apiVersion: influxdata.com/v2alpha1
kind: Label
metadata:
name: windows-system-template
spec:
name: Windows System Template
color: '#7A65F2'
---
apiVersion: influxdata.com/v2alpha1
kind: Label
metadata:
name: inputs-win-perf-counters
spec:
name: inputs.win_perf_counters
color: '#326BBA'
---
apiVersion: influxdata.com/v2alpha1
kind: Label
metadata:
name: outputs-influxdb-v2
spec:
name: outputs.influxdb_v2
color: '#108174'
---
apiVersion: influxdata.com/v2alpha1
kind: Bucket
metadata:
name: telegraf
spec:
name: telegraf
retentionRules:
- everySeconds: 604800
type: expire
---
apiVersion: influxdata.com/v2alpha1
kind: Variable
metadata:
name: bucket
spec:
name: bucket
associations:
- kind: Label
name: windows-system-template
language: flux
query: |-
buckets()
|> filter(fn: (r) => r.name !~ /^_/)
|> rename(columns: {name: "_value"})
|> keep(columns: ["_value"])
type: query
---
apiVersion: influxdata.com/v2alpha1
kind: Variable
metadata:
name: windows-host
spec:
name: windows_host
associations:
- kind: Label
name: windows-system-template
language: flux
query: |-
import "influxdata/influxdb/v1"
v1.measurementTagValues(bucket: v.bucket, measurement: "win_system", tag: "host")
type: query
---
apiVersion: influxdata.com/v2alpha1
kind: Telegraf
metadata:
name: windows-system-monitoring
spec:
name: Windows System Monitoring
associations:
- kind: Label
name: inputs-win-perf-counters
- kind: Label
name: outputs-influxdb-v2
- kind: Label
name: windows-system-template
config: |
# Telegraf Configuration
#
# Telegraf is entirely plugin driven. All metrics are gathered from the
# declared inputs, and sent to the declared outputs.
#
# Plugins must be declared in here to be active.
# To deactivate a plugin, comment out the name and any variables.
#
# Use 'telegraf -config telegraf.conf -test' to see what metrics a config
# file would generate.
#
# Environment variables can be used anywhere in this config file, simply surround
# them with ${}. For strings the variable must be within quotes (ie, "${STR_VAR}"),
# for numbers and booleans they should be plain (ie, ${INT_VAR}, ${BOOL_VAR})
# Global tags can be specified here in key="value" format.
[global_tags]
# dc = "us-east-1" # will tag all metrics with dc=us-east-1
# rack = "1a"
## Environment variables can be used as tags, and throughout the config file
# user = "$USER"
# Configuration for telegraf agent
[agent]
## Default data collection interval for all inputs
interval = "10s"
## Rounds collection interval to 'interval'
## ie, if interval="10s" then always collect on :00, :10, :20, etc.
round_interval = true
## Telegraf will send metrics to outputs in batches of at most
## metric_batch_size metrics.
## This controls the size of writes that Telegraf sends to output plugins.
metric_batch_size = 1000
## Maximum number of unwritten metrics per output. Increasing this value
## allows for longer periods of output downtime without dropping metrics at the
## cost of higher maximum memory usage.
metric_buffer_limit = 10000
## Collection jitter is used to jitter the collection by a random amount.
## Each plugin will sleep for a random time within jitter before collecting.
## This can be used to avoid many plugins querying things like sysfs at the
## same time, which can have a measurable effect on the system.
collection_jitter = "0s"
## Default flushing interval for all outputs. Maximum flush_interval will be
## flush_interval + flush_jitter
flush_interval = "10s"
## Jitter the flush interval by a random amount. This is primarily to avoid
## large write spikes for users running a large number of telegraf instances.
## ie, a jitter of 5s and interval 10s means flushes will happen every 10-15s
flush_jitter = "0s"
## By default or when set to "0s", precision will be set to the same
## timestamp order as the collection interval, with the maximum being 1s.
## ie, when interval = "10s", precision will be "1s"
## when interval = "250ms", precision will be "1ms"
## Precision will NOT be used for service inputs. It is up to each individual
## service input to set the timestamp at the appropriate precision.
## Valid time units are "ns", "us" (or "µs"), "ms", "s".
precision = ""
