diff options
Diffstat (limited to 'abs')
| -rwxr-xr-x | abs/core/xymon/PKGBUILD | 12 | ||||
| -rwxr-xr-x[-rw-r--r--] | abs/core/xymon/alerts.cfg | 128 | ||||
| -rw-r--r-- | abs/core/xymon/analysis.cfg | 145 | ||||
| -rw-r--r-- | abs/core/xymon/hbnotes.py | 130 | ||||
| -rw-r--r-- | abs/core/xymon/hobbit_notify.sh | 67 |
5 files changed, 329 insertions, 153 deletions
diff --git a/abs/core/xymon/PKGBUILD b/abs/core/xymon/PKGBUILD index 0c797ee..a0c603b 100755 --- a/abs/core/xymon/PKGBUILD +++ b/abs/core/xymon/PKGBUILD @@ -1,7 +1,7 @@ pkgbase=xymon pkgname=(xymonserver xymonclient) pkgver=4.3.5 -pkgrel=49 +pkgrel=50 pkgdesc="Hobbit is a system for monitoring servers and networks. " license="GPL" arch=('i686' 'x86_64') @@ -128,17 +128,17 @@ md5sums=('31923ec126fe1c264fceb459d2175161' '758cdd9f1ba5ae3e1b42e811172806f3' 'ee608dcafc050d790e28647a670f6b60' 'b2f98ac0df013332deedc1efae0a270d' - 'c31bcb503a227ed5ff7b218581793bfc' + '1141fc6f846e91f380bbcdb212b44f7d' '0f70e76a164f648f0a4a01110137cb20' - 'f6921f0413215ae174e81306be80d37f' + 'b0664f3b38717dce911f59bcbd84e7a4' '80d9cfac86c6d96836e6f406e35e7cf5' 'd210c43fb9ee9ad6cd7648e0c2e0efea' '0c808fa12672289f86b0651545381308' '0469d775db9fdd18ea95dd41937ada82' '0757294eec13771f8e63da23cf066796' - '622f400fd098cbc43c203e3210a6694e' - '84442377c6e914b65519076bda4e17a4' - 'd7116dc59319b893e90a26e6beb83994' + '6baa410da1dfb86435191f4805186ea7' + '81715c58ae495812da0e0f18e2f74c76' + '77a542c2fd13468791ef23057ba8e77d' 'b4e8641e97e6b689dbc634af785e6799' 'e2844513e2c92e8b5084818f3b2a478d' '98e9242ae346f729b14cb195786571f2' diff --git a/abs/core/xymon/alerts.cfg b/abs/core/xymon/alerts.cfg index e458655..4f97f18 100644..100755 --- a/abs/core/xymon/alerts.cfg +++ b/abs/core/xymon/alerts.cfg @@ -1,6 +1,128 @@ +# +# The alerts.cfg file controls who receives alerts +# when a status in the XYmon system goes into a critical +# state (usually: red, yellow or purple). +# +# This file is made up from RULES and RECIPIENTS. +# +# A RULE is a filter made from the PAGE where a host +# is located in XYmon; the HOST name, the SERVICE name, +# the COLOR of the status, the TIME of day, and the +# DURATION of the event. +# +# A RECIPIENT can be a MAIL address, or a SCRIPT. +# +# Recipients can also have rules associated with them, +# that modify the rules for a single recipient, e.g. +# you can define a rule for alerting, then add an +# extra criteria e.g. so a single recipient does not get +# alerted until after 20 minutes. +# +# A sample rule: +# +# HOST=www.foo.com SERVICE=http +# MAIL webadmin@foo.com REPEAT=20 RECOVERED +# MAIL cio@foo.com DURATION>60 COLOR=red +# SCRIPT /usr/local/bin/sendsms 1234567890 FORMAT=SMS +# +# The first line sets up a rule that catches alerts +# for the host "www.foo.com" and the "http" service. +# There are three recipients for these alerts: The first +# one is the "webadmin@foo.com" - they get alerted +# immediately when the status goes into an alert