Hello,
I'm having issues with a new virtual instance on CentOs 6. I have the latest integration services installed and all appears to be fine. When I test disk speed everything looks great, the issue comes into play when I load test the system. If
I start throwing requests at Apache I see a very rapid slowdown. Top shows me that ksoftirqd is locking up considerable system resources. If I take a look at cat /proc/interrupts i see:
CPU0 CPU1
0: 307 0 IO-APIC-edge timer
1: 46 0 IO-APIC-edge i8042
7: 103889 0 IO-APIC-edge hyperv
8: 0 0 IO-APIC-edge rtc0
9: 0 0 IO-APIC-fasteoi acpi
12: 114 0 IO-APIC-edge i8042
14: 411 0 IO-APIC-edge ata_piix
15: 80 0 IO-APIC-edge ata_piix
NMI: 0 0 Non-maskable interrupts
LOC: 55041 30365 Local timer interrupts
SPU: 0 0 Spurious interrupts
PMI: 0 0 Performance monitoring interrupts
IWI: 0 0 IRQ work interrupts
RES: 1961 5333 Rescheduling interrupts
CAL: 44 3629 Function call interrupts
TLB: 513 468 TLB shootdowns
TRM: 0 0 Thermal event interrupts
THR: 0 0 Threshold APIC interrupts
MCE: 0 0 Machine check exceptions
MCP: 2 2 Machine check polls
ERR: 0
MIS: 0
CPU0 CPU1
0: 307 0 IO-APIC-edge timer
1: 46 0 IO-APIC-edge i8042
7: 103889 0 IO-APIC-edge hyperv
8: 0 0 IO-APIC-edge rtc0
9: 0 0 IO-APIC-fasteoi acpi
12: 114 0 IO-APIC-edge i8042
14: 411 0 IO-APIC-edge ata_piix
15: 80 0 IO-APIC-edge ata_piix
NMI: 0 0 Non-maskable interrupts
LOC: 55041 30365 Local timer interrupts
SPU: 0 0 Spurious interrupts
PMI: 0 0 Performance monitoring interrupts
IWI: 0 0 IRQ work interrupts
RES: 1961 5333 Rescheduling interrupts
CAL: 44 3629 Function call interrupts
TLB: 513 468 TLB shootdowns
TRM: 0 0 Thermal event interrupts
THR: 0 0 Threshold APIC interrupts
MCE: 0 0 Machine check exceptions
MCP: 2 2 Machine check polls
ERR: 0
MIS: 0
Anything over about 5 users and the server will totally stop processing new requests.
Can anyone suggest where I may be having issues?
Thanks,
Keith