Virtualization + Database = Scalability, Availability

By By Derrick Harris, Editor

January 21, 2008

For years, the talk surrounding databases has been about “high availability” and “maximum uptime” — two terms that connote the inevitability of failure or, at the very least, downtime. Now, however, one lower-case start-up, xkoto, is looking to add a new phrase to the mix: “continuous availability.”

Achieving ‘Continuous Availability’

Marketed as a database load balancer, xkoto’s flagship Gridscale product is a middleware appliance that sits between the application and the database and allows for multiple active copies of the database to run simultaneously, as opposed to traditional high availability or disaster recovery solutions that normally run in an active-passive model. Active copies are updated, and latency is minimized, by Gridscale’s method of passing SQL statements between the databases and the application instead of taking the classic replication approaches of scanning for changes to the disk or to the database buffer. Thanks to virtualization, the software touches neither the database nor the application.

The goals in designing Gridscale, says xkoto president and CEO David Patrick, were to solve for two problems: (1) eliminating recovery time associated with failover situations and (2) providing scale to applications by allowing for the addition of commodity hardware. “The concept of failover doesn’t even exist anymore,” says Patrick. “It’s now the concept of continuous availability because you have multiple active copies of the database.”

In terms of scalability, Patrick says adding nodes is easy, and additional boxes can be provisioned or de-provisioned as needed — “basically immediately.” IBM experienced performance gains of 85 percent per additional server when it tested Gridscale, and the xkoto Web site suggests that “upwards of 30 nodes can be clustered while still delivering horizontal scalability.” Additionally, Patrick noted, “you can basically have an active database anywhere in the world,” as the only geographical limitations have to do with the physics of transmitting information over long distances, not with the Gridscale software. According to Patrick, several customers already have Gridscale databases located around the country.

The solution was designed to work with, and currently only officially supports, IBM’s DB2 database, but Patrick says the Gridscale architecture inherently supports other platforms. He added that xkoto is working on a SQL Server edition of Gridscale that should be available later this year.

This notion that Gridscale should be able to support multiple database platforms is particularly captivating to industry analyst and virtualization aficionado Dan Kusnetzky, of the eponymous Kusnetzky Group, who believes that xkoto’s attempt to get into the communication stream at a different level than any previous vendors has the potential to produce great benefits. “You could create these database clusters,” he said, based on his analysis of the product, “… where either side of the communications architecture was running on entirely different physical systems, or virtual systems, that didn’t look anything like the other side, and possibly even running an entirely different database engine.”

Who’s On Board?

Although start-ups generally experience some difficulty in getting customers on board with their new, and often innovative, products, xkoto has been relatively successful thus far, having notched 15-20 high-profile customers in the 12 months since it really began selling Gridscale. Patrick attributes a good portion of this success to his company’s close affiliation with IBM, who has made xkoto part of the sales effort for potential DB2 customers needing the levels of availability and scale Gridscale brings to the table. “IBM has been very, very helpful,” said Patrick, adding that he hopes to develop similar relationships with other database vendors as necessary.

Thus far, xkoto’s customers are comprised of the usual suspects in high-availability, high-scalability solutions: financial services (Genworth Financial); health care (United Health); online retail (Children’s Place); and online travel (Travelport, parent company of Orbitz). The main draw for the early-stage customers, said Patrick, has been the prospect of continuous availability, mostly because cost-analysis of continuous availability is fairly easy and, for certain customers, 100 percent uptime is critical in a world where “people book travel at three in the morning on Sunday night.” However, he added, “As we build a bigger customer base, we can refine the scalability part of the story.”

Gridscale is a horizontal solution, said Patrick, and while xkoto is currently targeting certain markets to build its customer base, it definitely plans to spread out in time.

Patrick believes the upcoming support for SQL Server will go along way toward increasing the company’s customer count and in opening up new markets. While the current focus is on markets with large-scale enterprise applications, he thinks that the SQL Server market will find broader functionality for Gridscale, including the possibility of using it to optimize large, database-driven e-mail environments.

Regardless why customers are buying into xkoto, though, the results have been noticeable within the company. The early sales wins by the skeleton crew in Toronto spurred investments from venture capitalists, resulting in the company moving to Boston in an effort to become a player in the enterprise IT scene, as well as a plan to increase xkoto’s employee count by 150 percent in the next 10 months.

One optimistic Gridscale user is Genworth Financial, which has been working with xkoto for well over a year as it moves an important insurance agent data management application from a few mainframes into a mid-tier Linux environment. Genworth has been running Gridscale in its test environment and is looking to put the application into production some time this quarter.

Predominantly an Oracle Real Application Cluster (RAC) shop, Adam Webb, an IT solutions architect in the retirement and protection division of Genworth, said his group decided to go with Gridscale after it was brought up by an IBM representative when discussing methods to derive maximum availability, scalability and flexibility from the DB2 environment in which this particular application resides. Preferring to stick with commodity boxes (we “tend to not invest in a lot of high-end hardware,” says Webb) and wanting a complete solution to address its needs, his group rejected several alternative solutions, including IBM’s High Availability and Disaster Recovery for DB2, data partitioning, and an in-house-built-and-supported Q based replication scheme.

