Hacker News Reader

Comment by hcks | Hacker News Reader

It’s interesting because while this is an extreme case of performance improvement, the ROI doesn’t seem amazing.

"rewriting in another language reduced the number of servers by 95%" is hard to beat, but at the same time, this saves "only" 2m a year, or about 0.3% of FY22 cost of revenue (per another post)

Pinterest per employee revenue seems to be around 1m, which basically suggest that this could even be a worse than average allocation of resources.

My takeaway would be "don’t bother with this kind of optimisation before you reach a scale where you can afford to do marginal improvements"

View on HN

It more than just server costs. They reduced the complexity of their services by a lot.

Having to maintain 95% less servers is worth it even if they didn't save any money IMO.

This also could lead to them reducing their engineering team that maintains these services which would reduce costs even more.

Can switching to an esoteric functional language from Python and Java really be considered reducing complexity? No matter how well it is written, I'm willing to bet that way fewer people in the company/industry understand the new codebase and can make changes to it.

> Can switching to an esoteric functional language from Python and Java really be considered reducing complexity?

It's not esoteric. It's a modern programing language, with 35 years behind its Virtual machine.

1 in 3 phone calls you've ever made was routed through a telephon switch written in a lang implemented in BEAM virtual machine.

WhatsApp was written in a lang implemented on the BEAM.

> I'm willing to bet that way fewer people in the company/industry understand the new codebase and can make changes to it.

It's really not hard to learn. It's not Haskell, It's not Coq, It's not Brainfuck.

You could pick up the syntax and the major semantics in a weekend.

This isn't a huge difference most of the time. Once you have cluster management at scale, 3 vs 3000 are pretty similar.

Wouldn't you also need a smaller ops team that way, further reducing your costs?

Managing 200 Python servers/nodes certainly sounds operationally challenging.

i disagree, not much more then 2 servers.. you should automate it fully for documentation purposes alone at this scale & test failover regulary

if you do this with 4 or 200 machines, does not make a big difference.

Actually it does because the chance of hitting strange edge cases grow significantly, as do the runtime of your deployment, plus networking problems risks.

Running 200 servers will force you to automate everything and also handle (relatively) rare edge cases, meaning added complexity, huge up front dev costs, and a continuous dev effort just to stay afloat. Work has to be balanced in a clever way, making tradeoffs that you otherwise wouldn't need to make. The mental model shifts from individual servers to a whole ecosystem that shows emergent behavior (= things break in a totally new way).

Maybe some of that also applies to 4 servers, but to a way lesser extent.

2 million dollars a year is "marginal improvement" just because the sales and customer support team is big? That's your logic?

Reply on news.ycombinator.com