Date: Sat, 03 Apr 2021 13:08:55 +0000 From: bugzilla-noreply@freebsd.org To: bugs@FreeBSD.org Subject: [Bug 248659] Specific generations of intel chips lock up with P-states active Message-ID: <bug-248659-227-3uie7mrPdx@https.bugs.freebsd.org/bugzilla/> In-Reply-To: <bug-248659-227@https.bugs.freebsd.org/bugzilla/> References: <bug-248659-227@https.bugs.freebsd.org/bugzilla/>
next in thread | previous in thread | raw e-mail | index | archive | help
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=3D248659 --- Comment #28 from Sergei Masharov <serzh@expir.org> --- I have updated couple more systems to RC5 and none of them have such strange dev.cpu.0.freq_levels As I have mentioned before, on the problematic Lenovo system it looks like= =20 dev.cpu.0.freq_levels: 2112/-1 if I try to change the dev.cpu.0.freq it looks even more strange: root@lenovo:/etc # sysctl dev.cpu.0.freq=3D99999 dev.cpu.0.freq: 1005 -> 936 root@lenovo:/etc # sysctl dev.cpu.0.freq=3D2112 dev.cpu.0.freq: 1005 -> 1005 root@lenovo:/etc # sysctl dev.cpu.0.freq=3D2112 dev.cpu.0.freq: 1005 -> 4222 root@lenovo:/etc # sysctl dev.cpu.0.freq=3D2112 dev.cpu.0.freq: 1005 -> 3911 root@lenovo:/etc # sysctl dev.cpu.0.freq=3D2112 dev.cpu.0.freq: 1005 -> 4222 Is it a normal and expected behavior? Because with hint.hwpstate_intel.0.disabled=3D"1" it looks like on any other system and = on the versions before 13.0 If the system is idle it can work up to several hours now, but on any significant CPU load it freezes just several minutes after. --=20 You are receiving this mail because: You are the assignee for the bug.=
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?bug-248659-227-3uie7mrPdx>