From fdf63436abeb7b79048f0cc80767eeca03de8c7d Mon Sep 17 00:00:00 2001
From: Josipmrden <josip.mrden@memgraph.io>
Date: Tue, 24 Oct 2023 19:44:11 +0200
Subject: [PATCH] Add cartesian and hash join mgbench (#1393)

---
 .github/workflows/daily_benchmark.yaml        |  8 ++++
 .github/workflows/performance_benchmarks.yaml |  8 ++++
 tests/mgbench/workloads/cartesian.py          | 39 +++++++++++++++++++
 3 files changed, 55 insertions(+)
 create mode 100644 tests/mgbench/workloads/cartesian.py

diff --git a/.github/workflows/daily_benchmark.yaml b/.github/workflows/daily_benchmark.yaml
index 9581d5e54..681e5a6a5 100644
--- a/.github/workflows/daily_benchmark.yaml
+++ b/.github/workflows/daily_benchmark.yaml
@@ -73,6 +73,8 @@ jobs:
 
           ./benchmark.py vendor-native --num-workers-for-benchmark 1 --export-results benchmark_high_write_set_property.json high_write_set_property
 
+          ./benchmark.py vendor-native --num-workers-for-benchmark 12 --export-results cartesian.json cartesian
+
       - name: Upload mgbench results
         run: |
           cd tools/bench-graph-client
@@ -96,3 +98,9 @@ jobs:
                     --github-run-id "${{ github.run_id }}" \
                     --github-run-number "${{ github.run_number }}" \
                     --head-branch-name "${{ env.BRANCH_NAME }}"
+
+          ./main.py --benchmark-name "cartesian" \
+                    --benchmark-results-path "../../tests/mgbench/cartesian.json" \
+                    --github-run-id "${{ github.run_id }}" \
+                    --github-run-number "${{ github.run_number }}" \
+                    --head-branch-name "${{ env.BRANCH_NAME }}"
diff --git a/.github/workflows/performance_benchmarks.yaml b/.github/workflows/performance_benchmarks.yaml
index a52d6d587..29b227556 100644
--- a/.github/workflows/performance_benchmarks.yaml
+++ b/.github/workflows/performance_benchmarks.yaml
@@ -52,6 +52,8 @@ jobs:
 
           ./benchmark.py vendor-native --num-workers-for-benchmark 1 --export-results benchmark_high_write_set_property.json high_write_set_property
 
+          ./benchmark.py vendor-native --num-workers-for-benchmark 12 --export-results benchmark_cartesian.json cartesian
+
       - name: Upload benchmark results
         run: |
           cd tools/bench-graph-client
@@ -75,3 +77,9 @@ jobs:
                     --github-run-id "${{ github.run_id }}" \
                     --github-run-number "${{ github.run_number }}" \
                     --head-branch-name "${{ env.BRANCH_NAME }}"
+
+          ./main.py --benchmark-name "cartesian" \
+                    --benchmark-results-path "../../tests/mgbench/cartesian.json" \
+                    --github-run-id "${{ github.run_id }}" \
+                    --github-run-number "${{ github.run_number }}" \
+                    --head-branch-name "${{ env.BRANCH_NAME }}"
diff --git a/tests/mgbench/workloads/cartesian.py b/tests/mgbench/workloads/cartesian.py
new file mode 100644
index 000000000..caa7598b7
--- /dev/null
+++ b/tests/mgbench/workloads/cartesian.py
@@ -0,0 +1,39 @@
+# Copyright 2023 Memgraph Ltd.
+#
+# Use of this software is governed by the Business Source License
+# included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
+# License, and you may not use this file except in compliance with the Business Source License.
+#
+# As of the Change Date specified in that file, in accordance with
+# the Business Source License, use of this software will be governed
+# by the Apache License, Version 2.0, included in the file
+# licenses/APL.txt.
+
+from workloads.base import Workload
+
+
+class Supernode(Workload):
+    NAME = "cartesian"
+    CARDINALITY = 1000
+
+    def indexes_generator(self):
+        return [
+            ("CREATE INDEX ON :Node;", {}),
+            ("CREATE INDEX ON :Node(id);", {}),
+        ]
+
+    def dataset_generator(self):
+        queries = []
+        for i in range(0, Supernode.CARDINALITY):
+            queries.append(("CREATE (:Node {id: $id, id2: $id});", {"id": i, "id2": i}))
+
+        return queries
+
+    def benchmark__test__plain_cartesian_filtering(self):
+        return ("MATCH (n1:Node), (n2:Node) WHERE n1.id < 100 and n2.id < 100 RETURN n1, n2;", {})
+
+    def benchmark__test__plain_cartesian_join(self):
+        return ("MATCH (n1:Node), (n2:Node) WHERE n1.id = n2.id RETURN n1, n2;", {})
+
+    def benchmark__test__plain_cartesian_different_props_join(self):
+        return ("MATCH (n1:Node), (n2:Node) WHERE n1.id = n2.id2 RETURN n1, n2;", {})