Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Most famously, Siri (used to?) run on a very large scale Mesos deployment (10000s of nodes, much higher than Kubernetes can scale to).

Unfortunately the original article is lost, but here's a summary: https://daringfireball.net/linked/2015/04/29/siri-apache-mes...



Wayback Machine has it[1], but there's not much more content than in Gruber's summary.

[1] https://web.archive.org/web/20150429225603/https://mesospher...


OK but what was the utilization? I'm not really sure K8s is state-of-the-art either. There are published research papers about very-large-scale clusters with 80%+ resource utilization.


In our production experience, utilization had far more to do with the service owners (or autoscalers/auto-tuners) correctly choosing the cgroups and CPU scheduler allocations, as well as the kernel settings for cgroup slicing and CPU scheduler. We had Mesos clusters with 3% utilization and have Kubernetes clusters with 95%+ utilization. But we also have Kubernetes clusters with <10% utilization.


To be fair, Kubernetes right now only schedules relatively small clusters. But it turns out that the majority of the world is not Facebook or Google and only needs relatively small clusters.



Even those numbers (10k to 15k nodes and 100k containers) are smaller than what a great Mesos framework was capable of.

Of course, this mattered to only a very small number of organizations.


Yes, 10k to 15k machines is a relatively small cluster in my world.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: