Among the many benefits of running @bitfinex outside of AWS (predictability of the system, performance, ...), we were sick tired of AWS rebooting instances without much of a notice.
In many occasions AWS sent a communication after the fact.
-
I agree, AWS doesn’t seem to have live migration figured out as well as others. I do wonder how much effort goes into having your own infrastructure as reliable as AWS, especially in disaster scenarios. But I’m sure you guys figured it out, and it’s very cool you made it work
We have built our systems around shards and replicas on a bare metal setup. We can resist to 2/3 of the servers dying and we have also off-site realtime replica on a separate infra waiting in idle.
-
-
Nice. Do you need to take rack space in different regions to serve different customers?
-
We use a main location. Then we have some POPs through cloudflare. But since the matching engine is one, pro customers are usually connecting from nearby
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.