state, +# and the alert is repeated every 20 minutes until it +# recovers. When it recovers, a message is sent about +# the recovery. +# +# The second recipient is "cio@foo.com". He gets alerted +# only when the service goes "red" for more than 60 minutes. +# +# The third recipient is a script, "/usr/local/bin/sendsms". +# The real recipient is "1234567890", but it is handled +# by the script - the script receives a set of environment +# variables with the details about the alert, including the +# real recipient. The alert message is preformatted for +# an SMS recipient. +# +# You can use Perl-compatible "regular expressions" for +# the PAGE, HOST and SERVICE definitions, by putting a "%" +# in front of the regex. E.g. +# +# HOST=%^www.* +# MAIL webadmin@foo.com EXHOST=www.testsite.foo.com +# +# This sets up a rule so that alerts from any hostname +# beginning with "www" goes to "webadmin@foo.com", EXCEPT +# alerts from "www.testsite.foo.com" +# +# The following keywords are recognized: +# PAGE - rule matching an alert by the name of the +# page in XYmon. This is the name following +# the "page", "subpage" or "subparent" keyword +# in the hosts.cfg file. +# EXPAGE - rule excluding an alert if the pagename matches. +# HOST - rule matching an alert by the hostname. +# EXHOST - rule excluding an alert by matching the hostname. +# SERVICE - rule matching an alert by the service name. +# EXSERVICE - rule excluding an alert by matching the hostname. +# GROUP - rule matching an alert by the group ID. +# (Group ID's are associated with a status through the +# analysis.cfg configuration). +# EXGROUP - rule excluding an alert by matching the group ID. +# COLOR - rule matching an alert by color. Can be "red", +# "yellow", or "purple". +# TIME - rule matching an alert by the time-of-day. This +# is specified as the DOWNTIME timespecification +# in the hosts.cfg file (see hosts.cfg(5)). +# DURATION - Rule matcing an alert if the event has lasted +# longer/shorter than the given duration. E.g. +# DURATION>10 (lasted longer than 10 minutes) or +# DURARION<30 (only sends alerts the first 30 minutes). +# RECOVERED - Rule matches if the alert has recovered from an +# alert state. +# NOTICE - Rule matches if the message is a "notify" message +# (typically sent when a status is enabled or disabled). +# MAIL - Recipient who receives an e-mail alert. This takes +# one parameter, the e-mail address. +# SCRIPT - Recipient that invokes a script. This takes two +# parameters: The script filename, and the recipient +# that gets passed to the script. +# FORMAT - format of the text message with the alert. Default +# is "TEXT" (suitable for e-mail alerts). "SMS" is +# a short message with no subject for SMS alerts. +# "SCRIPT" is a brief message template for scripts. +# REPEAT - How often an alert gets repeated, in minutes. +# STOP - Valid for a recipient: If this recipient gets an +# alert, recipients further down in alerts.cfg +# are ignored. +# UNMATCHED - Matches if no alerts have been sent so far. +# +# +# Script get the following environment variables pre-defined so +# that they can send a meaningful alert: +# +# BBCOLORLEVEL - The color of the alert: "red", "yellow" or "purple" +# BBALPHAMSG - The full text of the status log triggering the alert +# ACKCODE - The "cookie" that can be used to acknowledge the alert +# RCPT - The recipient, from the SCRIPT entry +# BBHOSTNAME - The name of the host that the alert is about +# MACHIP - The IP-address of the host that has a problem +# BBSVCNAME - The name of the service that the alert is about +# BBSVCNUM - The numeric code for the service. From SVCCODES definition. +# BBHOSTSVC - HOSTNAME.SERVICE that the alert is about. +# BBHOSTSVCCOMMAS - As BBHOSTSVC, but dots in the hostname replaced with commas +# BBNUMERIC - A 22-digit number made by BBSVCNUM, MACHIP and ACKCODE. +# RECOVERED - Is "1" if the service has recovered. +# DOWNSECS - Number of seconds the service has been down. +# DOWNSECSMSG - When recovered, holds the text "Event duration : N" where +# N is the DOWNSECS value. -HOST=* SERVICE=disk - SCRIPT /home/xymon/server/bin/hobbit_notify.sh 1234567890 FORMAT=SMS REPEAT=10h COLOR=yellow - SCRIPT /home/xymon/server/bin/hobbit_notify.sh 1234567890 FORMAT=SMS REPEAT=1h COLOR=red + +HOST=* SERVICE=func + SCRIPT /home/xymon/server/bin/hobbit_notify.sh 1234567890 FORMAT=SMS DURATION=4h REPEAT=48h COLOR=red + +HOST=* SERVICE=* EXSERVICE=conn + SCRIPT /home/xymon/server/bin/hobbit_notify.sh 1234567890 FORMAT=SMS DURATION=4h REPEAT=12h COLOR=red +# SCRIPT /home/xymon/server/bin/hobbit_notify.sh 1234567890 FORMAT=SMS DURATION=4H REPEAT=12H COLOR=yellow diff --git a/abs/core/xymon/analysis.cfg b/abs/core/xymon/analysis.cfg index 0de317b..da833e1 100644 --- a/abs/core/xymon/analysis.cfg +++ b/abs/core/xymon/analysis.cfg @@ -348,81 +348,98 @@ HOST=_MASTERBACKEND_ - PROC sshd 1 - PROC lighttpd - PROC hobbitd - PROC crond - PROC mysql - PROC mythbackend - DISK * 95 99 - PORT "LOCAL=%([.:]80)$" state=LISTEN TEXT=http - PORT "LOCAL=%([.:]1337)$" state=LISTEN TEXT=cgi - PORT "LOCAL=%([.:]22)$" state=LISTEN TEXT=ssh + PROC sshd 1 + PROC lighttpd + PROC xymond + PROC crond + PROC mysql + PROC mythbackend + PROC msg_daemon.py + DISK %^/cdrom.* IGNORE + DISK %^/mnt.* IGNORE + DISK %^/media.* IGNORE + DISK * 95 99 + PORT "LOCAL=%([.:]80)$" state=LISTEN TEXT=http + PORT "LOCAL=%([.:]1337)$" state=LISTEN TEXT=cgi + PORT "LOCAL=%([.:]22)$" state=LISTEN TEXT=ssh HOST=_MASTERFRONTEND_ - PROC mythfrontend - PROC sshd 1 - PROC lighttpd - PROC hobbitd - PROC crond - PROC mysql - PROC mythbackend - DISK * 95 99 - PORT "LOCAL=%([.:]80)$" state=LISTEN TEXT=http - PORT "LOCAL=%([.:]1337)$" state=LISTEN TEXT=cgi - PORT "LOCAL=%([.:]22)$" state=LISTEN TEXT=ssh - PORT "LOCAL=%([.:]5000)$" state=LISTEN TEXT=ghosd - PORT "LOCAL=%([.:]5001)$" state=LISTEN TEXT=ghosd + PROC mythfrontend + PROC sshd 1 + PROC lighttpd + PROC xymond + PROC crond + PROC mysql + PROC mythbackend + PROC msg_daemon.py + DISK %^/cdrom.