rollout telegraf für monitoring

common/telegraf/handlers/main.yml

+
+- name: restart telegraf
+  service: name=telegraf state=restarted

common/telegraf/tasks/main.yml

+---
+# Pakete installieren
+- name: pakete installieren
+  apt:
+    pkg: "{{ item }}"
+    update_cache: yes
+    state: installed
+  with_items:
+    - telegraf
+
+- name: pakete installieren (host_type = physical)
+  apt:
+    pkg: "{{ item }}"
+    update_cache: yes
+    state: installed
+  with_items:
+    - hddtemp
+    - lm-sensors
+    - smartmontools
+  when: host_type == 'physical'
+
+
+- name: create main config 
+  template: src={{ item }} dest=/etc/telegraf/{{ item }}
+  with_items: 
+    - telegraf.conf
+  notify: restart telegraf
+
+
+- name: reload systemd and enable service
+  command: systemctl enable telegraf
+  notify: restart telegraf
+
+  
+- name: delete config file 1
+  file: 
+    path: "/etc/telegraf/telegraf.d/outputs-influxdb.conf"
+    state: absent

common/telegraf/templates/telegraf.conf

+
+# 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"
+  server = "true"
+  host_type = "{{host_type}}"
+  
+
+# Configuration for telegraf agent
+[agent]
+  
+  ## Default data collection interval for all inputs
+  interval = "5s"
+
+  ## 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
+
+  ## For failed writes, telegraf will cache metric_buffer_limit metrics for each
+  ## output, and will flush this buffer on a successful write. Oldest metrics
+  ## are dropped first when this buffer fills.
+  ## This buffer only fills when writes fail to output plugin(s).
+  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. 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"
+
+  ## 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 = ""
+
+  ## Logging configuration:
+  ## Run telegraf with debug log messages.
+  debug = false
+
+  ## Run telegraf in quiet mode (error log messages only).
+  quiet = false
+
+  ## Specify the log file name. The empty string means to log to stderr.
+  logfile = ""
+
+  ## Override default hostname, if empty use os.Hostname()
+  hostname = "{{ inventory_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]]
+  ## The full HTTP or UDP URL for your InfluxDB instance.
+  ##
+  urls = ["{{influxdb_sysmon.url}}"]
+
+  ## The target database for metrics; will be created as needed.
+  database = "{{influxdb_sysmon.db}}"
+
+  ## If true, no CREATE DATABASE queries will be sent.  Set to true when using
+  ## Telegraf with a user without permissions to create databases or when the
+  ## database already exists.
+  skip_database_creation = true
+
+  ## Name of existing retention policy to write to.  Empty string writes to
+  ## the default retention policy.
+  # retention_policy = ""
+
+  ## Write consistency (clusters only), can be: "any", "one", "quorum", "all"
+  # write_consistency = "any"
+
+  ## Timeout for HTTP messages.
+  # timeout = "5s"
+
+  ## HTTP Basic Auth
+  username = "{{influxdb_sysmon.user}}"
+  password = "{{influxdb_sysmon.password}}"
+
+  ## HTTP User-Agent
+  # user_agent = "telegraf"
+
+  ## UDP payload size is the maximum packet size to send.
+  # udp_payload = 512
+
+  ## Optional SSL Config
+  # ssl_ca = "/etc/telegraf/ca.pem"
+  # ssl_cert = "/etc/telegraf/cert.pem"
+  # ssl_key = "/etc/telegraf/key.pem"
+  ## Use SSL but skip chain & host verification
+  # insecure_skip_verify = false
+
+  ## 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"
+
+  ## Additional HTTP headers
+  # http_headers = {"X-Special-Header" = "Special-Value"}
+
+  ## HTTP Content-Encoding for write request body, can be set to "gzip" to
+  ## compress body or "identity" to apply no encoding.
+  # content_encoding = "identity"
+
+  ## When true, Telegraf will output unsigned integers as unsigned values,
+  ## i.e.: "42u".  You will need a version of InfluxDB supporting unsigned
+  ## integer values.  Enabling this option will result in field type errors if
+  ## existing data has been written.
+  # influx_uint_support = false
+
+
+
+###############################################################################
+#                            INPUT PLUGINS                                    #
+###############################################################################
+
+
+# Read metrics about system load & uptime
+[[inputs.system]]
+  # no configuration
+
+
+[[inputs.interrupts]]
+  # no configuration
+
+
+[[inputs.linux_sysctl_fs]]
+  # no configuration
+
+
+# Get kernel statistics from /proc/stat
+[[inputs.kernel]]
+  # no configuration  
+
+
+# Read metrics about memory usage
+[[inputs.mem]]
+  # no configuration
+
+
+# Read metrics about swap memory usage
+[[inputs.swap]]
+  # no configuration
+
+
+# Get the number of processes and group them by status
+[[inputs.processes]]
+  # no configuration
+
+
