Yiannis Psaras

I don't have a clear view of what this would entail in terms of implementation, but it's certainly not a bad idea to consider. Our results show that we could...

I would be interested to hear other opinions after @guillaumemichel's study further up. I believe we can make a decision based on the data we have and either close the...

I'm definitely 100% in favour of what @aschmahmann suggests! We've done some extensive measurement studies and found that the DHT can, in many cases (mostly depending on geographic location of...

Thanks @mrd0ll4r ! Do you happen to have (even rough) estimates on the success rate of the bitswap discovery process? I.e., out of how many bitswap requests do the successful...

Thanks looking into this @iand ! Difficult to explain what's going on from these results :-D Do you have any explanation? Some questions regarding the experiment setup that might help...

Interesting setup 👌🏽 But I still can't explain where this performance difference comes from. Are these kubo nodes connected to the gateways? I guess they're not.

Quick update from ProbeLab side: we've started looking into this in more detail and we expect some first results to come out this week. @guillaumemichel to provide a more specific...

@tysonzero: there are different things mixed in your questions above, so let me try to clarify. IPFS is (at this point) detached from Filecoin. They are two different networks. Filecoin...

Ok, I see. Just for information: the Filecoin network also uses the IPFS CID and hash concept, so that's not a show-stopper in using Filecoin. It depends what you want...

IIUC what you describe is the pinning services (which already exist), where you store something on the service’s storage (commonly realized as a public gateway) and pay according to the...