Want to read Slashdot from your mobile device? Point it at m.slashdot.org and keep reading!

 



Forgot your password?
typodupeerror
×
Data Storage Hardware

How Data Center Operator IPR Survived Sandy 50

Nerval's Lobster writes "At the end of October, Hurricane Sandy struck the eastern seaboard of the United States, leaving massive amounts of property damage in its wake. Data center operators in Sandy's path were forced to take extreme measures to keep their systems up and running. While flooding and winds knocked some of them out of commission, others managed to keep their infrastructure online until the crisis passed. In our previous interview, we spoke with CoreSite, a Manhattan-based data center that endured even as much of New York City went without power. For this installment, Slashdot Datacenter sat down with executives from IPR, which operates two data centers—in Wilmington, Delaware and Reading, Pennsylvania—close to Sandy's track as it made landfall over New Jersey and pushed northwest."
This discussion has been archived. No new comments can be posted.

How Data Center Operator IPR Survived Sandy

Comments Filter:
  • Re:tl;dr version (Score:4, Informative)

    by kiite ( 1700846 ) on Monday November 19, 2012 @04:20PM (#42030931)

    Right. And, according to TFA, none of their supplies ever went out. I live in NYC. A lot of the city lost power, sure. The transit system was knocked out, sure. There was a lot of flooding in fringe areas, where most data centers weren't. This guy is talking about NYC like it got demolished by the storm. Slashdot already did a piece on how a NYC data center mitigated power loss; reading TFS, I was hoping for a point of view from a more heavily battered standpoint. Instead, I got, "We had back-ups, and we think they work because we test them regularly, but we didn't actually have to do anything."

  • Re:PPPPP (Score:5, Informative)

    by jesseck ( 942036 ) on Monday November 19, 2012 @04:33PM (#42031087)
    I remember seeing this in the past... but we used the 7 P's: "Proper Prior Planning Prevents Piss-Poor Performance"
  • Re:tl;dr version (Score:5, Informative)

    by Rich0 ( 548339 ) on Monday November 19, 2012 @04:49PM (#42031241) Homepage

    Yeah, Reading PA. Go look it up on a map. They weren't going to be having multiple substation outages that far inland. My own workplace didn't lose power and is about 20 miles further East. It doesn't hurt that they're about 200 yards from a substation and that both the substation and the plant site are fed by transmission lines on steel towards that stand WAY above the height of nearby trees.

    Most of the outages for Sandy were due to flooding or downed trees. The former was only a problem along the coast or near rivers, and really a big problem for NYC where they have transmission equipment underground. Trees are horrible for the last mile of power delivery, but aren't an issue for the major substations, since if you drive by one of them you'll note that the transmission lines are WAY up in the air, and the trees are trimmed back a huge distance on either side of them anyway. The towers themselves are steel and on concrete foundations - they're not going to fall unless they're hit by something like a tornado.

    The reason so many lost power wasn't because of transmission being cut, but by a bazillion downed trees taking out every other telephone pole in the region. If you want an IT analogy imagine if all your big network feeds and datacenter are intact, but some vandal walks around your building and sticks a firecracker next to every single network port.

    For an inland location like Reading PA, this was just a matter of having either good power connectivity, or generators. Wilmington is next to the Delaware Bay and would be at more risk, but as long as you're at reasonable elevation and above-ground you'd be fine.

And it should be the law: If you use the word `paradigm' without knowing what the dictionary says it means, you go to jail. No exceptions. -- David Jones

Working...