One of the world's leading technical institutes, the Tokyo Institute of Technology (Tokyo Tech) created the fastest supercomputer in Asia, and one of the largest outside of the United States. Using Sun x64 servers and data servers deployed in a grid architecture, Tokyo Tech built a cost-effective, flexible supercomputer that meets the demands of compute- and data-intensive applications. Built in just 35 days, the TSUBAME grid includes hundreds of systems incorporating thousands of processor cores and terabytes of memory, and delivers 47.38 trillion1 floating-point operations per second (TeraFLOPS) of sustained LINPACK benchmark performance and 1.1 petabyte of storage to users running common off-the-shelf applications. Based on the deployment architecture, the grid is expected to reach 100 TeraFLOPS in the future. This Sun BluePrints article provides an overview of the Tokyo Tech grid, named TSUBAME. The third in a series of Sun BluePrints articles on the TSUBAME grid, this document provides an overview of the overall system architecture of the grid, as well as a detailed look at the configuration of the Sun N1 Grid Engine software that makes the grid accessible to users.
Implementing the Lustre File System with Sun Storage: High Performance Storage for High Performance Computing
Much of the focus of high performance computing (HPC) has centered on CPU performance. However, as computing requirements grow, HPC clusters are demanding higher rates of aggregate data throughput. Today's clusters feature larger numbers of nodes with increased compute speeds. The higher clock rates and operations per clock cycle create increased demand for local data on each node. In addition, InfiniBand and other high-speed, low-latency interconnects increase the data throughput available to each node. Traditional shared file systems such as NFS have not been able to scale to meet this growing demand for data throughput on HPC clusters. Scalable cluster file systems that can provide parallel data access to hundreds of nodes and petabytes of storage are needed to provide the high data throughput required by large HPC applications, including manufacturing, electronic design, and research. This paper describes an implementation of the Sun Lustre file system as a scalable storage cluster using Sun Fire servers, high-speed/low-latency InfiniBand interconnects, and additional networking and storage devices. Furthermore, this paper explores the use of the Sun Lustre file system at a shared government and education research site, including configuration information and details on testing that was performed on-site to evaluate the performance of Sun's scalable storage solution.
When designing data storage solutions for High Performance Computing (HPC) environments, IT architects strive to balance complex and often conflicting requirements. The need to manage a skyrocketing amount of data, along with the goals of controlling cost and immediate data availability, can make it difficult to meet HPC application demands within the constraints of today's IT budgets. To help customers address an almost bewildering set of architectural challenges, Sun has developed the Sun Storage and Archive Solution for HPC, a reference architecture that can be easily customized to meet specific application goals and business requirements. This article is intended for IT managers and storage architects familiar with HPC applications and data requirements in the organization. It assumes that the audience has a technical background and some familiarity with issues surrounding the task of configuring systems and storage.
From Greg Linden on a talk Google Fellow Jeff Dean gave last week at University of Washington Computer Science titled "Research Challenges Inspired by Large-Scale Computing at Google" : Coming away from the talk, the biggest points for me were the considerable interest in reducing costs (especially reducing power costs), the suggestion that the Google cluster may eventually contain 10M machines at 1k locations, and the call to action for researchers on distributed systems and databases to think orders of magnitude bigger than they often are, not about running on hundreds of machines in one location, but hundreds of thousands of machines across many locations.
Microsoft SQL Server 2008 incorporates the tools and technologies that are necessary to implement relational databases, reporting systems, and data warehouses of enterprise scale, and provides optimal performance and responsiveness.
With SQL Server 2008, you can take advantage of the latest hardware technologies while scaling up your servers to support server consolidation. SQL Server 2008 also enables you to scale out your largest data solutions.
This white paper describes the performance and scalability capabilities of Microsoft® SQL Server® 2008 and explains how you can use these capabilities to:
* Optimize performance for any size of database with the tools and features that are available for the database engine, analysis services, reporting services, and integration services.
* Scale up your servers to take full advantage of new hardware capabilities.
* Scale out your database environment to optimize responsiveness and to move your data closer to your users.
Read the entire article about SQL Server 2008 Database Performance and Scalability at MyTestBox.com - web software reviews, news, tips & tricks.
