sparc article Tatung has sponsored this directory since 1997 sparc search

News about SPARC systems and related companies

2001, June week 1

Force Computers - CPCI-550
See also:- View from the Hill - Time for changes at the top in Sun?
Squeak! - The top 10 fastest growing storage companies in the US

current SPARC news, earlier SPARC news, Events, SPARC manufacturers, SPARC Product Directory
on other sites:- Solaris Central - news , SPARC-FLASH, SunFlash, STORAGEsearch - news
SPARC history:- June 2000, June 2001, June 2002, June 2003, June 2004, June 2005

click for more info

news about summary other news on this page
Lucent Technologies Bell Labs Internet traffic discovery could point the way to more efficient networks

MURRAY HILL, N.J. - JUNE 06, 2001 - A recent discovery by researchers at Bell Labs, the R&D arm of Lucent Technologies sheds new light on the nature of Internet traffic and could lead to more efficient routers and other network components. Using sophisticated new software programs to analyze and simulate data traffic in unprecedented detail, the researchers found that the "burstiness" seen in traffic at the edges of the Internet disappears at the core.

Their surprising discovery - that traffic on heavily loaded, high-capacity network links is unexpectedly regular - may point the way to more efficient system and network designs with better performance at lower cost. The Bell Labs research team of three statisticians and a computer scientist - Jin Cao, William Cleveland, Dong Lin, and Don Sun - analyzed billions of packets on an individual basis, the way equipment in the network sees them.

Packet traffic has long been characterized as bursty, fluctuating between extremes - from trickles of packets with large time intervals between them to floods of closely spaced packets. On local-area networks at the edges of the Internet, traffic does swing between such extremes, like local automobile traffic that can alternate rapidly between sparse and bumper-to-bumper conditions. For years, the industry has proceeded on the assumption that such behavior would be reflected and greatly magnified on higher-capacity links where traffic from many local tributary networks flows together. What the Bell Labs team found at the core of the Internet, however, is more like traffic on an ideal highway - a steady, high-speed stream that can be full to capacity with few serious delays.

The conventional wisdom would say that as both the capacity and the speed of Internet links increase, packet networks need to be engineered to accommodate ever greater rapid swings between low and high traffic loads, and Internet routers need ever larger packet buffers to accommodate increasingly variable queueing delays.

"But the burstiness that you can see in individual traffic flows vanishes in large aggregate streams of Internet traffic," said Sun. "The intermingling of packets from many different flows smooths out the aggregate traffic."

Traffic on a high-capacity link becomes more random, regular, smooth, and manageable when the numbers of users and simultaneous computer-to-computer connections go up. During their initial study, the research team assembled hundreds of gigabytes of packet traffic data from high-speed networks at Bell Labs and five universities, using a unique software system called S-Net for measurement and analysis. "S-Net is our statistical software microscope," Cleveland said, "which has enabled us to find patterns not seen before in studies using less precise data-viewing instruments."

Further research will be needed to fully explore the implications for Internet engineering, but the broad outlines seem clear: more efficient sizing of packet buffers, higher average utilization of link capacity, and greater flexibility in handling growth in Internet traffic. ...Lucent Technologies profile
Bell Labs Internet traffic discovery could point the way to more efficient networks

Avocent Announces Performance and Security Enhancements to DS1800(tm), a KVM OVER IP(tm) Solution for Server Management

GNP Continuant Cluster Suite™ Computing Environment Provides True Carrier Class System Availability for Telecom Switching Applications

Alstom Power Safeguards Critical Data with Resilience SPARC Servers

Force Introduces First Central Office-Standard SPARC/Solaris Dual-Segment compactPCI 12U System

Znyx Networks Announces First compactPCI Embedded Ethernet Switch Based on PICMG 2.16 Architecture

Raritan Computer and Lightwave Communications Join Forces to Provide Customers with the Most Complete Server Management Solutions

earlier news - archive
RAID systems on
Megabyte found that tying lots of barrels together to make his raft worked just as well as having a single huge one. And if one of the barrels got punctured, the raft didn't sink.

View from the Hill

Things to do during an eclipse of the Sun

During most of recorded history, astronomers believed that the Sun rotated around the Earth. The mathematician Copernicus (1473-1543) operating a hundred years before the invention of the telescope thought a better explanation was that the Earth actually revolved around the Sun. Teaching this theory got Galileo into a lot of trouble, in the early 17th century. This and other new ideas were part of the intellectual development we now call the Renaissance, in which great sceientists abandoned the received doctrines from classical antiquity, in those cases where their own experience and measurement suggested better theories.

