summaryrefslogtreecommitdiffstats
path: root/monitoring/ceph-mixin/tests_dashboards
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-21 11:54:28 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-21 11:54:28 +0000
commite6918187568dbd01842d8d1d2c808ce16a894239 (patch)
tree64f88b554b444a49f656b6c656111a145cbbaa28 /monitoring/ceph-mixin/tests_dashboards
parentInitial commit. (diff)
downloadceph-e6918187568dbd01842d8d1d2c808ce16a894239.tar.xz
ceph-e6918187568dbd01842d8d1d2c808ce16a894239.zip
Adding upstream version 18.2.2.upstream/18.2.2
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'monitoring/ceph-mixin/tests_dashboards')
-rw-r--r--monitoring/ceph-mixin/tests_dashboards/__init__.py189
-rw-r--r--monitoring/ceph-mixin/tests_dashboards/features/__init__.py0
-rw-r--r--monitoring/ceph-mixin/tests_dashboards/features/ceph-cluster.feature54
-rw-r--r--monitoring/ceph-mixin/tests_dashboards/features/environment.py135
-rw-r--r--monitoring/ceph-mixin/tests_dashboards/features/host-details.feature131
-rw-r--r--monitoring/ceph-mixin/tests_dashboards/features/hosts_overview.feature41
-rw-r--r--monitoring/ceph-mixin/tests_dashboards/features/osd-device-details.feature88
-rw-r--r--monitoring/ceph-mixin/tests_dashboards/features/osds-overview.feature15
-rw-r--r--monitoring/ceph-mixin/tests_dashboards/features/radosgw-detail.feature139
-rw-r--r--monitoring/ceph-mixin/tests_dashboards/features/radosgw_overview.feature250
-rw-r--r--monitoring/ceph-mixin/tests_dashboards/features/self.feature68
-rw-r--r--monitoring/ceph-mixin/tests_dashboards/features/steps/__init__.py1
-rw-r--r--monitoring/ceph-mixin/tests_dashboards/requirements.txt12
-rw-r--r--monitoring/ceph-mixin/tests_dashboards/util.py109
14 files changed, 1232 insertions, 0 deletions
diff --git a/monitoring/ceph-mixin/tests_dashboards/__init__.py b/monitoring/ceph-mixin/tests_dashboards/__init__.py
new file mode 100644
index 000000000..45147e5c3
--- /dev/null
+++ b/monitoring/ceph-mixin/tests_dashboards/__init__.py
@@ -0,0 +1,189 @@
+import re
+import subprocess
+import sys
+import tempfile
+from dataclasses import asdict, dataclass, field
+from typing import Any, List
+
+import yaml
+
+from .util import replace_grafana_expr_variables
+
+
+@dataclass
+class InputSeries:
+ series: str = ''
+ values: str = ''
+
+@dataclass
+class ExprSample:
+ labels: str = ''
+ value: float = -1
+
+@dataclass
+class PromqlExprTest:
+ expr: str = ''
+ eval_time: str = '1m'
+ exp_samples: List[ExprSample] = field(default_factory=list)
+
+@dataclass
+class Test:
+ interval: str = '1m'
+ input_series: List[InputSeries] = field(default_factory=list)
+ promql_expr_test: List[PromqlExprTest] = field(default_factory=list)
+
+
+@dataclass
+class TestFile:
+ evaluation_interval: str = '1m'
+ tests: List[Test] = field(default_factory=list)
+
+
+class PromqlTest:
+ """
+ Base class to provide prometheus query test capabilities. After setting up
+ the query test with its input and expected output it's expected to run promtool.
+
+ https://prometheus.io/docs/prometheus/latest/configuration/unit_testing_rules/#test-yml
+
+ The workflow of testing would be something like:
+
+ # add prometheus query to test
+ self.set_expression('bonding_slaves > 0')
+
+ # add some prometheus input series
+ self.add_series('bonding_slaves{master="bond0"}', '2')
+ self.add_series('bonding_slaves{master="bond1"}', '3')
+ self.add_series('node_network_receive_bytes{instance="127.0.0.1",
+ device="eth1"}', "10 100 230 22")
+
+ # expected output of the query
+ self.add_exp_samples('bonding_slaves{master="bond0"}', 2)
+ self.add_exp_samples('bonding_slaves{master="bond1"}', 3)
+
+ # at last, always call promtool with:
+ self.assertTrue(self.run_promtool())
+ # assertTrue means it expect promtool to succeed
+ """
+
+ def __init__(self):
+ self.test_output_file = tempfile.NamedTemporaryFile('w+')
+
+ self.test_file = TestFile()
+ self.test = Test()
+ self.promql_expr_test = PromqlExprTest()
+ self.test.promql_expr_test.append(self.promql_expr_test)
+ self.test_file.tests.append(self.test)
+
+ self.variables = {}
+
+ def __del__(self):
+ self.test_output_file.close()
+
+
+ def set_evaluation_interval(self, interval: int, unit: str = 'm') -> None:
+ """
+ Set the evaluation interval of the time series
+
+ Args:
+ interval (int): number of units.
+ unit (str): unit type: 'ms', 's', 'm', etc...
+ """
+ self.test_file.evaluation_interval = f'{interval}{unit}'
+
+ def set_interval(self, interval: int, unit: str = 'm') -> None:
+ """
+ Set the duration of the time series
+
+ Args:
+ interval (int): number of units.
+ unit (str): unit type: 'ms', 's', 'm', etc...
+ """
+ self.test.interval = f'{interval}{unit}'
+
+ def set_expression(self, expr: str) -> None:
+ """
+ Set the prometheus expression/query used to filter data.
+
+ Args:
+ expr(str): expression/query.
+ """
+ self.promql_expr_test.expr = expr
+
+ def add_series(self, series: str, values: str) -> None:
+ """
+ Add a series to the input.
+
+ Args:
+ series(str): Prometheus series.
+ Notation: '<metric name>{<label name>=<label value>, ...}'
+ values(str): Value of the series.
+ """
+ input_series = InputSeries(series=series, values=values)
+ self.test.input_series.append(input_series)
+
+ def set_eval_time(self, eval_time: int, unit: str = 'm') -> None:
+ """
+ Set the time when the expression will be evaluated
+
+ Args:
+ interval (int): number of units.
+ unit (str): unit type: 'ms', 's', 'm', etc...
+ """
+ self.promql_expr_test.eval_time = f'{eval_time}{unit}'
+
+ def add_exp_samples(self, sample: str, values: Any) -> None:
+ """
+ Add an expected sample/output of the query given the series/input
+
+ Args:
+ sample(str): Expected sample.
+ Notation: '<metric name>{<label name>=<label value>, ...}'
+ values(Any): Value of the sample.
+ """
+ expr_sample = ExprSample(labels=sample, value=values)
+ self.promql_expr_test.exp_samples.append(expr_sample)
+
+ def set_variable(self, variable: str, value: str):
+ """
+ If a query makes use of grafonnet variables, for example
+ '$osd_hosts', you should change this to a real value. Example:
+
+
+ > self.set_expression('bonding_slaves{master="$osd_hosts"} > 0')
+ > self.set_variable('osd_hosts', '127.0.0.1')
+ > print(self.query)
+ > bonding_slaves{master="127.0.0.1"} > 0
+
+ Args:
+ variable(str): Variable name
+ value(str): Value to replace variable with
+
+ """
+ self.variables[variable] = value
+
+ def run_promtool(self):
+ """
+ Run promtool to test the query after setting up the input, output
+ and extra parameters.
+
+ Returns:
+ bool: True if successful, False otherwise.
