Collect Hyperfoil data from Jenkins and plot

plot-hyperfoil-data.md

import os
import requests
from requests.auth import HTTPBasicAuth
import pandas as pd
import json
import matplotlib.pyplot as plt


class DownloadJenkinsHyperfoilData:
    def __init__(self, all_json_urls):
        self.all_json_urls = all_json_urls
        self.username = os.environ['JENKINS_USERNAME']
        self.token = os.environ['JENKINS_TOKEN']

    def download_all_json_hyperfoil_data(self, all_json_url):
        os.makedirs('/tmp/hyperfoil-notebook/', exist_ok=True)
        hash_key = hash(all_json_url)
        output_file = f'/tmp/hyperfoil-notebook/{hash_key}'
        if not os.path.exists(output_file):
            response = requests.get(all_json_url, auth=HTTPBasicAuth(self.username, self.token), verify=False)
            if response.status_code == 200:
                with open(output_file, 'w', encoding='utf-8') as f:
                    for chunk in response.iter_content(chunk_size=8192, decode_unicode=True):
                        if chunk:
                            f.write(chunk)
            else:
                raise Exception(f'Failed to download {all_json_url}')
        with open(output_file) as f:
            json_data = json.load(f)
        return hash_key, json_data

    def get_stats(self, hyperfoil_phase, metric):
        output_data = []
        for all_json_url in self.all_json_urls:
            hash_key, json_data = self.download_all_json_hyperfoil_data(all_json_url)
            df_stats = pd.DataFrame([
                {k: v for k, v in d.items()} for d in json_data['stats']
            ])
            filter_df = df_stats[(df_stats['phase'] == hyperfoil_phase) & (df_stats['metric'] == metric)]
            output_data.append({
                'all_json_url': all_json_url,
                'hash_key': hash_key,
                'df_stats': df_stats,
                'filter_df': filter_df,
            })
        return output_data

    def access_nested_dict(self, serie, key_string):
        keys = key_string.split(',')
        value = serie
        for key in keys:
            value = value[key]
        return value

    def plot(self, k, request_counts, stats_list):
        s = 20
        fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(12, 4), sharex=False)
        for i in range(len(request_counts)):
            ax1.scatter(i, request_counts[i], c='blue', s=s)
            ax2.scatter(i, stats_list[i], c='blue', s=s)
        ax1.set_title('Requests')
        ax1.set_ylabel('n Requests')
        ax2.set_title(k)
        ax2.set_ylabel('Latency')
        plt.tight_layout()
        plt.show()

    def run(self, hyperfoil_phase, metric):

        output_data = self.get_stats(hyperfoil_phase, metric)
        key_string = 'percentileResponseTime,50.0'
        for data in output_data:
            filter_df = data['filter_df']
            for index, row in filter_df.iterrows():
                k = f'{row["name"]} - {row["metric"]}'
                request_counts = []
                stats_list = []
                for serie in row['series']:
                    request_counts.append(serie['requestCount'])
                    stats_list.append(self.access_nested_dict(serie, key_string))
                self.plot(k, request_counts, stats_list)

%env JENKINS_USERNAME=......
%env JENKINS_TOKEN=......
%env JENKINS_EXAMPLE_URL=......

if __name__ == '__main__':
    DownloadJenkinsHyperfoilData(all_json_urls=[os.environ['JENKINS_EXAMPLE_URL']]).run('steadyState', 'getPolicyHolder')

env: JENKINS_USERNAME=......
env: JENKINS_TOKEN=......
env: JENKINS_EXAMPLE_URL=......