From f4ad39dc7212317b60b8dbcb7c9119ff8b9eed90 Mon Sep 17 00:00:00 2001
From: technowhizz <7688823+technowhizz@users.noreply.github.com>
Date: Thu, 16 May 2024 18:31:44 +0100
Subject: [PATCH 1/3] Update smart metrics to include rated DWPD

---
 etc/kayobe/ansible/get-nvme-drives.yml | 97 ++++++++++++++++++++++++++
 etc/kayobe/ansible/scripts/nvmemon.sh  | 73 +++++++++++++------
 etc/kayobe/ansible/smartmon-tools.yml  | 19 ++++-
 etc/kayobe/stackhpc-monitoring.yml     |  3 +
 4 files changed, 171 insertions(+), 21 deletions(-)
 create mode 100644 etc/kayobe/ansible/get-nvme-drives.yml

diff --git a/etc/kayobe/ansible/get-nvme-drives.yml b/etc/kayobe/ansible/get-nvme-drives.yml
new file mode 100644
index 000000000..7a1bbef12
--- /dev/null
+++ b/etc/kayobe/ansible/get-nvme-drives.yml
@@ -0,0 +1,97 @@
+---
+- name: Gather unique NVMe disk models and generate a prepopulated variable template
+  hosts: overcloud
+  gather_facts: no
+  tasks:
+    - name: Get NVMe device information
+      command: "nvme list -o json"
+      register: nvme_list
+      changed_when: false
+      become: true
+
+    - name: Parse NVMe device model names
+      set_fact:
+        nvme_models: "{{ nvme_models | default([]) + [item.ModelNumber] }}"
+      loop: "{{ nvme_list.stdout | from_json | json_query('Devices[].{ModelNumber: ModelNumber}') }}"
+      changed_when: false
+
+    - name: Set gathered NVMe models as host facts
+      set_fact:
+        unique_nvme_models: "{{ nvme_models | unique }}"
+      run_once: true
+
+- name: Update stackhpc-monitoring.yml with DWPD ratings
+  hosts: localhost
+  gather_facts: no
+  tasks:
+    - name: Aggregate unique NVMe models from all hosts
+      set_fact:
+        all_nvme_models: "{{ all_nvme_models | default([]) | union(hostvars[item].unique_nvme_models | default([])) }}"
+      with_items: "{{ groups['overcloud'] }}"
+      run_once: true
+
+    - name: Ensure unique NVMe models
+      set_fact:
+        all_nvme_models: "{{ all_nvme_models | unique }}"
+      run_once: true
+
+    - name: Create a dictionary for quick lookup of DWPD ratings
+      set_fact:
+        dwpd_lookup: "{{ stackhpc_dwpd_ratings | items2dict(key_name='model_name', value_name='rated_dwpd') }}"
+      when: stackhpc_dwpd_ratings is defined and stackhpc_dwpd_ratings | length > 0
+      run_once: true
+
+    - name: Generate new DWPD ratings section
+      set_fact:
+        new_dwpd_section: |
+          stackhpc_dwpd_ratings:
+          {% for model in all_nvme_models %}
+            - model_name: "{{ model }}"
+              rated_dwpd: "{{ dwpd_lookup[model] if model in dwpd_lookup else '#FILL ME IN' }}"
+          {% endfor %}
+      run_once: true
+
+    - name: Read the current stackhpc-monitoring.yml file
+      slurp:
+        src: "{{ playbook_dir }}/../stackhpc-monitoring.yml"
+      register: monitoring_file_content
+
+    - name: Ensure markers exist in the file
+      set_fact:
+        markers_exist: "{{ ('# BEGIN DWPD Ratings' in old_content) and ('# END DWPD Ratings' in old_content) }}"
+      vars:
+        old_content: "{{ monitoring_file_content.content | b64decode }}"
+      run_once: true
+
+    - name: Fail if markers do not exist
+      fail:
+        msg: "The stackhpc-monitoring.yml file does not contain the required markers: # BEGIN DWPD Ratings and # END DWPD Ratings"
+      when: not markers_exist
+      run_once: true
+
+    - name: Update the content with new DWPD ratings section
+      set_fact:
+        updated_monitoring_content: |
+          {% set old_content = monitoring_file_content.content | b64decode %}
+          {% set before_section = old_content.split('# BEGIN DWPD Ratings')[0] %}
+          {% set after_section = old_content.split('# END DWPD Ratings')[1] %}
+          {{ before_section }}# BEGIN DWPD Ratings
+          {{ new_dwpd_section }}
+          # END DWPD Ratings{{ after_section }}
+      when: markers_exist
+      run_once: true
+
+    - name: Write the updated content back to stackhpc-monitoring.yml
+      copy:
+        content: "{{ updated_monitoring_content }}"
+        dest: "{{ playbook_dir }}/../stackhpc-monitoring.yml"
+        backup: yes
+      when: markers_exist
+      run_once: true
+
+    - name: Print new DWPD ratings section
+      debug:
+        msg:
+          - "{{ new_dwpd_section }}"
+          - "PLEASE UPDATE stackhpc-monitoring.yml IF NEEDED AND REMEMBER TO COMMIT THE FILE TO GIT"
+      run_once: true
diff --git a/etc/kayobe/ansible/scripts/nvmemon.sh b/etc/kayobe/ansible/scripts/nvmemon.sh
index 761e81b7d..9b4696614 100644
--- a/etc/kayobe/ansible/scripts/nvmemon.sh
+++ b/etc/kayobe/ansible/scripts/nvmemon.sh
@@ -21,6 +21,28 @@ if ! command -v nvme >/dev/null 2>&1; then
   exit 1
 fi
 
