News for hackers. Stuff that matters.

A comment on Google Compute Engine Incident #16015. Parent comment

Re:Google Compute Engine Incident #16015 by lima on Tuesday August 09, 2016 @11:39AM (#12255330)
Their post-mortem states that only traffic for protocols other than TCP and UDP was dropped. Does your monitoring take this into account?

It states "1.67 hours" of downtime, which is not the same as increased latency due to sub-optimal routing.

[ Parent | on HN ]
Re:Google Compute Engine Incident #16015 by jread on Tuesday August 09, 2016 @11:56AM (#12255451)
Our outages were triggered as a result of ICMP timeouts.
[ Parent | on HN ]
Re:Google Compute Engine Incident #16015 by lima on Tuesday August 09, 2016 @12:42PM (#12255857)
In this case it would be fair to note that this outage did not affect all connectivity (web traffic would be unaffected while ICMP were blocked).
[ Parent | on HN ]