Merge branch 'dell:pub/k8s_telemetry' into pub/k8s_telemetry

Author: Milisha-Gupta

build_image_aarch64/roles/image_creation/tasks/build_compute_image.yml

@@ -49,8 +49,6 @@
     ansible-playbook {{ openchami_clone_path }}/dell/podman-quadlets/image.yaml \
     -i {{ aarch64_inventory_file }} -v \
       --extra-vars '@{{ openchami_dir }}/{{ item.key }}_compute_images.yaml' \
-      -e "minio_s3_username={{ minio_s3_username }}" \
-      -e "minio_s3_password={{ minio_s3_password }}" \
       --tags compute_image -v | \
       /usr/bin/tee '{{ openchami_log_dir }}/{{ item.key }}_compute_image.log'
   async: 3600   # Set async timeout (e.g., 1 hour)
@@ -68,14 +66,15 @@
         jid: "{{ item.ansible_job_id }}"
       register: job_result
       until: job_result.finished
+      no_log: true
       retries: "{{ job_retry }}"
       delay: "{{ job_delay }}"
       loop: "{{ compute_image_build_job.results }}"
       loop_control:
         label: "{{ item.item.key }}"
 
   rescue:
-    - name: Fail explicitly if job failed
+    - name: Failed to build the aarch64 compute image
       ansible.builtin.fail:
         msg: "{{ compute_image_failure_msg }}"
 

build_image_aarch64/roles/image_creation/templates/compute_images_templates.j2

@@ -9,6 +9,8 @@ group_name: "{{ item.key }}"
 rhel_base_compute_mounts: {{ ochami_compute_mounts | join(' ') }}
 image_build_name: {{ ochami_aarch64_image  | join (' ') }}
 rhel_base_compute_command_options: {{ ochami_base_command | join (' ') }}
+minio_s3_username: "{{ minio_s3_username }}"
+minio_s3_password: "{{ minio_s3_password }}"
 
 rhel_repos:
 {% set rhel_repo = rhel_aarch64_repos %}

build_image_aarch64/roles/image_creation/vars/main.yml

@@ -44,7 +44,9 @@ openchami_base_image_vars_template: "{{ role_path }}/templates/base_image_templa
 openchami_aarch64_base_image_vars_path: "/opt/omnia/openchami/aarch64_base_image_template.yaml"
 aarch64_inventory_file: "/tmp/temp_ochami_inventory.ini"
 base_image_failure_msg: "Base aarch64 image build job failed or timed out. Check logs at path {{ openchami_aarch64_base_image_log_path }} for details."
-compute_image_failure_msg: "Compute aarch64 image build job did not completed successfully."
+compute_image_failure_msg:
+  "aarch64 compute image build job did not complete successfully.
+  Check logs at {{ openchami_log_dir }} for respective functional group for more details."
 
 # Usage: build_compute_image.yml
 openchami_compute_image_vars_template: "{{ role_path }}/templates/compute_images_templates.j2"

build_image_x86_64/roles/image_creation/tasks/build_compute_image.yml

@@ -58,14 +58,15 @@
         jid: "{{ item.ansible_job_id }}"
       register: job_result
       until: job_result.finished
+      no_log: true
       retries: "{{ job_retry }}"
       delay: "{{ job_delay }}"
       loop: "{{ compute_image_build_job.results }}"
       loop_control:
         label: "{{ item.item.key }}"
 
   rescue:
-    - name: Fail explicitly if job failed
+    - name: Failed to build the x86_64 compute image
       ansible.builtin.fail:
         msg: "{{ compute_image_failure_msg }}"
 

build_image_x86_64/roles/image_creation/vars/main.yml

@@ -43,7 +43,9 @@ openchami_x86_64_base_image_log_path: "{{ openchami_log_dir }}/x86_64_base_image
 openchami_base_image_vars_template: "{{ role_path }}/templates/base_image_template.j2"
 openchami_x86_64_base_image_vars_path: "/opt/omnia/openchami/x86_64_base_image_template.yaml"
 base_image_failure_msg: "Base x86_64 image build job failed or timed out. Check logs at path {{ openchami_x86_64_base_image_log_path }} for details."
-compute_image_failure_msg: "x86 image build job did not completed successfully. Check logs at path {{ openchami_log_dir }} for respective item"
+compute_image_failure_msg:
+  "x86_64 compute image build job did not complete successfully.
+  Check logs at {{ openchami_log_dir }} for respective functional group for more details."
 
