fix(demo/trino-taxi-data): Use new listener service (#254)

* fix(demo/trino-taxi-data): Use new listener service
* fix(demo/trino-taxi-data): Use updated superset config
  - See: #251
* chore: Bump Trino worker by 2GB RAM
* fix(demo/trino-taxi-data): Disable ANALYZE step
  - See: trinodb/trino#26214

Author: NickLarsenNZ

demos/trino-taxi-data/create-table-in-trino.yaml

@@ -59,29 +59,32 @@ data:
 
     run_query(connection, "CREATE SCHEMA IF NOT EXISTS hive.demo WITH (location = 's3a://demo/')")
     run_query(connection, """
-        CREATE TABLE IF NOT EXISTS hive.demo.ny_taxi_data_raw (
-            VendorID BIGINT,
-            tpep_pickup_datetime TIMESTAMP,
-            tpep_dropoff_datetime TIMESTAMP,
-            passenger_count DOUBLE,
-            trip_distance DOUBLE,
-            payment_type BIGINT,
-            Fare_amount DOUBLE,
-            Tip_amount DOUBLE,
-            Total_amount DOUBLE
-        ) WITH (
-            external_location = 's3a://demo/ny-taxi-data/raw/',
-            format = 'parquet'
-        )
+    CREATE TABLE IF NOT EXISTS hive.demo.ny_taxi_data_raw (
+        VendorID BIGINT,
+        tpep_pickup_datetime TIMESTAMP,
+        tpep_dropoff_datetime TIMESTAMP,
+        passenger_count DOUBLE,
+        trip_distance DOUBLE,
+        payment_type BIGINT,
+        Fare_amount DOUBLE,
+        Tip_amount DOUBLE,
+        Total_amount DOUBLE
+    ) WITH (
+        external_location = 's3a://demo/ny-taxi-data/raw/',
+        format = 'parquet'
+    )
     """)
 
     loaded_rows = run_query(connection, "SELECT COUNT(*) FROM hive.demo.ny_taxi_data_raw")[0][0]
     print(f"Loaded {loaded_rows} rows")
     assert loaded_rows > 0
 
-    print("Analyzing table ny_taxi_data_raw")
-    analyze_rows = run_query(connection, """ANALYZE hive.demo.ny_taxi_data_raw""")[0][0]
-    assert analyze_rows == loaded_rows
+    # Disabling ANALYZE for now, as it seems to fail when run twice (which can happen if Trino OOMs)
+    # See issue: https://github.com/trinodb/trino/issues/26214
+    # print("Analyzing table ny_taxi_data_raw")
+    # analyze_rows = run_query(connection, """ANALYZE hive.demo.ny_taxi_data_raw""")[0][0]
+    # assert analyze_rows == loaded_rows
+
     stats = run_query(connection, """show stats for hive.demo.ny_taxi_data_raw""")
     print("Produced the following stats:")
     print(*stats, sep="\n")

demos/trino-taxi-data/setup-superset.yaml

@@ -39,7 +39,7 @@ data:
     import logging
     import requests
 
-    base_url = "http://superset-node-default:8088" # For local testing / developing replace it, afterwards change back to http://superset-node-default:8088
+    base_url = "http://superset-node:8088" # You can change this while running locally, but remember not to commit the change.
     superset_username = open("/superset-credentials/adminUser.username").read()
     superset_password =  open("/superset-credentials/adminUser.password").read()
     trino_username = "admin"

demos/trino-taxi-data/superset-assets.zip

@@ -23,7 +23,7 @@ This demo should not be run alongside other demos.
 To run this demo, your system needs at least:
 
 * 10 {k8s-cpu}[cpu units] (core/hyperthread)
-* 32GiB memory
+* 34GiB memory
 * 35GiB disk storage
 
 == Overview

docs/modules/demos/pages/spark-k8s-anomaly-detection-taxi-data.adoc

@@ -27,7 +27,7 @@ This demo should not be run alongside other demos.
 To run this demo, your system needs at least:
 
 * 7 {k8s-cpu}[cpu units] (core/hyperthread)
-* 16GiB memory
+* 18GiB memory
 * 28GiB disk storage
 
 == Overview

docs/modules/demos/pages/trino-taxi-data.adoc

@@ -29,7 +29,7 @@ spec:
           min: "1"
           max: "4"
         memory:
-          limit: '4Gi'
+          limit: '6Gi'
     roleGroups:
       default:
         replicas: 1