+# 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
+  ## If true, collect raw CPU time metrics.
+  collect_cpu_time = false
+  ## If true, compute and report the sum of all non-idle CPU states.
+  report_active = false
+
+
+# Read metrics about disk usage by mount point
+[[inputs.disk]]
+  ## By default stats will be gathered for all mount points.
+  ## Set mount_points will restrict the stats to only the specified mount points.
+  mount_points = ["/", "/srv"]
+
+  ## Ignore mount points by filesystem type.
+  ignore_fs = ["tmpfs", "devtmpfs", "devfs", "sysfs", "overlay" ]
+
+
+# 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 need disk serial numbers.
+  # skip_serial_number = false
+  #
+  ## On systems which support it, device metadata can be added in the form of
+  ## tags.
+  ## Currently only Linux is supported via udev properties. You can view
+  ## available properties for a device by running:
+  ## 'udevadm info -q property -n /dev/sda'
+  # device_tags = ["ID_FS_TYPE", "ID_FS_USAGE"]
+  #
+  ## Using the same metadata source as device_tags, you can also customize the
+  ## name of the device via templates.
+  ## The 'name_templates' parameter is a list of templates to try and apply to
+  ## the device. The template may contain variables in the form of '$PROPERTY' or
+  ## '${PROPERTY}'. The first template which does not contain any variables not
+  ## present for the device is used as the device name tag.
+  ## The typical use case is for LVM volumes, to get the VG/LV name instead of
+  ## the near-meaningless DM-0 name.
+  # name_templates = ["$ID_FS_LABEL","$DM_VG_NAME/$DM_LV_NAME"]
+
+
+# Read metrics about network interface usage
+[[inputs.net]]
+  ## By default, telegraf gathers stats from any up interface (excluding loopback)
+  ## Setting interfaces will tell it to gather these explicit interfaces,
+  ## regardless of status.
+  ##
+  interfaces = ["eth*", "en*"]
+  ##
+  ## On linux systems telegraf also collects protocol stats.
+  ## Setting ignore_protocol_stats to true will skip reporting of protocol metrics.
+  ##
+  # ignore_protocol_stats = false
+  ##
+
+# Read metrics about network usage
+[[inputs.netstat]]
+  # no configuration
+
+ # Collects conntrack stats from the configured directories and files.
+ [[inputs.conntrack]]
+   ## The following defaults would work with multiple versions of conntrack.
+   ## Note the nf_ and ip_ filename prefixes are mutually exclusive across
+   ## kernel versions, as are the directory locations.
+
+   ## Superset of filenames to look for within the conntrack dirs.
+   ## Missing files will be ignored.
+   files = ["ip_conntrack_count","ip_conntrack_max",
+            "nf_conntrack_count","nf_conntrack_max"]
+
+   ## Directories to search within for the conntrack files above.
+   ## Missing directrories will be ignored.
+   dirs = ["/proc/sys/net/ipv4/netfilter","/proc/sys/net/netfilter"]
+   
+
+{% if host_type == 'physical' %}
+
+# Monitor disks' temperatures using hddtemp
+[[inputs.hddtemp]]
+  ## By default, telegraf gathers temps data from all disks detected by the
+  ## hddtemp.
+  ##
+  ## Only collect temps from the selected disks.
+  ##
+  ## A * as the device name will return the temperature values of all disks.
+  ##
+  # address = "127.0.0.1:7634"
+  # devices = ["sda", "*"]
+
+
+# Monitor sensors, requires lm-sensors package
+[[inputs.sensors]]
+  ## Remove numbers from field names.
+  ## If true, a field name like 'temp1_input' will be changed to 'temp_input'.
+  # remove_numbers = true
+
+
+# Read metrics from storage devices supporting S.M.A.R.T.
+[[inputs.smart]]
+  ## Optionally specify the path to the smartctl executable
+  # path = "/usr/bin/smartctl"
+  #
+  ## On most platforms smartctl requires root access.
+  ## Setting 'use_sudo' to true will make use of sudo to run smartctl.
+  ## Sudo must be configured to to allow the telegraf user to run smartctl
+  ## with out password.
+  # use_sudo = false
+  #
+  ## Skip checking disks in this power mode. Defaults to
+  ## "standby" to not wake up disks that have stoped rotating.
+  ## See --nocheck in the man pages for smartctl.
+  ## smartctl version 5.41 and 5.42 have faulty detection of
+  ## power mode and might require changing this value to
+  ## "never" depending on your disks.
+  # nocheck = "standby"
+  #
+  ## Gather detailed metrics for each SMART Attribute.
+  ## Defaults to "false"
+  ##
+  # attributes = false
+  #
+  ## Optionally specify devices to exclude from reporting.
+  # excludes = [ "/dev/pass6" ]
+  #
+  ## Optionally specify devices and device type, if unset
+  ## a scan (smartctl --scan) for S.M.A.R.T. devices will
+  ## done and all found will be included except for the
+  ## excluded in excludes.
+  # devices = [ "/dev/ada0 -d atacam" ]
+
+
+{% else %}
+{% endif %}
\ No newline at end of file

