Developing a Storage Strategy for the Future.pdf

Developing a Storage Strategy for the Future an Storage eBook contents] [ Developing a Storage Strategy for the Future This content was adapted from Internet.com's Enterprise Storage Forum, Enterprise IT Planet, and InternetNews Web sites. Contributors: Richard Adhikari, Judy Mottl, Henry Newman, Drew Robb, Jennifer Schiff and Paul Shread. 2 2 4 The Data Pileup: Save Money or Save Data? Judy Mottl Three Acronyms That Could Change the Storage World Henry Newman 4 6 6 10 Sorting Out Your Storage Options Jennifer Schiff Choosing the Right HighPerformance File System Drew Robb 10 13 13 16 Managing Storage in a Virtual World Drew Robb The Trouble with Virtual Disaster Recovery Richard Adhikari 16 Developing a Storage Strategy for the Future, an Internet.com Storage eBook. © 2008, Jupitermedia Corp. 1 [ Developing a Storage Strategy for the Future ] The Data Pileup: Save Money or Save Data? By Judy Mottl G iven how cheap storage has become, it's understandable enterprises are expanding arrays to house growing data. But stocking up on hardware and software to hold more and more information is a costly misstep, according to a Gartner report. According to Gartner, the highest reported price in the first quarter of 2008 for managed storage was $12.50 per gigabyte per month, and the lowest was $0.29 per gigabyte per month for archive storage needs. A survey of Gartner clients reported that none expected its storage budget to decrease in 2008, and that 67 percent expected the budget for storage hardware to increase. Of those polled, 64 percent also expected storage software costs to increase as well. Just a quick look at backup storage provides a clear view of how storage costs are decreasing. Prices dropped by about 30 percent from 2006 to 2008, according to Gartner. Jupiterimages But then cheap storage isn't really cheap when additional management costs and increased power and cooling costs are factored in. New regulations and legal concerns are likely prompting IT to keep every bit and byte of data just in case some litigation issue arises, and since storage costs are decreasing, the urge to push another box into play can be tempting. The problem is that data growth will very quickly outpace the savings in storage, according to Whit Andrews, an analyst at Gartner. "It's time for companies to modernize storage strategies and understand how information access technology can be a good tool for making sure they need what they're keeping," Andrews told InternetNews.com. Enterprises that choose to retain everything run the risk of significant future costs, Gartner reported. Also, the A survey of Gartner clients reported that none expected its storage budget to decrease in 2008, and that 67 percent expected the budget for storage hardware to increase. 2 Developing a Storage Strategy for the Future, an Internet.com Storage eBook. © 2008, Jupitermedia Corp. “ ” [ Developing a Storage Strategy for the Future ] longer information is saved, the harder it is to discern value, according to the survey. Information-Access Tools Companies need to create a clear distinction on which data should be saved on primary storage and what data should be housed on cheaper secondary storage, as the costs vary greatly in terms of hardware and software. Gartner provided a scenario, using a rough estimate of $5 per gigabyte for backup storage and a generation rate of 10 gigabytes per employee per year. A 5,000worker company faces annual costs of $1.25 million for five years of storage with those financials. Cutting the amount of data by 80 percent could save about $1 million for five years and lower the organization's liability, noted the report. Information-access technologies include a wide range of tools such as enterprise search, content analytics and social search. Integration and deployment typically require some expertise, such as an information architect, to get the tools in place and working well, Andrews explained. And it's not cheap, either, as products can range from $10,000 to millions for advanced applications. Still, companies can offset the costs through storage savings, as well as benefits from improved business processes. The first step, according to Gartner, is to initiate and develop a content valuation process. "This is determining what's important to keep and how a company decides what to keep," explained Andrews. "It means establishing criteria on what data is to be stored, where, and why," he added. "Cheap storage is expensive when it's storing data that doesn't need to be stored," he noted. A good best practice is establishing a content-valuation policy on legacy data and making sure what's stored requires that storage investment. While some enterprises are using information-access technologies, the majority is not at this point, according to the research firm. But sooner or later companies will realize the waste taking place in storage and the costs of retaining data that has no value, Andrews said. He adds, "Is what you're storing on tape valuable at this point, because if it's not, then you don't need it."I 3 Developing a Storage Strategy for the Future, an Internet.com Storage eBook. © 2008, Jupitermedia Corp. [ Developing a Storage Strategy for the Future ] Three Acronyms That Could Change the Storage World By Henry Newman lot of claims have been made lately of disruptive storage technologies, but saying a particular company is disruptive is a long way from Clayton Christensen's original definition. Very few individual companies have changed the industry, and one big reason is that everyone wants a standards-based product, and standards require multiple companies to create them. Once a product is created that might be a disruptive technology, lots of other players jump into the mix. Clearly, disruptive technologies are not an everyday event, nor are they easy to predict. Let's examine some technologies that might significantly change enterprise storage and disrupt the market. I won't adhere to the strict definition, but I am going to suggest some technologies that if adopted could change the enterprise storage market. As I said, I think very few companies are going to be able to create a new technology market from a technology without a