On 27/02/16 13:51, Henrique de Moraes Holschuh wrote:
On Fri, 26 Feb 2016, Stuart Bennett wrote:
Some time after booting, all cores of an Intel E5-2680 v3 get throttled to
around 400MHz. The intel_pstate cpufreq driver is in use, as is the
Are you using thermald?
I'm afraid not; a list of all daemon-like things is below:
/sbin/init
/lib/systemd/systemd-journald
/lib/systemd/systemd-udevd
/usr/sbin/named -f -u bind
/usr/sbin/smartd -n
/usr/sbin/sshd -D
/usr/bin/rsync --daemon --no-detach
/usr/sbin/cron -f
/usr/sbin/rsyslogd -n
/usr/sbin/acpid
/usr/sbin/nullmailer-send -s
/sbin/agetty --noclear tty2 linux
/sbin/agetty --noclear tty1 linux
/sbin/agetty --noclear tty3 linux
/sbin/agetty --noclear tty4 linux
/usr/sbin/ntpd -p /var/run/ntpd.pid -g -u 104:109
/sbin/agetty --noclear tty5 linux
/sbin/agetty --noclear tty6 linux
/usr/sbin/rpc.mountd -N2 -N3 --manage-gids
/usr/sbin/dhcpd -q -cf /etc/dhcp/dhcpd.conf -pf /var/run/dhcpd.pid br0
/usr/sbin/nagios3 -d /etc/nagios3/nagios.cfg
/usr/sbin/apache2 -k start
thermald isn't even installed.
Downgrading that microcode exposes you to higher chances of data
corruption/unpredictable system behavior (I wish I could be more specific
than that, but I don't have the required information), so we really should
try to find a different solution.
Agreed.
The observed behaviour sounds similar to that in Launchpad bug #1506050.
Take a look at lp#1480349:
https://bugs.launchpad.net/ubuntu/wily/+source/thermald/+bug/1480349
Seems I don't have the thermald link, but I see from that bug that full
CPU info may be useful: here's the output for the last core (note it has
family 6, model 63, stepping 2; as in the referenced bug).
processor : 23
vendor_id : GenuineIntel
cpu family : 6
model : 63
model name : Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz
stepping : 2
microcode : 0x32
cpu MHz : 1200.097
cache size : 30720 KB
physical id : 0
siblings : 24
core id : 13
cpu cores : 12
apicid : 27
initial apicid : 27
fpu : yes
fpu_exception : yes
cpuid level : 15
wp : yes
flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov
pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx
pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl
xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64 monitor
ds_cpl vmx smx est tm2 ssse3 fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2
x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm
abm ida arat epb xsaveopt pln pts dtherm tpr_shadow vnmi flexpriority
ept vpid fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid
bogomips : 4988.45
clflush size : 64
cache_alignment : 64
address sizes : 46 bits physical, 48 bits virtual
power management:
Let me know if any other tests/information indicated in the other bug
would be potentially relevant in this case.
Stuart
