Hello guys,

I just installed a RH8.0 on a new system. When I am running "top" I see all the time an average load of 1.0 while there is nothing special running ... cpu0-1 states are showing 0% usage... So, I am wondering where this load of 1.0 is coming from.

Thanks for helping me out ...

System:
P4 2.8Ghz (Hyper threading enabled)
2*120 GB SATA (raid1)
512Mb RAM

OS:
Redhat 8.0 - 2.4.18-14smp

Output top:
2:02am up 24 min, 2 users, load average: 1.00, 0.97, 0.76
38 processes: 37 sleeping, 1 running, 0 zombie, 0 stopped
CPU0 states: 0.0% user, 0.0% system, 0.0% nice, 100.0% idle
CPU1 states: 0.0% user, 1.0% system, 0.0% nice, 99.0% idle
Mem: 512388K av, 66412K used, 445976K free, 0K shrd, 13608K buff
Swap: 1044216K av, 0K used, 1044216K free 32856K cached

PID USER PRI NI SIZE RSS SHARE STAT %CPU %MEM TIME COMMAND
1 root 15 0 492 492 448 S 0.0 0.0 0:04 init
2 root 0K 0 0 0 0 SW 0.0 0.0 0:00 migration_CPU0
3 root 0K 0 0 0 0 SW 0.0 0.0 0:00 migration_CPU1
4 root 15 0 0 0 0 SW 0.0 0.0 0:00 keventd
5 root 34 19 0 0 0 SWN 0.0 0.0 0:00 ksoftirqd_CPU0
6 root 34 19 0 0 0 SWN 0.0 0.0 0:00 ksoftirqd_CPU1
7 root 15 0 0 0 0 SW 0.0 0.0 0:00 kswapd
8 root 25 0 0 0 0 SW 0.0 0.0 0:00 bdflush
9 root 15 0 0 0 0 SW 0.0 0.0 0:06 kupdated
10 root 25 0 0 0 0 SW 0.0 0.0 0:00 mdrecoveryd
16 root 15 0 0 0 0 DW 0.0 0.0 0:00 AAR81XX watchdo
17 root 25 0 0 0 0 SW 0.0 0.0 0:00 scsi_eh_0
20 root 15 0 0 0 0 SW 0.0 0.0 0:00 kjournald
75 root 15 0 0 0 0 SW 0.0 0.0 0:00 khubd

That does seem a little high, try: ps -aux | more
This displays a list of running processes

Thanks for your reply!

Is it possible that the load of 1.0 has something todo with the Hyperthreading processor?

Output ps -aux:

