Merge pull request plambe#3 from ixcat/master

split/version agent configuration file sections, install makefile & more plots
tweiers · Jun 6, 2018 · 3c2f29a · 3c2f29a
2 parents 3c0f521 + 881e21d
commit 3c2f29a
Show file tree

Hide file tree

Showing 5 changed files with 114 additions and 27 deletions.
diff --git a/Makefile b/Makefile
@@ -0,0 +1,16 @@
+# installation makefile - 
+# tested against zabbix.com 3.x packages on ubuntu 16.04
+
+all:
+	@echo "usage: make install"
+
+install: install-agent-config install-script
+
+install-agent-config:
+	install -o root -g root -m 644 userparameter_nvidia-smi.conf.linux \
+		/etc/zabbix/zabbix_agentd.d/userparameter_nvidia-smi.conf
+
+install-script:
+	install -d -o root -g root -m 755 /etc/zabbix/scripts
+	install -o root -g root -m 755 get_gpus_info.sh /etc/zabbix/scripts
+
diff --git a/README.md b/README.md
@@ -25,18 +25,7 @@ This is essentially a multi-GPU rewrite of RichardKav's template, as found here:
 
 ## On Windows:
 
-```
-UserParameter=gpu.number,"C:\Program Files\NVIDIA Corporation\NVSMI\nvidia-smi.exe" -L | find /c /v ""
-UserParameter=gpu.discovery,C:\scripts\get_gpus_info.bat
-UserParameter=gpu.fanspeed[*],"C:\Program Files\NVIDIA Corporation\NVSMI\nvidia-smi.exe" --query-gpu=fan.speed --format=csv,noheader,nounits -i $1
-UserParameter=gpu.power[*],"C:\Program Files\NVIDIA Corporation\NVSMI\nvidia-smi.exe" --query-gpu=power.draw --format=csv,noheader,nounits -i $1
-UserParameter=gpu.temp[*],"C:\Program Files\NVIDIA Corporation\NVSMI\nvidia-smi.exe" --query-gpu=temperature.gpu --format=csv,noheader,nounits -i $1
-UserParameter=gpu.utilization[*],"C:\Program Files\NVIDIA Corporation\NVSMI\nvidia-smi.exe" --query-gpu=utilization.gpu --format=csv,noheader,nounits -i $1
-UserParameter=gpu.memfree[*],"C:\Program Files\NVIDIA Corporation\NVSMI\nvidia-smi.exe" --query-gpu=memory.free --format=csv,noheader,nounits -i $1
-UserParameter=gpu.memused[*],"C:\Program Files\NVIDIA Corporation\NVSMI\nvidia-smi.exe" --query-gpu=memory.used --format=csv,noheader,nounits -i $1
-UserParameter=gpu.memtotal[*],"C:\Program Files\NVIDIA Corporation\NVSMI\nvidia-smi.exe" --query-gpu=memory.total --format=csv,noheader,nounits -i $1
-```
-
+* Add the contents of the file `userparameter_nvidia-smi.conf.windows` to your zabbix_agentd.conf file.
 * The Windows script get_gpus_info.bat file should be put in C:\scripts\
 * It doesn't have any dependencies, other than having nvidia-smi.exe
 * Of course, it is possible to use other paths, but: 
@@ -46,20 +35,8 @@ UserParameter=gpu.memtotal[*],"C:\Program Files\NVIDIA Corporation\NVSMI\nvidia-
 ## On Linux: 
 
