SCSMON Roll : User Guide

[root@cluster rolls]# chkconfig --list mon
mon             0:off   1:off   2:off   3:off   4:off   5:off   6:off
[root@cluster rolls]# chkconfig mon on

[root@cluster ~]# cat /etc/mon/mon.cf
### Extremely basic mon.cf file
### global options
cfbasedir   = /etc/mon
pidfile     = /var/run/mon.pid
statedir    = /var/lib/mon/state.d
logdir      = /var/lib/mon/log.d
dtlogfile   = /var/lib/mon/log.d/downtime.log
alertdir    = /usr/lib/mon/alert.d
mondir      = /usr/lib/mon/mon.d
maxprocs    = 20
histlength  = 100
randstart   = 60s
authtype    = pam
userfile    = /etc/mon/userfile

watch frontend
    service ping
        interval 5m
        monitor ping.monitor
        period wd {Mon-Fri} hr {7am-10pm}
            alert mail.alert root@localhost
            alertevery 1h
        period wd {Sat-Sun}
    service ssh
        interval 10m
        monitor telnet.monitor
        period wd {Mon-Fri} hr {7am-10pm}
            alertevery 1h
            alertafter 2 30m
            alert mail.alert root@localhost
   service http
        interval 60m
        monitor http.monitor
        allow_empty_group
        period wd {Sun-Sat}
            upalert mail.alert -S "web server is back up" mis
            alertevery 45m

watch compute
    service ping
        interval 10m
        monitor ping.monitor
        period wd {Mon-Fri} hr {7am-10pm}
            alert mail.alert root@localhost
            alertevery 1h
        period wd {Sat-Sun}
            alert mail.alert root@localhost

[root@cluster ~]#  dbreport mon > /etc/mon/mon.cf

[root@cluster mon]# ls -1 /usr/lib/mon/mon.d/*.monitor
asyncreboot.monitor
bootp.monitor
cpqhealth.monitor
dialin.monitor
dir_file_age.monitor
dns.monitor
file_change.monitor
flexlm.monitor
foundry-chassis.monitor
fping.monitor
freespace.monitor
ftp.monitor
hpnp.monitor
http.monitor
https.monitor
http_t.monitor
http_tp.monitor
http_tpp.monitor
icecast.monitor
imap.monitor
informixdbspace.monitor
informix.monitor
ipsec.monitor
ldap.monitor
mailloop.monitor
mon.monitor
msql-mysql.monitor
na_quota.monitor
netappfree.monitor
netsnmp-exec.monitor
netsnmp-freespace.monitor
netsnmp-proc.monitor
nntp.monitor
ntp.monitor
ntservice.monitor
phttp.monitor
ping.monitor
pop3.monitor
postgresql.monitor
printmib.monitor
process-full-command-line.monitor
process.monitor
rd.monitor
reboot.monitor
remote.monitor
rpc.monitor
rptr.monitor
samba.monitor
seq.monitor
silkworm.monitor
smtp3.monitor
smtp.monitor
smtp_rt.monitor
snmp_interface.monitor
sqlconn.monitor
ssh.monitor
startremote.monitor
tcpch.monitor
tcp.monitor
telnet.monitor
traceroute.monitor
umn_mon.monitor
up_rtt.monitor
xedia-ipsec-tunnel.monitor

[root@cluster mon]# ls -1 /usr/lib/mon/alert.d/*.alert
aim.alert
bugzilla.alert
file.alert
gnats.alert
hpov.alert
irc.alert
mail.alert
netpage.alert
qpage.alert
sms.alert
snapdelete.alert
snpp.alert
test.alert
trap.alert
winpopup.alert

#!/usr/bin/perl
use strict;
use Getopt::Std;

getopts("s:g:h:t:l:u" . "D:S:");

# monが設定する共通オプション
my $summary      = <STDIN>; chomp $summary;
my $alert        = $Getopt::Std::opt_u ? "UPALERT" : "ALERT";
my $service      = $Getopt::Std::opt_s;
my $hostgroup    = $Getopt::Std::opt_g;
my $hostname     = $Getopt::Std::opt_h;
my $timesec      = $Getopt::Std::opt_t;
my $nextalertsec = $Getopt::Std::opt_l;

# このアラートスクリプトのオプション
my $dir      = $Getopt::Std::opt_D;
my $signal   = $Getopt::Std::opt_S;
my $progname = $1 if($0 =~ /([^\/]+)$/);

print "$progname: $hostgroup $hostname svc -$signal $dir\n";
exec "sudo", "svc", "-$signal", $dir

# swatch -t /var/log/messages &

ignore /パターン1/./パターン2/,....

watchfor /パターン1/
        アクション1
        アクション2
             :

[root@cluster rolls]# chkconfig --list swatch
swatch         0:off   1:off   2:off   3:off   4:off   5:off   6:off
[root@cluster rolls]# chkconfig mon swatch

#!/bin/bash
#
# swatch
#
# chkconfig: 2345 90 35
# description: swatch start/stop script

# Source function library.
. /etc/rc.d/init.d/functions

PATH=/sbin:/usr/local/bin:/bin:/usr/bin

mkdir -p /var/log/swatch

start() {
    # Start daemons.
    ls /var/run/swatch_*.pid > /dev/null 2>&1
    if [ $? -ne 0 ]; then
        echo -n "Starting swatch"
        pno=0
        for conf in /etc/swatch/*.conf
        do
            pno=`expr $pno + 1`
            WATCHLOG=`grep "^# logfile" $conf | awk '{ print $3 }'`
            swatch --config-file $conf --tail-file $WATCHLOG \
            --script-dir=/tmp --awk-field-syntax --use-cpan-file-tail --daemon \
            --pid-file /var/run/swatch_$pno.pid \
            >> /var/log/swatch/swatch.log 2>&1
            RETVAL=$?
            [ $RETVAL != 0 ] && return $RETVAL
        done
        echo
        [ $RETVAL = 0 ] && touch /var/lock/subsys/swatch
        return $RETVAL
    else
        echo "swatch is already started"
    fi
}

stop() {
    # Stop daemons.
    ls /var/run/swatch_*.pid > /dev/null 2>&1
    if [ $? -eq 0 ]; then
        echo -n "Shutting down swatch"
        for pid in /var/run/swatch_*.pid
        do
           kill $(cat $pid)
           rm -f $pid
        done
        echo
        rm -f /var/lock/subsys/swatch /tmp/.swatch_script.*
    else
        echo "swatch is not running"
    fi
}

status() {
    ls /var/run/swatch_*.pid > /dev/null 2>&1
    if [ $? -eq 0 ]; then
        echo -n "swatch (pid"
        for pid in /var/run/swatch_*.pid
        do
           echo -n " `cat $pid`"
        done
        echo ") is running..."
    else
        echo "swatch is stoped"
    fi
}

case "$1" in
  start)
        start
        ;;
  stop)
        stop
        ;;
  restart)
        stop
        start
        ;;
  status)
        status
        ;;
   *)
        echo "Usage: swatch {start|stop|restart|status}"
        exit 1
esac

exit $RETVAL