may be putting critical business operations at risk.

• Damage caused by the environment can be subtle, unseen, or attributed to other causes. Condensation, rust, and heat damage is usually hidden inside machines, out of human sight.
• The frequency and quality of a site check may vary from person to person. Even if procedures and schedules are in place, adherence to those procedures and schedules may vary.
• Environment threats occur 24 hours a day, seven days a week. But staff is not always on site. Depending on staffing levels and schedules, environments can be unmonitored up to seventy percent of the time during an average week.
• Without a log of changing conditions—temperature and humidity levels constantly increase and decrease—administrators and managers cannot identify problems caused by these changes. These problems can continue for days or months, while time and money is wasted investigating false causes and solutions.
• As soon as you have people checking on equipment or performing maintenance, you can actually create problems where they hadn’t existed before. For example, boxes set in front of vents “temporarily” are not moved.

An effective server environment monitoring system addresses the weaknesses in the current practice of having personnel monitor the environment.

Network Technologies, inc. offers a range of server environment monitoring solutions that monitor critical environmental conditions that can destroy network components in a server room or POP site. When a sensor exceeds a configurable threshold, the system will notify the selected administrators/staff via email, SNMP traps, Web-page alerts and a visual indicator (LED). The systems connect to your IP network, so they can be configured and monitored from any workstation with a Web browser. Event-triggered snapshots from an IP Camera can be sent by email.

Our products provide the following benefits:

• Control costs - In a stable environment, equipment lasts longer, and less equipment is damaged and needs replaced. Typically, the savings from not having to replace equipment can pay for the cost of the monitoring system.
• Increase lead-time to fix a problem - The earlier the warning alarm sounds, the sooner personnel can solve the problem before it becomes a disaster.
• Reduce downtime - Hardware housed at the recommended environmental conditions operates more efficiently, while also shutting down less frequently. Consequently, employees stay productive, and e-commerce sites continue to generate revenue.
• Log environmental data for greater insight - In order to maintain stable conditions in the server room, administrators must have accurate records of what has happened. Logging is also critical for investigating problems.

High Performance, Scalable Cloud-based Systems Management Technology

- Nand Mulchandani, CEO and co-founder of ScaleXtreme (www.scalextreme.com), says:

Enterprise data centers are evolving: most are using virtualized servers; many have private cloud deployments, and some are running hybrid clouds, combining public and private cloud infrastructure resources. ScaleXtreme’s high performance, scalable cloud-based systems management technology provides a simple way for IT administrators to manage all servers; whether they be cloud servers at Amazon EC2, VMware virtual machines hosted at a private cloud provider or physical server deployments in the data center. These capabilities significantly reduce the amount of manual server maintenance involved, and provide systems administrators with a simple way to both provision and manage the lifecycle of their cloud servers with end-to-end lifecycle management from a single system – all across multiple server types and hosting providers.

Any technology that enables the data center to elastically expand or contract based on IT needs is critical to creating a cost-effective, efficient infrastructure; cloud-based systems management does exactly this. While many products on the market provide the ability to provision machines, IT is typically required to pull together a mix of products from multiple vendors to solve their hybrid-cloud provisioning and systems management needs. The ability for one cloud management product to provision new machines across multiple clouds as well as maintain those machines throughout the machines’ lifecycle - including configuration management, inventory management, and task automation - is key and should be a priority since it saves time and money.

Legacy systems management has been a hindrance to cloud adoption, since the inability to configure, inventory, patch or audit machines in the cloud means that long-lived machines are typically not moved into the public cloud.

Legacy systems management applications were never designed to scale in line with an elastic data center. In a modern enterprise data center, where servers may be provisioned on demand, used for days, weeks or months, and decommissioned, the traditional approach to systems management just isn’t relevant any more.

Equally, the cost models for those legacy management tools – heavy on-site license fees, long implementation cycles, and expensive consultants on the project – simply doesn’t fit for cloud servers that are being paid for by the hour.

To overcome these challenges, it is important to unify the management for all of an organization’s servers, spanning private and public cloud machines, public cloud providers running on any virtualization platform and even physical machines. By managing the full lifecycle of machines through this “single pane of glass”, customers don’t have to stitch together multiple products to solve their hybrid-cloud provisioning and systems management needs, allowing for greater flexibility, scalability and cost effectiveness.

And by choosing a cloud-based systems management service that scales in line with their server footprint, IT managers can apply appropriate systems management resources that match their needs.

It is important to look into the options available on the market. Many solutions are expensive, have a steep learning curve, and require a number of people to run well. Also, some providers are limited to providing access across the cloud and through physical servers, which requires log-ins on multiple machines.

Cloud management should be seen as a full server lifecycle management process. Simply starting up some cloud servers and leaving the IT user with little more than a command prompt with which to manage them, is no longer enough. Systems administrations want to able to control the whole process: bring machines online, manage them on a day-to-day basis – moving files, automating installations, configuration changes etc - and decommission them at will. Make sure you invest in something that delivers end-to-end systems management – IT users will thank you for it.