In the SPARC systems market you could say we're in the Renaissance, where most people are quite comfortable with the idea that everything revolves around Sun Microsystems. So Sun's planned shut-down of operations during the first week in July, as a cost cutting measure designed to save jobs, could be the first time that people in this market get a chance to see other companies which are usually outshone by the strength of Sun's powerful marketing machine.

Just as the solar system would be a pretty dull place if you took away the planets, comets, and other stuff swirling around the center or the photons and other particles which are passing through, the same can be said of the markets for compatible products which revolve around Sun Microsystems.

If you were to take away the software which has been developed by thousands of independent software vendors which solve useful problems, or the specialised hardware developed by hundreds of independent manufacturers which let you use the operating system in more diverse physical situations, or connect to a wider range of external systems, the result would be a computer system which, while elegant, had little practical value except to computer scientists.

Sun has always known this, which is why it has invested in partnership programs, starting with the Catalyst in the 1980's, licensing the SPARC architecture via SPARC International in 1989, and more recently the Solaris Ready marketing programs. And let's not forget the resellers who historically have actually sold SPARC systems to more customers than Sun Microsystems. These thousands of partnerships have made the SPARC platform the powerful data factory it is today.

So, is the SPARC market going to screech to a grinding halt, while the people at Sun take an enforced sabbatical in July?

Are new Solaris product introductions going to wait in limbo for a week because they couldn't get the signoff from a marketing angel in Sun?

In the modern era of astronomy, we realise that the Sun is just one star in this galaxy. It's significant to us, beacuse we're close to it, but actually it's part of a much bigger system, we call the universe, which is drifting and may (or may not) be expanding. If you look at projections for the size of the computer market in as little as 3 years time, the segment which we currently call "storage" will be worth more than 10 times as much in annual revenue as Sun's entire revenue today...

Although people will still need servers and PC's they'll spend more on storage systems and a whole bunch of storage related networks and services which are still emerging from new companies. A recent press release from EMC, quoted research company Meta Group's estimate that storage-related costs will constitute up to 80 percent of server purchases through 2004 The gravitational effect from that all dark matter will change all parts of the computer market more strongly than any one company... even if that company is Sun, Intel or Microsoft.

Companies which still want to launch new products for the Sun compatible market in the first week in July should remember that during an eclipse, you can see halo effects clearer than at other times. Send your press releases here and you may find you can loosen that marketing umbilical cord more easily than you thought.

Disk Sanitizers
Disk Sanitizers on
Is it true that the Queen's apartments are
dusted clean by those bushy hats?
Megabyte was sworn to secrecy.
Squeak! - Animal Brands and Metaphors in the Storage Market
Squeak! - Animal Brands and Metaphors in the Storage Market
Animal marketing metaphors are popular in service industries, but you'd be surprised how many companies have used animals in their marketing of data storage products and services.

The storage market was worth over $150 billion in 2005, and as it gets bigger - more companies will turn to animal brands to help differentiate their otherwise bland products and lend them artificial (or deserving) characters and virtues.

The idea behind this type of marketing is to suggest positive connotations so it's unlikely that anyone will choose to associate their products with gremlins. But you may be surprised by the population of the storage ark.

This reference articles lists all known companies who have furry marketing brands, and also includes some which are slimy, scaly and scary too. the article, Mice in storage
Avocent Avocent Announces Performance and Security Enhancements to DS1800(tm), a KVM OVER IP(tm) Solution for Server Management

Huntsville, AL., June 6, 2001 – Avocent Corporation today announced it has made significant improvements to its DS1800 KVM over IP(tm) solution for server management. This system gives IT managers the unique ability to remotely access multiple racks of servers through an Ethernet connection, leveraging a company's existing investment in its network infrastructure.

Additionally, the DS1800 video processing and compression algorithms minimize the required network bandwidth to transmit keyboard, video, and mouse (KVM) signals. The DS1800 leverages industry standard DES encryption during transmission and provides virtually unlimited scalability along with an easy-to-use GUI interface.

Avocent's DS1800 is a KVM over IP server management solution that provides administrators complete access to virtually an unlimited number of servers or devices in their network, from any location. The DS1800 supports multi-platform environments, including Sun, USB and PS/2, and a variety of operating systems such as Windows 95, 98, NT, Windows 2000, Linux, NetWare and Solaris to name a few. Additionally, customer support is now available seven days a week, 24 hours a day. ...Avocent profile
GNP Computers GNP Continuant Cluster Suite™ Computing Environment Provides True Carrier Class System Availability for Telecom Switching Applications

MONROVIA, Calif. - June 5, 2001 - GNP Computers now offers Continuant Cluster Suite, a multi-node computer operating environment for use in telecommunications switching applications. Using GNP's patent-pending Natural Clustering Technology™ (NCT) - an ultra-reliable, virtual shared-memory programming model - the software delivers the 99.999 percent uptime required in a Central Office or other true carrier class networking environment. It provides fault detection/recovery, load sharing and management for multiprocessing systems that can contain heterogeneous processors.
NCT employs a software layer on top of the operating system of each installed computing node to implement fault detection/recovery and load sharing across the entire cluster. The application code running on each node has no dependency on the location or number of nodes running, providing true N + k mixed-mode support for multiple application architectures on the same system with natural scalability, augmenting system functionality. Simply put, adding more nodes within a cluster seamlessly provides more capacity that can be exploited for load sharing and for failure protection.

