Fix nightly tests (#2460)

Fixes #2459 

- Set `/data/` as primary storage `access_endpoint_url` in nightly test
chart
- Modify nightly test GH Actions workflow to spawn a separate job per
nightly test module using dynamic matrix
- Set configuration not to fail other jobs if one job fails
- Modify failing tests:
- Add fixture to background job nightly test module so it can run alone
- Add retry loop to crawlconfig stats nightly test so it's less
dependent on timing

GitHub limits each workflow to 256 jobs, so this should continue to be
able to scale up for us without issue.

---------

Co-authored-by: Ilya Kreymer <ikreymer@users.noreply.github.com>

.github/workflows/k3d-nightly-ci.yaml

@@ -8,8 +8,24 @@ on:
   workflow_dispatch:
 
 jobs:
-  btrix-k3d-nightly-test:
+  collect-test-modules:
     runs-on: ubuntu-latest
+    outputs:
+      matrix: ${{ steps.set-matrix.outputs.matrix }}
+    steps:
+      - uses: actions/checkout@v3
+      - id: set-matrix
+        run: |
+          echo matrix="$(ls ./backend/test_nightly/ | grep -o "^test_.*" | jq -R -s -c 'split("\n")[:-1]')" >> $GITHUB_OUTPUT
+
+  btrix-k3d-nightly-test:
+    name: ${{ matrix.module }}
+    needs: collect-test-modules
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        module: ${{fromJSON(needs.collect-test-modules.outputs.matrix)}}
+      fail-fast: false
     steps:
       - name: Create k3d Cluster
         uses: AbsaOSS/k3d-action@v2
@@ -82,7 +98,7 @@ jobs:
         run:  kubectl exec -i deployment/local-minio -c minio -- mkdir /data/replica-0
 
       - name: Run Tests
-        run: pytest -vv ./backend/test_nightly/test_*.py
+        run: pytest -vv ./backend/test_nightly/${{ matrix.module }}
 
       - name: Print Backend Logs (API)
         if: ${{ failure() }}

backend/test_nightly/conftest.py

@@ -320,3 +320,67 @@ def org_with_quotas(admin_auth_headers):
     data = r.json()
 
     return data["id"]
+
+
+@pytest.fixture(scope="session")
+def deleted_crawl_id(admin_auth_headers, default_org_id):
+    # Start crawl.
+    crawl_data = {
+        "runNow": True,
+        "name": "Test crawl",
+        "config": {
+            "seeds": [{"url": "https://webrecorder.net/"}],
+            "limit": 1,
+        },
+    }
+    r = requests.post(
+        f"{API_PREFIX}/orgs/{default_org_id}/crawlconfigs/",
+        headers=admin_auth_headers,
+        json=crawl_data,
+    )
+    data = r.json()
+
+    crawl_id = data["run_now_job"]
+
+    # Wait for it to complete
+    while True:
+        r = requests.get(
+            f"{API_PREFIX}/orgs/{default_org_id}/crawls/{crawl_id}/replay.json",
+            headers=admin_auth_headers,
+        )
+        data = r.json()
+        if data["state"] == "complete":
+            break
+        time.sleep(5)
+
+    # Wait until replica background job completes
+    while True:
+        r = requests.get(
+            f"{API_PREFIX}/orgs/{default_org_id}/jobs/?jobType=create-replica&success=True",
+            headers=admin_auth_headers,
+        )
+        assert r.status_code == 200
+        if r.json()["total"] == 1:
+            break
+        time.sleep(5)
+
+    # Delete crawl
+    r = requests.post(
+        f"{API_PREFIX}/orgs/{default_org_id}/crawls/delete",
+        headers=admin_auth_headers,
+        json={"crawl_ids": [crawl_id]},
+    )
+    assert r.status_code == 200
+
+    # Wait until delete replica background job completes
+    while True:
+        r = requests.get(
+            f"{API_PREFIX}/orgs/{default_org_id}/jobs/?jobType=delete-replica&success=True",
+            headers=admin_auth_headers,
+        )
+        assert r.status_code == 200
+        if r.json()["total"] == 1:
+            break
+        time.sleep(5)
+
+    return crawl_id

backend/test_nightly/test_crawlconfig_crawl_stats.py

@@ -71,17 +71,25 @@ def test_crawlconfig_crawl_stats(admin_auth_headers, default_org_id, crawl_confi
     data = r.json()
     assert data["deleted"]
 
