a4f8d4a972
All counter based graphs inside the the Swift dashboard are fixed and now correctly showing the timings per second rather than total values per telegraf flush interval. Additionally the High Response Time graphs are now using the timing_upper metrics. Minor issues inside the playbook-influx-telegraf.yml and telegraf.conf.j2 are fixed to support deployments without optional componentns like ironic, cinder etc. Change-Id: I0ac0d2004416cae7a6d137d98ab685b7abc22d3f
104 lines
2.9 KiB
Django/Jinja
104 lines
2.9 KiB
Django/Jinja
[global_tags]
|
|
{% if inventory_hostname in groups['all_containers'] %}
|
|
node_type = "container"
|
|
{% elif inventory_hostname in groups['hosts'] %}
|
|
node_type = "physical_host"
|
|
{% endif %}
|
|
|
|
{% set run_commands = [] %}
|
|
{% for key, value in command_plugins.items() %}
|
|
{% if value.when_group | bool and (value.group == inventory_hostname or inventory_hostname in value.group | default([])) %}
|
|
{% set _ = run_commands.extend(value.command) %}
|
|
{% endif %}
|
|
{% endfor %}
|
|
|
|
{# The run_int adds padding to the interval so that plugins being added to the system have #}
|
|
{# enough time to execute. Every added plugin will add 8 seconds to the interval with a #}
|
|
{# default of 24. This value is later used as the flush interval which needs to be 2x the agent. #}
|
|
{% set run_int = run_commands | length %}
|
|
{% set interval = (run_int < 1 | ternary(0, run_int * 8)) + 24 %}
|
|
|
|
[agent]
|
|
interval = "{{ interval }}s"
|
|
round_interval = false
|
|
metric_batch_size = 1024
|
|
metric_buffer_limit = 10240
|
|
collection_jitter = "8s"
|
|
flush_interval = "{{ interval * 2 }}s"
|
|
flush_jitter = "8s"
|
|
debug = false
|
|
quiet = true
|
|
{% if inventory_hostname in groups['all_containers'] %}
|
|
hostname = "{{ ansible_hostname }}"
|
|
{% else %}
|
|
hostname = "{{ inventory_hostname }}"
|
|
{% endif %}
|
|
omit_hostname = false
|
|
|
|
[[outputs.influxdb]]
|
|
urls = [{{ influx_telegraf_targets | map('quote') | join(',') }}]
|
|
database = "{{ influxdb_db_name }}"
|
|
precision = "s"
|
|
write_consistency = "any"
|
|
timeout = "5s"
|
|
|
|
[[inputs.processes]]
|
|
|
|
[[inputs.system]]
|
|
|
|
{% set run_commands = [] %}
|
|
{% for key, value in command_plugins.items() %}
|
|
{% if value.when_group | bool and (value.group == inventory_hostname or inventory_hostname in value.group | default([])) %}
|
|
{% set _ = run_commands.extend(value.command) %}
|
|
{% endif %}
|
|
{% endfor %}
|
|
|
|
{% if run_commands %}
|
|
[[inputs.exec]]
|
|
commands = [{{ run_commands | map('quote') | join(',') }}]
|
|
timeout = "{{ (run_commands | length) * 8 }}s"
|
|
data_format = "influx"
|
|
{% endif %}
|
|
|
|
[[inputs.conntrack]]
|
|
files = ["ip_conntrack_count","ip_conntrack_max",
|
|
"nf_conntrack_count","nf_conntrack_max"]
|
|
dirs = ["/proc/sys/net/ipv4/netfilter","/proc/sys/net/netfilter"]
|
|
|
|
{% if inventory_hostname in groups['swift-proxy_containers'] %}
|
|
[[inputs.statsd]]
|
|
service_address = ":8125"
|
|
metric_separator = "."
|
|
templates = [
|
|
"*.swift.proxy-server.*.*.*.* host.measurement.measurement.measurement.method.returncode.field*",
|
|
"*.swift.proxy-server.*.policy.*.*.*.* host.measurement.measurement.measurement.measurement.measurement.method.returncode.field*",
|
|
]
|
|
{% endif %}
|
|
|
|
{% if inventory_hostname in groups['all_containers'] %}
|
|
[[inputs.net]]
|
|
|
|
{% elif inventory_hostname in groups['hosts'] %}
|
|
[[inputs.cpu]]
|
|
percpu = true
|
|
totalcpu = true
|
|
fielddrop = ["time_*"]
|
|
|
|
[[inputs.net]]
|
|
|
|
[[inputs.netstat]]
|
|
|
|
[[inputs.disk]]
|
|
ignore_fs = ["tmpfs", "devtmpfs"]
|
|
|
|
[[inputs.diskio]]
|
|
|
|
[[inputs.kernel]]
|
|
|
|
[[inputs.mem]]
|
|
|
|
[[inputs.swap]]
|
|
|
|
{% endif %}
|
|
|