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.

Jepsen: Redpanda 21.10.1

193 pointsby aphyrabout 3 years ago

12 comments

doctor_evalabout 3 years ago
I just came here to thank Jepsen for these amazing reports. What a wonderful way to use your intellect to contribute to the wellbeing of the entire community.<p>Also I wanted to say to redpanda: I was on the fence but now I’m convinced. Will definitely be deploying on my next project, which has already kicked off. I only wish I could run it natively on MacOS instead of requiring docker.
rystsovabout 3 years ago
Hey folks, I was working with Kyle Kingsbury on this report from the Redpanda side and I&#x27;m happy to help if you have questions
评论 #31207763 未加载
评论 #31210873 未加载
mandevilabout 3 years ago
I was unfamiliar with Redpanda, and now I know and trust it. Whatever marketing budget Redpanda spent to get a Jepsen report was well worth it.
评论 #31211364 未加载
评论 #31207461 未加载
评论 #31209422 未加载
评论 #31208022 未加载
titanomachyabout 3 years ago
The level of intellectual discipline and competence on display here is inspiring.<p>I&#x27;d love to take one of the Jepsen courses, but it seems they&#x27;re offered only as corporate training. Maybe my employeer will agree to bring them in.<p>For now I&#x27;ll have to satisfy myself with the YouTube videos.
评论 #31234380 未加载
CJeffersonabout 3 years ago
This isn&#x27;t anything against Redpanda, but I&#x27;m always amazed how badly all these distributed databases do in Jepsen.<p>What would one use them for in practice, which wouldn&#x27;t be better suitable by a (the thing I&#x27;ve used), say postgresql and streaming replication in case the server goes down? (I&#x27;m not suggesting there isn&#x27;t a good application, just I&#x27;m not knowledgeable enough to know of one).
评论 #31208548 未加载
评论 #31208604 未加载
评论 #31207538 未加载
评论 #31207416 未加载
评论 #31213610 未加载
评论 #31207436 未加载
gigatexalabout 3 years ago
If your DB doesn&#x27;t pass the Jepsen tests it&#x27;s not worth using. Kudos to both teams.
antonmryabout 3 years ago
This report seems to have some wrong insights. Auto-commit offsets doesn&#x27;t imply dataloss if records are processed synchronously. This is the safest way to test Kafka instead of commit offsets manually
评论 #31210530 未加载
评论 #31235316 未加载
northstar702about 3 years ago
The blog for a deeper dive into results, fixes, and discussion on the write behavior in the kafka protocol. <a href="https:&#x2F;&#x2F;redpanda.com&#x2F;blog&#x2F;redpanda-official-jepsen-report-and-analysis&#x2F;" rel="nofollow">https:&#x2F;&#x2F;redpanda.com&#x2F;blog&#x2F;redpanda-official-jepsen-report-an...</a>
doommiusabout 3 years ago
Always great to read this. I preformed a jenkins test on Microsoft internal infra and it&#x27;s a huge insight. From an academic side it&#x27;s just as interesting looking into the lack of standards within consistently and the definitions of them.
评论 #31210616 未加载
dstrootabout 3 years ago
&gt; A KafkaConsumer, by contrast, will happily connect to a jar of applesauce14 and return successful, empty result sets for every call to consumer.poll. This makes it surprisingly difficult to tell the difference between “everything is fine and I’m up to date” versus “the cluster is on fire”, and led to significant confusion in our tests.<p>This tickled my funny bone. Never expected humor in a Jepsen writeup. Kudos!
评论 #31210549 未加载
评论 #31210588 未加载
dhshshdhdgfffabout 3 years ago
The first half is jepsen team trying to divine some actual testable guarantees from a pile of blog posts and a random Google doc. What a mess.
评论 #31207671 未加载
评论 #31207518 未加载
评论 #31209194 未加载
评论 #31207555 未加载
newman314about 3 years ago
Redpanda (back when they were VectorizedIO) spammed my work email after I starred one of their repos, denied it after I called them out on it and I just noticed that they had deleted their response to me.<p>Pretty sneaky to go back and delete the tweets first denying and then apologizing.<p>Receipts: <a href="https:&#x2F;&#x2F;twitter.com&#x2F;d11cc3s&#x2F;status&#x2F;1447573471152656389" rel="nofollow">https:&#x2F;&#x2F;twitter.com&#x2F;d11cc3s&#x2F;status&#x2F;1447573471152656389</a> <a href="https:&#x2F;&#x2F;twitter.com&#x2F;d11cc3s&#x2F;status&#x2F;1450906855115354116" rel="nofollow">https:&#x2F;&#x2F;twitter.com&#x2F;d11cc3s&#x2F;status&#x2F;1450906855115354116</a>
评论 #31208752 未加载
评论 #31210362 未加载