+# Set path to the DWPD ratings file
+dwpd_file="/opt/kayobe/etc/monitoring/dwpd_ratings.yml"
+
+# Function to load rated DWPD values from the YML file
+load_dwpd_ratings() {
+  declare -gA rated_dwpd
+  if [[ -f "$dwpd_file" ]]; then
+    while IFS= read -r line; do
+      key="$(echo "$line" | jq -r '.model_name')"
+      value="$(echo "$line" | jq -r '.rated_dwpd')"
+      # Strip trailing spaces
+      key="$(echo "$key" | sed 's/[[:space:]]*$//')"
+      value="$(echo "$value" | sed 's/[[:space:]]*$//')"
+      rated_dwpd["$key"]="$value"
+    done < <(jq -c '.[]' "$dwpd_file")
+  else
+    echo "Warning: DWPD ratings file not found at $dwpd_file. Defaulting to 1 DWPD."
+  fi
+}
+
+load_dwpd_ratings
+
 output_format_awk="$(
   cat <<'OUTPUTAWK'
 BEGIN { v = "" }
@@ -44,58 +66,69 @@ format_output() {
 nvme_version="$(nvme version | awk '$1 == "nvme" {print $3}')"
 echo "nvmecli{version=\"${nvme_version}\"} 1" | format_output
 
-# Get devices (DevicePath and PhysicalSize)
-device_info="$(nvme list -o json | jq -c '.Devices[] | {DevicePath: .DevicePath, PhysicalSize: .PhysicalSize}')"
+# Get devices (DevicePath, PhysicalSize and ModelNumber)
+device_info="$(nvme list -o json | jq -c '.Devices[] | {DevicePath, PhysicalSize, ModelNumber}')"
+
+# Convert device_info to an array
+device_info_array=()
+while IFS= read -r line; do
+  device_info_array+=("$line")
+done <<< "$device_info"
 
 # Loop through the NVMe devices
-echo "$device_info" | while read -r device_data; do
-  device=$(echo "$device_data" | jq -r '.DevicePath')
+for device_data in "${device_info_array[@]}"; do
+  device="$(echo "$device_data" | jq -r '.DevicePath')"
   json_check="$(nvme smart-log -o json "${device}")"
   disk="${device##*/}"
+  model_name="$(echo "$device_data" | jq -r '.ModelNumber')"
 
-  physical_size=$(echo "$device_data" | jq -r '.PhysicalSize')
-  echo "physical_size_bytes{device=\"${disk}\"} ${physical_size}"
+  physical_size="$(echo "$device_data" | jq -r '.PhysicalSize')"
+  echo "physical_size_bytes{device=\"${disk}\",model=\"${model_name}\"} ${physical_size}"
 
   # The temperature value in JSON is in Kelvin, we want Celsius
   value_temperature="$(echo "$json_check" | jq '.temperature - 273')"
-  echo "temperature_celsius{device=\"${disk}\"} ${value_temperature}"
+  echo "temperature_celsius{device=\"${disk}\",model=\"${model_name}\"} ${value_temperature}"
+
+  # Get the rated DWPD from the dictionary or default to 1 if not found
+  value_rated_dwpd="${rated_dwpd[$model_name]:-1}"
+  echo "rated_dwpd{device=\"${disk}\",model=\"${model_name}\"} ${value_rated_dwpd}"
 
   value_available_spare="$(echo "$json_check" | jq '.avail_spare / 100')"
-  echo "available_spare_ratio{device=\"${disk}\"} ${value_available_spare}"
+  echo "available_spare_ratio{device=\"${disk}\",model=\"${model_name}\"} ${value_available_spare}"
 
