If this has been answered before, please point me to the right thread or place...

I recently started using SNMP / Zenoss to monitor resources on my CentOS 5.2 hosts. The OS is installed with no packages whatsoever (I even uncheck "base") during the custom installation routine in order to minimize the server disk and memory footprint as much as possible (I install specific apps and dependencies as they are needed afterward via yum). However, I noticed that even with mostly-idle machines, the I/O usage kept going up over time. I decided to monitor a similar host with no applications installed whatsoever (other than what comes with the minimized OS install set).



The following is the process list:

Code:
USER       PID %CPU %MEM    VSZ   RSS TTY      STAT START   TIME COMMAND
root         1  0.0  0.1   2060   648 ?        Ss   Feb18   0:00 init [3]
root         2  0.0  0.0      0     0 ?        S<   Feb18   0:00 [migration/0]
root         3  0.0  0.0      0     0 ?        SN   Feb18   0:00 [ksoftirqd/0]
root         4  0.0  0.0      0     0 ?        S<   Feb18   0:00 [watchdog/0]
root         5  0.0  0.0      0     0 ?        S<   Feb18   0:00 [events/0]
root         6  0.0  0.0      0     0 ?        S<   Feb18   0:00 [khelper]
root         7  0.0  0.0      0     0 ?        S<   Feb18   0:00 [kthread]
root        10  0.0  0.0      0     0 ?        S<   Feb18   0:00 [kblockd/0]
root        11  0.0  0.0      0     0 ?        S<   Feb18   0:00 [kacpid]
root        67  0.0  0.0      0     0 ?        S<   Feb18   0:00 [cqueue/0]
root        70  0.0  0.0      0     0 ?        S<   Feb18   0:00 [khubd]
root        72  0.0  0.0      0     0 ?        S<   Feb18   0:00 [kseriod]
root       136  0.0  0.0      0     0 ?        S    Feb18   0:00 [pdflush]
root       137  0.0  0.0      0     0 ?        S    Feb18   0:00 [pdflush]
root       138  0.0  0.0      0     0 ?        S<   Feb18   0:00 [kswapd0]
root       139  0.0  0.0      0     0 ?        S<   Feb18   0:00 [aio/0]
root       292  0.0  0.0      0     0 ?        S<   Feb18   0:00 [kpsmoused]
root       322  0.0  0.0      0     0 ?        S<   Feb18   0:00 [scsi_eh_0]
root       325  0.0  0.0      0     0 ?        S<   Feb18   0:00 [ata/0]
root       326  0.0  0.0      0     0 ?        S<   Feb18   0:00 [ata_aux]
root       337  0.0  0.0      0     0 ?        S<   Feb18   0:00 [ksnapd]
root       340  0.0  0.0      0     0 ?        S<   Feb18   0:02 [kjournald]
root       372  0.0  0.0      0     0 ?        S<   Feb18   0:00 [kauditd]
root       406  0.0  0.2   2804  1336 ?        S<s  Feb18   0:00 /sbin/udevd -d
root      1092  0.0  0.0      0     0 ?        S<   Feb18   0:00 [kmpathd/0]
root      1115  0.0  0.0      0     0 ?        S<   Feb18   0:00 [kjournald]
root      1438  0.0  1.7  10372  8780 ?        Ss   Feb18   0:00 /usr/sbin/restorecond
root      1453  0.0  0.1   1720   612 ?        Ss   Feb18   0:00 syslogd -m 0
root      1456  0.0  0.0   1668   404 ?        Ss   Feb18   0:00 klogd -x
root      1475  0.0  0.0   2156   500 ?        Ss   Feb18   0:00 mcstransd
dbus      1491  0.0  0.1  12988   740 ?        Ssl  Feb18   0:00 dbus-daemon --system
root      1512  0.0  1.0  26076  5384 ?        Sl   Feb18   0:19 /usr/sbin/snmpd -Lsd -Lf /dev/null -p /var/run/snmpd.pid -a
root      1528  0.0  0.3  14924  1912 ?        Ss   Feb18   0:00 /usr/sbin/snmptrapd -Lsd -p /var/run/snmptrapd.pid
root      1558  0.0  0.2   6984  1052 ?        Ss   Feb18   0:00 /usr/sbin/sshd
ntp       1598  0.0  0.8   4232  4232 ?        SLs  Feb18   0:01 ntpd -u ntp:ntp -p /var/run/ntpd.pid -g
root      1608  0.0  0.0   1652   452 tty1     Ss+  Feb18   0:00 /sbin/mingetty tty1
root      1609  0.0  0.0   1652   448 tty2     Ss+  Feb18   0:00 /sbin/mingetty tty2
root      1610  0.0  0.0   1656   448 tty3     Ss+  Feb18   0:00 /sbin/mingetty tty3
root      1611  0.0  0.0   1652   448 tty4     Ss+  Feb18   0:00 /sbin/mingetty tty4
root      1612  0.0  0.0   1656   452 tty5     Ss+  Feb18   0:00 /sbin/mingetty tty5
root      1613  0.0  0.0   1656   452 tty6     Ss+  Feb18   0:00 /sbin/mingetty tty6
root      1709  1.0  0.5   9840  2752 ?        Ss   20:27   0:00 sshd: docrice [priv]
docrice   1711  0.1  0.3   9840  1608 ?        S    20:27   0:00 sshd: docrice@pts/0
docrice   1712  0.3  0.2   4524  1436 pts/0    Ss   20:27   0:00 -bash
docrice   1726  0.0  0.1   4240   940 pts/0    R+   20:27   0:00 ps aux
The I/O resets to zero after reboot and then climbs back up again over time. In this case, CentOS is running as a virtual machine under VMware ESXi and has 512 MB allocated for memory and roughly 3 GB of disk space as a virtual disk since I'm not doing anything on it. 2 GB of that is still available. I thought maybe SELinux might be a culprit, but even after putting it on permissive or even disabled on another machine, I don't see a change.

Does anyone know what this could be?