In operation, each computing node in the cluster can accommodate every failure mode typically encountered within a no-failover scenario. For example, in the event of failure of a server node, the remaining live system (either the master or its backup) assumes complete operational responsibility for executing transactions with its clients in a simplex mode while the failed system is rebooted and/or replaced and returned to service. In the event of a client node failure, all other functioning client nodes within the cluster automatically step in to share the processing load, without active intervention. In this case, when the sick client node returns to service, it automatically resumes its share of the processing load.

Such complete failure recovery also provides an ideal method for performing rolling upgrades of operating systems or applications software for server and client computing nodes within the Continuant Cluster Suite environment, without impacting service levels after installation in the field. Upgrades can be made node by node, and once completed the new node automatically rejoins the cluster to assume its designated role.
Target applications include softswitches, gateways and controllers for IP, wireless, optical and any other mission-critical network systems requiring true five-9's reliability, scalability and enhanced QOS (quality of service).

"The next generation platform for embedded telco applications is finally available," said Roger Baar, Ph.D., GNP's CEO and president. "We have responded to our customers' requirements for a computing environment that allows them to integrate Commercial-Off-The-Shelf (COTS) products into a continuously available system. Unfortunately, true five-9's availability is hard to achieve using standard computer industry systems and elements, which has kept the cost and availability of such computing systems out of reach for general network use so far. Our new Continuant Cluster Suite operating environment uses NCT to overcome traditional COTS limitations and deliver an affordable, scalable solution for a variety of network switching and management applications. Continuant is fundamentally - more robust than the conventional fail-over approaches, which have difficulty realizing true five-9s availability when the combined effects hardware outages, software failures and OA&M (Operations, Administration and Maintenance) are included."

GNP's Continuant Cluster Suite supports a wide mix of hardware, including all CompactPCI® platforms based on Intel, Motorola, or Sun processors and all Netra computing systems; as well as a range of server/enterprise and workstation systems. These computing nodes may be running any mixture of Solaris or Linux operating systems, and executing application code written in C, C++, Java or Prolog languages. This ability to work in heterogeneous environments is an important design consideration in supporting COTS elements, since the long deployment life of a telecommunications system usually spans multiple COTS generations. Therefore, it is desirable or even necessary to have several versions of processors, operating systems or other system elements co-existing as the equipment undergoes expansion and receives FRU replacements and upgrades.

The cost of the GNP Continuant Cluster Suite operating environment begins at approximately $9000, depending on the number and type of computing nodes supported. GNP offers a complete range of consulting services to support Continuant Cluster Suite, including those for architectural definition, porting of existing applications, and new software development. ...GNP Computers profile
Resilience Alstom Power Safeguards Critical Data with Resilience SPARC Servers

Sunnyvale, CA - June 5, 2001 — Resilience Corporation today announced that ALSTOM Power, a division of ALSTOM S.A. , the global specialist in transport infrastructure and energy, has deployed Resilience SPARC-based fault-tolerant Continuous Availability Systems to secure the company's sensitive data.

ALSTOM was looking for a reliable, yet cost-effective way to update and protect its firewall from downtime," said Richard Mekolichick, IT Network Manager for ALSTOM Power. "Our Resilience systems are significantly more affordable to administer and have been up and running, without a glitch since installation."

"Data integrity and availability are two important functions where reliability can not be left to chance," said Denny Olmsted, Resilience president and CEO. "Resilience servers provide the continuous uptime and ease of administration that more and more companies are looking for in a firewall application."