group_vars/all

@@ -11,7 +11,7 @@ ldap_readonly_bind_dn: cn=readonly,dc=warpzone,dc=ms
 
 # Zentrale InfluxDb für Systemmonitoring  
 influxdb_sysmon:
-  url: "http:// 192.168.0.201:18086"
+  url: "http://192.168.0.201:18086"
   db: "influx"
   user: "influx" 
   password: "influx" 

host_vars/vorstandspi

@@ -10,6 +10,10 @@ debian_sources:
 
 debian_keys:
 
+# Art des Hosts: physical, vm, docker 
+host_type: "physical"
+
+
 administratorenteam:
   - "ole"
   - "larsm"

host_vars/warphab

@@ -14,6 +14,9 @@ debian_keys:
   - "https://homegear.eu/packages/Release.key"
   - "https://bintray.com/user/downloadSubjectPublicKey?username=openhab"
 
+# Art des Hosts: physical, vm, docker 
+host_type: "physical"
+
 administratorenteam:
   - "user51"
   - "void"

host_vars/warpsrvext

@@ -12,6 +12,9 @@ debian_sources:
 
 debian_keys:
 
+# Art des Hosts: physical, vm, docker 
+host_type: "physical"
+
 administratorenteam:
   - "void"
   - "sandhome"

host_vars/warpsrvint

@@ -11,10 +11,17 @@ debian_sources:
   - "deb http://debian.uni-duisburg-essen.de/debian/ jessie-updates main contrib non-free"
   - "deb http://ftp.debian.org/debian jessie-backports main"
   - "deb https://apt.dockerproject.org/repo debian-jessie main"
-  - "deb [arch=amd64] https://download.docker.com/linux/debian jessie stable"
+  - "deb https://download.docker.com/linux/debian jessie stable"
+  - "deb https://repos.influxdata.com/debian stretch stable"
 
 debian_keys:
   - "https://download.docker.com/linux/debian/gpg"
+  - "https://repos.influxdata.com/influxdb.key"
+
+
+# Art des Hosts: physical, vm, docker 
+host_type: "physical"
+
 
 webserver_domains: 
   - "infra"

host_vars/webserver

@@ -10,10 +10,16 @@ debian_sources:
   - "deb http://security.debian.org/ stretch/updates main contrib non-free"
   - "deb http://ftp.de.debian.org/debian/ stretch-updates main"
   - "deb http://ftp.halifax.rwth-aachen.de/debian/ stretch-updates main contrib non-free"
-  - "deb [arch=amd64] https://download.docker.com/linux/debian stretch stable"
+  - "deb https://download.docker.com/linux/debian stretch stable"
+  - "deb https://repos.influxdata.com/debian stretch stable"
 
 debian_keys:
   - "https://download.docker.com/linux/debian/gpg"
+  - "https://repos.influxdata.com/influxdb.key"
+
+
+# Art des Hosts: physical, vm, docker 
+host_type: "vm"
 
 
 letsencrypt_tos_sha256: 6373439b9f29d67a5cd4d18cbc7f264809342dbf21cb2ba2fc7588df987a6221

warpsrvint/main.yml

@@ -5,8 +5,8 @@
   roles:
     - { role: ../common/borgbackup, tags: borgbackup }
     - { role: ../common/borgserver, tags: borgserver }
-    - { role: ../common/prometheus-node, tags: prometheus-node }
     - { role: ../common/docker, tags: docker }
+    - { role: ../common/telegraf, tags: telegraf }
     - { role: nginx, tags: nginx }
     - { role: docker_grafana, tags: grafana }
     - { role: docker_influx, tags: influx }

webserver/main.yml

@@ -5,6 +5,7 @@
   roles:
     - { role: ../common/borgbackup, tags: borgbackup }
     - { role: ../common/docker, tags: docker }
+    - { role: ../common/telegraf, tags: telegraf }
     - { role: nginx, tags: nginx }
     - { role: openvpn, tags: openvpn }
     - { role: docker_alerta, tags: alerta }