 # build_compute_image.yml
 openchami_compute_image_vars_template: "{{ role_path }}/templates/compute_images_templates.j2"

common/library/module_utils/input_validation/schema/telemetry_config.json

@@ -47,7 +47,18 @@
       "properties": {
         "plugin_name": {
           "type": "string",
-          "description": "Name of the LDMS sampler plugin"
+          "enum": [
+            "meminfo",
+            "procstat2",
+            "vmstat",
+            "loadavg",
+            "slurm_sampler",
+            "procnetdev2"
+          ],
+          "description": "Name of the LDMS sampler plugin. Must be one of the 6 supported plugin types: meminfo (memory usage), procstat2 (process statistics), vmstat (virtual memory), loadavg (system load), slurm_sampler (HPC workload monitoring), procnetdev2 (network interface statistics).",
+          "errorMessage": {
+            "enum": "Invalid plugin_name. Only 6 plugins are supported: meminfo, procstat2, vmstat, loadavg, slurm_sampler, procnetdev2"
+          }
         },
         "config_parameters": {
           "type": "string",
@@ -101,7 +112,7 @@
     }
     }
   },
-  "required": ["idrac_telemetry_support"],
+  "required": ["idrac_telemetry_support", "ldms_sampler_configurations"],
   "$defs": {
     "kafka_configurations": {
       "type": "object",

common/library/module_utils/input_validation/validation_flows/provision_validation.py

@@ -20,6 +20,8 @@
 import re
 import itertools
 import csv
+import yaml
+from io import StringIO
 from ansible.module_utils.input_validation.common_utils import validation_utils
 from ansible.module_utils.input_validation.common_utils import config
 from ansible.module_utils.input_validation.common_utils import en_us_validation_msg
@@ -29,6 +31,15 @@
 create_error_msg = validation_utils.create_error_msg
 create_file_path = validation_utils.create_file_path
 
+def load_oim_metadata(metadata_file_path):
+    with open(metadata_file_path, 'r') as file:
+        metadata = yaml.safe_load(file)
+    return metadata
+
+metadata_file_path = '/opt/omnia/.data/oim_metadata.yml'
+metadata = load_oim_metadata(metadata_file_path)
+oim_timezone = metadata['oim_timezone']
+
 # Expected header columns (case-insensitive)
 required_headers = [
     "FUNCTIONAL_GROUP_NAME",
@@ -459,7 +470,26 @@ def validate_provision_config(
     timezone = data["timezone"]
     if not validation_utils.validate_timezone(timezone, timezone_file_path):
         errors.append(
-            create_error_msg("timezone", timezone, en_us_validation_msg.TIMEZONE_FAIL_MSG)
+            create_error_msg(
+                "timezone",
+                timezone,
+                en_us_validation_msg.TIMEZONE_FAIL_MSG,
+            )
+        )
+
+    # Normalize input and system timezones for comparison
+    input_timezone = (timezone or "").strip()
+    system_timezone = (oim_timezone or "").strip()
+
+    # Compare both timezones (case-insensitive)
+    if system_timezone.lower() != input_timezone.lower():
+        errors.append(
+            create_error_msg(
+                ""
+                "timezone_mismatch detected between OIM host and provision_config.yml.",
+                f"Provided input timezone : {input_timezone}, Detected oim timezone: {system_timezone}",
+                "Timezone mismatch detected. Please ensure both timezones match; refer to timezone.txt.",
+            )
         )
 
     default_lease_time = data["default_lease_time"]

omnia.sh

@@ -620,6 +620,19 @@ validate_oim() {
         exit 1
     fi
 
+    # Detect OIM timezone from systemd in a stable, case‑independent way
+    oim_timezone=$(timedatectl show -p Timezone --value 2>/dev/null)
+
+    # Fallbacks if needed (non‑systemd or old timedatectl)
+    if [[ -z "$oim_timezone" ]]; then
+        if [[ -f /etc/timezone ]]; then
+            # Debian/Ubuntu style
+            oim_timezone=$(< /etc/timezone)
+        elif [[ -L /etc/localtime ]]; then
+            # Derive from /etc/localtime symlink
+            oim_timezone=$(readlink -f /etc/localtime | sed -n 's|^.*zoneinfo/||p')
+        fi
+    fi
 
     podman --version
 
@@ -740,6 +753,7 @@ EOF
             echo "oim_hostname: $(hostname)"
             echo "oim_node_name: $(hostname -s)"
             echo "domain_name: $domain_name"
+            echo "oim_timezone: $oim_timezone"
             echo "omnia_core_hashed_passwd: $hashed_passwd"
             echo "omnia_share_option: $share_option"
         } >> "$oim_metadata_file"