Benefiting from Cloud Computing Technology Trends

By Gary Orenstein

August 28, 2008

The emergence of cloud computing as a way to build and deliver always-on, pay-by-the-drink IT services has emerged as one of the hottest topics this year. Major players — including Amazon, EMC, Google and IBM — have promoted offerings that proclaim near infinite-scale computing, storage, database and related Web services that can be easily leveraged by talented developers with a browser.

This paper will specifically focus on how Web-scale and commercial enterprises can benefit from current cloud computing technology trends to build a new class of datacenters that are more autonomous and dynamic than traditional implementations. It also will examine how new cloud computing models enable the rapid scaling and reallocation of resources to a wide variety of customers, delivering core cost and agility benefits to purveyors of cloud computing services. And, specifically, we will explore how the change in application workloads is driving a need for accelerated file services to maintain optimized performance.

First, we’ll look at the most frequently mentioned companies and implementations around cloud computing, the latter of which generally fall into three cloud categories: applications, platforms and infrastructure.

In the applications category, Salesforce.com shines as the premier example of delivering a use-specific service over the Internet. On the platform side, Google’s App Engine represents developer-level access to a range of compute, database and storage functions within a specified framework. In the case of Google, that framework relies primarily on the Python programming language, but other options at different service providers also exist. On the infrastructure side, Amazon offers a complete set of offerings from raw CPU horsepower (EC2) to chunks of data storage (S3) through its Web services unit.

Of course, the lines between these companies and categories can easily blur. Salesforce.com offers its version of a platform through its Force.com initiative. And Amazon offers more than just CPUs and storage with services like SimpleDB, essentially providing database functionality as a platform. But the basic categories work to define the functionality, even across companies.

Figure 1: Cloud Computing Segments

Common Characteristics of Cloud Purveyors

All of the major players offering cloud services (including applications, platforms, and infrastructure) share common architectural approaches that benefit any Web-scale or enterprise datacenter. These include the ability to:

  • Scale — Rapidly increase workloads and concurrent users while sustaining solid, non-stop service.
  • Mix multiple workloads — Adapt to varying types of workloads across multiple instances of a single application or multiple applications.
  • Drive low costs and small footprints — Keep costs down through common hardware platforms and increased rack density to minimize power, space, and cooling charges.
  • Deliver service reliably — Sustain service non-stop so that businesses relying on cloud offerings can provide uninterrupted operations.
  • Stay data-ready — Be equipped to handle enormous spikes and volumes of storage, along with the ability to rapidly search, locate and retrieve this data.
  • Flexibly deploy resources — Assign and re-assign hardware and software resources through the use of virtualization technologies or a build-block approach that enables simple re-use.

Adopting Cloud Computing Architectural Approaches

There are several approaches to building cloud computing datacenters. One approach is to architect everything from the ground up, including the file systems, clustering technology and application software, as in the case of Amazon or Google. These companies have made scaling their compute infrastructures a top business priority and invested heavily in technology research and development.

Other approaches make use of more commercially available offerings. For example, virtualization solutions are a key enabler of rapidly assigning resources, such as server instances, within a compute pool for flexibility and cost savings, and are available in commercial and open-source implementations. Hardware and software products providing similar functionality at the networking or storage layers complete end-to-end datacenter flexibility.

Both the ground-up and commercial-offering approaches aim for self-healing architectures, support for well-defined service level agreements and the ability to handle a large number of concurrent users. There also are energy efficiency goals achieved by pooling compute resources into a fewer number of large datacenters, leveraging industry-standard hardware, software and networking infrastructure, and being able to handle the proliferation of rapidly growing volumes of data.

File Acceleration for Cloud Computing Datacenters

Of particular interest to datacenter architects is how to optimize storage infrastructure to handle the cloud computing requirements outlined above. This essentially represents the ability for a larger number of users to access a larger pool of storage while sustaining top service levels.

Change in workloads

Before examining the architectural detail, we need to take a quick look at changing workloads. Part of the impetus for cloud computing is based on these dramatic shifts, as shown in Figure 2. In the initial stages, users were connected to unique data on their computer. As the Web evolved, we migrated to shared, consolidated content. Now we are in a stage of contributed dynamic content that often push current infrastructures beyond what they were initially able to handle.

