OCI compute monitoring (metrics and alarm)

---
- name: Collect metrics
  oracle.oci.oci_monitoring_metric_actions:
    compartment_id: "your-compartment-ocid"
    action: list
    namespace: oci_computeagent
    dimension_filters: { "resourceID": "your-compute-instance-ocid"}
  register: result

- name: Set list of indexes (number of metrics)
  ansible.builtin.set_fact:
    l_index: "{{ range(result.metric | length) }}"

- name: Show metrics
  ansible.builtin.debug:
    msg:
      - "{{ (result | dict2items)[1][\"value\"][index][\"name\"] }}"
  loop: "{{ l_index }}"  # loop through list indexes
  loop_control:
    index_var: index
...

# Role tests main.yml is like:
---
- name: Test role
  connection: local
  hosts: localhost
  roles:
    - role: ../../oci-metrics
...

# Run role: ansible-playbook -i inventory test.yml

# Expect ten metrics in result:

ok: [localhost] => (item=0) => "CpuUtilization"
ok: [localhost] => (item=1) => "DiskBytesRead"
ok: [localhost] => (item=2) => "DiskBytesWritten"
ok: [localhost] => (item=3) => "DiskIopsRead"
ok: [localhost] => (item=4) => "DiskIopsWritten"
ok: [localhost] => (item=5) => "LoadAverage"
ok: [localhost] => (item=6) => "MemoryAllocationStalls"
ok: [localhost] => (item=7) => "MemoryUtilization"
ok: [localhost] => (item=8) => "NetworksBytesIn"
ok: [localhost] => (item=9) =>  "NetworksBytesOut"

#!/bin/python3

import socket
import argparse
import oci
import psutil
from datetime import datetime

# arguments are location (on-prem or OCI region) and partition (ex, /, /boot)
parser = argparse.ArgumentParser(description=f"OCI metric disk_usage for {socket.gethostname()}")
parser.add_argument("--location", help="Location", required=True)
parser.add_argument("--partition", help="Partition", required=True)
args = parser.parse_args()
location = args.location
partition = args.partition

comp_ocid = "...your-compartment-ocid..."
hostname = socket.gethostname()
metric_name = "disk_usage"
metric_namespace = "your-team"  # ex. custom metrics for your team

# Use default config file ~/.oci/config
config = oci.config.from_file()

# create monitoring service client
monitoring_client = \
    oci.monitoring.MonitoringClient(config, service_endpoint="https://telemetry-ingestion..oraclecloud.com")


def get_disk_usage():
    """ On-prem host root disk usage """
    # global disk_usage_percent
    df_cmd = psutil.disk_usage(f"{partition}")
    disk_usage_percent = df_cmd.percent
    return disk_usage_percent

# Metric value (disk usage) for a specific timestamp
datapoints_info = \
    [oci.monitoring.models.Datapoint(timestamp=f"{datetime.utcnow().isoformat('T')}Z", value=get_disk_usage())]

# A metric object and its details
metric_data_details = oci.monitoring.models.MetricDataDetails(compartment_id=comp_ocid, datapoints=datapoints_info,
                                                              dimensions={"location": f"{location}",
                                                                          "hostname": f"{hostname}",
                                                                          "partition": f"{partition}"},
                                                              name=f"{metric_name}",
                                                              namespace=f"{metric_namespace}")

# Metric object to be posted to Monitoring service
post_metric_data_details = oci.monitoring.models.PostMetricDataDetails(metric_data=[metric_data_details])

# Publishes metric data to Monitoring service.
post_metric_data_response = monitoring_client.post_metric_data(post_metric_data_details)

15 * * * * disk-usage.py --location IAD --partition /
15 * * * * disk-usage.py --location IAD --partition /boot

#
# the only supported return value for oci metrics is number
# workaround for plugins that return string
#
def check_service_state(service_name):
    try:
        subprocess.check_output(['systemctl', 'is-active', service_name])
        return 0
    except subprocess.CalledProcessError:
        return 1

15 * * * * service-state.py --location IAD --service mysqld

#!/bin/python3
# Returns aggregated data from query.
from datetime import datetime
import oci
import argparse

parser = argparse.ArgumentParser(description=f"Disk usage metrics")
parser.add_argument("--partition", help="Partition", required=True)
parser.add_argument("--start", help="Start time for metric yyyy-mm-dd", required=True)
parser.add_argument("--end", help="End time for metric yyyy-mm-dd", required=True)
args = parser.parse_args()
partition = args.partition
start = args.start
end = args.end

# Use default config file ~/.oci/config
config = oci.config.from_file()

# Initialize service client with default config file
monitoring_client = oci.monitoring.MonitoringClient(config)

comp_id = "ocid1.compartment.oc1..your-id"
namespace = "your-namespace"
query = f"disk_usage[1h]{{partition = \"{partition}\"}}.mean()"

summarize_metrics_data_response = monitoring_client.summarize_metrics_data(
    compartment_id=f"{comp_id}",
    summarize_metrics_data_details=oci.monitoring.models.SummarizeMetricsDataDetails(
        namespace=f"{namespace}",
        query=f"{query}",
        start_time=f"{start}T00:00:00+00",
        end_time=f"{end}T00:00:00+00"))

# Get the data from response
print(summarize_metrics_data_response.data)

$ python3 summarize-disk-usage.py --partition / --start 2023-06-19 --end 2023-06-21

[{
  "aggregated_datapoints": [
    {
      "timestamp": "2023-06-19T00:00:00+00:00",
      "value": 17.4
    },
    
    -- shortened --
    {
      "timestamp": "2023-06-21T00:00:00+00:00",
      "value": 17.0
    }
  ],
  "compartment_id": "ocid1.compartment.oc1...a",
  "dimensions": {
    "hostname": "myhostname.domain.com",
    "partition": "/"
  },
  "metadata": {},
  "name": "disk_usage",
  "namespace": "your-namespace",
  "resolution": null,
  "resource_group": null
}]

---
- name: Get alarm mysqld-down
  oracle.oci.oci_monitoring_alarm_facts:
    alarm_id: "your-alarm-ocid"
...

# expected result is like:

    "alarms": [
        {
            "body": "Mysqld service is not online. ",
            "display_name": "mysql-down",
            "is_enabled": true,
            "lifecycle_state": "ACTIVE",
            "namespace": "your-custom-team-namespace",
            "query": "service_state[1h]{service = \"mysqld\"}.mean() not in (0, 0)",
            "severity": "CRITICAL",
            "suppression": null,
        }