Difference between revisions of "Xymon custom graph config"

Revision as of 16:39, 21 July 2011 (view source) Rday (Talk | contribs) (Created page with "===collect the data with a script=== hobbit server:/usr/lib/hobbit/client/ext/cputemp: <pre> #!/bin/sh #/usr/bin/sensors -f | grep "CPU Temp" | awk '{print $1 $2 $3}' | # awk {'…")		Revision as of 16:53, 21 July 2011 (view source) Rday (Talk | contribs) Newer edit →
Line 33:		Line 33:
	exit 0		exit 0
	</pre>		</pre>
		+	* you can run the script from the command line to test it
		+	===launch the script with hobbit===
		+	hobbit server:/usr/lib/hobbit/server/etc/hobbitlaunch.cfg:
		+	<pre>
		+	[cputemp]
		+	ENVFILE /usr/lib/hobbit/client/etc/hobbitclient.cfg
		+	CMD /usr/lib/hobbit/client/ext/cputemp
		+	INTERVAL 5m
		+	</pre>
		+	hobbit client:/usr/lib/hobbit/client/etc/hobbitlaunch.cfg
		+	* wait for five minutes and then you should see the data in the web interface, but not the graph
		+	===collect the data in an RRD===
		+	hobbit server:/usr/lib/hobbit/server/etc/hobbitserver.cfg
		+	<pre>
		+	TEST2RRD="cpu=la,disk,inode,qtree,memory,$PINGCOLUMN=tcp,http=tcp,dns=tcp,dig=tcp,time=ntpstat,vmstat,iostat,netstat,temperature,apache,bind,sendmail,mailq,nmailq=mailq,socks,bea,iishealth,citrix,bbgen,bbtest,bbproxy,hobbitd,files,procs=processes,ports,clock,lines,ops,stats,cifs,JVM,JMS,HitCache,Session,JDBCConn,ExecQueue,JTA,TblSpace,RollBack,MemReq,InvObj,snapmirr,snaplist,snapshot,if_load=devmon,temp=devmon,paging,mdc,mdchitpct,cics,dsa,getvis,maxuser,nparts,cputemp=ncv,heater=ncv"
		+	</pre>
		+
		+	<pre>
		+	NCV_cputemp="temp1:GAUGE,Core0Temp:GAUGE,Core1Temp:GAUGE"
		+	</pre>
		+
		+	*restart hobbit after making these changes
		+
		+	* you can verify the RRD:
		+	hobbit server:/var/lib/hobbit/rrd/localhost/cputemp.rrd
		+	<pre>
		+	root@weasel:/var/lib/hobbit/rrd/localhost# rrdtool info ./cputemp.rrd
		+	filename = "./cputemp.rrd"
		+	rrd_version = "0003"
		+	step = 300
		+	last_update = 1311266629
		+	header_size = 2320
		+	ds[temp1].index = 0
		+	ds[temp1].type = "GAUGE"
		+	ds[temp1].minimal_heartbeat = 600
		+	ds[temp1].min = NaN
		+	ds[temp1].max = NaN
		+	ds[temp1].last_ds = "131"
		+	ds[temp1].value = 2.9999000000e+04
		+	ds[temp1].unknown_sec = 0
		+
		+	root@weasel:/var/lib/hobbit/rrd/localhost# ls -lt cputemp.rrd
		+	-rw-r--r-- 1 hobbit hobbit 57616 2011-07-21 09:43 cputemp.rrd
		+	</pre>
		+
		+	The timestamp on the file should be less than 5 minutes old and the data inside should correspond to the output of the script.
		+	===create a graph definition===

---

Revision as of 16:53, 21 July 2011

collect the data with a script

hobbit server:/usr/lib/hobbit/client/ext/cputemp:

#!/bin/sh

#/usr/bin/sensors -f | grep "CPU Temp" | awk '{print $1 $2 $3}' |
#	awk {'sub("\+", ""); sub("°F", ""); print }' > /tmp/cputemp.txt
#/usr/bin/sensors -f | grep -i temp | grep -v k8temp| awk '{ sub("°F", ""); sub("\+", ""); sub("/", ""); sub(" +", ""); sub("\(.*$", ""); print}' > /tmp/cputemp.txt

RAWTEMP=`nvidia-smi -a | grep Temperature | sed -e "s/.*.://g" -e "s/C//g"`
FGPUTEMP=$((${RAWTEMP:-0}*9/5+32))
echo "temp1:$FGPUTEMP" > /tmp/cputemp.txt

/usr/bin/sensors -f | grep Temp | grep -v k8temp | awk '{sub(".F.*$",
""); sub(" +",""); sub("+",""); print}' >> /tmp/cputemp.txt

RESULT=`grep Core0Temp /tmp/cputemp.txt | awk '{ FS=":";  print int($2) }'`;
COLOR=green
if test "$RESULT" -gt 120
then
	COLOR=red
fi
if test "$RESULT" -lt 70
then
	COLOR=red
fi

$BB $BBDISP "status $MACHINE.cputemp $COLOR `date`

`cat /tmp/cputemp.txt`
"

exit 0

• you can run the script from the command line to test it

launch the script with hobbit

hobbit server:/usr/lib/hobbit/server/etc/hobbitlaunch.cfg:

[cputemp]
    ENVFILE /usr/lib/hobbit/client/etc/hobbitclient.cfg
    CMD /usr/lib/hobbit/client/ext/cputemp
    INTERVAL 5m

hobbit client:/usr/lib/hobbit/client/etc/hobbitlaunch.cfg

• wait for five minutes and then you should see the data in the web interface, but not the graph

collect the data in an RRD

hobbit server:/usr/lib/hobbit/server/etc/hobbitserver.cfg

TEST2RRD="cpu=la,disk,inode,qtree,memory,$PINGCOLUMN=tcp,http=tcp,dns=tcp,dig=tcp,time=ntpstat,vmstat,iostat,netstat,temperature,apache,bind,sendmail,mailq,nmailq=mailq,socks,bea,iishealth,citrix,bbgen,bbtest,bbproxy,hobbitd,files,procs=processes,ports,clock,lines,ops,stats,cifs,JVM,JMS,HitCache,Session,JDBCConn,ExecQueue,JTA,TblSpace,RollBack,MemReq,InvObj,snapmirr,snaplist,snapshot,if_load=devmon,temp=devmon,paging,mdc,mdchitpct,cics,dsa,getvis,maxuser,nparts,cputemp=ncv,heater=ncv"

NCV_cputemp="temp1:GAUGE,Core0Temp:GAUGE,Core1Temp:GAUGE"

• restart hobbit after making these changes

• you can verify the RRD:

hobbit server:/var/lib/hobbit/rrd/localhost/cputemp.rrd

root@weasel:/var/lib/hobbit/rrd/localhost# rrdtool info ./cputemp.rrd 
filename = "./cputemp.rrd"
rrd_version = "0003"
step = 300
last_update = 1311266629
header_size = 2320
ds[temp1].index = 0
ds[temp1].type = "GAUGE"
ds[temp1].minimal_heartbeat = 600
ds[temp1].min = NaN
ds[temp1].max = NaN
ds[temp1].last_ds = "131"
ds[temp1].value = 2.9999000000e+04
ds[temp1].unknown_sec = 0

root@weasel:/var/lib/hobbit/rrd/localhost# ls -lt cputemp.rrd 
-rw-r--r-- 1 hobbit hobbit 57616 2011-07-21 09:43 cputemp.rrd

The timestamp on the file should be less than 5 minutes old and the data inside should correspond to the output of the script.

create a graph definition