The "New Blade" Form Factors

- John Fruehe, director of product marketing for Server, Embedded and FireStream products at AMD (www.amd.com), says:

If you look at the evolution of the data center in recent years, data centers continue to change rapidly. “Twin” form factors, which are two motherboards in one chassis, and high density modular form factors are becoming much more mainstream. These form factors are the “new blades” – a more cost effective way to address the need for increased density in a smaller physical footprint. This is critical because businesses today require more processing power than ever before, but they can’t always build a new datacenter to house additional servers. In addition, modular data centers, containerized data centers and even racks greater than 42U are all springing up as ways to address both density and efficiency. Greater density means greater power usage and cooling needs, so it is important to incorporate as may power-saving features into your data center as possible. This is why AMD offers processors with up to 12-cores in addition to processors with the world’s lowest per-core power draw: it’s all about achieving the perfect balance of price, power and performance.

We'r seeing a wide range of platforms targeted at cloud deployments. Modular form factors address computing from a thermal perspective rather than looking at raw performance and the same old vanilla form factors. Performance is important, but it’s still only one piece of the puzzle. These days, customers are demanding a balanced platform and OEMs are answering the call to action by providing a wide range of options.

We’ve seen a great reception from our OEM partners to the AMD Opteron 4000 Series and 6000 Series platforms introduced last year. Dell is one example of a manufacturer that is seeing demand for higher density; in February they launched the Dell PowerEdge C6145 which packs up to 96 cores into a 2U server.www.amd.com

Five Capacity Management Challenges for Private Clouds

- Bryan Semple, CMO at VKernel (www.vkernel.com), says:

Introduction
Organizations that are seeking to deploy “cloud” based business models for their infrastructure face unique capacity management challenges. This post will review these challenges to enable cloud providers, either public or private, to avoid the pitfalls of improper capacity management. While the post discusses both types of clouds, the needs of private cloud providers will be especially highlighted due to the unique challenges they face with this business model.

IT Becomes a Business within a Business
For years, we have been hearing “IT must behave more like a business”. A hypervisor’s ability to deliver utility computing moves this vision closer to reality. Using hypervisors to deploy an infrastructure cloud fundamentally changes the relationship between IT and their customers. Application portability combined with competing cloud offerings from companies like Amazon change the dynamic between application owners and corporate IT. If end users can’t explicitly move their applications between cloud providers, they can at least compare prices and service levels between providers. Right or wrong, Amazon S3 becomes a measuring stick in price, performance and service for IT organizations.

To deliver an Amazon S3 experience, requires significant retooling in IT processes. Capacity management is one of the areas requiring retooling. Virtualization alone causes changes to capacity management (for more information, see http://www.vkernel.com/solutions/capacity-planning). But virtualization deployed as an infrastructure cloud adds nuances to the capacity management problem. Capacity management for cloud providers is unique for the following five reasons:

• Capacity monitoring in addition to planning
• Chargeback is mandatory
• Efficiency drives return on assets
• Tenant reporting requirements are unique
• Optimization is a value add

Variable Demand Drives Criticality of Capacity Monitoring
Cloud deployments of virtualization technology introduce many operational changes for IT administrators. The first is a change in the amount of control IT has over the loads deployed on their hardware. With cloud deployments, either public or private, end users deploy applications using self service portals as they see fit, load them as they desire and consume resources at whatever pace they need.

Hence, unlike the careful P2V sizing process undertaken for the first wave of virtualization where applications are sized, scheduled and deployed in a methodical manner, clouds have no careful sizing or timing that the cloud operator is aware of. Applications of unknown sizes appear, consume resources, and may just as quickly disappear. Without adequate capacity, these applications will fail to perform to customer expectations. Without real time capacity monitoring, application deployment can dramatically impact other applications.

Hence capacity planning, a well thought out process for making sure there is sufficient capacity en masse, must be supplemented with capacity monitoring. Capacity monitoring is a real time process that takes raw performance and utilization data and transforms it into actionable information concerning system level capacity requirements. Without capacity monitoring, system administrators are left to interpret real time utilization metrics from individual virtual machines. VKernel’s research has shown that properly monitoring capacity in real time involves collecting over 20 metrics per VM at least 10 times per hour, and keeping this information for at least 30 days. A 100 VM environment would require about 17 million data points to accurately monitor capacity in the environment. This capacity monitoring, however, is a must have to augment standard capacity planning and prevent performance issues from impacting the cloud.

Chargeback Matters
For any cloud where resources can be deployed in a self service fashion, charging back for resources becomes a necessity. Without a method to chargeback or show back, self service clouds would quickly find themselves at capacity since resources are essentially free.

