Add tickscipts for telegraf

README.md

@@ -28,7 +28,7 @@ kapacitord config
 # Getting Started
 
 This README gives you a high level overview of what Kapacitor is and what its like to use it. As well as some details of how it works.
-To get started using Kapacitor see [this guide](https://docs.influxdata.com/kapacitor/latest/introduction/getting_started/).
+To get started using Kapacitor see [this guide](https://docs.influxdata.com/kapacitor/latest/introduction/getting_started/). After you finish the getting started exercise you can check out the [TICKscripts](https://github.com/influxdata/kapacitor/tree/master/examples/telegraf) for different Telegraf plugins.
 
 # Basic Example
 
@@ -79,4 +79,4 @@ kapacitor define \
 kapacitor enable cpu_alert
 ```
 
-For more complete examples see the [documentation](https://docs.influxdata.com/kapacitor/latest/examples/)
+For more complete examples see the [documentation](https://docs.influxdata.com/kapacitor/latest/examples/).

examples/telegraf/README.md

@@ -0,0 +1,127 @@
+# `telegraf`
+
+`telegraf` contains tickscripts for individual [telegraf](github.com/influxdata/telegraf) plugins. The directories at the root of the repo are named for the telegraf plugin they reference. There is a common structure for each of the tickscripts so as to be consistent and easily understandable for beginners. Each of the scripts are broken up into a few different sections:
+
+* Comments
+  - Name of the alert
+  - Name of field to alert on and other fields available from the telegraf plugin
+  - Full telegraf configuration for the plugin the tickscript references including comments
+  - Commands for `define`-ing and `enable`-ing the script from the root of the repo
+* Parameters
+  - A list of variables to make customization easy
+* Dataframe
+  - A definition of the data to alert on 
+* Thresholds
+  - Define the thresholds or expressions to alert on 
+* Alert
+  - Where to send the alert. All scripts `.log()` by default.
+  - The tickscripts are written to make it easy to swap in whatever alert output you need. Just change the `alert.log('/tmp/{alert_name}.txt')` line in each tickscipt to your desired alert output. A full listing of outputs with code samples is available in the [kapacitor documentation](https://docs.influxdata.com/kapacitor/v0.13/nodes/alert_node/).
+
+> **On Alert Volume:** These alerts may be very noisy or quiet depending on your environment. They are meant to be starting points for alerts with all the knobs easily adjustable from the Parameters. Many users will also want to eliminate the `.info()` level of logging. It is included here for completeness.
+
+> **On Verbosity:** These scripts are meant as templates for users who are new to writing tickscripts. All of the examples here can be written as one large stream. See the [documentation](https://docs.influxdata.com/kapacitor/v0.13/) for examples and full tick syntax.
+
+### Batch script example
+
+```javascript
+// {alert_name}
+
+// metric: {alert_metric}
+// available_fields: [[other_telegraf_fields]]
+
+// TELEGRAF CONFIGURATION
+// [inputs.{plugin}]
+//   # Full configuration
+
+// DEFINE: kapacitor define {alert_name} -type batch -tick {plugin}/{alert_name}.tick -dbrp telegraf.autogen
+// ENABLE: kapacitor enable {alert_name}
+
+// Parameters
+var info = {info_level} 
+var warn = {warn_level}
+var crit = {crit_level}
+var infoSig = 2.5
+var warnSig = 3
+var critSig = 3.5
+var period = 10s
+var every = 10s
+
+// Dataframe
+var data = batch
+  |query('''{InfluxQL_Query}''')
+    .period(period)
+    .every(every)
+    .groupBy('host')
+
+// Thresholds
+var alert = data
+  |eval(lambda: sigma("stat"))
+    .as('sigma')
+    .keep()
+  |alert()
+    .id('{{ index .Tags "host"}}/{alert_metric}')
