Data Center Exposure and Recovery in New York City

Data Center Exposure and Recovery in New York City

Hurricane Sandy provided a fascinating opportunity to study the both the level of disaster planning and the resilience of New York City data centers. This article will examine a) what actually happened, b) what was the risk, and c) what are the lessons learned.

What Actually Happened?

Simply put, data centers in New York were caught off guard. Consider these incidents.

Internap and Peer 1, located at 75 Broad Street, suffered basement-level flooding which knocked out diesel fuel pumps.

 

Datagram, located at 33 Whitehall, experienced the exact same problem – 5 feet of water in the basement. As a result several high profile blogs and numerous websites went dark.hurricane-sandy

Both of these facilities are located a Zone A flood zone. Zone A is FEMA’s second highest risk category.

Then there were fuel supply issues. Fog Creek who makes and hosts Trello, Copilot and other popular platforms is in Peer 1 had to assemble a bucket brigade to carry diesel fuel up 17 stories to refuel a generator at Peer 1. As a precaution Trello was moved to Amazon Web Services and it seems to have suffered limited downtime, but the bucket brigade was required.

Shoretel, the VoIP provider, had 3 data centers – all in lower Manhattan, including 75 Broad St which did successfully switch over to generator power but due to “city restrictions” they had shut the generators down. 700 customers went down.

Fortunately, things did not get worse for Fog Creek, but carrying 5 gallon buckets of diesel fuel up 17 stories in a building with power problems strikes us as a recipe for something truly horrible.

 

squarespace-75broad-bucketTeams from Squarespace fill buckets with diesel fuel to haul them up 17 stories to the generator keeping the data center online. Staff from Peer 1, Squarespace and Fog Creek Software have formed this unusual Internet bucket brigade. (Photo via Squarespace)

A typical rack of servers requires 5 to 10 KW of power including cooling/HVAC. Typical data centers range in size from 5,000 to 40,000 square feet. A mid-sized facility at 20,000 SqFt would house about 600 racks. That equates to roughly 5 megawatts (MW) of power. A reasonably efficient diesel generator would require roughly 200 gallons of diesel per hour to push out 5 megawatts – that’s a bit over 3 gallons per minute.

Typically data centers tell us they have 1 week of diesel onsite and a resupply contract. A full week for a 20,000 SqFt data center is 34,000 gallons. We suspect that in lower Manhattan, the standard was more like 1 day. Then resupply problems hit because of the street flooding, and road and bridge closures.

 

What was the Risk?

The Mid-Atlantic States do not see nearly as many hurricanes as the Southeast and the Gulf Coast of the United States. The average return period for hurricanes within 50 miles of New York City is 18 to 19 years.

For the largest part of Hurricane season the Typical Hurricane Tracks, as observed by NOAA, take these storms out to see at the more northern latitudes of the NYC area.

Here are the July, August and September typical tracks:

july-hurricane-track

august-hurricane-track

september-hurricane-track

But look at how this changes in October:

october-hurricane-track

 

And notice how closely Hurricane Sandy lined up with the typical October track.

hurricane-sandy-track

 

Finally, what about the frequency of storm origin in October? Compare below the frequency map for August 21 – 31 origin, which is the peak of Hurricane Season, to the October 11 – 20 origin map below:

august_21_31_origins

october_21_31__origins

You can see that activity is less in October, but it’s hardly dormant as it is a few weeks later:

november_21_30__origins

Just as August and September are the periods of greatest risk in the Southeast and the Gulf Coast, October clearly presents the greatest risk of hurricanes in NYC.

What is the solution?

If these providers had built to the following standards, downtime would have been minimized:

  • One week of fuel for standby power onsite
  • Resupply plan for fuel in place – or
  • A redundant or backup site more than several hundred miles away

For any disaster recovery, hosting or colocation solution, we would look to the Uptime Institute who publishes the Data Center Site Infrastructure Tier Standard for Operational Sustainability.

Based on their standard, we’d offer the following. Red indicates higher risk profile of Lower Manhattan.

Disaster Risk Component Higher Risk Lower Risk
Flooding and Tsunami < 100 Year Flood Plain > 100 Year Flood Plain
Hurricanes and Tornadoes High Medium
Seismic Activity Zone 3 or 4 Zone 2A or 2B
Airport/Military Airfield < 3 miles from active runway > 3 miles from active runway
Adjacent Properties Chemical plant, etc. Office buildings, land
Transportation Corridors < 1 mile > 1 mile

 

To review your site’s risk of various natural disasters, see our Natural Disaster Risk Maps.

 

