CI(benchmarking): set pub/sub projects for LR tests (#8483)

## Problem

> Currently, long-running LR tests recreate endpoints every night. We'd
like to have along-running buildup of history to exercise the pageserver
in this case (instead of "unit-testing" the same behavior everynight).

Closes #8317

## Summary of changes
- Update Postgres version for replication tests
- Set `BENCHMARK_PROJECT_ID_PUB`/`BENCHMARK_PROJECT_ID_SUB` env vars to
projects that were created for this purpose

---------

Co-authored-by: Sasha Krassovsky <krassovskysasha@gmail.com>

.github/actionlint.yml

@@ -8,6 +8,8 @@ self-hosted-runner:
     - small-arm64
     - us-east-2
 config-variables:
+  - BENCHMARK_PROJECT_ID_PUB
+  - BENCHMARK_PROJECT_ID_SUB
   - REMOTE_STORAGE_AZURE_CONTAINER
   - REMOTE_STORAGE_AZURE_REGION
   - SLACK_UPCOMING_RELEASE_CHANNEL_ID

.github/workflows/benchmarking.yml

@@ -147,7 +147,7 @@ jobs:
     if: ${{ github.event.inputs.run_only_pgvector_tests == 'false' || github.event.inputs.run_only_pgvector_tests == null }}
     env:
       POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
-      DEFAULT_PG_VERSION: 14
+      DEFAULT_PG_VERSION: 16
       TEST_OUTPUT: /tmp/test_output
       BUILD_TYPE: remote
       SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref_name == 'main' ) }}
@@ -168,7 +168,7 @@ jobs:
         path: /tmp/neon/
         prefix: latest
 
-    - name: Run benchmark
+    - name: Run Logical Replication benchmarks
       uses: ./.github/actions/run-python-test-set
       with:
         build_type: ${{ env.BUILD_TYPE }}
@@ -176,12 +176,15 @@ jobs:
         run_in_parallel: false
         save_perf_report: ${{ env.SAVE_PERF_REPORT }}
         extra_params: -m remote_cluster --timeout 5400
+        pg_version: ${{ env.DEFAULT_PG_VERSION }}
       env:
         VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
         PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
         NEON_API_KEY: ${{ secrets.NEON_STAGING_API_KEY }}
+        BENCHMARK_PROJECT_ID_PUB: ${{ vars.BENCHMARK_PROJECT_ID_PUB }}
+        BENCHMARK_PROJECT_ID_SUB: ${{ vars.BENCHMARK_PROJECT_ID_SUB }}
 
-    - name: Run benchmark
+    - name: Run Physical Replication benchmarks
       uses: ./.github/actions/run-python-test-set
       with:
         build_type: ${{ env.BUILD_TYPE }}

test_runner/fixtures/neon_api.py

@@ -285,9 +285,9 @@ class NeonApiEndpoint:
             self.project_id = project_id
             eps = neon_api.get_endpoints(project_id)["endpoints"]
             self.endpoint_id = eps[0]["id"]
-            self.connstr = neon_api.get_connection_uri(project_id, endpoint_id=self.endpoint_id)[
-                "uri"
-            ]
+            self.connstr = neon_api.get_connection_uri(
+                project_id, endpoint_id=self.endpoint_id, pooled=False
+            )["uri"]
             pw = self.connstr.split("@")[0].split(":")[-1]
             self.pgbench_env = {
                 "PGHOST": eps[0]["host"],

test_runner/performance/test_logical_replication.py

@@ -100,24 +100,32 @@ def test_subscriber_lag(
     pub_connstr = benchmark_project_pub.connstr
     sub_connstr = benchmark_project_sub.connstr
 
-    pg_bin.run_capture(["pgbench", "-i", "-s100"], env=pub_env)
-    pg_bin.run_capture(["pgbench", "-i", "-s100"], env=sub_env)
+    if benchmark_project_pub.is_new:
+        pg_bin.run_capture(["pgbench", "-i", "-s100"], env=pub_env)
+    if benchmark_project_sub.is_new:
+        pg_bin.run_capture(["pgbench", "-i", "-s100"], env=sub_env)
 
     pub_conn = psycopg2.connect(pub_connstr)
     sub_conn = psycopg2.connect(sub_connstr)
     pub_conn.autocommit = True
     sub_conn.autocommit = True
     with pub_conn.cursor() as pub_cur, sub_conn.cursor() as sub_cur:
-        if benchmark_project_pub.is_new:
-            pub_cur.execute("create publication pub1 for table pgbench_accounts, pgbench_history")
+        pub_cur.execute("SELECT 1 FROM pg_catalog.pg_publication WHERE pubname = 'pub1'")
+        pub_exists = len(pub_cur.fetchall()) != 0
 
-        if benchmark_project_sub.is_new:
+        if not pub_exists:
+            pub_cur.execute("CREATE PUBLICATION pub1 FOR TABLE pgbench_accounts, pgbench_history")
+
+        sub_cur.execute("SELECT 1 FROM pg_catalog.pg_subscription WHERE subname = 'sub1'")
+        sub_exists = len(sub_cur.fetchall()) != 0
+        if not sub_exists:
             sub_cur.execute("truncate table pgbench_accounts")
             sub_cur.execute("truncate table pgbench_history")
 
-            sub_cur.execute(f"create subscription sub1 connection '{pub_connstr}' publication pub1")
+            sub_cur.execute(f"CREATE SUBSCRIPTION sub1 CONNECTION '{pub_connstr}' PUBLICATION pub1")
 
         initial_sync_lag = measure_logical_replication_lag(sub_cur, pub_cur)
+
     pub_conn.close()
     sub_conn.close()
 
@@ -195,10 +203,15 @@ def test_publisher_restart(
     pub_conn.autocommit = True
     sub_conn.autocommit = True
     with pub_conn.cursor() as pub_cur, sub_conn.cursor() as sub_cur:
-        if benchmark_project_pub.is_new:
+        pub_cur.execute("SELECT 1 FROM pg_catalog.pg_publication WHERE pubname = 'pub1'")
+        pub_exists = len(pub_cur.fetchall()) != 0
+
+        if not pub_exists:
             pub_cur.execute("create publication pub1 for table pgbench_accounts, pgbench_history")
 
-        if benchmark_project_sub.is_new:
+        sub_cur.execute("SELECT 1 FROM pg_catalog.pg_subscription WHERE subname = 'sub1'")
+        sub_exists = len(sub_cur.fetchall()) != 0
+        if not sub_exists:
             sub_cur.execute("truncate table pgbench_accounts")
             sub_cur.execute("truncate table pgbench_history")