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.

SDPaxos: Building efficient semi-decentralized geo-replicated state machines

56 pointsby mattdemonover 6 years ago

3 comments

marknadalover 6 years ago
After going through the article, I&#x27;m not seeing anything that supports or justifies the phrase &quot;decentralized&quot; or even &quot;semi-decentralized&quot;. The terminology should be &quot;distributed&quot;.<p>Claiming this is semi-decentralized is confusing, and seemingly wanting to borrow from the recent success of decentralized systems (like IPFS, ours, GUN, and others) without being honest: There system is distributed, not decentralized. In the same way &quot;Serverless&quot; totally requires using servers.<p>Otherwise, very good article.
评论 #18412127 未加载
skydeover 6 years ago
anyone familiar with the algorithm can help answer a few question?<p>1- Why C-instance can come from any node without a paxos phase 1a Prepare message, is it because each node (R0 to R4) have its own distinct replication log for C-instance?<p>2-When sequencer receive a C-Accept why is it safe to assume this value was successfully accepted by other replica without receiving a paxos phase3 Commit?<p>3-If replicating large value, are the value only sent in C-instance message and not in O-instance messages?
评论 #18409024 未加载
fokkerover 6 years ago
Curious, why Paxos over Raft?
评论 #18409754 未加载
评论 #18410376 未加载
评论 #18412611 未加载