From @vtsukur on Tue Sep 29 2015 18:07:11 GMT+0000 (UTC)
From time to time it can be observed that initial seek for a file can be overly slow.
For example, when file is
ipfs add-ed on a locally running machine, and then retrieved via gateway.ipfs.io/ipfs, request can take any time in between several hundreds of milliseconds down to 2 minutes timing out several times in a row (ending in successful seek, eventually).
If file is
ipfs get-ed from a node that does not share same network, it is usually much much slower. Succeeds, but amount of attempts is usually bigger.
I am curious to know why these latency issues are present at the moment. Thanks!
Copied from original issue: https://github.com/ipfs/faq/issues/57