standard that others can use. Even Microsoft, for example, supports all types of standards, from SATA (T13) and FC/SCSI (T11) to IETF standards. No company can be an island today. A So without further ado, here are three things that I think will be truly disruptive to the enterprise storage market. FCoE Fibre Channel over Ethernet (FCoE) is my No. 1 pick for a technology that could change enterprise storage in dramatic ways. Today, any higher performance or higher reliability storage data moves over Fibre Channel. Fibre Channel has been around for 10 years or so as the de facto storage medium in the enterprise. iSCSI, in my opinion, has never taken reasonable market share because of the overhead both for CPU and packetization (the TCP/IP encapsulation uses a significant part of the packet for small I/O requests). Jupiterimages If FCoE happens, Fibre Channel connectivity to storage will be a thing of the past and we will have one network fabric for communications and storage. Even this year, as FC interface-based disk drives are being replaced by SAS, FC chipsets shipped are declining. FC Fibre Channel over Ethernet (FCoE) is my No. 1 pick for a technology that could change enterprise storage in dramatic ways. 4 Developing a Storage Strategy for the Future, an Internet.com Storage eBook. © 2008, Jupitermedia Corp. “ ” [ Developing a Storage Strategy for the Future ] chipsets never achieved the cost factor that Ethernet chipsets achieved because FC was never considered a commodity technology — it was always a higher-priced storage interconnect. Every computer from your laptop to a large SMP server has Ethernet built in. That is not true and has never been true for Fibre Channel. FCoE will reduce costs in a number of ways: • Cost per port: Although 10GbE is likely a bit higher than 4Gbit FC in the cost per Gbyte/sec, that trend will not last long. I suspect this will be changing, and so does most of the industry. • Personnel: Today you have a storage networking group and an IP networking group in most large organizations. They are separated, as the people must deal with different technologies, training, patches, pricing, and so on. Having a single group of people that can do the same things will save money. • In my opinion, much of the Fibre Channel community sees the writing on the wall, otherwise they would not have such broad participation in the FCoE community and standards. FCoE, when deployed, will change the storage networking world. The first steps will be the host side connections and switches and RAID controllers, and then will come the other peripheral devices such as tape drives. FCoE means that Ethernet gets a larger market and, in my opinion, it will likely mean the end of the line for InfiniBand, as the combined FC and Ethernet market is just far too large a commodity market. data from creation, to backup/archiving, restoration, deletion, and everything in between, including data protection and security. I believe OSD is coming to a system near you, but it is going to take some time. pNFS I am a big proponent of this technology, and it has some broad implications. In today's world we have SAN storage and NAS storage. Everyone knows that SAN-based storage is faster than NAS for lots of good reasons, not the least of which is that the NFS protocol was not really designed to deliver high-performance streaming or I/O. NFS was designed to solve a different problem. When NFSv4.1 is implemented and released, the ability to have SAN performance on NAS equipment could become a reality. Of course, the NAS equipment would need to be redesigned to deliver SAN performance, and most NAS equipment is not designed that way, as NFS is the bottleneck, but this would allow a merging of the technologies. In addition, many environments are going to shared file systems for clusters of systems. NFSv4.1, if it lives up to its billing, would allow high performance access from many nodes to a file system. Of course, you will need a high performance file system to support the high-speed access, and that could be a problem for some vendors, but the tools are there. I believe NFSv4.1 will be disruptive, as it will merge the SAN and NAS world over time together (yet another argument in favor of an IP-based storage world). NAS vendors are going to have to build faster hardware and better file systems, and SAN vendors are going to have to team with file system vendors to develop joint products. This will all be very interesting, and I believe it could also help OSD, as larger, higher performance file systems likely will have more of the issues that are solved by OSD. I am very skeptical of claims by vendors that their technology is disruptive, as I have seen far too many such claims never pan out, but we've covered a few technologies here that could turn out to be genuinely disruptive, and the implications for storage networks are very interesting. I OSD I have been writing about object-based storage for several years now, and I am a big proponent of T10 OSD, given the problems I see regularly with fragmentation. OSD has a long way to go before it could be disruptive. There is not as much momentum behind OSD as there is for FCoE. I think part of the problem is that the problems OSD solves are not as easily understood as the problems that FCoE solves, and because OSD is solving bigger, more complex problems, it requires a larger infrastructure change such as file systems, drives, storage controller changes, and disk drives. I still believe that OSD solves many of the bigger problems that most sites face for the management of the life of 5 Developing a Storage Strategy for the Future, an Internet.com Storage eBook. © 2008, Jupitermedia Corp. [ Developing a Storage Strategy for the Future ] Sorting Out Your Storage Options By Jennifer Schiff D AS, SAN, NAS... RAID, MAID, solid state technologies, grid storage, hard disk drive storage, tiered storage, tape storage... active storage, archival storage, remote storage, disaster recovery... self-healing disk drives, virtualization, de-duplication, thin provisioning… What's Your Problem? Before you even talk to a vendor, "you have to determine what problem is it that your enterprise is trying to solve... and define your pain points and requirements," said