But chargeback is a tricky area. For commercial cloud and private cloud operators, charging back for allocated resources is fairly straightforward. But, since the private chargeback operator is simply shifting costs insides the company and not impacting the bottom line, the motivations for chargeback are different. The public cloud operator is indifferent to allocated resources and utilized resources. If the public cloud operator is charging for an allocated resource pool, they make money. In fact, the higher the ratio between allocated and utilized, the more over allocation of resources is possible and the higher the profit margins. For private cloud operators, however, the goal is to actually lower the costs for the company. Hence, the private cloud operator wants the allocated resource usage to be very close to actual usage to drive resource efficiency. Highlighting the difference between actual resource usage and allocated resource usage shows internal business units the amount of corporate resources they are wasting. This motivation can then be used to right size environments and reduce overall IT spend.

While chargeback is important, cloud operators need to be mindful of what they charge. For public operators, there are competitive pressures. For private operators, charging provides a manner to directly compare internal IT costs vs. external costs such as Amazon.
But is a simple $/CPU comparison between internal clouds and Amazon a fair comparison? Does Amazon contain the same level of compliance? Control? Is the company comfortable with data outside the company firewall?

More importantly, chargeback for private cloud operators is primarily a means to minimize the difference between allocated and utilized resources to drive up efficiencies and VM densities. Chargeback or showback becomes a control mechanism as opposed to an actual financial transfer mechanism. Hence the rate of chargeback is not as important as the difference between allocated and actual usage.

However, even here, the challenges for private cloud operators are greater. Let’s assume a private cloud operator hosts 200 internal customers. Assume each of these internal customers is wasting 50% of their resource allocation. On an individual basis, the absolute value of the wasted resources may be insignificant. But across all 200 customers, the magnitude of the IT spend could be quite large. The greater good theory for IT would require that IT actually reduce resource usage for all the internal customers to claim additional savings for the company despite what the internal customers want. Private cloud operators must operate for both their internal customers needs, but also for the company’s needs.

Setting rates for chargeback is the final tricky area for cloud operators. For a public cloud operator, the rate needs to be competitive, provide some profit margin and match customer’s value. Easy enough. But what about private cloud operators? Once again, being a private operator makes things difficult. What are the rates for chargeback for a private cloud operator? Is the goal to set rates to make an internal profit when 50% of the VMs slots are filled? 75%? But if the internal cost center is making a profit, is that the right thing to do from a budgeting standpoint? Is the goal cost reclamation or efficiency?

The net of this, is that for cloud operators, chargeback is critical. For private cloud operators, chargeback’s purpose needs to be clearly defined to align IT not only with their customer’s goals, but also the broader corporate goals.

Capacity Planning Impacts Revenue and Cost
Customers expecting to use a cloud service have high expectations with regards to time to deploy a service. For public clouds, this expectation will be a nearly instant deployment after the service request. Private cloud operators may not have quite such an instantaneous expectation for their customers. Either way, however, the “acceptable” wait time of several weeks to deploy a new server is gone. Immediate is the word, not days.

To enable this immediate capability, sufficient capacity must be on hand to deploy new virtual machines based on both steady state and unexpected increases in demands. To meet this accelerated time duration, a high degree of capacity planning must take place to predict future capacity needs ahead of demand and allow for the slower process of procuring and installing physical servers, networks and storage.

It is easy to meet rapid deployment expectations by over procuring hardware. The danger here is that over procurement impacts cash flows and profitability for a cloud. Having large amounts of depreciating assets sitting around is not a sound business strategy. If these assets are plugged in and configured, the added power costs worsen an already bad situation. Under procuring hardware is just as bad since cloud operators will be unable to meet customer needs should their systems not have available capacity. Hence the goal is to have a solid understand of consumption and then apply a safety factor to allow for unexpected demand.

Understanding capacity needs across the entire IT infrastructure is important. But it is just as important to understand where there are available VM slots for best placement of VMs both from a performance and capacity standpoint. Utilizing available VM slot reporting ensures both performance of the running VMs but also increases the VM density per host which is critical to achieving a high return on assets.

Capacity planning is critical to cloud operators to generate a high return on assets while also meeting customer demand for near instantaneous deployment requests.

Tenant Reporting
With a standard virtualized environment, the IT organization may report on environment status to a few senior IT leaders. Not so with an infrastructure cloud. For public clouds and private clouds, there is a greater expectation of visibility into the environment. Reporting for cloud tenants could involve availability, resource allocation, resource utilization, current charges, and pricing plan. The amount of information revealed to a customer could depend on the business philosophy or type of cloud. For a private cloud, revealing differences between allocated resources and utilized resources and the savings a customer could achieve by reducing their resources allocation makes sense for a company trying to save money. For a public cloud provider, however, suggesting ways to reduce resource allocations may not be in the provider’s interest.

Beyond questions around what type of information to provide is the manner in which information is provided. For public cloud operators, online portals are most likely the reporting distribution mechanism of choice. For private clouds, however, information needs to flow seamlessly into the enterprises existing reporting infrastructure. This could involve connections with sharepoint, with IT service management frameworks, internal portals, or simple email distribution of reports on an ongoing basis.

Optimization is a Value Add
Many times, when virtual machines are first deployed, they are over allocated CPU, memory and storage. In a cloud deployment, this over allocation does not cost the cloud operator revenue. In fact, just the opposite occurs. The cloud operator deploys the requested resources, but despite not being used, the cloud operator still collects the revenue. As discussed earlier, the cloud operator can decide whether to reveal this to the tenant or not.