+    .message('{{ .ID }}:{{ index .Fields "stat" }}')
+    .info(lambda: "stat" > info OR "sigma" > infoSig)
+    .warn(lambda: "stat" > warn OR "sigma" > warnSig)
+    .crit(lambda: "stat" > crit OR "sigma" > critSig)
+
+// Alert
+alert
+  .log('/tmp/{alert_name}_log.txt')
+
+```
+
+### Stream script example
+
+```javascript
+// {alert_name}
+
+// metric: {alert_metric}
+// available_fields: [[other_telegraf_fields]]
+
+// TELEGRAF CONFIGURATION
+// [inputs.{plugin}]
+//   # full configuration
+
+// DEFINE: kapacitor define {alert_name} -type batch -tick {plugin}/{alert_name}.tick -dbrp telegraf.autogen
+// ENABLE: kapacitor enable {alert_name}
+
+// Parameters
+var info = {info_level} 
+var warn = {warn_level}
+var crit = {crit_level}
+var infoSig = 2.5
+var warnSig = 3
+var critSig = 3.5
+var period = 10s
+var every = 10s
+
+// Dataframe
+var data = stream
+  |from()
+    .database('telegraf')
+    .retentionPolicy('autogen')
+    .measurement({plugin})
+    .groupBy('host')
+  |window()
+    .period(period)
+    .every(every)
+  |mean({alert_metric})
+    .as("stat")
+
+// Thresholds
+var alert = data
+  |eval(lambda: sigma("stat"))
+    .as('sigma')
+    .keep()
+  |alert()
+    .id('{{ index .Tags "host"}}/{alert_metric}')
+    .message('{{ .ID }}:{{ index .Fields "stat" }}')
+    .info(lambda: "stat" > info OR "sigma" > infoSig)
+    .warn(lambda: "stat" > warn OR "sigma" > warnSig)
+    .crit(lambda: "stat" > crit OR "sigma" > critSig)
+
+// Alert
+alert
+  .log('/tmp/{alert_name}_log.txt')
+```

examples/telegraf/cpu/cpu_alert_batch.tick

@@ -0,0 +1,46 @@
+// cpu_alert_batch
+
+// metric: usage_user
+// available_fields: "usage_guest","usage_guest_nice","usage_idle","usage_iowait", "usage_irq","usage_nice","usage_softirq","usage_steal","usage_system"
+
+// TELEGRAF CONFIGURATION
+// [[inputs.cpu]]
+//   percpu = true
+//   totalcpu = true
+//   fielddrop = ["time_*"]
+
+// DEFINE: kapacitor define cpu_alert_batch -type batch -tick cpu/cpu_alert_batch.tick -dbrp telegraf.autogen
+// ENABLE: kapacitor enable cpu_alert_batch
+
+// Parameters 
+var info = 70
+var warn = 80
+var crit = 90
+var infoSig = 2.5
+var warnSig = 3
+var critSig = 3.5
+var period = 10s
+var every = 10s
+
+// Dataframe
+var data = batch
+  |query('''SELECT mean(usage_user) AS stat FROM "telegraf"."autogen"."cpu" WHERE cpu = 'cpu-total' ''')
+    .period(period)
+    .every(every)
+    .groupBy('host')
+
+// Thresholds
+var alert = data
+  |eval(lambda: sigma("stat"))
+    .as('sigma')
+    .keep()
+  |alert()
+    .id('{{ index .Tags "host"}}/cpu_used')
+    .message('{{ .ID }}:{{ index .Fields "stat" }}')
+    .info(lambda: "stat" > info OR "sigma" > infoSig)
+    .warn(lambda: "stat" > warn OR "sigma" > warnSig)
+    .crit(lambda: "stat" > crit OR "sigma" > critSig)
+
+// Alert
+alert
+  .log('/tmp/cpu_alert_log.txt')

examples/telegraf/cpu/cpu_alert_stream.tick

@@ -0,0 +1,53 @@
+// cpu_alert_stream
+
+// metric: usage_user
+// available_fields: "usage_guest","usage_guest_nice","usage_idle","usage_iowait", "usage_irq","usage_nice","usage_softirq","usage_steal","usage_system"
+
+// TELEGRAF CONFIGURATION
+// [[inputs.cpu]]
+//   percpu = true
+//   totalcpu = true
+//   fielddrop = ["time_*"]
+
+// DEFINE: kapacitor define cpu_alert_stream -type stream -tick cpu/cpu_alert_stream.tick -dbrp telegraf.autogen
+// ENABLE: kapacitor enable cpu_alert_stream
+
+// Parameters
+var info = 70
+var warn = 80
+var crit = 90
+var infoSig = 2.5
+var warnSig = 3
+var critSig = 3.5
+var period = 10s
+var every = 10s
+
+// Dataframe
+var data = stream
+  |from()
+    .database('telegraf')
+    .retentionPolicy('autogen')
+    .measurement('cpu')
+    .groupBy('host')
+    .where(lambda: "cpu" == 'cpu-total')
+  |window()
+    .period(period)