+ """
+
+ for variable, value in self.variables.items():
+ expr = self.promql_expr_test.expr
+ new_expr = replace_grafana_expr_variables(expr, variable, value)
+ self.set_expression(new_expr)
+
+ test_as_dict = asdict(self.test_file)
+ yaml.dump(test_as_dict, self.test_output_file)
+
+ args = f'promtool test rules {self.test_output_file.name}'.split()
+ try:
+ subprocess.run(args, check=True)
+ return True
+ except subprocess.CalledProcessError as process_error:
+ print(yaml.dump(test_as_dict))
+ print(process_error.stderr)
+ return False
diff --git a/monitoring/ceph-mixin/tests_dashboards/features/__init__.py b/monitoring/ceph-mixin/tests_dashboards/features/__init__.py
new file mode 100644
index 000000000..e69de29bb
--- /dev/null
+++ b/monitoring/ceph-mixin/tests_dashboards/features/__init__.py
diff --git a/monitoring/ceph-mixin/tests_dashboards/features/ceph-cluster.feature b/monitoring/ceph-mixin/tests_dashboards/features/ceph-cluster.feature
new file mode 100644
index 000000000..1a446cd2c
--- /dev/null
+++ b/monitoring/ceph-mixin/tests_dashboards/features/ceph-cluster.feature
@@ -0,0 +1,54 @@
+Feature: Ceph Cluster Dashboard
+
+Scenario: "Test total PG States"
+ Given the following series:
+ | metrics | values |
+ | ceph_pg_total{foo="var"} | 10 100 |
+ | ceph_pg_total{foo="bar"} | 20 200 |
+ Then Grafana panel `PG States` with legend `Total` shows:
+ | metrics | values |
+ | {} | 300 |
+
+Scenario: "Test OSDs in"
+ Given the following series:
+ | metrics | values |
+ | ceph_osd_in{ceph_daemon="osd.0"} | 1.0 |
+ | ceph_osd_in{ceph_daemon="osd.1"} | 0.0 |
+ | ceph_osd_in{ceph_daemon="osd.2"} | 1.0 |
+ When variable `instance` is `.*`
+ Then Grafana panel `OSDs` with legend `In` shows:
+ | metrics | values |
+ | {} | 2 |
+
+Scenario: "Test OSDs down"
+ Given the following series:
+ | metrics | values |
+ | ceph_osd_up{ceph_daemon="osd.0", instance="127.0.0.1"} | 0.0 |
+ | ceph_osd_up{ceph_daemon="osd.1", instance="127.0.0.1"} | 0.0 |
+ | ceph_osd_up{ceph_daemon="osd.2", instance="127.0.0.1"} | 0.0 |
+ When variable `instance` is `127.0.0.1`
+ Then Grafana panel `OSDs` with legend `Down` shows:
+ | metrics | values |
+ | {} | 3 |
+
+Scenario: "Test OSDs out"
+ Given the following series:
+ | metrics | values |
+ | ceph_osd_in{ceph_daemon="osd.0", instance="127.0.0.1"} | 0.0 |
+ | ceph_osd_in{ceph_daemon="osd.1", instance="127.0.0.1"} | 1.0 |
+ | ceph_osd_in{ceph_daemon="osd.2", instance="127.0.0.1"} | 0.0 |
+ When variable `instance` is `127.0.0.1`
+ Then Grafana panel `OSDs` with legend `Out` shows:
+ | metrics | values |
+ | {} | 2 |
+
+Scenario: "Test OSDs all"
+ Given the following series:
+ | metrics | values |
+ | ceph_osd_metadata{ceph_daemon="osd.0", instance="127.0.0.1"} | 1.0 |
+ | ceph_osd_metadata{ceph_daemon="osd.1", instance="127.0.0.1"} | 1.0 |
+ | ceph_osd_metadata{ceph_daemon="osd.2", instance="127.0.0.1"} | 1.0 |
+ When variable `instance` is `127.0.0.1`
+ Then Grafana panel `OSDs` with legend `All` shows:
+ | metrics | values |
+ | {} | 3 |
diff --git a/monitoring/ceph-mixin/tests_dashboards/features/environment.py b/monitoring/ceph-mixin/tests_dashboards/features/environment.py
new file mode 100644
index 000000000..5dc76a09e
--- /dev/null
+++ b/monitoring/ceph-mixin/tests_dashboards/features/environment.py
@@ -0,0 +1,135 @@
+# type: ignore[no-redef]
+# pylint: disable=E0611,W0613,E0102
+import copy
+
+from behave import given, then, when
+from prettytable import PrettyTable
+
+from tests_dashboards import PromqlTest
+from tests_dashboards.util import get_dashboards_data, resolve_time_and_unit
+
+
+class GlobalContext:
+ def __init__(self):
+ self.tested_queries_count = 0
+ self.promql_expr_test = None
+ self.data = get_dashboards_data()
+ self.query_map = self.data['queries']
+
+ def reset_promql_test(self):
+ self.promql_expr_test = PromqlTest()
+ self.promql_expr_test.variables = copy.copy(self.data['variables'])
+
+ def print_query_stats(self):
+ total = len(self.query_map)
+ table = PrettyTable()
+ table.field_names = ['Name', 'Queries', 'Tested', 'Cover']
+
+ def percent(tested, total):
+ return str(round((tested / total) * 100, 2)) + '%'
+
+ def file_name(path):
+ return path.split('/')[-1]
+
+ total = 0
+ tested = 0
+ for path, stat in self.data['stats'].items():
+ assert stat['total']
+ table.add_row([file_name(path), stat['total'], stat['tested'],
+ percent(stat['tested'], stat['total'])])
+ total += stat['total']
+ tested += stat['tested']
+
+ assert total
+ table.add_row(['Total', total, tested, percent(tested, total)])
+ print(table)
+
+
+global_context = GlobalContext()
+
+# Behave function overloading
+# ===========================
+
+
+def before_scenario(context, scenario):
+ global_context.reset_promql_test()
+
+
+def after_scenario(context, scenario):
+ assert global_context.promql_expr_test.run_promtool()
+
+
+def after_all(context):
+ global_context.print_query_stats()
+
+
+@given("the following series")
+def step_impl(context):
+ for row in context.table:
+ metric = row['metrics']
+ value = row['values']
+ global_context.promql_expr_test.add_series(metric, value)
+
+
+@when('evaluation interval is `{interval}`')
+def step_impl(context, interval):
+ interval_without_unit, unit = resolve_time_and_unit(interval)
+ if interval_without_unit is None:
+ raise ValueError(f'Invalid interval time: {interval_without_unit}. ' +
+ 'A valid time looks like "1m" where you have a number plus a unit')
+ global_context.promql_expr_test.set_evaluation_interval(interval_without_unit, unit)
+
+
+@when('interval is `{interval}`')
+def step_impl(context, interval):
+ interval_without_unit, unit = resolve_time_and_unit(interval)
+ if interval_without_unit is None:
+ raise ValueError(f'Invalid interval time: {interval_without_unit}. ' +
+ 'A valid time looks like "1m" where you have a number plus a unit')
+ global_context.promql_expr_test.set_interval(interval_without_unit, unit)
+
+
+@when('evaluation time is `{eval_time}`')
+def step_impl(context, eval_time):
+ eval_time_without_unit, unit = resolve_time_and_unit(eval_time)
+ if eval_time_without_unit is None:
+ raise ValueError(f'Invalid evalution time: {eval_time}. ' +
+ 'A valid time looks like "1m" where you have a number plus a unit')
+ global_context.promql_expr_test.set_eval_time(eval_time_without_unit, unit)
+
+
+@when('variable `{variable}` is `{value}`')
+def step_impl(context, variable, value):
+ global_context.promql_expr_test.set_variable(variable, value)
+
+
+@then('Grafana panel `{panel_name}` with legend `{legend}` shows')
+def step_impl(context, panel_name, legend):
+ """
+ This step can have an empty legend. As 'behave' doesn't provide a way
+ to say it's empty we use EMPTY to mark as empty.
+ """
+ if legend == "EMPTY":
+ legend = ''
+ query_id = panel_name + '-' + legend
+ if query_id not in global_context.query_map:
+ raise KeyError((f'Query with legend {legend} in panel "{panel_name}"'
+ 'couldn\'t be found'))
+
+ expr = global_context.query_map[query_id]['query']
+ global_context.promql_expr_test.set_expression(expr)
+ for row in context.table:
+ metric = row['metrics']
+ value = row['values']
+ global_context.promql_expr_test.add_exp_samples(metric, float(value))
+ path = global_context.query_map[query_id]['path']
+ global_context.data['stats'][path]['tested'] += 1
+
+
+@then('query `{query}` produces')
+def step_impl(context, query):
+ global_context.promql_expr_test.set_expression(query)
+ for row in context.table:
+ metric = row['metrics']
+ value = row['values']
+ global_context.promql_expr_test.add_exp_samples(metric, float(value))
diff --git a/monitoring/ceph-mixin/tests_dashboards/features/host-details.feature b/monitoring/ceph-mixin/tests_dashboards/features/host-details.feature
new file mode 100644
index 000000000..51e3c5819
--- /dev/null
+++ b/monitoring/ceph-mixin/tests_dashboards/features/host-details.feature
@@ -0,0 +1,131 @@
+Feature: Host Details Dashboard
+
+Scenario: "Test OSD"
+ Given the following series:
+ | metrics | values |
+ | ceph_osd_metadata{job="ceph",back_iface="",ceph_daemon="osd.0",cluster_addr="192.168.1.12",device_class="hdd",front_iface="",hostname="127.0.0.1",objectstore="bluestore",public_addr="192.168.1.12",ceph_version="ceph version 17.0.0-8967-g6932a4f702a (6932a4f702a0d557fc36df3ca7a3bca70de42667) quincy (dev)"} | 1.0 |
+ | ceph_osd_metadata{job="ceph",back_iface="",ceph_daemon="osd.1",cluster_addr="192.168.1.12",device_class="hdd",front_iface="",hostname="127.0.0.1",objectstore="bluestore",public_addr="192.168.1.12",ceph_version="ceph version 17.0.0-8967-g6932a4f702a (6932a4f702a0d557fc36df3ca7a3bca70de42667) quincy (dev)"} | 1.0 |
+ | ceph_osd_metadata{job="ceph",back_iface="",ceph_daemon="osd.2",cluster_addr="192.168.1.12",device_class="hdd",front_iface="",hostname="127.0.0.1",objectstore="bluestore",public_addr="192.168.1.12",ceph_version="ceph version 17.0.0-8967-g6932a4f702a (6932a4f702a0d557fc36df3ca7a3bca70de42667) quincy (dev)"} | 1.0 |
+ When variable `ceph_hosts` is `127.0.0.1`
+ Then Grafana panel `OSDs` with legend `EMPTY` shows:
+ | metrics | values |
+ | {} | 3 |
+
+# IOPS Panel - begin
+
+Scenario: "Test Disk IOPS - Writes - Several OSDs per device"
+ Given the following series:
+ | metrics | values |
+ | node_disk_writes_completed_total{job="ceph",device="sda",instance="localhost:9100"} | 10+60x1 |
+ | node_disk_writes_completed_total{job="ceph",device="sdb",instance="localhost:9100"} | 10+60x1 |
+ | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.0 osd.1 osd.2",device="/dev/sda",instance="localhost:9283"} | 1.0 |
+ | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.3 osd.4 osd.5",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
+ When variable `ceph_hosts` is `localhost`
+ Then Grafana panel `$ceph_hosts Disk IOPS` with legend `{{device}}({{ceph_daemon}}) writes` shows:
+ | metrics | values |
+ | {job="ceph",ceph_daemon="osd.0 osd.1 osd.2", device="sda", instance="localhost"} | 1 |
+ | {job="ceph",ceph_daemon="osd.3 osd.4 osd.5", device="sdb", instance="localhost"} | 1 |
+
+Scenario: "Test Disk IOPS - Writes - Single OSD per device"
+ Given the following series:
+ | metrics | values |
+ | node_disk_writes_completed_total{job="ceph",device="sda",instance="localhost:9100"} | 10+60x1 |
+ | node_disk_writes_completed_total{job="ceph",device="sdb",instance="localhost:9100"} | 10+60x1 |
+ | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
+ | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
+ When variable `ceph_hosts` is `localhost`
+ Then Grafana panel `$ceph_hosts Disk IOPS` with legend `{{device}}({{ceph_daemon}}) writes` shows:
+ | metrics | values |
+ | {job="ceph",ceph_daemon="osd.0", device="sda", instance="localhost"} | 1 |
+ | {job="ceph",ceph_daemon="osd.1", device="sdb", instance="localhost"} | 1 |
+
+Scenario: "Test Disk IOPS - Reads - Several OSDs per device"
+ Given the following series:
+ | metrics | values |
+ | node_disk_reads_completed_total{job="ceph",device="sda",instance="localhost:9100"} | 10+60x1 |
+ | node_disk_reads_completed_total{job="ceph",device="sdb",instance="localhost:9100"} | 10+60x1 |
+ | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.0 osd.1 osd.2",device="/dev/sda",instance="localhost:9283"} | 1.0 |
+ | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.3 osd.4 osd.5",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
+ When variable `ceph_hosts` is `localhost`
+ Then Grafana panel `$ceph_hosts Disk IOPS` with legend `{{device}}({{ceph_daemon}}) reads` shows:
+ | metrics | values |
+ | {job="ceph",ceph_daemon="osd.0 osd.1 osd.2", device="sda", instance="localhost"} | 1 |
+ | {job="ceph",ceph_daemon="osd.3 osd.4 osd.5", device="sdb", instance="localhost"} | 1 |
+
+Scenario: "Test Disk IOPS - Reads - Single OSD per device"
+ Given the following series:
+ | metrics | values |
+ | node_disk_reads_completed_total{job="ceph",device="sda",instance="localhost:9100"} | 10+60x1 |
+ | node_disk_reads_completed_total{job="ceph",device="sdb",instance="localhost:9100"} | 10+60x1 |
+ | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
+ | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
+ When variable `ceph_hosts` is `localhost`
+ Then Grafana panel `$ceph_hosts Disk IOPS` with legend `{{device}}({{ceph_daemon}}) reads` shows:
+ | metrics | values |
+ | {job="ceph",ceph_daemon="osd.0", device="sda", instance="localhost"} | 1 |
+ | {job="ceph",ceph_daemon="osd.1", device="sdb", instance="localhost"} | 1 |
+
+# IOPS Panel - end
+
+# Node disk bytes written/read panel - begin
+
+Scenario: "Test disk throughput - read"
+ Given the following series:
+ | metrics | values |
+ | node_disk_read_bytes_total{job="ceph",device="sda",instance="localhost:9100"} | 10+60x1 |
+ | node_disk_read_bytes_total{job="ceph",device="sdb",instance="localhost:9100"} | 100+600x1 |
+ | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
+ | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
+ When variable `ceph_hosts` is `localhost`
+ Then Grafana panel `$ceph_hosts Throughput by Disk` with legend `{{device}}({{ceph_daemon}}) read` shows:
+ | metrics | values |
+ | {job="ceph",ceph_daemon="osd.0", device="sda", instance="localhost"} | 1 |
+ | {job="ceph",ceph_daemon="osd.1", device="sdb", instance="localhost"} | 10 |
+
+Scenario: "Test disk throughput - write"
+ Given the following series:
+ | metrics | values |
+ | node_disk_written_bytes_total{job="ceph",device="sda",instance="localhost:9100"} | 10+60x1 |
+ | node_disk_written_bytes_total{job="ceph",device="sdb",instance="localhost:9100"} | 100+600x1 |
+ | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
+ | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
+ When variable `ceph_hosts` is `localhost`
+ Then Grafana panel `$ceph_hosts Throughput by Disk` with legend `{{device}}({{ceph_daemon}}) write` shows:
+ | metrics | values |
+ | {job="ceph",ceph_daemon="osd.0", device="sda", instance="localhost"} | 1 |
+ | {job="ceph",ceph_daemon="osd.1", device="sdb", instance="localhost"} | 10 |
+
+# Node disk bytes written/read panel - end
+
+Scenario: "Test $ceph_hosts Disk Latency panel"
+ Given the following series:
+ | metrics | values |
+ | node_disk_write_time_seconds_total{job="ceph",device="sda",instance="localhost:9100"} | 10+60x1 |
+ | node_disk_write_time_seconds_total{job="ceph",device="sdb",instance="localhost:9100"} | 10+60x1 |
+ | node_disk_writes_completed_total{job="ceph",device="sda",instance="localhost:9100"} | 10+60x1 |
+ | node_disk_writes_completed_total{job="ceph",device="sdb",instance="localhost:9100"} | 10+60x1 |
+ | node_disk_read_time_seconds_total{job="ceph",device="sda",instance="localhost:9100"} | 10+60x1 |
+ | node_disk_read_time_seconds_total{job="ceph",device="sdb",instance="localhost:9100"} | 10+60x1 |
+ | node_disk_reads_completed_total{job="ceph",device="sda",instance="localhost:9100"} | 10+60x1 |
+ | node_disk_reads_completed_total{job="ceph",device="sdb",instance="localhost:9100"} | 10+60x1 |
+ | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
+ | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
+ When variable `ceph_hosts` is `localhost`
+ Then Grafana panel `$ceph_hosts Disk Latency` with legend `{{device}}({{ceph_daemon}})` shows:
+ | metrics | values |
+ | {ceph_daemon="osd.0", device="sda", instance="localhost"} | 1 |
+ | {ceph_daemon="osd.1", device="sdb", instance="localhost"} | 1 |
+
+Scenario: "Test $ceph_hosts Disk utilization"
+ Given the following series:
+ | metrics | values |
+ | node_disk_io_time_seconds_total{job="ceph",device="sda",instance="localhost:9100"} | 10+60x1 |
+ | node_disk_io_time_seconds_total{job="ceph",device="sdb",instance="localhost:9100"} | 10+60x1 |
+ | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
+ | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
+ When variable `ceph_hosts` is `localhost`
+ Then Grafana panel `$ceph_hosts Disk utilization` with legend `{{device}}({{ceph_daemon}})` shows:
+ | metrics | values |
+ | {job="ceph",ceph_daemon="osd.0", device="sda", instance="localhost"} | 100 |
+ | {job="ceph",ceph_daemon="osd.1", device="sdb", instance="localhost"} | 100 |
+
diff --git a/monitoring/ceph-mixin/tests_dashboards/features/hosts_overview.feature b/monitoring/ceph-mixin/tests_dashboards/features/hosts_overview.feature
new file mode 100644
index 000000000..6c5eceaed
--- /dev/null
+++ b/monitoring/ceph-mixin/tests_dashboards/features/hosts_overview.feature
@@ -0,0 +1,41 @@
+Feature: Hosts Overview Dashboard
+
+Scenario: "Test network load succeeds"
+ Given the following series:
+ | metrics | values |
+ | node_network_receive_bytes{instance="127.0.0.1", device="eth1"} | 10 100 |
+ | node_network_receive_bytes{instance="127.0.0.1", device="eth2"} | 10 100 |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 10 100 |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 10 100 |
+ When variable `osd_hosts` is `127.0.0.1`
+ Then Grafana panel `Network Load` with legend `EMPTY` shows:
+ | metrics | values |
+ | {} | 6 |
+
+Scenario: "Test network load with bonding succeeds"
+ Given the following series:
+ | metrics | values |
+ | node_network_receive_bytes{instance="127.0.0.1", device="eth1"} | 10 100 200 |
+ | node_network_receive_bytes{instance="127.0.0.1", device="eth2"} | 10 100 200 |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 10 100 200 |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 10 100 200 |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="bond0"} | 20 200 300 |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="bond0"} | 20 200 300 |
+ | bonding_slaves{instance="127.0.0.1", master="bond0"} | 2 |
+ When variable `osd_hosts` is `127.0.0.1`
+ Then Grafana panel `Network Load` with legend `EMPTY` shows:
+ | metrics | values |
+ | {} | 6 |
+
+Scenario: "Test AVG Disk Utilization"
+ Given the following series:
+ | metrics | values |
+ | node_disk_io_time_seconds_total{device="sda",instance="localhost:9100"} | 10+60x1 |
+ | node_disk_io_time_seconds_total{device="sdb",instance="localhost:9100"} | 10+60x1 |
+ | node_disk_io_time_seconds_total{device="sdc",instance="localhost:9100"} | 10 2000 |
+ | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.0",device="sda",instance="localhost:9283"} | 1.0 |
+ | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
+ When variable `osd_hosts` is `localhost`
+ Then Grafana panel `AVG Disk Utilization` with legend `EMPTY` shows:
+ | metrics | values |
+ | {} | 100 |
diff --git a/monitoring/ceph-mixin/tests_dashboards/features/osd-device-details.feature b/monitoring/ceph-mixin/tests_dashboards/features/osd-device-details.feature
new file mode 100644
index 000000000..0d6ca8b17
--- /dev/null
+++ b/monitoring/ceph-mixin/tests_dashboards/features/osd-device-details.feature
@@ -0,0 +1,88 @@
+Feature: OSD device details
+
+Scenario: "Test Physical Device Latency for $osd - Reads"
+ Given the following series:
+ | metrics | values |
+ | node_disk_reads_completed_total{device="sda",instance="localhost"} | 10 60 |
+ | node_disk_reads_completed_total{device="sdb",instance="localhost"} | 10 60 |
+ | node_disk_read_time_seconds_total{device="sda",instance="localhost"} | 100 600 |
+ | node_disk_read_time_seconds_total{device="sdb",instance="localhost"} | 100 600 |
+ | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
+ | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
+ When variable `osd` is `osd.0`
+ Then Grafana panel `Physical Device Latency for $osd` with legend `{{instance}}/{{device}} Reads` shows:
+ | metrics | values |
+ | {device="sda",instance="localhost"} | 10 |
+
+Scenario: "Test Physical Device Latency for $osd - Writes"
+ Given the following series:
+ | metrics | values |
+ | node_disk_writes_completed_total{device="sda",instance="localhost"} | 10 60 |
+ | node_disk_writes_completed_total{device="sdb",instance="localhost"} | 10 60 |
+ | node_disk_write_time_seconds_total{device="sda",instance="localhost"} | 100 600 |
+ | node_disk_write_time_seconds_total{device="sdb",instance="localhost"} | 100 600 |
+ | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
+ | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
+ When variable `osd` is `osd.0`
+ Then Grafana panel `Physical Device Latency for $osd` with legend `{{instance}}/{{device}} Writes` shows:
+ | metrics | values |
+ | {device="sda",instance="localhost"} | 10 |
+
+Scenario: "Test Physical Device R/W IOPS for $osd - Writes"
+ Given the following series:
+ | metrics | values |
+ | node_disk_writes_completed_total{device="sda",instance="localhost"} | 10 100 |
+ | node_disk_writes_completed_total{device="sdb",instance="localhost"} | 10 100 |
+ | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
+ | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
+ When variable `osd` is `osd.0`
+ Then Grafana panel `Physical Device R/W IOPS for $osd` with legend `{{device}} on {{instance}} Writes` shows:
+ | metrics | values |
+ | {device="sda",instance="localhost"} | 1.5 |
+
+Scenario: "Test Physical Device R/W IOPS for $osd - Reads"
+ Given the following series:
+ | metrics | values |
+ | node_disk_reads_completed_total{device="sda",instance="localhost"} | 10 100 |
+ | node_disk_reads_completed_total{device="sdb",instance="localhost"} | 10 100 |
+ | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
+ | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
+ When variable `osd` is `osd.0`
+ Then Grafana panel `Physical Device R/W IOPS for $osd` with legend `{{device}} on {{instance}} Reads` shows:
+ | metrics | values |
+ | {device="sda",instance="localhost"} | 1.5 |
+
+Scenario: "Test Physical Device R/W Bytes for $osd - Reads"
+ Given the following series:
+ | metrics | values |
+ | node_disk_reads_completed_total{device="sda",instance="localhost"} | 10 100 |
+ | node_disk_reads_completed_total{device="sdb",instance="localhost"} | 10 100 |
+ | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
+ | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
+ When variable `osd` is `osd.0`
+ Then Grafana panel `Physical Device R/W IOPS for $osd` with legend `{{device}} on {{instance}} Reads` shows:
+ | metrics | values |
+ | {device="sda",instance="localhost"} | 1.5 |
+
+Scenario: "Test Physical Device R/W Bytes for $osd - Writes"
+ Given the following series:
+ | metrics | values |
+ | node_disk_writes_completed_total{device="sda",instance="localhost"} | 10 100 |
+ | node_disk_writes_completed_total{device="sdb",instance="localhost"} | 10 100 |
+ | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
+ | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
+ When variable `osd` is `osd.0`
+ Then Grafana panel `Physical Device R/W IOPS for $osd` with legend `{{device}} on {{instance}} Writes` shows:
+ | metrics | values |
+ | {device="sda",instance="localhost"} | 1.5 |
+
+Scenario: "Test Physical Device Util% for $osd"
+ Given the following series:
+ | metrics | values |
+ | node_disk_io_time_seconds_total{device="sda",instance="localhost:9100"} | 10 100 |
+ | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 |
+ | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 |
+ When variable `osd` is `osd.0`
+ Then Grafana panel `Physical Device Util% for $osd` with legend `{{device}} on {{instance}}` shows:
+ | metrics | values |
+ | {device="sda",instance="localhost"} | 1.5 |
diff --git a/monitoring/ceph-mixin/tests_dashboards/features/osds-overview.feature b/monitoring/ceph-mixin/tests_dashboards/features/osds-overview.feature
new file mode 100644
index 000000000..78d306419
--- /dev/null
+++ b/monitoring/ceph-mixin/tests_dashboards/features/osds-overview.feature
@@ -0,0 +1,15 @@
+Feature: OSD Overview
+
+Scenario: "Test OSD onode Hits Ratio"
+ Given the following series:
+ | metrics | values |
+ | ceph_bluestore_onode_hits{ceph_daemon="osd.0",instance="ceph:9283",job="ceph"} | 5255 |
+ | ceph_bluestore_onode_hits{ceph_daemon="osd.1",instance="ceph:9283",job="ceph"} | 5419 |
+ | ceph_bluestore_onode_hits{ceph_daemon="osd.2",instance="ceph:9283",job="ceph"} | 5242 |
+ | ceph_bluestore_onode_misses{ceph_daemon="osd.0",instance="ceph:9283",job="ceph"} | 202 |
+ | ceph_bluestore_onode_misses{ceph_daemon="osd.1",instance="ceph:9283",job="ceph"} | 247 |
+ | ceph_bluestore_onode_misses{ceph_daemon="osd.2",instance="ceph:9283",job="ceph"} | 234 |
+ Then Grafana panel `OSD onode Hits Ratio` with legend `EMPTY` shows:
+ | metrics | values |
+ | {} | 9.588529429483704E-01 |
+
diff --git a/monitoring/ceph-mixin/tests_dashboards/features/radosgw-detail.feature b/monitoring/ceph-mixin/tests_dashboards/features/radosgw-detail.feature
new file mode 100644
index 000000000..e0016c507
--- /dev/null
+++ b/monitoring/ceph-mixin/tests_dashboards/features/radosgw-detail.feature
@@ -0,0 +1,139 @@
+Feature: RGW Host Detail Dashboard
+
+Scenario: "Test $rgw_servers GET/PUT Latencies - GET"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_get_initial_lat_sum{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 10 50 100 |
+ | ceph_rgw_get_initial_lat_count{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 20 60 80 |
+ | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
+ When interval is `30s`
+ And variable `rgw_servers` is `rgw.foo`
+ Then Grafana panel `$rgw_servers GET/PUT Latencies` with legend `GET {{ceph_daemon}}` shows:
+ | metrics | values |
+ | {ceph_daemon="rgw.foo", instance_id="58892247"} | 1.5 |
+
+Scenario: "Test $rgw_servers GET/PUT Latencies - PUT"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_put_initial_lat_sum{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 15 35 55 |
+ | ceph_rgw_put_initial_lat_count{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 10 30 50 |
+ | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
+ When interval is `30s`
+ And variable `rgw_servers` is `rgw.foo`
+ Then Grafana panel `$rgw_servers GET/PUT Latencies` with legend `PUT {{ceph_daemon}}` shows:
+ | metrics | values |
+ | {ceph_daemon="rgw.foo", instance_id="58892247"} | 1 |
+
+Scenario: "Test Bandwidth by HTTP Operation - GET"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_get_b{instance="127.0.0.1", instance_id="92806566", job="ceph"} | 10 50 100 |
+ | ceph_rgw_metadata{ceph_daemon="rgw.1", hostname="localhost", instance="127.0.0.1", instance_id="92806566", job="ceph"} | 1 1 1 |
+ When interval is `30s`
+ And variable `rgw_servers` is `rgw.1`
+ Then Grafana panel `Bandwidth by HTTP Operation` with legend `GETs {{ceph_daemon}}` shows:
+ | metrics | values |
+ | {ceph_daemon="rgw.1", instance="127.0.0.1", instance_id="92806566", job="ceph"} | 1.5 |
+
+Scenario: "Test Bandwidth by HTTP Operation - PUT"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_put_b{instance="127.0.0.1", instance_id="92806566", job="ceph"} | 5 20 50 |
+ | ceph_rgw_metadata{ceph_daemon="rgw.1", hostname="localhost", instance="127.0.0.1", instance_id="92806566", job="ceph"} | 1 1 1 |
+ When interval is `30s`
+ And variable `rgw_servers` is `rgw.1`
+ Then Grafana panel `Bandwidth by HTTP Operation` with legend `PUTs {{ceph_daemon}}` shows:
+ | metrics | values |
+ | {ceph_daemon="rgw.1", instance="127.0.0.1", instance_id="92806566", job="ceph"} | 7.5E-01 |
+
+Scenario: "Test HTTP Request Breakdown - Requests Failed"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_failed_req{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 5 7 |
+ | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
+ When interval is `30s`
+ And variable `rgw_servers` is `rgw.foo`
+ Then Grafana panel `HTTP Request Breakdown` with legend `Requests Failed {{ceph_daemon}}` shows:
+ | metrics | values |
+ | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1E-01 |
+
+Scenario: "Test HTTP Request Breakdown - GET"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_get{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 100 150 170 |
+ | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
+ When interval is `30s`
+ And variable `rgw_servers` is `rgw.foo`
+ Then Grafana panel `HTTP Request Breakdown` with legend `GETs {{ceph_daemon}}` shows:
+ | metrics | values |
+ | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1.1666666666666667 |
+
+Scenario: "Test HTTP Request Breakdown - PUT"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_put{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 70 90 160 |
+ | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
+ When interval is `30s`
+ And variable `rgw_servers` is `rgw.foo`
+ Then Grafana panel `HTTP Request Breakdown` with legend `PUTs {{ceph_daemon}}` shows:
+ | metrics | values |
+ | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1.5 |
+
+Scenario: "Test HTTP Request Breakdown - Other"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_req{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 175 250 345 |
+ | ceph_rgw_get{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 100 150 170 |
+ | ceph_rgw_put{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 70 90 160 |
+ | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
+ When interval is `30s`
+ And variable `rgw_servers` is `rgw.foo`
+ Then Grafana panel `HTTP Request Breakdown` with legend `Other {{ceph_daemon}}` shows:
+ | metrics | values |
+ | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph"} | .16666666666666652 |
+
+Scenario: "Test Workload Breakdown - Failures"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_failed_req{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 5 7 |
+ | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
+ When interval is `30s`
+ And variable `rgw_servers` is `rgw.foo`
+ Then Grafana panel `Workload Breakdown` with legend `Failures {{ceph_daemon}}` shows:
+ | metrics | values |
+ | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1E-01 |
+
+Scenario: "Test Workload Breakdown - GETs"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_get{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 100 150 170 |
+ | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
+ When interval is `30s`
+ And variable `rgw_servers` is `rgw.foo`
+ Then Grafana panel `Workload Breakdown` with legend `GETs {{ceph_daemon}}` shows:
+ | metrics | values |
+ | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1.1666666666666667 |
+
+Scenario: "Test Workload Breakdown - PUTs"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_put{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 70 90 160 |
+ | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
+ When interval is `30s`
+ And variable `rgw_servers` is `rgw.foo`
+ Then Grafana panel `Workload Breakdown` with legend `PUTs {{ceph_daemon}}` shows:
+ | metrics | values |
+ | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1.5 |
+
+Scenario: "Test Workload Breakdown - Other"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_req{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 175 250 345 |
+ | ceph_rgw_get{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 100 150 170 |
+ | ceph_rgw_put{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 70 90 160 |
+ | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
+ When interval is `30s`
+ And variable `rgw_servers` is `rgw.foo`
+ Then Grafana panel `Workload Breakdown` with legend `Other (DELETE,LIST) {{ceph_daemon}}` shows:
+ | metrics | values |
+ | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph"} | .16666666666666652 |
diff --git a/monitoring/ceph-mixin/tests_dashboards/features/radosgw_overview.feature b/monitoring/ceph-mixin/tests_dashboards/features/radosgw_overview.feature
new file mode 100644
index 000000000..642e43978
--- /dev/null
+++ b/monitoring/ceph-mixin/tests_dashboards/features/radosgw_overview.feature
@@ -0,0 +1,250 @@
+Feature: RGW Overview Dashboard
+
+Scenario: "Test Average GET Latencies"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_get_initial_lat_sum{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 10 50 100 |
+ | ceph_rgw_get_initial_lat_count{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 20 60 80 |
+ | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
+ When interval is `30s`
+ Then Grafana panel `Average GET/PUT Latencies by RGW Instance` with legend `GET {{rgw_host}}` shows:
+ | metrics | values |
+ | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph", rgw_host="foo"} | 1.5 |
+
+Scenario: "Test Average PUT Latencies"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_put_initial_lat_sum{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 15 35 55 |
+ | ceph_rgw_put_initial_lat_count{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 10 30 50 |
+ | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
+ When interval is `30s`
+ Then Grafana panel `Average GET/PUT Latencies by RGW Instance` with legend `PUT {{rgw_host}}` shows:
+ | metrics | values |
+ | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph", rgw_host="foo"} | 1 |
+
+Scenario: "Test Total Requests/sec by RGW Instance"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_req{instance="127.0.0.1", instance_id="92806566", job="ceph"} | 10 50 100 |
+ | ceph_rgw_metadata{ceph_daemon="rgw.1", hostname="localhost", instance="127.0.0.1", instance_id="92806566", job="ceph"} | 1 1 1 |
+ When interval is `30s`
+ Then Grafana panel `Total Requests/sec by RGW Instance` with legend `{{rgw_host}}` shows:
+ | metrics | values |
+ | {rgw_host="1"} | 1.5 |
+
+Scenario: "Test GET Latencies by RGW Instance"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_get_initial_lat_sum{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 10 50 100 |
+ | ceph_rgw_get_initial_lat_count{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 20 60 80 |
+ | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
+ When interval is `30s`
+ Then Grafana panel `GET Latencies by RGW Instance` with legend `{{rgw_host}}` shows:
+ | metrics | values |
+ | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph", rgw_host="foo"} | 1.5 |
+
+Scenario: "Test Bandwidth Consumed by Type- GET"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_get_b{instance="127.0.0.1", instance_id="92806566", job="ceph"} | 10 50 100 |
+ When evaluation time is `1m`
+ And interval is `30s`
+ Then Grafana panel `Bandwidth Consumed by Type` with legend `GETs` shows:
+ | metrics | values |
+ | {} | 1.5 |
+
+Scenario: "Test Bandwidth Consumed by Type- PUT"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_put_b{instance="127.0.0.1", instance_id="92806566", job="ceph"} | 5 20 50 |
+ When evaluation time is `1m`
+ And interval is `30s`
+ Then Grafana panel `Bandwidth Consumed by Type` with legend `PUTs` shows:
+ | metrics | values |
+ | {} | 7.5E-01 |
+
+Scenario: "Test Bandwidth by RGW Instance"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_get_b{instance="127.0.0.1", instance_id="92806566", job="ceph"} | 10 50 100 |
+ | ceph_rgw_put_b{instance="127.0.0.1", instance_id="92806566", job="ceph"} | 5 20 50 |
+ | ceph_rgw_metadata{ceph_daemon="rgw.1", hostname="localhost", instance="127.0.0.1", instance_id="92806566", job="ceph"} | 1 1 1 |
+ When evaluation time is `1m`
+ And interval is `30s`
+ Then Grafana panel `Bandwidth by RGW Instance` with legend `{{rgw_host}}` shows:
+ | metrics | values |
+ | {ceph_daemon="rgw.1", instance_id="92806566", rgw_host="1"} | 2.25 |
+
+Scenario: "Test PUT Latencies by RGW Instance"
+ Given the following series:
+ | metrics | values |
+ | ceph_rgw_put_initial_lat_sum{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 15 35 55 |
+ | ceph_rgw_put_initial_lat_count{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 10 30 50 |
+ | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
+ When evaluation time is `1m`
+ And interval is `30s`
+ Then Grafana panel `PUT Latencies by RGW Instance` with legend `{{rgw_host}}` shows:
+ | metrics | values |
+ | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph", rgw_host="foo"} | 1 |
+
+Scenario: "Test Total backend responses by HTTP code"
+ Given the following series:
+ | metrics | values |
+ | haproxy_backend_http_responses_total{job="haproxy",code="200",instance="ingress.rgw.1",proxy="backend"} | 10 100 |
+ | haproxy_backend_http_responses_total{job="haproxy",code="404",instance="ingress.rgw.1",proxy="backend"} | 20 200 |
+ When variable `ingress_service` is `ingress.rgw.1`
+ When variable `code` is `200`
+ Then Grafana panel `Total responses by HTTP code` with legend `Backend {{ code }}` shows:
+ | metrics | values |
+ | {code="200"} | 1.5 |
+
+Scenario: "Test Total frontend responses by HTTP code"
+ Given the following series:
+ | metrics | values |
+ | haproxy_frontend_http_responses_total{job="haproxy",code="200",instance="ingress.rgw.1",proxy="frontend"} | 10 100 |
+ | haproxy_frontend_http_responses_total{job="haproxy",code="404",instance="ingress.rgw.1",proxy="frontend"} | 20 200 |
+ When variable `ingress_service` is `ingress.rgw.1`
+ When variable `code` is `200`
+ Then Grafana panel `Total responses by HTTP code` with legend `Frontend {{ code }}` shows:
+ | metrics | values |
+ | {code="200"} | 1.5 |
+
+Scenario: "Test Total http frontend requests by instance"
+ Given the following series:
+ | metrics | values |
+ | haproxy_frontend_http_requests_total{job="haproxy",proxy="frontend",instance="ingress.rgw.1"} | 10 100 |
+ | haproxy_frontend_http_requests_total{job="haproxy",proxy="frontend",instance="ingress.rgw.1"} | 20 200 |
+ When variable `ingress_service` is `ingress.rgw.1`
+ Then Grafana panel `Total requests / responses` with legend `Requests` shows:
+ | metrics | values |
+ | {instance="ingress.rgw.1"} | 3 |
+
+Scenario: "Test Total backend response errors by instance"
+ Given the following series:
+ | metrics | values |
+ | haproxy_backend_response_errors_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 10 100 |
+ | haproxy_backend_response_errors_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 20 200 |
+ When variable `ingress_service` is `ingress.rgw.1`
+ Then Grafana panel `Total requests / responses` with legend `Response errors` shows:
+ | metrics | values |
+ | {instance="ingress.rgw.1"} | 3 |
+
+Scenario: "Test Total frontend requests errors by instance"
+ Given the following series:
+ | metrics | values |
+ | haproxy_frontend_request_errors_total{job="haproxy",proxy="frontend",instance="ingress.rgw.1"} | 10 100 |
+ | haproxy_frontend_request_errors_total{job="haproxy",proxy="frontend",instance="ingress.rgw.1"} | 20 200 |
+ When variable `ingress_service` is `ingress.rgw.1`
+ Then Grafana panel `Total requests / responses` with legend `Requests errors` shows:
+ | metrics | values |
+ | {instance="ingress.rgw.1"} | 3 |
+
+Scenario: "Test Total backend redispatch warnings by instance"
+ Given the following series:
+ | metrics | values |
+ | haproxy_backend_redispatch_warnings_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 10 100 |
+ | haproxy_backend_redispatch_warnings_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 20 200 |
+ When variable `ingress_service` is `ingress.rgw.1`
+ Then Grafana panel `Total requests / responses` with legend `Backend redispatch` shows:
+ | metrics | values |
+ | {instance="ingress.rgw.1"} | 3 |
+
+Scenario: "Test Total backend retry warnings by instance"
+ Given the following series:
+ | metrics | values |
+ | haproxy_backend_retry_warnings_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 10 100 |
+ | haproxy_backend_retry_warnings_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 20 200 |
+ When variable `ingress_service` is `ingress.rgw.1`
+ Then Grafana panel `Total requests / responses` with legend `Backend retry` shows:
+ | metrics | values |
+ | {instance="ingress.rgw.1"} | 3 |
+
+Scenario: "Test Total frontend requests denied by instance"
+ Given the following series:
+ | metrics | values |
+ | haproxy_frontend_requests_denied_total{job="haproxy",proxy="frontend",instance="ingress.rgw.1"} | 10 100 |
+ | haproxy_frontend_requests_denied_total{job="haproxy",proxy="frontend",instance="ingress.rgw.1"} | 20 200 |
+ When variable `ingress_service` is `ingress.rgw.1`
+ Then Grafana panel `Total requests / responses` with legend `Request denied` shows:
+ | metrics | values |
+ | {instance="ingress.rgw.1"} | 3 |
+
+Scenario: "Test Total backend current queue by instance"
+ Given the following series:
+ | metrics | values |
+ | haproxy_backend_current_queue{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 10 100 |
+ | haproxy_backend_current_queue{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 20 200 |
+ When variable `ingress_service` is `ingress.rgw.1`
+ Then Grafana panel `Total requests / responses` with legend `Backend Queued` shows:
+ | metrics | values |
+ | {instance="ingress.rgw.1"} | 200 |
+
+Scenario: "Test Total frontend connections by instance"
+ Given the following series:
+ | metrics | values |
+ | haproxy_frontend_connections_total{job="haproxy",proxy="frontend",instance="ingress.rgw.1"} | 10 100 |
+ | haproxy_frontend_connections_total{job="haproxy",proxy="frontend",instance="ingress.rgw.1"} | 20 200 |
+ When variable `ingress_service` is `ingress.rgw.1`
+ Then Grafana panel `Total number of connections` with legend `Front` shows:
+ | metrics | values |
+ | {instance="ingress.rgw.1"} | 3 |
+
+Scenario: "Test Total backend connections attempts by instance"
+ Given the following series:
+ | metrics | values |
+ | haproxy_backend_connection_attempts_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 10 100 |
+ | haproxy_backend_connection_attempts_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 20 200 |
+ When variable `ingress_service` is `ingress.rgw.1`
+ Then Grafana panel `Total number of connections` with legend `Back` shows:
+ | metrics | values |
+ | {instance="ingress.rgw.1"} | 3 |
+
+Scenario: "Test Total backend connections error by instance"
+ Given the following series:
+ | metrics | values |
+ | haproxy_backend_connection_errors_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 10 100 |
+ | haproxy_backend_connection_errors_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 20 200 |
+ When variable `ingress_service` is `ingress.rgw.1`
+ Then Grafana panel `Total number of connections` with legend `Back errors` shows:
+ | metrics | values |
+ | {instance="ingress.rgw.1"} | 3 |
+
+Scenario: "Test Total frontend bytes incoming by instance"
+ Given the following series:
+ | metrics | values |
+ | haproxy_frontend_bytes_in_total{job="haproxy",proxy="frontend",instance="ingress.rgw.1"} | 10 100 |
+ | haproxy_frontend_bytes_in_total{job="haproxy",proxy="frontend",instance="ingress.rgw.1"} | 20 200 |
+ When variable `ingress_service` is `ingress.rgw.1`
+ Then Grafana panel `Current total of incoming / outgoing bytes` with legend `IN Front` shows:
+ | metrics | values |
+ | {instance="ingress.rgw.1"} | 24 |
+
+Scenario: "Test Total frontend bytes outgoing by instance"
+ Given the following series:
+ | metrics | values |
+ | haproxy_frontend_bytes_out_total{job="haproxy",proxy="frontend",instance="ingress.rgw.1"} | 10 100 |
+ | haproxy_frontend_bytes_out_total{job="haproxy",proxy="frontend",instance="ingress.rgw.1"} | 20 200 |
+ When variable `ingress_service` is `ingress.rgw.1`
+ Then Grafana panel `Current total of incoming / outgoing bytes` with legend `OUT Front` shows:
+ | metrics | values |
+ | {instance="ingress.rgw.1"} | 24 |
+
+Scenario: "Test Total backend bytes incoming by instance"
+ Given the following series:
+ | metrics | values |
+ | haproxy_backend_bytes_in_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 10 100 |
+ | haproxy_backend_bytes_in_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 20 200 |
+ When variable `ingress_service` is `ingress.rgw.1`
+ Then Grafana panel `Current total of incoming / outgoing bytes` with legend `IN Back` shows:
+ | metrics | values |
+ | {instance="ingress.rgw.1"} | 24 |
+
+Scenario: "Test Total backend bytes outgoing by instance"
+ Given the following series:
+ | metrics | values |
+ | haproxy_backend_bytes_out_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 10 100 |
+ | haproxy_backend_bytes_out_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 20 200 |
+ When variable `ingress_service` is `ingress.rgw.1`
+ Then Grafana panel `Current total of incoming / outgoing bytes` with legend `OUT Back` shows:
+ | metrics | values |
+ | {instance="ingress.rgw.1"} | 24 |
diff --git a/monitoring/ceph-mixin/tests_dashboards/features/self.feature b/monitoring/ceph-mixin/tests_dashboards/features/self.feature
new file mode 100644
index 000000000..2b44ce0dc
--- /dev/null
+++ b/monitoring/ceph-mixin/tests_dashboards/features/self.feature
@@ -0,0 +1,68 @@
+Feature: Test tester
+
+Scenario: "Simple query works"
+ Given the following series:
+ | metrics | values |
+ | node_network_receive_bytes{instance="127.0.0.1", device="eth1"} | 10 100 |
+ | node_network_receive_bytes{instance="127.0.0.1", device="eth2"} | 10 100 |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 10 100 |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 10 100 |
+ | node_network_transmit_bytes{instance="192.168.100.2", device="bond0"} | 20 200 |
+ | node_network_transmit_bytes{instance="192.168.100.1", device="bond0"} | 20 200 |
+ | bonding_slaves{instance="127.0.0.1", master="bond0"} | 2 |
+ Then query `node_network_transmit_bytes{instance="127.0.0.1"} > 0` produces:
+ | metrics | values |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 100 |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 100 |
+
+Scenario: "Query with evaluation time"
+ Given the following series:
+ | metrics | values |