Figure 2: Changing Workloads Leads to More Interactivity

Challenges of Today’s Architectures

Because of the workload changes facing Web-scale and enterprise businesses, new challenges are emerging within current computing architectures. One of the most pressing challenges is file access bottlenecks. Simply put, when dozens to hundreds of servers are trying to access the same data, it can lead to storage or I/O bottlenecks because the underlying disk-based storage systems cannot keep up with the massive amount of compute power at the server layer, as shown in Figure 3. This often leads to excessive storage over-provisioning and result in high costs.

But the main impact of this file access bottleneck is the poor end-user experience for Web-scale application users or the poor productivity for enterprise application clients. In both cases, the delays caused by insufficient application performance take a direct hit on the business.

Figure 3: Challenges of Current Architectures

New Options to Deliver Accelerated File Services with Centralized Caching

Many enterprise and Web-scale datacenters are solving their file access bottlenecks with centralized caching, particularly with network-centric, memory-based approaches.

By placing a pool of shared high-speed memory in the network to act as a central caching namespace, datacenter managers can instantly increase the performance of I/O-constrained applications. For example, an application that operates across multiple servers requiring access to a consolidated file repository can now retrieve files 10-50x faster than if the servers were on a conventional disk-based storage system. The caching appliance keeps the frequently requested files — or portions of files — in memory to deliver such improvements. And since the caching appliance automatically keeps the content up-to-date based on usage patterns, no ongoing active management is required.

Centralized caching appliances integrate easily with the core concepts of cloud computing architectures, as shown in Figure 4.

Figure 4: Centralized Caching Fits Cloud Computing Architectures

Scale

By serving data from memory, compared to mechanical disks, scalable caching appliances can support thousands of simultaneous connections to Web and application servers. This accommodates increased loads without having to over- provision disks.

Handle mixed workloads

Because memory-based caching appliances deliver low-latency response times, they can easily support mixed workloads in a single appliance. One caching appliance can support different Web, application and database servers, as well as multiple file systems, including clustered file systems.

Lower total cost and smaller footprints

Compared to trying to architect for high I/O operations per second from disks, a memory-based caching appliance dramatically reduces the overall cost and space required to fulfill such performance requirements. When deployed as a network resource, a memory-based caching appliance ensures high utilization and efficiency.

Reliable service delivery

Caching appliances help offload storage systems from I/O intensive workloads essentially streamlining the I/O traffic to guarantee reliable service delivery. Where in the past, excessive I/O loads can take their toll on disk-based systems and bring them to a crawl, complementing such systems with memory-based caching appliances provides the horsepower to guarantee continued service.

Data-readiness (large volumes, high-file-count repositories)

Caching appliances enable data-readiness for both large volumes of data as well as high-file-count repositories. For high-capacity installations, caching appliances perfectly complement high-capacity, low-cost disk storage such as SATA by delivering performance from that storage dynamically. For high-file-count installations, caching appliances cache index information that speeds up the search, location, and delivery of files.

Flexible deployment

Deploying new applications can be a burdensome process when storage has to be configured for performance. With a caching appliance, virtually any level of storage performance can be instantly delivered to provide enough I/O for the application. This frees architects from having to over-provision storage for IOPS.

Conclusions

Cloud computing datacenters represent a new wave of scalable computing architectures that deliver more data to more users more economically than ever before. Paying attention to the technology trends behind the “datacenter” aspects of cloud computing allow corporations to employ the same techniques to build high-scale, low-cost infrastructure. As application traffic patterns, particularly storage and I/O patterns change, the benefits to replicating these cloud approaches will become increasingly important.

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industy updates delivered to you every week!

Hyperion: AI-driven HPC Industry Continues to Push Growth Projections

November 21, 2019

Three major forces – AI, cloud and exascale – are combining to raise the HPC industry to heights exceeding expectations. According to market study results released this week by Hyperion Research at SC19 in Denver, Read more…

By Doug Black

At SC19: Bespoke Supercomputing for Climate and Weather

November 20, 2019

Weather and climate applications are some of the most important uses of HPC – a good model can save lives, as well as billions of dollars. But many weather and climate models struggle to run efficiently in their HPC en Read more…

By Oliver Peckham

Microsoft, Nvidia Launch Cloud HPC Service

November 20, 2019

Nvidia and Microsoft have joined forces to offer a cloud HPC capability based on the GPU vendor’s V100 Tensor Core chips linked via an InfiniBand network scaling up to 800 graphics processors. The partners announced Read more…

By George Leopold

Hazra Retiring from Intel Data Center Group, Successor Not Known

November 20, 2019

Rajeeb Hazra, corporate VP of Intel’s Data Center Group and GM for the Enterprise and Government Group, is retiring after more than 24 years at the company. At this writing, his successor is unknown. An earlier story on... Read more…