+    .every(every)
+  |mean('usage_user')
+    .as('stat')
+
+// Thresholds
+var alert = data
+  |eval(lambda: sigma("stat"))
+    .as('sigma')
+    .keep()
+  |alert()
+    .id('{{ index .Tags "host"}}/cpu_used')
+    .message('{{ .ID }}:{{ index .Fields "stat" }}')
+    .info(lambda: "stat" > info OR "sigma" > infoSig)
+    .warn(lambda: "stat" > warn OR "sigma" > warnSig)
+    .crit(lambda: "stat" > crit OR "sigma" > critSig)
+
+// Alert
+alert
+  .log('/tmp/cpu_alert_log.txt')

examples/telegraf/disk/disk_alert_batch.tick

@@ -0,0 +1,38 @@
+// disk_alert_batch
+
+// metric: used_percent
+// available_fields: "free","inodes_free","inodes_total","inodes_used","total","used"
+
+// TELEGRAF CONFIGURATION
+// [[inputs.disk]]
+//   ignore_fs = ["tmpfs", "devtmpfs"]
+
+// DEFINE: kapacitor define disk_alert_batch -type batch -tick disk/disk_alert_batch.tick -dbrp telegraf.autogen
+// ENABLE: kapacitor enable disk_alert_batch
+
+// Parameters
+var info = 75 
+var warn = 85
+var crit = 92
+var period = 10s
+var every = 10s
+
+// Dataframe
+var data = batch
+  |query('''SELECT mean(used_percent) AS stat FROM "telegraf"."autogen"."disk" WHERE path = '/' ''')
+    .period(period)
+    .every(every)
+    .groupBy('host')
+
+// Thresholds
+var alert = data
+  |alert()
+    .id('{{ index .Tags "host"}}/disk_used')
+    .message('{{ .ID }}:{{ index .Fields "stat" }}')
+    .info(lambda: "stat" > info)
+    .warn(lambda: "stat" > warn)
+    .crit(lambda: "stat" > crit)
+
+// Alert
+alert
+  .log('/tmp/disk_alert_log.txt')

examples/telegraf/disk/disk_alert_stream.tick

@@ -0,0 +1,44 @@
+// disk_alert_stream
+
+// metric: used_percent
+// available_fields: free","inodes_free","inodes_total","inodes_used","total","used"
+
+// TELEGRAF CONFIGURATION
+// [[inputs.disk]]
+//   ignore_fs = ["tmpfs", "devtmpfs"]
+
+// DEFINE: kapacitor define disk_alert_stream -type stream -tick disk/disk_alert_stream.tick -dbrp telegraf.autogen
+// ENABLE: kapacitor enable disk_alert_stream
+
+// Parameters
+var info = 75 
+var warn = 85
+var crit = 92
+var period = 10s
+var every = 10s
+
+// Dataframe
+var data = stream
+  |from()
+    .database('telegraf')
+    .retentionPolicy('autogen')
+    .measurement('mem')
+    .groupBy('host')
+  |window()
+    .period(period)
+    .every(every)
+  |mean('used_percent')
+    .as('stat')
+
+// Thresholds
+var alert = data
+  |alert()
+    .id('{{ index .Tags "host"}}/disk_used')
+    .message('{{ .ID }}:{{ index .Fields "stat" }}')
+    .info(lambda: "stat" > info)
+    .warn(lambda: "stat" > warn)
+    .crit(lambda: "stat" > crit)
+
+// Alert
+alert
+  .log('/tmp/mem_alert_log.txt')

examples/telegraf/generic_batch_example.tick

@@ -0,0 +1,44 @@
+// {alert_name}
+
+// metric: {alert_metric}
+// available_fields: [[other_telegraf_fields]]
+
+// TELEGRAF CONFIGURATION
+// [inputs.{plugin}]
+//   # Full configuration
+
+// DEFINE: kapacitor define {alert_name} -type batch -tick {plugin}/{alert_name}.tick -dbrp telegraf.autogen
+// ENABLE: kapacitor enable {alert_name}
+
+// Parameters
+var info = {info_level} 
+var warn = {warn_level}
+var crit = {crit_level}
+var infoSig = 2.5
+var warnSig = 3
+var critSig = 3.5
+var period = 10s
+var every = 10s
+
+// Dataframe
+var data = batch
+  |query('''{InfluxQL_Query}''')
+    .period(period)
+    .every(every)
+    .groupBy('host')
+
+// Thresholds
+var alert = data
+  |eval(lambda: sigma("stat"))
+    .as('sigma')
+    .keep()
+  |alert()
+    .id('{{ index .Tags "host"}}/{alert_metric}')
+    .message('{{ .ID }}:{{ index .Fields "stat" }}')
+    .info(lambda: "stat" > info OR "sigma" > infoSig)
+    .warn(lambda: "stat" > warn OR "sigma" > warnSig)
+    .crit(lambda: "stat" > crit OR "sigma" > critSig)
+
+// Alert
+alert
+  .log('/tmp/{alert_name}_log.txt')