-    time.sleep(10)
-
     # Verify crawl stats from /crawlconfigs
-    r = requests.get(
-        f"{API_PREFIX}/orgs/{default_org_id}/crawlconfigs/{crawl_config_id}",
-        headers=admin_auth_headers,
-    )
-    assert r.status_code == 200
-    data = r.json()
-    assert data["crawlAttemptCount"] == 2
-    assert data["crawlCount"] == 0
-    assert not data["lastCrawlId"]
-    assert not data["lastCrawlState"]
-    assert not data["lastCrawlTime"]
+    max_attempts = 18
+    attempts = 1
+    while True:
+        r = requests.get(
+            f"{API_PREFIX}/orgs/{default_org_id}/crawlconfigs/{crawl_config_id}",
+            headers=admin_auth_headers,
+        )
+        assert r.status_code == 200
+        data = r.json()
+
+        if data["crawlAttemptCount"] == 2 and data["crawlCount"] == 0:
+            assert not data["lastCrawlId"]
+            assert not data["lastCrawlState"]
+            assert not data["lastCrawlTime"]
+            break
+
+        if attempts >= max_attempts:
+            assert False
+
+        time.sleep(10)
+        attempts += 1

backend/test_nightly/test_z_background_jobs.py

@@ -10,7 +10,7 @@ from .conftest import API_PREFIX
 job_id = None
 
 
-def test_background_jobs_list(admin_auth_headers, default_org_id):
+def test_background_jobs_list(admin_auth_headers, default_org_id, deleted_crawl_id):
     r = requests.get(
         f"{API_PREFIX}/orgs/{default_org_id}/jobs/", headers=admin_auth_headers
     )
@@ -37,7 +37,7 @@ def test_background_jobs_list(admin_auth_headers, default_org_id):
 
 @pytest.mark.parametrize("job_type", [("create-replica"), ("delete-replica")])
 def test_background_jobs_list_filter_by_type(
-    admin_auth_headers, default_org_id, job_type
+    admin_auth_headers, default_org_id, deleted_crawl_id, job_type
 ):
     r = requests.get(
         f"{API_PREFIX}/orgs/{default_org_id}/jobs/?jobType={job_type}",
@@ -54,7 +54,9 @@ def test_background_jobs_list_filter_by_type(
         assert item["type"] == job_type
 
 
-def test_background_jobs_list_filter_by_success(admin_auth_headers, default_org_id):
+def test_background_jobs_list_filter_by_success(
+    admin_auth_headers, default_org_id, deleted_crawl_id
+):
     r = requests.get(
         f"{API_PREFIX}/orgs/{default_org_id}/jobs/?success=True",
         headers=admin_auth_headers,
@@ -70,7 +72,9 @@ def test_background_jobs_list_filter_by_success(admin_auth_headers, default_org_
         assert item["success"]
 
 
-def test_background_jobs_no_failures(admin_auth_headers, default_org_id):
+def test_background_jobs_no_failures(
+    admin_auth_headers, default_org_id, deleted_crawl_id
+):
     r = requests.get(
         f"{API_PREFIX}/orgs/{default_org_id}/jobs/?success=False",
         headers=admin_auth_headers,
@@ -81,7 +85,7 @@ def test_background_jobs_no_failures(admin_auth_headers, default_org_id):
     assert data["total"] == 0
 
 
-def test_get_background_job(admin_auth_headers, default_org_id):
+def test_get_background_job(admin_auth_headers, default_org_id, deleted_crawl_id):
     r = requests.get(
         f"{API_PREFIX}/orgs/{default_org_id}/jobs/{job_id}", headers=admin_auth_headers
     )
@@ -100,7 +104,7 @@ def test_get_background_job(admin_auth_headers, default_org_id):
     assert data["replica_storage"]
 
 
-def test_retry_all_failed_bg_jobs_not_superuser(crawler_auth_headers):
+def test_retry_all_failed_bg_jobs_not_superuser(crawler_auth_headers, deleted_crawl_id):
     r = requests.post(
         f"{API_PREFIX}/orgs/all/jobs/retryFailed", headers=crawler_auth_headers
     )

chart/test/test-nightly-addons.yaml

@@ -21,7 +21,8 @@ storages:
     bucket_name: *local_bucket_name
 
     endpoint_url: "http://local-minio.default:9000/"
-    is_default_primary: True
+    is_default_primary: true
+    access_endpoint_url: "/data/"
 
   - name: "replica-0"
     type: "s3"
@@ -30,6 +31,6 @@ storages:
     bucket_name: "replica-0"
 
     endpoint_url: "http://local-minio.default:9000/"
-    is_default_replica: True
+    is_default_replica: true