Code: Select all
# ls -ld /var/run/munin
drwxr-xr-x 2 munin root 1024 2007-11-23 10:46 /var/run/munin
# ls -ld /var/run/munin/*
-rw-r--r-- 1 munin munin 5 2007-11-23 10:46 /var/run/munin/munin-datafile.lock
-rw-r--r-- 1 munin munin 4 2007-11-23 10:46 /var/run/munin/munin-graph.lock
-rw-r--r-- 1 munin munin 4 2007-11-23 10:46 /var/run/munin/munin-html.lock
-rw-r--r-- 1 munin munin 0 2007-11-23 10:46 /var/run/munin/munin-limits.lock
-rw-r--r-- 1 munin munin 5 2007-11-23 10:45 /var/run/munin/munin-localdomain-localhost.localdomain.lock
-rw-r--r-- 1 munin munin 5 2007-11-23 10:45 /var/run/munin/munin-ncsrv.de-pvXX.ncsrv.de.lock
-rw-r--r-- 1 root root 6 2007-11-17 18:33 /var/run/munin/munin-node.pid
-rw-r--r-- 1 munin munin 5 2007-11-23 10:45 /var/run/munin/munin-update.lock
Code: Select all
# ls -ld /var/lib/munin
drwxr-xr-x 5 munin munin 1024 2007-11-23 10:50 /var/lib/munin
# ls -ld /var/lib/munin/*
-rw-r--r-- 1 munin munin 99096 2007-11-23 10:46 /var/lib/munin/datafile
-rw-r--r-- 1 munin munin 10574 2007-11-23 10:46 /var/lib/munin/limits
drwxr-xr-x 2 munin munin 8192 2007-11-06 03:25 /var/lib/munin/localdomain
-rw-r--r-- 1 munin munin 5065 2007-11-23 10:46 /var/lib/munin/munin-graph.stats
-rw-r--r-- 1 munin munin 10501 2007-11-23 10:46 /var/lib/munin/munin-update.stats
-rw-r--r-- 1 munin munin 4158 2007-11-23 10:51 /var/lib/munin/munin-update.stats.tmp
drwxr-xr-x 2 munin munin 7168 2007-11-06 03:15 /var/lib/munin/ncsrv.de
drwxrwxr-x 2 munin munin 1024 2007-02-03 13:40 /var/lib/munin/plugin-state
Code: Select all
# ls -l /etc/munin/templates/
total 38
-rw-r--r-- 1 root root 2555 2005-04-03 02:54 definitions.html
-rw-r--r-- 1 root root 473 2005-04-03 02:54 logo.png
-rw-r--r-- 1 root root 3286 2006-10-17 14:49 munin-comparison-day.tmpl
-rw-r--r-- 1 root root 3298 2006-10-17 14:49 munin-comparison-month.tmpl
-rw-r--r-- 1 root root 3292 2006-10-17 14:49 munin-comparison-week.tmpl
-rw-r--r-- 1 root root 3292 2006-10-17 14:49 munin-comparison-year.tmpl
-rw-r--r-- 1 root root 2351 2006-10-17 14:49 munin-domainview.tmpl
-rw-r--r-- 1 root root 3114 2006-10-17 14:49 munin-nodeview.tmpl
-rw-r--r-- 1 root root 1942 2006-10-17 14:49 munin-overview.tmpl
-rw-r--r-- 1 root root 4772 2006-10-17 14:49 munin-serviceview.tmpl
-rw-r--r-- 1 root root 3538 2005-04-03 02:54 style.css
Code: Select all
# find /etc -iname *munin*
/etc/cron.d/munin
/etc/cron.d/munin-node
/etc/init.d/munin-node
/etc/logcheck/ignore.d.server/munin
/etc/logrotate.d/munin-node
/etc/logrotate.d/munin
/etc/munin
/etc/munin/plugin-conf.d/munin-node
/etc/munin/plugin-conf.d/munin-node.dpkg-old
/etc/munin/templates/munin-domainview.tmpl
/etc/munin/templates/munin-comparison-day.tmpl
/etc/munin/templates/munin-comparison-month.tmpl
/etc/munin/templates/munin-comparison-week.tmpl
/etc/munin/templates/munin-comparison-year.tmpl
/etc/munin/templates/munin-nodeview.tmpl
/etc/munin/templates/munin-overview.tmpl
/etc/munin/templates/munin-serviceview.tmpl
/etc/munin/munin-node.conf
/etc/munin/munin.conf
/etc/rc0.d/K20munin-node
/etc/rc1.d/K20munin-node
/etc/rc2.d/S98munin-node
/etc/rc3.d/S98munin-node
/etc/rc4.d/S98munin-node
/etc/rc5.d/S98munin-node
/etc/rc6.d/K20munin-node
Code: Select all
# ls -l /etc/cron.d/munin
-rw-r--r-- 1 root root 525 2006-10-17 14:49 /etc/cron.d/munin
# ls -l /etc/cron.d/munin-node
-rw-r--r-- 1 root root 506 2006-10-17 14:49 /etc/cron.d/munin-node
# ls -l /etc/init.d/munin-node
-rwxr-xr-x 1 root root 5295 2006-10-14 23:35 /etc/init.d/munin-node
# cat /etc/cron.d/munin
Code: Select all
#
# cron-jobs for munin
#
MAILTO=root
@reboot root if [ ! -d /var/run/munin ]; then /bin/bash -c 'perms=(`/usr/sbin/dpkg-statoverride --list /var/run/munin`); mkdir /var/run/munin; chown ${perms[0]:-munin}:${perms[1]:-root} /var/run/munin; chmod ${perms[2]:-0755} /var/run/munin'; fi
*/5 * * * * munin if [ -x /usr/bin/munin-cron ]; then /usr/bin/munin-cron; fi
14 10 * * * munin if [ -x /usr/share/munin/munin-limits ]; then /usr/share/munin/munin-limits --force --contact nagios --contact old-nagios; fi