While the cloud operator may not care about wasted resources to an application, the end customer does as does the firm’s CFO. Decreasing requested CPU, memory and storage reduces monthly tenant costs. Hence, optimization becomes an optional value add service for the provider to offer tenants to reduce spending. This would be the equivalent of your cell phone company contacting you to suggest a lower monthly plan. While it lowers the monthly revenue of the cloud operator, it dramatically improves customer loyalty.

Conclusion
Because of the increased need for chargeback, monitoring, capacity planning, and reporting, capacity management takes on added urgency for cloud operators. Capacity management performed correctly enables cloud operators to maximize compute cycles delivered to a customer at the lowest possible cost and thus, capacity management is a key building block for any cloud implementation.

Adding I/O on Demand - Leveraging IOV (I/O Virtualization)

- Stephen Spellicy, vice president of marketing at Virtensys (www.virtensys.com), says:

Traditional data center managers and IT admins take a conservative approach related to managing/provisioning I/O connectivity to rack mount based servers, typically installing multiple network interfaces cards (NICs) and storage host bus adapters (HBAs), with redundant cables/switches. This causes a burden on IT’s ability to agile/responsive to their business needs, as the setup/teardown of these environment are both time consuming and costly.

In fact, server administrators make choices everyday on how I/O connectivity is assigned and dedicated to the servers they deploy. These choices are often based on “business as usual” behavior or process – rather than what’s best for the organization. Every time an I/O adapter is inserted within a server it’s made “captive”, essentially trapped within that particular server. This makes inefficient use of a critical/valuable resource that could be used by other servers with their data center.

In addition, the physical complexity of the traditional approach limits operational scale and IT agility. For instance, having to allocate a cable per connection, each to a dedicated network interface, not only consumes resources but also consumes a vast amount of time. It also causes headaches when trying to isolate issues -- troubleshooting a connectivity problem becomes a virtual nightmare.

Data center managers and IT admins can greatly improve the time to deploy and managing the task of provisioning I/O connectivity to servers. This can be done centrally within the Virtensys management console, providing an easy to use/manage experience that allows them to add I/O on demand, when they require it.

Virtensys’ approach leverages something called I/O Virtualization (IOV), which means that servers leverage virtual instances of traditional "off the shelf" NICs (network interface cards) and HBAs (host bus adapters). To the server, these virtualized I/O adapters appear and operate as if they were a locally installed physical I/O adapter but in reality it’s a virtualized in hardware and software. Because Virtensys’ approach consolidates traditional I/O adapters (specifically Intel’s 10 GbE NIC and Qlogic’s FC HBAs), it can drive up the resource utilization and make more efficient use of this traditional costly resource.

Using a Virtensys’ VIO-4000 Series IOV appliance, server administrators can “free” the “captive” and valuable I/O resources from single servers and make them available through the I/O Virtualization appliance to multiple servers within the data center. Not only does this make sense from a resource utilization perspective, but it also solves serious problems associated with network cabling and I/O configuration complexity for both network and storage connectivity. Ultimately, I/O Virtualization reduces the physical complexity, enabling server administrators to reduce “physical layer” guesswork when troubleshooting connectivity issues.

Virtensys's approach allows IT admins to deploy a solution to solve a serious problem by greatly improving their server I/O utilization and maximizing the value from their existing network/storage related investments. The I/O Virtualization appliance improves utilization of the critical I/O resource, can be configured to guarantee the Quality of Service (QoS) per server/per port, and can be applied to fine tune how those resources will be used.

Overall priority in the data center.

Virtensys’ technology covers a fundamental need within the data center – connectivity to storage and network resources. The Virtensys VIO-4000 Series IOV appliance allows standard rack mount based servers to access a variety of network/storage resources used in today’s data center. As far as rank, if IT organizations continue to grow their server environments (as they have been with the advent of server virtualization and new storage product adoption), for both physical and virtual data centers, their resource needs don’t go away, rather only increase. The core value of the product is to simplify the I/O provisioning process, so any IT organization seeking improvements in process and looking to become more agile in their operation should consider this improving this layer of infrastructure management in the data center. Virtensys’ value proposition enables IT to address operational challenges and reduce capital expense related to network and storage related peripherals.

The biggest challenges for data center and IT managers.

IOV is a relatively new technology approach within the data center. Naturally, the biggest challenge to adopting to IOV technology is IT's reliance on the “business as usual” approach. If IT adminis are looking control OPEX (operation expense), reduce CAPEX (capital expense), and remain competitive, then they need to be open to a new way of performing this critical task. With all technology adoption, stability is a key, disruptive technologies, like IOV, change the way people approach a traditional task. By adopting a new technology or approach, it shouldn't impact the stability of the environment or require vast changes. Within the Virtensys VIO-4000 Series architecture, a key component of the design is to leverage PCIe (PCI Express) sharing, which is the technology mechanism for how servers access virtualized I/O resources.

