test

- add manual compaction
- reduce compaction frequency

test_runner/batch_others/test_ancestor_branch.py

@@ -6,6 +6,7 @@ from fixtures.neon_fixtures import NeonEnv, NeonEnvBuilder, NeonPageserverApiExc
 #
 # Create ancestor branches off the main branch.
 #
+# @pytest.mark.parametrize("x", range(20))
 def test_ancestor_branch(neon_env_builder: NeonEnvBuilder):
     env = neon_env_builder.init_start()
 
@@ -21,7 +22,7 @@ def test_ancestor_branch(neon_env_builder: NeonEnvBuilder):
             'compaction_target_size': '4194304',
         })
 
-    env.pageserver.safe_psql("failpoints flush-frozen-before-sync=sleep(10000)")
+    # env.pageserver.safe_psql("failpoints flush-frozen-before-sync=sleep(10000)")
 
     pg_branch0 = env.postgres.create_start('main', tenant_id=tenant)
     branch0_cur = pg_branch0.connect().cursor()

test_runner/batch_others/test_branch_and_gc.py

@@ -1,3 +1,4 @@
+import pytest
 from fixtures.log_helper import log
 from fixtures.neon_fixtures import NeonEnv
 from fixtures.utils import lsn_from_hex
@@ -40,6 +41,7 @@ from fixtures.utils import lsn_from_hex
 # Because the delta layer D covering lsn1 is corrupted, creating a branch
 # starting from lsn1 should return an error as follows:
 #     could not find data for key ... at LSN ..., for request at LSN ...
+# @pytest.mark.skip("")
 def test_branch_and_gc(neon_simple_env: NeonEnv):
     env = neon_simple_env
 
@@ -56,9 +58,9 @@ def test_branch_and_gc(neon_simple_env: NeonEnv):
             'compaction_target_size': f'{1024 ** 3}',
 
             # tweak the default settings to allow quickly create image layers and L1 layers
-            'compaction_period': '1 s',
+            'compaction_period': '10 s',
             'compaction_threshold': '2',
-            'image_creation_threshold': '1',
+            'image_creation_threshold': '2',
 
             # set PITR interval to be small, so we can do GC
             'pitr_interval': '1 s'
@@ -77,6 +79,9 @@ def test_branch_and_gc(neon_simple_env: NeonEnv):
     lsn1 = main_cur.fetchone()[0]
     log.info(f'LSN1: {lsn1}')
 
+    # trigger a manual compaction
+    env.pageserver.safe_psql(f'''compact {tenant.hex} {timeline_main.hex}''')
+
     main_cur.execute('INSERT INTO foo SELECT FROM generate_series(1, 100000)')
     main_cur.execute('SELECT pg_current_wal_insert_lsn()')
     lsn2 = main_cur.fetchone()[0]

test_runner/batch_others/test_branching.py

@@ -44,7 +44,7 @@ def test_branching_with_pgbench(neon_simple_env: NeonEnv,
         log.info(f"Start a pgbench workload on pg {connstr}")
 
         pg_bin.run_capture(['pgbench', '-i', f'-s{scale}', connstr])
-        pg_bin.run_capture(['pgbench', '-c10', '-T15', connstr])
+        pg_bin.run_capture(['pgbench', '-T15', connstr])
 
     env.neon_cli.create_branch('b0', tenant_id=tenant)
     pgs: List[Postgres] = []
@@ -54,12 +54,24 @@ def test_branching_with_pgbench(neon_simple_env: NeonEnv,
     threads.append(threading.Thread(target=run_pgbench, args=(pgs[0], ), daemon=True))
     threads[-1].start()
 
+    thread_limit = 4
+
     for i in range(n_branches):
         # random a delay between [0, 5]
         delay = random.random() * 5
         time.sleep(delay)
         log.info(f"Sleep {delay}s")
 
+        # If the number of concurrent threads exceeds a threshold,
+        # wait for all the threads to finish before spawning a new one.
+        #
+        # Because tests defined in `batch_others` are run concurrently in CI,
+        # we want to avoid the situation that one test exhausts resources for other tests.
+        if len(threads) >= thread_limit:
+            for thread in threads:
+                thread.join()
+            threads = []
+
         if ty == "cascade":
             env.neon_cli.create_branch('b{}'.format(i + 1), 'b{}'.format(i), tenant_id=tenant)
         else: