Hacker News Reader

Comment by nonbirithm | Hacker News Reader

It makes me wonder if it has anything to do with GCP. Pure speculation, but if it's in the cloud then they probably wouldn't hesitate to dogfood their own platform. But then it would be interesting since search still works. Maybe search was too high-value to risk having a hard dependency on whatever it is that is causing the outage.

View on HN

Google has an internal cloud that they talk about sometimes. Borg, bigtable, spanner, etc. They run all their services on their internal cloud, including their public cloud, with the exception of Compute Engine, which is its own thing.

Compute Engine isn't really a separate thing so much as it's another thing built on the same infra. All the way down to the individual VMs, it runs on Google's production infrastructure and is scheduled by Borg (onto dedicated machine pools, although that sort of dedicated resource pooling is not unique to GCE). Once you get into VM networking things get a bit more exotic, although all of that still runs atop the same software defined network infrastructure as everything else (but, much like with Borg, it uses more features than many workloads at Google).

(I work on Compute Engine's virtualization infrastructure)

Thanks for the clarification! I had heard that Compute Engine ran on dedicated machines, but was under the impression that approach was unique to GCE.

There was interruption between GCP's monitoring & services on GCP. I also have my own Prometheus/Grafana stack in there and it kept chugging along fine, even though their DB graphs show severe dips in tx/sec in the time period in question.

Reply on news.ycombinator.com