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.

Performance Evaluation of IPFS in Private Networks

80 pointsby harporoederabout 3 years ago

9 comments

chockchocschoirabout 3 years ago
I&#x27;m not sure anyone would be surprised that IPFS&#x27;s performance would be worse than FTP or any other protocol when it comes to transfers between two (or three) hosts.<p>The benefits of distributes systems becomes bigger the larger the network. Replicate the same results with 100 nodes and we&#x27;ll see.<p>I still think torrents would be even more efficient though, than both FTP and IPFS.
评论 #30799398 未加载
评论 #30801503 未加载
评论 #30798005 未加载
评论 #30798090 未加载
kkielhofnerabout 3 years ago
No mention of node performance? Running your own IPFS node with any non-personal amount of traffic is ROUGH. Poor storage quota support combined with a terrible garbage collector that consumes 1000% CPU on my Epyc cores every time it runs…
评论 #30800690 未加载
评论 #30801462 未加载
nlabout 3 years ago
<a href="https:&#x2F;&#x2F;www.semanticscholar.org&#x2F;paper&#x2F;Performance-Evaluation-of-IPFS-in-Private-Networks-Lajam-Helmy&#x2F;e18310f0250786be1f573359ceb6c421711c76af" rel="nofollow">https:&#x2F;&#x2F;www.semanticscholar.org&#x2F;paper&#x2F;Performance-Evaluation...</a> has the graphs showing just how bad IPFS is.<p>People should judge <i>IPFS</i> on this, not p2p file systems or DHTs generally. Bitorrtent for example would do a lot better on those large file tests.
评论 #30799171 未加载
makeworldabout 3 years ago
FTP is obviously an unfair comparison, but I was surprised to see this:<p>&gt; the reading performance of IPFS degrades as the data become more popular in the network.<p>I&#x27;d have expected the opposite.
评论 #30798584 未加载
nine_kabout 3 years ago
Since IPFS&#x27;s performance is <i>worser</i> than FTP&#x27;s, a client-server architecture is, apparently, <i>betterer!</i><p>I wonder how representative of a real-world scenario a three-node IPFS network is. I thought that file fragments are strewn across more nodes typically, with some redundancy. FTP offers nothing like this.<p>So far this looks a bit too apples-to-oranges to me. Has anyone actually read the paper?
评论 #30797983 未加载
评论 #30799374 未加载
yawnxyzabout 3 years ago
I&#x27;m considering using IPFS for storing metadata (in a similar way that DOI tracks publications) for accessioning genomics and wetlab microbiology data. The data will still be stored in the institution (b&#x2F;c of data governance laws).<p>The reason I really like that IPFS exists is bc it&#x27;s a really convenient, mostly cheap and mostly reliable place to put stuff for quick access, even more than running my own server (ew), or paying for hosting and&#x2F;or using Supabase, Firebase, etc.<p>Basically using IPFS as a convenient k&#x2F;v store. The data is still stored locally, but it&#x27;s just much less convenient to access.<p>Is anyone else doing this kind of setup?
评论 #30799808 未加载
评论 #30798591 未加载
klabb3about 3 years ago
Seems highly dependent on the protocol implementation. In either case, if cpu or memory bottlenecks it&#x27;s pretty bad.
评论 #30799187 未加载
jaequeryabout 3 years ago
Anyone know what happened to Filecoin ? Thought it was the faster version of IPFS.
JaggerFooabout 3 years ago
I noticed that public ipfs is used to host image files for NFTs. NFT marketplace websites serve the images quickly enough.<p>I wonder how perkeep would perform in that situation.
评论 #30798787 未加载
评论 #30798381 未加载
评论 #30799242 未加载