Some intrepid company blogs are posting their technical challenges and how they solve them. I wish more would open up and talk about what they are doing as it helps everyone move forward. Here are a few blogs documenting their encounters with the bleeding edge:
Update 3: The book was released! Find it on Amazon at The Art of Capacity Planning. Update 2: Maybe the iPhone can use a little capacity planning? What's Behind the iPhone 3G Glitches: One source says Apple programmed the Infineon chip to demand a more powerful 3G signal than the iPhone really requires. So if too many people try to make a call or go on the Internet in a given area, some of the devices will decide there's insufficient power and switch to the slower network—even if there is enough 3G bandwidth available. Update: To get a taste of what will be served, mySQL DBA has a nice post titled Capacity Planning, Architecture, Scaling, Response time, Throughput. You learn how to figure out when your application will break by building a 3rd order polynomial. Cool stuff! John Allspaw who is the Operations Engineering Manager at Flickr is about to publish a book with O'Reilly. There are not much details so far but it seems interesting and relevant to High Scalability. Allspaw combines personal anecdotes from many phases of Flickr's growth with insights from his colleagues in many other industries to give you solid guidelines for measuring your growth, predicting trends, and making cost-effective preparations. Topics include:
- Evaluating tools for measurement and deployment
- Capacity analysis and prediction for storage, database, and application servers
- Designing architectures to easily add and measure capacity
- Handling sudden spikes
- Predicting exponential and explosive growth
- How cloud services such as EC2 can fit into a capacity strategy
This strategy is stated perfectly by Flickr's Myles Grant: The Flickr engineering team is obsessed with making pages load as quickly as possible. To that end, we’re refactoring large amounts of our code to do only the essential work up front, and rely on our queuing system to do the rest. Flickr uses a queuing system to process 11 million tasks a day. Leslie Michael Orchard also does a great job explaining the queuing meme in his excellent post Queue everything and delight everyone. Asynchronous work queues are how you scalably solve problems that are too big to handle in real-time. The process:
Queues Give You Lots of New Knobs to Play WithAs features are added data consumers multiply, so throwing a new task into a sequential process has a good chance of blowing latencies. Queueing gives much more control and flexibility over the performance of a system. With queues some advanced strategies you have at your disposal are:
What Can You do with Your Queue?The options are endless, but here are some uses I found out in the wild:
Queuing Implies an Event Driven State Machine Based Client ArchitectureMoving to queuing has architecture implications. The client and server are nolonger connected in a direct request-response sort of way. Instead, the server continually sends events to clients. The client is event driven instead of request-response driven. Internally clients often simulates the reqest-response model even though Ajax is asynchronous. It might be better to drop the request-response illusion and just make the client an event driven state machine. An event can come from a request, or from asynchronous jobs, or events can be generated by others performing activities that a client should see. Each client has an event channel that the system puts events on for a client to consume. The client is responspible for making sense of the event in its current context and is capable of handling any event regardless of its original source.
Queuing SystemsIf you are in the market for a queuing system take a look at:
One of the cool things about Mr. Scoble is he doesn't pretend to know everything, which can be an deadly boring affliction in this field. In this case Robert is asking for help in an upcoming interview. Maybe we can help? Here's Robert's plight: I’m really freaked out. I have one of the biggest interviews of my life coming up and I’m way under qualified to host it. It’s on Thursday and it’s about Scalability and Performance of Web Services. Look at who will be on. Matt Mullenweg, founder of Automattic, the company behind WordPress (and behind this blog). Paul Bucheit, one of the founders of FriendFeed and the creator of Gmail (he’s also the guy who gave Google the “don’t be evil” admonishion). Nat Brown, CTO of iLike, which got six million users on Facebook in about 10 days. What would you ask?
Although the problem of scaling human genome sequencing is not exactly about building bigger, faster and more reliable websites it is most interesting in terms of scalability. The paper describes a new technology by the startup company Complete Genomics to sequence the full human genome for the fraction of the cost of earlier possibilities. Complete Genomics is building the world’s largest commercial human genome sequencing center to provide turnkey, outsourced complete human genome sequencing to customers worldwide. By 2010, their data center will contain approximately 60,000 processors with 30 petabytes of storage running their sequencing software on Linux clusters. Do you find this interesting and relevant to HighScalability.com?