Resultados 1 a 4 de 4
  1. #1
    WHT-BR Top Member
    Data de Ingresso
    Dec 2010
    Posts
    17,329

    [EN] Server uptime: 24 anos

    Booted up in 1993, time is running out on a server that never had an unplanned downtime.

    Patrick Thibodeau
    Jan 28, 2017


    In 1993, President Bill Clinton was in the first year of his presidency, Windows NT 3.1 and Jurassic Park were both released, the North American Free Trade Agreement (NAFTA) was signed, and Phil Hogan, an IT application architect, booted up a brand-new Stratus Technologies fault tolerant server.

    A lot has changed in 24 years, but one thing hasn't: The Stratus server is still in operation and Hogan -- who works at steel products maker Great Lakes Works EGL in Dearborn Mich. -- continues to keep it that way.

    This is a fault tolerant server, which means that hardware components are redundant. Over the years, disk drives, power supplies and some other components have been replaced but Hogan estimates that close to 80% of the system is original.

    "It never shut down on its own because of a fault it couldn't handle," said Hogan. "I can't even think of an instance where we had an unplanned shutdown," he said.

    This is a famous server. In 2010 Stratus held a contest to identify one of its servers that had been running the longest. Hogan's then 17-year-old server was the winner. (At the time of the 2010 contest, the firm was known as Double Eagle Steel Coating Co.)

    This system runs an older version Stratus proprietary VOS operating system, which Hogan believes hasn't been updated since the early 2000s. "It's been extremely stable,' he said.

    His company doesn't have a maintenance contract with Stratus, and Hogan has been able to buy parts from a third-party vendor. Still, Stratus says it probably still has parts for it in stock.

    This server had been eyed for an upgrade over the years but ownership or business cycle changes interrupted or derailed plans. It also helped that the users weren't complaining.

    Even though the system has a character-driven interface, similar to an old green screen system, the users "like the reliability of it, and the screens are actually pretty simple," said Hogan.

    Jason Andersen, the vice president of business line management at Stratus, said the systems they produce "are totally redundant in every way shape or form."

    Since the 2010 server longevity contest, Andersen said Stratus has learned of other 20-year-old-plus systems but it's possible that the server at Great Lakes Works may still be the oldest.

    Stratus fault tolerant systems are used in payment processing, telecommunications, and credit card processing, as well as in manufacturing, energy and natural resources among other industry verticals, said Andersen. Stratus builds systems that support Windows, Linux, VMware and VOS.

    But the end is nearing for Hogan's server. Great Lakes Works is now part of United States Steel Corp., in a deal completed in 2015. There is now a plan to upgrade the system in April. At that point the Stratus will be retired.

    When the hardware is finally turned off, it might deliver a moment for Hogan. Maybe it will be akin to the feeling of getting rid of an old and faithful car. But the only person who will really know what the server has accomplished in its long life is the person who kept it running.

    http://www.computerworld.com/article...ch-longer.html

  2. #2
    WHT-BR Top Member
    Data de Ingresso
    Jul 2011
    Posts
    1,156
    Se é um sistema não conectado e que não tem usuários privilegiados x não privilegiados, OK... senão...

  3. #3
    WHT-BR Top Member
    Data de Ingresso
    Dec 2010
    Posts
    17,329
    Citação Postado originalmente por rubensk Ver Post
    Se é um sistema não conectado e que não tem usuários privilegiados x não privilegiados, OK... senão...
    Pelo que entendi, é um servidor usado em processo/automação industrial. Deve operar dentro de um gabinete que resiste de poeira à ataques nucleares. Quem era o dono desse campinho no Brasil era a Digital.

    Pelo que conta a lenda, os equipamentos das operadoras também são do tipo diehard, não são encontrados nas Casas Bahia.
    Última edição por 5ms; 01-02-2017 às 19:18.

  4. #4
    WHT-BR Top Member
    Data de Ingresso
    Dec 2010
    Posts
    17,329

    Asetek Achieves 200 Million Hours of Fault-Free Pump Operations at DataCenters

    With over 3.5 million units deployed worldwide in desktop PCs and servers, Asetek pumps have run fault-free for the equivalent of 22,000 years.

    February 1, 2017

    Today Asetek announced that its server pump has achieved 200 million hours of reliable operation in real world use. Installed at end-user locations as diverse as Singapore and Norway,

    “To date, we have not had a single server pump failure at any of our data center installations around the world,” said Mette Nørmølle, Vice President of Engineering. “Our low-pressure architecture is the key to enabling a cost-effective solution that is relied on by data centers demanding unrivaled performance and maximum uptime.”


    At the heart of Asetek liquid cooling is the Direct-to-Chip (D2C) CPU Cooler. The CPU Cooler is a patented integrated pump and cold plate assembly used to cool server CPUs. Because a single pump has sufficient power to circulate cooling water in a server node, servers with more than one CPU have multiple pumps, providing built in redundancy.

    With over 3.5 million units deployed worldwide in desktop PCs and servers, Asetek’s cooler pumps incorporate features designed to meet our customers’ strict demands for reliability, performance and uptime. Pumps are mechanically sealed with the impeller, the only moving part, suspended in lubricating cooling liquid. As a result, high reliability and low cost are both inherent in the pump design.

    Asetek’s reliable data center solutions include RackCDU D2C and Server Level Sealed Loop (ServerLSL). RackCDU D2C provides cooling energy savings greater than 50% and density increases of 2.5x-5x. ServerLSL provides liquid assisted air cooling for server nodes, replacing less efficient air coolers and enabling the servers to incorporate the highest performing CPUs and GPUs.

    http://insidehpc.com/2017/02/asetek-...s-datacenters/

Permissões de Postagem

  • Você não pode iniciar novos tópicos
  • Você não pode enviar respostas
  • Você não pode enviar anexos
  • Você não pode editar suas mensagens
  •