[Benchmark] Add mechanism to retreive the logs from test-execution.json

Pipfile

@@ -41,6 +41,7 @@ ruamel-yaml = "~=0.17.21"
 markdownify = "~=0.12.1"
 mistune = "~=3.0.1"
 semver = ">=3,<4"
+pandas = "~=2.2.2"
 
 [dev-packages]
 

jenkins/opensearch/benchmark-test-endpoint.jenkinsfile

@@ -121,6 +121,7 @@ parameters {
                         password: PASSWORD,
                         workload: TEST_WORKLOAD,
                         userTag: USER_TAGS.isEmpty() ? "security-enabled:${SECURITY_ENABLED}" : "${USER_TAGS},security-enabled:${SECURITY_ENABLED}",
+                        suffix: "${BUILD_NUMBER}",
                         workloadParams: WORKLOAD_PARAMS,
                         testProcedure: TEST_PROCEDURE,
                         excludeTasks: EXCLUDE_TASKS,
@@ -129,10 +130,14 @@ parameters {
                         captureSegmentReplicationStat: CAPTURE_SEGMENT_REPLICATION_STAT,
                         telemetryParams: TELEMETRY_PARAMS
                     )
+                    stash includes: 'test_execution.*', name: "benchmark"
+
                 }
             }
             post {
                 always {
+                    unstash "benchmark"
+                    archiveArtifacts artifacts: 'test_execution.*'
                     postCleanup()
                 }
             }

src/test_workflow/benchmark_test/benchmark_test_runner_opensearch.py

@@ -7,6 +7,7 @@
 
 import logging
 import os
+import subprocess
 from typing import Union
 
 import yaml
@@ -42,8 +43,10 @@ def run_tests(self) -> None:
             cluster = BenchmarkTestCluster(self.args)
             cluster.start()
             benchmark_test_suite = BenchmarkTestSuite(cluster.endpoint_with_port, self.security, self.args, cluster.fetch_password())
-            retry_call(benchmark_test_suite.execute, tries=3, delay=60, backoff=2)
-
+            try:
+                retry_call(benchmark_test_suite.execute, tries=3, delay=60, backoff=2)
+            finally:
+                subprocess.check_call(f"docker rm docker-container-{self.args.stack_suffix}", cwd=os.getcwd(), shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
         else:
             config = yaml.safe_load(self.args.config)
 
@@ -53,4 +56,7 @@ def run_tests(self) -> None:
                     with WorkingDirectory(current_workspace):
                         with BenchmarkCreateCluster.create(self.args, self.test_manifest, config, current_workspace) as test_cluster:
                             benchmark_test_suite = BenchmarkTestSuite(test_cluster.endpoint_with_port, self.security, self.args, test_cluster.fetch_password())
-                            retry_call(benchmark_test_suite.execute, tries=3, delay=60, backoff=2)
+                            try:
+                                benchmark_test_suite.execute()
+                            finally:
+                                subprocess.check_call(f"docker rm docker-container-{self.args.stack_suffix}", cwd=os.getcwd(), shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)

src/test_workflow/benchmark_test/benchmark_test_suite.py

@@ -5,11 +5,17 @@
 # this file be licensed under the Apache-2.0 license or a
 # compatible open source license.
 
+import glob
+import json
 import logging
 import os
+import shutil
 import subprocess
 from typing import Any
 
+import pandas as pd
+
+from system.temporary_directory import TemporaryDirectory
 from test_workflow.benchmark_test.benchmark_args import BenchmarkArgs
 
 
@@ -37,7 +43,7 @@ def __init__(
         self.password = password
 
         # Pass the cluster endpoints with -t for multi-cluster use cases(e.g. cross-cluster-replication)
-        self.command = 'docker run --rm'
+        self.command = f'docker run --name docker-container-{self.args.stack_suffix}'
         if self.args.benchmark_config:
             self.command += f" -v {args.benchmark_config}:/opensearch-benchmark/.benchmark/benchmark.ini"
         self.command += f" opensearchproject/opensearch-benchmark:latest execute-test --workload={self.args.workload} " \
@@ -67,11 +73,27 @@ def __init__(
             if self.args.telemetry_params:
                 self.command += f" --telemetry-params '{self.args.telemetry_params}'"
 
-    def execute(self) -> None:
         if self.security:
             self.command += f' --client-options="timeout:300,use_ssl:true,verify_certs:false,basic_auth_user:\'{self.args.username}\',basic_auth_password:\'{self.password}\'"'
         else:
             self.command += ' --client-options="timeout:300"'
+
+    def execute(self) -> None:
         log_info = f"Executing {self.command.replace(self.endpoint, len(self.endpoint) * '*').replace(self.args.username, len(self.args.username) * '*')}"
         logging.info(log_info.replace(self.password, len(self.password) * '*') if self.password else log_info)
         subprocess.check_call(f"{self.command}", cwd=os.getcwd(), shell=True)
+        with TemporaryDirectory() as work_dir:
+            subprocess.check_call(f"docker cp docker-container-{self.args.stack_suffix}:opensearch-benchmark/. {str(work_dir.path)}", cwd=os.getcwd(), shell=True)
+            file_path = glob.glob(os.path.join(str(work_dir.path), "test_executions", "*", "test_execution.json"))
+            self.convert(file_path[0])
+
+    def convert(self, results: str) -> None:
+        with open(results) as file:
+            data = json.load(file)
+        formatted_data = pd.json_normalize(data["results"]["op_metrics"])
+        formatted_data.to_csv(os.path.join(os.getcwd(), "test_execution.csv"), index=False)
+        df = pd.read_csv(os.path.join(os.getcwd(), "test_execution.csv"))
+        pd.set_option('display.width', int(2 * shutil.get_terminal_size().columns))
+        pd.set_option('display.max_rows', None)
+        pd.set_option('display.max_columns', None)
+        logging.info(f"\n{df}")