## Log at debug level.
# debug = false
## Log only error level messages.
# quiet = false
## Log target controls the destination for logs and can be one of "file",
## "stderr" or, on Windows, "eventlog". When set to "file", the output file
## is determined by the "logfile" setting.
# logtarget = "file"
## Name of the file to be logged to when using the "file" logtarget. If set to
## the empty string then logs are written to stderr.
# logfile = ""
## The logfile will be rotated after the time interval specified. When set
## to 0 no time based rotation is performed. Logs are rotated only when
## written to, if there is no log activity rotation may be delayed.
# logfile_rotation_interval = "0d"
## The logfile will be rotated when it becomes larger than the specified
## size. When set to 0 no size based rotation is performed.
# logfile_rotation_max_size = "0MB"
## Maximum number of rotated archives to keep, any older logs are deleted.
## If set to -1, no archives are removed.
# logfile_rotation_max_archives = 5
## Override default hostname, if empty use os.Hostname()
hostname = ""
## If set to true, do no set the "host" tag in the telegraf agent.
omit_hostname = false
###############################################################################
# OUTPUT PLUGINS #
###############################################################################
# Configuration for sending metrics to InfluxDB
[[outputs.influxdb_v2]]
## The URLs of the InfluxDB cluster nodes.
##
## Multiple URLs can be specified for a single cluster, only ONE of the
## urls will be written to each interval.
## ex: urls = ["https://us-west-2-1.aws.cloud2.influxdata.com"]
urls = ["$INFLUX_HOST"]
## Token for authentication.
token = "$INFLUX_TOKEN"
## Organization is the name of the organization you wish to write to; must exist.
organization = "$INFLUX_ORG" ## Destination bucket to write into.
bucket = "telegraf"
## The value of this tag will be used to determine the bucket. If this
## tag is not set the 'bucket' option is used as the default.
# bucket_tag = ""
## If true, the bucket tag will not be added to the metric.
# exclude_bucket_tag = false
## Timeout for HTTP messages.
# timeout = "5s"
## Additional HTTP headers
# http_headers = {"X-Special-Header" = "Special-Value"}
## HTTP Proxy override, if unset values the standard proxy environment
## variables are consulted to determine which proxy, if any, should be used.
# http_proxy = "http://corporate.proxy:3128"
## HTTP User-Agent
# user_agent = "telegraf"
## Content-Encoding for write request body, can be set to "gzip" to
## compress body or "identity" to apply no encoding.
# content_encoding = "gzip"
## Enable or disable uint support for writing uints influxdb 2.0.
# influx_uint_support = false
## Optional TLS Config for use on HTTP connections.
# tls_ca = "/etc/telegraf/ca.pem"
# tls_cert = "/etc/telegraf/cert.pem"
# tls_key = "/etc/telegraf/key.pem"
## Use TLS but skip chain & host verification
# insecure_skip_verify = false
###############################################################################
# INPUT PLUGINS #
###############################################################################
# Windows Performance Counters plugin.
# These are the recommended method of monitoring system metrics on windows,
# as the regular system plugins (inputs.cpu, inputs.mem, etc.) rely on WMI,
# which utilize more system resources.
#
# See more configuration examples at:
# https://github.com/influxdata/telegraf/tree/master/plugins/inputs/win_perf_counters
[[inputs.win_perf_counters]]
[[inputs.win_perf_counters.object]]
# Processor usage, alternative to native, reports on a per core.
ObjectName = "Processor"
Instances = ["*"]
Counters = [
"% Idle Time",
"% Interrupt Time",
"% Privileged Time",
"% User Time",
"% Processor Time",
"% DPC Time",
]
Measurement = "win_cpu"
# Set to true to include _Total instance when querying for all (*).
IncludeTotal=true
[[inputs.win_perf_counters.object]]
# Disk times and queues
ObjectName = "LogicalDisk"
Instances = ["*"]
Counters = [
"% Idle Time",
"% Disk Time",
"% Disk Read Time",
"% Disk Write Time",
"% Free Space",
"Current Disk Queue Length",
"Free Megabytes",
]
Measurement = "win_disk"
# Set to true to include _Total instance when querying for all (*).
#IncludeTotal=false
[[inputs.win_perf_counters.object]]
ObjectName = "PhysicalDisk"
Instances = ["*"]
Counters = [
"Disk Read Bytes/sec",
"Disk Write Bytes/sec",
"Current Disk Queue Length",
"Disk Reads/sec",
"Disk Writes/sec",
"% Disk Time",
"% Disk Read Time",
"% Disk Write Time",
]
Measurement = "win_diskio"
[[inputs.win_perf_counters.object]]
ObjectName = "Network Interface"
Instances = ["*"]
Counters = [
"Bytes Received/sec",
"Bytes Sent/sec",
"Packets Received/sec",
"Packets Sent/sec",
"Packets Received Discarded",
"Packets Outbound Discarded",
"Packets Received Errors",
"Packets Outbound Errors",
]
Measurement = "win_net"
[[inputs.win_perf_counters.object]]
ObjectName = "System"
Counters = [
"Context Switches/sec",
"System Calls/sec",
"Processor Queue Length",
"System Up Time",
]
Instances = ["------"]
Measurement = "win_system"
