diff --git a/telegraf.conf b/telegraf.conf index f8c9fcb..384d54e 100644 --- a/telegraf.conf +++ b/telegraf.conf @@ -1,199 +1,200 @@ # Telegraf Configuration # # 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 = "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 = "5s" ## 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, precision will be set to the same timestamp order as the ## collection interval, with the maximum being 1s. ## Precision will NOT be used for service inputs, such as logparser and statsd. ## Valid values 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 = "" ## If set to true, do no set the "host" tag in the telegraf agent. omit_hostname = false ############################################################################### # OUTPUT PLUGINS # ############################################################################### # 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 as part of the same cluster, ## this means that only ONE of the urls will be written to each interval. urls = ["http://overwatch.kde.org:8086"] # required ## The target database for metrics (telegraf will create it if not exists). database = "telegraf" # required ## Retention policy to write to. Empty string writes to the default rp. retention_policy = "" ## 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 = "telegraf" password = "{{influxdb_user_password}}" ############################################################################### # INPUT PLUGINS # ############################################################################### # 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 # 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 need disk serial numbers. # skip_serial_number = false # Get kernel statistics from /proc/stat [[inputs.kernel]] # no configuration # Read metrics about memory usage [[inputs.mem]] # no configuration # 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 = ["eth*", "en*", "br*"] {# this is horrible, but better than keeping them as local changes in the repo #} {# and risking overwriting them on every ansible run #} {% if inventory_hostname in ['nicoda.kde.org', 'edulis.kde.org'] %} [[inputs.apache]] # default URL works {% endif %} {% if inventory_hostname == 'rosetta.kde.org' %} [[inputs.filestat]] files = ["/tmp/stats-compendium.script.php.lock", "/tmp/stats-datas.script.php.lock", "/tmp/stats-dictionary.script.php.lock", "/home/scripty/mailme.lock"] ## If true, read the entire file and calculate an md5 checksum. md5 = false {% endif %} {% if inventory_hostname == 'nicoda.kde.org' and False %} [[inputs.logparser]] ## Log files to parse. ## These accept standard unix glob matching rules, but with the addition of ## ** as a "super asterisk". ie: ## /var/log/**.log -> recursively find all .log files in /var/log ## /var/log/*/*.log -> find all .log files with a parent dir in /var/log ## /var/log/apache.log -> only tail the apache log file files = ["/var/log/apache2/planet.kde.org.log"] ## Read files that currently exist from the beginning. Files that are created ## while telegraf is running (and that match the "files" globs) will always ## be read from the beginning. from_beginning = false ## Parse logstash-style "grok" patterns: [inputs.logparser.grok] ## This is a list of patterns to check the given log file(s) for. ## Note that adding patterns here increases processing time. The most ## efficient configuration is to have one pattern per logparser. ## Other common built-in patterns are: ## %{COMMON_LOG_FORMAT} (plain apache & nginx access logs) ## %{COMBINED_LOG_FORMAT} (access logs + referrer & agent) patterns = ["^%{COMBINED_LOG_FORMAT}$"] ## Name of the outputted measurement name. measurement = "apache_access_log" {% endif %} {% if inventory_hostname == 'overwatch.kde.org' %} [[inputs.http_response]] interval = "60s" urls = ["https://kde.org"] + response_timeout = "20s" {% endif %}