Disaster Recovery as a Service

Hurricane Impact Assessment: Isaac in New Orleans

Hurricane Impact Assessment: Isaac in New Orleans

Now that Hurricane Isaac is in our rear-view mirror, it’s time to assess the disaster damage. We monitored and shared the New Orleans power outages on Global Data Vault blog day-by-day, but we censored the wrath pointed at local energy provider Entergy to return the city’s electricity. As you can see from the time lapse video here, new-orleans-power-outages-1208311   the progress was slow (as tensions built) in the beginning, but by the 5th, major headway was made and tempers were calmed. Poor Entergy though, they just couldn’t get a break. Problems with an electrical substation knocked out power to about 11,000 customers in the Central Business District, Mid-City and Uptown a few days post recovery which no doubt added fuel to the fire. The good news – if there is good news after a hurricane — is that Officials with the National Weather Service said that their modeling of hurricanes before and after the improvements in New Orleans show no evidence that they led to increased flooding in the River Parishes. The great news is that the levees held. That’s a key accomplishment for Mayor Mitch Landrieu and a credit to his leadership over the past several years. However, we cannot forget that Isaac was only a category 1 hurricane. Katrina (2005) was a 3 hurricane when it came ashore. Here is a list of storms that reached Category 5 in the past ten years:
Storm Season Time as Cat 5 Peak wind speed
Isabel 2003 42 hours 165 mph
Ivan 2004 60 hours 165 mph
Emily 2005 6 hours 160 mph
Katrina 2005 18 hours 175 mph
Rita 2005 24 hours 180 mph
Wilma 2005 18 hours 185 mph
Dean 2007 24 hours 175 mph
Felix 2007 24 hours 175 mph
  The bad news is that Isaac was a hefty beast. His footprint was wide and like many who visit New Orleans for the first time, he just didn’t want to leave. Isaac became a slow-moving hurricane that pelted the city for far too long. Its lingering effects pushed more water into Lake Pontchartrain and Lake Maurepas and the swamps below them, which brought worse flooding to the areas than anyone expected. It will be some time before the actual bill from Isaac is totaled. Between the extra expenses and lost revenue, the city is reeling from yet another blow to its tightly stretched budget. Overtime for emergency responders and lost hotel taxes are easy to calculate, lost wages from city agencies, retailers, and those who scrapped their Labor Day plans for the Southern Decadence Festival are much more difficult to estimate. Many businesses were unable to operate for a full week without power, internet connectivity and access to their IT systems. Hurricanes have the potential to decimate a city and the businesses within it completely, but with pre-planning and a solid disaster recovery system in place, it doesn’t have to. Global Data Vault assisted a large number of customers through this recent storm. These businesses were back in business quickly. We’re happy that our customers weren’t significant victims of Hurricane Isaac.
Disaster Planning – Pacific Coast Tsunami Preparations

Disaster Planning – Pacific Coast Tsunami Preparations

The Cascadia subduction zone is a 600-mile-long offshore earthquake fault that runs from northern California to southern British Columbia. And that fault has a serious tale to tell. Geologists have found sand deposits up and down the Pacific coast along this zone, the result of a tsunami a little over 300 years ago.

Three hundred years is a long time and that bit of trivia in and of itself may not seem threatening, but pair it with what scientists now know about earthquake patterns, and the Pacific Northwest Coasters should be trembling in fear – or at least preparing for an impending disaster in the very near future.

“I think all subduction zones are guilty until proven otherwise,” Dr. Kerry Sieh told National Geographic in their February 2012 issue. Sieh, director of the Earth Observatory at Singapore’s Nanyang Technological University, is one of the world’s leading paleoseismologist. He spends his days obsessing over geologic records for evidence of ancient earthquakes and tsunamis, and identifies what he calls, “supercycles” or clusters of big earthquakes that occur at regular and predictable intervals. (more…)

Predicting Natural Disasters – Earthquakes and Tsunamis

Predicting Natural Disasters – Earthquakes and Tsunamis

Tsunamis are arguably one of the most devastating and difficult to predict natural disasters. Evidence of this is the 2004 Indian Ocean tsunami which is considered among the deadliest in human history, credited with more than 230,000 people killed in 14 countries bordering the Indian Ocean.

tsunami-9227937_sWhile the science is nowhere near exact, researchers are closely examining vulnerable areas of the world based on the theory that history does and will repeat itself. They have found what they refer to as “supercycles,” or clusters of big earthquakes occurring at regular intervals. It’s these underwater earthquakes that have the potential to create tsunamis of epic proportions.

Leading the supercycles charge is Dr. Kerry Sieh, currently serving as director of the Earth Observatory at Singapore’s Nanyang Technological University. Sieh is one of the world’s leading paleoseismologists studying earthquake patterns. He and his team have discovered that for at least the past 700 years, pairs of large earthquakes have occurred about every 200 years on a segment of the Sunda megathrust, a fault extending 3,300 miles from the southwestern side of Sumatra to the south of Java and Bali and ending near Australia. The earthquakes in each pair were separated by roughly 30 years. Sieh found there had been a pair of quakes around years 1350 and 1380, another pair in the early to mid 1600s, and a third pair n 1797 and 1833. (more…)

Extreme weather patterns prompt new business continuity policies

Extreme weather patterns prompt new business continuity policies

While people continue to debate the merits of global warming and its impact on their everyday lives, researchers are far more confident about the prospect of more intense heat waves, heavy downpours, earthquakes and even volcanic eruptions in our near future.extreme-weather-11268376_s-450x300

But no matter which side of the fence you’re on, the Washington Post reported last week that the new analysis also speaks to a broader trend: The world is facing a new reality of more extreme weather, and policymakers and businesses alike are beginning to adjust.

All the hullabaloo about global warming came to the forefront again when a recent special report was released on the human impact of extreme weather events by the Intergovernmental Panel on Climate Change (IPCC). The very detailed report talks of the correlation between global temperatures and the impact on everything from wind patterns to earthquakes. The IPCC warns for better civic planning as we should expect more of the same weather-related disasters experienced in 2011. (see our previously Top 10 Natural Disasters 2011) The concern is that these crazy weather extremes will overwhelm their target locations, making them unlivable.

Unlivable is one thing, another is how the businesses within those communities can be resilient after an unexpected natural disaster. A September 2011 study by Climate South West stated that 63% of businesses surveyed have taken some kind of action to prepare for extreme weather. Of the study respondents, most (76%) of the largest businesses have created or improved their Business Continuity Plan, compared to only 8% of the smallest businesses. Many larger businesses have also reviewed their health and safety procedures and/or sought advice on the issue.

At Global Data Vault, our daily focus is planning for disaster. But we know that it’s not something that most companies address as nearly as frequently. So we’re curious, has your company taken any new measures to protect against the impact of extreme weather on business continuity and data security?