Veritas Scalable File Server (SFS) Solution Brief for Energy (Oil and Gas) Industry By Greg Schulz Founder and Senior Analyst, the StorageIO Group Author The Green and Virtual Data Center (CRC) September 1, 2009 This Industry Trends and Perspectives Paper is Compliments of: www.symantec.com Copyright 2009 Server and StorageIO All Rights Reserved. 1 of 7 twitter @storageio
Introduction The oil and gas industry is faced with the challenge of supporting increased production to meet continued strong consumer demand while reducing costs. In addition, oil and gas organizations are looking to reduce the costs of finding new oil and gas deposit locations. Consequently there is renewed focus on effective energy exploration efforts, on land as well as marine based, with a goal of cost effective energy exploration and production (E&P). Energy Trends and IT Issues A current focus is on oil and gas energy research and exploration to address various demand objectives, initiatives and legislative needs. The result is a growing reliance on affordable and scalable shared file serving solutions. This means new E&P data is being generated on a regular basis. All of which requires processing for visualization, modeling, and analysis in a timely and cost effective manner. Another by-product of more effective methods is the Oil and Gas E&P Continuum need to go back and analyze previous explorations, leveraging prior data acquisitions with modern seismic data analysis and visualization technologies. Not surprisingly, given the cost and time associated with E&P, any new information will have intellectual property value going forward and need to be retained indefinitely. The result is more data being stored online for longer periods of time, requiring IT systems need that are scalable, secure and cost effective. Demand Drivers Digital data in conjunction with oil and gas exploration data acquisition is not a new topic. However, what is new and important is the need to support advanced analysis, modeling and visualization efforts. Data storage and management is important for supporting oil and gas activities including upstream exploration, visualization, development and production along with downstream business functions. Demand drivers, needs and issues taxing oil and gas industry organizations include: Growing demand for new and affordable energy spurring exploration and modeling Time and capital intensive investments associated with exploration and production Management of larger amounts of data required for 3D and 4D visualization analysis Data retention of larger data repositories for longer periods of time Need for speed and scalability to shorten exploration, visualization and production planning Enhancement of information flow and sharing during exploration and visualization lifecycles Today s energy analysis modeling and visualization tools provide many times greater definition, granularity and dimensions than previous generations technology. With the advent of multidimension data visualization capabilities such as three dimensional (3D) and 4D, more data is needed to support these enhanced capabilities, which, in turn, means more data to store and process. Copyright 2009 Server and StorageIO All Rights Reserved. 2 of 7 twitter @storageio
Given the various increasing demands, costs can be outweighed by the benefits of faster and more successful explorations, visualization and analysis. 3D exploration is more in-depth and prolonged than 2D data acquisition, however yields improved benefits. These include improved accuracies for well placement resulting in improved utilization of reservoirs. Recovery rates, or the ability to draw as much resource as efficiently as possible from a reservoir, can jump significantly with higher dimension visualization. 4D enhances the static views found in 2D or 3D by adding time-based or time-lapsed views of reservoirs. 4D views show what is going on underground for exploration purposes as well as for analysis of how the reservoir will flow or produce product and thus increase production yields. In addition to having to support more data from explorations, oil and gas organizations or service providers need to retain the resulting information for longer periods of time for both upstream and downstream processes. This means storing the information in a cost effective manner that is also easily accessible and sharable across different applications and business functions from research to production planning to reservoir management and others. By the Numbers: Digitally Discovered Data Oil and gas exploration and visualization activities rely on the acquisition of large amounts of data that needs to be stored, processed and maintained during project lifecycles now and for the future. Geography, mapping databases, and other data repositories collated from different sources result in the need for large amounts of fast, flexible and reliable storage. 2D, 3D and 4D seismic technologies enable multi-dimensional views of data including length, width, and depth with time being the 4th dimension. 