Why high load average DL120G6 with B110i SATA Raid Driver

[yito]

Hi,
why high load average over 1.0 all time.
I installed CentOS5.5 with B110i SATA Raid Driver on HP DL120G6.

HP Raid Driver:
hpahcisr-1.2.4-14.rhel5.i686.rpm

top - 18:06:45 up 1 day, 50 min, 1 user, load average: 1.03, 1.01, 1.00
Tasks: 123 total, 1 running, 122 sleeping, 0 stopped, 0 zombie
Cpu(s): 0.1%us, 0.1%sy, 0.0%ni, 99.8%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
Mem: 2066892k total, 1781028k used, 285864k free, 36524k buffers
Swap: 4128760k total, 0k used, 4128760k free, 1636436k cached

PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
9268 root 15 0 2412 1028 800 R 0.3 0.0 0:00.06 top
1 root 15 0 2152 608 528 S 0.0 0.0 0:00.59 init

[Alzhy]

There is likely a fair amount of CPU interrupts and context switching in your system?

I had a similar issue a few months ago. My system (a 24 cpu environment) even when idle had a "load" of over 24 consistently.

It turned out an improperly presented SAN disk was still being seen by the OS and there were several processes that although were not "cpu active" were very much doing a lot of interrupts.

It seems on Linux "Load" is calculated differnt from UNIX and includes other factors as CPY/system interrupts.

[yito]

Thx. Interrupts and context switch is bellow. This server is 1P/4C Intel Xeon X3430@2.40GHz CPU.

Because response is not bad, is it a problem only of how to see it?

# cat /proc/interrupts
CPU0 CPU1 CPU2 CPU3
0: 155292620 0 0 69235 IO-APIC-edge timer
8: 0 0 3 0 IO-APIC-edge rtc
9: 0 0 0 0 IO-APIC-level acpi
66: 101 0 0 9 IO-APIC-level ehci_hcd:usb2
74: 36 0 0 736514 PCI-MSI eth0
169: 0 0 26 0 IO-APIC-level ehci_hcd:usb1
185: 0 0 1733572 30359 IO-APIC-level hpahcisr0
NMI: 0 0 0 0
LOC: 155368032 155368032 155368020 155368033
ERR: 0
MIS: 0
[root@story-web ~]# vmstat
procs -----------memory---------- ---swap-- -----io---- --system-- -----cpu------
r b swpd free buff cache si so bi bo in cs us sy id wa st
0 0 0 291212 85320 1589996 0 0 0 4 47 59 0 0 100 0 0

# vmstat 10
procs -----------memory---------- ---swap-- -----io---- --system-- -----cpu------
r b swpd free buff cache si so bi bo in cs us sy id wa st
0 0 0 291212 85328 1589992 0 0 0 4 47 59 0 0 100 0 0
0 0 0 291212 85332 1589996 0 0 0 3 1014 455 0 0 100 0 0
0 0 0 291212 85336 1589996 0 0 0 13 1016 459 0 0 100 0 0
0 0 0 291212 85336 1589996 0 0 0 0 1010 454 0 0 100 0 0
0 0 0 291212 85336 1589996 0 0 0 0 1012 457 0 0 100 0 0
0 0 0 291212 85336 1589996 0 0 0 0 1010 454 0 0 100 0 0
0 0 0 291212 85336 1589996 0 0 0 0 1011 455 0 0 100 0 0
0 0 0 291212 85336 1589996 0 0 0 0 1013 460 0 0 100 0 0
0 0 0 291212 85340 1589996 0 0 0 6 1013 458 0 0 100 0 0
0 0 0 291212 85340 1589996 0 0 0 0 1011 456 0 0 100 0 0
0 0 0 291212 85348 1589996 0 0 0 1 1011 456 0 0 100 0 0
0 0 0 291212 85348 1589996 0 0 0 6 1013 455 0 0 100 0 0
0 0 0 291212 85348 1589996 0 0 0 0 1010 455 0 0 100 0 0
0 0 0 291212 85348 1589996 0 0 0 0 1012 456 0 0 100 0 0
0 0 0 291212 85352 1589996 0 0 0 6 1013 456 0 0 100 0 0
0 0 0 291212 85352 1589996 0 0 0 0 1010 454 0 0 100 0 0
0 0 0 291212 85352 1589996 0 0 0 0 1009 451 0 0 100 0 0
0 0 0 291212 85352 1589996 0 0 0 6 1011 454 0 0 100 0 0
0 0 0 291212 85352 1589996 0 0 0 0 1011 457 0 0 100 0 0
0 0 0 291212 85352 1589996 0 0 0 0 1011 457 0 0 100 0 0
0 0 0 291212 85356 1589996 0 0 0 6 1012 456 0 0 100 0 0
0 0 0 291212 85356 1589996 0 0 0 0 1012 456 0 0 100 0 0
0 0 0 291212 85356 1589996 0 0 0 0 1013 456 0 0 100 0 0
procs -----------memory---------- ---swap-- -----io---- --system-- -----cpu------

[Azamat]

salom,

we had the same issue on the DL380G6 and updated FW on the server. Try update fw(FWCD9.00) and drivers by smartstart 8.50