 The following UserParameters need to be added to the zabbix-agent configuration: 
-
-```
-UserParameter=gpu.number,/usr/bin/nvidia-smi -L | /bin/grep GeForce | /usr/bin/wc -l
-UserParameter=gpu.discovery,/etc/zabbix/scripts/get_gpus_info.sh
-UserParameter=gpu.fanspeed[*],nvidia-smi --query-gpu=fan.speed --format=csv,noheader,nounits -i $1 | tr -d "\n"
-UserParameter=gpu.power[*],nvidia-smi --query-gpu=power.draw --format=csv,noheader,nounits -i $1 | tr -d "\n"
-UserParameter=gpu.temp[*],nvidia-smi --query-gpu=temperature.gpu --format=csv,noheader,nounits -i $1 | tr -d "\n"
-UserParameter=gpu.utilization[*],nvidia-smi --query-gpu=utilization.gpu --format=csv,noheader,nounits -i $1 | tr -d "\n"
-UserParameter=gpu.memfree[*],nvidia-smi --query-gpu=memory.free --format=csv,noheader,nounits -i $1 | tr -d "\n"
-UserParameter=gpu.memused[*],nvidia-smi --query-gpu=memory.used --format=csv,noheader,nounits -i $1 | tr -d "\n"
-UserParameter=gpu.memtotal[*],nvidia-smi --query-gpu=memory.total --format=csv,noheader,nounits -i $1 | tr -d "\n"
-```
-
-The get_gpus_info.sh file should be put in /etc/zabbix/scripts/ and made executable by running ```chmod +x get_gpus_info.sh```
+* Add the contents of the file `userparameter_nvidia-smi.conf.linux` to your zabbix_agentd.conf file.
+* The get_gpus_info.sh file should be put in /etc/zabbix/scripts/ and made executable by running ```chmod +x get_gpus_info.sh```
 