Ashish Nadkarni, principal consultant at GlassHouse Technologies. You also need to know what it is you are actually storing, that is how much and what kind of data (e.g., file-based, block-based, structured or unstructured), said Mark Peters, an analyst with Enterprise Strategy Group. Other good questions to ask yourself and the people who will be using the storage, he said, include: How do you plan on utilizing this storage system? Is it for active storage or backup or archiving Jupiterimages — or remote storage or disaster recovery? What applications are you running? Do you want the system to be automated? Do you need it be scalable? How important are speed and performance? "You need to start from what you want rather than what a vendor or group of vendors is trying to tell you It would take pages just to list all the types, makes, and models of enterprise storage options currently on the market. Then add a list of the features and benefits of each one and it's almost enough to make a storage administrator in search of a new, additional, or supplemental storage system long for the days when a storage solution was whatever came with your server. Almost. To make it easier for you to cut through at least some of storage-decision-making clutter and make an informed purchasing decision, EnterpriseStorageForum.com spoke with a few storage analysts to gather advice to narrow down the number of choices and help you find a storage solution that's right for your enterprise. EnterpriseStorageForum.com spoke with a few storage analysts to gather advice to narrow down the number of choices and help you find a storage solution that's right for your enterprise. “ ” 6 Developing a Storage Strategy for the Future, an Internet.com Storage eBook. © 2008, Jupitermedia Corp. [ Developing a Storage Strategy for the Future ] [you need]," said Peters, who added that "the challenge for the user is to actually know and define what it is they want." To aid in that process, Greg Schulz, founder of and senior analyst at Storage IO, highly recommended drawing up a list divided into three columns or categories. In the first column should be those features and functionality you must have; in the second, those things you want or need to have; and in the third the features that would be nice to have. For Schulz, must-haves include "availability, reliability, some level of performance, some level of capacity and scalability," specifically "RAID 1, RAID 5, RAID 6, failover, redundant controllers, ease of management, tiered storage, different types of drives (fast drives and slow drives) and tape." Yes, even tape, which all three analysts said isn't going away any time soon — and is actually a good, economical, "green" storage solution. Things that fall into Schulz's want-to-have or nice-tohave bucket include de-duplication, thin provisioning, and snapshots, features that have generated a lot of buzz and may be very helpful but aren't absolutely essential to storing data. Above all, said all three analysts, stay focused on the essentials. If you happen to find a solution that meets all of your must-have requirements and can also provide you with some of your want-to-have or nice-tohave features — at the right price — then go for it. Remember, "it's what you want out of a solution, not what a company wants to sell you," stressed Nadkarni. For example, if a certain amount of capacity is a must-have requirement, focus on that. If compliance is your main issue, make sure the solution you choose has a good track record when it comes to compliance. If you are looking for a disaster recovery solution, stay focused on that. And be sure to validate vendor claims by checking with customers and reviewing test results (for things like performance) if a company is new. The Cloud Offers Promise for Storage Users By Marty Foltyn "Cloud computing" has been ill-defined and overhyped, yet storage vendors have been quick to trot out their own "cloud storage" offerings and end users are wondering whether there's significant cost savings in these services for them, particularly in tough economic times. "Cloud-speak" can be downright confusing. A recent Storage Networking World conference track proclaimed that clouds "are an evolving approach to providing users transparent IT services through a shared infrastructure of pools of systems and services." Clouds "provide a vision of a frictionless economy enabled by lowering the barrier for entry and reducing the penalty for failure." And clouds "are a vehicle to deliver infinite resources, a commitment proportional to need, and cost-effective economies of scale," albeit with a few caveats on existing infrastructure, manageability, and security. Surprisingly, Gartner considers the amorphous nature of the term to be good news: "The very confusion and contradiction that surrounds the term 'cloud computing' signifies its potential to change the status quo in the IT market," the IT research firm said earlier this year. Gartner perhaps didn't help matters any by defining cloud computing as a "style of computing where massively scalable ITrelated capabilities are provided 'as a service' using Internet technologies to multiple external customers." John Webster, principal IT advisor at Illuminata, simplifies matters by advising users to "think of the cloud as the Internet," delivering services and computing resources. Oddly enough, storage vendors developed some of the earliest cloud services, although it took another decade for the economics of Internet-based storage to make sense. "The application's storage is whatever sits up there on that 'ethereal thing,'" said Webster. There are different ways to access that storage, whether as an external service or setting up your own "cloud" inside your enterprise firewall. continued Watch for the Warning Signs While the analysts we spoke with believed good enterprise solutions far outweigh the bad, it's still pos7 Developing a Storage Strategy for the Future, an Internet.com Storage eBook. © 2008, Jupitermedia Corp. [ Developing a Storage Strategy for the Future ] sible to make a bad choice, particularly if you ignore your must-have list, base your decision on marketing hype, are too emotionally involved with a vendor or brand, act too quickly, or go