3D and 4D visualization and interpretations of acquired data, provide improved situational awareness and understanding of how an oil or gas reservoir would behave if put into production. Higher dimensional views (e.g. 3D vs. 2D, 4D vs. 3D) have the benefit of increasing success in exploration efforts with the price of having more data to collect, store and process. For example, as part of a visualization analysis, a data line of interest can require billions of data points, and each visualization analysis contains multiple lines of interest. The result is storage and performance needs adding up quickly. Information is Fundamental Issues More data needed for visualization More data to store for longer time Rising costs and shrinking budgets Reducing IT costs and complexity Return on Investment (ROI) Flexibility and cost effectiveness The Need for Robust File Serving The inherent file, data and storage sharing capabilities of a scalable network attached storage (NAS) including support for Unix or Linux Network File System (NFS) or Windows-based Common Internet File System (CIFS) data access and file sharing make for a flexible, resilient and cost effective solution for fueling energy IT data storage issues. also needed after visualization and modeling to support production planning should a decision be reached to proceed with drilling. A further example is that 3D models, as compared to 2D models, can require a 16-fold increase in the amount of data storage along with associated performance. Not surprisingly, 4D visualization Copyright 2009 Server and StorageIO All Rights Reserved. 3 of 7 twitter @storageio
and exploration have a further 32 factor increase in data processing and management needs in order to track all of the interrelated attributes involved with exploration and visualization. Consequently, in order to support the data-hungry and long-running compute tasks associated with 3D or 4D visualization, robust, scalable and flexible file server solutions are needed. What to look for in an energy industry file serving solution Given the diverse needs and requirements of oil and gas organizations that are looking to support growth while reducing costs, the following are attributes to consider when looking at a scalable and flexible data infrastructure solution. Scalability with stability (Solution remains stable with growth in a predictable manner) As capacity is increased, performance and availability/reliability are not negatively impacted. Likewise, as performance, availability or capacities are increased, there should not be a corresponding scaling of price. Needless to say, performance, availability, capacity or energy efficiency should not be a tradeoff at the expense of one or the other attributes. Scaling with stability also means that added complexity, including management costs, does not occur as a solution is expanded. Flexibility and Integration (Work with various applications and IT technologies) Co-existence and complementing investments in existing technologies (hardware, software, networks, applications, tools, procedures and people skills) are essential for removing complexity and cost while boosting productivity and efficiency. Other dimensions of integration include whether there is the flexibility to choose which hardware, including tiered storage, will be used, or is the solution tied to specific hardware or only available on a self-integration basis. Functionality integration is another consideration. For example, are snapshots, Why Scalable NAS File Serving? Accessible from networked devices Combines data and storage sharing Flexible to adapt to diverse needs Integrated file and data management Easy to use for IT staff and users Applicable for unstructured data environment replication, storage tiering, load-balancing, anti-virus, backup/recovery, data footprint reduction (archive, compress, dedupe) built-in or pre-integrated as part of a solution, or does a solution require additional 3 rd party products to be integrated? Ease of use (Leverage existing skill sets and technology) A combination of intuitive user interfaces (UI), including graphical user interfaces (GUI), command line interfaces (CLI) or interfaces with other management tools are part of enabling ease of use. Some NAS systems support many nodes as part of being a clustered file serving solution, however limit an individual file system to performance of single node. The existence of multiple nodes for availability or failover does not guarantee more performance. Clustered file systems should be a solution with a file system where files can be accessed by applications via any of the different file serving nodes in a cluster concurrently to meet performance requirements. Affordability (Total storage cost of ownership-tco-and Return on investment-roi) File sharing and data serving solutions for oil and gas organizations need to be affordable both for Copyright 2009 Server and StorageIO All Rights Reserved. 4 of 7 twitter @storageio
initial purchase and from an ongoing (maintenance and usability) basis to reduce costs of storing and retaining data for long periods of time. Veritas Scalable File Server (SFS) by Symantec Veritas Storage Foundation Scalable File Server (SFS) by Symantec is a software-based solution that transforms industry standard servers and Fibre Channel or Serial Attached SCSI (SAS) attached storage from different vendors into a scalable NAS file serving solution. By being scalable, SFS enables tiered storage, including Fibre Channel, SAS or Serial ATA (SATA) disk drives, to be configured to support diverse application needs and cost criteria along with configuring the applicable number of nodes to meet performance, availability/reliability and capacity requirements. Figure 1 Putting it All Together: Symantec SFS Examples (Courtesy Symantec) Figure 1 shows an example of how the Symantec SFS solution can be deployed to meet energy exploration, analysis and research data storage needs. From left to right, an environment can start with a simple configuration using existing servers and storage hardware combined with the Symantec SFS software to create a scale file serving solution. SFS can start in small configurations and scale in terms of performance, availability and capacity to meet changing needs while re-using existing hardware. Supporting concurrent NFS and CIFS access, SFS enables a mix of Windows, UNIX, and Linux along with other operating systems and applications sharing of data files. Copyright 2009 Server and StorageIO All Rights Reserved. 5 of 7 twitter @storageio