PCIe is a universally adopted and accepted server technology, it’s native/natural to the server and is well known/understood by every server admin today. By design, Virtensys enables investment protection through PCIe sharing. It leverages standard PCIe based I/O adapters and makes full use of the “standard” software drivers already within the operating system. This means there is no need for additional or special server-side software, rather servers merely connect to the appliance, access their virtualized instances of the standard I/O adapters they would normally have to dedicated in each hosts. Virtensys' VIO-4000 Series IOV appliance can be implemented in a non-disruptive manner. It allows the server admin to greatly reducing the number of interactions, from the initial installation to the on-going maintenance/provisioning of I/O to connected servers.

Overcoming the challenges.

In today's competitive IT marketplace, more CIOs now than ever are seeking such ways to lower their total cost of ownership (TCO). I/O virtualization enables real savings for IT departments. In some cases, a return on investment (ROI) analysis or proof of concept (POC) has been useful to demonstrate such value. This approach will typically help those data center managers and IT admins seeking justify implementing technology such as IOV. For those IT admins who have already chosen to deploy Virtensys' technology, they have been able to realize an immediate and clear ROI. Typically, Virtensys will engage in a proof of concept (POC) with customers to demonstrate that the technology works within their environment and provides the value that it claims.Once Virtensys's VIO-400 Series IOV appliance is deployed, a lower TCO can be realized by reducing the number of I/O adapters per server (4:1 from a server perspective, 8:1 from an appliance to switching layer perspective). Savings come from deploying fewer I/O adapters, less cabling and less power to the servers and fewer access layer switch ports.

Advice for data center and IT managers.

The best advice to those seeking solutions to solve I/O management issues is to do the research of the various approaches to solving the problem that Virtensys' VIO-4000 Series IOV appliance is addressing. Look carefully at the implementation choices/challenges of the various technology options. Factors to consider are installation, operating systems support and ISV certification/validation. Virtensys leverages and presents native 10 GbE and Fibre Channel connectivity, this means that it isn’t advocating using new protocols to encapsulate or change how the server hosts communicates with external network or storage resource. At core, Virtensys is improving the physical layer I/O management, which achieved through I/O consolidation. Virtensys' approach doesn’t alter or change the underlying network/storage protocol. Also, be careful to evaluate the impact to the server, related to adding new/different adapters or network switches, and any special purpose software that might need to be installed on the host itself.

Virtensys’ award-winning VIO-4000 Series IOV appliances are changing the way IT managers manage and deploy I/O resources to standard rackmount-based servers, enabling a more agile, scalable and dynamic data center. Built upon Virtensys’ patented PCIe sharing technology, the VIO-4000 Series consolidates, virtualizes and shares traditional I/O connectivity for both physical and virtualized server environments. Server administrators can now simply “wire-once” and then remotely manage and provision their I/O resources as needed.

For an in-depth explanation of how IOV works and specifically how Virtensys' VIO-4000 Series IOV appliance can be leveraged in the data center, please take a look at this video tutorial:

Watch Out For Falling CFD Prices

- Arik S. Dvinsky, CEO and CTO, Daat Research Corp. (www.daat.com), says:

For data center managers wrestling with demands to increase performance, server hot spots remain the bugaboo. Would it be better to shift racks around, replace equipment or just throw more CRACS at the problem?

For some companies, CFD (computational fluid dynamics) analysis delivers the answer. Its 3-D models of temperatures and flow can replace guesswork with answers accurate within 10% or better. What better way to design new facilities or enhance existing ones.

Other companies haven’t been so lucky. They’ve been cheated out of the benefits of CFD because they thought it is too expensive. Despite paybacks—from reduced down time, lower operating costs, increased efficiency and improved performance, CFD has been, indeed, costly.

It is not unusual for a data center CFD consulting project to run $40,000-$80,000. And that is just the first time around. Often within months, some underlying assumptions in the analysis will change: power dissipation proves to be higher than estimates, new equipment is added or replaced with more powerful version and so on. The choice then becomes whether to re-hire the consultant or take your chances on equipment failure.

Instead of hiring consultants, you can license a CFD package and have in-house engineers run the simulations. Until recently, purchasing high-end CFD data center software cost as much as $60,000 per year. Less costly options, ranging from $20,000 to $30,000 per year, were available, but lacked the full range of capabilities and implemented simplified assumptions that produced less accurate results. Recently new full-function high-end data center software, CoolitDC, was introduced by Daat. CoolitDC runs on a laptop and sells for a small fraction of competitive products--advances built on the company’s 20 + years in CFD development for electronics. Now you can purchase high-end CFD software for well under $10,000 including training and support.

The Face of Data Center Servers

- Andrew Feldman, CEO at SeaMicro (w ww.seamicro.com), says:

Have data center servers changed much in recent years?

The obvious question is why has there been so little innovation in the server space in the last 15 years.

Our view is that server companies became supply chain companies, focused on wringing every last ounce of cost out of their supply chain. They moved to low cost manufacturing regions, used massive purchasing power to pressure component vendors etc.

