Do you like Grafana but wish you could version your dashboard configuration? Do you find yourself repeating common patterns? If so, grafanalib is for you.
grafanalib lets you generate Grafana dashboards from simple Python scripts.
The following will configure a dashboard with a single row, with one QPS graph broken down by status code and another latency graph showing median and 99th percentile latency:
Warning
This example depends on unreleased changes to grafanalib. It will not work with grafanalib 0.1.2. See weaveworks#44 for details.
import itertools
from grafanalib.core import *
dashboard = Dashboard(
title="Frontend Stats",
rows=[
Row(panels=[
Graph(
title="Frontend QPS",
dataSource='My Prometheus',
targets=[
Target(
expr='sum(irate(nginx_http_requests_total{job="default/frontend",status=~"1.."}[1m]))',
legendFormat="1xx",
refId='A',
),
Target(
expr='sum(irate(nginx_http_requests_total{job="default/frontend",status=~"2.."}[1m]))',
legendFormat="2xx",
refId='B',
),
Target(
expr='sum(irate(nginx_http_requests_total{job="default/frontend",status=~"3.."}[1m]))',
legendFormat="3xx",
refId='C',
),
Target(
expr='sum(irate(nginx_http_requests_total{job="default/frontend",status=~"4.."}[1m]))',
legendFormat="4xx",
refId='D',
),
Target(
expr='sum(irate(nginx_http_requests_total{job="default/frontend",status=~"5.."}[1m]))',
legendFormat="5xx",
refId='E',
),
],
yAxes=[
YAxis(format=OPS_FORMAT),
YAxis(format=SHORT_FORMAT),
],
alert=Alert(
name="Too many 500s on Nginx",
message="More than 5 QPS of 500s on Nginx for 5 minutes",
alertConditions=[
AlertCondition(
Target(
expr='sum(irate(nginx_http_requests_total{job="default/frontend",status=~"5.."}[1m]))',
legendFormat="5xx",
refId='A',
),
timeRange=TimeRange("5m", "now"),
evaluator=GreaterThan(5),
operator=OP_AND,
reducerType=RTYPE_SUM,
),
],
)
),
Graph(
title="Frontend latency",
dataSource='My Prometheus',
targets=[
Target(
expr='histogram_quantile(0.5, sum(irate(nginx_http_request_duration_seconds_bucket{job="de
698A
fault/frontend"}[1m])) by (le))',
legendFormat="0.5 quantile",
refId='A',
),
Target(
expr='histogram_quantile(0.99, sum(irate(nginx_http_request_duration_seconds_bucket{job="default/frontend"}[1m])) by (le))',
legendFormat="0.99 quantile",
refId='B',
),
],
yAxes=[
YAxis(
format=SECONDS_FORMAT,
),
YAxis(
format=SHORT_FORMAT,
show=False,
)
],
),
]),
],
).auto_panel_ids()There is a fair bit of repetition here, but once you figure out what works for your needs, you can factor that out. See our Weave-specific customizations for inspiration.
If you save the above as frontend.dashboard.py (the suffix must be
.dashboard.py), you can then generate the JSON dashboard with:
$ generate-dashboard -o frontend.json frontend.dashboard.pygrafanalib is just a Python package, so:
$ pip install grafanalibThis library is in its very early stages. We'll probably make changes that break backwards compatibility, although we'll try hard not to.
grafanalib works with Python 3.4 and 3.5.