From 263d18e7e21c292a3c8dbcada472168f5cf01239 Mon Sep 17 00:00:00 2001
From: jbajic <jure.bajic@memgraph.com>
Date: Thu, 8 Dec 2022 13:30:14 +0100
Subject: [PATCH] Add github action

---
 .github/workflows/diff.yaml  | 39 ++++++++++++++++-
 tests/mgbench/format_json.py | 84 ++++++++++++++++++++++++++++++++++++
 2 files changed, 121 insertions(+), 2 deletions(-)
 create mode 100755 tests/mgbench/format_json.py

diff --git a/.github/workflows/diff.yaml b/.github/workflows/diff.yaml
index a7faa7d22..1003f37a2 100644
--- a/.github/workflows/diff.yaml
+++ b/.github/workflows/diff.yaml
@@ -73,7 +73,12 @@ jobs:
         # This is also needed if we want do to comparison against other branches
         # See https://github.community/t/checkout-code-fails-when-it-runs-lerna-run-test-since-master/17920
       - name: Fetch all history for all tags and branches
-        run: git fetch
+        uses: nick-fields/retry@v2
+        with:
+          timeout_minutes: 1
+          max_attempts: 3
+          shell: bash
+          command: git fetch
 
       - name: Initialize deps
         run: |
@@ -261,7 +266,37 @@ jobs:
 
           # Run simulation tests.
           cd tests/mgbench
-          ./benchmark.py accesscontrol/small --num-workers-for-import 1 --test-system-arg  "split-file splitfiles/accesscontrol_small.shard_configuration bolt-num-workers 1"
+          ./benchmark.py accesscontrol/small --num-workers-for-import 1 \
+            --export-results=output_github_benchmark.json --test-system-arg \
+            "split-file splitfiles/accesscontrol_small.shard_configuration bolt-num-workers 1"
+
+      - name: Adapt benchmark results to benchmark github
+        run: ./tests/mgbench/format_json.py -i output_github_benchmark.json -o formatted_output_benchmark.json
+
+      # Download previous benchmark result from cache (if exists)
+      - name: Download previous benchmark data
+        uses: actions/cache@v3
+        with:
+          path: ./cache
+          key: ${{ runner.os }}-benchmark
+
+      # Run `github-action-benchmark` action
+      - name: Store benchmark result
+        uses: benchmark-action/github-action-benchmark@v1
+        with:
+          # What benchmark tool the output.txt came from
+          tool: "customBiggerIsBetter"
+          # Where the output from the benchmark tool is stored
+          output-file-path: formatted_output_benchmark.json
+          # Where the previous data file is stored
+          external-data-json-path: ./cache/benchmark-data.json
+          # Workflow will fail when an alert happens
+          fail-on-alert: true
+          # GitHub API token to make a commit comment
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          # Enable alert commit comment
+          comment-on-alert: true
+          alert-threshold: "150%"
 
       - name: Run e2e tests
         run: |
diff --git a/tests/mgbench/format_json.py b/tests/mgbench/format_json.py
new file mode 100755
index 000000000..05b4bf44d
--- /dev/null
+++ b/tests/mgbench/format_json.py
@@ -0,0 +1,84 @@
+#!/usr/bin/env python3
+
+# Copyright 2022 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.
+
+import argparse
+import json
+from pathlib import Path
+from typing import Any, Dict, List
+
+
+def adapt_to_benchmark_action(data: Dict[str, Any]) -> List[Dict[str, Any]]:
+    output = []
+    keys = list(data.keys())
+    assert len(keys) == 1
+    dataset_name = keys[0]
+
+    dataset_keys = list(data[dataset_name])
+    assert len(dataset_keys) == 1
+    dataset_type = dataset_keys[0]
+
+    for execution_type, execution_data in data[dataset_name][dataset_type].items():
+        if execution_type == "__import__":
+            continue
+        for type, type_data in execution_data.items():
+            assert "throughput" in type_data, f"There is no throughput in {type_data}!"
+            output.append(
+                {
+                    "name": f"{dataset_name}_{dataset_type}_{execution_type}",
+                    "unit": "QPS",
+                    "value": type_data["throughput"],
+                }
+            )
+    return output
+
+
+ADAPTERS = {
+    "github_benchmark": adapt_to_benchmark_action,
+}
+
+
+def convert_input(input: Dict[str, Any], adapter: str) -> List[Dict[str, Any]]:
+    return ADAPTERS[adapter](input)
+
+
+def parse_args():
+    parser = argparse.ArgumentParser(
+        description="JSON adapter.", formatter_class=argparse.ArgumentDefaultsHelpFormatter
+    )
+    parser.add_argument("-i", "--input", help="Input JSON file.")
+    parser.add_argument("-o", "--output", help="Output JSON file.")
+    parser.add_argument(
+        "--adapter", default="github_benchmark", choices=ADAPTERS.keys(), help="Adapter function to use."
+    )
+
+    return parser.parse_args()
+
+
+def read_input(input: str) -> Dict[str, Any]:
+    with Path(input).open() as input_file:
+        return json.load(input_file)
+
+
+def output_results(content: List[Dict[str, Any]], output: str):
+    with Path(output).open("w") as output_file:
+        output_file.write(json.dumps(content))
+
+
+def main():
+    args = parse_args()
+    content = read_input(args.input)
+    output_results(convert_input(content, args.adapter), args.output)
+
+
+if __name__ == "__main__":
+    main()