with the low-ball quote without taking into account the total cost of ownership and whether the system actually addresses most of your needs. So what are some easy ways to avoid making a bad storage decision? "When you hear the words revolutionary, the only, the first, or the fastest or the most reliable, the alarm bells should be going off," said Schulz. If vendors make claims about having the best or the fastest performance, "have them back it up by showing you [using test results from organizations like SPEC, Microsoft ESRP, FPC, or TPC] and by comparing their performance to others.... And make sure it's an apples-toapples comparison, not apples to oranges." Another safeguard is to test out all the systems you are considering — or at least see one in action at a customer site — and to speak with customers who've been using that solution for at least a few months. "Don't settle for a WebEx demo," said Schulz. "Get your hands on a system if you can. Ask questions. Ask for references... but ask to hear about a story that didn't quite go well, though the customer still ended up buying." The truth is, he said, that "every vendor out there will have problems at some point or another. And any vendor that tells you they've never had a problem, they've never had an interruption, that's an alarm bell. All vendors have issues. All technologies have issues at some point in time. What separates the vendors is how they respond to those issues. How do they prevent them from recurring? How do they manage them? And then also have they improved their technology?" Speaking of which, because technologies get updated or replaced all the time, before you buy anything, "grill the vendors on what their product road map is," said Nadkarni. "For example, if they just released a product a year ago, then there's a very good chance that in the next year they're not going to have anything very drastic coming out that will replace that 8 While cloud storage is not applicable for tier-one, mission-critical data due to the nature of the information (e-mail, databases, transactional data), private clouds can serve as community storage pools for enterprise backup and archival data. Cloud storage can also be a viable option for static data resulting from applications such as digital content and distribution, video surveillance, or streaming media. Internal clouds can also offer advantages to users concerned with security issues who are more comfortable with their staff managing data within a corporate intranet than over the Internet. Especially with new regulations such as the Federal Rules of Civil Procedure (FRCP) on depositions and discovery, using cloud storage in a highly redundant way helps make sure enough copies are lying around based on a policy set. It can also free up expensive human resources now targeted to sorting and cataloging data. Security experts note, however, that for regulated data moving into any kind of a cloud, security best practices in the areas of encryption, key management and general storage security apply. As outlined in the SNIA Storage Security Best Current Practices Technical Proposal, organizations should "ensure appropriate service-level objectives for virtual storage: 1) match the availability objective for the 'storage cloud' to the application requirements; and 2) match the confidentiality and privacy requirements for the 'storage cloud' to the types of information stored." Companies might also be wise to examine their storage and retention procedures in light of tracking down data relevant to an e-discovery request. If organizations are already having trouble finding data, cloud computing could potentially create more places one has to look. And storage on external clouds or third-party facilities could also be included in any FRCP requests for backups and disaster recovery copies. I Developing a Storage Strategy for the Future, an Internet.com Storage eBook. © 2008, Jupitermedia Corp. [ Developing a Storage Strategy for the Future ] product. [But] if the product has been in the market for a few years, the vendor may be [coming out] with a brand new, completely redesigned product that's going to replace any and all products," which could pose a problem, he said. That's why it pays to see a product road map, to help you determine if the system you are considering is going to need to be upgraded or replaced sooner rather than later. As an example, Nadkarni points to modular storage arrays. Vendors, he said, have been moving "away from the old loop-based backend drives to a point-topoint system. [But] there are a lot of arrays out there in the market that have loop-based drives — and they're all being replaced, slowly, by point-to-pointbased drives. So if you're buying a modular storage array, definitely check if that storage array is due for a refresh, because once that point-to-point drive come out, [your] loop-based one is going to be obsolete, and you're going to have a disruptive upgrade to go from one to another." That's why establishing a good rapport with a vendor is important — and why you should talk to customers, to see if that vendor will be there for you when you need help, not just during installation. "We tend to get so embroiled in needs and feeds and speeds that the down-to-earth relationships can get missed," said Peters. "Reputation, references, and (where relevant) experience are crucial... to storage system choice." And if you do not feel comfortable making an important storage decision on your own, get help, in the form of an independent consultant. Take Your Time Above all, be patient when choosing a critical storage system. "Patience is a virtue," said Nadkarni, who said he thinks that phrase should be an operational guideline. "Never hurry into a large decision. If you are proactive about how you manage your [storage] environment, you will know ahead of time what you need to do — and to purchase — to keep it running. "If you are under the gun to make a decision quickly, chances are you're going to make a mistake," he said. "But when you have time on your side, you can make sure all your i's are dotted and your t's are crossed — and be more assured that you're making the right decision." I 9 Developing a Storage Strategy for the Future, an Internet.com