* IGNORE + DISK %^/mnt.* IGNORE + DISK %^/media.* IGNORE + DISK * 95 99 + PORT "LOCAL=%([.:]80)$" state=LISTEN TEXT=http + PORT "LOCAL=%([.:]1337)$" state=LISTEN TEXT=cgi + PORT "LOCAL=%([.:]22)$" state=LISTEN TEXT=ssh + HOST=_FRONTEND_ - PROC sshd 1 - PROC crond - PROC mythfrontend - PORT "LOCAL=%([.:]22)$" state=LISTEN TEXT=ssh - PORT "LOCAL=%([.:]5000)$" state=LISTEN TEXT=ghosd - PORT "LOCAL=%([.:]5001)$" state=LISTEN TEXT=ghosd + PROC sshd 1 + PROC crond + PROC mythfrontend + PROC msg_daemon.py + PORT "LOCAL=%([.:]22)$" state=LISTEN TEXT=ssh HOST=_SLAVEBACKEND_ - PROC sshd 1 - PROC crond - PROC mythbackend - DISK * 95 99 - PORT "LOCAL=%([.:]22)$" state=LISTEN TEXT=ssh + PROC sshd 1 + PROC crond + PROC mythbackend + DISK %^/cdrom.* IGNORE + DISK %^/mnt.* IGNORE + DISK %^/media.* IGNORE + DISK * 95 99 + PORT "LOCAL=%([.:]22)$" state=LISTEN TEXT=ssh HOST=_SLAVEFRONTEND_ - PROC sshd 1 - PROC lighttpd - PROC hobbitd - PROC crond - PROC mythbackend - PROC mythfrontend - DISK * 95 99 - PORT "LOCAL=%([.:]22)$" state=LISTEN TEXT=ssh - PORT "LOCAL=%([.:]5000)$" state=LISTEN TEXT=ghosd - PORT "LOCAL=%([.:]5001)$" state=LISTEN TEXT=ghosd + PROC sshd 1 + PROC lighttpd + PROC hobbitd + PROC crond + PROC mythbackend + PROC mythfrontend + PROC msg_daemon.py + DISK %^/cdrom.* IGNORE + DISK %^/mnt.* IGNORE + DISK %^/media.* IGNORE + DISK * 95 99 + PORT "LOCAL=%([.:]22)$" state=LISTEN TEXT=ssh + HOST=_STANDALONE_ - PROC sshd 1 - PROC lighttpd - PROC hobbitd - PROC crond - PROC mysql - PROC mythbackend - DISK * 95 99 - PORT "LOCAL=%([.:]22)$" state=LISTEN TEXT=ssh - PORT "LOCAL=%([.:]5000)$" state=LISTEN TEXT=ghosd - PORT "LOCAL=%([.:]5001)$" state=LISTEN TEXT=ghosd - PORT "LOCAL=%([.:]80)$" state=LISTEN TEXT=http - PORT "LOCAL=%([.:]1337)$" state=LISTEN TEXT=cgi - PORT "LOCAL=%([.:]22)$" state=LISTEN TEXT=ssh + PROC mythfrontend + PROC sshd 1 + PROC lighttpd + PROC xymond + PROC crond + PROC mysql + PROC mythbackend + PROC msg_daemon.py + DISK %^/cdrom.* IGNORE + DISK %^/mnt.* IGNORE + DISK %^/media.* IGNORE + DISK * 95 99 + PORT "LOCAL=%([.:]80)$" state=LISTEN TEXT=http + PORT "LOCAL=%([.:]1337)$" state=LISTEN TEXT=cgi + PORT "LOCAL=%([.:]22)$" state=LISTEN TEXT=ssh DEFAULT - # These are the built-in defaults. - UP 1h - LOAD 5.0 10.0 - DISK * 99 100 - MEMPHYS 100 101 - MEMSWAP 50 80 - MEMACT 90 97 + # These are the built-in defaults. + UP 1h + LOAD 5.0 10.0 + DISK %^/cdrom.* IGNORE + DISK %^/mnt.* IGNORE + DISK %^/media.