Setup InfluxDB (docker), Telegraf, and Grafana (docker) for metrics

grafan-run.sh

# Pull dockerfile
docker pull grafana/grafana

# Run the docker container
docker run -i -p 3000:3000 grafana/grafana

influxdb-run.sh

# Pull dockerfile
docker pull influxdb

# Run the docker container
docker run -p 8083:8083 -p 8086:8086 \
  -v $PWD:/var/lib/influxdb \
  influxdb

# Create database
curl -G http://localhost:8086/query --data-urlencode "q=CREATE DATABASE metrics"

telegraf-mac.sh

brew update
brew install telegraf

telegraf-windows.sh

# Download 
curl -O https://dl.influxdata.com/telegraf/releases/telegraf-1.0.0-rc1_windows_amd64.zip

# Get plugins
git clone https://github.com/influxdata/telegraf.git

# Run telegraf with specified config
telegraf -config telegraf.conf

telegraf.conf

# 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.

# 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"
  app = "myapp"

# 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 cache metric_buffer_limit metrics for each output, and will
  ## flush this buffer on a successful write.
  metric_buffer_limit = 1000
  ## Flush the buffer whenever full, regardless of flush_interval.
  flush_buffer_when_full = true

  ## 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. You shouldn't set this below
  ## interval. 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"

  ## Run telegraf in debug mode
  debug = false
  ## Run telegraf in quiet mode
  quiet = false
  ## Override default hostname, if empty use os.Hostname()
  hostname = ""


###############################################################################
#                                  OUTPUTS                                    #
###############################################################################

# Configuration for influxdb server to send metrics to
[[outputs.influxdb]]
  # The full HTTP or UDP endpoint URL for your InfluxDB instance.
  # Multiple urls can be specified but it is assumed that they are part of the same
  # cluster, this means that only ONE of the urls will be written to each interval.
  # urls = ["udp://localhost:8089"] # UDP endpoint example
  urls = ["http://10.211.55.2:8086"] # required
  # The target database for metrics (telegraf will create it if not exists)
  database = "metrics" # required
  # Precision of writes, valid values are "ns", "us" (or "µs"), "ms", "s", "m", "h".
  # note: using second precision greatly helps InfluxDB compression
  precision = "s"

  ## Write timeout (for the InfluxDB client), formatted as a string.
  ## If not provided, will default to 5s. 0s means no timeout (not recommended).
  timeout = "5s"
   username = "root"
   password = "root"
  # Set the user agent for HTTP POSTs (can be useful for log differentiation)
  # user_agent = "telegraf"
  # Set UDP payload size, defaults to InfluxDB UDP Client default (512 bytes)
  # udp_payload = 512


###############################################################################
#                                  INPUTS                                     #
###############################################################################

# 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 utilizes a lot of 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"]
    Measurement = "win_cpu"
    #IncludeTotal=false #Set to true to include _Total instance when querying for all (*).

  #[[inputs.win_perf_counters.object]]
    ## Disk times and queues
    #ObjectName = "LogicalDisk"
    #Instances = ["*"]
    #Counters = ["% Idle Time", "% Disk Time","% Disk Read Time", "% Disk Write Time", "% User Time", "Current Disk Queue Length"]
    #Measurement = "win_disk"
    ##IncludeTotal=false #Set to true to include _Total instance when querying for all (*).

  #[[inputs.win_perf_counters.object]]
    #ObjectName = "System"
    #Counters = ["Context Switches/sec","System Calls/sec"]
    #Instances = ["------"]
    #Measurement = "win_system"
    ##IncludeTotal=false #Set to true to include _Total instance when querying for all (*).

  [[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"]
    Instances = ["------"] # Use 6 x - to remove the Instance bit from the query.
    Measurement = "win_mem"
    #IncludeTotal=false #Set to true to include _Total instance when querying for all (*).


# Windows system plugins using WMI (disabled by default, using
# win_perf_counters over WMI is recommended)

# Read metrics about cpu usage
#[[inputs.cpu]]
  ## Whether to report per-cpu stats or not
  #percpu = true
  # Whether to report total system cpu stats or not
  #totalcpu = true
  ## Comment this line if you want the raw CPU time metrics
  #fielddrop = ["time_*"]

# Read metrics about disk usage by mount point
#[[inputs.disk]]
  ## By default, telegraf gather stats for all mountpoints.
  ## Setting mountpoints will restrict the stats to the specified mountpoints.
  ## mount_points=["/"]

  ## Ignore some mountpoints by filesystem type. For example (dev)tmpfs (usually
  ## present on /run, /var/run, /dev/shm or /dev).
  #ignore_fs = ["tmpfs", "devtmpfs"]

# Read metrics about disk IO by device
#[[inputs.diskio]]
  ## By default, telegraf will gather stats for all devices including
  ## disk partitions.
  ## Setting devices will restrict the stats to the specified devices.
  ## devices = ["sda", "sdb"]
  ## Uncomment the following line if you do not need disk serial numbers.
  ## skip_serial_number = true

# Read metrics about memory usage
#[[inputs.mem]]
  # no configuration

# Read metrics about swap memory usage
#[[inputs.swap]]
  # no configuration