Storage eBook. © 2008, Jupitermedia Corp. [ Developing a Storage Strategy for the Future ] Choosing the Right HighPerformance File System By Drew Robb T here are a lot of high-performance file systems out there: Sun QFS, IBM GPFS, Quantum StorNext, Red Hat GFS and Panasas, to name a few. So which is best? It depends on who you ask and what your needs are. "We typically compete with NetApp OnTap or OnTap GX, EMC, IBM GPFS, HP Polyserve or Sun's open source research project called Lustre," said Len Rosenthal, chief marketing officer of Panasas Inc. "Although we have replaced systems running Sun's QFS, we have never really competed with them in sales situations." for scratch storage, as they don't provide high enough I/O rates or a sufficient range of data management tools such as snapshots. Tough talk indeed from Panasas. So how do its rivals respond to these claims? Todd Neville, GPFS offering manager at IBM, said the GPFS installation base is diverse, including HPC, retail, media and entertainment, financial services, life sciences, healthcare, Web 2.0, telco, and manufacturing. Neville is also dismissive of the I/O rate claims. Greg Nuss, director of the software business line at Quantum, is more emphatic, stating that the stateJupiterimages ment by Panasas about StorNext's capabilities is completely false. "Each node in a StorNext cluster can act as NFS server, each presenting the common file system namespace at the back end," he said. "Today our stated node sup- Rosenthal claims that Quantum StorNext and HP Polyserve can only deal with a maximum of 16 clustered NFS servers, so they don't tend to compete in scale-out NAS bids. Similarly, he said that IBM GPFS and Sun Lustre, which are both parallel file systems like Panasas PanFS, are mainly used by universities and government research organizations There are a lot of high-performance file systems out there: Sun QFS, IBM GPFS, Quantum StorNext, Red Hat GFS and Panasas, to name a few. “ ” 10 Developing a Storage Strategy for the Future, an Internet.com Storage eBook. © 2008, Jupitermedia Corp. [ Developing a Storage Strategy for the Future ] port is 1,000 nodes and we support both SAN-attached as well as LAN-attached nodes into the cluster. We have practical installations in the 300 to 400 node range deployed today. We don't typically run into Panasas in the market because StorNext is not typically deployed in scale-out NAS configurations, but rather in high-performance workflow and archive configurations." HP, meanwhile, also took umbrage about the Panasas claims. The company said that HP Scalable NAS does not have an architectural limit on the number of NAS File Services server nodes that a customer can use in their clusters. "The stated 16 server node limit is a test limit only," said Ian Duncan, director of marketing for NAS for HP StorageWorks. "HP has a number of NAS File Services customers using clusters with more than 16 server nodes." Duncan said Panasas, Sun QFS, IBM GPFS, and Quantum StorNext are not true symmetrical file systems, but are cluster file systems based on master servers — whether for metadata operations, locking operations, or both — which are relatively easy to implement as an extension of traditional, single-node systems. However, Duncan believes they suffer from performance and availability limitations inherent in the master server's singular role. "As servers are added, the load on the master server increases, undercutting performance and subjecting more nodes to loss of functionality in the event of a master server's failure," said Duncan. "By contrast, the 4400 Scalable NAS File Services uses the HP Clustered File System (CFS), which exploits multiple, independent servers to provide better scalability and availability, insulating the cluster from any individual node's failure or performance limitation." With that out of the way, let's take a closer look at some of these file systems. ports, PanFS uses the parallel DirectFLOW protocol, which is the foundation of the upcoming pNFS (Parallel NFS) standard, which is the major advance in the upcoming NFS version 4.1. The key benefit to Panasas parallel storage is said to be superior application performance. Where NFS servers require that all I/O requests go through a single NAS filer head, PanFS enables parallel transfer of data directly from the clients or server nodes into the storage system. With Panasas, the NAS head is removed from the data path and is no longer the I/O bottleneck. Case in point: Panasas parallel storage is installed with the world's highest performance computer system in the world, the Roadrunner system at Los Alamos National Lab in New Mexico. It generates close to 100 GB/s to a single shared file system. "As a result of this architecture, Panasas parallel storage systems scale to thousands of users/servers, tens of Petabytes and can generate over 100GB/s in bandwidth," said Rosenthal. "Other key features include its software-based RAID architecture that enables parallel RAID reconstructions that are 5X to 10X faster than most storage systems." PanFS also includes Panasas Tiered Parity technology, which automatically detects and corrects unrecoverable media errors, which is important during reconstructions. Finally, this file system is optimized for use with many simulation and modeling applications. Note, though, that Panasas systems are designed for file storage, not block storage. Therefore, it is typically not installed for transaction-oriented applications such as ERP, order entry or CRM. Instead, it tends to be deployed in applications where a large number of users or server nodes need shared access to a common pool of large files. HP File Services HP claims superiority by pushing symmetry over parallelism. The product is aimed at medium-sized customers who need to seamlessly increase application throughput far in excess of traditional NAS products and easily grow storage capacity online without service disruption. HP StorageWorks 4400 Scalable NAS File Services includes an HP StorageWorks 4400 Enterprise Virtual Array with dual array controllers and 4.8 TB of Panasas PanFS The Panasas PanFS parallel file system is an objectbased file system designed for scale-out applications that require high performance in both