Hyper-V

[Pavel Timofeev]

I figured out another operations that cause caclru message appearance,
such as 'top -n', car /proc/0/status, etc.
But I tried these on 9.2-RELEASE LIVE CD and I saw calcru messages.

So it seems like it's not related to brand new hyper-v integrated
components. It's related to whole FreeBSD system. Which part? I don't
know.

2013/11/12 Pavel Timofeev <timp87 at gmail.com>:
> So, we catched the bug that caused crash. Thanks to all. Cool!
>
> As regards the messages about "calcru": I tried to install CentOS 6.4
> on new virt machine on same host system. Linux doesn't have any
> strange messages about time.
> I tried to migrate FreeBSD and CentOS virt machines to another host
> which has another hardware. Same story.
>
> For example, try to boot beta-3 in LIVE CD mode. You won't see calcru
> messages. But if you try to run 'dclient hn0' you'll see calcru
> message storm for some time.
> On already installed system I can cause messages by doing
> service zabbix_server start (even if it's not allowed in rc.conf (!))
>
> But I can start mysql-server, zabbix_agentd, apache22 and it doesn't
> cause appearance of calcru messages.
>
>
> Any ideas? How and where can I dig?
>
> 2013/11/6 Pavel Timofeev <timp87 at gmail.com>:
>> Small fix:
>> kern.timecounter.hardware=TSC covered messages, but now it looks stange
>> % time sleep 30
>>        20.24 real         0.00 user         0.00 sys
>>
>> 2013/11/6 Pavel Timofeev <timp87 at gmail.com>:
>>> I already tried disabling Hyper-v time syncing, setting
>>> kern.timecounter.hardware to different type from
>>> kern.timecounter.choice, setting kern.hz to different values. But
>>> nothing helped.
>>> I'll try to install CentOS 6.4 on this machine and see what happens.
>>>
>>> 2013/11/6 Pavel Timofeev <timp87 at gmail.com>:
>>>> Does anybody know how to disable Hyper-v time syncing it guest FreeBSD
>>>> OS? I'd like to try this one.
>>>>
>>>> 2013/11/6 Pavel Timofeev <timp87 at gmail.com>:
>>>>> Thank you very much!
>>>>> I started to dig, and found that I can reboot my server running under
>>>>> Hyper-V by doing 'sysctl -a'.
>>>>> Can anybody confirm same behavoiur?
>>>>>
>>>>> FreeBSD 10.0-BETA3, Win 2012 Datacenter
>>>>>
>>>>> 2013/11/5 Julian Elischer <julian at freebsd.org>:
>>>>>> On 11/4/13, 11:13 PM, Pavel Timofeev wrote:
>>>>>>>
>>>>>>> Hi! I upgraded to 10.0-BETA3 but still see messages like
>>>>>>>
>>>>>>> Tue Nov  5 11:09:05 MSK 2013
>>>>>>> calcru: runtime went backwards from 1728 usec to 889 usec for pid 981
>>>>>>> (zabbix_server)
>>>>>>> calcru: runtime went backwards from 1229 usec to 703 usec for pid 976
>>>>>>> (zabbix_server)
>>>>>>> calcru: runtime went backwards from 1019 usec to 595 usec for pid 978
>>>>>>> (zabbix_server)
>>>>>>> calcru: runtime went backwards from 3041 usec to 1611 usec for pid 969
>>>>>>> (zabbix_server)
>>>>>>> calcru: runtime went backwards from 1078 usec to 595 usec for pid 975
>>>>>>> (zabbix_server)
>>>>>>> calcru: runtime went backwards from 1114 usec to 617 usec for pid 980
>>>>>>> (zabbix_server)
>>>>>>> calcru: runtime went backwards from 1086 usec to 602 usec for pid 977
>>>>>>> (zabbix_server)
>>>>>>> calcru: runtime went backwards from 1195 usec to 782 usec for pid 970
>>>>>>> (zabbix_server)
>>>>>>> calcru: runtime went backwards from 3206 usec to 2157 usec for pid 979
>>>>>>> (zabbix_server)
>>>>>>> calcru: runtime went backwards from 2179 usec to 1542 usec for pid 972
>>>>>>> (zabbix_server)
>>>>>>> calcru: runtime went backwards from 1833 usec to 927 usec for pid 1026
>>>>>>> (cron)
>>>>>>> calcru: runtime went backwards from 1091 usec to 551 usec for pid 1022
>>>>>>> (sendmail)
>>>>>>> calcru: runtime went backwards from 823 usec to 416 usec for pid 1022
>>>>>>> (sendmail)
>>>>>>> calcru: runtime went backwards from 4691 usec to 2735 usec for pid
>>>>>>> 1011 (sendmail)
>>>>>>> calcru: runtime went backwards from 1162 usec to 587 usec for pid 1011
>>>>>>> (sendmail)
>>>>>>> calcru: runtime went backwards from 947 usec to 478 usec for pid 1010
>>>>>>> (httpd)
>>>>>>> calcru: runtime went backwards from 895 usec to 452 usec for pid 1009
>>>>>>> (httpd)
>>>>>>> calcru: runtime went backwards from 954 usec to 482 usec for pid 1008
>>>>>>> (httpd)
>>>>>>> calcru: runtime went backwards from 909 usec to 459 usec for pid 1007
>>>>>>> (httpd)
>>>>>>> calcru: runtime went backwards from 1214 usec to 653 usec for pid 1006
>>>>>>> (httpd)
>>>>>>> calcru: runtime went backwards from 201793 usec to 102672 usec for pid
>>>>>>> 996 (httpd)
>>>>>>> calcru: runtime went backwards from 1105 usec to 1064 usec for pid 991
>>>>>>> (sshd)
>>>>>>> calcru: runtime went backwards from 45196 usec to 23221 usec for pid
>>>>>>> 974 (zabbix_server)
>>>>>>> calcru: runtime went backwards from 2192 usec to 1436 usec for pid 973
>>>>>>> (zabbix_server)
>>>>>>> calcru: runtime went backwards from 605 usec to 306 usec for pid 968
>>>>>>> (zabbix_server)
>>>>>>> calcru: runtime went backwards from 626 usec to 316 usec for pid 967
>>>>>>> (zabbix_server)
>>>>>>> calcru: runtime went backwards from 773 usec to 391 usec for pid 966
>>>>>>> (zabbix_server)
>>>>>>> calcru: runtime went backwards from 663 usec to 335 usec for pid 965
>>>>>>> (zabbix_server)
>>>>>>> calcru: runtime went backwards from 799 usec to 404 usec for pid 964
>>>>>>> (zabbix_server)
>>>>>>> calcru: runtime went backwards from 37723 usec to 19422 usec for pid
>>>>>>> 963 (zabbix_server)
>>>>>>> calcru: runtime went backwards from 49425 usec to 26265 usec for pid
>>>>>>> 962 (zabbix_server)
>>>>>>> calcru: runtime went backwards from 38883 usec to 20993 usec for pid
>>>>>>> 961 (zabbix_server)
>>>>>>> calcru: runtime went backwards from 53478 usec to 27411 usec for pid
>>>>>>> 960 (zabbix_server)
>>>>>>> calcru: runtime went backwards from 40845 usec to 21750 usec for pid
>>>>>>> 959 (zabbix_server)
>>>>>>> calcru: runtime went backwards from 47835 usec to 24455 usec for pid
>>>>>>> 958 (zabbix_server)
>>>>>>> calcru: runtime went backwards from 2257 usec to 1612 usec for pid 957
>>>>>>> (zabbix_server)
>>>>>>> calcru: runtime went backwards from 2361 usec to 1193 usec for pid 932
>>>>>>> (zabbix_agentd)
>>>>>>> calcru: runtime went backwards from 32053 usec to 16204 usec for pid
>>>>>>> 928 (zabbix_server)
>>>>>>> calcru: runtime went backwards from 32517 usec to 19280 usec for pid 697
>>>>>>> (sh)
>>>>>>> calcru: runtime went backwards from 1128021 usec to 868022 usec for pid
>>>>>>> 697 (sh)
>>>>>>> calcru: runtime went backwards from 9609 usec to 5601 usec for pid 601
>>>>>>> (syslogd)
>>>>>>> calcru: runtime went backwards from 688 usec to 348 usec for pid 106
>>>>>>> (adjkerntz)
>>>>>>> calcru: runtime went backwards from 12 usec to 6 usec for pid 3
>>>>>>> (sctp_iterator)
>>>>>>> calcru: runtime went backwards from 5467 usec to 2853 usec for pid 2
>>>>>>> (fdc0)
>>>>>>> calcru: runtime went backwards from 11306 usec to 8408 usec for pid 14
>>>>>>> (rand_harvestq)
>>>>>>> calcru: runtime went backwards from 136242 usec to 76230 usec for pid 13
>>>>>>> (geom)
>>>>>>> calcru: runtime went backwards from 156117 usec to 118882 usec for pid 12
>>>>>>> (intr)
>>>>>>> calcru: runtime went backwards from 7820 usec to 4847 usec for pid 1
>>>>>>> (init)
>>>>>>> calcru: runtime went backwards from 2340313 usec to 1226503 usec for
>>>>>>> pid 1 (init)
>>>>>>> calcru: runtime went backwards from 4114 usec to 2164 usec for pid 0
>>>>>>> (kernel)
>>>>>>>
>>>>>>>
>>>>>>> Is it bad? Or I have to ignore them?
>>>>>>
>>>>>>
>>>>>> I'm not talking authoratatively but in some virtualization systems, if the
>>>>>> TSCs on the various processors are not sufficiently synchronized, then when
>>>>>> the hypervisor switches you from one CPU to another, you can get odd
>>>>>> (sometimes negative) time readings which give messages like this..
>>>>>>
>>>>>>> _______________________________________________
>>>>>>> freebsd-virtualization at freebsd.org mailing list
>>>>>>> http://lists.freebsd.org/mailman/listinfo/freebsd-virtualization
>>>>>>> To unsubscribe, send any mail to
>>>>>>> "freebsd-virtualization-unsubscribe at freebsd.org"
>>>>>>>
>>>>>>>
>>>>>>