It is amazing how there can single points of failure in data centers even though they were sold as highly available designs. Some make the mistake that just because it hasn't failed in the past and a lot of money was paid, failure is unlikely.

My dad was a civil engineer with CalTrans (California's Department of Transportation) Bridge Division which includes overpasses (CA has way more overpasses than bridges), so whenever I read about civil engineering stuff it reminds of a possible conversation with my Dad. Unfortunately, my dad died of colon cancer 19 years ago, so I need imagine the conversations.

In the state of Washington the I-5 has an outage, a bridge has collapsed when a truck's load hit the structure.

What is the cause of the bridge collapse, an outage of Interstate I-5 between Seattle and Vancouver, BC? One hit from a truck and it collapses? Sounds like a Jenga design. Knock out this one block and the whole thing falls.

Here is a view from Google maps of what the bridge used to look like before the collapse.

The WSJ has an answer to the outage. A single point of failure. The lack of redundancy in the design.

"This is not the sign of deteriorating infrastructure, this is a sign of vulnerable infrastructure," said Abolhassan Astaneh-Asl, a civil-engineering professor at the University of California, Berkeley.

"This original design in those days was fine," he said of bridges lacking redundancy, "but today we should invest in getting these…out of the system."

...

The bridge has what is known as a "fracture-critical" design, which means that if any part fails, the whole bridge could fail, said Mr. Astaneh-Asl. "A fracture critical bridge is like a chain," he said. "Any link in this chain you cut, it's going to fail."