Segmentation fault in perfcollect

[emchang1]

I'm following the instructions here: https://github.com/dotnet/coreclr/blob/master/Documentation/project-docs/linux-performance-tracing.md

I ran ./perfcollect collect trace and am seeing the error: ./perfcollect: line 641: 363 Segmentation fault (core dumped) $* >> $logFile 2>&1

It looks like the seg fault is happening on this command: /usr/bin/perf_4.9 record -g -a -F 999 -e cpu-clock

Any suggestions on how to resolve this?

[chwarr]

We built perf from source and included debugging info. Using this, we were able to determine that our distro's version of perf was crashing trying to copy namespace info. We were able to port a change from the v4.20-rc1 version of perf back atop our distro's code and use that to collect a trace.

We are using Debian Stretch with a v4.15 kernel.