Yes I agree, so then now that HPET is disabled I did the /proc/interrupts test again with a timebase of 25 minutes after reboot.
Without SFTP:
Code: Select all
[mi@scientific-centos ~]$ cat /proc/interrupts
CPU0 CPU1 CPU2 CPU3
0: 188 0 0 0 IO-APIC-edge timer
1: 2 1 1 1 IO-APIC-edge i8042
7: 0 0 0 0 IO-APIC-edge parport0
8: 0 0 0 0 IO-APIC-edge rtc0
9: 0 0 0 0 IO-APIC-fasteoi acpi
12: 1 1 2 2 IO-APIC-edge i8042
16: 0 0 0 0 IO-APIC-fasteoi uhci_hcd:usb3
17: 14 19 21 20 IO-APIC-fasteoi uhci_hcd:usb4, uhci_hcd:usb7, snd_hda_intel:card1
18: 0 0 0 0 IO-APIC-fasteoi uhci_hcd:usb8, i801_smbus
22: 0 0 0 0 IO-APIC-fasteoi ehci_hcd:usb1, uhci_hcd:usb5
23: 0 0 0 0 IO-APIC-fasteoi ehci_hcd:usb2, uhci_hcd:usb6
27: 85 3584 83 779877 PCI-MSI-edge enp0s25
28: 9067 1643 59560 1631 PCI-MSI-edge 0000:00:1f.2
29: 158 150 157 155 PCI-MSI-edge snd_hda_intel:card0
30: 2989 29 22 2 PCI-MSI-edge nvidia
NMI: 584 1071 574 1091 Non-maskable interrupts
LOC: 1525470 1635084 1657928 1781457 Local timer interrupts
SPU: 0 0 0 0 Spurious interrupts
PMI: 584 1071 574 1091 Performance monitoring interrupts
IWI: 156 215 110 126 IRQ work interrupts
RTR: 0 0 0 0 APIC ICR read retries
RES: 523166 446232 619187 437062 Rescheduling interrupts
CAL: 4626 4276 5395 5093 Function call interrupts
TLB: 37078 38531 34598 33057 TLB shootdowns
TRM: 0 0 0 0 Thermal event interrupts
THR: 0 0 0 0 Threshold APIC interrupts
DFR: 0 0 0 0 Deferred Error APIC interrupts
MCE: 0 0 0 0 Machine check exceptions
MCP: 6 6 6 6 Machine check polls
ERR: 0
MIS: 0
PIN: 0 0 0 0 Posted-interrupt notification event
NPI: 0 0 0 0 Nested posted-interrupt event
PIW: 0 0 0 0 Posted-interrupt wakeup event
[mi@scientific-centos ~]$ uptime
16:28:23 up 25 min, 1 user, load average: 1.45, 1.57, 1.42
with SFTP:
Code: Select all
[mi@scientific-centos ~]$ cat /proc/interrupts
CPU0 CPU1 CPU2 CPU3
0: 186 0 0 0 IO-APIC-edge timer
1: 2 1 1 1 IO-APIC-edge i8042
7: 0 0 0 0 IO-APIC-edge parport0
8: 0 0 0 0 IO-APIC-edge rtc0
9: 0 0 0 0 IO-APIC-fasteoi acpi
12: 1 1 2 2 IO-APIC-edge i8042
16: 0 0 0 0 IO-APIC-fasteoi uhci_hcd:usb3
17: 17 15 26 16 IO-APIC-fasteoi uhci_hcd:usb4, uhci_hcd:usb7, snd_hda_intel:card1
18: 0 0 0 0 IO-APIC-fasteoi uhci_hcd:usb8, i801_smbus
22: 0 0 0 0 IO-APIC-fasteoi ehci_hcd:usb1, uhci_hcd:usb5
23: 0 0 0 0 IO-APIC-fasteoi ehci_hcd:usb2, uhci_hcd:usb6
27: 102 3578 93 754521 PCI-MSI-edge enp0s25
28: 9775 1978 59671 1973 PCI-MSI-edge 0000:00:1f.2
29: 149 153 150 158 PCI-MSI-edge snd_hda_intel:card0
30: 3354 44 17 4 PCI-MSI-edge nvidia
NMI: 152 203 118 179 Non-maskable interrupts
LOC: 254632 293738 298788 809650 Local timer interrupts
SPU: 0 0 0 0 Spurious interrupts
PMI: 152 203 118 179 Performance monitoring interrupts
IWI: 2186 2506 4277 39026 IRQ work interrupts
RTR: 0 0 0 0 APIC ICR read retries
RES: 187839 167326 186857 147548 Rescheduling interrupts
CAL: 5436 5581 5572 6060 Function call interrupts
TLB: 14595 11398 13565 11335 TLB shootdowns
TRM: 0 0 0 0 Thermal event interrupts
THR: 0 0 0 0 Threshold APIC interrupts
DFR: 0 0 0 0 Deferred Error APIC interrupts
MCE: 0 0 0 0 Machine check exceptions
MCP: 6 6 6 6 Machine check polls
ERR: 0
MIS: 0
PIN: 0 0 0 0 Posted-interrupt notification event
NPI: 0 0 0 0 Nested posted-interrupt event
PIW: 0 0 0 0 Posted-interrupt wakeup event
[mi@scientific-centos ~]$ uptime
16:55:47 up 25 min, 1 user, load average: 0.04, 0.05, 0.16
As far as I can tell Local timer interrupts are much higher in number, as well as Rescheduling interrupts.
TLB shootdowns are also a bit higher.
What would you suggest to do now? I looked into the new BIOS versions for my machine but in the list of fixes there doesn't appear to be something related to timers, considering that I've never done a BIOS update i'd like to try something else first.
Is there any way to get more detailed information on these interrupts?