+ | node_network_receive_bytes{instance="127.0.0.1", device="eth1"} | 10 100 |
+ | node_network_receive_bytes{instance="127.0.0.1", device="eth2"} | 10 100 |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 10 100 |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 10 100 |
+ | node_network_transmit_bytes{instance="192.168.100.2", device="bond0"} | 20 200 |
+ | node_network_transmit_bytes{instance="192.168.100.1", device="bond0"} | 20 200 |
+ | bonding_slaves{instance="127.0.0.1", master="bond0"} | 2 |
+ When evaluation time is `0m`
+ Then query `node_network_transmit_bytes{instance="127.0.0.1"} > 0` produces:
+ | metrics | values |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 10 |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 10 |
+
+Scenario: "Query with evaluation time and variable value"
+ Given the following series:
+ | metrics | values |
+ | node_network_receive_bytes{instance="127.0.0.1", device="eth1"} | 10 100 |
+ | node_network_receive_bytes{instance="127.0.0.1", device="eth2"} | 10 100 |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 10 100 |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 10 100 |
+ | node_network_transmit_bytes{instance="192.168.100.2", device="bond0"} | 20 200 |
+ | node_network_transmit_bytes{instance="192.168.100.1", device="bond0"} | 20 200 |
+ | bonding_slaves{instance="127.0.0.1", master="bond0"} | 2 |
+ When evaluation time is `0m`
+ And variable `osd_hosts` is `127.0.0.1`
+ Then query `node_network_transmit_bytes{instance="$osd_hosts"} > 0` produces:
+ | metrics | values |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 10 |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 10 |
+
+Scenario: "Query with interval time"
+ Given the following series:
+ | metrics | values |
+ | node_network_receive_bytes{instance="127.0.0.1", device="eth1"} | 10 100 200 |
+ | node_network_receive_bytes{instance="127.0.0.1", device="eth2"} | 10 100 200 |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 10 100 200 |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 10 100 200 |
+ | node_network_transmit_bytes{instance="192.168.100.2", device="bond0"} | 20 200 300 |
+ | node_network_transmit_bytes{instance="192.168.100.1", device="bond0"} | 20 200 300 |
+ | bonding_slaves{instance="127.0.0.1", master="bond0"} | 2 |
+ When evaluation time is `2h`
+ And evaluation interval is `1h`
+ And interval is `1h`
+ And variable `osd_hosts` is `127.0.0.1`
+ Then query `node_network_transmit_bytes{instance="$osd_hosts"} > 0` produces:
+ | metrics | values |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 200 |
+ | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 200 | \ No newline at end of file
diff --git a/monitoring/ceph-mixin/tests_dashboards/features/steps/__init__.py b/monitoring/ceph-mixin/tests_dashboards/features/steps/__init__.py
new file mode 100644
index 000000000..0b90f46f2
--- /dev/null
+++ b/monitoring/ceph-mixin/tests_dashboards/features/steps/__init__.py
@@ -0,0 +1 @@
+# This file and steps files is needed even if its empty because of 'behave' :(
diff --git a/monitoring/ceph-mixin/tests_dashboards/requirements.txt b/monitoring/ceph-mixin/tests_dashboards/requirements.txt
new file mode 100644
index 000000000..8ad130e5b
--- /dev/null
+++ b/monitoring/ceph-mixin/tests_dashboards/requirements.txt
@@ -0,0 +1,12 @@
+attrs==21.2.0
+behave==1.2.6
+py==1.10.0
+pyparsing==2.4.7
+PyYAML==6.0
+types-PyYAML==6.0.0
+typing-extensions==3.10.0.2
+termcolor==1.1.0
+types-termcolor==1.1.2
+dataclasses==0.6
+types-dataclasses==0.6.1
+prettytable==2.4.0
diff --git a/monitoring/ceph-mixin/tests_dashboards/util.py b/monitoring/ceph-mixin/tests_dashboards/util.py
new file mode 100644
index 000000000..1fce6559d
--- /dev/null
+++ b/monitoring/ceph-mixin/tests_dashboards/util.py
@@ -0,0 +1,109 @@
+import json
+import re
+from pathlib import Path
+from typing import Any, Dict, Tuple, Union
+
+from termcolor import cprint
+
+UNITS = ['ms', 's', 'm', 'h', 'd', 'w', 'y']
+
+
+def resolve_time_and_unit(time: str) -> Union[Tuple[int, str], Tuple[None, None]]:
+ """
+ Divide time with its unit and return a tuple like (10, 'm')
+ Return None if its and invalid prometheus time
+ Valid units are inside UNITS.
+ """
+ if time[-1] in UNITS:
+ return int(time[:-1]), time[-1]
+ if time[-2:] in UNITS:
+ return int(time[:-2]), time[-2:]
+ return None, None
+
+
+def get_dashboards_data() -> Dict[str, Any]:
+ data: Dict[str, Any] = {'queries': {}, 'variables': {}, 'stats': {}}
+ for file in Path(__file__).parent.parent \
+ .joinpath('dashboards_out').glob('*.json'):
+ with open(file, 'r') as f:
+ dashboard_data = json.load(f)
+ data['stats'][str(file)] = {'total': 0, 'tested': 0}
+ add_dashboard_queries(data, dashboard_data, str(file))
+ add_dashboard_variables(data, dashboard_data)
+ add_default_dashboards_variables(data)
+ return data
+
+
+def add_dashboard_queries(data: Dict[str, Any], dashboard_data: Dict[str, Any], path: str) -> None:
+ """
+ Grafana panels can have more than one target/query, in order to identify each
+ query in the panel we append the "legendFormat" of the target to the panel name.
+ format: panel_name-legendFormat
+ """
+ if 'panels' not in dashboard_data:
+ return
+ error = 0
+ for panel in dashboard_data['panels']:
+ if (
+ 'title' in panel
+ and 'targets' in panel
+ and len(panel['targets']) > 0
+ and 'expr' in panel['targets'][0]
+ ):
+ for target in panel['targets']:
+ title = panel['title']
+ legend_format = target['legendFormat'] if 'legendFormat' in target else ""
+ query_id = f'{title}-{legend_format}'
+ if query_id in data['queries']:
+ # NOTE: If two or more panels have the same name and legend it
+ # might suggest a refactoring is needed or add something else
+ # to identify each query.
+ conflict_file = Path(data['queries'][query_id]['path']).name
+ file = Path(path).name
+ cprint((f'ERROR: Query in panel "{title}" with legend "{legend_format}"'
+ f' already exists. Conflict "{conflict_file}" '
+ f'with: "{file}"'), 'red')
+ error = 1
+ data['queries'][query_id] = {'query': target['expr'], 'path': path}
+ data['stats'][path]['total'] += 1
+ if error:
+ raise ValueError('Missing legend_format in queries, please add a proper value.')
+
+
+def add_dashboard_variables(data: Dict[str, Any], dashboard_data: Dict[str, Any]) -> None:
+ if 'templating' not in dashboard_data or 'list' not in dashboard_data['templating']:
+ return
+ for variable in dashboard_data['templating']['list']:
+ if 'name' in variable:
+ data['variables'][variable['name']] = 'UNSET VARIABLE'
+
+def add_default_dashboards_variables(data: Dict[str, Any]) -> None:
+ data['variables']['job'] = 'ceph'
+ data['variables']['job_haproxy'] = 'haproxy'
+ data['variables']['__rate_interval'] = '1m'
+
+def replace_grafana_expr_variables(expr: str, variable: str, value: Any) -> str:
+ """ Replace grafana variables in expression with a value
+
+ It should match the whole word, 'osd' musn't match with the 'osd' prefix in 'osd_hosts'
+ >>> replace_grafana_expr_variables('metric{name~="$osd_hosts|$other|$osd"}', \
+ 'osd', 'replacement')
+ 'metric{name~="$osd_hosts|$other|replacement"}'
+
+ >>> replace_grafana_expr_variables('metric{name~="$osd_hosts|$other|$osd"}', \
+ 'other', 'replacement')
+ 'metric{name~="$osd_hosts|replacement|$osd"}'
+
+ It replaces words with dollar prefix
+ >>> replace_grafana_expr_variables('metric{name~="no_dollar|$other|$osd"}', \
+ 'no_dollar', 'replacement')
+ 'metric{name~="no_dollar|$other|$osd"}'
+
+ It shouldn't replace the next char after the variable (positive lookahead test).
+ >>> replace_grafana_expr_variables('metric{name~="$osd"}', \
+ 'osd', 'replacement')
+ 'metric{name~="replacement"}'
+ """
+ regex = fr'\${variable}(?=\W)'
+ new_expr = re.sub(regex, fr'{value}', expr)
+ return new_expr