[munificent]

This is an excellent slideshow.

The slide on measuring by having a fake server replaying order data, a second server calculating runtimes, the server under test, and a hardware switch to let you measure packet times is so delightfully hardcore.

I don't have any interest in working in finance, but it must be fun working on something so performance critical that buying a rack of hardware just for benchmarking is economically feasible.

[nine_k]

Delightfully hardcore indeed!

But of course you don't have to buy a rack of servers for testing, you can rent it. Servers are a quickly depreciating asset, why invest in them?

[CyberDildonics]

Why would replaying data for testing be "Delightfully hardcore indeed!". That's how people program in general, they run the same data through their program.

Servers are a quickly depreciating asset, why invest in them?

I don't think they are a quickly depreciating asset compared to the price of renting, but you would want total control over them in this scenario anyway.

[nine_k]

I thought that the hardcore part is taking the data from the switch to account for the network latency.

[munificent]

> Why would replaying data for testing be "Delightfully hardcore indeed!".

Replaying data isn't hardcore. Buying a dedicated server and running it through a dedicated switch just to gather precise timing info is.

[a_t48]

You'd want it to be the exact same hardware as in production, for one.

[a_t48]

The self driving space does this :)