Server Scaling Debate
The cluster focuses on discussions about the number of servers required to handle massive user scales, such as millions of monthly or concurrent users, with debates on single-server capabilities versus multi-server setups and real-world examples like WhatsApp.
Activity Over Time
Top Contributors
Keywords
Sample Comments
Is it 1000x times harder to server 10K users?
Holy cow, 28 000 servers, can you give us a clue to what you need so many servers for?
Monthly users reaching 70 million. I doubt a basic server could handle that.
"So what scale are we talking about? A few million monthly users? So like hackernews? I would use a single server... "
100 servers for billions of requests per day seems crazy optimistic. It sounds like they're running pretty lean as it is.
A dedicated server of decent size should easily be able to handle this kind of traffic.
Serving a social network is not the case where you'd want just one server. Mainly due to reliability concerns, spikes in traffic and different patterns at different times.But if you like the idea of ignoring best practices, there are EC2 instances with 192 vCPUs that go for several thousands an hour. And taking as example Golang benchmarks https://github.com/smallnest/go-web-framewor
How many servers does this run on? How does this scale?
WhatsApp used to be hosted on ~15 bare metal servers serving 100 million concurrent users...
I understand your point, but millions sounds an exaggeration- I have a hard time believing a single node can handle millions of concurrent users