By Doug Black

Jensen Huang’s SC19 – Fast Cars, a Strong Arm, and Aiming for the Cloud(s)

November 20, 2019

We’ve come to expect Nvidia CEO Jensen Huang’s annual SC keynote to contain stunning graphics and lively bravado (with plenty of examples) in support of GPU-accelerated computing. In recent years, AI has joined the s Read more…

By John Russell

AWS Solution Channel

Making High Performance Computing Affordable and Accessible for Small and Medium Businesses with HPC on AWS

High performance computing (HPC) brings a powerful set of tools to a broad range of industries, helping to drive innovation and boost revenue in finance, genomics, oil and gas extraction, and other fields. Read more…

IBM Accelerated Insights

Data Management – The Key to a Successful AI Project

 

Five characteristics of an awesome AI data infrastructure

[Attend the IBM LSF & HPC User Group Meeting at SC19 in Denver on November 19!]

AI is powered by data

While neural networks seem to get all the glory, data is the unsung hero of AI projects – data lies at the heart of everything from model training to tuning to selection to validation. Read more…

SC19 Student Cluster Competition: Know Your Teams

November 19, 2019

I’m typing this live from Denver, the location of the 2019 Student Cluster Competition… and, oh yeah, the annual SC conference too. The attendance this year should be north of 13,000 people, with the majority attende Read more…

By Dan Olds

Hyperion: AI-driven HPC Industry Continues to Push Growth Projections

November 21, 2019

Three major forces – AI, cloud and exascale – are combining to raise the HPC industry to heights exceeding expectations. According to market study results r Read more…

By Doug Black

At SC19: Bespoke Supercomputing for Climate and Weather

November 20, 2019

Weather and climate applications are some of the most important uses of HPC – a good model can save lives, as well as billions of dollars. But many weather an Read more…

By Oliver Peckham

Hazra Retiring from Intel Data Center Group, Successor Not Known

November 20, 2019

Rajeeb Hazra, corporate VP of Intel’s Data Center Group and GM for the Enterprise and Government Group, is retiring after more than 24 years at the company. At this writing, his successor is unknown. An earlier story on... Read more…

By Doug Black

Jensen Huang’s SC19 – Fast Cars, a Strong Arm, and Aiming for the Cloud(s)

November 20, 2019

We’ve come to expect Nvidia CEO Jensen Huang’s annual SC keynote to contain stunning graphics and lively bravado (with plenty of examples) in support of GPU Read more…

By John Russell

Top500: US Maintains Performance Lead; Arm Tops Green500

November 18, 2019

The 54th Top500, revealed today at SC19, is a familiar list: the U.S. Summit (ORNL) and Sierra (LLNL) machines, offering 148.6 and 94.6 petaflops respectively, Read more…

By Tiffany Trader

ScaleMatrix and Nvidia Launch ‘Deploy Anywhere’ DGX HPC and AI in a Controlled Enclosure

November 18, 2019

HPC and AI in a phone booth: ScaleMatrix and Nvidia announced today at the SC19 conference in Denver a joint offering that puts up to 13 petaflops of Nvidia DGX Read more…

By Doug Black

Intel Debuts New GPU – Ponte Vecchio – and Outlines Aspirations for oneAPI

November 17, 2019

Intel today revealed a few more details about its forthcoming Xe line of GPUs – the top SKU is named Ponte Vecchio and will be used in Aurora, the first plann Read more…

By John Russell

SC19: Welcome to Denver

November 17, 2019

A significant swath of the HPC community has come to Denver for SC19, which began today (Sunday) with a rich technical program. As is customary, the ribbon cutt Read more…

By Tiffany Trader

Supercomputer-Powered AI Tackles a Key Fusion Energy Challenge

August 7, 2019

Fusion energy is the Holy Grail of the energy world: low-radioactivity, low-waste, zero-carbon, high-output nuclear power that can run on hydrogen or lithium. T Read more…

By Oliver Peckham

Using AI to Solve One of the Most Prevailing Problems in CFD

October 17, 2019

How can artificial intelligence (AI) and high-performance computing (HPC) solve mesh generation, one of the most commonly referenced problems in computational engineering? A new study has set out to answer this question and create an industry-first AI-mesh application... Read more…