I/O and bandwidth. Unlike NFS or CIFS, which Panasas also sup11 Developing a Storage Strategy for the Future, an Internet.com Storage eBook. © 2008, Jupitermedia Corp. [ Developing a Storage Strategy for the Future ] storage, three file serving nodes, management and replication software, and support for Windows or Linux. With three file serving nodes and dual array controllers, the 4400 Scalable NAS File Services does not have a single point of failure. Downsides? "The 4400 Scalable NAS File Services is less suitable for high-performance computing applications that require more than 6 GB/sec of throughput," said Duncan. Originally designed for technical high performance computing (HPC), it has since expanded into environments that require performance, fault tolerance and high capacity such as relational databases, CRM, Web 2.0 and media applications, engineering, financial applications and data archiving. "GPFS is built on a SAN model where all the servers see all the storage," said Neville. "To allow data access from systems not attached to the SAN, GPFS provides a software simulation of a SAN, allowing access to the data using general purpose networks such as Ethernet." Data is striped across all the disks in each file system, which allows the bandwidth of each disk to be used for service of a single file or to produce aggregate performance for multiple files. This performance can be delivered to all the nodes that make up the cluster. GPFS can also be configured so that there are no single points of failure. On top of the core file service features, GPFS provides functions such as the ability to share data between clusters and a policy-based information life cycle management (ILM) tool where data is migrated among different tiers of storage, which can include tape. In addition, GPFS can be used at the core of a file-serving NAS cluster where all the data is served via NFS, CIFS, FTP, or HTTP from all nodes of the cluster simultaneously. Further nodes or storage devices can be added or removed from the cluster as demands change. The IBM Scale Out File Services (SoFS) offering, based on GPFS, includes additional functionality. "As file-centric data and storage continues to expand rapidly, NAS is expected to follow the trend of HPC, Web serving, and other similar industries into a scaleout model based on standard low-cost components, which is a core competency for GPFS," said Neville. I Quantum StorNext StorNext is certainly the platform of choice for anyone using Apple. Further, in media rich environments where Apple, Windows, and other systems must interact, StorNext appears to have the market cornered. For example, StorNext is commonly used in demanding video production and playback applications because of its ability to handle the large capacity and frame rates of high-definition content. How does it do beyond that niche? "The key differentiators between StorNext and other shared file systems are our tight level of integration with the archive tier (StorNext/StorageManager) along with the robust tape support, as well as the broad OS platform support," said Nuss. "No other file system can support varieties of Linux, Unix, Apple and Windows within a single cluster environment." The StorNext file system is a heterogeneous, shared file system with integrated archive capability. It enables systems to share a high-speed pool of images, media, content, analytical data and other files so they can be processed and distributed rapidly, whether SAN or LAN connected. According to Nuss, it excels at both highperformance data rates and high capacity in terms of the file size as well as number of files in the file system. IBM GPFS The General Parallel File System (GPFS) from IBM has been out for a few years. "GPFS is a high-performance, shared disk, clustered file system for AIX and Linux," said John Webster, an analyst at Iluminata Inc. 12 Developing a Storage Strategy for the Future, an Internet.com Storage eBook. © 2008, Jupitermedia Corp. [ Developing a Storage Strategy for the Future ] Managing Storage in a Virtual World By Drew Robb D emand for storage has been growing rapidly for some time to meet ever-expanding volumes of data. And it seems that the more common virtualized servers become, the more storage is required. Together, the two trends — data growth and virtualization — are becoming a potent combination for storage growth. capacity. And it also makes it easier to provision away an awful lot of storage. In theory, this is supposed to make storage more efficient by improving utilization rates. But could it inadvertently be doing the opposite? "VMware virtualized environments do not inherently need more storage than their physical counterparts," said Jon Bock, VMware's senior product marketing manager. "An important and relevant point is that customers do often change the way they use and manage storage in VMware environments to leverage the unique capabilities of VMware virtualization, and their storage capacity require- "Storage capacity continues to grow at a rate of nearly 60 percent per year," said Benjamin Woo, an analyst at IDC. "2008 is likely to represent an inflection point in the way applications and storage will be interfaced. And virtual servers will emerge as the killer application for iSCSI." Are virtual machines (VMs) accelerating storage growth? According to Scott McIntyre, vice president of software and customer marketing at Emulex, VMware is typically given a large storage allocation than normal. This acts as an extra reserve to supply capacity on demand to various virtual machines as they are created. In fact, VMware actually encourages storage administrators to provision far more storage than is physically present, for example, giving each of 20 VMs a 25 percent share of Jupiterimages ments will reflect that." What seems to be happening is that companies are adapting their storage needs to take advantage of the capabilities built into virtual environments. For example, the snapshot capability provided by VMware's storage interface, VMFS (virtual machine file system), is used to enable online backups, to generate archive What seems to be happening is that companies are adapting their storage needs to take advantage of the capabilities built into virtual environments. 