What they didn’t do was invest in R&D or invent new technology. They didn’t innovate. Even the so-called ‘blade revolution’ is largely a packaging exercise that takes a 1 RU server and rotates it 90 degrees and slides it into a backplane. Instead of real innovation, server companies relied on the next Intel reference board, the next processor…

SeaMicro’s approach is very different. We invested tens of millions of dollars in research and development. We invented technology that allows us to remove 90 percent of the components from the mother shrinking the motherboard to the size of a business card. We then developed technology that could link hundreds of these mini-motherboards together at radically reduced cost and power draw.

And the result is a new server architecture that uses one-quarter the power and takes one-quarter the space.

Today, most of the server manufacturers are focused on modifying existing designs.
They are working to remove a component here or there. At SeaMicro, we don’t think that is a productive approach. Our view was that the server needed to be rethought from the ground up. The question isn’t ‘what component should we change’ but rather, if we were to begin with a blank sheet of paper, which components would we use, and what technologies would we invent to eliminate dozens of components?

The most important trends are around the rise of the Internet workload and the recognition that one server size does not fit all needs.

Think Servers Haven't Changed Much?

- Don Clegg, vice president of marketing and business development at Supermicro (www.supermicro.com), says:

Servers haven’t changed much in recent years. This may be a common misperception, but it’s a huge misperception. There have been significant advances in overall processing power, core counts, compute power and density, power efficiency and cooling, chassis and rack enclosures, interconnection technologies, server management, virtualization, etc., etc. Supermicro has leveraged all of these technical advancements to create industry-leading application-optimized data center server solutions. Because one size doesn’t fit all Supermicro uses a server building block approach that allows our data center customers to create and configure systems tailored to their specific needs (vs. a generic “pizza box” approach often used by others).

A key trend involves driving down service costs while increasing up-time. Supermicro accomplishes this in a number of ways, such as powerful server management to remotely manage servers along with increased hot-swap capabilities in its servers to minimize any down time. Blades are often fantastic solutions for data centers and Supermicro has solutions with world’s best power efficiency and density, but there’s also another class of servers, namely Twin™ architecture servers that have gained wide adoption and are gaining market share in this space. Supermicro, led the way with their concept of two or four hot-swap fully independent server nodes in a single 1U or 2U enclosure. Since that early Twin platform, many generations of innovative Twin™ products have been created to enable data centers to easily scale up and out while benefiting from hot-swap-ability and reduced costs by sharing power and cooling among nodes in a single enclosure.

Where are things headed? Many data centers want to drive down their operational cooling costs so that they can continue to grow without exceeding their overall electrical power budgets. Both Supermicro blade and Supermicro Twin™ architectures accomplish this. In addition, Supermicro has designed a family of rack enclosures that improve cable routing and air flow so that cooling costs can be further lowered. In the future, data Centers will become greener and greener. Not just because of their desire to be good citizens (which is important on its own merit) but because of the cost savings associated with improved efficiencies. With its housands of server building blocks and in-house design for fastest time-to-market, Supermicro really is the market leader in server innovation for data centers.

Data Center Infrastructure Management: Not Just Useful, It’s Imperative

- Pete Manca, president and CEO of Egenera (www.egenera.com), says:

Data center infrastructure management is not just useful, it’s imperative. If you share my point of view that an IT network is analogous to a neural network, it’s easy to understand just how critical it is to maintaining business continuity. The data center is the cortex of the business, delivering critical applications, data, security and a host of other important business functions. When the infrastructure is working as designed, a business can run smoothly. However, when the infrastructure is interrupted or fails, it often has severe negative impact on the business: customers and partners can’t place orders; manufacturing and service delivery can be interrupted; vital information is lost. Not only can this result in an immediate loss of revenue, but a company’s brand can be de-valued or destroyed. Just think about the recent Amazon EC2 outage.

The benefits to optimizing data center management range from costs savings such as lower power consumption, capital expenditures, and software licensing costs to creating new revenue opportunities. For example, cloud service providers can stand up servers more quickly and accelerate revenue recognition. A financial services firm can quickly provision server capacity for a hot new trading application. The possibility of generating new revenue streams by improving data center management should excite everyone.

Where should data center infrastructure management rank in terms of overall priority in the data center?

Building and maintaining a reliable, high-performance data center is a C-level, even boardroom, issue. Organizations and individuals who don’t grasp the strategic importance of ensuring business continuity by maintaining application availability and planning for disasters put themselves in jeopardy. I recently read a blog post from a front-line IT consultant who identified the five top data center issues for enterprise IT executives. They include growth and expansion; cost control; governance; risk management and security; outsourcing; and resistance to change. The first four are clearly infrastructure management issues.

The biggest challenges for data center and IT managers when it comes to data center infrastructure management.

Reliability, security, and simplicity are the biggest challenges. It can be fairly easy to bring a new application online. However, keeping that application running through various outages and keeping it secure can be a challenge. How the infrastructure is configured and managed is key to consistently meeting service level agreements and providing effective secure. For example, creating complicated procedures for availability can lead to a fragile environment, and one that is often only manageable by a select few. Creating an IT environment that is not only highly-available and secure, but also simple to manage, is nirvana for the data center manager.

