The problem is that they make it super easy in very hacky ways and it becomes painful to improve things without startup money.
Also, per the hackiness, it tends to have visible perf impact. I know with dynatrace agent we had 0-1MS metrics pop up to 5-10ms (this service had a lot of traffic so it added up) and I'm pretty sure on .NET side there's issues around general performance of OTEL. I also know some of the work/'fun' colleagues have had to endure to make OTEL performant for their libs, in spite of the fact it was a message passing framework where that should be fairly simple...
Well let's be fair. You can't get the type of telemetry Dyntrace provides "for free". You have to pay for it somewhere. Pretty sure you can exclude the agent from instrumenting performance critical parts of the code, if that is your concern.
Also, per the hackiness, it tends to have visible perf impact. I know with dynatrace agent we had 0-1MS metrics pop up to 5-10ms (this service had a lot of traffic so it added up) and I'm pretty sure on .NET side there's issues around general performance of OTEL. I also know some of the work/'fun' colleagues have had to endure to make OTEL performant for their libs, in spite of the fact it was a message passing framework where that should be fairly simple...