# Set to true to include _Total instance when querying for all (*).
#IncludeTotal=false
[[inputs.win_perf_counters.object]]
# Example query where the Instance portion must be removed to get data back,
# such as from the Memory object.
ObjectName = "Memory"
Counters = [
"Available Bytes",
"Cache Faults/sec",
"Demand Zero Faults/sec",
"Page Faults/sec",
"Pages/sec",
"Transition Faults/sec",
"Pool Nonpaged Bytes",
"Pool Paged Bytes",
"Standby Cache Reserve Bytes",
"Standby Cache Normal Priority Bytes",
"Standby Cache Core Bytes",
]
# Use 6 x - to remove the Instance bit from the query.
Instances = ["------"]
Measurement = "win_mem"
# Set to true to include _Total instance when querying for all (*).
#IncludeTotal=false
[[inputs.win_perf_counters.object]]
# Example query where the Instance portion must be removed to get data back,
# such as from the Paging File object.
ObjectName = "Paging File"
Counters = [
"% Usage",
]
Instances = ["_Total"]
Measurement = "win_swap"
# Windows system plugins using WMI (disabled by default, using
# win_perf_counters over WMI is recommended)
description: A set of plugins for monitoring your Windows system.
---
apiVersion: influxdata.com/v2alpha1
kind: Dashboard
metadata:
name: windows-system
spec:
name: Windows System
associations:
- kind: Label
name: windows-system-template
charts:
- height: 1
kind: Markdown
name: Name this Cell
note: This dashboard gives you an overview of your Windows System metrics
and will work with the default Windows Telegraf config. See the [Telegraf
Win Perf Counters Documentation](https://github.com/influxdata/telegraf/tree/master/plugins/inputs/win_perf_counters)
for more information.
queries: null
width: 12
- colors:
- hex: '#00C9FF'
name: laser
type: text
height: 1
kind: Single_Stat
name: System Uptime
queries:
- query: |-
from(bucket: v.bucket)
|> range(start: v.timeRangeStart)
|> filter(fn: (r) => r._measurement == "win_system")
|> filter(fn: (r) => r._field == "System_Up_Time")
|> filter(fn: (r) => r.host == v.windows_host)
|> last()
|> map(fn: (r) => ({r with _value: r._value / 86400.0}))
|> yield(name: "last")
suffix: ' days'
width: 3
yPos: 1
- axes:
- base: "10"
name: x
scale: linear
- base: "10"
name: y
scale: linear
suffix: '%'
- base: "10"
name: y2
scale: linear
geom: line
height: 3
kind: Xy
name: Disk Usage
queries:
- query: |-
from(bucket: v.bucket)
|> range(start: v.timeRangeStart)
|> filter(fn: (r) => r._measurement == "win_disk")
|> filter(fn: (r) => r._field == "Percent_Free_Space")
|> filter(fn: (r) => r.host == v.windows_host)
|> aggregateWindow(every: v.windowPeriod, fn: mean, createEmpty: false)
|> map(fn: (r) => ({ r with _value: 100.0 - r._value }))
|> set(key: "_field", value: "Percent Used Space")
//|> yield(name: "mean")
width: 3
xCol: _time
yCol: _value
yPos: 2
- axes:
- base: "10"
name: x
scale: linear
- base: "2"
label: Bytes
name: y
scale: linear
- base: "10"
name: y2
scale: linear
geom: line
height: 3
kind: Xy
name: Disk IO (bytes/sec)
position: overlaid
queries:
- query: |-
from(bucket: v.bucket)
|> range(start: v.timeRangeStart)
|> filter(fn: (r) => r._measurement == "win_diskio")
|> filter(fn: (r) => r._field =~ /_Bytes_persec$/)
|> filter(fn: (r) => r.host == v.windows_host)
|> derivative(unit: 1s, nonNegative: false)
|> yield(name: "derivative")
width: 4
xCol: _time
yCol: _value
yPos: 5
- colors:
- hex: '#00C9FF'
name: laser
type: text
decimalPlaces: 2
height: 1
kind: Single_Stat
name: Processor Queue Length
queries:
- query: |-
from(bucket: v.bucket)
|> range(start: v.timeRangeStart)
|> filter(fn: (r) => r._measurement == "win_system")
|> filter(fn: (r) => r._field == "Processor_Queue_Length")
|> filter(fn: (r) => r.host == v.windows_host)
|> last()
width: 2
xPos: 3
yPos: 1
- axes:
- base: "10"
name: y
scale: linear
suffix: '%'
- base: "10"
name: y2
scale: linear
- base: "10"