   value_available_spare_threshold="$(echo "$json_check" | jq '.spare_thresh / 100')"
-  echo "available_spare_threshold_ratio{device=\"${disk}\"} ${value_available_spare_threshold}"
+  echo "available_spare_threshold_ratio{device=\"${disk}\",model=\"${model_name}\"} ${value_available_spare_threshold}"
 
   value_percentage_used="$(echo "$json_check" | jq '.percent_used / 100')"
-  echo "percentage_used_ratio{device=\"${disk}\"} ${value_percentage_used}"
+  echo "percentage_used_ratio{device=\"${disk}\",model=\"${model_name}\"} ${value_percentage_used}"
 
   value_critical_warning="$(echo "$json_check" | jq '.critical_warning')"
-  echo "critical_warning_total{device=\"${disk}\"} ${value_critical_warning}"
+  echo "critical_warning_total{device=\"${disk}\",model=\"${model_name}\"} ${value_critical_warning}"
 
   value_media_errors="$(echo "$json_check" | jq '.media_errors')"
-  echo "media_errors_total{device=\"${disk}\"} ${value_media_errors}"
+  echo "media_errors_total{device=\"${disk}\",model=\"${model_name}\"} ${value_media_errors}"
 
   value_num_err_log_entries="$(echo "$json_check" | jq '.num_err_log_entries')"
-  echo "num_err_log_entries_total{device=\"${disk}\"} ${value_num_err_log_entries}"
+  echo "num_err_log_entries_total{device=\"${disk}\",model=\"${model_name}\"} ${value_num_err_log_entries}"
 
   value_power_cycles="$(echo "$json_check" | jq '.power_cycles')"
-  echo "power_cycles_total{device=\"${disk}\"} ${value_power_cycles}"
+  echo "power_cycles_total{device=\"${disk}\",model=\"${model_name}\"} ${value_power_cycles}"
 
   value_power_on_hours="$(echo "$json_check" | jq '.power_on_hours')"
-  echo "power_on_hours_total{device=\"${disk}\"} ${value_power_on_hours}"
+  echo "power_on_hours_total{device=\"${disk}\",model=\"${model_name}\"} ${value_power_on_hours}"
 
   value_controller_busy_time="$(echo "$json_check" | jq '.controller_busy_time')"
-  echo "controller_busy_time_seconds{device=\"${disk}\"} ${value_controller_busy_time}"
+  echo "controller_busy_time_seconds{device=\"${disk}\",model=\"${model_name}\"} ${value_controller_busy_time}"
 
   value_data_units_written="$(echo "$json_check" | jq '.data_units_written')"
-  echo "data_units_written_total{device=\"${disk}\"} ${value_data_units_written}"
+  echo "data_units_written_total{device=\"${disk}\",model=\"${model_name}\"} ${value_data_units_written}"
 
   value_data_units_read="$(echo "$json_check" | jq '.data_units_read')"
-  echo "data_units_read_total{device=\"${disk}\"} ${value_data_units_read}"
+  echo "data_units_read_total{device=\"${disk}\",model=\"${model_name}\"} ${value_data_units_read}"
 
   value_host_read_commands="$(echo "$json_check" | jq '.host_read_commands')"
-  echo "host_read_commands_total{device=\"${disk}\"} ${value_host_read_commands}"
+  echo "host_read_commands_total{device=\"${disk}\",model=\"${model_name}\"} ${value_host_read_commands}"
 
   value_host_write_commands="$(echo "$json_check" | jq '.host_write_commands')"
-  echo "host_write_commands_total{device=\"${disk}\"} ${value_host_write_commands}"
+  echo "host_write_commands_total{device=\"${disk}\",model=\"${model_name}\"} ${value_host_write_commands}"
 done | format_output
diff --git a/etc/kayobe/ansible/smartmon-tools.yml b/etc/kayobe/ansible/smartmon-tools.yml
index b4a064b63..1fac2e575 100644
--- a/etc/kayobe/ansible/smartmon-tools.yml
+++ b/etc/kayobe/ansible/smartmon-tools.yml
@@ -1,6 +1,5 @@
 ---
 - hosts: overcloud
-
   tasks:
     - name: Ensure smartmontools, jq, nvme-cli and cron/cronie are installed
       package:
@@ -49,3 +48,21 @@
         - smartmon
         - nvmemon
       become: yes
+
+    - name: Ensure the DWPD Ratings directory exists
+      file:
+        path: /opt/kayobe/etc/monitoring
+        state: directory
+        mode: '0755'
+      when: stackhpc_dwpd_ratings is defined
+      become: true
+
+    - name: Create a DWPD ratings file
+      copy:
+        content: |
+          {% for drive in stackhpc_dwpd_ratings %}
+          {{ drive.model_name }}: {{ drive.rated_dwpd }}
+          {% endfor %}
+        dest: /opt/kayobe/etc/monitoring/dwpd_ratings.yml
+      when: stackhpc_dwpd_ratings is defined
+      become: true
diff --git a/etc/kayobe/stackhpc-monitoring.yml b/etc/kayobe/stackhpc-monitoring.yml
index e8e0bb91f..a4c6fafd7 100644
--- a/etc/kayobe/stackhpc-monitoring.yml
+++ b/etc/kayobe/stackhpc-monitoring.yml
@@ -23,3 +23,6 @@ stackhpc_enable_os_capacity: true
 # Whether TLS certificate verification is enabled for the OpenStack Capacity
 # exporter during Keystone authentication.
 stackhpc_os_capacity_openstack_verify: true
+
+# BEGIN DWPD Ratings
+# END DWPD Ratings

