https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=272944
--- Comment #4 from Mark Johnston <ma...@freebsd.org> --- (In reply to jSML4ThWwBID69YC from comment #2) Hmm, that's a bit surprising. If you look at "top -SHza" output while the benchmark is running, do you see an epair thread consuming 100% of a CPU? There might be a bottleneck elsewhere. (In reply to jSML4ThWwBID69YC from comment #3) You'd also need to add "options PCBGROUP" to the kernel config. -- You are receiving this mail because: You are the assignee for the bug.
