TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Mesos, Omega, Borg: A Survey

80 pointsby r4umabout 10 years ago

6 comments

menageabout 10 years ago
One important point that the author seems to have misunderstood is that Borg was the <i>predecessor</i> to the other two systems, not the successor. Borg went into production (running a bunch of websearch dedicated clusters) in late 2004, long before Mesos or Omega were around. Omega is&#x2F;was an experimental replacement for Borg that was started much later, although I&#x27;m not sure how much production load it actually took over.
评论 #9641276 未加载
评论 #9639617 未加载
mckossabout 10 years ago
See also Google&#x27;s blog post summarizing Borg -&gt; Kubernetes improvements.<p><a href="http:&#x2F;&#x2F;blog.kubernetes.io&#x2F;2015&#x2F;04&#x2F;borg-predecessor-to-kubernetes.html" rel="nofollow">http:&#x2F;&#x2F;blog.kubernetes.io&#x2F;2015&#x2F;04&#x2F;borg-predecessor-to-kubern...</a>
KaiserProabout 10 years ago
Its interesting to see how other industries tackle the same problem.<p>VFX has essentially the same problem to google: a huge bunch of tasks that need to perform all at once.<p>However VFX only tend to have one data center, so they don;t need or want clustered scheduler.<p><a href="https:&#x2F;&#x2F;github.com&#x2F;mikrosimage&#x2F;openrendermanagement" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;mikrosimage&#x2F;openrendermanagement</a>, Alfred and tractor from pixar, and framestore&#x27;s FQ (which is faster and more efficient than Borg at job dispatch. ) Are a few good example of task management.
presspotabout 10 years ago
I know a lot about Mesos and Mesosphere&#x27;s DCOS, so can comment on those:<p>* There are users of these systems that get 90+% cluster utilization.<p>* Pre-emptable tasks (e.g., best effort scheduling vs guaranteed SLA scheduling) will be landing in Mesos.<p>* Mesosphere is building advanced scheduling plug-ins that will use the new scheduling models to do oversubscription of a cluster, helping to drive utilization to the 90%+ range without the need for any special tooling. You can get an idea of some of the algorithms being employed by checking out the Kozyrakis&#x2F;Delimitrou Quasar paper[1].<p>[1] <a href="http:&#x2F;&#x2F;csl.stanford.edu&#x2F;~christos&#x2F;publications&#x2F;2014.quasar.asplos.pdf" rel="nofollow">http:&#x2F;&#x2F;csl.stanford.edu&#x2F;~christos&#x2F;publications&#x2F;2014.quasar.a...</a>
jefe78about 10 years ago
Is anyone using these at scale but with a small team to support it? We have a 5-6k fleet of servers across 3 DCs + another 1.5k in AWS. I tried deploying Mesos with mixed results. I also experimented with CoreOS. Considering re-exploring XEN&#x2F;VMWare.
syskabout 10 years ago
I&#x27;m not a sysadmin but recently started using CoreOS to deploy small web apps. Could anyone explain to me like I&#x27;m 5 what&#x27;s the difference between those cluster schedulers and something like CoreOS&#x27; fleet (<a href="https:&#x2F;&#x2F;github.com&#x2F;coreos&#x2F;fleet" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;coreos&#x2F;fleet</a>)?
评论 #9640538 未加载
评论 #9637792 未加载
评论 #9641724 未加载