https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=219399
--- Comment #88 from Nils Beyer <n...@renzel.net> ---
(In reply to Don Lewis from comment #87)
thanks for the modified version; I've tried it. It loads the CPU more, yes, but
there's still at least one core (sometimes two or more) idling around. I don't
get any segmentation faults within an acceptable time frame (<5 minutes).
Please try the version that I've attached
https://bugs.freebsd.org/bugzilla/attachment.cgi?id=184539
I know you've said that you've already tried it - but perhaps there's something
different on my system compiler. Here it segfaults after a maximum of one
minute.
I believe that the key to these segmentation faults are inner-thread core
switches that are prevented by pinning these threads to specific cores. How far
any instruction cache is involved with that, I don't know...
TIA
--
You are receiving this mail because:
You are the assignee for the bug.
_______________________________________________
freebsd-bugs@freebsd.org mailing list
https://lists.freebsd.org/mailman/listinfo/freebsd-bugs
To unsubscribe, send any mail to "freebsd-bugs-unsubscr...@freebsd.org"