Overcoming the challenges.

These challenges can be overcome by embracing new technology to simplify the data center. Converged infrastructure (CI) is a good example. It simplifies the physical connectivity for storage, networking, and management interfaces, introduces automation, and reduces the number of moving parts in the data center. When done correctly, CI can provide for a more robust environment and a simpler infrastructure to manage. Why do with hardware what can be done with software? Providing consistent, uninterrupted application availability and planning for catastrophic events is also a must.

Choose best of breed and don’t allow for vendor lock-in. Choose an open solution that allows you to pick best-of-breed technologies at all layers of the stack. Options are always a good thing.

Server virtualization is common practice for many valid reasons, and there has been a lot of buzz about virtual desktop infrastructure, but the virtualization story doesn’t stop there. IT sprawl and server virtualization has added complexity to the data center. Service providers and enterprises are looking for a way to simplify the deployment and management of IT infrastructure. These challenges are solved by reducing physical hardware and converging infrastructure management.

The benefits of server consolidation and virtualization are proven and clear. But it addresses only half of the data center cost and complexity problem. Hardware virtualization eliminates time consuming, error-prone, costly human intervention and eliminating hardware components, including NIC and HBA infrastructure.

Why Remote Access Management? Security and Efficiency

- Eran Kessel vice president of marketing & products at Minicom (www.minicom.com), says:

The benefits of remote server access
Years ago, the idea of operating and maintaining data centers remotely, or with “lights out” in the server room, seemed radical. Now it’s standard procedure. Why? Because of three compelling advantages:

1. Increased data security—with remote access, the data center can be secured from unwanted visitors.
2. Improved operational efficiency—with remote access, your IT staff can fix problems from their computer screen—they don’t have to be onsite. Remote access means doing more with less.
3. Better cooling/power efficiency—one of the major causes of cooling inefficiency is service staff who open doors and wander around. With remote access, server rooms are sealed tight.

Remote Access Management: maximizing the benefits, minimizing the risks
Despite the above, many companies are not maximizing their benefits. Worse, they may have actually created new security risks. This comes from the fact that remote server access tools have been adopted gradually, one at a time, often supplied by the manufacturers of the data center’s existing equipment. To maximize the benefits of remote server access, while minimizing the risks, companies need a strategy and a dedicated software solution for Remote Access Management.

What are the new security risks?
A critical security risk lies in access management: the vast majority of organizations store their passwords, user names, IP addresses, server names and more in a single spreadsheet or homegrown database. This provides IT personnel with almost unrestricted access to security-critical data, even data that has no relevance to their tasks. Windows admins can see how to access Unix machines, network admins can see how to access servers etc. There is no benefit to this, and considerable security risk. All an employee, intern or consultant needs to do is download the spreadsheet to a flash drive, and they can carry a corporation’s secrets out of the building.

The solution: task-appropriate access
To improve corporate security, a Remote Access Management solution should limit servers and IT tools to task-appropriate access, e.g. Windows admins should be able to access Windows servers only. An admin that only require RDP access should not have access to power and KVM.

Measuring operational efficiency: resolving critical issues faster
When a server goes down, resolution speed is what matters. With a spreadsheet or custom database, speed is a problem: first, the IT admin is notified of the issue. Then they have to open the spreadsheet, locate the name of the server, and copy and paste its IP address and password and username info. Dozens of mouse clicks and many minutes can pass before a device can be found. If, for example, an attempted RDP solution fails, the operator may try a KVM fix, and the copy and paste process begins again.

Over a typical shift, the wasted minutes can add up to wasted hours of valuable work time.

The solution: a minimum 6x faster server access and resolution
Minicom compared the mouse-clicks required to access a server with RDP and a spreadsheet, vs RDP and our AccessIT dashboard.

The spreadsheet took 37 clicks simply to access a server. AccessIT software cut the number of clicks to six. And that was a best-case situation. For each service attempt—KVM, iLO, PDU—the number of clicks, and the server downtime—jumps drastically.

Never Underestimate Choosing a Server Based on the Right Processor

- John Fruehe, director of product marketing for server, embedded and FireStream products at AMD (www.amd.com),

Why are AMD Opteron processors useful in today's enterprise data centers?

As today’s IT environments encounter increasing demands for more efficiency, driven by a need to reduce power while simultaneously increasing application performance, server technology has needed to adapt dynamically. AMD Opteron processor-based servers meet these needs by delivering the right balance of price, performance and power consumption regardless of whether you have one server running your small business or thousands of servers powering your mega data center. With the AMD Opteron 4000 Series platform, for 1P and 2P server environments, and the AMD Opteron 6000 Series platform, for 2P and 4P server environments, AMD is able to offer simple, yet strategic, options for data center managers who can rest assured regardless of what they choose it will come with consistent set of full features.

Where should AMD Opteron processors rank in terms of overall priority in the data center?

