When recurring 10–15 second outages made the database behind #LinkedIn’s user feed briefly unavailable - with no useful logs - engineers turned to off-CPU profiling with #eBPF to find the root cause.

The failures were ephemeral, patternless, and had no clear external trigger.

Here is how they solved it ⇨ https://bit.ly/3PS1RtN

#InfoQ #SoftwareArchitecture #Profilers #Monitoring #Database