From 30de21586e2c7cedff1d096dd6c63210ae424d42 Mon Sep 17 00:00:00 2001
From: technowhizz <7688823+technowhizz@users.noreply.github.com>
Date: Thu, 16 May 2024 18:35:55 +0100
Subject: [PATCH 2/3] Add release note

---
 releasenotes/notes/rated-dwpd-40526e85e24ef7ea.yaml | 8 ++++++++
 1 file changed, 8 insertions(+)
 create mode 100644 releasenotes/notes/rated-dwpd-40526e85e24ef7ea.yaml

diff --git a/releasenotes/notes/rated-dwpd-40526e85e24ef7ea.yaml b/releasenotes/notes/rated-dwpd-40526e85e24ef7ea.yaml
new file mode 100644
index 000000000..5b8eb5065
--- /dev/null
+++ b/releasenotes/notes/rated-dwpd-40526e85e24ef7ea.yaml
@@ -0,0 +1,8 @@
+---
+features:
+  - |
+    Add support of the operator supplying the rated DWPD value for NVMe drives.
+    There is a playbook ``get-nvme-drives.yml`` that will populate a new
+    section in the ``stackhpc-monitoring.yml`` file with drive model names for
+    NVMes in the cloud. The operator can then fill in the rated DWPD values for
+    each drive.

From 16cb22395b3a82b3d0da063e92f99a8cfc395e71 Mon Sep 17 00:00:00 2001
From: technowhizz <7688823+technowhizz@users.noreply.github.com>
Date: Thu, 16 May 2024 18:39:23 +0100
Subject: [PATCH 3/3] Update alert to use new metric

---
 etc/kayobe/kolla/config/prometheus/smart.rules | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/etc/kayobe/kolla/config/prometheus/smart.rules b/etc/kayobe/kolla/config/prometheus/smart.rules
index 853d9268a..cd7dbb3d6 100644
--- a/etc/kayobe/kolla/config/prometheus/smart.rules
+++ b/etc/kayobe/kolla/config/prometheus/smart.rules
@@ -14,19 +14,19 @@ groups:
       description: "{{ $labels.instance }} is reporting unhealthy for the disk at {{ $labels.disk }}. Disk serial number is: {{ $labels.serial_number }}"
 
   - alert: DWPDTooHigh
-    expr: (delta(nvme_data_units_written_total[30d])*512000 / nvme_physical_size_bytes) / 30 > 1
+    expr: (delta(nvme_data_units_written_total[30d])*512000 / nvme_physical_size_bytes) / 30 > nvme_rated_dwpd
     labels:
       severity: alert
     annotations:
       summary: "High 30-Day Average DWPD for {{ $labels.instance }}"
-      description: "The 30-Day average for Disk Writes Per Day for disk {{ $labels.device }} on {{ $labels.instance }} exceeds 1 DWPD"
+      description: "The 30-Day average for Disk Writes Per Day for disk {{ $labels.device }} on {{ $labels.instance }} exceeds the rated DWPD"
 
   - alert: DWPDTooHighWarning
-    expr: (delta(nvme_data_units_written_total[7d])*512000 / nvme_physical_size_bytes) / 7 > 1
+    expr: (delta(nvme_data_units_written_total[7d])*512000 / nvme_physical_size_bytes) / 7 > nvme_rated_dwpd
     labels:
       severity: warning
     annotations:
       summary: "High 7-Day Average DWPD for {{ $labels.instance }}"
-      description: "The 7-day average for Disk Writes Per Day for disk {{ $labels.device }} on {{ $labels.instance }} exceeds 1 DWPD"
+      description: "The 7-day average for Disk Writes Per Day for disk {{ $labels.device }} on {{ $labels.instance }} exceeds the rated DWPD"
 
 {% endraw %}