fix(test): only test num of L1 layers in compaction smoke test (#9186)

close https://github.com/neondatabase/neon/issues/9160

For whatever reason, pg17's WAL pattern seems different from others,
which triggers some flaky behavior within the compaction smoke test.

## Summary of changes

* Run L0 compaction before proceeding with the read benchmark.
* So that we can ensure the num of L0 layers is 0 and test the
compaction behavior only with L1 layers.

We have a threshold for triggering L0 compaction. In some cases, the
test case did not produce enough L0 layers to do a L0 compaction,
therefore leaving the layer map with 3+ L0 layers above the L1 layers.
This increases the average read depth for the timeline.

---------

Signed-off-by: Alex Chi Z <chi@neon.tech>

test_runner/fixtures/pageserver/http.py

@@ -586,6 +586,7 @@ class PageserverHttpClient(requests.Session, MetricsGetter):
         timeline_id: TimelineId,
         force_repartition=False,
         force_image_layer_creation=False,
+        force_l0_compaction=False,
         wait_until_uploaded=False,
         enhanced_gc_bottom_most_compaction=False,
     ):
@@ -595,6 +596,8 @@ class PageserverHttpClient(requests.Session, MetricsGetter):
             query["force_repartition"] = "true"
         if force_image_layer_creation:
             query["force_image_layer_creation"] = "true"
+        if force_l0_compaction:
+            query["force_l0_compaction"] = "true"
         if wait_until_uploaded:
             query["wait_until_uploaded"] = "true"
         if enhanced_gc_bottom_most_compaction:
@@ -701,6 +704,7 @@ class PageserverHttpClient(requests.Session, MetricsGetter):
         timeline_id: TimelineId,
         force_repartition=False,
         force_image_layer_creation=False,
+        force_l0_compaction=False,
         wait_until_uploaded=False,
         compact: Optional[bool] = None,
         **kwargs,
@@ -711,6 +715,8 @@ class PageserverHttpClient(requests.Session, MetricsGetter):
             query["force_repartition"] = "true"
         if force_image_layer_creation:
             query["force_image_layer_creation"] = "true"
+        if force_l0_compaction:
+            query["force_l0_compaction"] = "true"
         if wait_until_uploaded:
             query["wait_until_uploaded"] = "true"
 

test_runner/fixtures/workload.py

@@ -175,7 +175,9 @@ class Workload:
                 if upload:
                     # Wait for written data to be uploaded to S3 (force a checkpoint to trigger upload)
                     ps_http.timeline_checkpoint(
-                        tenant_shard_id, self.timeline_id, wait_until_uploaded=True
+                        tenant_shard_id,
+                        self.timeline_id,
+                        wait_until_uploaded=True,
                     )
                     log.info(f"Churn: waiting for remote LSN {last_flush_lsn}")
                 else:

test_runner/regress/test_compaction.py

@@ -63,7 +63,10 @@ page_cache_size=10
             log.info(f"Running churn round {i}/{churn_rounds} ...")
 
         workload.churn_rows(row_count, env.pageserver.id)
-        ps_http.timeline_compact(tenant_id, timeline_id)
+        # Force L0 compaction to ensure the number of layers is within bounds; we don't want to count L0 layers
+        # in this benchmark. In other words, this smoke test ensures number of L1 layers are bound.
+        ps_http.timeline_compact(tenant_id, timeline_id, force_l0_compaction=True)
+        assert ps_http.perf_info(tenant_id, timeline_id)[0]["num_of_l0"] <= 1
 
     log.info("Validating at workload end ...")
     workload.validate(env.pageserver.id)