USER PID %CPU %MEM VSZ RSS TTY STAT START TIME COMMAND
root 1 0.3 0.0 1392 492 ? S 09:49 0:04 init
root 2 0.0 0.0 0 0 ? SW 09:49 0:00 [migration_CPU0]
root 3 0.0 0.0 0 0 ? SW 09:49 0:00 [migration_CPU1]
root 4 0.0 0.0 0 0 ? SW 09:49 0:00 [keventd]
root 5 0.0 0.0 0 0 ? SWN 09:49 0:00 [ksoftirqd_CPU0]
root 6 0.0 0.0 0 0 ? SWN 09:49 0:00 [ksoftirqd_CPU1]
root 7 0.0 0.0 0 0 ? SW 09:49 0:00 [kswapd]
root 8 0.0 0.0 0 0 ? SW 09:49 0:00 [bdflush]
root 9 0.4 0.0 0 0 ? SW 09:49 0:05 [kupdated]
root 10 0.0 0.0 0 0 ? SW 09:49 0:00 [mdrecoveryd]
root 16 0.0 0.0 0 0 ? DW 09:49 0:00 [AAR81XX watchdo]
root 17 0.0 0.0 0 0 ? SW 09:49 0:00 [scsi_eh_0]
root 20 0.0 0.0 0 0 ? SW 09:49 0:00 [kjournald]
root 75 0.0 0.0 0 0 ? SW 09:49 0:00 [khubd]
root 233 0.0 0.0 0 0 ? SW 09:50 0:00 [kjournald]
root 234 0.0 0.0 0 0 ? SW 09:50 0:00 [kjournald]
root 235 0.0 0.0 0 0 ? SW 09:50 0:00 [kjournald]
root 236 0.0 0.0 0 0 ? SW 09:50 0:00 [kjournald]
root 529 0.0 0.1 1464 556 ? S 09:50 0:00 syslogd -m 0
root 533 0.0 0.0 1396 448 ? S 09:50 0:00 klogd -x
rpcuser 569 0.0 0.1 1604 772 ? S 09:50 0:00 rpc.statd
root 679 0.0 0.2 3352 1468 ? S 09:50 0:00 /usr/sbin/sshd
root 694 0.0 0.1 2060 824 ? S 09:50 0:00 xinetd -stayalive
root 718 0.0 0.1 1452 600 ? S 09:51 0:00 crond
root 731 0.0 0.1 1424 600 ? SN 09:51 0:00 anacron -s
daemon 740 0.0 0.1 1436 560 ? S 09:51 0:00 /usr/sbin/atd
root 752 0.0 0.1 3432 556 ? S 09:51 0:00 rhnsd --interval
root 757 0.0 0.0 1380 424 tty1 S 09:51 0:00 /sbin/mingetty tt
root 758 0.0 0.0 1380 424 tty2 S 09:51 0:00 /sbin/mingetty tt
root 759 0.0 0.0 1380 424 tty3 S 09:51 0:00 /sbin/mingetty tt
root 760 0.0 0.0 1380 424 tty4 S 09:51 0:00 /sbin/mingetty tt
root 761 0.0 0.0 1380 424 tty5 S 09:51 0:00 /sbin/mingetty tt
root 762 0.0 0.0 1380 424 tty6 S 09:51 0:00 /sbin/mingetty tt
root 765 0.0 0.4 6672 2092 ? S 09:51 0:00 /usr/sbin/sshd
root 767 0.0 0.2 4344 1420 pts/0 S 09:51 0:00 -bash
root 833 0.0 0.1 2756 768 pts/0 R 10:11 0:00 ps -aux
root 834 0.0 0.0 3468 480 pts/0 S 10:11 0:00 more

Hello guys,

Have been searching and searching about my problem ... but found nothing.

Anyone that can help me finding the missing link?

Thanks!

This thread is old, but I'll share my story...

Got the same problem.. I have a SuperMicro "SuperServer" with their X6DHT-G motherboard with the 8-port Marvell SATA "300" controller. We have two 300GB Segate SATA drives in a RAID-1. A 160GB WesternDigital IDE drive running a RedHat EL 3 -based distro. With everything on the IDE drive, and the SATA array only being used for backup, I've had some time to test the Marvell controller. The Marvell controller itself has Adaptec Embedded SATA HostRAID firmware. This requires the aar81xx kernel module / driver. When this driver is modprobe'd, it takes about 45 seconds for the load average to reach 1.0 and stay there for ever and ever even though the dual Xeon's are doing nothing. modprobe -r it and it the load average falls back to normal.. usually .25 or so.

This modules is not GPL and taints the kernel. So, to test, I did "echo 0 > /proc/sys/kernel/tainted" but that has nothing to do with it.

The dual Xeon's have HyperThreading enabled. I have not had time to take the server down to turn off HT and see if that fixes the load average problem. This is a primary mission critical web server with many many accounts, so it kinda hard to take it down.. even for 3-1/2 minutes. If this turns out to be the problem, I wont be surprised. The 2.6 kernels have better HT support.

Over a week of discussion with SuperMicro they say it's not the hardware, it is because the OS is Open Source and cannot be supported. WHAT!!!! Suck my #$%@$!!! The people know nothing about Linux and they can barely speak english.

Release the source for the driver, and the Linux community will fix it.. but we all know thats not going to happen.

Hi geskorup you have a solution for loadavg set to 1 in idle time ?

I have fedora core 3 with 2 Opteron processors and
scsi0 : Adaptec AAR-1420SA Serial ATA HostRAID driver
Vendor: WDC WD74 Model: 0GD-00FLA2 Rev: 31.0

Thx

phil