Ultimately, all of the technology within a data center must work together in harmony to deliver the greatest efficiencies, therefore it is impossible to have one completely outrank another, it is always most important to match your platforms to your workloads. However, as the processor is essentially the brains of the server, and the server is the essence of the data center, AMD believes you cannot underestimate choosing a server based on the right processor. And, in making that choice, need to consider a variety of factors beyond just raw performance. The key for any deployment is a balanced system.

What are the biggest challenges for data center and IT managers when it comes to identifying the right server configuration?

Oftentimes, it can be a struggle to accurately calculate the cost of a server and how that relates to both capital expenditure as well as operational expenditure. Meaning, when choosing the right server configuration and considering cost, there is much more that comes into play beyond just the sticker price. It’s critical to have a clear understanding of how the server will perform over its lifespan and what the power and management costs will be. We believe the efficiency that AMD Opteron processors deliver in the data center offer an immense amount of value from an operational standpoint and deliver outstanding ROI.

How can data center and IT managers overcome those challenges?

It’s vital that IT managers look beyond industry benchmarks to understand the performance of a server and qualify how the server will perform in their real world environment. This is the only way to have an appropriate gauge on the kind of price, performance and power considerations to take into account. Look beyond the vendor hype to understand your own environment and how your applications behave. While AMD Opteron processors do deliver significant performance advantages, customers really need to look at their the right blend of processor, memory and I/O in order to determine the best platform to meet their needs.

What advice can you give to IT and data center managers that have a plethora of similar solutions to choose from?

In addition to taking a very hard look at how the server will perform in your real world environment, it’s important to plan not only for your business needs today, but what those needs will be in 3 or 5 years. AMD architects its server processors to allow businesses to scale. Customers can either scale out (buy more servers over time) or scale up (buy a larger more powerful server and grow your utilization within that box). This is a critical factor to keep in mind. In addition it is critical to make sure that the platforms you purchase will easily integrate into your existing environment. AMD Opteron processor-based servers are available from all of the leading OEMs like Dell, HP and IBM, as well as others, helping to ensure that the investments that you have already made in your data center can continue to be leveraged. With the same chassis designs, service spares, management tools and other components, the time that your team has spent learning their existing platforms can be easily leveraged for continued efficiency when adding AMD Opteron processor-based platforms to the data center.

At the processor level, there is a growing interest around the idea of more cores, and what is the appropriate amount of cores for your data center. As a matter of fact, with each new generation with higher core count, customers are making that transition quicker than the previous transition. Today, AMD offers 12-core processors and soon will offer 16-core processors, more than any other x86 processor vendor. While some may think that many cores aren’t necessary for their workloads, as noted above, AMD believes it’s important to plan for the future and account for how computing is changing. Meaning, workloads such as virtualization, cloud computing, database and HPC benefit greatly from having more cores and more memory. If your business is using virtualization today, or considering it, having more cores will drive significant efficiency for you.

Continuous Availability: Application Delivery Controllers

- Peter Melerud, co-founder and VP of product management at KEMP Technologies (www.kemptechnologies.com), says:

Whether an organization has an e-commerce site relying on web applications for revenue, or is a service organization dependent on information delivered through web applications, constant and continuous availability is a major concern. KEMP Technologies’ application delivery controllers and load balancers ensure applications are consistently and reliably accessible, and ensure users are never adversely affected by system, application, or site failures or scheduled maintenance. This article will explain the importance of load balancing for IT and data center managers.

With the volume of data that flows through networks these days, load balancing in enterprise data centers is not only prudent – it’s essential. Servers have to handle larger amounts of data, and with current networks, bottlenecks can occur during high traffic times, slowing down sites and hosted applications. For businesses, these snafus could mean lost customers and reduced productivity. Load balancing is the most effective way to keep uptime high.

The basic problem is simple: If a website or a hosted application crashes customers get frustrated and leave the site. That could mean literally millions of dollars flying out the window. So load balancing should definitely be a high priority.
IT managers need to maintain the right balance between features and capabilities, which means that they need to know their current and future requirements. Data loads are increasing each day, and IT managers have to stay ahead of the curve. Downtime can kill a company, and always seems to come at the worst possible time, so knowing traffic management needs can help prevent future headaches when the traffic spikes.
Load balancers can sense when data traffic spikes, and re-direct that traffic to less busy servers, while optimizing the performance of hosted applications. These solutions can help overcome the challenges IT managers face both today and in the future.

With all the solutions out there, it comes down to cost-effectiveness and value. Load balancing used to be solely the domain of massive enterprises with enormous IT budgets. But now we have to do more with less. Managers should understand exactly what features they need when getting a load balancer, such as whether it should be hardware-based or virtual. Some come with features users don’t need. In a tight economy, they need to make sure they’re not overpaying for their solution.

Both virtual and hardware load balancers provide solutions any size business needs. Data traffic will only increase, thanks to mobile devices and cloud computing. Demands on IT staff will also increase. So the better our networks can handle that data, the more profit and productivity we will see. And in this economy, that’s not a bad thing.