name: x
scale: linear
geom: line
height: 3
kind: Xy
name: CPU Usage
queries:
- query: |-
from(bucket: v.bucket)
|> range(start: v.timeRangeStart)
|> filter(fn: (r) => r._measurement == "win_cpu")
|> filter(fn: (r) => r._field =~ /^Percent_/)
|> filter(fn: (r) => r.instance == "_Total")
|> filter(fn: (r) => r.host == v.windows_host)
|> aggregateWindow(every: v.windowPeriod, fn: mean, createEmpty: false)
|> drop(columns: ["objectname"])
width: 3
xCol: _time
xPos: 3
yCol: _value
yPos: 2
- axes:
- base: "10"
name: x
scale: linear
- base: "2"
label: Bytes
name: y
scale: linear
- base: "10"
name: y2
scale: linear
geom: line
height: 3
kind: Xy
name: Network
queries:
- query: |-
from(bucket: v.bucket)
|> range(start: v.timeRangeStart)
|> filter(fn: (r) => r._measurement == "win_net")
|> filter(fn: (r) => r.host == v.windows_host)
|> filter(fn: (r) => r._field =~ /^Bytes_(Received|Sent)_persec$/)
|> derivative(unit: 1s, nonNegative: false)
width: 4
xCol: _time
xPos: 4
yCol: _value
yPos: 5
- colors:
- hex: '#00C9FF'
name: laser
type: text
decimalPlaces: 2
height: 1
kind: Single_Stat
name: System Calls / Sec
queries:
- query: |-
from(bucket: v.bucket)
|> range(start: v.timeRangeStart)
|> filter(fn: (r) => r._measurement == "win_system")
|> filter(fn: (r) => r._field == "System_Calls_persec")
|> filter(fn: (r) => r.host == v.windows_host)
|> last()
width: 2
xPos: 5
yPos: 1
- axes:
- base: "10"
name: x
scale: linear
- base: "10"
label: Load
name: y
scale: linear
- base: "10"
name: y2
scale: linear
geom: line
height: 3
kind: Xy
name: System Load
queries:
- query: |-
from(bucket: v.bucket)
|> range(start: v.timeRangeStart)
|> filter(fn: (r) => r._measurement == "win_system")
|> filter(fn: (r) => r._field =~ /_persec$/)
|> filter(fn: (r) => r.host == v.windows_host)
|> aggregateWindow(every: v.windowPeriod, fn: mean, createEmpty: false)
|> yield(name: "mean")
width: 3
xCol: _time
xPos: 6
yCol: _value
yPos: 2
- colors:
- hex: '#00C9FF'
name: laser
type: text
decimalPlaces: 2
height: 1
kind: Single_Stat
name: Available Memory
queries:
- query: |-
from(bucket: v.bucket)
|> range(start: v.timeRangeStart)
|> filter(fn: (r) => r._measurement == "win_mem")
|> filter(fn: (r) => r._field == "Available_Bytes")
|> filter(fn: (r) => r.host == v.windows_host)
|> last()
|> map(fn: (r) => ({r with _value: float(v: r._value) / 1024.0 / 1024.0 / 1024.0}))
|> yield(name: "last")
suffix: ' GB'
width: 2
xPos: 7
yPos: 1
- axes:
- base: "10"
name: x
scale: linear
- base: "2"
name: y
scale: linear
- base: "10"
name: y2
scale: linear
geom: line
height: 3
kind: Xy
name: Swap
queries:
- query: |-
from(bucket: v.bucket)
|> range(start: v.timeRangeStart)
|> filter(fn: (r) => r._measurement == "win_swap")
|> filter(fn: (r) => r.host == v.windows_host)
|> aggregateWindow(every: v.windowPeriod, fn: mean, createEmpty: false)
|> yield(name: "mean")
width: 4
xCol: _time
xPos: 8
yCol: _value
yPos: 5
- axes:
- base: "10"
name: x
scale: linear
- base: "10"
name: y
scale: linear
suffix: '%'
- base: "10"
name: y2
scale: linear
colors:
- hex: '#00C9FF'
name: laser
type: text
- hex: '#8F8AF4'
name: Do Androids Dream of Electric Sheep?
type: scale
- hex: '#A51414'
name: Do Androids Dream of Electric Sheep?
type: scale
- hex: '#F4CF31'
name: Do Androids Dream of Electric Sheep?
type: scale
decimalPlaces: 1
height: 4
kind: Single_Stat_Plus_Line
name: Available Memory (bytes)
queries:
- query: |-
from(bucket: v.bucket)
|> range(start: v.timeRangeStart)
|> filter(fn: (r) => r._measurement == "win_mem")
|> filter(fn: (r) => r._field == "Available_Bytes")
|> filter(fn: (r) => r.host == v.windows_host)
|> aggregateWindow(every: v.windowPeriod, fn: mean, createEmpty: false)
|> yield(name: "mean")
width: 3
xCol: _time
xPos: 9
yCol: _value
yPos: 1
description: A collection of useful visualizations for monitoring your Windows system
stats