https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=219399
--- Comment #85 from Nils Beyer <[email protected]> --- (In reply to Andriy Gapon from comment #83) makes sense to me; if there are undetected errors in the instruction cache like corrupted memory addresses that would explain these corrupted stack traces, too. I got these messages on an other Ryzen system, too; different core, but still "MCA: CPU 10 COR ICACHE L1 IRD error". No system lock-ups or reboots there yet, but this system is not poudriering due to lack of RAM (only 16GB). The only thing I did there was buildworlds in a RAM disk; and failed serveral times because of the "unable to rename temporary"-TMPFS-phenonema. The CPU is the same model (1700) but bought three months after my CPU, so I don't think it's the same batch. For me, the hints lead more and more to a design flaw within the CPU; and hopefully, that could be fixed with a microcode update... -- 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]"
