Hacker News Reader

This is for very bursty logs. You don't log every 7 ns. On average you are not generating a huge amount of logs.

But you need each logging call to be very fast, cause logging calls are usually synchronous.

If the logging call is in the critical path then logging data is probably critical as well. After all, the fastest call is the one you don't do.

If you're writing telemetry then that's different. But if you're using logging to write your telemetry then there are better ways to do it.

I think the idea here is to separate the log call site in application code from the log processing/persistence?

So, the nanosecond values quoted are the impact exposed to your application code, but some other process takes over the bulk of the work of the logging.

So as long as the offloaded process can keep up with the average log rate, it'll be fine - but also as a bonus the application does not see increased latency due to logging.

Sounds a bit like how Tracy works

Battery backed SRAM