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.

Timelike 2: everything fails all the time

99 pointsby krgabout 12 years ago

5 comments

eitlandabout 12 years ago
&#62; Really enjoying @RapGenius’s latest mix tape, “I Have No Idea How Distributed Systems Work”.<p>I guess someone didn't take their history lesson: In the opinion of a lot of people here Heroku was very close to perfect. Then they attempted to scale their approach and expand to different platforms. In this process they created a whole different product that they kept marketing as the original thing.<p>That is the problem.<p>Solving it isn't really that hard. As a thought experiment consider: 1.) The system was working nicely. Leaving it that way and adding no further customers would have left rapgenius happy. 2.) Adding a new, completely separate pool could serve more customers with the same needs as rapgenius.<p>I'm not saying this is an optimal soulution, I'm just pointing out that unless they were loosing money in their previous configuration, Heroku didn't need to change to the new architecture, -they chose to.
评论 #5255728 未加载
评论 #5256112 未加载
codemacabout 12 years ago
I'm now working on my <i>third</i> distributed high performance enterprise storage cluster. SCSI requires a certain (high) level of consistency per LU. And availability... and I'm delivering performance?<p>What? How could that be possible?<p>This blog post has so many assumptions about how nodes can and should behave that it's almost unreadable.<p>Faulty network? Get two fabrics. Nodes going down? RDMA to non volatile ram, and fail the I/O to the other node. This works for all your banks, airlines, governments, etc.<p>Heroku could do much better, but really: most of these startups should be hiring some ops people and design their own architectures already!
评论 #5255793 未加载
Dylan16807about 12 years ago
I don't understand this post. It starts off by insulting rapgenius for wanting working intelligent routing, and concludes by showing a way to hook up intelligent routers at scale and maintain performance.<p>What, exactly, is rapgenius wrong about then?
评论 #5262808 未加载
GhotiFishabout 12 years ago
aphyr that was a fascinating read. Any thought into testing some more complex routing strategies?<p>Also, I would love to see this graph: <a href="http://aphyr.com/data/posts/277/bamboo.png" rel="nofollow">http://aphyr.com/data/posts/277/bamboo.png</a> filled out.<p>How long do the simulations take to run?
评论 #5259089 未加载
askimtoabout 12 years ago
CAP is not applicable here from what I can tell. Glad to know Coda Hale understands it though. Sounds like a real nice guy.
评论 #5257789 未加载
评论 #5255752 未加载