https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=219399
--- Comment #88 from Nils Beyer <[email protected]> --- (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. _______________________________________________ [email protected] mailing list https://lists.freebsd.org/mailman/listinfo/freebsd-bugs To unsubscribe, send any mail to "[email protected]"
