Debian Jessie Hyper-V 2012 – ksoftirqd usando un sacco di tempo CPU

Ho un Debian VM in esecuzione che utilizza un po 'di tempo di CPU in ksoftirqd. Ho altri server che eseguono Ubuntu (entrambi 12.04 / 14.04) che non hanno questo problema e potrebbero wherer migrare nuovamente a Ubuntu se non riesco a capire perché questo accade con Debian.

Uscita dalla parte superiore (ordinata per volta)

top - 08:24:49 up 11:44, 1 user, load average: 0.32, 0.14, 0.13 Tasks: 102 total, 2 running, 100 sleeping, 0 stopped, 0 zombie %Cpu(s): 0.4 us, 0.0 sy, 0.0 ni, 99.6 id, 0.0 wa, 0.0 hi, 0.0 si, 0.0 st MiB Mem: 2003.797 total, 1031.148 used, 972.648 free, 27.559 buffers MiB Swap: 4092.996 total, 0.000 used, 4092.996 free. 766.535 cached Mem PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 13 root 20 0 0.0m 0.0m 0.0m S 16.0 0.0 31:08.33 ksoftirqd/1 3 root 20 0 0.0m 0.0m 0.0m S 2.3 0.0 23:28.20 ksoftirqd/0 497 webapps 20 0 1128.5m 67.6m 14.8m S 0.0 3.4 3:09.39 python3 7 root 20 0 0.0m 0.0m 0.0m S 1.5 0.0 2:16.28 rcu_sched 496 webapps 20 0 127.0m 43.4m 9.0m S 0.8 2.2 1:29.28 celery 879 root 20 0 0.0m 0.0m 0.0m S 0.8 0.0 1:24.55 kworker/1:2 454 redis 20 0 37.6m 4.0m 2.3m S 0.0 0.2 1:08.58 redis-server 826 root 20 0 0.0m 0.0m 0.0m R 0.0 0.0 1:00.38 kworker/0:1 472 www-data 20 0 89.7m 4.5m 2.8m S 0.0 0.2 0:27.94 nginx 490 root 20 0 56.0m 12.6m 3.6m S 0.0 0.6 0:26.24 supervisord 11 root rt 0 0.0m 0.0m 0.0m S 0.0 0.0 0:05.86 watchdog/1 487 postgres 20 0 364.7m 20.5m 19.1m S 0.0 1.0 0:05.17 postgres 486 postgres 20 0 364.7m 6.6m 5.2m S 0.0 0.3 0:04.68 postgres 

Uscita da / proc / interrupt

  CPU0 CPU1 0: 772416 0 IO-APIC-edge timer 1: 9 0 IO-APIC-edge i8042 6: 3 0 IO-APIC-edge floppy 8: 0 0 IO-APIC-edge rtc0 9: 0 0 IO-APIC-fasteoi acpi 12: 161 0 IO-APIC-edge i8042 14: 0 0 IO-APIC-edge ata_piix 15: 41523 0 IO-APIC-edge ata_piix NMI: 0 0 Non-maskable interrupts LOC: 1447155 1235282 Local timer interrupts SPU: 0 0 Spurious interrupts PMI: 0 0 Performance monitoring interrupts IWI: 0 0 IRQ work interrupts RTR: 0 0 APIC ICR read retries RES: 109019 174764 Rescheduling interrupts CAL: 6495 376 Function call interrupts TLB: 308 185 TLB shootdowns TRM: 0 0 Thermal event interrupts THR: 0 0 Threshold APIC interrupts MCE: 0 0 Machine check exceptions MCP: 142 142 Machine check polls HYP: 1613643 15969 Hypervisor callback interrupts ERR: 0 MIS: 0 

È questo un normale per Debian su Hyper-V? Se non come scoprire cosa sta causando questo e risolverlo? Sono le impostazioni Hyper-V e non Debian?

Suggerimenti per Linux e Windows Server, quali Ubuntu, Centos, Apache, Nginx, Debian e argomenti di rete.