The phenomenon on display in the Facebook search result screenshots is known in technology circles as a “data void”, after a paper by the Data & Society founder and researcher danah boyd. For certain search terms, boyd explains, “the available relevant data is limited, non-existent, or deeply problematic”.

In the case of vaccines, the fact that scientists and doctors are not producing a steady stream of new digital content about settled science has left a void for conspiracy theorists and fraudsters to fill with fear-mongering propaganda and misinformation. [...]

Pinterest has responded by building a “blacklist” of “polluted” search terms.

“We are doing our best to remove bad content, but we know that there is bad content that we haven’t gotten to yet,” explained Ifeoma Ozoma, a public policy and social impact manager at Pinterest. “We don’t want to surface that with search terms like ‘cancer cure’ or ‘suicide’. We’re hoping that we can move from breaking the site to surfacing only good content. Until then, this is preferable.”

I went into one of the instances and quickly did an iptables DROP on all packets coming from the other two instances.  This would simulate an availability zone continuing to function, but that zone losing network connectivity to the other availability zones.  What I saw was that the two other instances noticed the first server “going away”, but they continued to function as they still saw a majority (66%).  More interestingly the first instance noticed the other two servers “going away”, dropping the ensemble availability to 33%.  This caused the first server to stop serving requests to clients (not only writes, but also reads).

ZooKeeper, while tolerant against single node failures, doesn't react well to long partitioning events. For us, it's vastly more important that we maintain an available registry than a necessarily consistent registry. If us-east-1d sees 23 nodes, and us-east-1c sees 22 nodes for a little bit, that's OK with us.

Today we’re open sourcing Secor, a zero data loss log persistence service whose initial use case was to save logs produced by our monetization pipeline. Secor persists Kafka logs to long-term storage such as Amazon S3. It’s not affected by S3’s weak eventual consistency model, incurs no data loss, scales horizontally, and optionally partitions data based on date.

a [Cassandra-style] Cluster Management Algorithm is a SPOF. If there’s a bug it impacts every node. This took them down 4 times.