By James Sharpe

Cray Wins NNSA-Livermore ‘El Capitan’ Exascale Contract

August 13, 2019

Cray has won the bid to build the first exascale supercomputer for the National Nuclear Security Administration (NNSA) and Lawrence Livermore National Laborator Read more…

By Tiffany Trader

DARPA Looks to Propel Parallelism

September 4, 2019

As Moore’s law runs out of steam, new programming approaches are being pursued with the goal of greater hardware performance with less coding. The Defense Advanced Projects Research Agency is launching a new programming effort aimed at leveraging the benefits of massive distributed parallelism with less sweat. Read more…

By George Leopold

AMD Launches Epyc Rome, First 7nm CPU

August 8, 2019

From a gala event at the Palace of Fine Arts in San Francisco yesterday (Aug. 7), AMD launched its second-generation Epyc Rome x86 chips, based on its 7nm proce Read more…

By Tiffany Trader

D-Wave’s Path to 5000 Qubits; Google’s Quantum Supremacy Claim

September 24, 2019

On the heels of IBM’s quantum news last week come two more quantum items. D-Wave Systems today announced the name of its forthcoming 5000-qubit system, Advantage (yes the name choice isn’t serendipity), at its user conference being held this week in Newport, RI. Read more…

By John Russell

Ayar Labs to Demo Photonics Chiplet in FPGA Package at Hot Chips

August 19, 2019

Silicon startup Ayar Labs continues to gain momentum with its DARPA-backed optical chiplet technology that puts advanced electronics and optics on the same chip Read more…

By Tiffany Trader

Crystal Ball Gazing: IBM’s Vision for the Future of Computing

October 14, 2019

Dario Gil, IBM’s relatively new director of research, painted a intriguing portrait of the future of computing along with a rough idea of how IBM thinks we’ Read more…

By John Russell

Leading Solution Providers

ISC 2019 Virtual Booth Video Tour

CRAY
CRAY
DDN
DDN
DELL EMC
DELL EMC
GOOGLE
GOOGLE
ONE STOP SYSTEMS
ONE STOP SYSTEMS
PANASAS
PANASAS
VERNE GLOBAL
VERNE GLOBAL

Cray, Fujitsu Both Bringing Fujitsu A64FX-based Supercomputers to Market in 2020

November 12, 2019

The number of top-tier HPC systems makers has shrunk due to a steady march of M&A activity, but there is increased diversity and choice of processing compon Read more…

By Tiffany Trader

Intel Confirms Retreat on Omni-Path

August 1, 2019

Intel Corp.’s plans to make a big splash in the network fabric market for linking HPC and other workloads has apparently belly-flopped. The chipmaker confirmed to us the outlines of an earlier report by the website CRN that it has jettisoned plans for a second-generation version of its Omni-Path interconnect... Read more…

By Staff report

Kubernetes, Containers and HPC

September 19, 2019

Software containers and Kubernetes are important tools for building, deploying, running and managing modern enterprise applications at scale and delivering enterprise software faster and more reliably to the end user — while using resources more efficiently and reducing costs. Read more…

By Daniel Gruber, Burak Yenier and Wolfgang Gentzsch, UberCloud

Dell Ramps Up HPC Testing of AMD Rome Processors

October 21, 2019

Dell Technologies is wading deeper into the AMD-based systems market with a growing evaluation program for the latest Epyc (Rome) microprocessors from AMD. In a Read more…

By John Russell

Rise of NIH’s Biowulf Mirrors the Rise of Computational Biology

July 29, 2019

The story of NIH’s supercomputer Biowulf is fascinating, important, and in many ways representative of the transformation of life sciences and biomedical res Read more…

By John Russell

Xilinx vs. Intel: FPGA Market Leaders Launch Server Accelerator Cards

August 6, 2019

The two FPGA market leaders, Intel and Xilinx, both announced new accelerator cards this week designed to handle specialized, compute-intensive workloads and un Read more…

By Doug Black

Intel Debuts New GPU – Ponte Vecchio – and Outlines Aspirations for oneAPI

November 17, 2019

Intel today revealed a few more details about its forthcoming Xe line of GPUs – the top SKU is named Ponte Vecchio and will be used in Aurora, the first plann Read more…

By John Russell

When Dense Matrix Representations Beat Sparse

September 9, 2019

In our world filled with unintended consequences, it turns out that saving memory space to help deal with GPU limitations, knowing it introduces performance pen Read more…

By James Reinders

  • arrow
  • Click Here for More Headlines
  • arrow
Do NOT follow this link or you will be banned from the site!
Share This