Merge pull request #1216 from spack/commit_id-to-pipeline_id

Rename `commit_id` to `pipeline_id`

Author: jjnesbitt

.github/workflows/custom_docker_builds.yml

@@ -45,7 +45,7 @@ jobs:
           - docker-image: ./images/cache-indexer
             image-tags: ghcr.io/spack/cache-indexer:0.0.6
           - docker-image: ./analytics
-            image-tags: ghcr.io/spack/django:0.5.9
+            image-tags: ghcr.io/spack/django:0.5.10
           - docker-image: ./images/ci-prune-buildcache
             image-tags: ghcr.io/spack/ci-prune-buildcache:0.0.4
           - docker-image: ./images/protected-publish

analytics/analytics/core/job_log_uploader/__init__.py

@@ -60,7 +60,7 @@ def store_job_data(job_input_data_json: str) -> None:
     retry_info = get_job_retry_data(
         job_id=job_input_data["build_id"],
         job_name=job_input_data["build_name"],
-        job_commit_id=job_input_data["commit"]["id"],
+        job_pipeline_id=job_input_data["pipeline_id"],
         job_failure_reason=job_input_data["build_failure_reason"],
     )
     job_input_data.update(asdict(retry_info))

analytics/analytics/core/migrations/0013_gitlabjob_commit_id_to_pipeline_id.py

@@ -0,0 +1,26 @@
+# Generated by Django 5.2.6 on 2025-10-02 20:46
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('core', '0012_jobfact_core_jobfact_started_at_and_more'),
+    ]
+
+    operations = [
+        migrations.RemoveConstraint(
+            model_name='gitlabjobdatadimension',
+            name='unique-gitlab-job-data',
+        ),
+        migrations.RenameField(
+            model_name='gitlabjobdatadimension',
+            old_name='commit_id',
+            new_name='pipeline_id',
+        ),
+        migrations.AddConstraint(
+            model_name='gitlabjobdatadimension',
+            constraint=models.UniqueConstraint(fields=('gitlab_runner_version', 'ref', 'tags', 'pipeline_id'), name='unique-gitlab-job-data'),
+        ),
+    ]

analytics/analytics/core/models/dimensions.py

@@ -171,7 +171,7 @@ class GitlabJobDataDimension(models.Model):
     gitlab_runner_version = models.CharField(max_length=16)
     ref = models.CharField(max_length=256)
     tags = ArrayField(base_field=models.CharField(max_length=32), default=list)
-    commit_id = models.PositiveBigIntegerField(null=True)
+    pipeline_id = models.PositiveBigIntegerField(null=True)
 
     class Meta:
         constraints = [
@@ -181,7 +181,7 @@ class Meta:
                     "gitlab_runner_version",
                     "ref",
                     "tags",
-                    "commit_id",
+                    "pipeline_id",
                 ],
             ),
         ]

analytics/analytics/job_processor/dimensions.py

@@ -134,7 +134,7 @@ def create_gitlab_job_data_dimension(
         gitlab_runner_version=runner_version,
         ref=gljob.ref,
         tags=gljob.tag_list,
-        commit_id=job_input_data["commit"]["id"],
+        pipeline_id=job_input_data["pipeline_id"],
     )
 
     return res
@@ -165,12 +165,12 @@ def create_job_result_dimension(job_input_data: dict, job_trace: str):
 def create_job_retry_dimension(job_input_data: dict):
     job_id = job_input_data["build_id"]
     job_name = job_input_data["build_name"]
-    job_commit_id = job_input_data["commit"]["id"]
+    job_pipeline_id = job_input_data["pipeline_id"]
     job_failure_reason: str = job_input_data["build_failure_reason"]
     retry_info = get_job_retry_data(
         job_id=job_id,
         job_name=job_name,
-        job_commit_id=job_commit_id,
+        job_pipeline_id=job_pipeline_id,
         job_failure_reason=job_failure_reason,
     )
 

analytics/analytics/job_processor/utils.py

@@ -24,12 +24,13 @@ class RetryInfo:
 
 
 def get_job_retry_data(
-    job_id: int, job_name: str, job_commit_id: int, job_failure_reason: str
+    job_id: int, job_name: str, job_pipeline_id: int, job_failure_reason: str
 ) -> RetryInfo:
     with connections["gitlab"].cursor() as cursor:
-        # the prior attempts for a given job are all jobs with a lower id, the same commit_id, and
-        # the same name. the commit_id is the foreign key for the pipeline.
-        # it's important to filter for a lower job id in the event that the webhook is delayed or
+        # In gitlab, the pipeline ID is stored as `commit_id`.
+        # The prior attempts for a given job are all jobs with a lower id, the same commit_id, and
+        # the same name. 
+        # It's important to filter for a lower job id in the event that the webhook is delayed or
         # received out of order.
         cursor.execute(
             """
@@ -39,7 +40,7 @@ def get_job_retry_data(
             AND commit_id = %(commit_id)s
             AND name = %(job_name)s
             """,
-            {"job_id": job_id, "job_name": job_name, "commit_id": job_commit_id},
+            {"job_id": job_id, "job_name": job_name, "commit_id": job_pipeline_id},
         )
         attempt_number = cursor.fetchone()[0] + 1
 

k8s/production/custom/webhook-handler/deployments.yaml

@@ -23,7 +23,7 @@ spec:
       serviceAccountName: webhook-handler
       containers:
         - name: webhook-handler
-          image: ghcr.io/spack/django:0.5.9
+          image: ghcr.io/spack/django:0.5.10
           imagePullPolicy: Always
           resources:
             requests:
@@ -146,7 +146,7 @@ spec:
       serviceAccountName: webhook-handler
       containers:
         - name: webhook-handler-worker
-          image: ghcr.io/spack/django:0.5.9
+          image: ghcr.io/spack/django:0.5.10
           command:
             [
               "celery",