# cat /etc/cron.d/munin-node
Code: Select all
#
# cron-jobs for munin-node
#
MAILTO=root
# If the APT plugin is enabled, update packages databases approx. once
# an hour (12 invokations an hour, 1 in 12 chance that the update will
# happen), but ensure that there will never be more than two hour (7200
# seconds) interval between updates..
*/5 * * * * root if [ -x /etc/munin/plugins/apt_all ]; then /etc/munin/plugins/apt_all update 7200 12 >/dev/null; elif [ -x /etc/munin/plugins/apt ]; then /etc/munin/plugins/apt update 7200 12 >/dev/null; fi
Ich denke, wegen "too many open files", und den damit verbundenen Problemen, bekomme ich manchmal diese Mail von logcheck:
Code: Select all
Lock already exists: /var/run/munin/munin-update.lock. Dying.
Lock already exists: /var/run/munin/munin-html.lock. Dying.
Das sieht dann im auth.log so aus:
Code: Select all
Nov 23 12:12:51 pvXX CRON[5567]: (pam_unix) session opened for user munin by (uid=0)
Nov 23 12:13:10 pvXX CRON[3247]: (pam_unix) session closed for user root
Nov 23 12:13:22 pvXX CRON[5568]: (pam_unix) session closed for user root
Nov 23 12:13:32 pvXX su[7454]: Unknown UID: 0
Nov 23 12:13:52 pvXX su[9230]: Successful su for root by root
Nov 23 12:13:56 pvXX su[9230]: + ??? root:root
Nov 23 12:14:00 pvXX su[9230]: (pam_unix) session opened for user root by (uid=0)
Nov 23 12:14:04 pvXX su[9230]: (pam_unix) session closed for user root
Nov 23 12:14:08 pvXX su[9387]: Successful su for root by root
Nov 23 12:14:12 pvXX su[9387]: + ??? root:root
Nov 23 12:14:16 pvXX su[9387]: (pam_unix) session opened for user root by (uid=0)
Nov 23 12:14:22 pvXX su[9387]: (pam_unix) session closed for user root
Nov 23 12:14:26 pvXX su[9505]: Successful su for root by root
Nov 23 12:14:30 pvXX su[9505]: + ??? root:root
Nov 23 12:14:36 pvXX su[9505]: (pam_unix) session opened for user root by (uid=0)
Nov 23 12:14:41 pvXX su[9909]: Successful su for root by root
Nov 23 12:14:45 pvXX su[9909]: + ??? root:root
Nov 23 12:14:49 pvXX su[10024]: PAM unable to dlopen(/lib/security/pam_mail.so)
Nov 23 12:14:53 pvXX su[10024]: PAM [dlerror: /lib/security/pam_mail.so: cannot open shared object file: Too many open files in system]
Nov 23 12:14:56 pvXX su[10024]: PAM adding faulty module: /lib/security/pam_mail.so
Nov 23 12:14:59 pvXX su[10024]: PAM no modules loaded for `su' service
Nov 23 12:15:07 pvXX su[10024]: Successful su for root by root
Nov 23 12:15:14 pvXX su[10024]: + ??? root:root
Nov 23 12:15:21 pvXX CRON[3436]: (pam_unix) session closed for user munin
Hier ein Ausschnitt des dazu gehörenden /var/log/munin/munin-node.log:
Code: Select all
/etc/munin/plugins/vebc_physpages_oomguarpages_33189: cannot make pipe for command substitution: Too many open files in system
/etc/munin/plugins/vebc_physpages_oomguarpages_33189: pipe error: Too many open files in system
2007/11/23-12:15:22 Plugin "vebc_physpages_oomguarpages_33189" exited with status 33024. ----
/etc/munin/plugins/vebc_physpages_oomguarpages_privvmpages_33189: pipe error: Too many open files in system
/etc/munin/plugins/vebc_physpages_oomguarpages_privvmpages_33189: pipe error: Too many open files in system
/etc/munin/plugins/vebc_physpages_oomguarpages_privvmpages_33189: line 110: /bin/su: Too many open files in system
/etc/munin/plugins/vebc_physpages_oomguarpages_privvmpages_33189: pipe error: Too many open files in system
2007/11/23-12:15:22 Plugin "vebc_physpages_oomguarpages_privvmpages_33189" exited with status 33024. ----
/etc/munin/plugins/netstat: line 95: /bin/netstat: Too many open files in system
/etc/munin/plugins/netstat: line 95: /usr/bin/awk: Too many open files in system
2007/11/23-12:15:22 Plugin "netstat" exited with status 32256. ----
Funktioniert allerdings trotzdem.
Ich würde sagen, wenn mehrmaliges vergleichen nichts bringt, bleibt noch die munin user maillist auf sf.net.
Ansonsten cacti, monit oder nagios.
http://www.debianhelp.co.uk/monitortools.htm