When the application is ready to go live, Webb expects to have at least three production nodes running active databases with an additional two for disaster recovery. The online DB2 database will contain about 1TB of data, which will be stored separately in each box, for a total of 5TB. Because the project is a composite of three mainframe systems, Webb said sizing estimates have been tricky. “Of course,” he said, speaking about the Gridscale solution, “we have flexibility, which is one of the great things. If our load exceeds what we need, we have the ability to plug extra hardware behind it pretty easily.”

An interesting sidenote of Genworth’s Gridscale implementation has been the amount of time it has taken. Although xkoto prides itself on quick deployments — often in three days or less — Genworth’s Gridscale environment has been under construction for over a year. According to Webb, the reason for this is twofold: (1) the application development cycle has taken that long; and (2) the application is a composite, with both Java and COBOL responsible for accessing the data tier. Although xkoto didn’t have much experience with COBOL applications using Gridscale to access the data layer, Webb said the company was very willing to work with Genworth to make everything function properly.

Perhaps because Genworth deployed Gridscale to solve a technical need rather than to achieve a competitive advantage, Webb said there hasn’t been much discussion about expanding its use into other database environments. But that could change. “If things continue to go as they have gone — which is to say they’ve gone well,” he added, “I think we would certainly be willing to evaluate that as an option.” Aside from the bargained for levels of availability and scalability, Webb has been impressed with Gridscale’s facilitation of 24×7 processing and the fact the software allows his team to take nodes offline as needed to handle batch jobs associated with the application.

Success Could Hinge on a Delicate Balance

Speaking from an analyst’s perspective, Kusnetzky doesn’t think xkoto’s future challenges will revolve around technology — which he says is both “clever” and “innovative,” especially given its heterogeneous potential — but rather how well the company is able to spread its message over the noise made by much richer and much louder vendors. Part of this, he noted, will be in distinguishing Gridscale’s capabilities from seemingly (at least outwardly) similar technologies like storage replication, database replication or distributed data caching, each of which has its own well-established vendors. It’s not impossible to believe they’ll succeed, he said, noting that VMware was once a start-up, but it will take some skillful marketing.

Assuming they do manage to make a name for themselves, though, Kusnetzky foresees acquisition as the most likely outcome for xkoto. “I don’t expect them to be a standalone company two years from now,” he said. “My expectation is somebody like IBM or Hewlett-Packard or EMC will look at that capability and say, ‘I need it in my portfolio.’ “

For xkoto CEO Patrick, though, the trick isn’t so much about the company setting itself apart as it is about the company fitting in with the rest of the virtualization vendors and their various solutions. “We’re really focused down lower in the stack, specifically on taking the database and … scaling it virtually across the enterprise. We see ourselves as complementary to the other solutions in the stack,” he said. “We ultimately want to fit in with as many of these management frameworks and other tools that are out there so we become a component in an overall datacenter virtualization strategy.”

However, even if it does require some “skillful marketing” to get customers’ ears, the folks at xkoto are confident they can close the deal once in position, and the reason for this confidence is in the simplicity of their message. “This isn’t what I would call a difficult-to-grasp virtualization vision that we’re trying to paint with a broad paintbrush,” said Patrick. “We’re going in very specifically and solving for two really big challenges for enterprise customers — … continuous availability and scalability — and we’re using these virtualization tools to get it done.”

Learn more about xkoto and Gridscale at www.xkoto.com

Subscribe to HPCwire's Weekly Update!

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

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing power it brings to artificial intelligence.  Nvidia's DGX Read more…

Call for Participation in Workshop on Potential NSF CISE Quantum Initiative

March 26, 2024

Editor’s Note: Next month there will be a workshop to discuss what a quantum initiative led by NSF’s Computer, Information Science and Engineering (CISE) directorate could entail. The details are posted below in a Ca Read more…

Waseda U. Researchers Reports New Quantum Algorithm for Speeding Optimization

March 25, 2024

Optimization problems cover a wide range of applications and are often cited as good candidates for quantum computing. However, the execution time for constrained combinatorial optimization applications on quantum device Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at the network layer threatens to make bigger and brawnier pro Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HBM3E memory as well as the the ability to train 1 trillion pa Read more…

Nvidia Appoints Andy Grant as EMEA Director of Supercomputing, Higher Education, and AI

March 22, 2024

Nvidia recently appointed Andy Grant as Director, Supercomputing, Higher Education, and AI for Europe, the Middle East, and Africa (EMEA). With over 25 years of high-performance computing (HPC) experience, Grant brings a Read more…

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing po Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HB Read more…

Nvidia Looks to Accelerate GenAI Adoption with NIM

March 19, 2024

Today at the GPU Technology Conference, Nvidia launched a new offering aimed at helping customers quickly deploy their generative AI applications in a secure, s Read more…

The Generative AI Future Is Now, Nvidia’s Huang Says

March 19, 2024

We are in the early days of a transformative shift in how business gets done thanks to the advent of generative AI, according to Nvidia CEO and cofounder Jensen Read more…