 ## If you feel like donating:
 

diff --git a/userparameter_nvidia-smi.conf.linux b/userparameter_nvidia-smi.conf.linux
@@ -0,0 +1,9 @@
+UserParameter=gpu.number,/usr/bin/nvidia-smi -L | /bin/grep GeForce | /usr/bin/wc -l
+UserParameter=gpu.discovery,/etc/zabbix/scripts/get_gpus_info.sh
+UserParameter=gpu.fanspeed[*],nvidia-smi --query-gpu=fan.speed --format=csv,noheader,nounits -i $1 | tr -d "\n"
+UserParameter=gpu.power[*],nvidia-smi --query-gpu=power.draw --format=csv,noheader,nounits -i $1 | tr -d "\n"
+UserParameter=gpu.temp[*],nvidia-smi --query-gpu=temperature.gpu --format=csv,noheader,nounits -i $1 | tr -d "\n"
+UserParameter=gpu.utilization[*],nvidia-smi --query-gpu=utilization.gpu --format=csv,noheader,nounits -i $1 | tr -d "\n"
+UserParameter=gpu.memfree[*],nvidia-smi --query-gpu=memory.free --format=csv,noheader,nounits -i $1 | tr -d "\n"
+UserParameter=gpu.memused[*],nvidia-smi --query-gpu=memory.used --format=csv,noheader,nounits -i $1 | tr -d "\n"
+UserParameter=gpu.memtotal[*],nvidia-smi --query-gpu=memory.total --format=csv,noheader,nounits -i $1 | tr -d "\n"
diff --git a/userparameter_nvidia-smi.conf.windows b/userparameter_nvidia-smi.conf.windows
@@ -0,0 +1,9 @@
+UserParameter=gpu.number,"C:\Program Files\NVIDIA Corporation\NVSMI\nvidia-smi.exe" -L | find /c /v ""
+UserParameter=gpu.discovery,C:\scripts\get_gpus_info.bat
+UserParameter=gpu.fanspeed[*],"C:\Program Files\NVIDIA Corporation\NVSMI\nvidia-smi.exe" --query-gpu=fan.speed --format=csv,noheader,nounits -i $1
+UserParameter=gpu.power[*],"C:\Program Files\NVIDIA Corporation\NVSMI\nvidia-smi.exe" --query-gpu=power.draw --format=csv,noheader,nounits -i $1
+UserParameter=gpu.temp[*],"C:\Program Files\NVIDIA Corporation\NVSMI\nvidia-smi.exe" --query-gpu=temperature.gpu --format=csv,noheader,nounits -i $1
+UserParameter=gpu.utilization[*],"C:\Program Files\NVIDIA Corporation\NVSMI\nvidia-smi.exe" --query-gpu=utilization.gpu --format=csv,noheader,nounits -i $1
+UserParameter=gpu.memfree[*],"C:\Program Files\NVIDIA Corporation\NVSMI\nvidia-smi.exe" --query-gpu=memory.free --format=csv,noheader,nounits -i $1
+UserParameter=gpu.memused[*],"C:\Program Files\NVIDIA Corporation\NVSMI\nvidia-smi.exe" --query-gpu=memory.used --format=csv,noheader,nounits -i $1
+UserParameter=gpu.memtotal[*],"C:\Program Files\NVIDIA Corporation\NVSMI\nvidia-smi.exe" --query-gpu=memory.total --format=csv,noheader,nounits -i $1
diff --git a/zbx_nvidia-smi-multi-gpu.xml b/zbx_nvidia-smi-multi-gpu.xml
@@ -1,7 +1,7 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <zabbix_export>
     <version>3.0</version>
-    <date>2018-01-31T17:55:26Z</date>
+    <date>2018-06-05T20:56:12Z</date>
     <groups>
         <group>
             <name>Templates</name>
@@ -443,6 +443,50 @@
                         </trigger_prototype>
                     </trigger_prototypes>
                     <graph_prototypes>
+                        <graph_prototype>
+                            <name>GPU {#GPUINDEX} Memory</name>
+                            <width>900</width>
+                            <height>200</height>
+                            <yaxismin>0.0000</yaxismin>
+                            <yaxismax>100.0000</yaxismax>
+                            <show_work_period>1</show_work_period>
+                            <show_triggers>1</show_triggers>
+                            <type>0</type>
+                            <show_legend>1</show_legend>
+                            <show_3d>0</show_3d>
+                            <percent_left>0.0000</percent_left>
+                            <percent_right>0.0000</percent_right>
+                            <ymin_type_1>0</ymin_type_1>
+                            <ymax_type_1>0</ymax_type_1>
+                            <ymin_item_1>0</ymin_item_1>
+                            <ymax_item_1>0</ymax_item_1>
+                            <graph_items>
+                                <graph_item>
+                                    <sortorder>0</sortorder>
+                                    <drawtype>0</drawtype>
+                                    <color>00AA00</color>
+                                    <yaxisside>0</yaxisside>
+                                    <calc_fnc>2</calc_fnc>
+                                    <type>0</type>
+                                    <item>
+                                        <host>Template Nvidia GPUs Performance</host>
+                                        <key>gpu.memfree[{#GPUINDEX}]</key>
+                                    </item>
+                                </graph_item>
+                                <graph_item>
+                                    <sortorder>1</sortorder>
+                                    <drawtype>0</drawtype>
+                                    <color>0000DD</color>
+                                    <yaxisside>0</yaxisside>
+                                    <calc_fnc>2</calc_fnc>
+                                    <type>0</type>
+                                    <item>
+                                        <host>Template Nvidia GPUs Performance</host>
+                                        <key>gpu.memused[{#GPUINDEX}]</key>
+                                    </item>
+                                </graph_item>
+                            </graph_items>
+                        </graph_prototype>
                         <graph_prototype>
                             <name>GPU {#GPUINDEX} Temperature, Fan Speed and Power</name>
                             <width>900</width>
@@ -499,6 +543,38 @@
                                 </graph_item>
                             </graph_items>
                         </graph_prototype>
+                        <graph_prototype>
+                            <name>GPU {#GPUINDEX} Utilization</name>
+                            <width>900</width>
+                            <height>200</height>
+                            <yaxismin>0.0000</yaxismin>
+                            <yaxismax>100.0000</yaxismax>
+                            <show_work_period>1</show_work_period>
+                            <show_triggers>1</show_triggers>
+                            <type>0</type>
+                            <show_legend>1</show_legend>
+                            <show_3d>0</show_3d>
+                            <percent_left>0.0000</percent_left>
+                            <percent_right>0.0000</percent_right>
+                            <ymin_type_1>0</ymin_type_1>
+                            <ymax_type_1>0</ymax_type_1>
+                            <ymin_item_1>0</ymin_item_1>
+                            <ymax_item_1>0</ymax_item_1>
+                            <graph_items>
+                                <graph_item>
+                                    <sortorder>0</sortorder>
+                                    <drawtype>0</drawtype>
+                                    <color>2774A4</color>
+                                    <yaxisside>0</yaxisside>
+                                    <calc_fnc>2</calc_fnc>
+                                    <type>0</type>
+                                    <item>
+                                        <host>Template Nvidia GPUs Performance</host>
+                                        <key>gpu.utilization[{#GPUINDEX}]</key>
+                                    </item>
+                                </graph_item>
+                            </graph_items>
+                        </graph_prototype>
                     </graph_prototypes>
                     <host_prototypes/>
                 </discovery_rule>