IDEAS Insights

After HP’s Acquisition of 3Com, What’s Next for Storage and Network Virtualization?

Following HP's announcement last week that it would acquire 3Com, speculation has arisen that more acquisitions related to storage and networking could happen soon, possibly including HP's absorption of 3PAR or Pillar. Another leading network company, Brocade, issued a denial that it was for sale, which nonetheless raises questions about whether its products and technology would fit well into a larger company.

As the industry moves into the next stage of applying virtualization, going beyond basic use cases such as consolidation, users are focusing increasingly on the broader impact that virtualization will have across storage and network infrastructures. Especially in large organizations, system managers now seek to achieve some of the same benefits from virtualizing storage and networking resources that they gained with server virtualization. In particular, they would like to reconfigure storage and network infrastructures with the same flexibility as virtual machines. For example, just as virtual machines can be moved around a network with functions such as VMware vMotion or Hyper-V Live Migration, virtual storage can be transparently relocated from one physical storage device to another with tools such VMware Storage vMotion. Similarly, administrators expect to be able to dynamically reconfigure virtual networks independently of the physical network and storage connections, which are generally changed as little as possible to avoid burdening network and storage management personnel.

Some of the requirements for these capabilities must be handled at the level of server hardware. Indeed, I/O virtualization technologies such as HP Virtual Connect, IBM BladeCenter Open Fabric Manager, and Egenera PAN Manager enable flexible connections between servers and the physical topology of networks and storage. However, to fully integrate virtual machines into virtual networks spanning datacenters or enterprises, specific functions must be implemented within virtual machine hypervisors. For this reason, the integration of Cisco's Nexus 1000V virtual switch with VMware vSphere 4.0 represents an especially crucial link. The commonality between Cisco and VMware's virtual networking technology enables VMware-based virtual networks to be managed with the same tools used for managing Cisco-based physical networks, in a way that allows virtual networks to be flexibly reconfigured. A key strength of the Virtual Computing Environment (VCE) coalition between EMC, Cisco, and VMware is their ability to further optimize the hypervisor, virtualized storage, and virtualized networking as a single integrated stack. Coupled with Cisco's entry into the server market with its Unified Computing System (UCS), VCE's thrust deep into the heart of virtual infrastructure steps up the challenge for other major systems vendors to respond with a credible alternative for end-to-end virtual infrastructures spanning servers, storage, and networking.

HP's acquisition of 3Com, following its renewed focus on the HP ProCurve line of networking gear in the past year, clearly represents a dramatic first step towards adapting to the new realities of the IT systems business, in which Cisco has become a strategic competitor. HP has also quietly started promoting an industry standard for virtualized networking called Virtual Ethernet Port Aggregator (VEPA), which it hopes will be more palatable for adoption by multiple server vendors than the VN-Link technology underlying Cisco's Nexus 1000V switch and the vNetwork distributed switch in VMware vSphere 4.0. As the strategic importance of virtual switching has become clearer, some other alternatives have sprung up in the industry as well, including Open vSwitch, which is based on open source technology developed in part by Nicira Networks and is being promoted by Citrix for its XenServer hypervisor.

How would additional acquisitions then help HP to compete with Cisco and VCE? First, acquiring 3PAR does not appear to be necessary. HP already has a broad range of storage solutions, including Modular Smart Array (MSA), Enterprise Virtual Array (EVA), XP, X9000, ExDS9900, AiO (Proliant Storage Server), RISS, and Lefthand. It is not clear how 3PAR would fit into this lineup, unless some existing product family were phased out. Indeed, most of the big storage companies have now made their clustered storage technology acquisitions, leaving 3PAR to compete independently. At this stage, it is unlikely that any of the major vendors would want to acquire the company, except for an irresistible fire sale price. One possibility would be for 3PAR to be acquired by Rackable (now SGI), should it still have any money left after its acquisition of SGI. More far-fetched, 3PAR could be acquired by someone out of left field, such as a cloud service provider like Amazon, Salesforce.com, Google, or even Microsoft. Any of these companies could take advantage of 3PAR's technology to build out a cloud service infrastructure that requires vast amounts of high-performance storage.

Acquiring Brocade could be more strategically significant, either for HP or another vendor such as Cisco. From the perspective of storage customers, Brocade is far more relevant than 3Com, which does not make Storage Area Network (SAN) switches. Brocade is one of only two independent suppliers of enterprise-grade Fibre Channel (FC) switches, the other being Cisco, which entered the FC market relatively late. While Brocade insists it is not for sale, the company now faces a long-term strategic issue as its core market of FC solutions nears the end of its natural lifespan. FC technology is now 30 years old, and while it has been the SAN interface of choice for the last 10 years, it will soon enter the sunset phase when FCoE and/or Infiniband start taking off as expected. As a result, Brocade needs to break out with some major new innovation or be acquired, otherwise it will perish.

One key advantage for Brocade is its DCX Backbones technology, which enables true Storage Network Virtualization, whereby SAN switches themselves are transformed into hosting virtual networks. Cisco is targeting converged storage networking with Fibre Channel over Ethernet (FCoE), but its technology is optimized more for the virtualized Ethernet layer of the stack, and it does not have quite the same degree of storage virtualization functionality as DCX Backbones. Whichever company acquires Brocade and its DCX Backbones technology could gain a crucial edge in the pursuit of Storage Network Virtualization.

Integrating DCX Backbones with Nexus 1000V technology would put Cisco, and the VCE coalition, in an even stronger position than before to drive the agenda of virtual infrastructure and Storage Network Virtualization, since most of the major systems vendors now OEM Brocade's technology for their existing SAN products. Conversely, should HP proceed to acquire Brocade, it would significantly strengthen its defenses against Cisco's drive into the server market. At minimum, having another switch supplier in its fold would help HP establish VEPA as a standard for virtual switching. Further, integrating Brocade's technology with other elements of HP's virtual infrastructure such Virtual Connect would go far in enabling HP to propose an alternative to VCE for virtualizing everything outside of the hypervisor (regardless of which hypervisor is installed, i.e. VMware, Hyper-V, or XenServer). While there is no evidence at present that either Cisco or HP is about to make a move on Brocade, the control of that company's assets remains a critical variable for determining how virtual infrastructure will be adopted across the industry.

Will SAS Replace FC in Disk Array Making?

Serial-Attached SCSI (SAS) technology has been available for a few years. So far, SAS has proven itself to be a robust technology through various product implementations; there have been no major complaints from storage end-users. It seems like SAS-based products have fulfilled the design proposition of the SAS protocol, which is to overcome the I/O bus limitation of the Parallel-SCSI protocol in order to achieve higher performance and scalability.Hence, many customers are now wondering when they will be able to replace their costly Fibre Channel (FC) disks with more affordable SAS disks. For some of them, the answer is today, and for some of them, the answer is indefinite.

Customers with direct-attached external RAID disk systems can migrate from FC-based disk enclosures to SAS-based disk enclosures by swapping the FC HBAs inside the server with SAS host adapters (for JBOD) or SAS RAID cards. FC HBAs typically do not offer RAID capability and often rely on host-based software RAID. SAS JBOD adapters are available for those users who prefer software RAID. However, more users today prefer to deploy hardware RAID (host adapter with RAID-processing ASIC) to avoid the performance impact of RAID processing on the host.

Customers with storage servers, such as Windows- and Solaris-based network storage servers, can enjoy SAS today as well. Storage servers are made from industry-standard servers running storage-serving operating systems. They contain direct-attached storage subsystems, which can be SAS-based enclosures. For example, the Sun Storage 7000 series is one commercial-grade storage server implementation that employs SAS-based disk subsystems. Note that the Sun 7000 platform does not use hardware RAID, but implements the Solaris ZFS zRAID.

Customers with network storage systems, known as SAN platforms, may face a longer, indefinite FC to SAS transition cycle. While all the entry-level network storage platforms from major storage vendors – such as the Dell|EMC AX4, HP MSA2000, HDS SMS100, IBM DS3000, and NetApp FAS2000 systems – have already transitioned to SAS-based disk subsystems, the midrange and high-end storage platforms from these vendors are still using FC-based disk subsystems. The only exception is the midrange HDS AMS2000 line, which provides a large number of I/O slots to populate SAS adapters and connect to SAS-based disk enclosures. To date, the AMS2000 series is the only midrange network storage platform from a major storage vendor that supports FC host connectivity with a SAS back end. None of the high-end platforms have transitioned to a SAS back end.

Vendors have their reasons for not switching to a SAS back end. Midrange and high-end storage platforms from major storage vendors such as EMC, HDS (resold by HP and Sun), and IBM commonly employ a switched-disk subsystem design. A switched design provides non-blocking, point-to-point connection between disks and controllers. Engineers argue that a switched connection is more advanced than a serial connection. Serial connections can potentially become congested and cause performance degradation when they are shared by heavy I/O operations. Hence, it is very likely that the midrange and high-end storage platforms from these vendors will retain their switched back-end architectures for the foreseeable future. However, the HDS AMS2000 midrange arrays producedindustry-leading SPC-1 benchmark results, and did not show any signs of I/O congestion for the test workload.

Nevertheless, SAS is without a doubt more affordable than FC. The traditional FC SAN platforms are increasingly being challenged on the cost front by storage servers based on industry-standard technologies. As more and more customers are attracted to the affordability of SAS-based disk systems, the leading storage vendors may have no choice but to switch to a SAS-based back end. However, it is also possible to implement a SAS switch, instead of an FC switch, to have the best of both worlds. Such a SAS switch is available today – just not in a storage product implementation. Take for example, the HP ProLiant BL SAS switch. Therefore, while the day that SAS disks replace FC disks in high-end network storage platforms is still unknown, it may not be too far away.

What are the Performance & Energy Tradeoffs of 15K vs.10K RPM Disk Drives?

Have you ever wondered what the combined performance and energy tradeoffs are when considering whether to go down the high-capacity lower-performance 10K rpm drive route, compared with using faster 15K RPM, but lower capacity drives? And thus, which ones really fit your needs? The Storage Performance Council (SPC) is starting to provide these sorts of answers, with its next release of a performance benchmark for storage with energy extensions.

Green IT concerns, such as power consumption and carbon emissions, continue to grow in importance with end users. While cost-cutting is a tangible incentive for Green IT programs, such initiatives are no longer just about saving money. Higher level issues, such as understanding and minimizing an organization’s environmental impact, are driving organizations to quantify their carbon footprint and take action to reduce it. As such, demand is growing for suitable tools that help IT decision makers weigh their energy reduction goals against the performance requirements of their organization.

This leads to the inevitable question of to how to measure and quantify the situation. So, pressure is growing for suitable tools to help IT decision makers navigate this new world.

SPC-1/E Benchmark

The Storage Performance Council (SPC) is one organization working to meet that demand. Today, the SPC announced the SPC-1/E Benchmark, its second storage performance benchmark to include energy extensions. Historically, industry-standard benchmarks have focused primarily on the performance and price/performance of the tested configurations. The SPC-1/E Benchmark adds real-world energy consumption to the mix, offering more detailed insight into the various tradeoffs (performance, energy usage, and cost) of deploying one product – or one technology – over another.

Two New Results

Two SPC-1/E results have been released to coincide with the introduction of the new benchmark. Xiotech, a storage solution provider, has posted two separate results for the same Emprise 5000 product. What is very interesting is that two tests for the same product have been released at the same time, with only the drive type changing between the tested configurations. The first test used 146 GB 15K RPM FC disk drives while the second used 600 GB 10K RPM FC Seagate drives. Everything else about the configurations remained the same.

So, even if you are not in the market for a Xiotech product, the outcomes of these tests are interesting because they begin to give some visibility on more general issues, such as what is the real impact on performance and energy consumption between using 15K RPM and 10K RPM drives.

So which is best?

As expected, the faster 146 GB 15K RPM drive configuration provides higher levels of performance. It also consumes more power. But if absolute performance is not a primary factor then the lower energy profile of the slower disks may be of interest. Interestingly, the relationship between performance and power consumption is not linear. Compared to the 146 GB 15K RPM configuration, the 600 GB 10K RPM configuration consumes 19.4% less energy yet delivers only 12.9% less performance. (Chart 1) These results suggest that a modest tradeoff in performance can result in potentially significant energy savings. These potential savings may be further enhanced once the extra storage capacity of the 600 GB drive is factored in. More food for thought!

Free Research Report

IDEAS has produced a free Research Report titled ‘Energy and Performance Come Together with Storage Benchmarking’, which can be downloaded from the Sample Research section of www.ideasinternational.com  This report analyzes the outcomes of the two test results in more detail to help users understand which disk technology may be better suited to their needs.

In Review

With the addition of energy extensions, IDEAS believes that the SPC Benchmarks are taking on a new level of relevance. In light of the increasing focus on Green IT, the IT community is crying out for independent, quantifiable, and verifiable insights into the tradeoffs involved in choosing one technology over another. The addition of the energy extensions to the performance perspectives of the SPC Benchmarks enables more in-depth analysis of the technologies being tested. The benchmarks enable users to probe multiple dimensions – not only in isolation, but in conjunction with each other – in order to choose the technology that best suits their needs.

Gary Burgess
Senior Vice President, Research & Operations
 Follow Gary on Twitter

 

Storage Performance Council

The SPC is a non-profit corporation founded to define, standardize and promote storage benchmarks and to disseminate objective, verifiable storage performance data to the computer industry and its customers. The organization’s strategic objectives are to empower storage vendors to build better products as well as to stimulate the IT community to more rapidly trust and deploy multi-vendor storage technology.

www.storageperformance.org

What Storage Would Sun-Oracle Sell Post-Merger?

The Oracle acquisition of Sun Microsystems has been approved by multiple stakeholders, such as the Sun stockholders and the U.S. Department of Justice, and the merger appears likely to happen soon. Customers, competitors, industry and Wall Street analysts, as well as individual technology enthusiasts have all started speculating about the post-merger offerings from Sun-Oracle. The future storage lineup from the combined entity stands out as one of the most uncertain areas.

One key factor in this case concerns the destiny of Pillar Data Systems, which is a network storage vendor funded by Oracle CEO Larry Ellison. Many IT professionals are expecting the convergence of Pillar and Sun storage, and industry rumors suggest the same. However, while the Sun-Oracle acquisition and post-merger restructuring will be subject to corporate governance, the destiny of Pillar will essentially be Mr. Ellison’s personal decision. And, since Pillar is an independent entity, the adoption of Pillar into the Sun-Oracle storage offering portfolio will not be free. The Sun-Oracle corporation would need to offer Mr. Ellison an attractive price to acquire Pillar.

From Mr. Ellison’s standpoint, it would be difficult to balance the competition between Sun Storage and Pillar. With Oracle alone, there is no conflict of interest for Mr. Ellison since Oracle is not a storage vendor. But with Sun-Oracle, Mr. Ellison will be juggling competing storage hardware offerings from both the public company that he leads and his private company – unless he sells Pillar to Sun.

Does Sun need Pillar for the Sun Storage portfolio? Probably not.

Sun already has an extensive storage offering portfolio, including the 2500 and 6000 series entry and midrange arrays OEMed from LSI; the 7000 series IP-storage and Sun Fire Storage Servers based on Solaris ZFS; and the 9000 series enterprise platform OEMed from HDS. The Pillar Axiom storage platform does not appear to be a reasonable replacement for any of above.

The Sun Storage 2500 and 6000 series are built with industry-standard hardware from LSI. These systems are also resold by many other storage vendors and integrators as best-of-breed commodity storage platforms. The Pillar Axiom platform is based on a proprietary design and sold at premium prices compared to the LSI-based storage products. If the Pillar Axiom replaces the Sun 6000 series midrange offerings, it is likely that Sun-Oracle would be unable to compete on prices, which is crucial for the midrange market, especially during an economy downturn.  

The Sun 7000 series and the Sun Fire Storage Servers are built with industry-standard server hardware running Solaris ZFS. These products represent commercial-grade solutions and are based on the Solaris ZFS technology (which is also available in OpenSolaris and can be used to build open storage solutions). The Sun 7000 series and Sun Fire Storage Servers are even more affordable than the Sun 6000 series. The affordability of these ZFS-based storage solutions has been highlighted as one of the key advantages of the Solaris operating environment. The Pillar Axiom is not likely to replace the Sun 7000, due to the significance of the 7000 products as part of the Solaris proposition.

The Sun 9000 series storage arrays are rebranded from the HDS USP V platform. The HDS USP V platform is also being resold by HP as the XP arrays. The main reason why Sun and HP resell the HDS USP V platform is mainframe support. Although Pillar considers the Axiom array an enterprise platform competing with other high-end arrays such as the HDS USP V, Axiom lacks support for mainframes. Hence, Sun-Oracle would not likely discontinue the 9000 series and replace its enterprise storage offering with Axiom.

