# missing Automation # curl -s https://repos.influxdata.com/influxdata-archive_compat.key > influxdata-archive_compat.key # echo '393e8779c89ac8d958f81f942f9ad7fb82a25e133faddaf92e15b16e6ac9ce4c influxdata-archive_compat.key' | sha256sum -c && cat influxdata-archive_compat.key | gpg --dearmor | sudo tee /etc/apt/trusted.gpg.d/influxdata-archive_compat.gpg > /dev/null # echo 'deb [signed-by=/etc/apt/trusted.gpg.d/influxdata-archive_compat.gpg] https://repos.influxdata.com/debian stable main' | sudo tee /etc/apt/sources.list.d/influxdata.list # sudo apt-get update && sudo apt-get install telegraf - name: Install Telegraf become: true ansible.builtin.package: name: - telegraf state: latest - name: Enable Telegraf Service become: true ansible.builtin.service: name: telegraf enabled: true - name: Setup Telegraf Agent Config become: true copy: dest: "/etc/telegraf/telegraf.d/myInfra-01-agent.conf" content: | # file created automatically by ansiable myInfra.rsyslog-client role [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" ## Collection offset is used to shift the collection by the given amount. ## This can be be used to avoid many plugins querying constraint devices ## at the same time by manually scheduling them in time. # collection_offset = "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" ## Collected metrics are rounded to the precision specified. Precision is ## specified as an interval with an integer + unit (e.g. 0s, 10ms, 2us, 4s). ## Valid time units are "ns", "us" (or "µs"), "ms", "s". ## ## 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. precision = "0s" ## 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 = "var/log/telegraf.log" ## 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 = "0h" ## 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 = "100MB" ## 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 ## Pick a timezone to use when logging or type 'local' for local time. ## Example: America/Chicago # log_with_timezone = "" ## 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 notify: - restart_telegraf - name: Setup Telegraf Influxdb Config become: true copy: dest: "/etc/telegraf/telegraf.d/myInfra-02-influxdb.conf" content: | [[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 = ["{{telegraf_influxdb_url}}"] ## Token for authentication. token = "{{telegraf_influxdb_token}}" # # ## Organization is the name of the organization you wish to write to. organization = "{{telegraf_influxdb_org}}" # # ## Destination bucket to write into. bucket = "{{telegraf_influxdb_bucket}}" # notify: - restart_telegraf - name: Setup Telegraf Inputs Config become: true copy: dest: "/etc/telegraf/telegraf.d/myInfra-03-inputs.conf" content: | # 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 = ["/"] ## Ignore mount points by filesystem type. ignore_fs = ["tmpfs", "devtmpfs", "devfs", "iso9660", "overlay", "aufs", "squashfs"] [[inputs.diskio]] [[inputs.kernel]] [[inputs.mem]] # Get the number of processes and group them by status [[inputs.processes]] # no configuration # Read metrics about swap memory usage [[inputs.swap]] # no configuration # Read metrics about system load & uptime [[inputs.system]] # no configuration # 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 = ["eth0"] notify: - restart_telegraf