Nvidia’s New Blackwell GPU Can Train AI Models with Trillions of Parameters

March 18, 2024

Nvidia's latest and fastest GPU, codenamed Blackwell, is here and will underpin the company's AI plans this year. The chip offers performance improvements from Read more…

Nvidia Showcases Quantum Cloud, Expanding Quantum Portfolio at GTC24

March 18, 2024

Nvidia’s barrage of quantum news at GTC24 this week includes new products, signature collaborations, and a new Nvidia Quantum Cloud for quantum developers. Wh Read more…

Houston We Have a Solution: Addressing the HPC and Tech Talent Gap

March 15, 2024

Generations of Houstonian teachers, counselors, and parents have either worked in the aerospace industry or know people who do - the prospect of entering the fi Read more…

Alibaba Shuts Down its Quantum Computing Effort

November 30, 2023

In case you missed it, China’s e-commerce giant Alibaba has shut down its quantum computing research effort. It’s not entirely clear what drove the change. Read more…

Nvidia H100: Are 550,000 GPUs Enough for This Year?

August 17, 2023

The GPU Squeeze continues to place a premium on Nvidia H100 GPUs. In a recent Financial Times article, Nvidia reports that it expects to ship 550,000 of its lat Read more…

Shutterstock 1285747942

AMD’s Horsepower-packed MI300X GPU Beats Nvidia’s Upcoming H200

December 7, 2023

AMD and Nvidia are locked in an AI performance battle – much like the gaming GPU performance clash the companies have waged for decades. AMD has claimed it Read more…

DoD Takes a Long View of Quantum Computing

December 19, 2023

Given the large sums tied to expensive weapon systems – think $100-million-plus per F-35 fighter – it’s easy to forget the U.S. Department of Defense is a Read more…

Synopsys Eats Ansys: Does HPC Get Indigestion?

February 8, 2024

Recently, it was announced that Synopsys is buying HPC tool developer Ansys. Started in Pittsburgh, Pa., in 1970 as Swanson Analysis Systems, Inc. (SASI) by John Swanson (and eventually renamed), Ansys serves the CAE (Computer Aided Engineering)/multiphysics engineering simulation market. Read more…

Choosing the Right GPU for LLM Inference and Training

December 11, 2023

Accelerating the training and inference processes of deep learning models is crucial for unleashing their true potential and NVIDIA GPUs have emerged as a game- Read more…

Intel’s Server and PC Chip Development Will Blur After 2025

January 15, 2024

Intel's dealing with much more than chip rivals breathing down its neck; it is simultaneously integrating a bevy of new technologies such as chiplets, artificia Read more…

Baidu Exits Quantum, Closely Following Alibaba’s Earlier Move

January 5, 2024

Reuters reported this week that Baidu, China’s giant e-commerce and services provider, is exiting the quantum computing development arena. Reuters reported � Read more…

Leading Solution Providers

Contributors

Comparing NVIDIA A100 and NVIDIA L40S: Which GPU is Ideal for AI and Graphics-Intensive Workloads?

October 30, 2023

With long lead times for the NVIDIA H100 and A100 GPUs, many organizations are looking at the new NVIDIA L40S GPU, which it’s a new GPU optimized for AI and g Read more…

Shutterstock 1179408610

Google Addresses the Mysteries of Its Hypercomputer 

December 28, 2023

When Google launched its Hypercomputer earlier this month (December 2023), the first reaction was, "Say what?" It turns out that the Hypercomputer is Google's t Read more…

AMD MI3000A

How AMD May Get Across the CUDA Moat

October 5, 2023

When discussing GenAI, the term "GPU" almost always enters the conversation and the topic often moves toward performance and access. Interestingly, the word "GPU" is assumed to mean "Nvidia" products. (As an aside, the popular Nvidia hardware used in GenAI are not technically... Read more…

Shutterstock 1606064203

Meta’s Zuckerberg Puts Its AI Future in the Hands of 600,000 GPUs

January 25, 2024

In under two minutes, Meta's CEO, Mark Zuckerberg, laid out the company's AI plans, which included a plan to build an artificial intelligence system with the eq Read more…

Google Introduces ‘Hypercomputer’ to Its AI Infrastructure

December 11, 2023

Google ran out of monikers to describe its new AI system released on December 7. Supercomputer perhaps wasn't an apt description, so it settled on Hypercomputer Read more…

China Is All In on a RISC-V Future

January 8, 2024

The state of RISC-V in China was discussed in a recent report released by the Jamestown Foundation, a Washington, D.C.-based think tank. The report, entitled "E Read more…

Intel Won’t Have a Xeon Max Chip with New Emerald Rapids CPU

December 14, 2023

As expected, Intel officially announced its 5th generation Xeon server chips codenamed Emerald Rapids at an event in New York City, where the focus was really o Read more…

IBM Quantum Summit: Two New QPUs, Upgraded Qiskit, 10-year Roadmap and More

December 4, 2023

IBM kicks off its annual Quantum Summit today and will announce a broad range of advances including its much-anticipated 1121-qubit Condor QPU, a smaller 133-qu Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire