By: James Sessions JES Hardware Solutions

Phone (305) 597-3980 Internet: www.jessolutions.com

Introduction

Prior to 1980, minicomputers and mainframes dominated the business computing scene. These machines were designed using the concept that application and data be centralized, accessible to terminals with keyboards in decentralized locations over various communication mediums, none of which could qualify as a "network" by today's standards. Such design concepts were, understandably, limited by technology of the time and affordability.

Minicomputers and mainframes were expensive to own and maintain, not to mention complex. In order to justify the cost of ownership, the ability to amortize this enormous investment over a respectable number of users was mandatory. However, the added investment of terminals, keyboards, multiplexers and off-site printers became part of the total cost of ownership. The total investment was non-trivial but nevertheless offered enough corporate infrastructure productivity enhancement to justify the expense. That is, until microprocessors showed up in turn key microcomputers in early 1980 promising to change the landscape of small to mid-sized business computing forever.

Over the course of the next several years, what became known as the PC was finding its way onto corporate America's desktop by virtue of its productivity to affordability ratio. The inability of these new micro-computers to share data without the need for a minicomputer or mainframe became an issue to be reckoned with. Hence, courtesy of several innovative companies, "Network Operating Systems", or NOSes, began to appear either written for PC platforms or adapted to the PC as was the case for Unix, inclusive all derivatives thereof.

Within the context of "networking", emerging terminology ensued to classify various equipment by form, fit and function. A PC running a NOS was called a "server" because it served PC's running standalone OSes, called "clients", with applications and/or data. (Please note the definition of both a "server" and a "client" encompass hardware and software together). Largely unnoticed was an interesting phenomenon not recognized as significant at the time. This phenomenon became known as the decentralized application and data model (data and application need no longer reside on the same computer as in former times).

The Old Server Paradigm

Acceptance of networking as a viable medium for decentralized data and application processing in business has, over the past decade, given rise to ever increasing server responsibilities. As responsibilities have escalated, so too has the cost, complexity and manageability of servers. The result is a danger of coming full circle, back to the confining centralized data and application approach of old so diametrically opposed in today's distributed networks,

Distributed networking liberated us from an era in which centralized data and applications ran on mainframes and minicomputers that were expensive to own and maintain. Advances in microprocessor and ASIC technology, coupled with innovative interface topologies and standards initiatives, enabled systems manufacturers to develop and deploy relatively inexpensive general purpose servers with more and more horsepower over time. As a result, servers are capable of performing a myriad of tasks. In the face of this, a pervasive trend toward client centric networking is ushering in a new server paradigm (see figure1).

Figure 1

In today's network environment, some database and E-mail applications excepted, most users launch and run applications on their clients. As such, severs are quickly becoming massive repositories of shared information, shifting away from their traditional role of applications processing. Herein lies one of most significant challenges facing the next generation of server engines and the microprocessors powering them.

Servers today are based on microprocessors designed for application processing. Evidence attesting to this fact is the presence of additional function specific processors in server sub-systems. Servers, PC based or otherwise, are routinely built using add-in boards with embedded RISC processor engines controlling functions such as Ethernet and/or SCSI interfaces. Even as these embedded engines find their way down onto the motherboard, the principle reason for these inclusions is to unload the application processor from tasks it was not principally designed to perform, such as moving data. Up until now, manufacturing process technology had not advanced sufficiently for a new paradigm to take hold thus forcing the only available alternative, expanding upon the old paradigm by empowering the server with more and more responsibility. By taking advantage of current technology, the possibility now exists to embed most server functions into what JES engineers have defined as a "solution set" (a combination of hardware and software coupled together to perform a particular function or finite set of functions within highly integrated semiconductors).

Issues Driving a New Server Paradigm

• Servers are expensive. You thought you got a good deal with that "entry-level-server" until you shelled out for the missing hardware and software.

• With today's servers you learned the term "plug-and-play" really means "plug-and-pray."

• Installing or upgrading traditional server hardware and/or software requires a computer guru that is not included.

• Maintaining servers requires a separate line item in the budget.

• When the server is down nothing gets done.

• The solution costs ten times more than the problem and then stays with you like a ball and chain.

Enter the New Server Paradigm

For the same reason the trend toward client-centric networking has given rise to the NetPC initiative (a low cost, function specific, network PC proposal) the trend toward lower cost, function specific servers has begun. The essence of the new paradigm embodies the notion of extracting solution sets from the general purpose server and moving them to a more optimized environment. This allows for the most advantageous hardware and software architectures to be selected for processing these services and then embedding all the resultant parts into a chip, or chip sets, or an extensible small footprint printed circuit board. The level of integration depends chiefly on available process technology in several areas of fabrication described later.

Key to any intelligent embedded architecture is the processor core selected. For example, the NetPC thin client reference platform calls for a Pentium processor. Actually, any applications microprocessor could have been selected. In this case, since Microsoft's products are to be used in conjunction with this particular solution set, the Pentium was an obvious choice.

Under the new server paradigm, the solution set will be evaluated and may, or may not, use applications microprocessors. For example, moving data, the principle function of a file server, optimally requires an input/output processor tightly coupled with a realtime operating system, not an application processor with a scaled down version of a general purpose operating system.

JES Network Appliances

In order to bring about this new server paradigm JES Hardware Solutions has released a complete line of high speed network connected storage solutions. The simplest being a network attached hard drive and the most complex being a network connect RAID system. All systems will come with a Fast-Ethernet 10/100 RJ-45 interface. The SCSI interface will be ULTRA SCSI III running at 20MHZ and transferring at 40MB per second.

Direct Connect Hard Drive (DC)

The DC will be a four bay tower with the 10/100 network interface built into the tower. The tower will contain one hard drive of sizes 1G,2G ,4G ,9G and 23G. We will use 10,000 RPM drives where applicable. Users can expand the drive in the tower up to four. There will be a chainning connection to allow for the addition of chained towers.

The tower simply plugs into your existing network system. The device can be managed using a common web browser. Supported clients are WFW 3.11 with TCP/IP, Win95 and WinNT for SMB. UNIX workstations running NFS V2 and above.

Direct Connect Mirror (DM)

The DM will function the same as the Direct Connect Drive (DC). The difference is that there will be a second disk drive used for mirroring data. This is useful for when the primary drive fails and the mirror can take over until the failed drive can be replaced. Once the failed drive is replaced the mirror can be copied and again function as a mirror drive. The mirror software is build right into the direct connect controller and performance is not affected for this reason.

Direct Connect Tape/Jazz (DT)

The DT will be a tape or Jazz drive that can be hooked up to the computer network and can be used by all users to backup their data. This method is much easier than trying to hook up a tape or Jazz directly to a computer be it a server or workstation. All software will be contained on then device and backup is made simple. The back up speed will be much faster since it will be hooked up to a SCSI interface.

Direct Connect RAID (DR)

The DR will be a very fast RAID system that you can connect directly to your computer network . The system will be composed of a seven bay SCSI to SCSI RAID with two network connections. These two network connections will allow for much faster thruput on the network. The SCSI to SCSI RAID controller will control all of the RAID features and all levels of RAID storage. The system will allow for additional drives to be paced on the system without re-configuration. The drive system will be ULTRA SCSI III FAST WIDE. The SCSI to SCSI RAID controller will have four drive channels and two host channels (network connections). The four drive channels will reduce the number of drives serviced by each channel, thus increasing system performance. All hard disk drives will be hot swappable and hot spare option available. Each drive comes in its own separately powered drive canister. The need for redundant power supplies is therefore eliminated. The entire system will come pre-configured for level 5, however if you desire another level of RAID the system can be re-configured for that level.

Summary

JES network appliances is poised to address today’s basic network needs such as performance without high cost, "plug and play" simplicity, optimized design, self management with easy to understand options and no need for complex network operating systems. This coupled with the leveraging of a mature network topology makes the new network appliances a possible and best solution for network storage, backup and other well defined solutions sets.

As network appliances begin to enter the marketplace be ready to see E-Mail servers, Internet Servers, Print Spoolers, file servers and hand held network appliances.

© 1997, 1998, 1999, JES Hardware Solutions and , Inc. Coconut Grove, Fla. All Rights Reserved.