13 Developing a Storage Strategy for the Future, an Internet.com Storage eBook. © 2008, Jupitermedia Corp. “ ” [ Developing a Storage Strategy for the Future ] copies of virtual machines, and to provide a known good copy for rollback in cases such as failed patch installs, virus infections, and so on. While you can do a lot with it, it also requires a lot more space. Solving Management Headaches Perhaps the bigger problem, however, is the management confusion inherent in the collision of virtual servers and virtual storage. "The question of coordinating virtualized servers and virtualized storage is a particularly thorny issue," said Mike Karp, an analyst with Enterprise Management Associates. "The movement toward virtualizing enterprise data centers, while it offers enormous opportunities for management and power use efficiencies, also creates a whole new set of challenges for IT managers." Virtualization, after all, is all about introducing an abstraction layer to simplify management and administration. Storage virtualization, for example, refers to the presentation of a simple file, logical volume, or other storage object (such as a disk drive) to an application in such a way that allows the physical complexity of the storage to be hidden from both the storage administrator and the application. However, even in one domain — such as servers — this "simple layer" can get pretty darn complicated. Just take a look at what it does to the traditional art of CPU measurement using as an example an IBM micropartition in an AIX simultaneous multi-threaded (SMT) environment that consists of two virtual CPUs in a shared processor pool. This partition has a single process running that uses, let's say, 45 seconds of a physical CPU in a 60-second interval. When you come to measure such an environment, it presents some challenges. The results can be different, for example, if SMT is enabled or disabled, and if the processor is capped or uncapped. The CPU statistic %busy represents the percentage of the virtual processor capacity consumed. In this example, it might come out as 37.5 percent. Now take another CPU measurement, this time by LPAR (Logical Partition) known as %entc. This represents the percentage of the entitled processor capacity consumed and it comes out as 75 percent. Take another metric, 14 %lpar_pool_busy, which is percentage of the processor pool capacity consumed. It comes out at only 18.75 percent. Or %lpar_phys_busy — the percentage of the physical processor capacity consumed. It scores 9.38 percent. And there are other metrics that might show completely different results. "A capacity planner might look at one score and think utilization is low, whereas another takes a different view and sees an entirely different picture," said Jim Smith, an enterprise performance specialist at TeamQuest Corp. of Clear Lake, Iowa. "So who's right? It's not an easy question to answer with virtualized processors. Each answer is correct from its own perspective." Finding the Root Cause To make things more challenging, there is the ongoing trend of marrying up virtual servers with virtual storage. That means having to manage across two abstraction layers instead of one. Now let's suppose something goes wrong. How do you find out where the problem lies? Is it on the application server, on the storage, on the network or somewhere in between? "Identifying the root cause of the problem that potentially could be in any one of several technology domains (storage, servers, network) is not a problem for the faint of heart and, in fact, is not a problem that is always solvable given the state of the art of the current generation of monitoring and analysis solutions," said Karp. "Few vendors offer solutions with an appropriate set of cross-domain analytics that allow real root cause analysis of the problem." EMC — majority owner of VMware — starts to look pretty smart now for its acquisition of Smarts a little while back. It is heading down the road of being able to provide at least some of the vitally needed cross-virtualization management. And NetApp is heading down the same road with the acquisition of Onaro. "Onaro extends the NetApp Manageability Software family, as SANscreen's VM Insight and Service Insight products help minimize complexity while maximizing return," said Patrick Rogers, vice president of solutions marketing at NetApp. "These capabilities make Onaro a key element in NetApp's strategy to help customers improve their IT infrastructure and processes." Developing a Storage Strategy for the Future, an Internet.com Storage eBook. © 2008, Jupitermedia Corp. [ Developing a Storage Strategy for the Future ] For virtual machine environments, VM Insight provides virtual machine-to-disk performance information to optimize the number of virtual machines per server. For large-scale virtual machine farms, this type of crossdomain analytics assists in maintaining application availability and performance. SANscreen Service Insight makes it easier to map resources used to support an application in a storage virtualization environment. It provides service level visibility from the virtualized environment to the back-end storage systems. Meanwhile, the management of multiple virtualization technologies is coming together under the banner of enterprise or data center virtualization. This encompasses server virtualization, storage virtualization, and fabric virtualization. "IT managers are increasingly considering the prospect of a fully virtualized data center infrastructure," said Emulex's McIntyre. "One of the characteristics of enterprise data centers is the existence of storage area networks. There is a high degree of affinity between SANs and server virtualization, because the connectivity offered by a SAN simplifies the deployment and migration of virtual machines." SAN-based storage can be shared between multiple servers, enabling data consolidation. Conversely, a virtual storage device can be constructed from multiple physical devices in a SAN and be made available to one or more host servers. Not surprisingly then, not only are storage devices being virtualized, but increasingly there is interest in virtualizing the SAN fabric itself in order to consolidate multiple physical SANs