* IGNORE + DISK * 99 100 + MEMPHYS 100 101 + MEMSWAP 50 80 + MEMACT 90 97 diff --git a/abs/core/xymon/hbnotes.py b/abs/core/xymon/hbnotes.py index d643044..b5ad72a 100644 --- a/abs/core/xymon/hbnotes.py +++ b/abs/core/xymon/hbnotes.py @@ -28,7 +28,7 @@ def create_dot_file(): result = cursor.fetchall() frontonly="_FRONTEND_" masterbackend="_MASTERBACKEND_" - masterbacked_w_fe="_MASTERFE_" + masterbacked_w_fe="_MASTERFRONTEND_" slave_w_fe="_SLAVEFE_" slave="_SLAVEBACKEND_" stand_alone="_STANDALONE_" @@ -166,7 +166,8 @@ def create_dot_file(): # cmd="/usr/bin/circo -Tpng -o/data/srv/httpd/htdocs/xymon/gifs/network.png " + dotfilename results=os.popen(cmd,'r') - + return frontonly,masterbackend,masterbacked_w_fe,slave_w_fe,slave,stand_alone + @@ -458,68 +459,73 @@ function Do_it () file.write(string) -def main(argv): - create_dot_file() - create_notes() - +def create_hobbit_analysis(frontonly, + masterbackend, + masterbacked_w_fe, + slave_w_fe, + slave, + stand_alone): -#------------------------------write client-config------------------------------------------------ - - - #-------------------------------------------------- - #hobbitfile="/home/xymon/server/etc/hobbit-clients.cfg" - - ###WHY WAS THIS HERE?? - #hobbitfile="/home/xymon/server/etc/tasks.cfg" - #hobbitf=open(hobbitfile,'r') - #hobbitconfig=hobbitf.readlines() - #hobbitf.close() - #hobbitf=open(hobbitfile,'w') - #print "FE",frontonly - #print "MBE",masterbackend - #print "MBEwFW",masterbacked_w_fe - #print "SLAVEwFW",slave_w_fe - #print "SLAVE",slave - #print "STD",stand_alone - - #for line in hobbitconfig: - #if line.startswith("HOST"): - #cline=line.split("=") - #if cline[1].startswith("_FRONTEND_"): - #pline="HOST=" - #pline+=frontonly.strip() - #hobbitf.write(pline + "\n") - #elif cline[1].startswith("_MASTERBACKEND_"): - #pline="HOST=" - #pline+=masterbackend.strip() - ##print pline - #hobbitf.write(pline+ "\n") - #elif cline[1].startswith("_MASTERFRONTEND_"): - #pline="HOST=" - #pline+=masterbacked_w_fe.strip() - ##print pline - #hobbitf.write(pline+ "\n") - #elif cline[1].startswith("_SLAVEBACKEND_"): - #pline="HOST=" - #pline+=slave.strip() - ##print pline - #hobbitf.write(pline+ "\n") - #elif cline[1].startswith("_SLAVEFE_"): - #pline="HOST=" - #pline+=slave_w_fe.strip() - ##print pline - #hobbitf.write(pline+ "\n") - #else: - ##print line - #hobbitf.write(line) - #else: - ##print line - #hobbitf.write(line) - -#-----------------------------------------------------------END CLIENT CONFIG - - # execute SQL statement + hobbitfile="/home/xymon/server/etc/analysis.cfg" + hobbitf=open(hobbitfile,'r') + hobbitconfig=hobbitf.readlines() + hobbitf.close() + try: + hobbitf=open(hobbitfile,'w') + print "FE",frontonly + print "MBE",masterbackend + print "MBEwFW",masterbacked_w_fe + print "SLAVEwFW",slave_w_fe + print "SLAVE",slave + print "STD",stand_alone + + for line in hobbitconfig: + if line.startswith("HOST"): + cline=line.split("=") + if cline[1].startswith("_FRONTEND_"): + pline="HOST=" + pline+=frontonly.strip() + hobbitf.write(pline + "\n") + elif cline[1].startswith("_MASTERBACKEND_"): + pline="HOST=" + pline+=masterbackend.strip() + #print pline + hobbitf.write(pline+ "\n") + elif cline[1].startswith("_MASTERFRONTEND_"): + pline="HOST=" + pline+=masterbacked_w_fe.strip() + #print pline + hobbitf.write(pline+ "\n") + elif cline[1].startswith("_SLAVEBACKEND_"): + pline="HOST=" + pline+=slave.strip() + #print pline + hobbitf.write(pline+ "\n") + elif cline[1].startswith("_SLAVEFE_"): + pline="HOST=" + pline+=slave_w_fe.strip() + #print pline + hobbitf.write(pline+ "\n") + else: + #print line + hobbitf.write(line) + else: + #print line + hobbitf.write(line) + hobbitf.close() + except: + print "problem writing analysis.cfg" +def main(argv): + frontonly,masterbackend,masterbacked_w_fe,slave_w_fe,slave,stand_alone = create_dot_file() + create_notes() + create_hobbit_analysis(frontonly, + masterbackend, + masterbacked_w_fe, + slave_w_fe, + slave, + stand_alone) + if __name__ == "__main__": main(sys.argv[1:]) diff --git a/abs/core/xymon/hobbit_notify.sh b/abs/core/xymon/hobbit_notify.sh index 7569e2a..742b3db 100644 --- a/abs/core/xymon/hobbit_notify.sh +++ b/abs/core/xymon/hobbit_notify.sh @@ -1,4 +1,5 @@ #!/bin/bash +. /etc/systemconfig # # BBCOLORLEVEL - The color of the alert: "red", "yellow" or "purple" # BBALPHAMSG - The full text of the status log triggering the alert @@ -14,35 +15,65 @@ # RECOVERED - Is "1" if the service has recovered. # DOWNSECS - Number of seconds the service has been down. # DOWNSECSMSG - When recovered, holds the text "Event duration : N" where -echo $BBCOLORLEVEL > /tmp/hobbitout -echo $BBALPHAMSG >>/tmp/hobbitout -echo $RCPT >>/tmp/hobbitout -echo $BBHOSTNAME >>/tmp/hobbitout -echo $BBSVCNAME >>/tmp/hobbitout -echo $BBHOSTSVC >>/tmp/hobbitout + + +# echo $BBCOLORLEVEL > /tmp/hobbitout +# echo $BBALPHAMSG >>/tmp/hobbitout +# echo $RCPT >>/tmp/hobbitout +# echo $BBHOSTNAME >>/tmp/hobbitout +# echo $BBSVCNAME >>/tmp/hobbitout +# echo $BBHOSTSVC >>/tmp/hobbitout #BBCOLORLEVEL=red #BBCOLORLEVEL=yellow #BBALPHAMSG="vmtest:disk red [751147]" -#BBHOSTNAME="vmtest" +#BBHOSTNAME="testcraa" #BBSVCNAME="disk" +#BBSVCNAME="func" #BBHOSTSVC="vmtest.disk" -if [ x$BBSVCNAME = xdisk ] -then - case $BBCOLORLEVEL in - red ) - /usr/bin/notify.py ALT "$BBHOSTNAME disk is full" - ;; - yellow ) +#/usr/LH/bin/msg_client.py --msg "$BBCOLORLEVEL\n$BBHOSTSVC" +#/usr/bin/func "*" call msg display + +function msg_func_out() { + /usr/bin/func "*" call msg display "${1}" +} + +function msg_local_out() { + + /usr/LH/bin/msg_client.py --msg "${1}" + + } + - /usr/bin/notify.py PHN "$BBHOSTNAME disk almost full " - ;; - esac -fi +case x$BBSVCNAME in + xdisk) + case $BBCOLORLEVEL in + red ) + msg_func_out "$BBHOSTNAME disk is at 95% full or greater|alert" + ;; + yellow ) + msg_func_out "$BBHOSTNAME disk is almost full" + ;; + esac + ;; + + xfunc) + if [ "x$hostname" = "x$BBHOSTNAME" ] + then + msg_local_out "System can not communicate with itself (func) |alert" + else + msg_func_out "$hostname can not communicate with $BBHOSTNAME (func)|alert" + fi + ;; + *) + #catch all for everything else + msg_func_out "Condition $BBCOLORLEVEL\n$BBHOSTNAME $BBSVCNAME\n Please check the system health webpage|alert" + ;; +esac |