Scalability - Being a clustered file system as opposed to a traditional clustered for failover NAS solution, SFS has the ability to scale out performance, availability and capacity across multiple (n-way) storage processing nodes. The benefit is scalable performance, availability and capacity without adding cost or complexity or hardware vendor lock in. This also means supporting large PB-plus data repositories with many 250TB file systems. In addition, SFS supports large numbers of small files as well as supporting large files from a performance capacity standpoint. Flexibility - Symantec SFS supports mixed workloads and applications. Another feature of SFS is the pre-integration of Symantec backup/restore data protection tools. Symantec SFS supports different tiers of storage including high performance Fibre Channel or SAS disk drives for time sensitive applications and lower cost, high capacity SATA disk drives for less frequently accessed data. Ease of use - Integrated data and storage management enable clustered file sharing to co-exist with different applications to enable ease of use. As a scalable NAS clustered file serving solution that leverages different vendors server and storage hardware, Symantec SFS also enhances ease of use leveraging LAN, server and storage skill sets. Ease of use features includes cluster wide management of file system, availability and data protection via command line (CLI) and graphical user interfaces (GUIs). Affordability The abilities to pay-as-you grow, leverage and re-use existing servers and storage hardware combined with built-in features such as snapshots, and high-availability clustering for availability combines to reduce hidden fees. SFS provides the flexibility of a software based solution with the ability to leverage cost effective existing or third party hardware including servers and storage. Scalability Flexibility Characteristic Performance Availability Capacity Integration Tiered Storage SFS Capabilities Scale to sixteen storage server nodes Proven clustered file system and data protection suite Leverage tiered storage to meet capacity needs Built-in high availability (HA) supports scaling NFS and CIFS host application access Fibre Channel, SAS and SATA tiered storage devices Ease of use Integration Co-exist with existing technologies and tools Leverage existing skill sets while working with diverse Oil and Gas E&P application portfolios Affordability Pay as you Support 3 rd party and existing hardware (investment protection) grow Align performance, availability and capacity to application needs while preserving investment in existing technologies. Summary of Veritas Storage Foundation Scalable File Server by Symantec Of these attributes, three in particular stand out: scalability, high-availability and affordability. Pound-for-pound, SFS offers a great value to the energy industry as well as other highperformance computing-based industries. Learn more about Veritas Storage Foundation Scalable File Server by Symantec along with other related topics at www.symantec.com/business/scalable-file-server. Copyright 2009 Server and StorageIO All Rights Reserved. 6 of 7 twitter @storageio
Conclusion Scalable file serving solutions, such as Symantec SFS, for the energy industry enable modular growth to support large data repositories allowing cost conscious oil and gas organizations to pay as they go while reducing costs by leveraging existing server and storage hardware. Symantec SFS leverages time-tested software for file and data management while supporting industry standard file sharing including NFS for UNIX or Linux as well as CIFS for Windows-based IT environments.. Additional interoperability is in the form of support for shared SAS along with Fibre Channel attached storage systems (SANs) that support Fibre Channel, SAS and SATA tiered disk storage to meet various performance, availability and capacity requirements. Another benefit of the solution is the integration with other Symantec data protection software to help remove complexity while improving on availability along with supporting BC and DR requirements. With a continued trend of more data being generated and stored for longer periods of time, scalability of file serving solutions will become more important as will efficient and cost effective storage solutions. The bottom line is that Symantec SFS provides a comprehensive, highly scalable file serving clustered NAS solution in a storage-agnostic manner with the proven reliability that energy focused organizations of all size require at a lower cost compared to traditional file serving solutions. About the author Greg Schulz is founder of Server and StorageIO, an IT industry analyst consultancy firm and author of the books The Green and Virtual Data Center (CRC) and Resilient Storage Network (Elsevier). Learn more at www.serverandstorageio.com or on twitter @storageio. All trademarks are the property of their respective companies and owners. The Server and StorageIO (StorageIO) Group makes no expressed or implied warranties in this document relating to the use or operation of the products and techniques described herein. StorageIO in no event shall be liable for any indirect, inconsequential, special, incidental or other damages arising out of or associated with any aspect of this document, its use, reliance upon the information, recommendations, or inadvertent errors contained herein. Information, opinions and recommendations made by StorageIO are based upon public information believed to be accurate, reliable, and subject to change. This industry trends and perspective white paper is compliments of Symantec Corporation (www.symantec.com). Copyright 2009 Server and StorageIO All Rights Reserved. 7 of 7 twitter @storageio