into one logical SAN, or segment one physical SAN into multiple logical storage networks. Emulex, for example, is providing the virtual plumbing to handle some of the connectivity gaps between storage and server silos. Emulex LightPulse Virtual HBA technology virtualizes SAN connections so that each virtual machine has independent access to its own protected storage. "The end result is greater storage security, enhanced management and migration of virtual machines and the ability to implement SAN best practices such as LUN masking and zoning for individual virtual machines," said McIntyre. "In addition, Virtual HBA Technology allows virtual machines with different I/O workloads to co-exist without impacting each other's I/O performance. This mixed workload performance enhancement is crucial in consolidated, virtual environments where multiple virtual machines and applications are all accessing storage through the same set of physical HBAs." No doubt over time, more and more of the pieces of the virtual plumbing and a whole lot more analytics will have to be added to the mix to make virtualization function adequately in an enterprise-wide setting. Until then, get ready for an awful lot of complexity in the name of simplification. "It is absolutely necessary to understand the topology, in real time — or at the very least, in near real-time — in order both to identify problems and to manage the entire environment proactively as a system and preempt problems," said Karp. "In a best-case scenario, a constantly updated topology map would be available for each process being monitored." I 15 Developing a Storage Strategy for the Future, an Internet.com Storage eBook. © 2008, Jupitermedia Corp. [ Developing a Storage Strategy for the Future ] The Trouble with Virtual Disaster Recovery By Richard Adhikari A s enterprises virtualize their data centers to cut costs and consolidate their servers, they may be setting themselves up for big trouble. Lamorena. So why are virtual servers being left out of DR plans, or, if they're included, aren't being backed up? That's because enterprise IT just does not have the right tools to back up virtual servers, according to Symantec. The biggest problem for 44 percent of North American respondents was the plethora of different tools for physical and virtual environments. There are so many that IT doesn't know what to use and when. Another 41 percent complained about the lack of automated recovery tools. Much of the disaster recovery process is manuJupiterimages al, although VMware recently unveiled a tool to automate the run book. Another 39 percent of respondents said the backup tools available are inadequate. Hewlett-Packard, IBM, CA, and smaller vendors such as ManageIQ, Avocent, and Apani offer tools to manage both the virtual and physical environments. And com- According to the latest disaster recovery research report from Symantec, based on surveys of 1,000 IT managers in large organizations worldwide, 35 percent of an organization's virtual servers are not included in its disaster recovery (DR) plans. Worse yet, not all virtual servers included in an organization's DR plan will be backed up. Only 37 percent of respondents to the survey said they back up more than 90 percent of their virtual systems. When companies virtualize, they need to overhaul their backup and DR plans, Symantec says; the survey found that 64 percent of organizations are doing so. "That's no surprise, because virtualization has had a huge impact on the way enterprises do disaster recovery," said Symantec senior product marketing manager for high availability and disaster recovery Dan When companies virtualize, they need to overhaul their backup and DR plans, Symantec says; the survey found that 64 percent of organizations are doing so. 16 Developing a Storage Strategy for the Future, an Internet.com Storage eBook. © 2008, Jupitermedia Corp. “ ” [ Developing a Storage Strategy for the Future ] panies like Hyperic are bringing out new tools. However, virtual server management tools, being relatively new, are not as sophisticated as their counterparts for the physical environment. Also, they have not been around long enough for users to be familiar with them. For example, provisioning, or setting up, virtual machines from physical ones and vice versa can also be a problem, and tools for this have only recently emerged. "Virtualization makes some aspects of backup and disaster recovery more difficult," said Symantec senior product marketing manager for NetBackup Eric Schou. "IT shops are still struggling with the steep learning curve." Porting over solutions from the physical environment won't work, Schou said. "IT shops need to get solutions that are finely tuned for virtualization," he added. For 35 percent of the respondents, the tests failed because "people didn't do what they were supposed to do," Lamorena said. This means that much of recovery is still a manual process, and companies must begin looking at automation, he said. Another cause is that tests are not run frequently enough. That's because "when you run a test, it disrupts employees and customers," Lamorena said. He added that 20 percent of the respondents said their revenue is hurt by DR tests, so "the tests cause the same pain to their customers as if they had a real disaster." Finally, the survey found that top-level executive involvement in DR planning has fallen. "Last year, the C-level involvement on disaster recovery committees was 55 percent; this year, it's 33 percent," Lamorena said. C-level executives are CIOs, CTOs and CEOs. Lamorena finds the reduction in top-level involvement disturbing because it could lead to more problems with DR. "That's a huge drop, and we've been thinking about this day and night," he said. "What's alarming is, companies may be getting a little lax and don't think they'll be affected by a disaster." I Failing DR Judging from the results of the survey, IT is still not as familiar with DR as it should be. DR testing is a mess. A whopping 30 percent of respondents said their DR tests failed. That's better than the 50 percent failure rate in 2007, but it's still pretty scary. 17 Developing a Storage Strategy for the Future, an Internet.com Storage eBook. © 2008, Jupitermedia Corp.