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.

What Makes Containers at Scale So Difficult

26 pointsby orrsellaover 9 years ago

4 comments

jacques_chesterover 9 years ago
This is an advertorial for Mesos, which attacks some of these problems at a deep level.<p>It&#x27;s (not yet) a full PaaS, though Mesosphere is driving there along with Docker and Hashicorp and everyone else who built parts of the solution and then realised there&#x27;s not much profit in selling cogs.<p>I like Cloud Foundry -- which <i>is</i> a PaaS -- probably because I&#x27;ve worked on and seen how that sausage gets made. But there&#x27;s also OpenShift. And Heroku, which people often forgot pioneered the whole space.<p>The bin packing problem is hard in theory, but at the scale we&#x27;re talking about, it becomes less about the perfect fit and more about the fact that keeping up-to-date information is hard under realistic conditions. You can show linear scaling for short tasks. Wait until you&#x27;re running in someone&#x27;s whacky private DC.<p>Diego (the container scheduler in the next generation of Cloud Foundry) doesn&#x27;t try to maintain a perfect view of state in order to do its job. It&#x27;s basically impossible to really do so. Instead it satisfices by turning container placement into an auction, then periodically goes out to sync up with reality.<p>If you want to play with it, the best option is to install Lattice[0].<p>Standard disclaimer: I work for Pivotal Labs, a division of Pivotal, which is the largest donor of engineering effort to the Cloud Foundry Foundation. So I guess my comment is an advertorial too.<p>[0] <a href="http:&#x2F;&#x2F;lattice.cf&#x2F;" rel="nofollow">http:&#x2F;&#x2F;lattice.cf&#x2F;</a>
pcuniteover 9 years ago
I am not sysadmin, so, thinking out loud here: why not build software services in a way that does not require this large and sprawling infrastructure? The future could be simple binaries that run in user space and cache everything in simple data structures all in RAM. 64GB is cheap and will handle C1M easily.<p>I want my future server to abstract the hardware (memory, socket too), provide a few simple API calls, run my runtime (C++, rust, .NET, etc.), and then I&#x27;ll build my application business logic to handle all my customers waiting on the other end of the socket.<p>Perhaps it the open source way where you have 40+ dependencies. I recently built my own webserver and found it very liberating.<p>Think outside the container.
评论 #10325973 未加载
评论 #10326204 未加载
erikpukinskisover 9 years ago
Generic containers are an awkward mid-way point between special-purpose containers (a Wordpress instance or a rails app on heroku) and an actual machine.<p>You get the hassle of maintaining your own instances, without the flexibility or well-defined performance characteristics of an actual box.<p>I just don&#x27;t see the market.
评论 #10326214 未加载
bestusername111over 9 years ago
Because not enough memes and hype and buzzwords.