Flash Memory Arrays: Enabling the Virtualized Data Center

Virtualization continues to spread throughout the data center at an unrelenting pace. Server virtualization coupled with multi-core processors means as many as 20 virtual servers can be hosted on one physical platform. Storage virtualization reduces the number of storage systems and the ultimate capacity required. And in the network, virtualization promises to bring about a convergence with storage protocols which will eliminate much of the cabling and drastically reduce the number of switches and adapters required.

One element continues to act as the bottleneck – spinning hard disk drives (HDDs). While the latest multi-core CPU’s process billions of operations a second, and local memory can deal with tens of millions of operations a second, hard drives move at a far more leisurely pace. The fastest disks around have access times averaging about 5 milliseconds, which equates to 200 operations per second.

To read the rest, submit a request for this white paper

Accelerating Software Development with Centralized Caching

Scalable caching appliances speed build times for existing development tools

Fast and efficient software development allows high technology companies to thrive. And the time it takes to compile and test new software versions can determine the difference between successful product launches or perpetual delays.

Our demanding industry environment mandates shorter development cycles, more frequent product updates, and adhering to stringent deadlines. For software-centric companies, a high performance build management system is more important than ever.

To read the rest, submit a request for this document

Solving Rendering Bottlenecks in Computer Animation

A technical overview of centralized storage caching success in computer animation

Computer generated animation requires enormous amounts of processing and storage horsepower to create dazzling movies. But the production process is always under pressure. Typical movie schedules adhere to fixed release dates coinciding with multi- million dollar marketing launches. In the race to the finish, time saving production techniques provide a chance to improve scene quality, enhance special effects, or spend extra time creating a more engaging storyline. This can lead to bigger box office sales.

While there are numerous steps in creating a digitally animated movie, rendering is a critical element which is both compute and I/O intensive. This paper examines in detail how a centralized storage caching solution accelerates the rendering process to improve time-to-market cycles, streamline storage infrastructure costs, and maximize the productivity of animation teams operating under extreme deadline pressures.

Rendering Overview

 

Movies are made up of scenes, shots, and frames, with rendering taking place at the frame level. Each frame must be generated from a set of models that reside within a single storage repository or model farm. The rendering process is extremely compute intensive because each frame contains multiple models, each of which requires millions of calculations to be properly presented. Similarly, the process is also I/O intensive, as during a frame render, the CPU must have instant access to every model within that frame.

To read the rest, submit a request for this document

Server Virtualization: Avoiding the I/O Trap

How centralized storage caching helps balance increasing I/O loads of virtualized servers.

Many companies see dramatic improvements with server virtualization by streamlining application deployments, and increasing overall server utilization. But the rush to capitalize on these rewards can leave some installations with looming performance impacts. This occurs when consolidation driven by server virtualization does not include plans for a corresponding storage I/O performance adjustment. This paper examines how server virtualization impacts overall IT performance and how centralized storage caching protects the performance levels of the entire infrastructure, including storage.

“...I think that over the past few years so much emphasis had been put on server consolidation that much of the [virtualization] community has ignored the disk I/O discussion. I don’t think this was intentional but the value prop was so impressive around consolidation and test/dev that the I/O discussion was not a primary concern, the target audience has often also been server engineering teams and not storage engineering.”

Richard Bocchinfuso, Chief Technology Officer, MTI Technology

To read the rest, submit a request for this document

Data Center Megatrends: Consolidate, Conserve, and Virtualize

Preparing data centers for 2007 and beyond.

Data center design principles are changing. Driven by the need to scale to unprecedented levels of size and performance, the Megatrends of consolidation, conservation, and virtualization are being led by the Internet giants and adopted by enterprises. Today’s densest server and storage deployments showcase new principles and technologies to:

• Drive data center consolidation and improve utilization
• Use the most cost effective industry standard hardware
• Reduce power consumption
• Increase operating efficiency
• Ensure high reliability and predictable quality of service
• Attain administrator capability metrics eclipsing previous ratios

The Megatrends capture these design goals, and each trend has a direct impact on the shape of the data center, both large and small. In particular, we review how these Megatrends require a closer look at the server-storage performance gap and how to restore data center equilibrium with centralized storage caching.

Consolidate: Trends and Implications

Consolidation focuses on cost-savings across several areas:

• Minimize the total amount of operating equipment
• Reducing space and facility requirements
• Increasing management productivity
• Improving asset utilization

The massive Federal data center consolidation effort is a good example of this trend. A recent article provides a concise description of what lies ahead for the company and many other mainstream enterprises.

To read the rest, submit a request for this document

Data Center Performance Insurance

How centralized storage caching guarantees rapid response times during peak workloads.

Saving Millions By Making It Easier And Faster

Every year slow data centers and application failures cost companies hundreds of millions of dollars. Centralized storage caching applies the well-known concept of caching using high-speed DRAM & flash memory, but adds a new and innovative architecture which offers data center performance insurance.

Data Center Challenge: Surviving Peak Workloads

Typically, a data center’s inability to process peak workloads stems from the I/O bottleneck inherent to traditional storage architectures. Facing pain from slow and sequential data access using mechanical hard disk drives, attempts to solve the problem range from over-provisioning parallel disks to placing cache memory directly in compute servers or storage devices. All of the proposed solutions have been expensive and unable to close the widening server-storage performance gap.

Shortfall Of Existing Solutions

• Parallelizing disk I/O does not accelerate response time. It still takes milliseconds to access data on a mechanical disk drive no matter how many of them are available.
• Traditional cache capacity is very limited in servers or storage systems. Storage experts recommend sizing a disk cache at ten percent of the disk’s capacity. Following this rule-of-thumb a terabyte disk would need 100GB of cache which is unheard of.
• Server and storage devices contain “closed” caches in that the cache resource is not usable by any other devices.

To read the rest, submit a request for this document

Provisioning for Predictable Performance

A closer look at server, network, and storage provisioning in enterprise computing.

Businesses thrive on the ability to achieve consistent and predictable results. From the movement of manufactured goods to the flow of company information and data, success depends on management’s ability to optimize the entire food chain with a steady and reliable outcome. Predictable results drive the most important measures of corporate performance - customer satisfaction and the bottom line.

Information technology helps managers understand and evaluate numerous business statistics, often in a timeframe that depends on real time information and real time analysis. Patience is rarely granted to companies operating in today’s global economy. To reach decisions and act quickly, the underlying IT infrastructure must deliver predictable performance.

Architects and operators of enterprise data centers have seen a recent increase in the tools available to provision and tune performance for business applications, particularly at the server and network layers. However, the storage layer has not reached the same adaptability leading to an imbalance crying out for attention. This paper explores current provisioning and outlines requirements to reach predictable performance in enterprise computing.

To read the rest, submit a request for this document

The Server-Storage Performance Gap

How disk drive throughput and access time affect performance In enterprise storage configurations and data centers, hard disk drives serve as the foundation of information operations.

While we are bound to have disk drives for a long time, current disk-based storage cannot keep up with the increasing processing capabilities of powerful servers and appetite of data-intensive applications. The existing disk storage infrastructure needs assistance, and it is time to properly apply advanced technology to solve this performance gap.

Historically, different computer system components have advanced performance at different relative rates. Although disk capacity has improved somewhat, disk performance ranks at the bottom with no significant improvement compared to million-fold boosts by other system components. For example, CPU performance has progressed at an impressive clip, driven by Moore’s law, multi-core processors, and threading technology to increase 2,000,000 times since 1987. In comparison, disk performance only improved by 11 times. This has created a significant and growing Server-Storage Performance Gap shown in Figure 1. Note the multiple orders of magnitude difference between CPU and disk increases made visible by a logarithmic scale.

To download this document, Click Here

Disk Storage Shortfall

Understanding the root cause of the I/O bottleneck

Many data centers have performance bottlenecks that impact application performance and service delivery to users. These bottlenecks exist across data center locations including servers (application, web, file, email and database), networks, application software, and storage systems as shown in Figure 1. Resolving performance problems is challenging and requires the analysis and understanding of complex interdependent system environments.

Server bottlenecks due to lack of CPU processing power, memory or under sized I/O interfaces can result in poor performance or in worse case scenarios application instability.

To download this document, Click Here