Dataline Inc., a computer systems integration firm, provided the Resilience solution to ALSTOM. ...Resilience profile
Force Introduces First Central Office-Standard SPARC/Solaris Dual-Segment compactPCI 12U System

SUPERCOMM 2001, ATLANTA - June 5, 2001 —
Force Computers today at the SUPERCOMM 2001 trade show introduces the Centellis™ CO 16543-12U platform, the first embedded system to exceed the requirements of major telecommunications carriers for telecom-standard SPARC®/Solaris® technology in a Network Equipment Building System (NEBS) Level 3, 12U design for Central Office (CO) deployment.
The Centellis CO 16543-12U system adheres to the PICMG 2.9 specification for system management functionality (IPMI compliance) by offering a telecom alarm module (TAM) for system environmental monitoring and management. Other major features of the Centellis CO 16543-12U platform include:
  • UltraSPARC-IIi 440MHz processor-based single board computer (SBC)
  • 256MBytes onboard memory (option to 1GByte)
  • Redundant N+1 hot-swappable 500W DC power supplies and fan trays
  • Hot-swappable media bay accommodating up to four 3.5-inch devices
  • Four serial, two Ultra2 SCSI and three onboard 10/100 Ethernet interfaces
  • factory-installed Solaris 8 operating system
More I/O functionality is available via the IO-70 rear transition board that provides two PCI mezzanine card (PMC) option slots, four 10/100 Ethernet interfaces and one Ultra2 SCSI interface.
The latest of Force's NEBS building-block systems with FaultZone Technology™, the Centellis CO 16543-12U platform leverages legacy communications equipment investments with its implementation on CO-standard SPARC/Solaris technology. With 16 CompactPCI® slots—14 of which support the H.110 bus—the Centellis CO 16543-12U system provides one of the highest density I/O capabilities in a 12U chassis. This makes it an ideal solution for interactive voice response (IVR), unified messaging and other computer telephony integration (CTI) applications for use with products from Force's "Running with Force" third-party partners such as NMS Communications.

"Leveraging Force's expertise as the only major processor/OS-independent designer and developer of embedded systems for the telecommunications industry, the Centellis CO 16543-12U platform offers the small footprint, high-density I/O capability and SPARC/Solaris technology major telcos require in all Central Office equipment," said Dave Berry, Force product manager. "By incorporating Force's own FaultZone Technology, this platform will test to NEBS Level 3 criteria. And single-segment backplane solutions can't hope to match its high-density I/O capability."

Force will demonstrate the Centellis CO 16543-12U platform at SUPERCOMM 2001, June 5-7, Georgia World Congress Center, East Hall, Booth 3150.

The Centellis CO 16543-12U platform is available immediately through Force's Early Access Unit (EAU) program with volume shipments scheduled for August 2001. Prices start at approximately US$19,000. ...Force Computers profile
Znyx Networks Znyx Networks Announces First compactPCI Embedded Ethernet Switch Based on PICMG 2.16 Architecture

Atlanta, Georgia. World Congress Center, June 4, 2001 - ZNYX Networks today announced the first CompactPCI® embedded Ethernet switch designed to support the upcoming PICMG 2.16 specification for packet-switched backplanes (CPSB). ZNYX Networks' ZX4300P is the first Layer 2 Ethernet switch to seamlessly support operation in both standard CompactPCI chassis and the fabric slots of chassis designed to support the upcoming PICMG 2.16 CPSB specification. Several rear transition modules are available to support 5 through 24 10/100 egress ports, depending upon the chassis architecture.

Other features of the ZX4300P include non-blocking line-rate switching performance, HotSwap capabilities, 802.3x and back-pressure flow control. The switch integrates easily with any host operating system, and supports Intel x86, Sun SPARC, and Motorola PowerPC host CPUs. ...Znyx profile
Lightwave Communications

Raritan Computer
Raritan Computer and Lightwave Communications Join Forces to Provide Customers with the Most Complete Server Management Solutions

Somerset, NJ - Milford, CT - June 4, 2001- Raritan Computer and Lightwave Communications today announced the formation of a corporate alliance designed to develop and offer a complete and complementary line of server access and management products. Raritan and Lightwave will collaborate on product development to provide integration across both companies' product lines.

As a first step, both companies will immediately implement product enhancements so that all serial devices controlled by Lightwave's ConsoleServer serial products are automatically recognized by Raritan's award-winning Cat5-based KVM switching system, Paragon. Consequently, all GUI systems and ASCII systems will be controlled directly from a single enhanced Paragon on-screen menu.

"Our goal is to develop a comprehensive line of complementary products that combine seamlessly to give our customers feature rich, efficient, and reliable solutions to their server access and management needs", states David Cheever, President of Lightwave. ...Lightwave Communications profile, ...Raritan Computer profile

current SPARC news

click for more info
SPARC History (from 1987 till last month) STORAGEsearch SPARC Product Directory ACSL - the publisher

SPARC(R) is a registered trademark of SPARC International, Inc. SPARC PRODUCT DIRECTORY(SM) is a service mark of SPARC International, Inc used under license by ACSL. Products using the SPARC trademarks are based on an architecture developed by Sun Microsystems, Inc.