Hence, in conclusion, Mr. Ellison will surely be facing conflicting interests between Pillar and Sun storage offerings. The convergence of Pillar and the existing Sun storage portfolio will not be an easy task. Given the fact that Sun’s 2500, 6000, and 9000 series are all rebranded products, and that Pillar Axiom is not a direct replacement for any of them, the only reasonable scenario would be converging the Pillar technology into Solaris. But, we question whether Mr. Ellison is likely to donate the Axiom controller code to the OpenSolaris community. Is it possible that the Sun-Oracle corporation will come up with a handsome budget to purchase the intellectual property from Pillar and utilize it for future Solaris-based storage solutions so as to avoid the conflicting interests of Mr. Ellision?

Oracle's Table Stakes in Hardware Game

With great fanfare, this week Oracle announced version 2 of its Exadata Database Machine, claiming it to be the world’s fastest for both data warehousing and online transaction processing (OLTP). Using terms like “quantum leap in performance,” “20x increase in random I/O,” “5x I/O bandwidth speedup’” the announcement webcast was big on superlatives but vague on apples-to-apples competitive comparison details. Soon, we hope, will appear the quantitative benchmark substantiation versus competitive offerings.  

Oracle’s initial Exadata hardware platform, labeled "HP Oracle Database Machine", employed HP ProLiant servers as compute and storage server nodes, running Oracle’s own Linux distribution. The new “Sun Oracle Database Machine” employs the same software, but switches to Sun Nehalem-based servers. The jump from Xeon 5400 in the HP edition to Xeon 5500 Nehalem in the v2 Sun version understandably yields substantial performance benefits, with Oracle claiming 80% faster processors and 200% faster memory, as well as faster disk throughput and networking.

In a significant enhancement, the Sun servers incorporate “FlashFire” flash storage cards (addressed as an extended memory not as disk to avoid disk controller limitations). With up to 56 flash cards per rack, each containing 96 GB, the over 5 TB of flash cache per rack, coupled with the nearly 1 TB DRAM per rack, allows for a very large in-memory database. Furthermore, Oracle claims that advanced Exadata compression allows 10-15X, even up to 50X, data compression to permit even larger databases to fully reside in memory.

Further details on the Sun Oracle Database Machine will be available in the next IDEAS TechTrends Monthly newsletter (free with registration).

Thanks to large in-memory databases, Oracle predicts that the Sun Oracle Database Machine will offer outstanding OLTP capabilities in addition to superior Data Warehousing performance. Naturally, we await benchmark substantiation. Oracle indicates it will demonstrate record-breaking 1TB TPC-H, which sounds entirely feasible given the huge “memory” of combined flash and DRAM. What’s less clear is whether Oracle plans to substantiate OLTP claims via TPC-C or TPC-E. 

Oracle emphasized that this announcement demonstrated the benefits of its pending acquisition of Sun. Admittedly, Sun has been a leader in adoption of flash memory, but it is not clear that Sun Nehalem servers offer substantive benefits over HP Nehalem servers, had version 2 been based on HP ProLiant instead of Sun boxes. Nonetheless, it does indicate that Oracle will continue to offer and support Sun x86 hardware, at least for the near term.

Note that Oracle has also issued statements that it plans to continue investment in SPARC and intends to set new TPC-C records.To be clear, Sun Oracle Database Machine is x86 and not SPARC. And, despite the advantages of flash memory, the Exadata Database Machine version 2 is unlikely to be the vehicle to challenge IBM’s 6 million TPC-C mark. Our speculation is that the promised TPC-C result to be unveiled at Oracle World will be measured on a cluster of Victoria Falls servers, likely a collection of Sun T5440

So why is Oracle so aggressive in claiming leadership performance with Sun hardware? It is understood that a major acquisition often endures lengthy regulatory scrutiny. Competitors typically seize upon the uncertainty to preach FUD and poach customers. To preserve the Sun base, Oracle needed to clarify its commitment to Sun hardware, and probably should have done so long ago. Admittedly, Sun and Oracle remain separate until the merger is approved and consummated. Still, the Sun Oracle Database Machine helps to confirm Oracle’s willingness to retain Sun’s hardware business. Reported benchmark results on Sun-based servers, be it TPC-H or TPC-C, will further demonstrate Oracle’s interest in promoting Sun platforms. We look forward to such benchmark results confirming the benefits of an integrated Oracle/Sun.